Merge branch 'tracing/core' into tracing/hw-breakpoints

Conflicts:
	arch/Kconfig
	kernel/trace/trace.h

Merge reason: resolve the conflicts, plus adopt to the new
              ring-buffer APIs.

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

94 files changed, 6975 insertions, 3141 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index f88decb1b44..52508612a08 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -69,8 +69,9 @@ obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
-obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
+obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
+obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += kgdb.o
@@ -95,6 +96,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
+obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
diff --git a/kernel/acct.c b/kernel/acct.c
index 7afa3156416..9f3391090b3 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -215,6 +215,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
 static int acct_on(char *name)
 {
 	struct file *file;
+	struct vfsmount *mnt;
 	int error;
 	struct pid_namespace *ns;
 	struct bsd_acct_struct *acct = NULL;
@@ -256,11 +257,12 @@ static int acct_on(char *name)
 		acct = NULL;
 	}
 
-	mnt_pin(file->f_path.mnt);
+	mnt = file->f_path.mnt;
+	mnt_pin(mnt);
 	acct_file_reopen(ns->bacct, file, ns);
 	spin_unlock(&acct_lock);
 
-	mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
+	mntput(mnt); /* it's pinned, now give up active reference */
 	kfree(acct);
 
 	return 0;
diff --git a/kernel/audit.c b/kernel/audit.c
index 9442c3533ba..defc2e6f1e3 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -115,9 +115,6 @@ static atomic_t    audit_lost = ATOMIC_INIT(0);
 /* The netlink socket. */
 static struct sock *audit_sock;
 
-/* Inotify handle. */
-struct inotify_handle *audit_ih;
-
 /* Hash for inode-based rules */
 struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
 
@@ -136,7 +133,7 @@ static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
 static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
 
 /* Serialize requests from userspace. */
-static DEFINE_MUTEX(audit_cmd_mutex);
+DEFINE_MUTEX(audit_cmd_mutex);
 
 /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
  * audit records.  Since printk uses a 1024 byte buffer, this buffer
@@ -375,6 +372,25 @@ static void audit_hold_skb(struct sk_buff *skb)
 		kfree_skb(skb);
 }
 
+/*
+ * For one reason or another this nlh isn't getting delivered to the userspace
+ * audit daemon, just send it to printk.
+ */
+static void audit_printk_skb(struct sk_buff *skb)
+{
+	struct nlmsghdr *nlh = nlmsg_hdr(skb);
+	char *data = NLMSG_DATA(nlh);
+
+	if (nlh->nlmsg_type != AUDIT_EOE) {
+		if (printk_ratelimit())
+			printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, data);
+		else
+			audit_log_lost("printk limit exceeded\n");
+	}
+
+	audit_hold_skb(skb);
+}
+
 static void kauditd_send_skb(struct sk_buff *skb)
 {
 	int err;
@@ -427,14 +443,8 @@ static int kauditd_thread(void *dummy)
 		if (skb) {
 			if (audit_pid)
 				kauditd_send_skb(skb);
-			else {
-				if (printk_ratelimit())
-					printk(KERN_NOTICE "%s\n", skb->data + NLMSG_SPACE(0));
-				else
-					audit_log_lost("printk limit exceeded\n");
-
-				audit_hold_skb(skb);
-			}
+			else
+				audit_printk_skb(skb);
 		} else {
 			DECLARE_WAITQUEUE(wait, current);
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -495,42 +505,25 @@ int audit_send_list(void *_dest)
 	return 0;
 }
 
-#ifdef CONFIG_AUDIT_TREE
-static int prune_tree_thread(void *unused)
-{
-	mutex_lock(&audit_cmd_mutex);
-	audit_prune_trees();
-	mutex_unlock(&audit_cmd_mutex);
-	return 0;
-}
-
-void audit_schedule_prune(void)
-{
-	kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
-}
-#endif
-
 struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
 				 int multi, void *payload, int size)
 {
 	struct sk_buff	*skb;
 	struct nlmsghdr	*nlh;
-	int		len = NLMSG_SPACE(size);
 	void		*data;
 	int		flags = multi ? NLM_F_MULTI : 0;
 	int		t     = done  ? NLMSG_DONE  : type;
 
-	skb = alloc_skb(len, GFP_KERNEL);
+	skb = nlmsg_new(size, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
-	nlh		 = NLMSG_PUT(skb, pid, seq, t, size);
-	nlh->nlmsg_flags = flags;
-	data		 = NLMSG_DATA(nlh);
+	nlh	= NLMSG_NEW(skb, pid, seq, t, size, flags);
+	data	= NLMSG_DATA(nlh);
 	memcpy(data, payload, size);
 	return skb;
 
-nlmsg_failure:			/* Used by NLMSG_PUT */
+nlmsg_failure:			/* Used by NLMSG_NEW */
 	if (skb)
 		kfree_skb(skb);
 	return NULL;
@@ -926,28 +919,29 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 }
 
 /*
- * Get message from skb (based on rtnetlink_rcv_skb).  Each message is
- * processed by audit_receive_msg.  Malformed skbs with wrong length are
- * discarded silently.
+ * Get message from skb.  Each message is processed by audit_receive_msg.
+ * Malformed skbs with wrong length are discarded silently.
  */
 static void audit_receive_skb(struct sk_buff *skb)
 {
-	int		err;
-	struct nlmsghdr	*nlh;
-	u32		rlen;
+	struct nlmsghdr *nlh;
+	/*
+	 * len MUST be signed for NLMSG_NEXT to be able to dec it below 0
+	 * if the nlmsg_len was not aligned
+	 */
+	int len;
+	int err;
 
-	while (skb->len >= NLMSG_SPACE(0)) {
-		nlh = nlmsg_hdr(skb);
-		if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
-			return;
-		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
-		if (rlen > skb->len)
-			rlen = skb->len;
-		if ((err = audit_receive_msg(skb, nlh))) {
+	nlh = nlmsg_hdr(skb);
+	len = skb->len;
+
+	while (NLMSG_OK(nlh, len)) {
+		err = audit_receive_msg(skb, nlh);
+		/* if err or if this message says it wants a response */
+		if (err || (nlh->nlmsg_flags & NLM_F_ACK))
 			netlink_ack(skb, nlh, err);
-		} else if (nlh->nlmsg_flags & NLM_F_ACK)
-			netlink_ack(skb, nlh, 0);
-		skb_pull(skb, rlen);
+
+		nlh = NLMSG_NEXT(nlh, len);
 	}
 }
 
@@ -959,13 +953,6 @@ static void audit_receive(struct sk_buff  *skb)
 	mutex_unlock(&audit_cmd_mutex);
 }
 
-#ifdef CONFIG_AUDITSYSCALL
-static const struct inotify_operations audit_inotify_ops = {
-	.handle_event	= audit_handle_ievent,
-	.destroy_watch	= audit_free_parent,
-};
-#endif
-
 /* Initialize audit support at boot time. */
 static int __init audit_init(void)
 {
@@ -991,12 +978,6 @@ static int __init audit_init(void)
 
 	audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
 
-#ifdef CONFIG_AUDITSYSCALL
-	audit_ih = inotify_init(&audit_inotify_ops);
-	if (IS_ERR(audit_ih))
-		audit_panic("cannot initialize inotify handle");
-#endif
-
 	for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
 		INIT_LIST_HEAD(&audit_inode_hash[i]);
 
@@ -1070,18 +1051,20 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
 			goto err;
 	}
 
-	ab->skb = alloc_skb(AUDIT_BUFSIZ, gfp_mask);
-	if (!ab->skb)
-		goto err;
-
 	ab->ctx = ctx;
 	ab->gfp_mask = gfp_mask;
-	nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0));
-	nlh->nlmsg_type = type;
-	nlh->nlmsg_flags = 0;
-	nlh->nlmsg_pid = 0;
-	nlh->nlmsg_seq = 0;
+
+	ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask);
+	if (!ab->skb)
+		goto nlmsg_failure;
+
+	nlh = NLMSG_NEW(ab->skb, 0, 0, type, 0, 0);
+
 	return ab;
+
+nlmsg_failure:                  /* Used by NLMSG_NEW */
+	kfree_skb(ab->skb);
+	ab->skb = NULL;
 err:
 	audit_buffer_free(ab);
 	return NULL;
@@ -1452,6 +1435,15 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
 	kfree(pathname);
 }
 
+void audit_log_key(struct audit_buffer *ab, char *key)
+{
+	audit_log_format(ab, " key=");
+	if (key)
+		audit_log_untrustedstring(ab, key);
+	else
+		audit_log_format(ab, "(null)");
+}
+
 /**
  * audit_log_end - end one audit record
  * @ab: the audit_buffer
@@ -1475,15 +1467,7 @@ void audit_log_end(struct audit_buffer *ab)
 			skb_queue_tail(&audit_skb_queue, ab->skb);
 			wake_up_interruptible(&kauditd_wait);
 		} else {
-			if (nlh->nlmsg_type != AUDIT_EOE) {
-				if (printk_ratelimit()) {
-					printk(KERN_NOTICE "type=%d %s\n",
-						nlh->nlmsg_type,
-						ab->skb->data + NLMSG_SPACE(0));
-				} else
-					audit_log_lost("printk limit exceeded\n");
-			}
-			audit_hold_skb(ab->skb);
+			audit_printk_skb(ab->skb);
 		}
 		ab->skb = NULL;
 	}
diff --git a/kernel/audit.h b/kernel/audit.h
index 16f18cac661..208687be4f3 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -53,18 +53,7 @@ enum audit_state {
 };
 
 /* Rule lists */
-struct audit_parent;
-
-struct audit_watch {
-	atomic_t		count;	/* reference count */
-	char			*path;	/* insertion path */
-	dev_t			dev;	/* associated superblock device */
-	unsigned long		ino;	/* associated inode number */
-	struct audit_parent	*parent; /* associated parent */
-	struct list_head	wlist;	/* entry in parent->watches list */
-	struct list_head	rules;	/* associated rules */
-};
-
+struct audit_watch;
 struct audit_tree;
 struct audit_chunk;
 
@@ -108,19 +97,28 @@ struct audit_netlink_list {
 
 int audit_send_list(void *);
 
-struct inotify_watch;
-/* Inotify handle */
-extern struct inotify_handle *audit_ih;
-
-extern void audit_free_parent(struct inotify_watch *);
-extern void audit_handle_ievent(struct inotify_watch *, u32, u32, u32,
-				const char *, struct inode *);
 extern int selinux_audit_rule_update(void);
 
 extern struct mutex audit_filter_mutex;
 extern void audit_free_rule_rcu(struct rcu_head *);
 extern struct list_head audit_filter_list[];
 
+/* audit watch functions */
+extern unsigned long audit_watch_inode(struct audit_watch *watch);
+extern dev_t audit_watch_dev(struct audit_watch *watch);
+extern void audit_put_watch(struct audit_watch *watch);
+extern void audit_get_watch(struct audit_watch *watch);
+extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op);
+extern int audit_add_watch(struct audit_krule *krule);
+extern void audit_remove_watch(struct audit_watch *watch);
+extern void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list);
+extern void audit_inotify_unregister(struct list_head *in_list);
+extern char *audit_watch_path(struct audit_watch *watch);
+extern struct list_head *audit_watch_rules(struct audit_watch *watch);
+
+extern struct audit_entry *audit_dupe_rule(struct audit_krule *old,
+					   struct audit_watch *watch);
+
 #ifdef CONFIG_AUDIT_TREE
 extern struct audit_chunk *audit_tree_lookup(const struct inode *);
 extern void audit_put_chunk(struct audit_chunk *);
@@ -130,10 +128,9 @@ extern int audit_add_tree_rule(struct audit_krule *);
 extern int audit_remove_tree_rule(struct audit_krule *);
 extern void audit_trim_trees(void);
 extern int audit_tag_tree(char *old, char *new);
-extern void audit_schedule_prune(void);
-extern void audit_prune_trees(void);
 extern const char *audit_tree_path(struct audit_tree *);
 extern void audit_put_tree(struct audit_tree *);
+extern void audit_kill_trees(struct list_head *);
 #else
 #define audit_remove_tree_rule(rule) BUG()
 #define audit_add_tree_rule(rule) -EINVAL
@@ -142,6 +139,7 @@ extern void audit_put_tree(struct audit_tree *);
 #define audit_put_tree(tree) (void)0
 #define audit_tag_tree(old, new) -EINVAL
 #define audit_tree_path(rule) ""	/* never called */
+#define audit_kill_trees(list) BUG()
 #endif
 
 extern char *audit_unpack_string(void **, size_t *, size_t);
@@ -160,7 +158,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t)
 	return 0;
 }
 extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
+extern struct list_head *audit_killed_trees(void);
 #else
 #define audit_signal_info(s,t) AUDIT_DISABLED
 #define audit_filter_inodes(t,c) AUDIT_DISABLED
 #endif
+
+extern struct mutex audit_cmd_mutex;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 1f6396d7668..2451dc6f328 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -2,6 +2,7 @@
 #include <linux/inotify.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
+#include <linux/kthread.h>
 
 struct audit_tree;
 struct audit_chunk;
@@ -441,13 +442,11 @@ static void kill_rules(struct audit_tree *tree)
 		if (rule->tree) {
 			/* not a half-baked one */
 			ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
-			audit_log_format(ab, "op=remove rule dir=");
+			audit_log_format(ab, "op=");
+			audit_log_string(ab, "remove rule");
+			audit_log_format(ab, " dir=");
 			audit_log_untrustedstring(ab, rule->tree->pathname);
-			if (rule->filterkey) {
-				audit_log_format(ab, " key=");
-				audit_log_untrustedstring(ab, rule->filterkey);
-			} else
-				audit_log_format(ab, " key=(null)");
+			audit_log_key(ab, rule->filterkey);
 			audit_log_format(ab, " list=%d res=1", rule->listnr);
 			audit_log_end(ab);
 			rule->tree = NULL;
@@ -519,6 +518,8 @@ static void trim_marked(struct audit_tree *tree)
 	}
 }
 
+static void audit_schedule_prune(void);
+
 /* called with audit_filter_mutex */
 int audit_remove_tree_rule(struct audit_krule *rule)
 {
@@ -824,10 +825,11 @@ int audit_tag_tree(char *old, char *new)
 
 /*
  * That gets run when evict_chunk() ends up needing to kill audit_tree.
- * Runs from a separate thread, with audit_cmd_mutex held.
+ * Runs from a separate thread.
  */
-void audit_prune_trees(void)
+static int prune_tree_thread(void *unused)
 {
+	mutex_lock(&audit_cmd_mutex);
 	mutex_lock(&audit_filter_mutex);
 
 	while (!list_empty(&prune_list)) {
@@ -844,6 +846,40 @@ void audit_prune_trees(void)
 	}
 
 	mutex_unlock(&audit_filter_mutex);
+	mutex_unlock(&audit_cmd_mutex);
+	return 0;
+}
+
+static void audit_schedule_prune(void)
+{
+	kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
+}
+
+/*
+ * ... and that one is done if evict_chunk() decides to delay until the end
+ * of syscall.  Runs synchronously.
+ */
+void audit_kill_trees(struct list_head *list)
+{
+	mutex_lock(&audit_cmd_mutex);
+	mutex_lock(&audit_filter_mutex);
+
+	while (!list_empty(list)) {
+		struct audit_tree *victim;
+
+		victim = list_entry(list->next, struct audit_tree, list);
+		kill_rules(victim);
+		list_del_init(&victim->list);
+
+		mutex_unlock(&audit_filter_mutex);
+
+		prune_one(victim);
+
+		mutex_lock(&audit_filter_mutex);
+	}
+
+	mutex_unlock(&audit_filter_mutex);
+	mutex_unlock(&audit_cmd_mutex);
 }
 
 /*
@@ -854,6 +890,8 @@ void audit_prune_trees(void)
 static void evict_chunk(struct audit_chunk *chunk)
 {
 	struct audit_tree *owner;
+	struct list_head *postponed = audit_killed_trees();
+	int need_prune = 0;
 	int n;
 
 	if (chunk->dead)
@@ -869,15 +907,21 @@ static void evict_chunk(struct audit_chunk *chunk)
 		owner->root = NULL;
 		list_del_init(&owner->same_root);
 		spin_unlock(&hash_lock);
-		kill_rules(owner);
-		list_move(&owner->list, &prune_list);
-		audit_schedule_prune();
+		if (!postponed) {
+			kill_rules(owner);
+			list_move(&owner->list, &prune_list);
+			need_prune = 1;
+		} else {
+			list_move(&owner->list, postponed);
+		}
 		spin_lock(&hash_lock);
 	}
 	list_del_rcu(&chunk->hash);
 	for (n = 0; n < chunk->count; n++)
 		list_del_init(&chunk->owners[n].list);
 	spin_unlock(&hash_lock);
+	if (need_prune)
+		audit_schedule_prune();
 	mutex_unlock(&audit_filter_mutex);
 }
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
new file mode 100644
index 00000000000..0e96dbc60ea
--- /dev/null
+++ b/kernel/audit_watch.c
@@ -0,0 +1,543 @@
+/* audit_watch.c -- watching inodes
+ *
+ * Copyright 2003-2009 Red Hat, Inc.
+ * Copyright 2005 Hewlett-Packard Development Company, L.P.
+ * Copyright 2005 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/audit.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/netlink.h>
+#include <linux/sched.h>
+#include <linux/inotify.h>
+#include <linux/security.h>
+#include "audit.h"
+
+/*
+ * Reference counting:
+ *
+ * audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED
+ * 	event.  Each audit_watch holds a reference to its associated parent.
+ *
+ * audit_watch: if added to lists, lifetime is from audit_init_watch() to
+ * 	audit_remove_watch().  Additionally, an audit_watch may exist
+ * 	temporarily to assist in searching existing filter data.  Each
+ * 	audit_krule holds a reference to its associated watch.
+ */
+
+struct audit_watch {
+	atomic_t		count;	/* reference count */
+	char			*path;	/* insertion path */
+	dev_t			dev;	/* associated superblock device */
+	unsigned long		ino;	/* associated inode number */
+	struct audit_parent	*parent; /* associated parent */
+	struct list_head	wlist;	/* entry in parent->watches list */
+	struct list_head	rules;	/* associated rules */
+};
+
+struct audit_parent {
+	struct list_head	ilist;	/* entry in inotify registration list */
+	struct list_head	watches; /* associated watches */
+	struct inotify_watch	wdata;	/* inotify watch data */
+	unsigned		flags;	/* status flags */
+};
+
+/* Inotify handle. */
+struct inotify_handle *audit_ih;
+
+/*
+ * audit_parent status flags:
+ *
+ * AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to
+ * a filesystem event to ensure we're adding audit watches to a valid parent.
+ * Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot
+ * receive them while we have nameidata, but must be used for IN_MOVE_SELF which
+ * we can receive while holding nameidata.
+ */
+#define AUDIT_PARENT_INVALID	0x001
+
+/* Inotify events we care about. */
+#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF
+
+static void audit_free_parent(struct inotify_watch *i_watch)
+{
+	struct audit_parent *parent;
+
+	parent = container_of(i_watch, struct audit_parent, wdata);
+	WARN_ON(!list_empty(&parent->watches));
+	kfree(parent);
+}
+
+void audit_get_watch(struct audit_watch *watch)
+{
+	atomic_inc(&watch->count);
+}
+
+void audit_put_watch(struct audit_watch *watch)
+{
+	if (atomic_dec_and_test(&watch->count)) {
+		WARN_ON(watch->parent);
+		WARN_ON(!list_empty(&watch->rules));
+		kfree(watch->path);
+		kfree(watch);
+	}
+}
+
+void audit_remove_watch(struct audit_watch *watch)
+{
+	list_del(&watch->wlist);
+	put_inotify_watch(&watch->parent->wdata);
+	watch->parent = NULL;
+	audit_put_watch(watch); /* match initial get */
+}
+
+char *audit_watch_path(struct audit_watch *watch)
+{
+	return watch->path;
+}
+
+struct list_head *audit_watch_rules(struct audit_watch *watch)
+{
+	return &watch->rules;
+}
+
+unsigned long audit_watch_inode(struct audit_watch *watch)
+{
+	return watch->ino;
+}
+
+dev_t audit_watch_dev(struct audit_watch *watch)
+{
+	return watch->dev;
+}
+
+/* Initialize a parent watch entry. */
+static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+{
+	struct audit_parent *parent;
+	s32 wd;
+
+	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	if (unlikely(!parent))
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&parent->watches);
+	parent->flags = 0;
+
+	inotify_init_watch(&parent->wdata);
+	/* grab a ref so inotify watch hangs around until we take audit_filter_mutex */
+	get_inotify_watch(&parent->wdata);
+	wd = inotify_add_watch(audit_ih, &parent->wdata,
+			       ndp->path.dentry->d_inode, AUDIT_IN_WATCH);
+	if (wd < 0) {
+		audit_free_parent(&parent->wdata);
+		return ERR_PTR(wd);
+	}
+
+	return parent;
+}
+
+/* Initialize a watch entry. */
+static struct audit_watch *audit_init_watch(char *path)
+{
+	struct audit_watch *watch;
+
+	watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+	if (unlikely(!watch))
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&watch->rules);
+	atomic_set(&watch->count, 1);
+	watch->path = path;
+	watch->dev = (dev_t)-1;
+	watch->ino = (unsigned long)-1;
+
+	return watch;
+}
+
+/* Translate a watch string to kernel respresentation. */
+int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op)
+{
+	struct audit_watch *watch;
+
+	if (!audit_ih)
+		return -EOPNOTSUPP;
+
+	if (path[0] != '/' || path[len-1] == '/' ||
+	    krule->listnr != AUDIT_FILTER_EXIT ||
+	    op != Audit_equal ||
+	    krule->inode_f || krule->watch || krule->tree)
+		return -EINVAL;
+
+	watch = audit_init_watch(path);
+	if (IS_ERR(watch))
+		return PTR_ERR(watch);
+
+	audit_get_watch(watch);
+	krule->watch = watch;
+
+	return 0;
+}
+
+/* Duplicate the given audit watch.  The new watch's rules list is initialized
+ * to an empty list and wlist is undefined. */
+static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
+{
+	char *path;
+	struct audit_watch *new;
+
+	path = kstrdup(old->path, GFP_KERNEL);
+	if (unlikely(!path))
+		return ERR_PTR(-ENOMEM);
+
+	new = audit_init_watch(path);
+	if (IS_ERR(new)) {
+		kfree(path);
+		goto out;
+	}
+
+	new->dev = old->dev;
+	new->ino = old->ino;
+	get_inotify_watch(&old->parent->wdata);
+	new->parent = old->parent;
+
+out:
+	return new;
+}
+
+static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op)
+{
+	if (audit_enabled) {
+		struct audit_buffer *ab;
+		ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+		audit_log_format(ab, "auid=%u ses=%u op=",
+				 audit_get_loginuid(current),
+				 audit_get_sessionid(current));
+		audit_log_string(ab, op);
+		audit_log_format(ab, " path=");
+		audit_log_untrustedstring(ab, w->path);
+		audit_log_key(ab, r->filterkey);
+		audit_log_format(ab, " list=%d res=1", r->listnr);
+		audit_log_end(ab);
+	}
+}
+
+/* Update inode info in audit rules based on filesystem event. */
+static void audit_update_watch(struct audit_parent *parent,
+			       const char *dname, dev_t dev,
+			       unsigned long ino, unsigned invalidating)
+{
+	struct audit_watch *owatch, *nwatch, *nextw;
+	struct audit_krule *r, *nextr;
+	struct audit_entry *oentry, *nentry;
+
+	mutex_lock(&audit_filter_mutex);
+	list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
+		if (audit_compare_dname_path(dname, owatch->path, NULL))
+			continue;
+
+		/* If the update involves invalidating rules, do the inode-based
+		 * filtering now, so we don't omit records. */
+		if (invalidating && current->audit_context)
+			audit_filter_inodes(current, current->audit_context);
+
+		nwatch = audit_dupe_watch(owatch);
+		if (IS_ERR(nwatch)) {
+			mutex_unlock(&audit_filter_mutex);
+			audit_panic("error updating watch, skipping");
+			return;
+		}
+		nwatch->dev = dev;
+		nwatch->ino = ino;
+
+		list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) {
+
+			oentry = container_of(r, struct audit_entry, rule);
+			list_del(&oentry->rule.rlist);
+			list_del_rcu(&oentry->list);
+
+			nentry = audit_dupe_rule(&oentry->rule, nwatch);
+			if (IS_ERR(nentry)) {
+				list_del(&oentry->rule.list);
+				audit_panic("error updating watch, removing");
+			} else {
+				int h = audit_hash_ino((u32)ino);
+				list_add(&nentry->rule.rlist, &nwatch->rules);
+				list_add_rcu(&nentry->list, &audit_inode_hash[h]);
+				list_replace(&oentry->rule.list,
+					     &nentry->rule.list);
+			}
+
+			audit_watch_log_rule_change(r, owatch, "updated rules");
+
+			call_rcu(&oentry->rcu, audit_free_rule_rcu);
+		}
+
+		audit_remove_watch(owatch);
+		goto add_watch_to_parent; /* event applies to a single watch */
+	}
+	mutex_unlock(&audit_filter_mutex);
+	return;
+
+add_watch_to_parent:
+	list_add(&nwatch->wlist, &parent->watches);
+	mutex_unlock(&audit_filter_mutex);
+	return;
+}
+
+/* Remove all watches & rules associated with a parent that is going away. */
+static void audit_remove_parent_watches(struct audit_parent *parent)
+{
+	struct audit_watch *w, *nextw;
+	struct audit_krule *r, *nextr;
+	struct audit_entry *e;
+
+	mutex_lock(&audit_filter_mutex);
+	parent->flags |= AUDIT_PARENT_INVALID;
+	list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
+		list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
+			e = container_of(r, struct audit_entry, rule);
+			audit_watch_log_rule_change(r, w, "remove rule");
+			list_del(&r->rlist);
+			list_del(&r->list);
+			list_del_rcu(&e->list);
+			call_rcu(&e->rcu, audit_free_rule_rcu);
+		}
+		audit_remove_watch(w);
+	}
+	mutex_unlock(&audit_filter_mutex);
+}
+
+/* Unregister inotify watches for parents on in_list.
+ * Generates an IN_IGNORED event. */
+void audit_inotify_unregister(struct list_head *in_list)
+{
+	struct audit_parent *p, *n;
+
+	list_for_each_entry_safe(p, n, in_list, ilist) {
+		list_del(&p->ilist);
+		inotify_rm_watch(audit_ih, &p->wdata);
+		/* the unpin matching the pin in audit_do_del_rule() */
+		unpin_inotify_watch(&p->wdata);
+	}
+}
+
+/* Get path information necessary for adding watches. */
+static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+{
+	struct nameidata *ndparent, *ndwatch;
+	int err;
+
+	ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
+	if (unlikely(!ndparent))
+		return -ENOMEM;
+
+	ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
+	if (unlikely(!ndwatch)) {
+		kfree(ndparent);
+		return -ENOMEM;
+	}
+
+	err = path_lookup(path, LOOKUP_PARENT, ndparent);
+	if (err) {
+		kfree(ndparent);
+		kfree(ndwatch);
+		return err;
+	}
+
+	err = path_lookup(path, 0, ndwatch);
+	if (err) {
+		kfree(ndwatch);
+		ndwatch = NULL;
+	}
+
+	*ndp = ndparent;
+	*ndw = ndwatch;
+
+	return 0;
+}
+
+/* Release resources used for watch path information. */
+static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
+{
+	if (ndp) {
+		path_put(&ndp->path);
+		kfree(ndp);
+	}
+	if (ndw) {
+		path_put(&ndw->path);
+		kfree(ndw);
+	}
+}
+
+/* Associate the given rule with an existing parent inotify_watch.
+ * Caller must hold audit_filter_mutex. */
+static void audit_add_to_parent(struct audit_krule *krule,
+				struct audit_parent *parent)
+{
+	struct audit_watch *w, *watch = krule->watch;
+	int watch_found = 0;
+
+	list_for_each_entry(w, &parent->watches, wlist) {
+		if (strcmp(watch->path, w->path))
+			continue;
+
+		watch_found = 1;
+
+		/* put krule's and initial refs to temporary watch */
+		audit_put_watch(watch);
+		audit_put_watch(watch);
+
+		audit_get_watch(w);
+		krule->watch = watch = w;
+		break;
+	}
+
+	if (!watch_found) {
+		get_inotify_watch(&parent->wdata);
+		watch->parent = parent;
+
+		list_add(&watch->wlist, &parent->watches);
+	}
+	list_add(&krule->rlist, &watch->rules);
+}
+
+/* Find a matching watch entry, or add this one.
+ * Caller must hold audit_filter_mutex. */
+int audit_add_watch(struct audit_krule *krule)
+{
+	struct audit_watch *watch = krule->watch;
+	struct inotify_watch *i_watch;
+	struct audit_parent *parent;
+	struct nameidata *ndp = NULL, *ndw = NULL;
+	int ret = 0;
+
+	mutex_unlock(&audit_filter_mutex);
+
+	/* Avoid calling path_lookup under audit_filter_mutex. */
+	ret = audit_get_nd(watch->path, &ndp, &ndw);
+	if (ret) {
+		/* caller expects mutex locked */
+		mutex_lock(&audit_filter_mutex);
+		goto error;
+	}
+
+	/* update watch filter fields */
+	if (ndw) {
+		watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
+		watch->ino = ndw->path.dentry->d_inode->i_ino;
+	}
+
+	/* The audit_filter_mutex must not be held during inotify calls because
+	 * we hold it during inotify event callback processing.  If an existing
+	 * inotify watch is found, inotify_find_watch() grabs a reference before
+	 * returning.
+	 */
+	if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode,
+			       &i_watch) < 0) {
+		parent = audit_init_parent(ndp);
+		if (IS_ERR(parent)) {
+			/* caller expects mutex locked */
+			mutex_lock(&audit_filter_mutex);
+			ret = PTR_ERR(parent);
+			goto error;
+		}
+	} else
+		parent = container_of(i_watch, struct audit_parent, wdata);
+
+	mutex_lock(&audit_filter_mutex);
+
+	/* parent was moved before we took audit_filter_mutex */
+	if (parent->flags & AUDIT_PARENT_INVALID)
+		ret = -ENOENT;
+	else
+		audit_add_to_parent(krule, parent);
+
+	/* match get in audit_init_parent or inotify_find_watch */
+	put_inotify_watch(&parent->wdata);
+
+error:
+	audit_put_nd(ndp, ndw);		/* NULL args OK */
+	return ret;
+
+}
+
+void audit_remove_watch_rule(struct audit_krule *krule, struct list_head *list)
+{
+	struct audit_watch *watch = krule->watch;
+	struct audit_parent *parent = watch->parent;
+
+	list_del(&krule->rlist);
+
+	if (list_empty(&watch->rules)) {
+		audit_remove_watch(watch);
+
+		if (list_empty(&parent->watches)) {
+			/* Put parent on the inotify un-registration
+			 * list.  Grab a reference before releasing
+			 * audit_filter_mutex, to be released in
+			 * audit_inotify_unregister().
+			 * If filesystem is going away, just leave
+			 * the sucker alone, eviction will take
+			 * care of it. */
+			if (pin_inotify_watch(&parent->wdata))
+				list_add(&parent->ilist, list);
+		}
+	}
+}
+
+/* Update watch data in audit rules based on inotify events. */
+static void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask,
+			 u32 cookie, const char *dname, struct inode *inode)
+{
+	struct audit_parent *parent;
+
+	parent = container_of(i_watch, struct audit_parent, wdata);
+
+	if (mask & (IN_CREATE|IN_MOVED_TO) && inode)
+		audit_update_watch(parent, dname, inode->i_sb->s_dev,
+				   inode->i_ino, 0);
+	else if (mask & (IN_DELETE|IN_MOVED_FROM))
+		audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1);
+	/* inotify automatically removes the watch and sends IN_IGNORED */
+	else if (mask & (IN_DELETE_SELF|IN_UNMOUNT))
+		audit_remove_parent_watches(parent);
+	/* inotify does not remove the watch, so remove it manually */
+	else if(mask & IN_MOVE_SELF) {
+		audit_remove_parent_watches(parent);
+		inotify_remove_watch_locked(audit_ih, i_watch);
+	} else if (mask & IN_IGNORED)
+		put_inotify_watch(i_watch);
+}
+
+static const struct inotify_operations audit_inotify_ops = {
+	.handle_event   = audit_handle_ievent,
+	.destroy_watch  = audit_free_parent,
+};
+
+static int __init audit_watch_init(void)
+{
+	audit_ih = inotify_init(&audit_inotify_ops);
+	if (IS_ERR(audit_ih))
+		audit_panic("cannot initialize inotify handle");
+	return 0;
+}
+subsys_initcall(audit_watch_init);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 713098ee5a0..a70604047f3 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -27,7 +27,6 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
-#include <linux/inotify.h>
 #include <linux/security.h>
 #include "audit.h"
 
@@ -44,36 +43,6 @@
  * 		be written directly provided audit_filter_mutex is held.
  */
 
-/*
- * Reference counting:
- *
- * audit_parent: lifetime is from audit_init_parent() to receipt of an IN_IGNORED
- * 	event.  Each audit_watch holds a reference to its associated parent.
- *
- * audit_watch: if added to lists, lifetime is from audit_init_watch() to
- * 	audit_remove_watch().  Additionally, an audit_watch may exist
- * 	temporarily to assist in searching existing filter data.  Each
- * 	audit_krule holds a reference to its associated watch.
- */
-
-struct audit_parent {
-	struct list_head	ilist;	/* entry in inotify registration list */
-	struct list_head	watches; /* associated watches */
-	struct inotify_watch	wdata;	/* inotify watch data */
-	unsigned		flags;	/* status flags */
-};
-
-/*
- * audit_parent status flags:
- *
- * AUDIT_PARENT_INVALID - set anytime rules/watches are auto-removed due to
- * a filesystem event to ensure we're adding audit watches to a valid parent.
- * Technically not needed for IN_DELETE_SELF or IN_UNMOUNT events, as we cannot
- * receive them while we have nameidata, but must be used for IN_MOVE_SELF which
- * we can receive while holding nameidata.
- */
-#define AUDIT_PARENT_INVALID	0x001
-
 /* Audit filter lists, defined in <linux/audit.h> */
 struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
 	LIST_HEAD_INIT(audit_filter_list[0]),
@@ -97,41 +66,6 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
 
 DEFINE_MUTEX(audit_filter_mutex);
 
-/* Inotify events we care about. */
-#define AUDIT_IN_WATCH IN_MOVE|IN_CREATE|IN_DELETE|IN_DELETE_SELF|IN_MOVE_SELF
-
-void audit_free_parent(struct inotify_watch *i_watch)
-{
-	struct audit_parent *parent;
-
-	parent = container_of(i_watch, struct audit_parent, wdata);
-	WARN_ON(!list_empty(&parent->watches));
-	kfree(parent);
-}
-
-static inline void audit_get_watch(struct audit_watch *watch)
-{
-	atomic_inc(&watch->count);
-}
-
-static void audit_put_watch(struct audit_watch *watch)
-{
-	if (atomic_dec_and_test(&watch->count)) {
-		WARN_ON(watch->parent);
-		WARN_ON(!list_empty(&watch->rules));
-		kfree(watch->path);
-		kfree(watch);
-	}
-}
-
-static void audit_remove_watch(struct audit_watch *watch)
-{
-	list_del(&watch->wlist);
-	put_inotify_watch(&watch->parent->wdata);
-	watch->parent = NULL;
-	audit_put_watch(watch); /* match initial get */
-}
-
 static inline void audit_free_rule(struct audit_entry *e)
 {
 	int i;
@@ -156,50 +90,6 @@ void audit_free_rule_rcu(struct rcu_head *head)
 	audit_free_rule(e);
 }
 
-/* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
-{
-	struct audit_parent *parent;
-	s32 wd;
-
-	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
-	if (unlikely(!parent))
-		return ERR_PTR(-ENOMEM);
-
-	INIT_LIST_HEAD(&parent->watches);
-	parent->flags = 0;
-
-	inotify_init_watch(&parent->wdata);
-	/* grab a ref so inotify watch hangs around until we take audit_filter_mutex */
-	get_inotify_watch(&parent->wdata);
-	wd = inotify_add_watch(audit_ih, &parent->wdata,
-			       ndp->path.dentry->d_inode, AUDIT_IN_WATCH);
-	if (wd < 0) {
-		audit_free_parent(&parent->wdata);
-		return ERR_PTR(wd);
-	}
-
-	return parent;
-}
-
-/* Initialize a watch entry. */
-static struct audit_watch *audit_init_watch(char *path)
-{
-	struct audit_watch *watch;
-
-	watch = kzalloc(sizeof(*watch), GFP_KERNEL);
-	if (unlikely(!watch))
-		return ERR_PTR(-ENOMEM);
-
-	INIT_LIST_HEAD(&watch->rules);
-	atomic_set(&watch->count, 1);
-	watch->path = path;
-	watch->dev = (dev_t)-1;
-	watch->ino = (unsigned long)-1;
-
-	return watch;
-}
-
 /* Initialize an audit filterlist entry. */
 static inline struct audit_entry *audit_init_entry(u32 field_count)
 {
@@ -260,31 +150,6 @@ static inline int audit_to_inode(struct audit_krule *krule,
 	return 0;
 }
 
-/* Translate a watch string to kernel respresentation. */
-static int audit_to_watch(struct audit_krule *krule, char *path, int len,
-			  u32 op)
-{
-	struct audit_watch *watch;
-
-	if (!audit_ih)
-		return -EOPNOTSUPP;
-
-	if (path[0] != '/' || path[len-1] == '/' ||
-	    krule->listnr != AUDIT_FILTER_EXIT ||
-	    op != Audit_equal ||
-	    krule->inode_f || krule->watch || krule->tree)
-		return -EINVAL;
-
-	watch = audit_init_watch(path);
-	if (IS_ERR(watch))
-		return PTR_ERR(watch);
-
-	audit_get_watch(watch);
-	krule->watch = watch;
-
-	return 0;
-}
-
 static __u32 *classes[AUDIT_SYSCALL_CLASSES];
 
 int __init audit_register_class(int class, unsigned *list)
@@ -766,7 +631,8 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 			break;
 		case AUDIT_WATCH:
 			data->buflen += data->values[i] =
-				audit_pack_string(&bufp, krule->watch->path);
+				audit_pack_string(&bufp,
+						  audit_watch_path(krule->watch));
 			break;
 		case AUDIT_DIR:
 			data->buflen += data->values[i] =
@@ -818,7 +684,8 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
 				return 1;
 			break;
 		case AUDIT_WATCH:
-			if (strcmp(a->watch->path, b->watch->path))
+			if (strcmp(audit_watch_path(a->watch),
+				   audit_watch_path(b->watch)))
 				return 1;
 			break;
 		case AUDIT_DIR:
@@ -844,32 +711,6 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
 	return 0;
 }
 
-/* Duplicate the given audit watch.  The new watch's rules list is initialized
- * to an empty list and wlist is undefined. */
-static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
-{
-	char *path;
-	struct audit_watch *new;
-
-	path = kstrdup(old->path, GFP_KERNEL);
-	if (unlikely(!path))
-		return ERR_PTR(-ENOMEM);
-
-	new = audit_init_watch(path);
-	if (IS_ERR(new)) {
-		kfree(path);
-		goto out;
-	}
-
-	new->dev = old->dev;
-	new->ino = old->ino;
-	get_inotify_watch(&old->parent->wdata);
-	new->parent = old->parent;
-
-out:
-	return new;
-}
-
 /* Duplicate LSM field information.  The lsm_rule is opaque, so must be
  * re-initialized. */
 static inline int audit_dupe_lsm_field(struct audit_field *df,
@@ -904,8 +745,8 @@ static inline int audit_dupe_lsm_field(struct audit_field *df,
  * rule with the new rule in the filterlist, then free the old rule.
  * The rlist element is undefined; list manipulations are handled apart from
  * the initial copy. */
-static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
-					   struct audit_watch *watch)
+struct audit_entry *audit_dupe_rule(struct audit_krule *old,
+				    struct audit_watch *watch)
 {
 	u32 fcount = old->field_count;
 	struct audit_entry *entry;
@@ -977,137 +818,6 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
 	return entry;
 }
 
-/* Update inode info in audit rules based on filesystem event. */
-static void audit_update_watch(struct audit_parent *parent,
-			       const char *dname, dev_t dev,
-			       unsigned long ino, unsigned invalidating)
-{
-	struct audit_watch *owatch, *nwatch, *nextw;
-	struct audit_krule *r, *nextr;
-	struct audit_entry *oentry, *nentry;
-
-	mutex_lock(&audit_filter_mutex);
-	list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
-		if (audit_compare_dname_path(dname, owatch->path, NULL))
-			continue;
-
-		/* If the update involves invalidating rules, do the inode-based
-		 * filtering now, so we don't omit records. */
-		if (invalidating && current->audit_context)
-			audit_filter_inodes(current, current->audit_context);
-
-		nwatch = audit_dupe_watch(owatch);
-		if (IS_ERR(nwatch)) {
-			mutex_unlock(&audit_filter_mutex);
-			audit_panic("error updating watch, skipping");
-			return;
-		}
-		nwatch->dev = dev;
-		nwatch->ino = ino;
-
-		list_for_each_entry_safe(r, nextr, &owatch->rules, rlist) {
-
-			oentry = container_of(r, struct audit_entry, rule);
-			list_del(&oentry->rule.rlist);
-			list_del_rcu(&oentry->list);
-
-			nentry = audit_dupe_rule(&oentry->rule, nwatch);
-			if (IS_ERR(nentry)) {
-				list_del(&oentry->rule.list);
-				audit_panic("error updating watch, removing");
-			} else {
-				int h = audit_hash_ino((u32)ino);
-				list_add(&nentry->rule.rlist, &nwatch->rules);
-				list_add_rcu(&nentry->list, &audit_inode_hash[h]);
-				list_replace(&oentry->rule.list,
-					     &nentry->rule.list);
-			}
-
-			call_rcu(&oentry->rcu, audit_free_rule_rcu);
-		}
-
-		if (audit_enabled) {
-			struct audit_buffer *ab;
-			ab = audit_log_start(NULL, GFP_NOFS,
-				AUDIT_CONFIG_CHANGE);
-			audit_log_format(ab, "auid=%u ses=%u",
-				audit_get_loginuid(current),
-				audit_get_sessionid(current));
-			audit_log_format(ab,
-				" op=updated rules specifying path=");
-			audit_log_untrustedstring(ab, owatch->path);
-			audit_log_format(ab, " with dev=%u ino=%lu\n",
-				 dev, ino);
-			audit_log_format(ab, " list=%d res=1", r->listnr);
-			audit_log_end(ab);
-		}
-		audit_remove_watch(owatch);
-		goto add_watch_to_parent; /* event applies to a single watch */
-	}
-	mutex_unlock(&audit_filter_mutex);
-	return;
-
-add_watch_to_parent:
-	list_add(&nwatch->wlist, &parent->watches);
-	mutex_unlock(&audit_filter_mutex);
-	return;
-}
-
-/* Remove all watches & rules associated with a parent that is going away. */
-static void audit_remove_parent_watches(struct audit_parent *parent)
-{
-	struct audit_watch *w, *nextw;
-	struct audit_krule *r, *nextr;
-	struct audit_entry *e;
-
-	mutex_lock(&audit_filter_mutex);
-	parent->flags |= AUDIT_PARENT_INVALID;
-	list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
-		list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
-			e = container_of(r, struct audit_entry, rule);
-			if (audit_enabled) {
-				struct audit_buffer *ab;
-				ab = audit_log_start(NULL, GFP_NOFS,
-					AUDIT_CONFIG_CHANGE);
-				audit_log_format(ab, "auid=%u ses=%u",
-					audit_get_loginuid(current),
-					audit_get_sessionid(current));
-				audit_log_format(ab, " op=remove rule path=");
-				audit_log_untrustedstring(ab, w->path);
-				if (r->filterkey) {
-					audit_log_format(ab, " key=");
-					audit_log_untrustedstring(ab,
-							r->filterkey);
-				} else
-					audit_log_format(ab, " key=(null)");
-				audit_log_format(ab, " list=%d res=1",
-					r->listnr);
-				audit_log_end(ab);
-			}
-			list_del(&r->rlist);
-			list_del(&r->list);
-			list_del_rcu(&e->list);
-			call_rcu(&e->rcu, audit_free_rule_rcu);
-		}
-		audit_remove_watch(w);
-	}
-	mutex_unlock(&audit_filter_mutex);
-}
-
-/* Unregister inotify watches for parents on in_list.
- * Generates an IN_IGNORED event. */
-static void audit_inotify_unregister(struct list_head *in_list)
-{
-	struct audit_parent *p, *n;
-
-	list_for_each_entry_safe(p, n, in_list, ilist) {
-		list_del(&p->ilist);
-		inotify_rm_watch(audit_ih, &p->wdata);
-		/* the unpin matching the pin in audit_do_del_rule() */
-		unpin_inotify_watch(&p->wdata);
-	}
-}
-
 /* Find an existing audit rule.
  * Caller must hold audit_filter_mutex to prevent stale rule data. */
 static struct audit_entry *audit_find_rule(struct audit_entry *entry,
@@ -1145,134 +855,6 @@ out:
 	return found;
 }
 
-/* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp,
-			struct nameidata **ndw)
-{
-	struct nameidata *ndparent, *ndwatch;
-	int err;
-
-	ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
-	if (unlikely(!ndparent))
-		return -ENOMEM;
-
-	ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
-	if (unlikely(!ndwatch)) {
-		kfree(ndparent);
-		return -ENOMEM;
-	}
-
-	err = path_lookup(path, LOOKUP_PARENT, ndparent);
-	if (err) {
-		kfree(ndparent);
-		kfree(ndwatch);
-		return err;
-	}
-
-	err = path_lookup(path, 0, ndwatch);
-	if (err) {
-		kfree(ndwatch);
-		ndwatch = NULL;
-	}
-
-	*ndp = ndparent;
-	*ndw = ndwatch;
-
-	return 0;
-}
-
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
-	if (ndp) {
-		path_put(&ndp->path);
-		kfree(ndp);
-	}
-	if (ndw) {
-		path_put(&ndw->path);
-		kfree(ndw);
-	}
-}
-
-/* Associate the given rule with an existing parent inotify_watch.
- * Caller must hold audit_filter_mutex. */
-static void audit_add_to_parent(struct audit_krule *krule,
-				struct audit_parent *parent)
-{
-	struct audit_watch *w, *watch = krule->watch;
-	int watch_found = 0;
-
-	list_for_each_entry(w, &parent->watches, wlist) {
-		if (strcmp(watch->path, w->path))
-			continue;
-
-		watch_found = 1;
-
-		/* put krule's and initial refs to temporary watch */
-		audit_put_watch(watch);
-		audit_put_watch(watch);
-
-		audit_get_watch(w);
-		krule->watch = watch = w;
-		break;
-	}
-
-	if (!watch_found) {
-		get_inotify_watch(&parent->wdata);
-		watch->parent = parent;
-
-		list_add(&watch->wlist, &parent->watches);
-	}
-	list_add(&krule->rlist, &watch->rules);
-}
-
-/* Find a matching watch entry, or add this one.
- * Caller must hold audit_filter_mutex. */
-static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp,
-			   struct nameidata *ndw)
-{
-	struct audit_watch *watch = krule->watch;
-	struct inotify_watch *i_watch;
-	struct audit_parent *parent;
-	int ret = 0;
-
-	/* update watch filter fields */
-	if (ndw) {
-		watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
-		watch->ino = ndw->path.dentry->d_inode->i_ino;
-	}
-
-	/* The audit_filter_mutex must not be held during inotify calls because
-	 * we hold it during inotify event callback processing.  If an existing
-	 * inotify watch is found, inotify_find_watch() grabs a reference before
-	 * returning.
-	 */
-	mutex_unlock(&audit_filter_mutex);
-
-	if (inotify_find_watch(audit_ih, ndp->path.dentry->d_inode,
-			       &i_watch) < 0) {
-		parent = audit_init_parent(ndp);
-		if (IS_ERR(parent)) {
-			/* caller expects mutex locked */
-			mutex_lock(&audit_filter_mutex);
-			return PTR_ERR(parent);
-		}
-	} else
-		parent = container_of(i_watch, struct audit_parent, wdata);
-
-	mutex_lock(&audit_filter_mutex);
-
-	/* parent was moved before we took audit_filter_mutex */
-	if (parent->flags & AUDIT_PARENT_INVALID)
-		ret = -ENOENT;
-	else
-		audit_add_to_parent(krule, parent);
-
-	/* match get in audit_init_parent or inotify_find_watch */
-	put_inotify_watch(&parent->wdata);
-	return ret;
-}
-
 static u64 prio_low = ~0ULL/2;
 static u64 prio_high = ~0ULL/2 - 1;
 
@@ -1282,7 +864,6 @@ static inline int audit_add_rule(struct audit_entry *entry)
 	struct audit_entry *e;
 	struct audit_watch *watch = entry->rule.watch;
 	struct audit_tree *tree = entry->rule.tree;
-	struct nameidata *ndp = NULL, *ndw = NULL;
 	struct list_head *list;
 	int h, err;
 #ifdef CONFIG_AUDITSYSCALL
@@ -1296,8 +877,8 @@ static inline int audit_add_rule(struct audit_entry *entry)
 
 	mutex_lock(&audit_filter_mutex);
 	e = audit_find_rule(entry, &list);
-	mutex_unlock(&audit_filter_mutex);
 	if (e) {
+		mutex_unlock(&audit_filter_mutex);
 		err = -EEXIST;
 		/* normally audit_add_tree_rule() will free it on failure */
 		if (tree)
@@ -1305,22 +886,16 @@ static inline int audit_add_rule(struct audit_entry *entry)
 		goto error;
 	}
 
-	/* Avoid calling path_lookup under audit_filter_mutex. */
-	if (watch) {
-		err = audit_get_nd(watch->path, &ndp, &ndw);
-		if (err)
-			goto error;
-	}
-
-	mutex_lock(&audit_filter_mutex);
 	if (watch) {
 		/* audit_filter_mutex is dropped and re-taken during this call */
-		err = audit_add_watch(&entry->rule, ndp, ndw);
+		err = audit_add_watch(&entry->rule);
 		if (err) {
 			mutex_unlock(&audit_filter_mutex);
 			goto error;
 		}
-		h = audit_hash_ino((u32)watch->ino);
+		/* entry->rule.watch may have changed during audit_add_watch() */
+		watch = entry->rule.watch;
+		h = audit_hash_ino((u32)audit_watch_inode(watch));
 		list = &audit_inode_hash[h];
 	}
 	if (tree) {
@@ -1358,11 +933,9 @@ static inline int audit_add_rule(struct audit_entry *entry)
 #endif
 	mutex_unlock(&audit_filter_mutex);
 
-	audit_put_nd(ndp, ndw);		/* NULL args OK */
  	return 0;
 
 error:
-	audit_put_nd(ndp, ndw);		/* NULL args OK */
 	if (watch)
 		audit_put_watch(watch); /* tmp watch, matches initial get */
 	return err;
@@ -1372,7 +945,7 @@ error:
 static inline int audit_del_rule(struct audit_entry *entry)
 {
 	struct audit_entry  *e;
-	struct audit_watch *watch, *tmp_watch = entry->rule.watch;
+	struct audit_watch *watch = entry->rule.watch;
 	struct audit_tree *tree = entry->rule.tree;
 	struct list_head *list;
 	LIST_HEAD(inotify_list);
@@ -1394,29 +967,8 @@ static inline int audit_del_rule(struct audit_entry *entry)
 		goto out;
 	}
 
-	watch = e->rule.watch;
-	if (watch) {
-		struct audit_parent *parent = watch->parent;
-
-		list_del(&e->rule.rlist);
-
-		if (list_empty(&watch->rules)) {
-			audit_remove_watch(watch);
-
-			if (list_empty(&parent->watches)) {
-				/* Put parent on the inotify un-registration
-				 * list.  Grab a reference before releasing
-				 * audit_filter_mutex, to be released in
-				 * audit_inotify_unregister().
-				 * If filesystem is going away, just leave
-				 * the sucker alone, eviction will take
-				 * care of it.
-				 */
-				if (pin_inotify_watch(&parent->wdata))
-					list_add(&parent->ilist, &inotify_list);
-			}
-		}
-	}
+	if (e->rule.watch)
+		audit_remove_watch_rule(&e->rule, &inotify_list);
 
 	if (e->rule.tree)
 		audit_remove_tree_rule(&e->rule);
@@ -1438,8 +990,8 @@ static inline int audit_del_rule(struct audit_entry *entry)
 		audit_inotify_unregister(&inotify_list);
 
 out:
-	if (tmp_watch)
-		audit_put_watch(tmp_watch); /* match initial get */
+	if (watch)
+		audit_put_watch(watch); /* match initial get */
 	if (tree)
 		audit_put_tree(tree);	/* that's the temporary one */
 
@@ -1527,11 +1079,9 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid,
 			security_release_secctx(ctx, len);
 		}
 	}
-	audit_log_format(ab, " op=%s rule key=", action);
-	if (rule->filterkey)
-		audit_log_untrustedstring(ab, rule->filterkey);
-	else
-		audit_log_format(ab, "(null)");
+	audit_log_format(ab, " op=");
+	audit_log_string(ab, action);
+	audit_log_key(ab, rule->filterkey);
 	audit_log_format(ab, " list=%d res=%d", rule->listnr, res);
 	audit_log_end(ab);
 }
@@ -1595,7 +1145,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 			return PTR_ERR(entry);
 
 		err = audit_add_rule(entry);
-		audit_log_rule_change(loginuid, sessionid, sid, "add",
+		audit_log_rule_change(loginuid, sessionid, sid, "add rule",
 				      &entry->rule, !err);
 
 		if (err)
@@ -1611,7 +1161,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 			return PTR_ERR(entry);
 
 		err = audit_del_rule(entry);
-		audit_log_rule_change(loginuid, sessionid, sid, "remove",
+		audit_log_rule_change(loginuid, sessionid, sid, "remove rule",
 				      &entry->rule, !err);
 
 		audit_free_rule(entry);
@@ -1793,7 +1343,7 @@ static int update_lsm_rule(struct audit_krule *r)
 		list_del(&r->list);
 	} else {
 		if (watch) {
-			list_add(&nentry->rule.rlist, &watch->rules);
+			list_add(&nentry->rule.rlist, audit_watch_rules(watch));
 			list_del(&r->rlist);
 		} else if (tree)
 			list_replace_init(&r->rlist, &nentry->rule.rlist);
@@ -1829,27 +1379,3 @@ int audit_update_lsm_rules(void)
 
 	return err;
 }
-
-/* Update watch data in audit rules based on inotify events. */
-void audit_handle_ievent(struct inotify_watch *i_watch, u32 wd, u32 mask,
-			 u32 cookie, const char *dname, struct inode *inode)
-{
-	struct audit_parent *parent;
-
-	parent = container_of(i_watch, struct audit_parent, wdata);
-
-	if (mask & (IN_CREATE|IN_MOVED_TO) && inode)
-		audit_update_watch(parent, dname, inode->i_sb->s_dev,
-				   inode->i_ino, 0);
-	else if (mask & (IN_DELETE|IN_MOVED_FROM))
-		audit_update_watch(parent, dname, (dev_t)-1, (unsigned long)-1, 1);
-	/* inotify automatically removes the watch and sends IN_IGNORED */
-	else if (mask & (IN_DELETE_SELF|IN_UNMOUNT))
-		audit_remove_parent_watches(parent);
-	/* inotify does not remove the watch, so remove it manually */
-	else if(mask & IN_MOVE_SELF) {
-		audit_remove_parent_watches(parent);
-		inotify_remove_watch_locked(audit_ih, i_watch);
-	} else if (mask & IN_IGNORED)
-		put_inotify_watch(i_watch);
-}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 7d6ac7c1f41..68d3c6a0ecd 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -199,6 +199,7 @@ struct audit_context {
 
 	struct audit_tree_refs *trees, *first_trees;
 	int tree_count;
+	struct list_head killed_trees;
 
 	int type;
 	union {
@@ -548,9 +549,9 @@ static int audit_filter_rules(struct task_struct *tsk,
 			}
 			break;
 		case AUDIT_WATCH:
-			if (name && rule->watch->ino != (unsigned long)-1)
-				result = (name->dev == rule->watch->dev &&
-					  name->ino == rule->watch->ino);
+			if (name && audit_watch_inode(rule->watch) != (unsigned long)-1)
+				result = (name->dev == audit_watch_dev(rule->watch) &&
+					  name->ino == audit_watch_inode(rule->watch));
 			break;
 		case AUDIT_DIR:
 			if (ctx)
@@ -853,6 +854,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state)
 	if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
 		return NULL;
 	audit_zero_context(context, state);
+	INIT_LIST_HEAD(&context->killed_trees);
 	return context;
 }
 
@@ -1024,8 +1026,8 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 {
 	char arg_num_len_buf[12];
 	const char __user *tmp_p = p;
-	/* how many digits are in arg_num? 3 is the length of " a=" */
-	size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 3;
+	/* how many digits are in arg_num? 5 is the length of ' a=""' */
+	size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
 	size_t len, len_left, to_send;
 	size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
 	unsigned int i, has_cntl = 0, too_long = 0;
@@ -1137,7 +1139,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 		if (has_cntl)
 			audit_log_n_hex(*ab, buf, to_send);
 		else
-			audit_log_format(*ab, "\"%s\"", buf);
+			audit_log_string(*ab, buf);
 
 		p += to_send;
 		len_left -= to_send;
@@ -1372,11 +1374,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 
 
 	audit_log_task_info(ab, tsk);
-	if (context->filterkey) {
-		audit_log_format(ab, " key=");
-		audit_log_untrustedstring(ab, context->filterkey);
-	} else
-		audit_log_format(ab, " key=(null)");
+	audit_log_key(ab, context->filterkey);
 	audit_log_end(ab);
 
 	for (aux = context->aux; aux; aux = aux->next) {
@@ -1549,6 +1547,8 @@ void audit_free(struct task_struct *tsk)
 	/* that can happen only if we are called from do_exit() */
 	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
 		audit_log_exit(context, tsk);
+	if (!list_empty(&context->killed_trees))
+		audit_kill_trees(&context->killed_trees);
 
 	audit_free_context(context);
 }
@@ -1692,6 +1692,9 @@ void audit_syscall_exit(int valid, long return_code)
 	context->in_syscall = 0;
 	context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 
+	if (!list_empty(&context->killed_trees))
+		audit_kill_trees(&context->killed_trees);
+
 	if (context->previous) {
 		struct audit_context *new_context = context->previous;
 		context->previous  = NULL;
@@ -2525,3 +2528,11 @@ void audit_core_dumps(long signr)
 	audit_log_format(ab, " sig=%ld", signr);
 	audit_log_end(ab);
 }
+
+struct list_head *audit_killed_trees(void)
+{
+	struct audit_context *ctx = current->audit_context;
+	if (likely(!ctx || !ctx->in_syscall))
+		return NULL;
+	return &ctx->killed_trees;
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3fb789f6df9..b6eadfe30e7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -47,6 +47,7 @@
 #include <linux/hash.h>
 #include <linux/namei.h>
 #include <linux/smp_lock.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/atomic.h>
 
@@ -734,16 +735,28 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
  * reference to css->refcnt. In general, this refcnt is expected to goes down
  * to zero, soon.
  *
- * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
+ * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
  */
 DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
 
-static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
+static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
 {
-	if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
 		wake_up_all(&cgroup_rmdir_waitq);
 }
 
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
+{
+	css_get(css);
+}
+
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
+{
+	cgroup_wakeup_rmdir_waiter(css->cgroup);
+	css_put(css);
+}
+
+
 static int rebind_subsystems(struct cgroupfs_root *root,
 			      unsigned long final_bits)
 {
@@ -843,6 +856,11 @@ static int parse_cgroupfs_options(char *data,
 				     struct cgroup_sb_opts *opts)
 {
 	char *token, *o = data ?: "all";
+	unsigned long mask = (unsigned long)-1;
+
+#ifdef CONFIG_CPUSETS
+	mask = ~(1UL << cpuset_subsys_id);
+#endif
 
 	opts->subsys_bits = 0;
 	opts->flags = 0;
@@ -887,6 +905,15 @@ static int parse_cgroupfs_options(char *data,
 		}
 	}
 
+	/*
+	 * 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_bits & mask))
+		return -EINVAL;
+
 	/* We can't have an empty hierarchy */
 	if (!opts->subsys_bits)
 		return -EINVAL;
@@ -946,6 +973,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->children);
 	INIT_LIST_HEAD(&cgrp->css_sets);
 	INIT_LIST_HEAD(&cgrp->release_list);
+	INIT_LIST_HEAD(&cgrp->pids_list);
 	init_rwsem(&cgrp->pids_mutex);
 }
 static void init_cgroup_root(struct cgroupfs_root *root)
@@ -1343,7 +1371,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
 	 * is no longer empty.
 	 */
-	cgroup_wakeup_rmdir_waiters(cgrp);
+	cgroup_wakeup_rmdir_waiter(cgrp);
 	return 0;
 }
 
@@ -2187,12 +2215,30 @@ err:
 	return ret;
 }
 
+/*
+ * Cache pids for all threads in the same pid namespace that are
+ * opening the same "tasks" file.
+ */
+struct cgroup_pids {
+	/* The node in cgrp->pids_list */
+	struct list_head list;
+	/* The cgroup those pids belong to */
+	struct cgroup *cgrp;
+	/* The namepsace those pids belong to */
+	struct pid_namespace *ns;
+	/* Array of process ids in the cgroup */
+	pid_t *tasks_pids;
+	/* How many files are using the this tasks_pids array */
+	int use_count;
+	/* Length of the current tasks_pids array */
+	int length;
+};
+
 static int cmppid(const void *a, const void *b)
 {
 	return *(pid_t *)a - *(pid_t *)b;
 }
 
-
 /*
  * seq_file methods for the "tasks" file. The seq_file position is the
  * next pid to display; the seq_file iterator is a pointer to the pid
@@ -2207,45 +2253,47 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
 	 * after a seek to the start). Use a binary-search to find the
 	 * next pid to display, if any
 	 */
-	struct cgroup *cgrp = s->private;
+	struct cgroup_pids *cp = s->private;
+	struct cgroup *cgrp = cp->cgrp;
 	int index = 0, pid = *pos;
 	int *iter;
 
 	down_read(&cgrp->pids_mutex);
 	if (pid) {
-		int end = cgrp->pids_length;
+		int end = cp->length;
 
 		while (index < end) {
 			int mid = (index + end) / 2;
-			if (cgrp->tasks_pids[mid] == pid) {
+			if (cp->tasks_pids[mid] == pid) {
 				index = mid;
 				break;
-			} else if (cgrp->tasks_pids[mid] <= pid)
+			} else if (cp->tasks_pids[mid] <= pid)
 				index = mid + 1;
 			else
 				end = mid;
 		}
 	}
 	/* If we're off the end of the array, we're done */
-	if (index >= cgrp->pids_length)
+	if (index >= cp->length)
 		return NULL;
 	/* Update the abstract position to be the actual pid that we found */
-	iter = cgrp->tasks_pids + index;
+	iter = cp->tasks_pids + index;
 	*pos = *iter;
 	return iter;
 }
 
 static void cgroup_tasks_stop(struct seq_file *s, void *v)
 {
-	struct cgroup *cgrp = s->private;
+	struct cgroup_pids *cp = s->private;
+	struct cgroup *cgrp = cp->cgrp;
 	up_read(&cgrp->pids_mutex);
 }
 
 static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct cgroup *cgrp = s->private;
+	struct cgroup_pids *cp = s->private;
 	int *p = v;
-	int *end = cgrp->tasks_pids + cgrp->pids_length;
+	int *end = cp->tasks_pids + cp->length;
 
 	/*
 	 * Advance to the next pid in the array. If this goes off the
@@ -2272,26 +2320,33 @@ static struct seq_operations cgroup_tasks_seq_operations = {
 	.show = cgroup_tasks_show,
 };
 
-static void release_cgroup_pid_array(struct cgroup *cgrp)
+static void release_cgroup_pid_array(struct cgroup_pids *cp)
 {
+	struct cgroup *cgrp = cp->cgrp;
+
 	down_write(&cgrp->pids_mutex);
-	BUG_ON(!cgrp->pids_use_count);
-	if (!--cgrp->pids_use_count) {
-		kfree(cgrp->tasks_pids);
-		cgrp->tasks_pids = NULL;
-		cgrp->pids_length = 0;
+	BUG_ON(!cp->use_count);
+	if (!--cp->use_count) {
+		list_del(&cp->list);
+		put_pid_ns(cp->ns);
+		kfree(cp->tasks_pids);
+		kfree(cp);
 	}
 	up_write(&cgrp->pids_mutex);
 }
 
 static int cgroup_tasks_release(struct inode *inode, struct file *file)
 {
-	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+	struct seq_file *seq;
+	struct cgroup_pids *cp;
 
 	if (!(file->f_mode & FMODE_READ))
 		return 0;
 
-	release_cgroup_pid_array(cgrp);
+	seq = file->private_data;
+	cp = seq->private;
+
+	release_cgroup_pid_array(cp);
 	return seq_release(inode, file);
 }
 
@@ -2310,6 +2365,8 @@ static struct file_operations cgroup_tasks_operations = {
 static int cgroup_tasks_open(struct inode *unused, struct file *file)
 {
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+	struct pid_namespace *ns = current->nsproxy->pid_ns;
+	struct cgroup_pids *cp;
 	pid_t *pidarray;
 	int npids;
 	int retval;
@@ -2336,20 +2393,37 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
 	 * array if necessary
 	 */
 	down_write(&cgrp->pids_mutex);
-	kfree(cgrp->tasks_pids);
-	cgrp->tasks_pids = pidarray;
-	cgrp->pids_length = npids;
-	cgrp->pids_use_count++;
+
+	list_for_each_entry(cp, &cgrp->pids_list, list) {
+		if (ns == cp->ns)
+			goto found;
+	}
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp) {
+		up_write(&cgrp->pids_mutex);
+		kfree(pidarray);
+		return -ENOMEM;
+	}
+	cp->cgrp = cgrp;
+	cp->ns = ns;
+	get_pid_ns(ns);
+	list_add(&cp->list, &cgrp->pids_list);
+found:
+	kfree(cp->tasks_pids);
+	cp->tasks_pids = pidarray;
+	cp->length = npids;
+	cp->use_count++;
 	up_write(&cgrp->pids_mutex);
 
 	file->f_op = &cgroup_tasks_operations;
 
 	retval = seq_open(file, &cgroup_tasks_seq_operations);
 	if (retval) {
-		release_cgroup_pid_array(cgrp);
+		release_cgroup_pid_array(cp);
 		return retval;
 	}
-	((struct seq_file *)file->private_data)->private = cgrp;
+	((struct seq_file *)file->private_data)->private = cp;
 	return 0;
 }
 
@@ -2682,33 +2756,42 @@ again:
 	mutex_unlock(&cgroup_mutex);
 
 	/*
+	 * In general, subsystem has no css->refcnt after pre_destroy(). But
+	 * in racy cases, subsystem may have to get css->refcnt after
+	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
+	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
+	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
+	 * and subsystem's reference count handling. Please see css_get/put
+	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
+	 */
+	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+
+	/*
 	 * Call pre_destroy handlers of subsys. Notify subsystems
 	 * that rmdir() request comes.
 	 */
 	ret = cgroup_call_pre_destroy(cgrp);
-	if (ret)
+	if (ret) {
+		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		return ret;
+	}
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
 	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
-	/*
-	 * css_put/get is provided for subsys to grab refcnt to css. In typical
-	 * case, subsystem has no reference after pre_destroy(). But, under
-	 * hierarchy management, some *temporal* refcnt can be hold.
-	 * To avoid returning -EBUSY to a user, waitqueue is used. If subsys
-	 * is really busy, it should return -EBUSY at pre_destroy(). wake_up
-	 * is called when css_put() is called and refcnt goes down to 0.
-	 */
-	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-
 	if (!cgroup_clear_css_refs(cgrp)) {
 		mutex_unlock(&cgroup_mutex);
-		schedule();
+		/*
+		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
+		 * prepare_to_wait(), we need to check this flag.
+		 */
+		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
+			schedule();
 		finish_wait(&cgroup_rmdir_waitq, &wait);
 		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		if (signal_pending(current))
@@ -3280,7 +3363,7 @@ void __css_put(struct cgroup_subsys_state *css)
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		cgroup_wakeup_rmdir_waiters(cgrp);
+		cgroup_wakeup_rmdir_waiter(cgrp);
 	}
 	rcu_read_unlock();
 }
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 395b6974dc8..8ce10043e4a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -34,14 +34,11 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
-} cpu_hotplug;
-
-void __init cpu_hotplug_init(void)
-{
-	cpu_hotplug.active_writer = NULL;
-	mutex_init(&cpu_hotplug.lock);
-	cpu_hotplug.refcount = 0;
-}
+} cpu_hotplug = {
+	.active_writer = NULL,
+	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
+	.refcount = 0,
+};
 
 #ifdef CONFIG_HOTPLUG_CPU
 
diff --git a/kernel/exit.c b/kernel/exit.c
index b6c90b5ef50..869dc221733 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -12,7 +12,6 @@
 #include <linux/completion.h>
 #include <linux/personality.h>
 #include <linux/tty.h>
-#include <linux/mnt_namespace.h>
 #include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/security.h>
@@ -375,9 +374,8 @@ static void set_special_pids(struct pid *pid)
 }
 
 /*
- * Let kernel threads use this to say that they
- * allow a certain signal (since daemonize() will
- * have disabled all of them by default).
+ * Let kernel threads use this to say that they allow a certain signal.
+ * Must not be used if kthread was cloned with CLONE_SIGHAND.
  */
 int allow_signal(int sig)
 {
@@ -385,14 +383,14 @@ int allow_signal(int sig)
 		return -EINVAL;
 
 	spin_lock_irq(&current->sighand->siglock);
+	/* This is only needed for daemonize()'ed kthreads */
 	sigdelset(&current->blocked, sig);
-	if (!current->mm) {
-		/* Kernel threads handle their own signals.
-		   Let the signal code know it'll be handled, so
-		   that they don't get converted to SIGKILL or
-		   just silently dropped */
-		current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
-	}
+	/*
+	 * Kernel threads handle their own signals. Let the signal code
+	 * know it'll be handled, so that they don't get converted to
+	 * SIGKILL or just silently dropped.
+	 */
+	current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 	return 0;
@@ -591,7 +589,7 @@ retry:
 	/*
 	 * Search in the siblings
 	 */
-	list_for_each_entry(c, &p->parent->children, sibling) {
+	list_for_each_entry(c, &p->real_parent->children, sibling) {
 		if (c->mm == mm)
 			goto assign_new_owner;
 	}
@@ -758,7 +756,7 @@ static void reparent_thread(struct task_struct *father, struct task_struct *p,
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
-	if (!p->ptrace &&
+	if (!task_ptrace(p) &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
 		do_notify_parent(p, p->exit_signal);
 		if (task_detached(p)) {
@@ -783,7 +781,7 @@ static void forget_original_parent(struct task_struct *father)
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
 		p->real_parent = reaper;
 		if (p->parent == father) {
-			BUG_ON(p->ptrace);
+			BUG_ON(task_ptrace(p));
 			p->parent = p->real_parent;
 		}
 		reparent_thread(father, p, &dead_children);
@@ -1081,6 +1079,18 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
 	return 0;
 }
 
+struct wait_opts {
+	enum pid_type		wo_type;
+	int			wo_flags;
+	struct pid		*wo_pid;
+
+	struct siginfo __user	*wo_info;
+	int __user		*wo_stat;
+	struct rusage __user	*wo_rusage;
+
+	int			notask_error;
+};
+
 static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 {
 	struct pid *pid = NULL;
@@ -1091,13 +1101,12 @@ static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 	return pid;
 }
 
-static int eligible_child(enum pid_type type, struct pid *pid, int options,
-			  struct task_struct *p)
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
 {
 	int err;
 
-	if (type < PIDTYPE_MAX) {
-		if (task_pid_type(p, type) != pid)
+	if (wo->wo_type < PIDTYPE_MAX) {
+		if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
 			return 0;
 	}
 
@@ -1106,8 +1115,8 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
 	 * set; otherwise, wait for non-clone children *only*.  (Note:
 	 * A "clone" child here is one that reports to its parent
 	 * using a signal other than SIGCHLD.) */
-	if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
-	    && !(options & __WALL))
+	if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
+	    && !(wo->wo_flags & __WALL))
 		return 0;
 
 	err = security_task_wait(p);
@@ -1117,14 +1126,15 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options,
 	return 1;
 }
 
-static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
-			       int why, int status,
-			       struct siginfo __user *infop,
-			       struct rusage __user *rusagep)
+static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
+				pid_t pid, uid_t uid, int why, int status)
 {
-	int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
+	struct siginfo __user *infop;
+	int retval = wo->wo_rusage
+		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
 
 	put_task_struct(p);
+	infop = wo->wo_info;
 	if (!retval)
 		retval = put_user(SIGCHLD, &infop->si_signo);
 	if (!retval)
@@ -1148,19 +1158,18 @@ static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
  * the lock and this task is uninteresting.  If we return nonzero, we have
  * released the lock and the system call should return.
  */
-static int wait_task_zombie(struct task_struct *p, int options,
-			    struct siginfo __user *infop,
-			    int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 {
 	unsigned long state;
 	int retval, status, traced;
 	pid_t pid = task_pid_vnr(p);
 	uid_t uid = __task_cred(p)->uid;
+	struct siginfo __user *infop;
 
-	if (!likely(options & WEXITED))
+	if (!likely(wo->wo_flags & WEXITED))
 		return 0;
 
-	if (unlikely(options & WNOWAIT)) {
+	if (unlikely(wo->wo_flags & WNOWAIT)) {
 		int exit_code = p->exit_code;
 		int why, status;
 
@@ -1173,8 +1182,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
 			why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
 			status = exit_code & 0x7f;
 		}
-		return wait_noreap_copyout(p, pid, uid, why,
-					   status, infop, ru);
+		return wait_noreap_copyout(wo, p, pid, uid, why, status);
 	}
 
 	/*
@@ -1188,11 +1196,13 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	}
 
 	traced = ptrace_reparented(p);
-
-	if (likely(!traced)) {
+	/*
+	 * It can be ptraced but not reparented, check
+	 * !task_detached() to filter out sub-threads.
+	 */
+	if (likely(!traced) && likely(!task_detached(p))) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
-		struct task_cputime cputime;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1205,26 +1215,23 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * p->signal fields, because they are only touched by
 		 * __exit_signal, which runs with tasklist_lock
 		 * write-locked anyway, and so is excluded here.  We do
-		 * need to protect the access to p->parent->signal fields,
+		 * need to protect the access to parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
-		 *
-		 * We use thread_group_cputime() to get times for the thread
-		 * group, which consolidates times for all threads in the
-		 * group including the group leader.
 		 */
-		thread_group_cputime(p, &cputime);
-		spin_lock_irq(&p->parent->sighand->siglock);
-		psig = p->parent->signal;
+		spin_lock_irq(&p->real_parent->sighand->siglock);
+		psig = p->real_parent->signal;
 		sig = p->signal;
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(cputime.utime,
-				    sig->cutime));
+			cputime_add(p->utime,
+			cputime_add(sig->utime,
+				    sig->cutime)));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(cputime.stime,
-				    sig->cstime));
+			cputime_add(p->stime,
+			cputime_add(sig->stime,
+				    sig->cstime)));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,
@@ -1246,7 +1253,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
 			sig->oublock + sig->coublock;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		spin_unlock_irq(&p->parent->sighand->siglock);
+		spin_unlock_irq(&p->real_parent->sighand->siglock);
 	}
 
 	/*
@@ -1255,11 +1262,14 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	 */
 	read_unlock(&tasklist_lock);
 
-	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+	retval = wo->wo_rusage
+		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
 	status = (p->signal->flags & SIGNAL_GROUP_EXIT)
 		? p->signal->group_exit_code : p->exit_code;
-	if (!retval && stat_addr)
-		retval = put_user(status, stat_addr);
+	if (!retval && wo->wo_stat)
+		retval = put_user(status, wo->wo_stat);
+
+	infop = wo->wo_info;
 	if (!retval && infop)
 		retval = put_user(SIGCHLD, &infop->si_signo);
 	if (!retval && infop)
@@ -1327,15 +1337,18 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace)
  * the lock and this task is uninteresting.  If we return nonzero, we have
  * released the lock and the system call should return.
  */
-static int wait_task_stopped(int ptrace, struct task_struct *p,
-			     int options, struct siginfo __user *infop,
-			     int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_stopped(struct wait_opts *wo,
+				int ptrace, struct task_struct *p)
 {
+	struct siginfo __user *infop;
 	int retval, exit_code, *p_code, why;
 	uid_t uid = 0; /* unneeded, required by compiler */
 	pid_t pid;
 
-	if (!(options & WUNTRACED))
+	/*
+	 * Traditionally we see ptrace'd stopped tasks regardless of options.
+	 */
+	if (!ptrace && !(wo->wo_flags & WUNTRACED))
 		return 0;
 
 	exit_code = 0;
@@ -1349,7 +1362,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
 	if (!exit_code)
 		goto unlock_sig;
 
-	if (!unlikely(options & WNOWAIT))
+	if (!unlikely(wo->wo_flags & WNOWAIT))
 		*p_code = 0;
 
 	/* don't need the RCU readlock here as we're holding a spinlock */
@@ -1371,14 +1384,15 @@ unlock_sig:
 	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
 	read_unlock(&tasklist_lock);
 
-	if (unlikely(options & WNOWAIT))
-		return wait_noreap_copyout(p, pid, uid,
-					   why, exit_code,
-					   infop, ru);
+	if (unlikely(wo->wo_flags & WNOWAIT))
+		return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
 
-	retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
-	if (!retval && stat_addr)
-		retval = put_user((exit_code << 8) | 0x7f, stat_addr);
+	retval = wo->wo_rusage
+		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
+	if (!retval && wo->wo_stat)
+		retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat);
+
+	infop = wo->wo_info;
 	if (!retval && infop)
 		retval = put_user(SIGCHLD, &infop->si_signo);
 	if (!retval && infop)
@@ -1405,15 +1419,13 @@ unlock_sig:
  * the lock and this task is uninteresting.  If we return nonzero, we have
  * released the lock and the system call should return.
  */
-static int wait_task_continued(struct task_struct *p, int options,
-			       struct siginfo __user *infop,
-			       int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 {
 	int retval;
 	pid_t pid;
 	uid_t uid;
 
-	if (!unlikely(options & WCONTINUED))
+	if (!unlikely(wo->wo_flags & WCONTINUED))
 		return 0;
 
 	if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
@@ -1425,7 +1437,7 @@ static int wait_task_continued(struct task_struct *p, int options,
 		spin_unlock_irq(&p->sighand->siglock);
 		return 0;
 	}
-	if (!unlikely(options & WNOWAIT))
+	if (!unlikely(wo->wo_flags & WNOWAIT))
 		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
 	uid = __task_cred(p)->uid;
 	spin_unlock_irq(&p->sighand->siglock);
@@ -1434,17 +1446,17 @@ static int wait_task_continued(struct task_struct *p, int options,
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
 
-	if (!infop) {
-		retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+	if (!wo->wo_info) {
+		retval = wo->wo_rusage
+			? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
 		put_task_struct(p);
-		if (!retval && stat_addr)
-			retval = put_user(0xffff, stat_addr);
+		if (!retval && wo->wo_stat)
+			retval = put_user(0xffff, wo->wo_stat);
 		if (!retval)
 			retval = pid;
 	} else {
-		retval = wait_noreap_copyout(p, pid, uid,
-					     CLD_CONTINUED, SIGCONT,
-					     infop, ru);
+		retval = wait_noreap_copyout(wo, p, pid, uid,
+					     CLD_CONTINUED, SIGCONT);
 		BUG_ON(retval == 0);
 	}
 
@@ -1454,19 +1466,16 @@ static int wait_task_continued(struct task_struct *p, int options,
 /*
  * Consider @p for a wait by @parent.
  *
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
  * Returns nonzero for a final return, when we have unlocked tasklist_lock.
  * Returns zero if the search for a child should continue;
- * then *@notask_error is 0 if @p is an eligible child,
+ * then ->notask_error is 0 if @p is an eligible child,
  * or another error from security_task_wait(), or still -ECHILD.
  */
-static int wait_consider_task(struct task_struct *parent, int ptrace,
-			      struct task_struct *p, int *notask_error,
-			      enum pid_type type, struct pid *pid, int options,
-			      struct siginfo __user *infop,
-			      int __user *stat_addr, struct rusage __user *ru)
+static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
+				int ptrace, struct task_struct *p)
 {
-	int ret = eligible_child(type, pid, options, p);
+	int ret = eligible_child(wo, p);
 	if (!ret)
 		return ret;
 
@@ -1478,17 +1487,17 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 		 * to look for security policy problems, rather
 		 * than for mysterious wait bugs.
 		 */
-		if (*notask_error)
-			*notask_error = ret;
+		if (wo->notask_error)
+			wo->notask_error = ret;
 		return 0;
 	}
 
-	if (likely(!ptrace) && unlikely(p->ptrace)) {
+	if (likely(!ptrace) && unlikely(task_ptrace(p))) {
 		/*
 		 * This child is hidden by ptrace.
 		 * We aren't allowed to see it now, but eventually we will.
 		 */
-		*notask_error = 0;
+		wo->notask_error = 0;
 		return 0;
 	}
 
@@ -1499,34 +1508,30 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 	 * We don't reap group leaders with subthreads.
 	 */
 	if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
-		return wait_task_zombie(p, options, infop, stat_addr, ru);
+		return wait_task_zombie(wo, p);
 
 	/*
 	 * It's stopped or running now, so it might
 	 * later continue, exit, or stop again.
 	 */
-	*notask_error = 0;
+	wo->notask_error = 0;
 
 	if (task_stopped_code(p, ptrace))
-		return wait_task_stopped(ptrace, p, options,
-					 infop, stat_addr, ru);
+		return wait_task_stopped(wo, ptrace, p);
 
-	return wait_task_continued(p, options, infop, stat_addr, ru);
+	return wait_task_continued(wo, p);
 }
 
 /*
  * Do the work of do_wait() for one thread in the group, @tsk.
  *
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
  * Returns nonzero for a final return, when we have unlocked tasklist_lock.
  * Returns zero if the search for a child should continue; then
- * *@notask_error is 0 if there were any eligible children,
+ * ->notask_error is 0 if there were any eligible children,
  * or another error from security_task_wait(), or still -ECHILD.
  */
-static int do_wait_thread(struct task_struct *tsk, int *notask_error,
-			  enum pid_type type, struct pid *pid, int options,
-			  struct siginfo __user *infop, int __user *stat_addr,
-			  struct rusage __user *ru)
+static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
 {
 	struct task_struct *p;
 
@@ -1535,9 +1540,7 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error,
 		 * Do not consider detached threads.
 		 */
 		if (!task_detached(p)) {
-			int ret = wait_consider_task(tsk, 0, p, notask_error,
-						     type, pid, options,
-						     infop, stat_addr, ru);
+			int ret = wait_consider_task(wo, tsk, 0, p);
 			if (ret)
 				return ret;
 		}
@@ -1546,22 +1549,12 @@ static int do_wait_thread(struct task_struct *tsk, int *notask_error,
 	return 0;
 }
 
-static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
-			  enum pid_type type, struct pid *pid, int options,
-			  struct siginfo __user *infop, int __user *stat_addr,
-			  struct rusage __user *ru)
+static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 {
 	struct task_struct *p;
 
-	/*
-	 * Traditionally we see ptrace'd stopped tasks regardless of options.
-	 */
-	options |= WUNTRACED;
-
 	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
-		int ret = wait_consider_task(tsk, 1, p, notask_error,
-					     type, pid, options,
-					     infop, stat_addr, ru);
+		int ret = wait_consider_task(wo, tsk, 1, p);
 		if (ret)
 			return ret;
 	}
@@ -1569,65 +1562,59 @@ static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
 	return 0;
 }
 
-static long do_wait(enum pid_type type, struct pid *pid, int options,
-		    struct siginfo __user *infop, int __user *stat_addr,
-		    struct rusage __user *ru)
+static long do_wait(struct wait_opts *wo)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct task_struct *tsk;
 	int retval;
 
-	trace_sched_process_wait(pid);
+	trace_sched_process_wait(wo->wo_pid);
 
 	add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
 	/*
 	 * If there is nothing that can match our critiera just get out.
-	 * We will clear @retval to zero if we see any child that might later
-	 * match our criteria, even if we are not able to reap it yet.
+	 * We will clear ->notask_error to zero if we see any child that
+	 * might later match our criteria, even if we are not able to reap
+	 * it yet.
 	 */
-	retval = -ECHILD;
-	if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
-		goto end;
+	wo->notask_error = -ECHILD;
+	if ((wo->wo_type < PIDTYPE_MAX) &&
+	   (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+		goto notask;
 
-	current->state = TASK_INTERRUPTIBLE;
+	set_current_state(TASK_INTERRUPTIBLE);
 	read_lock(&tasklist_lock);
 	tsk = current;
 	do {
-		int tsk_result = do_wait_thread(tsk, &retval,
-						type, pid, options,
-						infop, stat_addr, ru);
-		if (!tsk_result)
-			tsk_result = ptrace_do_wait(tsk, &retval,
-						    type, pid, options,
-						    infop, stat_addr, ru);
-		if (tsk_result) {
-			/*
-			 * tasklist_lock is unlocked and we have a final result.
-			 */
-			retval = tsk_result;
+		retval = do_wait_thread(wo, tsk);
+		if (retval)
+			goto end;
+
+		retval = ptrace_do_wait(wo, tsk);
+		if (retval)
 			goto end;
-		}
 
-		if (options & __WNOTHREAD)
+		if (wo->wo_flags & __WNOTHREAD)
 			break;
-		tsk = next_thread(tsk);
-		BUG_ON(tsk->signal != current->signal);
-	} while (tsk != current);
+	} while_each_thread(current, tsk);
 	read_unlock(&tasklist_lock);
 
-	if (!retval && !(options & WNOHANG)) {
+notask:
+	retval = wo->notask_error;
+	if (!retval && !(wo->wo_flags & WNOHANG)) {
 		retval = -ERESTARTSYS;
 		if (!signal_pending(current)) {
 			schedule();
 			goto repeat;
 		}
 	}
-
 end:
-	current->state = TASK_RUNNING;
+	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&current->signal->wait_chldexit,&wait);
-	if (infop) {
+	if (wo->wo_info) {
+		struct siginfo __user *infop = wo->wo_info;
+
 		if (retval > 0)
 			retval = 0;
 		else {
@@ -1656,6 +1643,7 @@ end:
 SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 		infop, int, options, struct rusage __user *, ru)
 {
+	struct wait_opts wo;
 	struct pid *pid = NULL;
 	enum pid_type type;
 	long ret;
@@ -1685,7 +1673,14 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 
 	if (type < PIDTYPE_MAX)
 		pid = find_get_pid(upid);
-	ret = do_wait(type, pid, options, infop, NULL, ru);
+
+	wo.wo_type	= type;
+	wo.wo_pid	= pid;
+	wo.wo_flags	= options;
+	wo.wo_info	= infop;
+	wo.wo_stat	= NULL;
+	wo.wo_rusage	= ru;
+	ret = do_wait(&wo);
 	put_pid(pid);
 
 	/* avoid REGPARM breakage on x86: */
@@ -1696,6 +1691,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {
+	struct wait_opts wo;
 	struct pid *pid = NULL;
 	enum pid_type type;
 	long ret;
@@ -1717,7 +1713,13 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		pid = find_get_pid(upid);
 	}
 
-	ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
+	wo.wo_type	= type;
+	wo.wo_pid	= pid;
+	wo.wo_flags	= options | WEXITED;
+	wo.wo_info	= NULL;
+	wo.wo_stat	= stat_addr;
+	wo.wo_rusage	= ru;
+	ret = do_wait(&wo);
 	put_pid(pid);
 
 	/* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index be022c200da..e6c04d462ab 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/completion.h>
-#include <linux/mnt_namespace.h>
 #include <linux/personality.h>
 #include <linux/mempolicy.h>
 #include <linux/sem.h>
@@ -568,18 +567,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	 * the value intact in a core dump, and to save the unnecessary
 	 * trouble otherwise.  Userland only wants this done for a sys_exit.
 	 */
-	if (tsk->clear_child_tid
-	    && !(tsk->flags & PF_SIGNALED)
-	    && atomic_read(&mm->mm_users) > 1) {
-		u32 __user * tidptr = tsk->clear_child_tid;
+	if (tsk->clear_child_tid) {
+		if (!(tsk->flags & PF_SIGNALED) &&
+		    atomic_read(&mm->mm_users) > 1) {
+			/*
+			 * We don't check the error code - if userspace has
+			 * not set up a proper pointer then tough luck.
+			 */
+			put_user(0, tsk->clear_child_tid);
+			sys_futex(tsk->clear_child_tid, FUTEX_WAKE,
+					1, NULL, NULL, 0);
+		}
 		tsk->clear_child_tid = NULL;
-
-		/*
-		 * We don't check the error code - if userspace has
-		 * not set up a proper pointer then tough luck.
-		 */
-		put_user(0, tidptr);
-		sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
 	}
 }
 
@@ -816,11 +815,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 
-	if (clone_flags & CLONE_THREAD) {
-		atomic_inc(&current->signal->count);
-		atomic_inc(&current->signal->live);
+	if (clone_flags & CLONE_THREAD)
 		return 0;
-	}
 
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
@@ -878,16 +874,6 @@ void __cleanup_signal(struct signal_struct *sig)
 	kmem_cache_free(signal_cachep, sig);
 }
 
-static void cleanup_signal(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-
-	atomic_dec(&sig->live);
-
-	if (atomic_dec_and_test(&sig->count))
-		__cleanup_signal(sig);
-}
-
 static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
@@ -1029,7 +1015,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->vfork_done = NULL;
 	spin_lock_init(&p->alloc_lock);
 
-	clear_tsk_thread_flag(p, TIF_SIGPENDING);
 	init_sigpending(&p->pending);
 
 	p->utime = cputime_zero;
@@ -1241,6 +1226,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (clone_flags & CLONE_THREAD) {
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
 	}
@@ -1270,6 +1257,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
+	perf_counter_fork(p);
 	return p;
 
 bad_fork_free_pid:
@@ -1283,7 +1271,8 @@ bad_fork_cleanup_mm:
 	if (p->mm)
 		mmput(p->mm);
 bad_fork_cleanup_signal:
-	cleanup_signal(p);
+	if (!(clone_flags & CLONE_THREAD))
+		__cleanup_signal(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
@@ -1409,12 +1398,6 @@ long do_fork(unsigned long clone_flags,
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
 			init_completion(&vfork);
-		} else if (!(clone_flags & CLONE_VM)) {
-			/*
-			 * vfork will do an exec which will call
-			 * set_task_comm()
-			 */
-			perf_counter_fork(p);
 		}
 
 		audit_finish_fork(p);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 2f4936cf708..bd1d42b17cb 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -44,12 +44,19 @@ void refrigerator(void)
 	recalc_sigpending(); /* We sent fake signal, clean it up */
 	spin_unlock_irq(&current->sighand->siglock);
 
+	/* prevent accounting of that task to load */
+	current->flags |= PF_FREEZING;
+
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!frozen(current))
 			break;
 		schedule();
 	}
+
+	/* Remove the accounting blocker */
+	current->flags &= ~PF_FREEZING;
+
 	pr_debug("%s left refrigerator\n", current->comm);
 	__set_current_state(save);
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 80b5ce71659..e18cfbdc719 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -247,6 +247,7 @@ again:
 	if (err < 0)
 		return err;
 
+	page = compound_head(page);
 	lock_page(page);
 	if (!page->mapping) {
 		unlock_page(page);
@@ -284,6 +285,25 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
+/*
+ * fault_in_user_writeable - fault in user address and verify RW access
+ * @uaddr:	pointer to faulting user space address
+ *
+ * Slow path to fixup the fault we just took in the atomic write
+ * access to @uaddr.
+ *
+ * We have no generic implementation of a non destructive write to the
+ * user address. We know that we faulted in the atomic pagefault
+ * disabled section so we can as well avoid the #PF overhead by
+ * calling get_user_pages() right away.
+ */
+static int fault_in_user_writeable(u32 __user *uaddr)
+{
+	int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
+				 1, 1, 0, NULL, NULL);
+	return ret < 0 ? ret : 0;
+}
+
 /**
  * futex_top_waiter() - Return the highest priority waiter on a futex
  * @hb:     the hash bucket the futex_q's reside in
@@ -896,7 +916,6 @@ retry:
 retry_private:
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-		u32 dummy;
 
 		double_unlock_hb(hb1, hb2);
 
@@ -914,7 +933,7 @@ retry_private:
 			goto out_put_keys;
 		}
 
-		ret = get_user(dummy, uaddr2);
+		ret = fault_in_user_writeable(uaddr2);
 		if (ret)
 			goto out_put_keys;
 
@@ -991,15 +1010,19 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
  * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
  * q:	the futex_q
  * key:	the key of the requeue target futex
+ * hb:  the hash_bucket of the requeue target futex
  *
  * During futex_requeue, with requeue_pi=1, it is possible to acquire the
  * target futex if it is uncontended or via a lock steal.  Set the futex_q key
  * to the requeue target futex so the waiter can detect the wakeup on the right
  * futex, but remove it from the hb and NULL the rt_waiter so it can detect
- * atomic lock acquisition.  Must be called with the q->lock_ptr held.
+ * atomic lock acquisition.  Set the q->lock_ptr to the requeue target hb->lock
+ * to protect access to the pi_state to fixup the owner later.  Must be called
+ * with both q->lock_ptr and hb->lock held.
  */
 static inline
-void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
+			   struct futex_hash_bucket *hb)
 {
 	drop_futex_key_refs(&q->key);
 	get_futex_key_refs(key);
@@ -1011,6 +1034,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
 	WARN_ON(!q->rt_waiter);
 	q->rt_waiter = NULL;
 
+	q->lock_ptr = &hb->lock;
+#ifdef CONFIG_DEBUG_PI_LIST
+	q->list.plist.lock = &hb->lock;
+#endif
+
 	wake_up_state(q->task, TASK_NORMAL);
 }
 
@@ -1069,7 +1097,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   set_waiters);
 	if (ret == 1)
-		requeue_pi_wake_futex(top_waiter, key2);
+		requeue_pi_wake_futex(top_waiter, key2, hb2);
 
 	return ret;
 }
@@ -1204,7 +1232,7 @@ retry_private:
 			double_unlock_hb(hb1, hb2);
 			put_futex_key(fshared, &key2);
 			put_futex_key(fshared, &key1);
-			ret = get_user(curval2, uaddr2);
+			ret = fault_in_user_writeable(uaddr2);
 			if (!ret)
 				goto retry;
 			goto out;
@@ -1228,8 +1256,15 @@ retry_private:
 		if (!match_futex(&this->key, &key1))
 			continue;
 
-		WARN_ON(!requeue_pi && this->rt_waiter);
-		WARN_ON(requeue_pi && !this->rt_waiter);
+		/*
+		 * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
+		 * be paired with each other and no other futex ops.
+		 */
+		if ((requeue_pi && !this->rt_waiter) ||
+		    (!requeue_pi && this->rt_waiter)) {
+			ret = -EINVAL;
+			break;
+		}
 
 		/*
 		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
@@ -1254,7 +1289,7 @@ retry_private:
 							this->task, 1);
 			if (ret == 1) {
 				/* We got the lock. */
-				requeue_pi_wake_futex(this, &key2);
+				requeue_pi_wake_futex(this, &key2, hb2);
 				continue;
 			} else if (ret) {
 				/* -EDEADLK */
@@ -1482,7 +1517,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = get_user(uval, uaddr);
+	ret = fault_in_user_writeable(uaddr);
 
 	spin_lock(q->lock_ptr);
 
@@ -1807,7 +1842,6 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct futex_hash_bucket *hb;
-	u32 uval;
 	struct futex_q q;
 	int res, ret;
 
@@ -1909,16 +1943,9 @@ out:
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
-	/*
-	 * We have to r/w  *(int __user *)uaddr, and we have to modify it
-	 * atomically.  Therefore, if we continue to fault after get_user()
-	 * below, we need to handle the fault ourselves, while still holding
-	 * the mmap_sem.  This can occur if the uaddr is under contention as
-	 * we have to drop the mmap_sem in order to call get_user().
-	 */
 	queue_unlock(&q, hb);
 
-	ret = get_user(uval, uaddr);
+	ret = fault_in_user_writeable(uaddr);
 	if (ret)
 		goto out_put_key;
 
@@ -2013,17 +2040,10 @@ out:
 	return ret;
 
 pi_faulted:
-	/*
-	 * We have to r/w  *(int __user *)uaddr, and we have to modify it
-	 * atomically.  Therefore, if we continue to fault after get_user()
-	 * below, we need to handle the fault ourselves, while still holding
-	 * the mmap_sem.  This can occur if the uaddr is under contention as
-	 * we have to drop the mmap_sem in order to call get_user().
-	 */
 	spin_unlock(&hb->lock);
 	put_futex_key(fshared, &key);
 
-	ret = get_user(uval, uaddr);
+	ret = fault_in_user_writeable(uaddr);
 	if (!ret)
 		goto retry;
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index d607a5b9ee2..235716556bf 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -180,7 +180,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
 	int cmd = op & FUTEX_CMD_MASK;
 
 	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
-		      cmd == FUTEX_WAIT_BITSET)) {
+		      cmd == FUTEX_WAIT_BITSET ||
+		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
 		if (get_compat_timespec(&ts, utime))
 			return -EFAULT;
 		if (!timespec_valid(&ts))
@@ -191,7 +192,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
 			t = ktime_add_safe(ktime_get(), t);
 		tp = &t;
 	}
-	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE)
+	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
+	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
 		val2 = (int) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
new file mode 100644
index 00000000000..22e9dcfaa3d
--- /dev/null
+++ b/kernel/gcov/Kconfig
@@ -0,0 +1,48 @@
+menu "GCOV-based kernel profiling"
+
+config GCOV_KERNEL
+	bool "Enable gcov-based kernel profiling"
+	depends on DEBUG_FS && CONSTRUCTORS
+	default n
+	---help---
+	This option enables gcov-based code profiling (e.g. for code coverage
+	measurements).
+
+	If unsure, say N.
+
+	Additionally specify CONFIG_GCOV_PROFILE_ALL=y to get profiling data
+	for the entire kernel. To enable profiling for specific files or
+	directories, add a line similar to the following to the respective
+	Makefile:
+
+	For a single file (e.g. main.o):
+	        GCOV_PROFILE_main.o := y
+
+	For all files in one directory:
+	        GCOV_PROFILE := y
+
+	To exclude files from being profiled even when CONFIG_GCOV_PROFILE_ALL
+	is specified, use:
+
+	        GCOV_PROFILE_main.o := n
+	and:
+	        GCOV_PROFILE := n
+
+	Note that the debugfs filesystem has to be mounted to access
+	profiling data.
+
+config GCOV_PROFILE_ALL
+	bool "Profile entire Kernel"
+	depends on GCOV_KERNEL
+	depends on S390 || X86
+	default n
+	---help---
+	This options activates profiling for the entire kernel.
+
+	If unsure, say N.
+
+	Note that a kernel compiled with profiling flags will be significantly
+	larger and run slower. Also be sure to exclude files from profiling
+	which are not linked to the kernel image to prevent linker errors.
+
+endmenu
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
new file mode 100644
index 00000000000..3f761001d51
--- /dev/null
+++ b/kernel/gcov/Makefile
@@ -0,0 +1,3 @@
+EXTRA_CFLAGS := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
+
+obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
new file mode 100644
index 00000000000..9b22d03cc58
--- /dev/null
+++ b/kernel/gcov/base.c
@@ -0,0 +1,148 @@
+/*
+ *  This code maintains a list of active profiling data structures.
+ *
+ *    Copyright IBM Corp. 2009
+ *    Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ *    Uses gcc-internal data definitions.
+ *    Based on the gcov-kernel patch by:
+ *		 Hubertus Franke <frankeh@us.ibm.com>
+ *		 Nigel Hinds <nhinds@us.ibm.com>
+ *		 Rajan Ravindran <rajancr@us.ibm.com>
+ *		 Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *		 Paul Larson
+ */
+
+#define pr_fmt(fmt)	"gcov: " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include "gcov.h"
+
+static struct gcov_info *gcov_info_head;
+static int gcov_events_enabled;
+static DEFINE_MUTEX(gcov_lock);
+
+/*
+ * __gcov_init is called by gcc-generated constructor code for each object
+ * file compiled with -fprofile-arcs.
+ */
+void __gcov_init(struct gcov_info *info)
+{
+	static unsigned int gcov_version;
+
+	mutex_lock(&gcov_lock);
+	if (gcov_version == 0) {
+		gcov_version = info->version;
+		/*
+		 * Printing gcc's version magic may prove useful for debugging
+		 * incompatibility reports.
+		 */
+		pr_info("version magic: 0x%x\n", gcov_version);
+	}
+	/*
+	 * Add new profiling data structure to list and inform event
+	 * listener.
+	 */
+	info->next = gcov_info_head;
+	gcov_info_head = info;
+	if (gcov_events_enabled)
+		gcov_event(GCOV_ADD, info);
+	mutex_unlock(&gcov_lock);
+}
+EXPORT_SYMBOL(__gcov_init);
+
+/*
+ * These functions may be referenced by gcc-generated profiling code but serve
+ * no function for kernel profiling.
+ */
+void __gcov_flush(void)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_flush);
+
+void __gcov_merge_add(gcov_type *counters, unsigned int n_counters)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_add);
+
+void __gcov_merge_single(gcov_type *counters, unsigned int n_counters)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_single);
+
+void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_delta);
+
+/**
+ * gcov_enable_events - enable event reporting through gcov_event()
+ *
+ * Turn on reporting of profiling data load/unload-events through the
+ * gcov_event() callback. Also replay all previous events once. This function
+ * is needed because some events are potentially generated too early for the
+ * callback implementation to handle them initially.
+ */
+void gcov_enable_events(void)
+{
+	struct gcov_info *info;
+
+	mutex_lock(&gcov_lock);
+	gcov_events_enabled = 1;
+	/* Perform event callback for previously registered entries. */
+	for (info = gcov_info_head; info; info = info->next)
+		gcov_event(GCOV_ADD, info);
+	mutex_unlock(&gcov_lock);
+}
+
+#ifdef CONFIG_MODULES
+static inline int within(void *addr, void *start, unsigned long size)
+{
+	return ((addr >= start) && (addr < start + size));
+}
+
+/* Update list and generate events when modules are unloaded. */
+static int gcov_module_notifier(struct notifier_block *nb, unsigned long event,
+				void *data)
+{
+	struct module *mod = data;
+	struct gcov_info *info;
+	struct gcov_info *prev;
+
+	if (event != MODULE_STATE_GOING)
+		return NOTIFY_OK;
+	mutex_lock(&gcov_lock);
+	prev = NULL;
+	/* Remove entries located in module from linked list. */
+	for (info = gcov_info_head; info; info = info->next) {
+		if (within(info, mod->module_core, mod->core_size)) {
+			if (prev)
+				prev->next = info->next;
+			else
+				gcov_info_head = info->next;
+			if (gcov_events_enabled)
+				gcov_event(GCOV_REMOVE, info);
+		} else
+			prev = info;
+	}
+	mutex_unlock(&gcov_lock);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gcov_nb = {
+	.notifier_call	= gcov_module_notifier,
+};
+
+static int __init gcov_init(void)
+{
+	return register_module_notifier(&gcov_nb);
+}
+device_initcall(gcov_init);
+#endif /* CONFIG_MODULES */
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
new file mode 100644
index 00000000000..ef3c3f88a7a
--- /dev/null
+++ b/kernel/gcov/fs.c
@@ -0,0 +1,673 @@
+/*
+ *  This code exports profiling data as debugfs files to userspace.
+ *
+ *    Copyright IBM Corp. 2009
+ *    Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ *    Uses gcc-internal data definitions.
+ *    Based on the gcov-kernel patch by:
+ *		 Hubertus Franke <frankeh@us.ibm.com>
+ *		 Nigel Hinds <nhinds@us.ibm.com>
+ *		 Rajan Ravindran <rajancr@us.ibm.com>
+ *		 Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *		 Paul Larson
+ *		 Yi CDL Yang
+ */
+
+#define pr_fmt(fmt)	"gcov: " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include "gcov.h"
+
+/**
+ * struct gcov_node - represents a debugfs entry
+ * @list: list head for child node list
+ * @children: child nodes
+ * @all: list head for list of all nodes
+ * @parent: parent node
+ * @info: associated profiling data structure if not a directory
+ * @ghost: when an object file containing profiling data is unloaded we keep a
+ *         copy of the profiling data here to allow collecting coverage data
+ *         for cleanup code. Such a node is called a "ghost".
+ * @dentry: main debugfs entry, either a directory or data file
+ * @links: associated symbolic links
+ * @name: data file basename
+ *
+ * struct gcov_node represents an entity within the gcov/ subdirectory
+ * of debugfs. There are directory and data file nodes. The latter represent
+ * the actual synthesized data file plus any associated symbolic links which
+ * are needed by the gcov tool to work correctly.
+ */
+struct gcov_node {
+	struct list_head list;
+	struct list_head children;
+	struct list_head all;
+	struct gcov_node *parent;
+	struct gcov_info *info;
+	struct gcov_info *ghost;
+	struct dentry *dentry;
+	struct dentry **links;
+	char name[0];
+};
+
+static const char objtree[] = OBJTREE;
+static const char srctree[] = SRCTREE;
+static struct gcov_node root_node;
+static struct dentry *reset_dentry;
+static LIST_HEAD(all_head);
+static DEFINE_MUTEX(node_lock);
+
+/* If non-zero, keep copies of profiling data for unloaded modules. */
+static int gcov_persist = 1;
+
+static int __init gcov_persist_setup(char *str)
+{
+	unsigned long val;
+
+	if (strict_strtoul(str, 0, &val)) {
+		pr_warning("invalid gcov_persist parameter '%s'\n", str);
+		return 0;
+	}
+	gcov_persist = val;
+	pr_info("setting gcov_persist to %d\n", gcov_persist);
+
+	return 1;
+}
+__setup("gcov_persist=", gcov_persist_setup);
+
+/*
+ * seq_file.start() implementation for gcov data files. Note that the
+ * gcov_iterator interface is designed to be more restrictive than seq_file
+ * (no start from arbitrary position, etc.), to simplify the iterator
+ * implementation.
+ */
+static void *gcov_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	loff_t i;
+
+	gcov_iter_start(seq->private);
+	for (i = 0; i < *pos; i++) {
+		if (gcov_iter_next(seq->private))
+			return NULL;
+	}
+	return seq->private;
+}
+
+/* seq_file.next() implementation for gcov data files. */
+static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos)
+{
+	struct gcov_iterator *iter = data;
+
+	if (gcov_iter_next(iter))
+		return NULL;
+	(*pos)++;
+
+	return iter;
+}
+
+/* seq_file.show() implementation for gcov data files. */
+static int gcov_seq_show(struct seq_file *seq, void *data)
+{
+	struct gcov_iterator *iter = data;
+
+	if (gcov_iter_write(iter, seq))
+		return -EINVAL;
+	return 0;
+}
+
+static void gcov_seq_stop(struct seq_file *seq, void *data)
+{
+	/* Unused. */
+}
+
+static const struct seq_operations gcov_seq_ops = {
+	.start	= gcov_seq_start,
+	.next	= gcov_seq_next,
+	.show	= gcov_seq_show,
+	.stop	= gcov_seq_stop,
+};
+
+/*
+ * Return the profiling data set for a given node. This can either be the
+ * original profiling data structure or a duplicate (also called "ghost")
+ * in case the associated object file has been unloaded.
+ */
+static struct gcov_info *get_node_info(struct gcov_node *node)
+{
+	if (node->info)
+		return node->info;
+
+	return node->ghost;
+}
+
+/*
+ * open() implementation for gcov data files. Create a copy of the profiling
+ * data set and initialize the iterator and seq_file interface.
+ */
+static int gcov_seq_open(struct inode *inode, struct file *file)
+{
+	struct gcov_node *node = inode->i_private;
+	struct gcov_iterator *iter;
+	struct seq_file *seq;
+	struct gcov_info *info;
+	int rc = -ENOMEM;
+
+	mutex_lock(&node_lock);
+	/*
+	 * Read from a profiling data copy to minimize reference tracking
+	 * complexity and concurrent access.
+	 */
+	info = gcov_info_dup(get_node_info(node));
+	if (!info)
+		goto out_unlock;
+	iter = gcov_iter_new(info);
+	if (!iter)
+		goto err_free_info;
+	rc = seq_open(file, &gcov_seq_ops);
+	if (rc)
+		goto err_free_iter_info;
+	seq = file->private_data;
+	seq->private = iter;
+out_unlock:
+	mutex_unlock(&node_lock);
+	return rc;
+
+err_free_iter_info:
+	gcov_iter_free(iter);
+err_free_info:
+	gcov_info_free(info);
+	goto out_unlock;
+}
+
+/*
+ * release() implementation for gcov data files. Release resources allocated
+ * by open().
+ */
+static int gcov_seq_release(struct inode *inode, struct file *file)
+{
+	struct gcov_iterator *iter;
+	struct gcov_info *info;
+	struct seq_file *seq;
+
+	seq = file->private_data;
+	iter = seq->private;
+	info = gcov_iter_get_info(iter);
+	gcov_iter_free(iter);
+	gcov_info_free(info);
+	seq_release(inode, file);
+
+	return 0;
+}
+
+/*
+ * Find a node by the associated data file name. Needs to be called with
+ * node_lock held.
+ */
+static struct gcov_node *get_node_by_name(const char *name)
+{
+	struct gcov_node *node;
+	struct gcov_info *info;
+
+	list_for_each_entry(node, &all_head, all) {
+		info = get_node_info(node);
+		if (info && (strcmp(info->filename, name) == 0))
+			return node;
+	}
+
+	return NULL;
+}
+
+static void remove_node(struct gcov_node *node);
+
+/*
+ * write() implementation for gcov data files. Reset profiling data for the
+ * associated file. If the object file has been unloaded (i.e. this is
+ * a "ghost" node), remove the debug fs node as well.
+ */
+static ssize_t gcov_seq_write(struct file *file, const char __user *addr,
+			      size_t len, loff_t *pos)
+{
+	struct seq_file *seq;
+	struct gcov_info *info;
+	struct gcov_node *node;
+
+	seq = file->private_data;
+	info = gcov_iter_get_info(seq->private);
+	mutex_lock(&node_lock);
+	node = get_node_by_name(info->filename);
+	if (node) {
+		/* Reset counts or remove node for unloaded modules. */
+		if (node->ghost)
+			remove_node(node);
+		else
+			gcov_info_reset(node->info);
+	}
+	/* Reset counts for open file. */
+	gcov_info_reset(info);
+	mutex_unlock(&node_lock);
+
+	return len;
+}
+
+/*
+ * Given a string <path> representing a file path of format:
+ *   path/to/file.gcda
+ * construct and return a new string:
+ *   <dir/>path/to/file.<ext>
+ */
+static char *link_target(const char *dir, const char *path, const char *ext)
+{
+	char *target;
+	char *old_ext;
+	char *copy;
+
+	copy = kstrdup(path, GFP_KERNEL);
+	if (!copy)
+		return NULL;
+	old_ext = strrchr(copy, '.');
+	if (old_ext)
+		*old_ext = '\0';
+	if (dir)
+		target = kasprintf(GFP_KERNEL, "%s/%s.%s", dir, copy, ext);
+	else
+		target = kasprintf(GFP_KERNEL, "%s.%s", copy, ext);
+	kfree(copy);
+
+	return target;
+}
+
+/*
+ * Construct a string representing the symbolic link target for the given
+ * gcov data file name and link type. Depending on the link type and the
+ * location of the data file, the link target can either point to a
+ * subdirectory of srctree, objtree or in an external location.
+ */
+static char *get_link_target(const char *filename, const struct gcov_link *ext)
+{
+	const char *rel;
+	char *result;
+
+	if (strncmp(filename, objtree, strlen(objtree)) == 0) {
+		rel = filename + strlen(objtree) + 1;
+		if (ext->dir == SRC_TREE)
+			result = link_target(srctree, rel, ext->ext);
+		else
+			result = link_target(objtree, rel, ext->ext);
+	} else {
+		/* External compilation. */
+		result = link_target(NULL, filename, ext->ext);
+	}
+
+	return result;
+}
+
+#define SKEW_PREFIX	".tmp_"
+
+/*
+ * For a filename .tmp_filename.ext return filename.ext. Needed to compensate
+ * for filename skewing caused by the mod-versioning mechanism.
+ */
+static const char *deskew(const char *basename)
+{
+	if (strncmp(basename, SKEW_PREFIX, sizeof(SKEW_PREFIX) - 1) == 0)
+		return basename + sizeof(SKEW_PREFIX) - 1;
+	return basename;
+}
+
+/*
+ * Create links to additional files (usually .c and .gcno files) which the
+ * gcov tool expects to find in the same directory as the gcov data file.
+ */
+static void add_links(struct gcov_node *node, struct dentry *parent)
+{
+	char *basename;
+	char *target;
+	int num;
+	int i;
+
+	for (num = 0; gcov_link[num].ext; num++)
+		/* Nothing. */;
+	node->links = kcalloc(num, sizeof(struct dentry *), GFP_KERNEL);
+	if (!node->links)
+		return;
+	for (i = 0; i < num; i++) {
+		target = get_link_target(get_node_info(node)->filename,
+					 &gcov_link[i]);
+		if (!target)
+			goto out_err;
+		basename = strrchr(target, '/');
+		if (!basename)
+			goto out_err;
+		basename++;
+		node->links[i] = debugfs_create_symlink(deskew(basename),
+							parent,	target);
+		if (!node->links[i])
+			goto out_err;
+		kfree(target);
+	}
+
+	return;
+out_err:
+	kfree(target);
+	while (i-- > 0)
+		debugfs_remove(node->links[i]);
+	kfree(node->links);
+	node->links = NULL;
+}
+
+static const struct file_operations gcov_data_fops = {
+	.open		= gcov_seq_open,
+	.release	= gcov_seq_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= gcov_seq_write,
+};
+
+/* Basic initialization of a new node. */
+static void init_node(struct gcov_node *node, struct gcov_info *info,
+		      const char *name, struct gcov_node *parent)
+{
+	INIT_LIST_HEAD(&node->list);
+	INIT_LIST_HEAD(&node->children);
+	INIT_LIST_HEAD(&node->all);
+	node->info = info;
+	node->parent = parent;
+	if (name)
+		strcpy(node->name, name);
+}
+
+/*
+ * Create a new node and associated debugfs entry. Needs to be called with
+ * node_lock held.
+ */
+static struct gcov_node *new_node(struct gcov_node *parent,
+				  struct gcov_info *info, const char *name)
+{
+	struct gcov_node *node;
+
+	node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL);
+	if (!node) {
+		pr_warning("out of memory\n");
+		return NULL;
+	}
+	init_node(node, info, name, parent);
+	/* Differentiate between gcov data file nodes and directory nodes. */
+	if (info) {
+		node->dentry = debugfs_create_file(deskew(node->name), 0600,
+					parent->dentry, node, &gcov_data_fops);
+	} else
+		node->dentry = debugfs_create_dir(node->name, parent->dentry);
+	if (!node->dentry) {
+		pr_warning("could not create file\n");
+		kfree(node);
+		return NULL;
+	}
+	if (info)
+		add_links(node, parent->dentry);
+	list_add(&node->list, &parent->children);
+	list_add(&node->all, &all_head);
+
+	return node;
+}
+
+/* Remove symbolic links associated with node. */
+static void remove_links(struct gcov_node *node)
+{
+	int i;
+
+	if (!node->links)
+		return;
+	for (i = 0; gcov_link[i].ext; i++)
+		debugfs_remove(node->links[i]);
+	kfree(node->links);
+	node->links = NULL;
+}
+
+/*
+ * Remove node from all lists and debugfs and release associated resources.
+ * Needs to be called with node_lock held.
+ */
+static void release_node(struct gcov_node *node)
+{
+	list_del(&node->list);
+	list_del(&node->all);
+	debugfs_remove(node->dentry);
+	remove_links(node);
+	if (node->ghost)
+		gcov_info_free(node->ghost);
+	kfree(node);
+}
+
+/* Release node and empty parents. Needs to be called with node_lock held. */
+static void remove_node(struct gcov_node *node)
+{
+	struct gcov_node *parent;
+
+	while ((node != &root_node) && list_empty(&node->children)) {
+		parent = node->parent;
+		release_node(node);
+		node = parent;
+	}
+}
+
+/*
+ * Find child node with given basename. Needs to be called with node_lock
+ * held.
+ */
+static struct gcov_node *get_child_by_name(struct gcov_node *parent,
+					   const char *name)
+{
+	struct gcov_node *node;
+
+	list_for_each_entry(node, &parent->children, list) {
+		if (strcmp(node->name, name) == 0)
+			return node;
+	}
+
+	return NULL;
+}
+
+/*
+ * write() implementation for reset file. Reset all profiling data to zero
+ * and remove ghost nodes.
+ */
+static ssize_t reset_write(struct file *file, const char __user *addr,
+			   size_t len, loff_t *pos)
+{
+	struct gcov_node *node;
+
+	mutex_lock(&node_lock);
+restart:
+	list_for_each_entry(node, &all_head, all) {
+		if (node->info)
+			gcov_info_reset(node->info);
+		else if (list_empty(&node->children)) {
+			remove_node(node);
+			/* Several nodes may have gone - restart loop. */
+			goto restart;
+		}
+	}
+	mutex_unlock(&node_lock);
+
+	return len;
+}
+
+/* read() implementation for reset file. Unused. */
+static ssize_t reset_read(struct file *file, char __user *addr, size_t len,
+			  loff_t *pos)
+{
+	/* Allow read operation so that a recursive copy won't fail. */
+	return 0;
+}
+
+static const struct file_operations gcov_reset_fops = {
+	.write	= reset_write,
+	.read	= reset_read,
+};
+
+/*
+ * Create a node for a given profiling data set and add it to all lists and
+ * debugfs. Needs to be called with node_lock held.
+ */
+static void add_node(struct gcov_info *info)
+{
+	char *filename;
+	char *curr;
+	char *next;
+	struct gcov_node *parent;
+	struct gcov_node *node;
+
+	filename = kstrdup(info->filename, GFP_KERNEL);
+	if (!filename)
+		return;
+	parent = &root_node;
+	/* Create directory nodes along the path. */
+	for (curr = filename; (next = strchr(curr, '/')); curr = next + 1) {
+		if (curr == next)
+			continue;
+		*next = 0;
+		if (strcmp(curr, ".") == 0)
+			continue;
+		if (strcmp(curr, "..") == 0) {
+			if (!parent->parent)
+				goto err_remove;
+			parent = parent->parent;
+			continue;
+		}
+		node = get_child_by_name(parent, curr);
+		if (!node) {
+			node = new_node(parent, NULL, curr);
+			if (!node)
+				goto err_remove;
+		}
+		parent = node;
+	}
+	/* Create file node. */
+	node = new_node(parent, info, curr);
+	if (!node)
+		goto err_remove;
+out:
+	kfree(filename);
+	return;
+
+err_remove:
+	remove_node(parent);
+	goto out;
+}
+
+/*
+ * The profiling data set associated with this node is being unloaded. Store a
+ * copy of the profiling data and turn this node into a "ghost".
+ */
+static int ghost_node(struct gcov_node *node)
+{
+	node->ghost = gcov_info_dup(node->info);
+	if (!node->ghost) {
+		pr_warning("could not save data for '%s' (out of memory)\n",
+			   node->info->filename);
+		return -ENOMEM;
+	}
+	node->info = NULL;
+
+	return 0;
+}
+
+/*
+ * Profiling data for this node has been loaded again. Add profiling data
+ * from previous instantiation and turn this node into a regular node.
+ */
+static void revive_node(struct gcov_node *node, struct gcov_info *info)
+{
+	if (gcov_info_is_compatible(node->ghost, info))
+		gcov_info_add(info, node->ghost);
+	else {
+		pr_warning("discarding saved data for '%s' (version changed)\n",
+			   info->filename);
+	}
+	gcov_info_free(node->ghost);
+	node->ghost = NULL;
+	node->info = info;
+}
+
+/*
+ * Callback to create/remove profiling files when code compiled with
+ * -fprofile-arcs is loaded/unloaded.
+ */
+void gcov_event(enum gcov_action action, struct gcov_info *info)
+{
+	struct gcov_node *node;
+
+	mutex_lock(&node_lock);
+	node = get_node_by_name(info->filename);
+	switch (action) {
+	case GCOV_ADD:
+		/* Add new node or revive ghost. */
+		if (!node) {
+			add_node(info);
+			break;
+		}
+		if (gcov_persist)
+			revive_node(node, info);
+		else {
+			pr_warning("could not add '%s' (already exists)\n",
+				   info->filename);
+		}
+		break;
+	case GCOV_REMOVE:
+		/* Remove node or turn into ghost. */
+		if (!node) {
+			pr_warning("could not remove '%s' (not found)\n",
+				   info->filename);
+			break;
+		}
+		if (gcov_persist) {
+			if (!ghost_node(node))
+				break;
+		}
+		remove_node(node);
+		break;
+	}
+	mutex_unlock(&node_lock);
+}
+
+/* Create debugfs entries. */
+static __init int gcov_fs_init(void)
+{
+	int rc = -EIO;
+
+	init_node(&root_node, NULL, NULL, NULL);
+	/*
+	 * /sys/kernel/debug/gcov will be parent for the reset control file
+	 * and all profiling files.
+	 */
+	root_node.dentry = debugfs_create_dir("gcov", NULL);
+	if (!root_node.dentry)
+		goto err_remove;
+	/*
+	 * Create reset file which resets all profiling counts when written
+	 * to.
+	 */
+	reset_dentry = debugfs_create_file("reset", 0600, root_node.dentry,
+					   NULL, &gcov_reset_fops);
+	if (!reset_dentry)
+		goto err_remove;
+	/* Replay previous events to get our fs hierarchy up-to-date. */
+	gcov_enable_events();
+	return 0;
+
+err_remove:
+	pr_err("init failed\n");
+	if (root_node.dentry)
+		debugfs_remove(root_node.dentry);
+
+	return rc;
+}
+device_initcall(gcov_fs_init);
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
new file mode 100644
index 00000000000..ae5bb426003
--- /dev/null
+++ b/kernel/gcov/gcc_3_4.c
@@ -0,0 +1,447 @@
+/*
+ *  This code provides functions to handle gcc's profiling data format
+ *  introduced with gcc 3.4. Future versions of gcc may change the gcov
+ *  format (as happened before), so all format-specific information needs
+ *  to be kept modular and easily exchangeable.
+ *
+ *  This file is based on gcc-internal definitions. Functions and data
+ *  structures are defined to be compatible with gcc counterparts.
+ *  For a better understanding, refer to gcc source: gcc/gcov-io.h.
+ *
+ *    Copyright IBM Corp. 2009
+ *    Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ *    Uses gcc-internal data definitions.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include "gcov.h"
+
+/* Symbolic links to be created for each profiling data file. */
+const struct gcov_link gcov_link[] = {
+	{ OBJ_TREE, "gcno" },	/* Link to .gcno file in $(objtree). */
+	{ 0, NULL},
+};
+
+/*
+ * Determine whether a counter is active. Based on gcc magic. Doesn't change
+ * at run-time.
+ */
+static int counter_active(struct gcov_info *info, unsigned int type)
+{
+	return (1 << type) & info->ctr_mask;
+}
+
+/* Determine number of active counters. Based on gcc magic. */
+static unsigned int num_counter_active(struct gcov_info *info)
+{
+	unsigned int i;
+	unsigned int result = 0;
+
+	for (i = 0; i < GCOV_COUNTERS; i++) {
+		if (counter_active(info, i))
+			result++;
+	}
+	return result;
+}
+
+/**
+ * gcov_info_reset - reset profiling data to zero
+ * @info: profiling data set
+ */
+void gcov_info_reset(struct gcov_info *info)
+{
+	unsigned int active = num_counter_active(info);
+	unsigned int i;
+
+	for (i = 0; i < active; i++) {
+		memset(info->counts[i].values, 0,
+		       info->counts[i].num * sizeof(gcov_type));
+	}
+}
+
+/**
+ * gcov_info_is_compatible - check if profiling data can be added
+ * @info1: first profiling data set
+ * @info2: second profiling data set
+ *
+ * Returns non-zero if profiling data can be added, zero otherwise.
+ */
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
+{
+	return (info1->stamp == info2->stamp);
+}
+
+/**
+ * gcov_info_add - add up profiling data
+ * @dest: profiling data set to which data is added
+ * @source: profiling data set which is added
+ *
+ * Adds profiling counts of @source to @dest.
+ */
+void gcov_info_add(struct gcov_info *dest, struct gcov_info *source)
+{
+	unsigned int i;
+	unsigned int j;
+
+	for (i = 0; i < num_counter_active(dest); i++) {
+		for (j = 0; j < dest->counts[i].num; j++) {
+			dest->counts[i].values[j] +=
+				source->counts[i].values[j];
+		}
+	}
+}
+
+/* Get size of function info entry. Based on gcc magic. */
+static size_t get_fn_size(struct gcov_info *info)
+{
+	size_t size;
+
+	size = sizeof(struct gcov_fn_info) + num_counter_active(info) *
+	       sizeof(unsigned int);
+	if (__alignof__(struct gcov_fn_info) > sizeof(unsigned int))
+		size = ALIGN(size, __alignof__(struct gcov_fn_info));
+	return size;
+}
+
+/* Get address of function info entry. Based on gcc magic. */
+static struct gcov_fn_info *get_fn_info(struct gcov_info *info, unsigned int fn)
+{
+	return (struct gcov_fn_info *)
+		((char *) info->functions + fn * get_fn_size(info));
+}
+
+/**
+ * gcov_info_dup - duplicate profiling data set
+ * @info: profiling data set to duplicate
+ *
+ * Return newly allocated duplicate on success, %NULL on error.
+ */
+struct gcov_info *gcov_info_dup(struct gcov_info *info)
+{
+	struct gcov_info *dup;
+	unsigned int i;
+	unsigned int active;
+
+	/* Duplicate gcov_info. */
+	active = num_counter_active(info);
+	dup = kzalloc(sizeof(struct gcov_info) +
+		      sizeof(struct gcov_ctr_info) * active, GFP_KERNEL);
+	if (!dup)
+		return NULL;
+	dup->version		= info->version;
+	dup->stamp		= info->stamp;
+	dup->n_functions	= info->n_functions;
+	dup->ctr_mask		= info->ctr_mask;
+	/* Duplicate filename. */
+	dup->filename		= kstrdup(info->filename, GFP_KERNEL);
+	if (!dup->filename)
+		goto err_free;
+	/* Duplicate table of functions. */
+	dup->functions = kmemdup(info->functions, info->n_functions *
+				 get_fn_size(info), GFP_KERNEL);
+	if (!dup->functions)
+		goto err_free;
+	/* Duplicate counter arrays. */
+	for (i = 0; i < active ; i++) {
+		struct gcov_ctr_info *ctr = &info->counts[i];
+		size_t size = ctr->num * sizeof(gcov_type);
+
+		dup->counts[i].num = ctr->num;
+		dup->counts[i].merge = ctr->merge;
+		dup->counts[i].values = vmalloc(size);
+		if (!dup->counts[i].values)
+			goto err_free;
+		memcpy(dup->counts[i].values, ctr->values, size);
+	}
+	return dup;
+
+err_free:
+	gcov_info_free(dup);
+	return NULL;
+}
+
+/**
+ * gcov_info_free - release memory for profiling data set duplicate
+ * @info: profiling data set duplicate to free
+ */
+void gcov_info_free(struct gcov_info *info)
+{
+	unsigned int active = num_counter_active(info);
+	unsigned int i;
+
+	for (i = 0; i < active ; i++)
+		vfree(info->counts[i].values);
+	kfree(info->functions);
+	kfree(info->filename);
+	kfree(info);
+}
+
+/**
+ * struct type_info - iterator helper array
+ * @ctr_type: counter type
+ * @offset: index of the first value of the current function for this type
+ *
+ * This array is needed to convert the in-memory data format into the in-file
+ * data format:
+ *
+ * In-memory:
+ *   for each counter type
+ *     for each function
+ *       values
+ *
+ * In-file:
+ *   for each function
+ *     for each counter type
+ *       values
+ *
+ * See gcc source gcc/gcov-io.h for more information on data organization.
+ */
+struct type_info {
+	int ctr_type;
+	unsigned int offset;
+};
+
+/**
+ * struct gcov_iterator - specifies current file position in logical records
+ * @info: associated profiling data
+ * @record: record type
+ * @function: function number
+ * @type: counter type
+ * @count: index into values array
+ * @num_types: number of counter types
+ * @type_info: helper array to get values-array offset for current function
+ */
+struct gcov_iterator {
+	struct gcov_info *info;
+
+	int record;
+	unsigned int function;
+	unsigned int type;
+	unsigned int count;
+
+	int num_types;
+	struct type_info type_info[0];
+};
+
+static struct gcov_fn_info *get_func(struct gcov_iterator *iter)
+{
+	return get_fn_info(iter->info, iter->function);
+}
+
+static struct type_info *get_type(struct gcov_iterator *iter)
+{
+	return &iter->type_info[iter->type];
+}
+
+/**
+ * gcov_iter_new - allocate and initialize profiling data iterator
+ * @info: profiling data set to be iterated
+ *
+ * Return file iterator on success, %NULL otherwise.
+ */
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
+{
+	struct gcov_iterator *iter;
+
+	iter = kzalloc(sizeof(struct gcov_iterator) +
+		       num_counter_active(info) * sizeof(struct type_info),
+		       GFP_KERNEL);
+	if (iter)
+		iter->info = info;
+
+	return iter;
+}
+
+/**
+ * gcov_iter_free - release memory for iterator
+ * @iter: file iterator to free
+ */
+void gcov_iter_free(struct gcov_iterator *iter)
+{
+	kfree(iter);
+}
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
+{
+	return iter->info;
+}
+
+/**
+ * gcov_iter_start - reset file iterator to starting position
+ * @iter: file iterator
+ */
+void gcov_iter_start(struct gcov_iterator *iter)
+{
+	int i;
+
+	iter->record = 0;
+	iter->function = 0;
+	iter->type = 0;
+	iter->count = 0;
+	iter->num_types = 0;
+	for (i = 0; i < GCOV_COUNTERS; i++) {
+		if (counter_active(iter->info, i)) {
+			iter->type_info[iter->num_types].ctr_type = i;
+			iter->type_info[iter->num_types++].offset = 0;
+		}
+	}
+}
+
+/* Mapping of logical record number to actual file content. */
+#define RECORD_FILE_MAGIC	0
+#define RECORD_GCOV_VERSION	1
+#define RECORD_TIME_STAMP	2
+#define RECORD_FUNCTION_TAG	3
+#define RECORD_FUNCTON_TAG_LEN	4
+#define RECORD_FUNCTION_IDENT	5
+#define RECORD_FUNCTION_CHECK	6
+#define RECORD_COUNT_TAG	7
+#define RECORD_COUNT_LEN	8
+#define RECORD_COUNT		9
+
+/**
+ * gcov_iter_next - advance file iterator to next logical record
+ * @iter: file iterator
+ *
+ * Return zero if new position is valid, non-zero if iterator has reached end.
+ */
+int gcov_iter_next(struct gcov_iterator *iter)
+{
+	switch (iter->record) {
+	case RECORD_FILE_MAGIC:
+	case RECORD_GCOV_VERSION:
+	case RECORD_FUNCTION_TAG:
+	case RECORD_FUNCTON_TAG_LEN:
+	case RECORD_FUNCTION_IDENT:
+	case RECORD_COUNT_TAG:
+		/* Advance to next record */
+		iter->record++;
+		break;
+	case RECORD_COUNT:
+		/* Advance to next count */
+		iter->count++;
+		/* fall through */
+	case RECORD_COUNT_LEN:
+		if (iter->count < get_func(iter)->n_ctrs[iter->type]) {
+			iter->record = 9;
+			break;
+		}
+		/* Advance to next counter type */
+		get_type(iter)->offset += iter->count;
+		iter->count = 0;
+		iter->type++;
+		/* fall through */
+	case RECORD_FUNCTION_CHECK:
+		if (iter->type < iter->num_types) {
+			iter->record = 7;
+			break;
+		}
+		/* Advance to next function */
+		iter->type = 0;
+		iter->function++;
+		/* fall through */
+	case RECORD_TIME_STAMP:
+		if (iter->function < iter->info->n_functions)
+			iter->record = 3;
+		else
+			iter->record = -1;
+		break;
+	}
+	/* Check for EOF. */
+	if (iter->record == -1)
+		return -EINVAL;
+	else
+		return 0;
+}
+
+/**
+ * seq_write_gcov_u32 - write 32 bit number in gcov format to seq_file
+ * @seq: seq_file handle
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file.
+ */
+static int seq_write_gcov_u32(struct seq_file *seq, u32 v)
+{
+	return seq_write(seq, &v, sizeof(v));
+}
+
+/**
+ * seq_write_gcov_u64 - write 64 bit number in gcov format to seq_file
+ * @seq: seq_file handle
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. 64 bit numbers are stored as two 32 bit numbers, the low part
+ * first.
+ */
+static int seq_write_gcov_u64(struct seq_file *seq, u64 v)
+{
+	u32 data[2];
+
+	data[0] = (v & 0xffffffffUL);
+	data[1] = (v >> 32);
+	return seq_write(seq, data, sizeof(data));
+}
+
+/**
+ * gcov_iter_write - write data for current pos to seq_file
+ * @iter: file iterator
+ * @seq: seq_file handle
+ *
+ * Return zero on success, non-zero otherwise.
+ */
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
+{
+	int rc = -EINVAL;
+
+	switch (iter->record) {
+	case RECORD_FILE_MAGIC:
+		rc = seq_write_gcov_u32(seq, GCOV_DATA_MAGIC);
+		break;
+	case RECORD_GCOV_VERSION:
+		rc = seq_write_gcov_u32(seq, iter->info->version);
+		break;
+	case RECORD_TIME_STAMP:
+		rc = seq_write_gcov_u32(seq, iter->info->stamp);
+		break;
+	case RECORD_FUNCTION_TAG:
+		rc = seq_write_gcov_u32(seq, GCOV_TAG_FUNCTION);
+		break;
+	case RECORD_FUNCTON_TAG_LEN:
+		rc = seq_write_gcov_u32(seq, 2);
+		break;
+	case RECORD_FUNCTION_IDENT:
+		rc = seq_write_gcov_u32(seq, get_func(iter)->ident);
+		break;
+	case RECORD_FUNCTION_CHECK:
+		rc = seq_write_gcov_u32(seq, get_func(iter)->checksum);
+		break;
+	case RECORD_COUNT_TAG:
+		rc = seq_write_gcov_u32(seq,
+			GCOV_TAG_FOR_COUNTER(get_type(iter)->ctr_type));
+		break;
+	case RECORD_COUNT_LEN:
+		rc = seq_write_gcov_u32(seq,
+				get_func(iter)->n_ctrs[iter->type] * 2);
+		break;
+	case RECORD_COUNT:
+		rc = seq_write_gcov_u64(seq,
+			iter->info->counts[iter->type].
+				values[iter->count + get_type(iter)->offset]);
+		break;
+	}
+	return rc;
+}
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
new file mode 100644
index 00000000000..060073ebf7a
--- /dev/null
+++ b/kernel/gcov/gcov.h
@@ -0,0 +1,128 @@
+/*
+ *  Profiling infrastructure declarations.
+ *
+ *  This file is based on gcc-internal definitions. Data structures are
+ *  defined to be compatible with gcc counterparts. For a better
+ *  understanding, refer to gcc source: gcc/gcov-io.h.
+ *
+ *    Copyright IBM Corp. 2009
+ *    Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+ *
+ *    Uses gcc-internal data definitions.
+ */
+
+#ifndef GCOV_H
+#define GCOV_H GCOV_H
+
+#include <linux/types.h>
+
+/*
+ * Profiling data types used for gcc 3.4 and above - these are defined by
+ * gcc and need to be kept as close to the original definition as possible to
+ * remain compatible.
+ */
+#define GCOV_COUNTERS		5
+#define GCOV_DATA_MAGIC		((unsigned int) 0x67636461)
+#define GCOV_TAG_FUNCTION	((unsigned int) 0x01000000)
+#define GCOV_TAG_COUNTER_BASE	((unsigned int) 0x01a10000)
+#define GCOV_TAG_FOR_COUNTER(count)					\
+	(GCOV_TAG_COUNTER_BASE + ((unsigned int) (count) << 17))
+
+#if BITS_PER_LONG >= 64
+typedef long gcov_type;
+#else
+typedef long long gcov_type;
+#endif
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @ident: object file-unique function identifier
+ * @checksum: function checksum
+ * @n_ctrs: number of values per counter type belonging to this function
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ */
+struct gcov_fn_info {
+	unsigned int ident;
+	unsigned int checksum;
+	unsigned int n_ctrs[0];
+};
+
+/**
+ * struct gcov_ctr_info - profiling data per counter type
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ * @merge: merge function for counter values of this type (unused)
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+	unsigned int	num;
+	gcov_type	*values;
+	void		(*merge)(gcov_type *, unsigned int);
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: time stamp
+ * @filename: name of the associated gcov data file
+ * @n_functions: number of instrumented functions
+ * @functions: function data
+ * @ctr_mask: mask specifying which counter types are active
+ * @counts: counter data per counter type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+	unsigned int			version;
+	struct gcov_info		*next;
+	unsigned int			stamp;
+	const char			*filename;
+	unsigned int			n_functions;
+	const struct gcov_fn_info	*functions;
+	unsigned int			ctr_mask;
+	struct gcov_ctr_info		counts[0];
+};
+
+/* Base interface. */
+enum gcov_action {
+	GCOV_ADD,
+	GCOV_REMOVE,
+};
+
+void gcov_event(enum gcov_action action, struct gcov_info *info);
+void gcov_enable_events(void);
+
+/* Iterator control. */
+struct seq_file;
+struct gcov_iterator;
+
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info);
+void gcov_iter_free(struct gcov_iterator *iter);
+void gcov_iter_start(struct gcov_iterator *iter);
+int gcov_iter_next(struct gcov_iterator *iter);
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq);
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter);
+
+/* gcov_info control. */
+void gcov_info_reset(struct gcov_info *info);
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2);
+void gcov_info_add(struct gcov_info *dest, struct gcov_info *source);
+struct gcov_info *gcov_info_dup(struct gcov_info *info);
+void gcov_info_free(struct gcov_info *info);
+
+struct gcov_link {
+	enum {
+		OBJ_TREE,
+		SRC_TREE,
+	} dir;
+	const char *ext;
+};
+extern const struct gcov_link gcov_link[];
+
+#endif /* GCOV_H */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b675a67c9ac..49da79ab848 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -191,6 +191,46 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 	}
 }
 
+
+/*
+ * Get the preferred target CPU for NOHZ
+ */
+static int hrtimer_get_target(int this_cpu, int pinned)
+{
+#ifdef CONFIG_NO_HZ
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
+		int preferred_cpu = get_nohz_load_balancer();
+
+		if (preferred_cpu >= 0)
+			return preferred_cpu;
+	}
+#endif
+	return this_cpu;
+}
+
+/*
+ * With HIGHRES=y we do not migrate the timer when it is expiring
+ * before the next event on the target cpu because we cannot reprogram
+ * the target cpu hardware and we would cause it to fire late.
+ *
+ * Called with cpu_base->lock of target cpu held.
+ */
+static int
+hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+	ktime_t expires;
+
+	if (!new_base->cpu_base->hres_active)
+		return 0;
+
+	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
+	return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+#else
+	return 0;
+#endif
+}
+
 /*
  * Switch the timer base to the current CPU when possible.
  */
@@ -200,16 +240,8 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 {
 	struct hrtimer_clock_base *new_base;
 	struct hrtimer_cpu_base *new_cpu_base;
-	int cpu, preferred_cpu = -1;
-
-	cpu = smp_processor_id();
-#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
-	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
-		preferred_cpu = get_nohz_load_balancer();
-		if (preferred_cpu >= 0)
-			cpu = preferred_cpu;
-	}
-#endif
+	int this_cpu = smp_processor_id();
+	int cpu = hrtimer_get_target(this_cpu, pinned);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
@@ -217,7 +249,7 @@ again:
 
 	if (base != new_base) {
 		/*
-		 * We are trying to schedule the timer on the local CPU.
+		 * We are trying to move timer to new_base.
 		 * However we can't change timer's base while it is running,
 		 * so we keep it on the same CPU. No hassle vs. reprogramming
 		 * the event source in the high resolution case. The softirq
@@ -233,38 +265,12 @@ again:
 		spin_unlock(&base->cpu_base->lock);
 		spin_lock(&new_base->cpu_base->lock);
 
-		/* Optimized away for NOHZ=n SMP=n */
-		if (cpu == preferred_cpu) {
-			/* Calculate clock monotonic expiry time */
-#ifdef CONFIG_HIGH_RES_TIMERS
-			ktime_t expires = ktime_sub(hrtimer_get_expires(timer),
-							new_base->offset);
-#else
-			ktime_t expires = hrtimer_get_expires(timer);
-#endif
-
-			/*
-			 * Get the next event on target cpu from the
-			 * clock events layer.
-			 * This covers the highres=off nohz=on case as well.
-			 */
-			ktime_t next = clockevents_get_next_event(cpu);
-
-			ktime_t delta = ktime_sub(expires, next);
-
-			/*
-			 * We do not migrate the timer when it is expiring
-			 * before the next event on the target cpu because
-			 * we cannot reprogram the target cpu hardware and
-			 * we would cause it to fire late.
-			 */
-			if (delta.tv64 < 0) {
-				cpu = smp_processor_id();
-				spin_unlock(&new_base->cpu_base->lock);
-				spin_lock(&base->cpu_base->lock);
-				timer->base = base;
-				goto again;
-			}
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			spin_unlock(&new_base->cpu_base->lock);
+			spin_lock(&base->cpu_base->lock);
+			timer->base = base;
+			goto again;
 		}
 		timer->base = new_base;
 	}
@@ -380,6 +386,8 @@ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
 	return res;
 }
 
+EXPORT_SYMBOL_GPL(ktime_add_safe);
+
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 
 static struct debug_obj_descr hrtimer_debug_descr;
@@ -1274,14 +1282,22 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	expires_next.tv64 = KTIME_MAX;
 
+	spin_lock(&cpu_base->lock);
+	/*
+	 * We set expires_next to KTIME_MAX here with cpu_base->lock
+	 * held to prevent that a timer is enqueued in our queue via
+	 * the migration code. This does not affect enqueueing of
+	 * timers which run their callback and need to be requeued on
+	 * this CPU.
+	 */
+	cpu_base->expires_next.tv64 = KTIME_MAX;
+
 	base = cpu_base->clock_base;
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		ktime_t basenow;
 		struct rb_node *node;
 
-		spin_lock(&cpu_base->lock);
-
 		basenow = ktime_add(now, base->offset);
 
 		while ((node = base->first)) {
@@ -1314,11 +1330,15 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 			__run_hrtimer(timer);
 		}
-		spin_unlock(&cpu_base->lock);
 		base++;
 	}
 
+	/*
+	 * Store the new expiry value so the migration code can verify
+	 * against it.
+	 */
 	cpu_base->expires_next = expires_next;
+	spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
 	if (expires_next.tv64 != KTIME_MAX) {
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 73468253143..e70ed5592eb 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -42,8 +42,7 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern int irq_select_affinity_usr(unsigned int irq);
 
-extern void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+extern void irq_set_thread_affinity(struct irq_desc *desc);
 
 /*
  * Debugging printout:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index aaf5c9d0577..0ec9ed83173 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -80,14 +80,22 @@ int irq_can_set_affinity(unsigned int irq)
 	return 1;
 }
 
-void
-irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+/**
+ *	irq_set_thread_affinity - Notify irq threads to adjust affinity
+ *	@desc:		irq descriptor which has affitnity changed
+ *
+ *	We just set IRQTF_AFFINITY and delegate the affinity setting
+ *	to the interrupt thread itself. We can not call
+ *	set_cpus_allowed_ptr() here as we hold desc->lock and this
+ *	code can be called from hard interrupt context.
+ */
+void irq_set_thread_affinity(struct irq_desc *desc)
 {
 	struct irqaction *action = desc->action;
 
 	while (action) {
 		if (action->thread)
-			set_cpus_allowed_ptr(action->thread, cpumask);
+			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 		action = action->next;
 	}
 }
@@ -112,7 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	if (desc->status & IRQ_MOVE_PCNTXT) {
 		if (!desc->chip->set_affinity(irq, cpumask)) {
 			cpumask_copy(desc->affinity, cpumask);
-			irq_set_thread_affinity(desc, cpumask);
+			irq_set_thread_affinity(desc);
 		}
 	}
 	else {
@@ -122,7 +130,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 #else
 	if (!desc->chip->set_affinity(irq, cpumask)) {
 		cpumask_copy(desc->affinity, cpumask);
-		irq_set_thread_affinity(desc, cpumask);
+		irq_set_thread_affinity(desc);
 	}
 #endif
 	desc->status |= IRQ_AFFINITY_SET;
@@ -176,7 +184,7 @@ int irq_select_affinity_usr(unsigned int irq)
 	spin_lock_irqsave(&desc->lock, flags);
 	ret = setup_affinity(irq, desc);
 	if (!ret)
-		irq_set_thread_affinity(desc, desc->affinity);
+		irq_set_thread_affinity(desc);
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	return ret;
@@ -443,6 +451,39 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 	return -1;
 }
 
+#ifdef CONFIG_SMP
+/*
+ * Check whether we need to change the affinity of the interrupt thread.
+ */
+static void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
+{
+	cpumask_var_t mask;
+
+	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
+		return;
+
+	/*
+	 * In case we are out of memory we set IRQTF_AFFINITY again and
+	 * try again next time
+	 */
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+		set_bit(IRQTF_AFFINITY, &action->thread_flags);
+		return;
+	}
+
+	spin_lock_irq(&desc->lock);
+	cpumask_copy(mask, desc->affinity);
+	spin_unlock_irq(&desc->lock);
+
+	set_cpus_allowed_ptr(current, mask);
+	free_cpumask_var(mask);
+}
+#else
+static inline void
+irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
+#endif
+
 /*
  * Interrupt handler thread
  */
@@ -458,6 +499,8 @@ static int irq_thread(void *data)
 
 	while (!irq_wait_for_interrupt(action)) {
 
+		irq_thread_check_affinity(desc, action);
+
 		atomic_inc(&desc->threads_active);
 
 		spin_lock_irq(&desc->lock);
@@ -564,7 +607,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		get_task_struct(t);
 		new->thread = t;
-		wake_up_process(t);
 	}
 
 	/*
@@ -647,6 +689,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 				(int)(new->flags & IRQF_TRIGGER_MASK));
 	}
 
+	new->irq = irq;
 	*old_ptr = new;
 
 	/* Reset broken irq detection when installing new handler */
@@ -664,7 +707,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	spin_unlock_irqrestore(&desc->lock, flags);
 
-	new->irq = irq;
+	/*
+	 * Strictly no need to wake it up, but hung_task complains
+	 * when no hard interrupt wakes the thread up.
+	 */
+	if (new->thread)
+		wake_up_process(new->thread);
+
 	register_irq_proc(irq, desc);
 	new->dir = NULL;
 	register_handler_proc(irq, new);
@@ -718,7 +767,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action, **action_ptr;
-	struct task_struct *irqthread;
 	unsigned long flags;
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
@@ -766,9 +814,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 			desc->chip->disable(irq);
 	}
 
-	irqthread = action->thread;
-	action->thread = NULL;
-
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	unregister_handler_proc(irq, action);
@@ -776,12 +821,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 	/* Make sure it's not being used on another CPU: */
 	synchronize_irq(irq);
 
-	if (irqthread) {
-		if (!test_bit(IRQTF_DIED, &action->thread_flags))
-			kthread_stop(irqthread);
-		put_task_struct(irqthread);
-	}
-
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
 	 * It's a shared IRQ -- the driver ought to be prepared for an IRQ
@@ -797,6 +836,13 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 		local_irq_restore(flags);
 	}
 #endif
+
+	if (action->thread) {
+		if (!test_bit(IRQTF_DIED, &action->thread_flags))
+			kthread_stop(action->thread);
+		put_task_struct(action->thread);
+	}
+
 	return action;
 }
 
@@ -856,7 +902,7 @@ EXPORT_SYMBOL(free_irq);
  *	still called in hard interrupt context and has to check
  *	whether the interrupt originates from the device. If yes it
  *	needs to disable the interrupt on the device and return
- *	IRQ_THREAD_WAKE which will wake up the handler thread and run
+ *	IRQ_WAKE_THREAD which will wake up the handler thread and run
  *	@thread_fn. This split handler design is necessary to support
  *	shared interrupts.
  *
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index cfe767ca154..fcb6c96f262 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -45,7 +45,7 @@ void move_masked_irq(int irq)
 		   < nr_cpu_ids))
 		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
 			cpumask_copy(desc->affinity, desc->pending_mask);
-			irq_set_thread_affinity(desc, desc->pending_mask);
+			irq_set_thread_affinity(desc);
 		}
 
 	cpumask_clear(desc->pending_mask);
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 2f69bee57bf..3fd30197da2 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -107,8 +107,8 @@ out_unlock:
 
 struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 {
-	/* those all static, do move them */
-	if (desc->irq < NR_IRQS_LEGACY)
+	/* those static or target node is -1, do not move them */
+	if (desc->irq < NR_IRQS_LEGACY || node == -1)
 		return desc;
 
 	if (desc->node != node)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ae1c35201cc..f336e2107f9 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1228,7 +1228,7 @@ static int __init parse_crashkernel_mem(char 			*cmdline,
 	} while (*cur++ == ',');
 
 	if (*crash_size > 0) {
-		while (*cur != ' ' && *cur != '@')
+		while (*cur && *cur != ' ' && *cur != '@')
 			cur++;
 		if (*cur == '@') {
 			cur++;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 7e95bedb2bf..a92280870e3 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -24,7 +24,6 @@
 #include <linux/unistd.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/mnt_namespace.h>
 #include <linux/completion.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
@@ -38,6 +37,8 @@
 #include <linux/suspend.h>
 #include <asm/uaccess.h>
 
+#include <trace/events/module.h>
+
 extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
@@ -109,6 +110,8 @@ int __request_module(bool wait, const char *fmt, ...)
 		return -ENOMEM;
 	}
 
+	trace_module_request(module_name, wait, _RET_IP_);
+
 	ret = call_usermodehelper(modprobe_path, argv, envp,
 			wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 	atomic_dec(&kmod_concurrent);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c0fa54b276d..ef177d653b2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -103,7 +103,7 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
 #define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 
 struct kprobe_insn_page {
-	struct hlist_node hlist;
+	struct list_head list;
 	kprobe_opcode_t *insns;		/* Page of instruction slots */
 	char slot_used[INSNS_PER_PAGE];
 	int nused;
@@ -117,7 +117,7 @@ enum kprobe_slot_state {
 };
 
 static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
-static struct hlist_head kprobe_insn_pages;
+static LIST_HEAD(kprobe_insn_pages);
 static int kprobe_garbage_slots;
 static int collect_garbage_slots(void);
 
@@ -152,10 +152,9 @@ loop_end:
 static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
  retry:
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->nused < INSNS_PER_PAGE) {
 			int i;
 			for (i = 0; i < INSNS_PER_PAGE; i++) {
@@ -189,8 +188,8 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 		kfree(kip);
 		return NULL;
 	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
+	INIT_LIST_HEAD(&kip->list);
+	list_add(&kip->list, &kprobe_insn_pages);
 	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
 	kip->slot_used[0] = SLOT_USED;
 	kip->nused = 1;
@@ -219,12 +218,8 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * so as not to have to set it up again the
 		 * next time somebody inserts a probe.
 		 */
-		hlist_del(&kip->hlist);
-		if (hlist_empty(&kprobe_insn_pages)) {
-			INIT_HLIST_NODE(&kip->hlist);
-			hlist_add_head(&kip->hlist,
-				       &kprobe_insn_pages);
-		} else {
+		if (!list_is_singular(&kprobe_insn_pages)) {
+			list_del(&kip->list);
 			module_free(NULL, kip->insns);
 			kfree(kip);
 		}
@@ -235,18 +230,13 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 
 static int __kprobes collect_garbage_slots(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos, *next;
-	int safety;
+	struct kprobe_insn_page *kip, *next;
 
 	/* Ensure no-one is preepmted on the garbages */
-	mutex_unlock(&kprobe_insn_mutex);
-	safety = check_safety();
-	mutex_lock(&kprobe_insn_mutex);
-	if (safety != 0)
+	if (check_safety())
 		return -EAGAIN;
 
-	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
+	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
 		int i;
 		if (kip->ngarbage == 0)
 			continue;
@@ -264,19 +254,17 @@ static int __kprobes collect_garbage_slots(void)
 void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
 	mutex_lock(&kprobe_insn_mutex);
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->insns <= slot &&
 		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
 			int i = (slot - kip->insns) / MAX_INSN_SIZE;
 			if (dirty) {
 				kip->slot_used[i] = SLOT_DIRTY;
 				kip->ngarbage++;
-			} else {
+			} else
 				collect_one_slot(kip, i);
-			}
 			break;
 		}
 	}
@@ -698,7 +686,7 @@ int __kprobes register_kprobe(struct kprobe *p)
 	p->addr = addr;
 
 	preempt_disable();
-	if (!__kernel_text_address((unsigned long) p->addr) ||
+	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr)) {
 		preempt_enable();
 		return -EINVAL;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 7fa44133352..eb8751aa041 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -27,7 +27,6 @@ struct kthread_create_info
 	/* Information passed to kthread() from kthreadd. */
 	int (*threadfn)(void *data);
 	void *data;
-	struct completion started;
 
 	/* Result passed back to kthread_create() from kthreadd. */
 	struct task_struct *result;
@@ -36,17 +35,13 @@ struct kthread_create_info
 	struct list_head list;
 };
 
-struct kthread_stop_info
-{
-	struct task_struct *k;
-	int err;
-	struct completion done;
+struct kthread {
+	int should_stop;
+	struct completion exited;
 };
 
-/* Thread stopping is done by setthing this var: lock serializes
- * multiple kthread_stop calls. */
-static DEFINE_MUTEX(kthread_stop_lock);
-static struct kthread_stop_info kthread_stop_info;
+#define to_kthread(tsk)	\
+	container_of((tsk)->vfork_done, struct kthread, exited)
 
 /**
  * kthread_should_stop - should this kthread return now?
@@ -57,36 +52,35 @@ static struct kthread_stop_info kthread_stop_info;
  */
 int kthread_should_stop(void)
 {
-	return (kthread_stop_info.k == current);
+	return to_kthread(current)->should_stop;
 }
 EXPORT_SYMBOL(kthread_should_stop);
 
 static int kthread(void *_create)
 {
+	/* Copy data: it's on kthread's stack */
 	struct kthread_create_info *create = _create;
-	int (*threadfn)(void *data);
-	void *data;
-	int ret = -EINTR;
+	int (*threadfn)(void *data) = create->threadfn;
+	void *data = create->data;
+	struct kthread self;
+	int ret;
 
-	/* Copy data: it's on kthread's stack */
-	threadfn = create->threadfn;
-	data = create->data;
+	self.should_stop = 0;
+	init_completion(&self.exited);
+	current->vfork_done = &self.exited;
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
-	complete(&create->started);
+	complete(&create->done);
 	schedule();
 
-	if (!kthread_should_stop())
+	ret = -EINTR;
+	if (!self.should_stop)
 		ret = threadfn(data);
 
-	/* It might have exited on its own, w/o kthread_stop.  Check. */
-	if (kthread_should_stop()) {
-		kthread_stop_info.err = ret;
-		complete(&kthread_stop_info.done);
-	}
-	return 0;
+	/* we can't just return, we must preserve "self" on stack */
+	do_exit(ret);
 }
 
 static void create_kthread(struct kthread_create_info *create)
@@ -95,11 +89,10 @@ static void create_kthread(struct kthread_create_info *create)
 
 	/* We want our own signal handler (we take no signals by default). */
 	pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
-	if (pid < 0)
+	if (pid < 0) {
 		create->result = ERR_PTR(pid);
-	else
-		wait_for_completion(&create->started);
-	complete(&create->done);
+		complete(&create->done);
+	}
 }
 
 /**
@@ -130,7 +123,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 
 	create.threadfn = threadfn;
 	create.data = data;
-	init_completion(&create.started);
 	init_completion(&create.done);
 
 	spin_lock(&kthread_create_lock);
@@ -188,40 +180,34 @@ EXPORT_SYMBOL(kthread_bind);
  * @k: thread created by kthread_create().
  *
  * Sets kthread_should_stop() for @k to return true, wakes it, and
- * waits for it to exit.  Your threadfn() must not call do_exit()
- * itself if you use this function!  This can also be called after
- * kthread_create() instead of calling wake_up_process(): the thread
- * will exit without calling threadfn().
+ * waits for it to exit. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will exit without
+ * calling threadfn().
+ *
+ * If threadfn() may call do_exit() itself, the caller must ensure
+ * task_struct can't go away.
  *
  * Returns the result of threadfn(), or %-EINTR if wake_up_process()
  * was never called.
  */
 int kthread_stop(struct task_struct *k)
 {
+	struct kthread *kthread;
 	int ret;
 
-	mutex_lock(&kthread_stop_lock);
-
-	/* It could exit after stop_info.k set, but before wake_up_process. */
-	get_task_struct(k);
-
 	trace_sched_kthread_stop(k);
+	get_task_struct(k);
 
-	/* Must init completion *before* thread sees kthread_stop_info.k */
-	init_completion(&kthread_stop_info.done);
-	smp_wmb();
+	kthread = to_kthread(k);
+	barrier(); /* it might have exited */
+	if (k->vfork_done != NULL) {
+		kthread->should_stop = 1;
+		wake_up_process(k);
+		wait_for_completion(&kthread->exited);
+	}
+	ret = k->exit_code;
 
-	/* Now set kthread_should_stop() to true, and wake it up. */
-	kthread_stop_info.k = k;
-	wake_up_process(k);
 	put_task_struct(k);
-
-	/* Once it dies, reset stop ptr, gather result and we're done. */
-	wait_for_completion(&kthread_stop_info.done);
-	kthread_stop_info.k = NULL;
-	ret = kthread_stop_info.err;
-	mutex_unlock(&kthread_stop_lock);
-
 	trace_sched_kthread_stop_ret(ret);
 
 	return ret;
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d7135aa2d2c..e94caa666db 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void)
 		    &proc_lockdep_stats_operations);
 
 #ifdef CONFIG_LOCK_STAT
-	proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations);
+	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
+		    &proc_lock_stat_operations);
 #endif
 
 	return 0;
diff --git a/kernel/module.c b/kernel/module.c
index 215aaab09e9..46580edff0c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -55,6 +55,11 @@
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/module.h>
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 #if 0
 #define DEBUGP printk
 #else
@@ -909,16 +914,18 @@ void __symbol_put(const char *symbol)
 }
 EXPORT_SYMBOL(__symbol_put);
 
+/* Note this assumes addr is a function, which it currently always is. */
 void symbol_put_addr(void *addr)
 {
 	struct module *modaddr;
+	unsigned long a = (unsigned long)dereference_function_descriptor(addr);
 
-	if (core_kernel_text((unsigned long)addr))
+	if (core_kernel_text(a))
 		return;
 
 	/* module_text_address is safe here: we're supposed to have reference
 	 * to module from symbol_get, so it can't go away. */
-	modaddr = __module_text_address((unsigned long)addr);
+	modaddr = __module_text_address(a);
 	BUG_ON(!modaddr);
 	module_put(modaddr);
 }
@@ -940,6 +947,8 @@ void module_put(struct module *module)
 	if (module) {
 		unsigned int cpu = get_cpu();
 		local_dec(__module_ref_addr(module, cpu));
+		trace_module_put(module, _RET_IP_,
+				 local_read(__module_ref_addr(module, cpu)));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1068,7 +1077,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 {
 	const unsigned long *crc;
 
-	if (!find_symbol("module_layout", NULL, &crc, true, false))
+	if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL,
+			 &crc, true, false))
 		BUG();
 	return check_version(sechdrs, versindex, "module_layout", mod, crc);
 }
@@ -1271,6 +1281,10 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect,
 	struct module_notes_attrs *notes_attrs;
 	struct bin_attribute *nattr;
 
+	/* failed to create section attributes, so can't create notes */
+	if (!mod->sect_attrs)
+		return;
+
 	/* Count notes sections and allocate structures.  */
 	notes = 0;
 	for (i = 0; i < nsect; i++)
@@ -1490,6 +1504,8 @@ static int __unlink_module(void *_mod)
 /* Free a module, remove from lists, etc (must hold module_mutex). */
 static void free_module(struct module *mod)
 {
+	trace_module_free(mod);
+
 	/* Delete from various lists */
 	stop_machine(__unlink_module, mod, NULL);
 	remove_notes_attrs(mod);
@@ -2216,6 +2232,10 @@ static noinline struct module *load_module(void __user *umod,
 	mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings,
 					    "__kcrctab_unused_gpl");
 #endif
+#ifdef CONFIG_CONSTRUCTORS
+	mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors",
+				  sizeof(*mod->ctors), &mod->num_ctors);
+#endif
 
 #ifdef CONFIG_MARKERS
 	mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers",
@@ -2353,6 +2373,8 @@ static noinline struct module *load_module(void __user *umod,
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
+	trace_module_load(mod);
+
 	/* Done! */
 	return mod;
 
@@ -2389,6 +2411,17 @@ static noinline struct module *load_module(void __user *umod,
 	goto free_hdr;
 }
 
+/* Call module constructors. */
+static void do_mod_ctors(struct module *mod)
+{
+#ifdef CONFIG_CONSTRUCTORS
+	unsigned long i;
+
+	for (i = 0; i < mod->num_ctors; i++)
+		mod->ctors[i]();
+#endif
+}
+
 /* This is where the real work happens */
 SYSCALL_DEFINE3(init_module, void __user *, umod,
 		unsigned long, len, const char __user *, uargs)
@@ -2417,6 +2450,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	blocking_notifier_call_chain(&module_notify_list,
 			MODULE_STATE_COMING, mod);
 
+	do_mod_ctors(mod);
 	/* Start the module */
 	if (mod->init != NULL)
 		ret = do_one_initcall(mod->init);
@@ -2435,9 +2469,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 		return ret;
 	}
 	if (ret > 0) {
-		printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
-				    "it should follow 0/-E convention\n"
-		       KERN_WARNING "%s: loading module anyway...\n",
+		printk(KERN_WARNING
+"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
+"%s: loading module anyway...\n",
 		       __func__, mod->name, ret,
 		       __func__);
 		dump_stack();
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 63598dca2d0..09b4ff9711b 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -26,19 +26,14 @@ static struct kmem_cache *nsproxy_cachep;
 
 struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
 
-/*
- * creates a copy of "orig" with refcount 1.
- */
-static inline struct nsproxy *clone_nsproxy(struct nsproxy *orig)
+static inline struct nsproxy *create_nsproxy(void)
 {
-	struct nsproxy *ns;
+	struct nsproxy *nsproxy;
 
-	ns = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
-	if (ns) {
-		memcpy(ns, orig, sizeof(struct nsproxy));
-		atomic_set(&ns->count, 1);
-	}
-	return ns;
+	nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
+	if (nsproxy)
+		atomic_set(&nsproxy->count, 1);
+	return nsproxy;
 }
 
 /*
@@ -52,7 +47,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	struct nsproxy *new_nsp;
 	int err;
 
-	new_nsp = clone_nsproxy(tsk->nsproxy);
+	new_nsp = create_nsproxy();
 	if (!new_nsp)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 984b3ecbd72..512ab73b0ca 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -301,6 +301,7 @@ int oops_may_print(void)
  */
 void oops_enter(void)
 {
+	tracing_off();
 	/* can't trust the integrity of the kernel anymore: */
 	debug_locks_off();
 	do_oops_enter_exit();
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 29b685f551a..d7cbc579fc8 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -42,6 +42,7 @@ static int perf_overcommit __read_mostly = 1;
 static atomic_t nr_counters __read_mostly;
 static atomic_t nr_mmap_counters __read_mostly;
 static atomic_t nr_comm_counters __read_mostly;
+static atomic_t nr_task_counters __read_mostly;
 
 /*
  * perf counter paranoia level:
@@ -49,7 +50,7 @@ static atomic_t nr_comm_counters __read_mostly;
  *  1 - disallow cpu counters to unpriv
  *  2 - disallow kernel profiling to unpriv
  */
-int sysctl_perf_counter_paranoid __read_mostly;
+int sysctl_perf_counter_paranoid __read_mostly = 1;
 
 static inline bool perf_paranoid_cpu(void)
 {
@@ -87,6 +88,7 @@ void __weak hw_perf_disable(void)		{ barrier(); }
 void __weak hw_perf_enable(void)		{ barrier(); }
 
 void __weak hw_perf_counter_setup(int cpu)	{ barrier(); }
+void __weak hw_perf_counter_setup_online(int cpu)	{ barrier(); }
 
 int __weak
 hw_perf_group_sched_in(struct perf_counter *group_leader,
@@ -124,7 +126,7 @@ void perf_enable(void)
 
 static void get_ctx(struct perf_counter_context *ctx)
 {
-	atomic_inc(&ctx->refcount);
+	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
 static void free_ctx(struct rcu_head *head)
@@ -146,6 +148,28 @@ static void put_ctx(struct perf_counter_context *ctx)
 	}
 }
 
+static void unclone_ctx(struct perf_counter_context *ctx)
+{
+	if (ctx->parent_ctx) {
+		put_ctx(ctx->parent_ctx);
+		ctx->parent_ctx = NULL;
+	}
+}
+
+/*
+ * If we inherit counters we want to return the parent counter id
+ * to userspace.
+ */
+static u64 primary_counter_id(struct perf_counter *counter)
+{
+	u64 id = counter->id;
+
+	if (counter->parent)
+		id = counter->parent->id;
+
+	return id;
+}
+
 /*
  * Get the perf_counter_context for a task and lock it.
  * This has to cope with with the fact that until it is locked,
@@ -175,6 +199,11 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
 			spin_unlock_irqrestore(&ctx->lock, *flags);
 			goto retry;
 		}
+
+		if (!atomic_inc_not_zero(&ctx->refcount)) {
+			spin_unlock_irqrestore(&ctx->lock, *flags);
+			ctx = NULL;
+		}
 	}
 	rcu_read_unlock();
 	return ctx;
@@ -193,7 +222,6 @@ static struct perf_counter_context *perf_pin_task_context(struct task_struct *ta
 	ctx = perf_lock_task_context(task, &flags);
 	if (ctx) {
 		++ctx->pin_count;
-		get_ctx(ctx);
 		spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 	return ctx;
@@ -232,6 +260,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 
 	list_add_rcu(&counter->event_entry, &ctx->event_list);
 	ctx->nr_counters++;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat++;
 }
 
 /*
@@ -246,6 +276,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 	if (list_empty(&counter->list_entry))
 		return;
 	ctx->nr_counters--;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat--;
 
 	list_del_init(&counter->list_entry);
 	list_del_rcu(&counter->event_entry);
@@ -275,6 +307,10 @@ counter_sched_out(struct perf_counter *counter,
 		return;
 
 	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	if (counter->pending_disable) {
+		counter->pending_disable = 0;
+		counter->state = PERF_COUNTER_STATE_OFF;
+	}
 	counter->tstamp_stopped = ctx->time;
 	counter->pmu->disable(counter);
 	counter->oncpu = -1;
@@ -1002,6 +1038,81 @@ static int context_equiv(struct perf_counter_context *ctx1,
 		&& !ctx1->pin_count && !ctx2->pin_count;
 }
 
+static void __perf_counter_read(void *counter);
+
+static void __perf_counter_sync_stat(struct perf_counter *counter,
+				     struct perf_counter *next_counter)
+{
+	u64 value;
+
+	if (!counter->attr.inherit_stat)
+		return;
+
+	/*
+	 * Update the counter value, we cannot use perf_counter_read()
+	 * because we're in the middle of a context switch and have IRQs
+	 * disabled, which upsets smp_call_function_single(), however
+	 * we know the counter must be on the current CPU, therefore we
+	 * don't need to use it.
+	 */
+	switch (counter->state) {
+	case PERF_COUNTER_STATE_ACTIVE:
+		__perf_counter_read(counter);
+		break;
+
+	case PERF_COUNTER_STATE_INACTIVE:
+		update_counter_times(counter);
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * In order to keep per-task stats reliable we need to flip the counter
+	 * values when we flip the contexts.
+	 */
+	value = atomic64_read(&next_counter->count);
+	value = atomic64_xchg(&counter->count, value);
+	atomic64_set(&next_counter->count, value);
+
+	swap(counter->total_time_enabled, next_counter->total_time_enabled);
+	swap(counter->total_time_running, next_counter->total_time_running);
+
+	/*
+	 * Since we swizzled the values, update the user visible data too.
+	 */
+	perf_counter_update_userpage(counter);
+	perf_counter_update_userpage(next_counter);
+}
+
+#define list_next_entry(pos, member) \
+	list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+				   struct perf_counter_context *next_ctx)
+{
+	struct perf_counter *counter, *next_counter;
+
+	if (!ctx->nr_stat)
+		return;
+
+	counter = list_first_entry(&ctx->event_list,
+				   struct perf_counter, event_entry);
+
+	next_counter = list_first_entry(&next_ctx->event_list,
+					struct perf_counter, event_entry);
+
+	while (&counter->event_entry != &ctx->event_list &&
+	       &next_counter->event_entry != &next_ctx->event_list) {
+
+		__perf_counter_sync_stat(counter, next_counter);
+
+		counter = list_next_entry(counter, event_entry);
+		next_counter = list_next_entry(next_counter, event_entry);
+	}
+}
+
 /*
  * Called from scheduler to remove the counters of the current task,
  * with interrupts disabled.
@@ -1057,6 +1168,8 @@ void perf_counter_task_sched_out(struct task_struct *task,
 			ctx->task = next;
 			next_ctx->task = task;
 			do_switch = 0;
+
+			perf_counter_sync_stat(ctx, next_ctx);
 		}
 		spin_unlock(&next_ctx->lock);
 		spin_unlock(&ctx->lock);
@@ -1203,7 +1316,6 @@ static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
 #define MAX_INTERRUPTS (~0ULL)
 
 static void perf_log_throttle(struct perf_counter *counter, int enable);
-static void perf_log_period(struct perf_counter *counter, u64 period);
 
 static void perf_adjust_period(struct perf_counter *counter, u64 events)
 {
@@ -1222,8 +1334,6 @@ static void perf_adjust_period(struct perf_counter *counter, u64 events)
 	if (!sample_period)
 		sample_period = 1;
 
-	perf_log_period(counter, sample_period);
-
 	hwc->sample_period = sample_period;
 }
 
@@ -1283,7 +1393,7 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
 		if (!interrupts) {
 			perf_disable();
 			counter->pmu->disable(counter);
-			atomic_set(&hwc->period_left, 0);
+			atomic64_set(&hwc->period_left, 0);
 			counter->pmu->enable(counter);
 			perf_enable();
 		}
@@ -1344,14 +1454,70 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
 }
 
 /*
+ * Enable all of a task's counters that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_counter_enable_on_exec(struct task_struct *task)
+{
+	struct perf_counter_context *ctx;
+	struct perf_counter *counter;
+	unsigned long flags;
+	int enabled = 0;
+
+	local_irq_save(flags);
+	ctx = task->perf_counter_ctxp;
+	if (!ctx || !ctx->nr_counters)
+		goto out;
+
+	__perf_counter_task_sched_out(ctx);
+
+	spin_lock(&ctx->lock);
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (!counter->attr.enable_on_exec)
+			continue;
+		counter->attr.enable_on_exec = 0;
+		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+			continue;
+		counter->state = PERF_COUNTER_STATE_INACTIVE;
+		counter->tstamp_enabled =
+			ctx->time - counter->total_time_enabled;
+		enabled = 1;
+	}
+
+	/*
+	 * Unclone this context if we enabled any counter.
+	 */
+	if (enabled)
+		unclone_ctx(ctx);
+
+	spin_unlock(&ctx->lock);
+
+	perf_counter_task_sched_in(task, smp_processor_id());
+ out:
+	local_irq_restore(flags);
+}
+
+/*
  * Cross CPU call to read the hardware counter
  */
-static void __read(void *info)
+static void __perf_counter_read(void *info)
 {
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_counter *counter = info;
 	struct perf_counter_context *ctx = counter->ctx;
 	unsigned long flags;
 
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu.  If not it has been
+	 * scheduled out before the smp call arrived.  In that case
+	 * counter->count would have been updated to a recent sample
+	 * when the counter was scheduled out.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
 	local_irq_save(flags);
 	if (ctx->is_active)
 		update_context_time(ctx);
@@ -1368,7 +1534,7 @@ static u64 perf_counter_read(struct perf_counter *counter)
 	 */
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
 		smp_call_function_single(counter->oncpu,
-					 __read, counter, 1);
+					 __perf_counter_read, counter, 1);
 	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
 		update_counter_times(counter);
 	}
@@ -1394,7 +1560,6 @@ __perf_counter_init_context(struct perf_counter_context *ctx,
 
 static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
 {
-	struct perf_counter_context *parent_ctx;
 	struct perf_counter_context *ctx;
 	struct perf_cpu_context *cpuctx;
 	struct task_struct *task;
@@ -1454,16 +1619,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
  retry:
 	ctx = perf_lock_task_context(task, &flags);
 	if (ctx) {
-		parent_ctx = ctx->parent_ctx;
-		if (parent_ctx) {
-			put_ctx(parent_ctx);
-			ctx->parent_ctx = NULL;		/* no longer a clone */
-		}
-		/*
-		 * Get an extra reference before dropping the lock so that
-		 * this context won't get freed if the task exits.
-		 */
-		get_ctx(ctx);
+		unclone_ctx(ctx);
 		spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
@@ -1509,11 +1665,15 @@ static void free_counter(struct perf_counter *counter)
 {
 	perf_pending_sync(counter);
 
-	atomic_dec(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_dec(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_dec(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_dec(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_dec(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_dec(&nr_comm_counters);
+		if (counter->attr.task)
+			atomic_dec(&nr_task_counters);
+	}
 
 	if (counter->destroy)
 		counter->destroy(counter);
@@ -1547,14 +1707,133 @@ static int perf_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int perf_counter_read_size(struct perf_counter *counter)
+{
+	int entry = sizeof(u64); /* value */
+	int size = 0;
+	int nr = 1;
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		size += sizeof(u64);
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		size += sizeof(u64);
+
+	if (counter->attr.read_format & PERF_FORMAT_ID)
+		entry += sizeof(u64);
+
+	if (counter->attr.read_format & PERF_FORMAT_GROUP) {
+		nr += counter->group_leader->nr_siblings;
+		size += sizeof(u64);
+	}
+
+	size += entry * nr;
+
+	return size;
+}
+
+static u64 perf_counter_read_value(struct perf_counter *counter)
+{
+	struct perf_counter *child;
+	u64 total = 0;
+
+	total += perf_counter_read(counter);
+	list_for_each_entry(child, &counter->child_list, child_list)
+		total += perf_counter_read(child);
+
+	return total;
+}
+
+static int perf_counter_read_entry(struct perf_counter *counter,
+				   u64 read_format, char __user *buf)
+{
+	int n = 0, count = 0;
+	u64 values[2];
+
+	values[n++] = perf_counter_read_value(counter);
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_counter_id(counter);
+
+	count = n * sizeof(u64);
+
+	if (copy_to_user(buf, values, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static int perf_counter_read_group(struct perf_counter *counter,
+				   u64 read_format, char __user *buf)
+{
+	struct perf_counter *leader = counter->group_leader, *sub;
+	int n = 0, size = 0, err = -EFAULT;
+	u64 values[3];
+
+	values[n++] = 1 + leader->nr_siblings;
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = leader->total_time_enabled +
+			atomic64_read(&leader->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = leader->total_time_running +
+			atomic64_read(&leader->child_total_time_running);
+	}
+
+	size = n * sizeof(u64);
+
+	if (copy_to_user(buf, values, size))
+		return -EFAULT;
+
+	err = perf_counter_read_entry(leader, read_format, buf + size);
+	if (err < 0)
+		return err;
+
+	size += err;
+
+	list_for_each_entry(sub, &leader->sibling_list, list_entry) {
+		err = perf_counter_read_entry(sub, read_format,
+				buf + size);
+		if (err < 0)
+			return err;
+
+		size += err;
+	}
+
+	return size;
+}
+
+static int perf_counter_read_one(struct perf_counter *counter,
+				 u64 read_format, char __user *buf)
+{
+	u64 values[4];
+	int n = 0;
+
+	values[n++] = perf_counter_read_value(counter);
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+	}
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_counter_id(counter);
+
+	if (copy_to_user(buf, values, n * sizeof(u64)))
+		return -EFAULT;
+
+	return n * sizeof(u64);
+}
+
 /*
  * Read the performance counter - simple non blocking version for now
  */
 static ssize_t
 perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
 {
-	u64 values[3];
-	int n;
+	u64 read_format = counter->attr.read_format;
+	int ret;
 
 	/*
 	 * Return end-of-file for a read on a counter that is in
@@ -1564,28 +1843,18 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
 	if (counter->state == PERF_COUNTER_STATE_ERROR)
 		return 0;
 
+	if (count < perf_counter_read_size(counter))
+		return -ENOSPC;
+
 	WARN_ON_ONCE(counter->ctx->parent_ctx);
 	mutex_lock(&counter->child_mutex);
-	values[0] = perf_counter_read(counter);
-	n = 1;
-	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		values[n++] = counter->total_time_enabled +
-			atomic64_read(&counter->child_total_time_enabled);
-	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		values[n++] = counter->total_time_running +
-			atomic64_read(&counter->child_total_time_running);
-	if (counter->attr.read_format & PERF_FORMAT_ID)
-		values[n++] = counter->id;
+	if (read_format & PERF_FORMAT_GROUP)
+		ret = perf_counter_read_group(counter, read_format, buf);
+	else
+		ret = perf_counter_read_one(counter, read_format, buf);
 	mutex_unlock(&counter->child_mutex);
 
-	if (count < n * sizeof(u64))
-		return -EINVAL;
-	count = n * sizeof(u64);
-
-	if (copy_to_user(buf, values, count))
-		return -EFAULT;
-
-	return count;
+	return ret;
 }
 
 static ssize_t
@@ -1620,22 +1889,6 @@ static void perf_counter_reset(struct perf_counter *counter)
 	perf_counter_update_userpage(counter);
 }
 
-static void perf_counter_for_each_sibling(struct perf_counter *counter,
-					  void (*func)(struct perf_counter *))
-{
-	struct perf_counter_context *ctx = counter->ctx;
-	struct perf_counter *sibling;
-
-	WARN_ON_ONCE(ctx->parent_ctx);
-	mutex_lock(&ctx->mutex);
-	counter = counter->group_leader;
-
-	func(counter);
-	list_for_each_entry(sibling, &counter->sibling_list, list_entry)
-		func(sibling);
-	mutex_unlock(&ctx->mutex);
-}
-
 /*
  * Holding the top-level counter's child_mutex means that any
  * descendant process that has inherited this counter will block
@@ -1658,14 +1911,18 @@ static void perf_counter_for_each_child(struct perf_counter *counter,
 static void perf_counter_for_each(struct perf_counter *counter,
 				  void (*func)(struct perf_counter *))
 {
-	struct perf_counter *child;
+	struct perf_counter_context *ctx = counter->ctx;
+	struct perf_counter *sibling;
 
-	WARN_ON_ONCE(counter->ctx->parent_ctx);
-	mutex_lock(&counter->child_mutex);
-	perf_counter_for_each_sibling(counter, func);
-	list_for_each_entry(child, &counter->child_list, child_list)
-		perf_counter_for_each_sibling(child, func);
-	mutex_unlock(&counter->child_mutex);
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	counter = counter->group_leader;
+
+	perf_counter_for_each_child(counter, func);
+	func(counter);
+	list_for_each_entry(sibling, &counter->sibling_list, list_entry)
+		perf_counter_for_each_child(counter, func);
+	mutex_unlock(&ctx->mutex);
 }
 
 static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
@@ -1694,8 +1951,6 @@ static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
 
 		counter->attr.sample_freq = value;
 	} else {
-		perf_log_period(counter, value);
-
 		counter->attr.sample_period = value;
 		counter->hw.sample_period = value;
 	}
@@ -1764,6 +2019,18 @@ int perf_counter_task_disable(void)
 	return 0;
 }
 
+#ifndef PERF_COUNTER_INDEX_OFFSET
+# define PERF_COUNTER_INDEX_OFFSET 0
+#endif
+
+static int perf_counter_index(struct perf_counter *counter)
+{
+	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+		return 0;
+
+	return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
+}
+
 /*
  * Callers need to ensure there can be no nesting of this function, otherwise
  * the seqlock logic goes bad. We can not serialize this because the arch
@@ -1788,11 +2055,17 @@ void perf_counter_update_userpage(struct perf_counter *counter)
 	preempt_disable();
 	++userpg->lock;
 	barrier();
-	userpg->index = counter->hw.idx;
+	userpg->index = perf_counter_index(counter);
 	userpg->offset = atomic64_read(&counter->count);
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
 		userpg->offset -= atomic64_read(&counter->hw.prev_count);
 
+	userpg->time_enabled = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+
+	userpg->time_running = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+
 	barrier();
 	++userpg->lock;
 	preempt_enable();
@@ -1806,6 +2079,12 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct perf_mmap_data *data;
 	int ret = VM_FAULT_SIGBUS;
 
+	if (vmf->flags & FAULT_FLAG_MKWRITE) {
+		if (vmf->pgoff == 0)
+			ret = 0;
+		return ret;
+	}
+
 	rcu_read_lock();
 	data = rcu_dereference(counter->data);
 	if (!data)
@@ -1819,9 +2098,16 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		if ((unsigned)nr > data->nr_pages)
 			goto unlock;
 
+		if (vmf->flags & FAULT_FLAG_WRITE)
+			goto unlock;
+
 		vmf->page = virt_to_page(data->data_pages[nr]);
 	}
+
 	get_page(vmf->page);
+	vmf->page->mapping = vma->vm_file->f_mapping;
+	vmf->page->index   = vmf->pgoff;
+
 	ret = 0;
 unlock:
 	rcu_read_unlock();
@@ -1874,6 +2160,14 @@ fail:
 	return -ENOMEM;
 }
 
+static void perf_mmap_free_page(unsigned long addr)
+{
+	struct page *page = virt_to_page((void *)addr);
+
+	page->mapping = NULL;
+	__free_page(page);
+}
+
 static void __perf_mmap_data_free(struct rcu_head *rcu_head)
 {
 	struct perf_mmap_data *data;
@@ -1881,9 +2175,10 @@ static void __perf_mmap_data_free(struct rcu_head *rcu_head)
 
 	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
 
-	free_page((unsigned long)data->user_page);
+	perf_mmap_free_page((unsigned long)data->user_page);
 	for (i = 0; i < data->nr_pages; i++)
-		free_page((unsigned long)data->data_pages[i]);
+		perf_mmap_free_page((unsigned long)data->data_pages[i]);
+
 	kfree(data);
 }
 
@@ -1920,9 +2215,10 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 }
 
 static struct vm_operations_struct perf_mmap_vmops = {
-	.open  = perf_mmap_open,
-	.close = perf_mmap_close,
-	.fault = perf_mmap_fault,
+	.open		= perf_mmap_open,
+	.close		= perf_mmap_close,
+	.fault		= perf_mmap_fault,
+	.page_mkwrite	= perf_mmap_fault,
 };
 
 static int perf_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1936,7 +2232,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	long user_extra, extra;
 	int ret = 0;
 
-	if (!(vma->vm_flags & VM_SHARED) || (vma->vm_flags & VM_WRITE))
+	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
 	vma_size = vma->vm_end - vma->vm_start;
@@ -1995,10 +2291,12 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	atomic_long_add(user_extra, &user->locked_vm);
 	vma->vm_mm->locked_vm += extra;
 	counter->data->nr_locked = extra;
+	if (vma->vm_flags & VM_WRITE)
+		counter->data->writable = 1;
+
 unlock:
 	mutex_unlock(&counter->mmap_mutex);
 
-	vma->vm_flags &= ~VM_MAYWRITE;
 	vma->vm_flags |= VM_RESERVED;
 	vma->vm_ops = &perf_mmap_vmops;
 
@@ -2064,7 +2362,7 @@ static void perf_pending_counter(struct perf_pending_entry *entry)
 
 	if (counter->pending_disable) {
 		counter->pending_disable = 0;
-		perf_counter_disable(counter);
+		__perf_counter_disable(counter);
 	}
 
 	if (counter->pending_wakeup) {
@@ -2175,11 +2473,38 @@ struct perf_output_handle {
 	unsigned long		head;
 	unsigned long		offset;
 	int			nmi;
-	int			overflow;
+	int			sample;
 	int			locked;
 	unsigned long		flags;
 };
 
+static bool perf_output_space(struct perf_mmap_data *data,
+			      unsigned int offset, unsigned int head)
+{
+	unsigned long tail;
+	unsigned long mask;
+
+	if (!data->writable)
+		return true;
+
+	mask = (data->nr_pages << PAGE_SHIFT) - 1;
+	/*
+	 * Userspace could choose to issue a mb() before updating the tail
+	 * pointer. So that all reads will be completed before the write is
+	 * issued.
+	 */
+	tail = ACCESS_ONCE(data->user_page->data_tail);
+	smp_rmb();
+
+	offset = (offset - tail) & mask;
+	head   = (head   - tail) & mask;
+
+	if ((int)(head - offset) < 0)
+		return false;
+
+	return true;
+}
+
 static void perf_output_wakeup(struct perf_output_handle *handle)
 {
 	atomic_set(&handle->data->poll, POLL_IN);
@@ -2270,12 +2595,57 @@ out:
 	local_irq_restore(handle->flags);
 }
 
+static void perf_output_copy(struct perf_output_handle *handle,
+			     const void *buf, unsigned int len)
+{
+	unsigned int pages_mask;
+	unsigned int offset;
+	unsigned int size;
+	void **pages;
+
+	offset		= handle->offset;
+	pages_mask	= handle->data->nr_pages - 1;
+	pages		= handle->data->data_pages;
+
+	do {
+		unsigned int page_offset;
+		int nr;
+
+		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
+		page_offset = offset & (PAGE_SIZE - 1);
+		size	    = min_t(unsigned int, PAGE_SIZE - page_offset, len);
+
+		memcpy(pages[nr] + page_offset, buf, size);
+
+		len	    -= size;
+		buf	    += size;
+		offset	    += size;
+	} while (len);
+
+	handle->offset = offset;
+
+	/*
+	 * Check we didn't copy past our reservation window, taking the
+	 * possible unsigned int wrap into account.
+	 */
+	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
+}
+
+#define perf_output_put(handle, x) \
+	perf_output_copy((handle), &(x), sizeof(x))
+
 static int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_counter *counter, unsigned int size,
-			     int nmi, int overflow)
+			     int nmi, int sample)
 {
 	struct perf_mmap_data *data;
 	unsigned int offset, head;
+	int have_lost;
+	struct {
+		struct perf_event_header header;
+		u64			 id;
+		u64			 lost;
+	} lost_event;
 
 	/*
 	 * For inherited counters we send all the output towards the parent.
@@ -2288,19 +2658,25 @@ static int perf_output_begin(struct perf_output_handle *handle,
 	if (!data)
 		goto out;
 
-	handle->data	 = data;
-	handle->counter	 = counter;
-	handle->nmi	 = nmi;
-	handle->overflow = overflow;
+	handle->data	= data;
+	handle->counter	= counter;
+	handle->nmi	= nmi;
+	handle->sample	= sample;
 
 	if (!data->nr_pages)
 		goto fail;
 
+	have_lost = atomic_read(&data->lost);
+	if (have_lost)
+		size += sizeof(lost_event);
+
 	perf_output_lock(handle);
 
 	do {
 		offset = head = atomic_long_read(&data->head);
 		head += size;
+		if (unlikely(!perf_output_space(data, offset, head)))
+			goto fail;
 	} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);
 
 	handle->offset	= offset;
@@ -2309,55 +2685,27 @@ static int perf_output_begin(struct perf_output_handle *handle,
 	if ((offset >> PAGE_SHIFT) != (head >> PAGE_SHIFT))
 		atomic_set(&data->wakeup, 1);
 
+	if (have_lost) {
+		lost_event.header.type = PERF_EVENT_LOST;
+		lost_event.header.misc = 0;
+		lost_event.header.size = sizeof(lost_event);
+		lost_event.id          = counter->id;
+		lost_event.lost        = atomic_xchg(&data->lost, 0);
+
+		perf_output_put(handle, lost_event);
+	}
+
 	return 0;
 
 fail:
-	perf_output_wakeup(handle);
+	atomic_inc(&data->lost);
+	perf_output_unlock(handle);
 out:
 	rcu_read_unlock();
 
 	return -ENOSPC;
 }
 
-static void perf_output_copy(struct perf_output_handle *handle,
-			     const void *buf, unsigned int len)
-{
-	unsigned int pages_mask;
-	unsigned int offset;
-	unsigned int size;
-	void **pages;
-
-	offset		= handle->offset;
-	pages_mask	= handle->data->nr_pages - 1;
-	pages		= handle->data->data_pages;
-
-	do {
-		unsigned int page_offset;
-		int nr;
-
-		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
-		page_offset = offset & (PAGE_SIZE - 1);
-		size	    = min_t(unsigned int, PAGE_SIZE - page_offset, len);
-
-		memcpy(pages[nr] + page_offset, buf, size);
-
-		len	    -= size;
-		buf	    += size;
-		offset	    += size;
-	} while (len);
-
-	handle->offset = offset;
-
-	/*
-	 * Check we didn't copy past our reservation window, taking the
-	 * possible unsigned int wrap into account.
-	 */
-	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
-}
-
-#define perf_output_put(handle, x) \
-	perf_output_copy((handle), &(x), sizeof(x))
-
 static void perf_output_end(struct perf_output_handle *handle)
 {
 	struct perf_counter *counter = handle->counter;
@@ -2365,7 +2713,7 @@ static void perf_output_end(struct perf_output_handle *handle)
 
 	int wakeup_events = counter->attr.wakeup_events;
 
-	if (handle->overflow && wakeup_events) {
+	if (handle->sample && wakeup_events) {
 		int events = atomic_inc_return(&data->events);
 		if (events >= wakeup_events) {
 			atomic_sub(wakeup_events, &data->events);
@@ -2399,7 +2747,80 @@ static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p)
 	return task_pid_nr_ns(p, counter->ns);
 }
 
-static void perf_counter_output(struct perf_counter *counter, int nmi,
+static void perf_output_read_one(struct perf_output_handle *handle,
+				 struct perf_counter *counter)
+{
+	u64 read_format = counter->attr.read_format;
+	u64 values[4];
+	int n = 0;
+
+	values[n++] = atomic64_read(&counter->count);
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		values[n++] = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		values[n++] = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+	}
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_counter_id(counter);
+
+	perf_output_copy(handle, values, n * sizeof(u64));
+}
+
+/*
+ * XXX PERF_FORMAT_GROUP vs inherited counters seems difficult.
+ */
+static void perf_output_read_group(struct perf_output_handle *handle,
+			    struct perf_counter *counter)
+{
+	struct perf_counter *leader = counter->group_leader, *sub;
+	u64 read_format = counter->attr.read_format;
+	u64 values[5];
+	int n = 0;
+
+	values[n++] = 1 + leader->nr_siblings;
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		values[n++] = leader->total_time_enabled;
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		values[n++] = leader->total_time_running;
+
+	if (leader != counter)
+		leader->pmu->read(leader);
+
+	values[n++] = atomic64_read(&leader->count);
+	if (read_format & PERF_FORMAT_ID)
+		values[n++] = primary_counter_id(leader);
+
+	perf_output_copy(handle, values, n * sizeof(u64));
+
+	list_for_each_entry(sub, &leader->sibling_list, list_entry) {
+		n = 0;
+
+		if (sub != counter)
+			sub->pmu->read(sub);
+
+		values[n++] = atomic64_read(&sub->count);
+		if (read_format & PERF_FORMAT_ID)
+			values[n++] = primary_counter_id(sub);
+
+		perf_output_copy(handle, values, n * sizeof(u64));
+	}
+}
+
+static void perf_output_read(struct perf_output_handle *handle,
+			     struct perf_counter *counter)
+{
+	if (counter->attr.read_format & PERF_FORMAT_GROUP)
+		perf_output_read_group(handle, counter);
+	else
+		perf_output_read_one(handle, counter);
+}
+
+void perf_counter_output(struct perf_counter *counter, int nmi,
 				struct perf_sample_data *data)
 {
 	int ret;
@@ -2410,10 +2831,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 	struct {
 		u32 pid, tid;
 	} tid_entry;
-	struct {
-		u64 id;
-		u64 counter;
-	} group_entry;
 	struct perf_callchain_entry *callchain = NULL;
 	int callchain_size = 0;
 	u64 time;
@@ -2421,15 +2838,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		u32 cpu, reserved;
 	} cpu_entry;
 
-	header.type = 0;
+	header.type = PERF_EVENT_SAMPLE;
 	header.size = sizeof(header);
 
-	header.misc = PERF_EVENT_MISC_OVERFLOW;
+	header.misc = 0;
 	header.misc |= perf_misc_flags(data->regs);
 
 	if (sample_type & PERF_SAMPLE_IP) {
 		ip = perf_instruction_pointer(data->regs);
-		header.type |= PERF_SAMPLE_IP;
 		header.size += sizeof(ip);
 	}
 
@@ -2438,7 +2854,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		tid_entry.pid = perf_counter_pid(counter, current);
 		tid_entry.tid = perf_counter_tid(counter, current);
 
-		header.type |= PERF_SAMPLE_TID;
 		header.size += sizeof(tid_entry);
 	}
 
@@ -2448,47 +2863,51 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		 */
 		time = sched_clock();
 
-		header.type |= PERF_SAMPLE_TIME;
 		header.size += sizeof(u64);
 	}
 
-	if (sample_type & PERF_SAMPLE_ADDR) {
-		header.type |= PERF_SAMPLE_ADDR;
+	if (sample_type & PERF_SAMPLE_ADDR)
 		header.size += sizeof(u64);
-	}
 
-	if (sample_type & PERF_SAMPLE_ID) {
-		header.type |= PERF_SAMPLE_ID;
+	if (sample_type & PERF_SAMPLE_ID)
+		header.size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
 		header.size += sizeof(u64);
-	}
 
 	if (sample_type & PERF_SAMPLE_CPU) {
-		header.type |= PERF_SAMPLE_CPU;
 		header.size += sizeof(cpu_entry);
 
 		cpu_entry.cpu = raw_smp_processor_id();
+		cpu_entry.reserved = 0;
 	}
 
-	if (sample_type & PERF_SAMPLE_PERIOD) {
-		header.type |= PERF_SAMPLE_PERIOD;
+	if (sample_type & PERF_SAMPLE_PERIOD)
 		header.size += sizeof(u64);
-	}
 
-	if (sample_type & PERF_SAMPLE_GROUP) {
-		header.type |= PERF_SAMPLE_GROUP;
-		header.size += sizeof(u64) +
-			counter->nr_siblings * sizeof(group_entry);
-	}
+	if (sample_type & PERF_SAMPLE_READ)
+		header.size += perf_counter_read_size(counter);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		callchain = perf_callchain(data->regs);
 
 		if (callchain) {
 			callchain_size = (1 + callchain->nr) * sizeof(u64);
-
-			header.type |= PERF_SAMPLE_CALLCHAIN;
 			header.size += callchain_size;
-		}
+		} else
+			header.size += sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_RAW) {
+		int size = sizeof(u32);
+
+		if (data->raw)
+			size += data->raw->size;
+		else
+			size += sizeof(u32);
+
+		WARN_ON_ONCE(size & (sizeof(u64)-1));
+		header.size += size;
 	}
 
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2509,7 +2928,13 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 	if (sample_type & PERF_SAMPLE_ADDR)
 		perf_output_put(&handle, data->addr);
 
-	if (sample_type & PERF_SAMPLE_ID)
+	if (sample_type & PERF_SAMPLE_ID) {
+		u64 id = primary_counter_id(counter);
+
+		perf_output_put(&handle, id);
+	}
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
 		perf_output_put(&handle, counter->id);
 
 	if (sample_type & PERF_SAMPLE_CPU)
@@ -2518,76 +2943,125 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		perf_output_put(&handle, data->period);
 
-	/*
-	 * XXX PERF_SAMPLE_GROUP vs inherited counters seems difficult.
-	 */
-	if (sample_type & PERF_SAMPLE_GROUP) {
-		struct perf_counter *leader, *sub;
-		u64 nr = counter->nr_siblings;
-
-		perf_output_put(&handle, nr);
-
-		leader = counter->group_leader;
-		list_for_each_entry(sub, &leader->sibling_list, list_entry) {
-			if (sub != counter)
-				sub->pmu->read(sub);
+	if (sample_type & PERF_SAMPLE_READ)
+		perf_output_read(&handle, counter);
 
-			group_entry.id = sub->id;
-			group_entry.counter = atomic64_read(&sub->count);
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		if (callchain)
+			perf_output_copy(&handle, callchain, callchain_size);
+		else {
+			u64 nr = 0;
+			perf_output_put(&handle, nr);
+		}
+	}
 
-			perf_output_put(&handle, group_entry);
+	if (sample_type & PERF_SAMPLE_RAW) {
+		if (data->raw) {
+			perf_output_put(&handle, data->raw->size);
+			perf_output_copy(&handle, data->raw->data, data->raw->size);
+		} else {
+			struct {
+				u32	size;
+				u32	data;
+			} raw = {
+				.size = sizeof(u32),
+				.data = 0,
+			};
+			perf_output_put(&handle, raw);
 		}
 	}
 
-	if (callchain)
-		perf_output_copy(&handle, callchain, callchain_size);
+	perf_output_end(&handle);
+}
+
+/*
+ * read event
+ */
+
+struct perf_read_event {
+	struct perf_event_header	header;
+
+	u32				pid;
+	u32				tid;
+};
+
+static void
+perf_counter_read_event(struct perf_counter *counter,
+			struct task_struct *task)
+{
+	struct perf_output_handle handle;
+	struct perf_read_event event = {
+		.header = {
+			.type = PERF_EVENT_READ,
+			.misc = 0,
+			.size = sizeof(event) + perf_counter_read_size(counter),
+		},
+		.pid = perf_counter_pid(counter, task),
+		.tid = perf_counter_tid(counter, task),
+	};
+	int ret;
+
+	ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, event);
+	perf_output_read(&handle, counter);
 
 	perf_output_end(&handle);
 }
 
 /*
- * fork tracking
+ * task tracking -- fork/exit
+ *
+ * enabled by: attr.comm | attr.mmap | attr.task
  */
 
-struct perf_fork_event {
-	struct task_struct	*task;
+struct perf_task_event {
+	struct task_struct		*task;
+	struct perf_counter_context	*task_ctx;
 
 	struct {
 		struct perf_event_header	header;
 
 		u32				pid;
 		u32				ppid;
+		u32				tid;
+		u32				ptid;
 	} event;
 };
 
-static void perf_counter_fork_output(struct perf_counter *counter,
-				     struct perf_fork_event *fork_event)
+static void perf_counter_task_output(struct perf_counter *counter,
+				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
-	int size = fork_event->event.header.size;
-	struct task_struct *task = fork_event->task;
+	int size = task_event->event.header.size;
+	struct task_struct *task = task_event->task;
 	int ret = perf_output_begin(&handle, counter, size, 0, 0);
 
 	if (ret)
 		return;
 
-	fork_event->event.pid = perf_counter_pid(counter, task);
-	fork_event->event.ppid = perf_counter_pid(counter, task->real_parent);
+	task_event->event.pid = perf_counter_pid(counter, task);
+	task_event->event.ppid = perf_counter_pid(counter, current);
+
+	task_event->event.tid = perf_counter_tid(counter, task);
+	task_event->event.ptid = perf_counter_tid(counter, current);
 
-	perf_output_put(&handle, fork_event->event);
+	perf_output_put(&handle, task_event->event);
 	perf_output_end(&handle);
 }
 
-static int perf_counter_fork_match(struct perf_counter *counter)
+static int perf_counter_task_match(struct perf_counter *counter)
 {
-	if (counter->attr.comm || counter->attr.mmap)
+	if (counter->attr.comm || counter->attr.mmap || counter->attr.task)
 		return 1;
 
 	return 0;
 }
 
-static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
-				  struct perf_fork_event *fork_event)
+static void perf_counter_task_ctx(struct perf_counter_context *ctx,
+				  struct perf_task_event *task_event)
 {
 	struct perf_counter *counter;
 
@@ -2596,51 +3070,62 @@ static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_counter_fork_match(counter))
-			perf_counter_fork_output(counter, fork_event);
+		if (perf_counter_task_match(counter))
+			perf_counter_task_output(counter, task_event);
 	}
 	rcu_read_unlock();
 }
 
-static void perf_counter_fork_event(struct perf_fork_event *fork_event)
+static void perf_counter_task_event(struct perf_task_event *task_event)
 {
 	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx;
+	struct perf_counter_context *ctx = task_event->task_ctx;
 
 	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_counter_fork_ctx(&cpuctx->ctx, fork_event);
+	perf_counter_task_ctx(&cpuctx->ctx, task_event);
 	put_cpu_var(perf_cpu_context);
 
 	rcu_read_lock();
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (!ctx)
+		ctx = rcu_dereference(task_event->task->perf_counter_ctxp);
 	if (ctx)
-		perf_counter_fork_ctx(ctx, fork_event);
+		perf_counter_task_ctx(ctx, task_event);
 	rcu_read_unlock();
 }
 
-void perf_counter_fork(struct task_struct *task)
+static void perf_counter_task(struct task_struct *task,
+			      struct perf_counter_context *task_ctx,
+			      int new)
 {
-	struct perf_fork_event fork_event;
+	struct perf_task_event task_event;
 
 	if (!atomic_read(&nr_comm_counters) &&
-	    !atomic_read(&nr_mmap_counters))
+	    !atomic_read(&nr_mmap_counters) &&
+	    !atomic_read(&nr_task_counters))
 		return;
 
-	fork_event = (struct perf_fork_event){
-		.task	= task,
-		.event  = {
+	task_event = (struct perf_task_event){
+		.task	  = task,
+		.task_ctx = task_ctx,
+		.event    = {
 			.header = {
-				.type = PERF_EVENT_FORK,
-				.size = sizeof(fork_event.event),
+				.type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
+				.misc = 0,
+				.size = sizeof(task_event.event),
 			},
+			/* .pid  */
+			/* .ppid */
+			/* .tid  */
+			/* .ptid */
 		},
 	};
 
-	perf_counter_fork_event(&fork_event);
+	perf_counter_task_event(&task_event);
+}
+
+void perf_counter_fork(struct task_struct *task)
+{
+	perf_counter_task(task, NULL, 1);
 }
 
 /*
@@ -2708,8 +3193,10 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)
 	struct perf_cpu_context *cpuctx;
 	struct perf_counter_context *ctx;
 	unsigned int size;
-	char *comm = comm_event->task->comm;
+	char comm[TASK_COMM_LEN];
 
+	memset(comm, 0, sizeof(comm));
+	strncpy(comm, comm_event->task->comm, sizeof(comm));
 	size = ALIGN(strlen(comm)+1, sizeof(u64));
 
 	comm_event->comm = comm;
@@ -2736,13 +3223,24 @@ void perf_counter_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
 
+	if (task->perf_counter_ctxp)
+		perf_counter_enable_on_exec(task);
+
 	if (!atomic_read(&nr_comm_counters))
 		return;
 
 	comm_event = (struct perf_comm_event){
 		.task	= task,
+		/* .comm      */
+		/* .comm_size */
 		.event  = {
-			.header = { .type = PERF_EVENT_COMM, },
+			.header = {
+				.type = PERF_EVENT_COMM,
+				.misc = 0,
+				/* .size */
+			},
+			/* .pid */
+			/* .tid */
 		},
 	};
 
@@ -2825,8 +3323,15 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
 	char *buf = NULL;
 	const char *name;
 
+	memset(tmp, 0, sizeof(tmp));
+
 	if (file) {
-		buf = kzalloc(PATH_MAX, GFP_KERNEL);
+		/*
+		 * d_path works from the end of the buffer backwards, so we
+		 * need to add enough zero bytes after the string to handle
+		 * the 64bit alignment we do later.
+		 */
+		buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
 		if (!buf) {
 			name = strncpy(tmp, "//enomem", sizeof(tmp));
 			goto got_name;
@@ -2837,9 +3342,11 @@ static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
 			goto got_name;
 		}
 	} else {
-		name = arch_vma_name(mmap_event->vma);
-		if (name)
+		if (arch_vma_name(mmap_event->vma)) {
+			name = strncpy(tmp, arch_vma_name(mmap_event->vma),
+				       sizeof(tmp));
 			goto got_name;
+		}
 
 		if (!vma->vm_mm) {
 			name = strncpy(tmp, "[vdso]", sizeof(tmp));
@@ -2884,8 +3391,16 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
 
 	mmap_event = (struct perf_mmap_event){
 		.vma	= vma,
+		/* .file_name */
+		/* .file_size */
 		.event  = {
-			.header = { .type = PERF_EVENT_MMAP, },
+			.header = {
+				.type = PERF_EVENT_MMAP,
+				.misc = 0,
+				/* .size */
+			},
+			/* .pid */
+			/* .tid */
 			.start  = vma->vm_start,
 			.len    = vma->vm_end - vma->vm_start,
 			.pgoff  = vma->vm_pgoff,
@@ -2896,49 +3411,6 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
 }
 
 /*
- * Log sample_period changes so that analyzing tools can re-normalize the
- * event flow.
- */
-
-struct freq_event {
-	struct perf_event_header	header;
-	u64				time;
-	u64				id;
-	u64				period;
-};
-
-static void perf_log_period(struct perf_counter *counter, u64 period)
-{
-	struct perf_output_handle handle;
-	struct freq_event event;
-	int ret;
-
-	if (counter->hw.sample_period == period)
-		return;
-
-	if (counter->attr.sample_type & PERF_SAMPLE_PERIOD)
-		return;
-
-	event = (struct freq_event) {
-		.header = {
-			.type = PERF_EVENT_PERIOD,
-			.misc = 0,
-			.size = sizeof(event),
-		},
-		.time = sched_clock(),
-		.id = counter->id,
-		.period = period,
-	};
-
-	ret = perf_output_begin(&handle, counter, sizeof(event), 1, 0);
-	if (ret)
-		return;
-
-	perf_output_put(&handle, event);
-	perf_output_end(&handle);
-}
-
-/*
  * IRQ throttle logging
  */
 
@@ -2951,16 +3423,21 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
 		struct perf_event_header	header;
 		u64				time;
 		u64				id;
+		u64				stream_id;
 	} throttle_event = {
 		.header = {
-			.type = PERF_EVENT_THROTTLE + 1,
+			.type = PERF_EVENT_THROTTLE,
 			.misc = 0,
 			.size = sizeof(throttle_event),
 		},
-		.time	= sched_clock(),
-		.id	= counter->id,
+		.time		= sched_clock(),
+		.id		= primary_counter_id(counter),
+		.stream_id	= counter->id,
 	};
 
+	if (enable)
+		throttle_event.header.type = PERF_EVENT_UNTHROTTLE;
+
 	ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
 	if (ret)
 		return;
@@ -2970,7 +3447,7 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
 }
 
 /*
- * Generic counter overflow handling.
+ * Generic counter overflow handling, sampling.
  */
 
 int perf_counter_overflow(struct perf_counter *counter, int nmi,
@@ -3037,130 +3514,111 @@ int perf_counter_overflow(struct perf_counter *counter, int nmi,
  * Generic software counter infrastructure
  */
 
-static void perf_swcounter_update(struct perf_counter *counter)
+/*
+ * We directly increment counter->count and keep a second value in
+ * counter->hw.period_left to count intervals. This period counter
+ * is kept in the range [-sample_period, 0] so that we can use the
+ * sign as trigger.
+ */
+
+static u64 perf_swcounter_set_period(struct perf_counter *counter)
 {
 	struct hw_perf_counter *hwc = &counter->hw;
-	u64 prev, now;
-	s64 delta;
+	u64 period = hwc->last_period;
+	u64 nr, offset;
+	s64 old, val;
+
+	hwc->last_period = hwc->sample_period;
 
 again:
-	prev = atomic64_read(&hwc->prev_count);
-	now = atomic64_read(&hwc->count);
-	if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev)
-		goto again;
+	old = val = atomic64_read(&hwc->period_left);
+	if (val < 0)
+		return 0;
 
-	delta = now - prev;
+	nr = div64_u64(period + val, period);
+	offset = nr * period;
+	val -= offset;
+	if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
+		goto again;
 
-	atomic64_add(delta, &counter->count);
-	atomic64_sub(delta, &hwc->period_left);
+	return nr;
 }
 
-static void perf_swcounter_set_period(struct perf_counter *counter)
+static void perf_swcounter_overflow(struct perf_counter *counter,
+				    int nmi, struct perf_sample_data *data)
 {
 	struct hw_perf_counter *hwc = &counter->hw;
-	s64 left = atomic64_read(&hwc->period_left);
-	s64 period = hwc->sample_period;
+	u64 overflow;
 
-	if (unlikely(left <= -period)) {
-		left = period;
-		atomic64_set(&hwc->period_left, left);
-		hwc->last_period = period;
-	}
+	data->period = counter->hw.last_period;
+	overflow = perf_swcounter_set_period(counter);
 
-	if (unlikely(left <= 0)) {
-		left += period;
-		atomic64_add(period, &hwc->period_left);
-		hwc->last_period = period;
-	}
+	if (hwc->interrupts == MAX_INTERRUPTS)
+		return;
 
-	atomic64_set(&hwc->prev_count, -left);
-	atomic64_set(&hwc->count, -left);
+	for (; overflow; overflow--) {
+		if (perf_counter_overflow(counter, nmi, data)) {
+			/*
+			 * We inhibit the overflow from happening when
+			 * hwc->interrupts == MAX_INTERRUPTS.
+			 */
+			break;
+		}
+	}
 }
 
-static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
+static void perf_swcounter_unthrottle(struct perf_counter *counter)
 {
-	enum hrtimer_restart ret = HRTIMER_RESTART;
-	struct perf_sample_data data;
-	struct perf_counter *counter;
-	u64 period;
-
-	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
-	counter->pmu->read(counter);
-
-	data.addr = 0;
-	data.regs = get_irq_regs();
 	/*
-	 * In case we exclude kernel IPs or are somehow not in interrupt
-	 * context, provide the next best thing, the user IP.
+	 * Nothing to do, we already reset hwc->interrupts.
 	 */
-	if ((counter->attr.exclude_kernel || !data.regs) &&
-			!counter->attr.exclude_user)
-		data.regs = task_pt_regs(current);
-
-	if (data.regs) {
-		if (perf_counter_overflow(counter, 0, &data))
-			ret = HRTIMER_NORESTART;
-	}
-
-	period = max_t(u64, 10000, counter->hw.sample_period);
-	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
-
-	return ret;
 }
 
-static void perf_swcounter_overflow(struct perf_counter *counter,
-				    int nmi, struct pt_regs *regs, u64 addr)
+static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
+			       int nmi, struct perf_sample_data *data)
 {
-	struct perf_sample_data data = {
-		.regs	= regs,
-		.addr	= addr,
-		.period	= counter->hw.last_period,
-	};
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	atomic64_add(nr, &counter->count);
 
-	perf_swcounter_update(counter);
-	perf_swcounter_set_period(counter);
-	if (perf_counter_overflow(counter, nmi, &data))
-		/* soft-disable the counter */
-		;
+	if (!hwc->sample_period)
+		return;
+
+	if (!data->regs)
+		return;
 
+	if (!atomic64_add_negative(nr, &hwc->period_left))
+		perf_swcounter_overflow(counter, nmi, data);
 }
 
 static int perf_swcounter_is_counting(struct perf_counter *counter)
 {
-	struct perf_counter_context *ctx;
-	unsigned long flags;
-	int count;
-
+	/*
+	 * The counter is active, we're good!
+	 */
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
 		return 1;
 
+	/*
+	 * The counter is off/error, not counting.
+	 */
 	if (counter->state != PERF_COUNTER_STATE_INACTIVE)
 		return 0;
 
 	/*
-	 * If the counter is inactive, it could be just because
-	 * its task is scheduled out, or because it's in a group
-	 * which could not go on the PMU.  We want to count in
-	 * the first case but not the second.  If the context is
-	 * currently active then an inactive software counter must
-	 * be the second case.  If it's not currently active then
-	 * we need to know whether the counter was active when the
-	 * context was last active, which we can determine by
-	 * comparing counter->tstamp_stopped with ctx->time.
-	 *
-	 * We are within an RCU read-side critical section,
-	 * which protects the existence of *ctx.
+	 * The counter is inactive, if the context is active
+	 * we're part of a group that didn't make it on the 'pmu',
+	 * not counting.
 	 */
-	ctx = counter->ctx;
-	spin_lock_irqsave(&ctx->lock, flags);
-	count = 1;
-	/* Re-check state now we have the lock */
-	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
-	    counter->ctx->is_active ||
-	    counter->tstamp_stopped < ctx->time)
-		count = 0;
-	spin_unlock_irqrestore(&ctx->lock, flags);
-	return count;
+	if (counter->ctx->is_active)
+		return 0;
+
+	/*
+	 * We're inactive and the context is too, this means the
+	 * task is scheduled out, we're counting events that happen
+	 * to us, like migration events.
+	 */
+	return 1;
 }
 
 static int perf_swcounter_match(struct perf_counter *counter,
@@ -3186,19 +3644,10 @@ static int perf_swcounter_match(struct perf_counter *counter,
 	return 1;
 }
 
-static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
-			       int nmi, struct pt_regs *regs, u64 addr)
-{
-	int neg = atomic64_add_negative(nr, &counter->hw.count);
-
-	if (counter->hw.sample_period && !neg && regs)
-		perf_swcounter_overflow(counter, nmi, regs, addr);
-}
-
 static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
-				     enum perf_type_id type, u32 event,
-				     u64 nr, int nmi, struct pt_regs *regs,
-				     u64 addr)
+				     enum perf_type_id type,
+				     u32 event, u64 nr, int nmi,
+				     struct perf_sample_data *data)
 {
 	struct perf_counter *counter;
 
@@ -3207,8 +3656,8 @@ static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
-		if (perf_swcounter_match(counter, type, event, regs))
-			perf_swcounter_add(counter, nr, nmi, regs, addr);
+		if (perf_swcounter_match(counter, type, event, data->regs))
+			perf_swcounter_add(counter, nr, nmi, data);
 	}
 	rcu_read_unlock();
 }
@@ -3227,9 +3676,9 @@ static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
 	return &cpuctx->recursion[0];
 }
 
-static void __perf_swcounter_event(enum perf_type_id type, u32 event,
-				   u64 nr, int nmi, struct pt_regs *regs,
-				   u64 addr)
+static void do_perf_swcounter_event(enum perf_type_id type, u32 event,
+				    u64 nr, int nmi,
+				    struct perf_sample_data *data)
 {
 	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
 	int *recursion = perf_swcounter_recursion_context(cpuctx);
@@ -3242,7 +3691,7 @@ static void __perf_swcounter_event(enum perf_type_id type, u32 event,
 	barrier();
 
 	perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
-				 nr, nmi, regs, addr);
+				 nr, nmi, data);
 	rcu_read_lock();
 	/*
 	 * doesn't really matter which of the child contexts the
@@ -3250,7 +3699,7 @@ static void __perf_swcounter_event(enum perf_type_id type, u32 event,
 	 */
 	ctx = rcu_dereference(current->perf_counter_ctxp);
 	if (ctx)
-		perf_swcounter_ctx_event(ctx, type, event, nr, nmi, regs, addr);
+		perf_swcounter_ctx_event(ctx, type, event, nr, nmi, data);
 	rcu_read_unlock();
 
 	barrier();
@@ -3260,35 +3709,79 @@ out:
 	put_cpu_var(perf_cpu_context);
 }
 
-void
-perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+			    struct pt_regs *regs, u64 addr)
 {
-	__perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs, addr);
+	struct perf_sample_data data = {
+		.regs = regs,
+		.addr = addr,
+	};
+
+	do_perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, &data);
 }
 
 static void perf_swcounter_read(struct perf_counter *counter)
 {
-	perf_swcounter_update(counter);
 }
 
 static int perf_swcounter_enable(struct perf_counter *counter)
 {
-	perf_swcounter_set_period(counter);
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	if (hwc->sample_period) {
+		hwc->last_period = hwc->sample_period;
+		perf_swcounter_set_period(counter);
+	}
 	return 0;
 }
 
 static void perf_swcounter_disable(struct perf_counter *counter)
 {
-	perf_swcounter_update(counter);
 }
 
 static const struct pmu perf_ops_generic = {
 	.enable		= perf_swcounter_enable,
 	.disable	= perf_swcounter_disable,
 	.read		= perf_swcounter_read,
+	.unthrottle	= perf_swcounter_unthrottle,
 };
 
 /*
+ * hrtimer based swcounter callback
+ */
+
+static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
+{
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct perf_counter *counter;
+	u64 period;
+
+	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
+	counter->pmu->read(counter);
+
+	data.addr = 0;
+	data.regs = get_irq_regs();
+	/*
+	 * In case we exclude kernel IPs or are somehow not in interrupt
+	 * context, provide the next best thing, the user IP.
+	 */
+	if ((counter->attr.exclude_kernel || !data.regs) &&
+			!counter->attr.exclude_user)
+		data.regs = task_pt_regs(current);
+
+	if (data.regs) {
+		if (perf_counter_overflow(counter, 0, &data))
+			ret = HRTIMER_NORESTART;
+	}
+
+	period = max_t(u64, 10000, counter->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
+}
+
+/*
  * Software counter: cpu wall time clock
  */
 
@@ -3404,36 +3897,25 @@ static const struct pmu perf_ops_task_clock = {
 	.read		= task_clock_perf_counter_read,
 };
 
-/*
- * Software counter: cpu migrations
- */
-void perf_counter_task_migration(struct task_struct *task, int cpu)
-{
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_counter_context *ctx;
-
-	perf_swcounter_ctx_event(&cpuctx->ctx, PERF_TYPE_SOFTWARE,
-				 PERF_COUNT_SW_CPU_MIGRATIONS,
-				 1, 1, NULL, 0);
-
-	ctx = perf_pin_task_context(task);
-	if (ctx) {
-		perf_swcounter_ctx_event(ctx, PERF_TYPE_SOFTWARE,
-					 PERF_COUNT_SW_CPU_MIGRATIONS,
-					 1, 1, NULL, 0);
-		perf_unpin_context(ctx);
-	}
-}
-
 #ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id)
+void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size)
 {
-	struct pt_regs *regs = get_irq_regs();
+	struct perf_raw_record raw = {
+		.size = entry_size,
+		.data = record,
+	};
+
+	struct perf_sample_data data = {
+		.regs = get_irq_regs(),
+		.addr = addr,
+		.raw = &raw,
+	};
 
-	if (!regs)
-		regs = task_pt_regs(current);
+	if (!data.regs)
+		data.regs = task_pt_regs(current);
 
-	__perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs, 0);
+	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data);
 }
 EXPORT_SYMBOL_GPL(perf_tpcounter_event);
 
@@ -3442,16 +3924,20 @@ extern void ftrace_profile_disable(int);
 
 static void tp_perf_counter_destroy(struct perf_counter *counter)
 {
-	ftrace_profile_disable(perf_event_id(&counter->attr));
+	ftrace_profile_disable(counter->attr.config);
 }
 
 static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 {
-	int event_id = perf_event_id(&counter->attr);
-	int ret;
+	/*
+	 * Raw tracepoint data is a severe data leak, only allow root to
+	 * have these.
+	 */
+	if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
+			!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
 
-	ret = ftrace_profile_enable(event_id);
-	if (ret)
+	if (ftrace_profile_enable(counter->attr.config))
 		return NULL;
 
 	counter->destroy = tp_perf_counter_destroy;
@@ -3465,9 +3951,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 }
 #endif
 
+atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_counter_destroy(struct perf_counter *counter)
+{
+	u64 event = counter->attr.config;
+
+	WARN_ON(counter->parent);
+
+	atomic_dec(&perf_swcounter_enabled[event]);
+}
+
 static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 {
 	const struct pmu *pmu = NULL;
+	u64 event = counter->attr.config;
 
 	/*
 	 * Software counters (currently) can't in general distinguish
@@ -3476,7 +3974,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	 * to be kernel events, and page faults are never hypervisor
 	 * events.
 	 */
-	switch (counter->attr.config) {
+	switch (event) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 		pmu = &perf_ops_cpu_clock;
 
@@ -3497,6 +3995,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
 	case PERF_COUNT_SW_CONTEXT_SWITCHES:
 	case PERF_COUNT_SW_CPU_MIGRATIONS:
+		if (!counter->parent) {
+			atomic_inc(&perf_swcounter_enabled[event]);
+			counter->destroy = sw_perf_counter_destroy;
+		}
 		pmu = &perf_ops_generic;
 		break;
 	}
@@ -3512,6 +4014,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 		   int cpu,
 		   struct perf_counter_context *ctx,
 		   struct perf_counter *group_leader,
+		   struct perf_counter *parent_counter,
 		   gfp_t gfpflags)
 {
 	const struct pmu *pmu;
@@ -3547,6 +4050,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	counter->ctx		= ctx;
 	counter->oncpu		= -1;
 
+	counter->parent		= parent_counter;
+
 	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
 	counter->id		= atomic64_inc_return(&perf_counter_id);
 
@@ -3561,13 +4066,14 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	hwc->sample_period = attr->sample_period;
 	if (attr->freq && attr->sample_freq)
 		hwc->sample_period = 1;
+	hwc->last_period = hwc->sample_period;
 
 	atomic64_set(&hwc->period_left, hwc->sample_period);
 
 	/*
-	 * we currently do not support PERF_SAMPLE_GROUP on inherited counters
+	 * we currently do not support PERF_FORMAT_GROUP on inherited counters
 	 */
-	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
+	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto done;
 
 	switch (attr->type) {
@@ -3604,11 +4110,15 @@ done:
 
 	counter->pmu = pmu;
 
-	atomic_inc(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_inc(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_inc(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_inc(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_inc(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_inc(&nr_comm_counters);
+		if (counter->attr.task)
+			atomic_inc(&nr_task_counters);
+	}
 
 	return counter;
 }
@@ -3771,7 +4281,7 @@ SYSCALL_DEFINE5(perf_counter_open,
 	}
 
 	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
-				     GFP_KERNEL);
+				     NULL, GFP_KERNEL);
 	ret = PTR_ERR(counter);
 	if (IS_ERR(counter))
 		goto err_put_context;
@@ -3837,7 +4347,8 @@ inherit_counter(struct perf_counter *parent_counter,
 
 	child_counter = perf_counter_alloc(&parent_counter->attr,
 					   parent_counter->cpu, child_ctx,
-					   group_leader, GFP_KERNEL);
+					   group_leader, parent_counter,
+					   GFP_KERNEL);
 	if (IS_ERR(child_counter))
 		return child_counter;
 	get_ctx(child_ctx);
@@ -3860,12 +4371,6 @@ inherit_counter(struct perf_counter *parent_counter,
 	 */
 	add_counter_to_ctx(child_counter, child_ctx);
 
-	child_counter->parent = parent_counter;
-	/*
-	 * inherit into child's child as well:
-	 */
-	child_counter->attr.inherit = 1;
-
 	/*
 	 * Get a reference to the parent filp - we will fput it
 	 * when the child counter exits. This is safe to do because
@@ -3909,10 +4414,14 @@ static int inherit_group(struct perf_counter *parent_counter,
 }
 
 static void sync_child_counter(struct perf_counter *child_counter,
-			       struct perf_counter *parent_counter)
+			       struct task_struct *child)
 {
+	struct perf_counter *parent_counter = child_counter->parent;
 	u64 child_val;
 
+	if (child_counter->attr.inherit_stat)
+		perf_counter_read_event(child_counter, child);
+
 	child_val = atomic64_read(&child_counter->count);
 
 	/*
@@ -3941,7 +4450,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
 
 static void
 __perf_counter_exit_task(struct perf_counter *child_counter,
-			 struct perf_counter_context *child_ctx)
+			 struct perf_counter_context *child_ctx,
+			 struct task_struct *child)
 {
 	struct perf_counter *parent_counter;
 
@@ -3955,7 +4465,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter,
 	 * counters need to be zapped - but otherwise linger.
 	 */
 	if (parent_counter) {
-		sync_child_counter(child_counter, parent_counter);
+		sync_child_counter(child_counter, child);
 		free_counter(child_counter);
 	}
 }
@@ -3969,8 +4479,10 @@ void perf_counter_exit_task(struct task_struct *child)
 	struct perf_counter_context *child_ctx;
 	unsigned long flags;
 
-	if (likely(!child->perf_counter_ctxp))
+	if (likely(!child->perf_counter_ctxp)) {
+		perf_counter_task(child, NULL, 0);
 		return;
+	}
 
 	local_irq_save(flags);
 	/*
@@ -3989,17 +4501,20 @@ void perf_counter_exit_task(struct task_struct *child)
 	 */
 	spin_lock(&child_ctx->lock);
 	child->perf_counter_ctxp = NULL;
-	if (child_ctx->parent_ctx) {
-		/*
-		 * This context is a clone; unclone it so it can't get
-		 * swapped to another process while we're removing all
-		 * the counters from it.
-		 */
-		put_ctx(child_ctx->parent_ctx);
-		child_ctx->parent_ctx = NULL;
-	}
-	spin_unlock(&child_ctx->lock);
-	local_irq_restore(flags);
+	/*
+	 * If this context is a clone; unclone it so it can't get
+	 * swapped to another process while we're removing all
+	 * the counters from it.
+	 */
+	unclone_ctx(child_ctx);
+	spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+	/*
+	 * Report the task dead after unscheduling the counters so that we
+	 * won't get any samples after PERF_EVENT_EXIT. We can however still
+	 * get a few PERF_EVENT_READ events.
+	 */
+	perf_counter_task(child, child_ctx, 0);
 
 	/*
 	 * We can recurse on the same lock type through:
@@ -4017,7 +4532,7 @@ void perf_counter_exit_task(struct task_struct *child)
 again:
 	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
 				 list_entry)
-		__perf_counter_exit_task(child_counter, child_ctx);
+		__perf_counter_exit_task(child_counter, child_ctx, child);
 
 	/*
 	 * If the last counter was a group counter, it will have appended all
@@ -4220,6 +4735,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 		perf_counter_init_cpu(cpu);
 		break;
 
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		hw_perf_counter_setup_online(cpu);
+		break;
+
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		perf_counter_exit_cpu(cpu);
@@ -4244,6 +4764,8 @@ void __init perf_counter_init(void)
 {
 	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
 			(void *)(long)smp_processor_id());
+	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
+			(void *)(long)smp_processor_id());
 	register_cpu_notifier(&perf_cpu_nb);
 }
 
diff --git a/kernel/pid.c b/kernel/pid.c
index b2e5f78fd28..31310b5d3f5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -378,26 +378,15 @@ EXPORT_SYMBOL(pid_task);
 /*
  * Must be called under rcu_read_lock() or with tasklist_lock read-held.
  */
-struct task_struct *find_task_by_pid_type_ns(int type, int nr,
-		struct pid_namespace *ns)
+struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
-	return pid_task(find_pid_ns(nr, ns), type);
+	return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
 }
 
-EXPORT_SYMBOL(find_task_by_pid_type_ns);
-
 struct task_struct *find_task_by_vpid(pid_t vnr)
 {
-	return find_task_by_pid_type_ns(PIDTYPE_PID, vnr,
-			current->nsproxy->pid_ns);
-}
-EXPORT_SYMBOL(find_task_by_vpid);
-
-struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
-{
-	return find_task_by_pid_type_ns(PIDTYPE_PID, nr, ns);
+	return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns);
 }
-EXPORT_SYMBOL(find_task_by_pid_ns);
 
 struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 {
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 2d1001b4858..821722ae58a 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -67,9 +67,10 @@ err_alloc:
 	return NULL;
 }
 
-static struct pid_namespace *create_pid_namespace(unsigned int level)
+static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
 {
 	struct pid_namespace *ns;
+	unsigned int level = parent_pid_ns->level + 1;
 	int i;
 
 	ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
@@ -86,6 +87,7 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
 
 	kref_init(&ns->kref);
 	ns->level = level;
+	ns->parent = get_pid_ns(parent_pid_ns);
 
 	set_bit(0, ns->pidmap[0].page);
 	atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -114,25 +116,11 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 
 struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
 {
-	struct pid_namespace *new_ns;
-
-	BUG_ON(!old_ns);
-	new_ns = get_pid_ns(old_ns);
 	if (!(flags & CLONE_NEWPID))
-		goto out;
-
-	new_ns = ERR_PTR(-EINVAL);
+		return get_pid_ns(old_ns);
 	if (flags & CLONE_THREAD)
-		goto out_put;
-
-	new_ns = create_pid_namespace(old_ns->level + 1);
-	if (!IS_ERR(new_ns))
-		new_ns->parent = get_pid_ns(old_ns);
-
-out_put:
-	put_pid_ns(old_ns);
-out:
-	return new_ns;
+		return ERR_PTR(-EINVAL);
+	return create_pid_namespace(old_ns);
 }
 
 void free_pid_ns(struct kref *kref)
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index bece7c0b67b..e33a21cb940 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -521,11 +521,12 @@ void posix_cpu_timers_exit(struct task_struct *tsk)
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	struct task_cputime cputime;
+	struct signal_struct *const sig = tsk->signal;
 
-	thread_group_cputimer(tsk, &cputime);
 	cleanup_timers(tsk->signal->cpu_timers,
-		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
+		       cputime_add(tsk->utime, sig->utime),
+		       cputime_add(tsk->stime, sig->stime),
+		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
 }
 
 static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 052ec4d195c..d089d052c4a 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -202,6 +202,12 @@ static int no_timer_create(struct k_itimer *new_timer)
 	return -EOPNOTSUPP;
 }
 
+static int no_nsleep(const clockid_t which_clock, int flags,
+		     struct timespec *tsave, struct timespec __user *rmtp)
+{
+	return -EOPNOTSUPP;
+}
+
 /*
  * Return nonzero if we know a priori this clockid_t value is bogus.
  */
@@ -254,6 +260,7 @@ static __init int init_posix_timers(void)
 		.clock_get = posix_get_monotonic_raw,
 		.clock_set = do_posix_clock_nosettime,
 		.timer_create = no_timer_create,
+		.nsleep = no_nsleep,
 	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ed97375daae..bf0014d6a5f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -23,7 +23,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
 #include <scsi/scsi_scan.h>
 
 #include <asm/uaccess.h>
diff --git a/kernel/profile.c b/kernel/profile.c
index 69911b5745e..419250ebec4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -117,11 +117,12 @@ int __ref profile_init(void)
 
 	cpumask_copy(prof_cpu_mask, cpu_possible_mask);
 
-	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
+	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
 	if (prof_buffer)
 		return 0;
 
-	prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
+	prof_buffer = alloc_pages_exact(buffer_bytes,
+					GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
 	if (prof_buffer)
 		return 0;
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f6d8b8cb5e3..082c320e4db 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -167,67 +167,82 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 int ptrace_attach(struct task_struct *task)
 {
 	int retval;
-	unsigned long flags;
 
 	audit_ptrace(task);
 
 	retval = -EPERM;
+	if (unlikely(task->flags & PF_KTHREAD))
+		goto out;
 	if (same_thread_group(task, current))
 		goto out;
 
-	/* Protect the target's credential calculations against our
+	/*
+	 * Protect exec's credential calculations against our interference;
 	 * interference; SUID, SGID and LSM creds get determined differently
 	 * under ptrace.
 	 */
-	retval = mutex_lock_interruptible(&task->cred_guard_mutex);
-	if (retval  < 0)
+	retval = -ERESTARTNOINTR;
+	if (mutex_lock_interruptible(&task->cred_guard_mutex))
 		goto out;
 
-	retval = -EPERM;
-repeat:
-	/*
-	 * Nasty, nasty.
-	 *
-	 * We want to hold both the task-lock and the
-	 * tasklist_lock for writing at the same time.
-	 * But that's against the rules (tasklist_lock
-	 * is taken for reading by interrupts on other
-	 * cpu's that may have task_lock).
-	 */
 	task_lock(task);
-	if (!write_trylock_irqsave(&tasklist_lock, flags)) {
-		task_unlock(task);
-		do {
-			cpu_relax();
-		} while (!write_can_lock(&tasklist_lock));
-		goto repeat;
-	}
-
-	if (!task->mm)
-		goto bad;
-	/* the same process cannot be attached many times */
-	if (task->ptrace & PT_PTRACED)
-		goto bad;
 	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+	task_unlock(task);
 	if (retval)
-		goto bad;
+		goto unlock_creds;
 
-	/* Go */
-	task->ptrace |= PT_PTRACED;
+	write_lock_irq(&tasklist_lock);
+	retval = -EPERM;
+	if (unlikely(task->exit_state))
+		goto unlock_tasklist;
+	if (task->ptrace)
+		goto unlock_tasklist;
+
+	task->ptrace = PT_PTRACED;
 	if (capable(CAP_SYS_PTRACE))
 		task->ptrace |= PT_PTRACE_CAP;
 
 	__ptrace_link(task, current);
-
 	send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
-bad:
-	write_unlock_irqrestore(&tasklist_lock, flags);
-	task_unlock(task);
+
+	retval = 0;
+unlock_tasklist:
+	write_unlock_irq(&tasklist_lock);
+unlock_creds:
 	mutex_unlock(&task->cred_guard_mutex);
 out:
 	return retval;
 }
 
+/**
+ * ptrace_traceme  --  helper for PTRACE_TRACEME
+ *
+ * Performs checks and sets PT_PTRACED.
+ * Should be used by all ptrace implementations for PTRACE_TRACEME.
+ */
+int ptrace_traceme(void)
+{
+	int ret = -EPERM;
+
+	write_lock_irq(&tasklist_lock);
+	/* Are we already being traced? */
+	if (!current->ptrace) {
+		ret = security_ptrace_traceme(current->parent);
+		/*
+		 * Check PF_EXITING to ensure ->real_parent has not passed
+		 * exit_ptrace(). Otherwise we don't report the error but
+		 * pretend ->real_parent untraces us right after return.
+		 */
+		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
+			current->ptrace = PT_PTRACED;
+			__ptrace_link(current, current->real_parent);
+		}
+	}
+	write_unlock_irq(&tasklist_lock);
+
+	return ret;
+}
+
 /*
  * Called with irqs disabled, returns true if childs should reap themselves.
  */
@@ -409,37 +424,33 @@ static int ptrace_setoptions(struct task_struct *child, long data)
 
 static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
 {
+	unsigned long flags;
 	int error = -ESRCH;
 
-	read_lock(&tasklist_lock);
-	if (likely(child->sighand != NULL)) {
+	if (lock_task_sighand(child, &flags)) {
 		error = -EINVAL;
-		spin_lock_irq(&child->sighand->siglock);
 		if (likely(child->last_siginfo != NULL)) {
 			*info = *child->last_siginfo;
 			error = 0;
 		}
-		spin_unlock_irq(&child->sighand->siglock);
+		unlock_task_sighand(child, &flags);
 	}
-	read_unlock(&tasklist_lock);
 	return error;
 }
 
 static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
 {
+	unsigned long flags;
 	int error = -ESRCH;
 
-	read_lock(&tasklist_lock);
-	if (likely(child->sighand != NULL)) {
+	if (lock_task_sighand(child, &flags)) {
 		error = -EINVAL;
-		spin_lock_irq(&child->sighand->siglock);
 		if (likely(child->last_siginfo != NULL)) {
 			*child->last_siginfo = *info;
 			error = 0;
 		}
-		spin_unlock_irq(&child->sighand->siglock);
+		unlock_task_sighand(child, &flags);
 	}
-	read_unlock(&tasklist_lock);
 	return error;
 }
 
@@ -566,72 +577,16 @@ int ptrace_request(struct task_struct *child, long request,
 	return ret;
 }
 
-/**
- * ptrace_traceme  --  helper for PTRACE_TRACEME
- *
- * Performs checks and sets PT_PTRACED.
- * Should be used by all ptrace implementations for PTRACE_TRACEME.
- */
-int ptrace_traceme(void)
-{
-	int ret = -EPERM;
-
-	/*
-	 * Are we already being traced?
-	 */
-repeat:
-	task_lock(current);
-	if (!(current->ptrace & PT_PTRACED)) {
-		/*
-		 * See ptrace_attach() comments about the locking here.
-		 */
-		unsigned long flags;
-		if (!write_trylock_irqsave(&tasklist_lock, flags)) {
-			task_unlock(current);
-			do {
-				cpu_relax();
-			} while (!write_can_lock(&tasklist_lock));
-			goto repeat;
-		}
-
-		ret = security_ptrace_traceme(current->parent);
-
-		/*
-		 * Check PF_EXITING to ensure ->real_parent has not passed
-		 * exit_ptrace(). Otherwise we don't report the error but
-		 * pretend ->real_parent untraces us right after return.
-		 */
-		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
-			current->ptrace |= PT_PTRACED;
-			__ptrace_link(current, current->real_parent);
-		}
-
-		write_unlock_irqrestore(&tasklist_lock, flags);
-	}
-	task_unlock(current);
-	return ret;
-}
-
-/**
- * ptrace_get_task_struct  --  grab a task struct reference for ptrace
- * @pid:       process id to grab a task_struct reference of
- *
- * This function is a helper for ptrace implementations.  It checks
- * permissions and then grabs a task struct for use of the actual
- * ptrace implementation.
- *
- * Returns the task_struct for @pid or an ERR_PTR() on failure.
- */
-struct task_struct *ptrace_get_task_struct(pid_t pid)
+static struct task_struct *ptrace_get_task_struct(pid_t pid)
 {
 	struct task_struct *child;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	child = find_task_by_vpid(pid);
 	if (child)
 		get_task_struct(child);
+	rcu_read_unlock();
 
-	read_unlock(&tasklist_lock);
 	if (!child)
 		return ERR_PTR(-ESRCH);
 	return child;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0dccfbba6d2..7717b95c202 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1533,7 +1533,7 @@ void __init __rcu_init(void)
 	int j;
 	struct rcu_node *rnp;
 
-	printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+	printk(KERN_INFO "Hierarchical RCU implementation.\n");
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
@@ -1546,7 +1546,6 @@ void __init __rcu_init(void)
 		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
 	/* Register notifier for non-boot CPUs */
 	register_cpu_notifier(&rcu_nb);
-	printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
 }
 
 module_param(blimit, int, 0);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index bf8e7534c80..e1338f07431 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -18,7 +18,7 @@
 void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
-	counter->limit = (unsigned long long)LLONG_MAX;
+	counter->limit = RESOURCE_MAX;
 	counter->parent = parent;
 }
 
@@ -133,6 +133,16 @@ int res_counter_memparse_write_strategy(const char *buf,
 					unsigned long long *res)
 {
 	char *end;
+
+	/* return RESOURCE_MAX(unlimited) if "-1" is specified */
+	if (*buf == '-') {
+		*res = simple_strtoull(buf + 1, &end, 10);
+		if (*res != 1 || *end != '\0')
+			return -EINVAL;
+		*res = RESOURCE_MAX;
+		return 0;
+	}
+
 	/* FIXME - make memparse() take const char* args */
 	*res = memparse((char *)buf, &end);
 	if (*end != '\0')
diff --git a/kernel/resource.c b/kernel/resource.c
index ac5f3a36923..78b087221c1 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -787,7 +787,7 @@ static int __init reserve_setup(char *str)
 	static struct resource reserve[MAXRESERVE];
 
 	for (;;) {
-		int io_start, io_num;
+		unsigned int io_start, io_num;
 		int x = reserved;
 
 		if (get_option (&str, &io_start) != 2)
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index fcd107a78c5..29bd4baf9e7 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
 		/* We got the lock for task. */
 		debug_rt_mutex_lock(lock);
-
 		rt_mutex_set_owner(lock, task, 0);
-
+		spin_unlock(&lock->wait_lock);
 		rt_mutex_deadlock_account_lock(lock, task);
 		return 1;
 	}
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-
 	if (ret && !waiter->task) {
 		/*
 		 * Reset the return value. We might have
diff --git a/kernel/sched.c b/kernel/sched.c
index 8fb88a906aa..1b59e265273 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -493,6 +493,7 @@ struct rt_rq {
 #endif
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
+	unsigned long rt_nr_total;
 	int overloaded;
 	struct plist_head pushable_tasks;
 #endif
@@ -1978,7 +1979,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (task_hot(p, old_rq->clock, NULL))
 			schedstat_inc(p, se.nr_forced2_migrations);
 #endif
-		perf_counter_task_migration(p, new_cpu);
+		perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+				     1, 1, NULL, 0);
 	}
 	p->se.vruntime -= old_cfsrq->min_vruntime -
 					 new_cfsrq->min_vruntime;
@@ -2570,15 +2572,37 @@ static void __sched_fork(struct task_struct *p)
 	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_start		= 0;
-	p->se.sum_sleep_runtime		= 0;
-	p->se.sleep_start		= 0;
-	p->se.block_start		= 0;
-	p->se.sleep_max			= 0;
-	p->se.block_max			= 0;
-	p->se.exec_max			= 0;
-	p->se.slice_max			= 0;
-	p->se.wait_max			= 0;
+	p->se.wait_start			= 0;
+	p->se.wait_max				= 0;
+	p->se.wait_count			= 0;
+	p->se.wait_sum				= 0;
+
+	p->se.sleep_start			= 0;
+	p->se.sleep_max				= 0;
+	p->se.sum_sleep_runtime			= 0;
+
+	p->se.block_start			= 0;
+	p->se.block_max				= 0;
+	p->se.exec_max				= 0;
+	p->se.slice_max				= 0;
+
+	p->se.nr_migrations_cold		= 0;
+	p->se.nr_failed_migrations_affine	= 0;
+	p->se.nr_failed_migrations_running	= 0;
+	p->se.nr_failed_migrations_hot		= 0;
+	p->se.nr_forced_migrations		= 0;
+	p->se.nr_forced2_migrations		= 0;
+
+	p->se.nr_wakeups			= 0;
+	p->se.nr_wakeups_sync			= 0;
+	p->se.nr_wakeups_migrate		= 0;
+	p->se.nr_wakeups_local			= 0;
+	p->se.nr_wakeups_remote			= 0;
+	p->se.nr_wakeups_affine			= 0;
+	p->se.nr_wakeups_affine_attempts	= 0;
+	p->se.nr_wakeups_passive		= 0;
+	p->se.nr_wakeups_idle			= 0;
+
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -6540,6 +6564,11 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
+static inline int should_resched(void)
+{
+	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
 static void __cond_resched(void)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -6559,8 +6588,7 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
-					system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		__cond_resched();
 		return 1;
 	}
@@ -6578,12 +6606,12 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int cond_resched_lock(spinlock_t *lock)
 {
-	int resched = need_resched() && system_state == SYSTEM_RUNNING;
+	int resched = should_resched();
 	int ret = 0;
 
 	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
-		if (resched && need_resched())
+		if (resched)
 			__cond_resched();
 		else
 			cpu_relax();
@@ -6598,7 +6626,7 @@ int __sched cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (need_resched() && system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
 		local_bh_disable();
@@ -7045,7 +7073,7 @@ static int migration_thread(void *data)
 
 		if (cpu_is_offline(cpu)) {
 			spin_unlock_irq(&rq->lock);
-			goto wait_to_die;
+			break;
 		}
 
 		if (rq->active_balance) {
@@ -7071,16 +7099,7 @@ static int migration_thread(void *data)
 		complete(&req->done);
 	}
 	__set_current_state(TASK_RUNNING);
-	return 0;
 
-wait_to_die:
-	/* Wait for kthread_stop */
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
-	}
-	__set_current_state(TASK_RUNNING);
 	return 0;
 }
 
@@ -7270,6 +7289,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 static void calc_global_load_remove(struct rq *rq)
 {
 	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+	rq->calc_load_active = 0;
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -7494,7 +7514,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		rq = task_rq_lock(p, &flags);
 		__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 		task_rq_unlock(rq, &flags);
+		get_task_struct(p);
 		cpu_rq(cpu)->migration_thread = p;
+		rq->calc_load_update = calc_load_update;
 		break;
 
 	case CPU_ONLINE:
@@ -7505,8 +7527,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
-		rq->calc_load_update = calc_load_update;
-		rq->calc_load_active = 0;
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
@@ -7524,6 +7544,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		kthread_bind(cpu_rq(cpu)->migration_thread,
 			     cpumask_any(cpu_online_mask));
 		kthread_stop(cpu_rq(cpu)->migration_thread);
+		put_task_struct(cpu_rq(cpu)->migration_thread);
 		cpu_rq(cpu)->migration_thread = NULL;
 		break;
 
@@ -7533,6 +7554,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		migrate_live_tasks(cpu);
 		rq = cpu_rq(cpu);
 		kthread_stop(rq->migration_thread);
+		put_task_struct(rq->migration_thread);
 		rq->migration_thread = NULL;
 		/* Idle task back to normal (off runqueue, low prio) */
 		spin_lock_irq(&rq->lock);
@@ -7828,7 +7850,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		free_rootdomain(old_rd);
 }
 
-static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
+static int init_rootdomain(struct root_domain *rd, bool bootmem)
 {
 	gfp_t gfp = GFP_KERNEL;
 
@@ -9075,7 +9097,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
-	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
+	plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
 #endif
 
 	rt_rq->rt_time = 0;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 7deffc9f0e5..d014efbf947 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -81,8 +81,21 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
 			continue;
 
-		if (lowest_mask)
+		if (lowest_mask) {
 			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+
+			/*
+			 * We have to ensure that we have at least one bit
+			 * still set in the array, since the map could have
+			 * been concurrently emptied between the first and
+			 * second reads of vec->mask.  If we hit this
+			 * condition, simply act as though we never hit this
+			 * priority level and continue on.
+			 */
+			if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+				continue;
+		}
+
 		return 1;
 	}
 
@@ -152,7 +165,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
  *
  * Returns: -ENOMEM if memory fails.
  */
-int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
+int cpupri_init(struct cpupri *cp, bool bootmem)
 {
 	gfp_t gfp = GFP_KERNEL;
 	int i;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 467ca72f165..70c7e0b7994 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -162,7 +162,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
 		spread, rq0_min_vruntime, spread0;
-	struct rq *rq = &per_cpu(runqueues, cpu);
+	struct rq *rq = cpu_rq(cpu);
 	struct sched_entity *last;
 	unsigned long flags;
 
@@ -191,7 +191,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	if (last)
 		max_vruntime = last->vruntime;
 	min_vruntime = cfs_rq->min_vruntime;
-	rq0_min_vruntime = per_cpu(runqueues, 0).cfs.min_vruntime;
+	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
 	spin_unlock_irqrestore(&rq->lock, flags);
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
 			SPLIT_NS(MIN_vruntime));
@@ -248,7 +248,7 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 static void print_cpu(struct seq_file *m, int cpu)
 {
-	struct rq *rq = &per_cpu(runqueues, cpu);
+	struct rq *rq = cpu_rq(cpu);
 
 #ifdef CONFIG_X86
 	{
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5f9650e8fe7..652e8bdef9a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
 	return min_vruntime;
 }
 
+static inline int entity_before(struct sched_entity *a,
+				struct sched_entity *b)
+{
+	return (s64)(a->vruntime - b->vruntime) < 0;
+}
+
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return se->vruntime - cfs_rq->min_vruntime;
@@ -430,12 +436,13 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	for_each_sched_entity(se) {
 		struct load_weight *load;
+		struct load_weight lw;
 
 		cfs_rq = cfs_rq_of(se);
 		load = &cfs_rq->load;
 
 		if (unlikely(!se->on_rq)) {
-			struct load_weight lw = cfs_rq->load;
+			lw = cfs_rq->load;
 
 			update_load_add(&lw, se->load.weight);
 			load = &lw;
@@ -604,9 +611,13 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 #ifdef CONFIG_SCHEDSTATS
+	struct task_struct *tsk = NULL;
+
+	if (entity_is_task(se))
+		tsk = task_of(se);
+
 	if (se->sleep_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
-		struct task_struct *tsk = task_of(se);
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -617,11 +628,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->sleep_start = 0;
 		se->sum_sleep_runtime += delta;
 
-		account_scheduler_latency(tsk, delta >> 10, 1);
+		if (tsk)
+			account_scheduler_latency(tsk, delta >> 10, 1);
 	}
 	if (se->block_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
-		struct task_struct *tsk = task_of(se);
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -632,17 +643,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		se->block_start = 0;
 		se->sum_sleep_runtime += delta;
 
-		/*
-		 * Blocking time is in units of nanosecs, so shift by 20 to
-		 * get a milliseconds-range estimation of the amount of
-		 * time that the task spent sleeping:
-		 */
-		if (unlikely(prof_on == SLEEP_PROFILING)) {
-
-			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
-				     delta >> 20);
+		if (tsk) {
+			/*
+			 * Blocking time is in units of nanosecs, so shift by
+			 * 20 to get a milliseconds-range estimation of the
+			 * amount of time that the task spent sleeping:
+			 */
+			if (unlikely(prof_on == SLEEP_PROFILING)) {
+				profile_hits(SLEEP_PROFILING,
+						(void *)get_wchan(tsk),
+						delta >> 20);
+			}
+			account_scheduler_latency(tsk, delta >> 10, 0);
 		}
-		account_scheduler_latency(tsk, delta >> 10, 0);
 	}
 #endif
 }
@@ -686,7 +699,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 			 * all of which have the same weight.
 			 */
 			if (sched_feat(NORMALIZED_SLEEPER) &&
-					task_of(se)->policy != SCHED_IDLE)
+					(!entity_is_task(se) ||
+					 task_of(se)->policy != SCHED_IDLE))
 				thresh = calc_delta_fair(thresh, se);
 
 			vruntime -= thresh;
@@ -1015,7 +1029,7 @@ static void yield_task_fair(struct rq *rq)
 	/*
 	 * Already in the rightmost position?
 	 */
-	if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
+	if (unlikely(!rightmost || entity_before(rightmost, se)))
 		return;
 
 	/*
@@ -1711,7 +1725,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 
 	/* 'curr' will be NULL if the child belongs to a different group */
 	if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
-			curr && curr->vruntime < se->vruntime) {
+			curr && entity_before(curr, se)) {
 		/*
 		 * Upon rescheduling, sched_class::put_prev_task() will place
 		 * 'current' within the tree based on its new key value.
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9bf0d2a7304..3918e01994e 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -10,6 +10,8 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 
 #ifdef CONFIG_RT_GROUP_SCHED
 
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return rt_rq->rq;
@@ -22,6 +24,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 
 #else /* CONFIG_RT_GROUP_SCHED */
 
+#define rt_entity_is_task(rt_se) (1)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return container_of(rt_rq, struct rq, rt);
@@ -73,7 +77,7 @@ static inline void rt_clear_overload(struct rq *rq)
 
 static void update_rt_migration(struct rt_rq *rt_rq)
 {
-	if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
+	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
 		if (!rt_rq->overloaded) {
 			rt_set_overload(rq_of_rt_rq(rt_rq));
 			rt_rq->overloaded = 1;
@@ -86,6 +90,12 @@ static void update_rt_migration(struct rt_rq *rt_rq)
 
 static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total++;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
@@ -94,6 +104,12 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 
 static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total--;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;
 
diff --git a/kernel/signal.c b/kernel/signal.c
index d81f4952eeb..64c5deeaca5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1410,7 +1410,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
  	/* do_notify_parent_cldstop should have been called instead.  */
  	BUG_ON(task_is_stopped_or_traced(tsk));
 
-	BUG_ON(!tsk->ptrace &&
+	BUG_ON(!task_ptrace(tsk) &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
 	info.si_signo = sig;
@@ -1449,7 +1449,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	psig = tsk->parent->sighand;
 	spin_lock_irqsave(&psig->siglock, flags);
-	if (!tsk->ptrace && sig == SIGCHLD &&
+	if (!task_ptrace(tsk) && sig == SIGCHLD &&
 	    (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
 	     (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
 		/*
@@ -1486,7 +1486,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 	struct task_struct *parent;
 	struct sighand_struct *sighand;
 
-	if (tsk->ptrace & PT_PTRACED)
+	if (task_ptrace(tsk))
 		parent = tsk->parent;
 	else {
 		tsk = tsk->group_leader;
@@ -1499,7 +1499,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 	 * see comment in do_notify_parent() abot the following 3 lines
 	 */
 	rcu_read_lock();
-	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+	info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
 	info.si_uid = __task_cred(tsk)->uid;
 	rcu_read_unlock();
 
@@ -1535,7 +1535,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 
 static inline int may_ptrace_stop(void)
 {
-	if (!likely(current->ptrace & PT_PTRACED))
+	if (!likely(task_ptrace(current)))
 		return 0;
 	/*
 	 * Are we in the middle of do_coredump?
@@ -1753,7 +1753,7 @@ static int do_signal_stop(int signr)
 static int ptrace_signal(int signr, siginfo_t *info,
 			 struct pt_regs *regs, void *cookie)
 {
-	if (!(current->ptrace & PT_PTRACED))
+	if (!task_ptrace(current))
 		return signr;
 
 	ptrace_signal_deliver(regs, cookie);
@@ -2454,11 +2454,9 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
 	stack_t oss;
 	int error;
 
-	if (uoss) {
-		oss.ss_sp = (void __user *) current->sas_ss_sp;
-		oss.ss_size = current->sas_ss_size;
-		oss.ss_flags = sas_ss_flags(sp);
-	}
+	oss.ss_sp = (void __user *) current->sas_ss_sp;
+	oss.ss_size = current->sas_ss_size;
+	oss.ss_flags = sas_ss_flags(sp);
 
 	if (uss) {
 		void __user *ss_sp;
@@ -2466,10 +2464,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
 		int ss_flags;
 
 		error = -EFAULT;
-		if (!access_ok(VERIFY_READ, uss, sizeof(*uss))
-		    || __get_user(ss_sp, &uss->ss_sp)
-		    || __get_user(ss_flags, &uss->ss_flags)
-		    || __get_user(ss_size, &uss->ss_size))
+		if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
+			goto out;
+		error = __get_user(ss_sp, &uss->ss_sp) |
+			__get_user(ss_flags, &uss->ss_flags) |
+			__get_user(ss_size, &uss->ss_size);
+		if (error)
 			goto out;
 
 		error = -EPERM;
@@ -2501,13 +2501,16 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
 		current->sas_ss_size = ss_size;
 	}
 
+	error = 0;
 	if (uoss) {
 		error = -EFAULT;
-		if (copy_to_user(uoss, &oss, sizeof(oss)))
+		if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss)))
 			goto out;
+		error = __put_user(oss.ss_sp, &uoss->ss_sp) |
+			__put_user(oss.ss_size, &uoss->ss_size) |
+			__put_user(oss.ss_flags, &uoss->ss_flags);
 	}
 
-	error = 0;
 out:
 	return error;
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index ad63d850120..94188b8ecc3 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -57,7 +57,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			return NOTIFY_BAD;
 		break;
 
-#ifdef CONFIG_CPU_HOTPLUG
+#ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b41fb710e11..eb5e131a048 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -213,6 +213,7 @@ restart:
 	do {
 		if (pending & 1) {
 			int prev_count = preempt_count();
+			kstat_incr_softirqs_this_cpu(h - softirq_vec);
 
 			trace_softirq_entry(h, softirq_vec);
 			h->action(h);
@@ -344,7 +345,9 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
 	softirq_vec[nr].action = action;
 }
 
-/* Tasklets */
+/*
+ * Tasklets
+ */
 struct tasklet_head
 {
 	struct tasklet_struct *head;
@@ -492,6 +495,66 @@ void tasklet_kill(struct tasklet_struct *t)
 
 EXPORT_SYMBOL(tasklet_kill);
 
+/*
+ * tasklet_hrtimer
+ */
+
+/*
+ * The trampoline is called when the hrtimer expires. If this is
+ * called from the hrtimer interrupt then we schedule the tasklet as
+ * the timer callback function expects to run in softirq context. If
+ * it's called in softirq context anyway (i.e. high resolution timers
+ * disabled) then the hrtimer callback is called right away.
+ */
+static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
+{
+	struct tasklet_hrtimer *ttimer =
+		container_of(timer, struct tasklet_hrtimer, timer);
+
+	if (hrtimer_is_hres_active(timer)) {
+		tasklet_hi_schedule(&ttimer->tasklet);
+		return HRTIMER_NORESTART;
+	}
+	return ttimer->function(timer);
+}
+
+/*
+ * Helper function which calls the hrtimer callback from
+ * tasklet/softirq context
+ */
+static void __tasklet_hrtimer_trampoline(unsigned long data)
+{
+	struct tasklet_hrtimer *ttimer = (void *)data;
+	enum hrtimer_restart restart;
+
+	restart = ttimer->function(&ttimer->timer);
+	if (restart != HRTIMER_NORESTART)
+		hrtimer_restart(&ttimer->timer);
+}
+
+/**
+ * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
+ * @ttimer:	 tasklet_hrtimer which is initialized
+ * @function:	 hrtimer callback funtion which gets called from softirq context
+ * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
+ * @mode:	 hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
+ */
+void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
+			  enum hrtimer_restart (*function)(struct hrtimer *),
+			  clockid_t which_clock, enum hrtimer_mode mode)
+{
+	hrtimer_init(&ttimer->timer, which_clock, mode);
+	ttimer->timer.function = __hrtimer_tasklet_trampoline;
+	tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
+		     (unsigned long)ttimer);
+	ttimer->function = function;
+}
+EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
+
+/*
+ * Remote softirq bits
+ */
+
 DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
 EXPORT_PER_CPU_SYMBOL(softirq_work_list);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ab462b9968d..58be76017fd 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -49,6 +49,7 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/security.h>
 #include <linux/slow-work.h>
 #include <linux/perf_counter.h>
 
@@ -335,7 +336,10 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 #endif
 	{
@@ -744,6 +748,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
 		.ctl_name	= KERN_BOOTLOADER_TYPE,
 		.procname	= "bootloader_type",
 		.data		= &bootloader_type,
@@ -1295,10 +1307,10 @@ static struct ctl_table vm_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "mmap_min_addr",
-		.data		= &mmap_min_addr,
-		.maxlen         = sizeof(unsigned long),
+		.data		= &dac_mmap_min_addr,
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= &proc_doulongvec_minmax,
+		.proc_handler	= &mmap_min_addr_handler,
 	},
 #ifdef CONFIG_NUMA
 	{
@@ -2283,7 +2295,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 		  void *data)
 {
 #define TMPBUFLEN 21
-	int *i, vleft, first=1, neg, val;
+	int *i, vleft, first = 1, neg;
 	unsigned long lval;
 	size_t left, len;
 	
@@ -2336,8 +2348,6 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 			len = p-buf;
 			if ((len < left) && *p && !isspace(*p))
 				break;
-			if (neg)
-				val = -val;
 			s += len;
 			left -= len;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ad6dd46111..620b58abdc3 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -137,11 +137,12 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
  */
 int clockevents_register_notifier(struct notifier_block *nb)
 {
+	unsigned long flags;
 	int ret;
 
-	spin_lock(&clockevents_lock);
+	spin_lock_irqsave(&clockevents_lock, flags);
 	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	spin_unlock(&clockevents_lock);
+	spin_unlock_irqrestore(&clockevents_lock, flags);
 
 	return ret;
 }
@@ -178,16 +179,18 @@ static void clockevents_notify_released(void)
  */
 void clockevents_register_device(struct clock_event_device *dev)
 {
+	unsigned long flags;
+
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
 	BUG_ON(!dev->cpumask);
 
-	spin_lock(&clockevents_lock);
+	spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
 	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
 	clockevents_notify_released();
 
-	spin_unlock(&clockevents_lock);
+	spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
@@ -235,8 +238,9 @@ void clockevents_exchange_device(struct clock_event_device *old,
 void clockevents_notify(unsigned long reason, void *arg)
 {
 	struct list_head *node, *tmp;
+	unsigned long flags;
 
-	spin_lock(&clockevents_lock);
+	spin_lock_irqsave(&clockevents_lock, flags);
 	clockevents_do_notify(reason, arg);
 
 	switch (reason) {
@@ -251,18 +255,7 @@ void clockevents_notify(unsigned long reason, void *arg)
 	default:
 		break;
 	}
-	spin_unlock(&clockevents_lock);
+	spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
-
-ktime_t clockevents_get_next_event(int cpu)
-{
-	struct tick_device *td;
-	struct clock_event_device *dev;
-
-	td = &per_cpu(tick_cpu_device, cpu);
-	dev = td->evtdev;
-
-	return dev->next_event;
-}
 #endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 592bf584d1d..7466cb81125 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -513,7 +513,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 	 * Check to make sure we don't switch to a non-highres capable
 	 * clocksource if the tick code is in oneshot mode (highres or nohz)
 	 */
-	if (tick_oneshot_mode_active() &&
+	if (tick_oneshot_mode_active() && ovr &&
 	    !(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) {
 		printk(KERN_WARNING "%s clocksource is not HRT compatible. "
 			"Cannot switch while in HRT/NOHZ mode\n", ovr->name);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 877dbedc311..c2ec25087a3 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -205,11 +205,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
  * Powerstate information: The system enters/leaves a state, where
  * affected devices might stop
  */
-static void tick_do_broadcast_on_off(void *why)
+static void tick_do_broadcast_on_off(unsigned long *reason)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
-	unsigned long flags, *reason = why;
+	unsigned long flags;
 	int cpu, bc_stopped;
 
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
@@ -276,8 +276,7 @@ void tick_broadcast_on_off(unsigned long reason, int *oncpu)
 		printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
 		       "offline CPU #%d\n", *oncpu);
 	else
-		smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
-					 &reason, 1);
+		tick_do_broadcast_on_off(&reason);
 }
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2aff39c6f10..e0f59a21c06 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -222,6 +222,15 @@ void tick_nohz_stop_sched_tick(int inidle)
 
 	cpu = smp_processor_id();
 	ts = &per_cpu(tick_cpu_sched, cpu);
+
+	/*
+	 * Call to tick_nohz_start_idle stops the last_update_time from being
+	 * updated. Thus, it must not be called in the event we are called from
+	 * irq_exit() with the prior state different than idle.
+	 */
+	if (!inidle && !ts->inidle)
+		goto end;
+
 	now = tick_nohz_start_idle(ts);
 
 	/*
@@ -239,9 +248,6 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
 		goto end;
 
-	if (!inidle && !ts->inidle)
-		goto end;
-
 	ts->inidle = 1;
 
 	if (need_resched())
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index a999b92a127..fddd69d16e0 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -286,7 +286,7 @@ static int __init init_timer_list_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = proc_create("timer_list", 0644, NULL, &timer_list_fops);
+	pe = proc_create("timer_list", 0444, NULL, &timer_list_fops);
 	if (!pe)
 		return -ENOMEM;
 	return 0;
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index c994530d166..4cde8b9c716 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex);
 /*
  * Collection status, active/inactive:
  */
-static int __read_mostly active;
+int __read_mostly timer_stats_active;
 
 /*
  * Beginning/end timestamps of measurement:
@@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	struct entry *entry, input;
 	unsigned long flags;
 
-	if (likely(!active))
+	if (likely(!timer_stats_active))
 		return;
 
 	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
@@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	input.timer_flag = timer_flag;
 
 	spin_lock_irqsave(lock, flags);
-	if (!active)
+	if (!timer_stats_active)
 		goto out_unlock;
 
 	entry = tstat_lookup(&input, comm);
@@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v)
 	/*
 	 * If still active then calculate up to now:
 	 */
-	if (active)
+	if (timer_stats_active)
 		time_stop = ktime_get();
 
 	time = ktime_sub(time_stop, time_start);
@@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf,
 	mutex_lock(&show_mutex);
 	switch (ctl[0]) {
 	case '0':
-		if (active) {
-			active = 0;
+		if (timer_stats_active) {
+			timer_stats_active = 0;
 			time_stop = ktime_get();
 			sync_access();
 		}
 		break;
 	case '1':
-		if (!active) {
+		if (!timer_stats_active) {
 			reset_entries();
 			time_start = ktime_get();
 			smp_mb();
-			active = 1;
+			timer_stats_active = 1;
 		}
 		break;
 	default:
diff --git a/kernel/timer.c b/kernel/timer.c
index 54d3912f8ca..a7f07d5a624 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer)
 {
 	unsigned int flag = 0;
 
+	if (likely(!timer->start_site))
+		return;
 	if (unlikely(tbase_get_deferrable(timer->base)))
 		flag |= TIMER_STATS_FLAG_DEFERRABLE;
 
@@ -712,7 +714,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	 * networking code - if the timer is re-modified
 	 * to be the same thing then just return:
 	 */
-	if (timer->expires == expires && timer_pending(timer))
+	if (timer_pending(timer) && timer->expires == expires)
 		return 1;
 
 	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index ae048a2dbbe..5efeb4229ea 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -18,6 +18,13 @@ config HAVE_FUNCTION_TRACER
 config HAVE_FUNCTION_GRAPH_TRACER
 	bool
 
+config HAVE_FUNCTION_GRAPH_FP_TEST
+	bool
+	help
+	 An arch may pass in a unique value (frame pointer) to both the
+	 entering and exiting of a function. On exit, the value is compared
+	 and if it does not match, then it will panic the kernel.
+
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	bool
 	help
@@ -34,7 +41,7 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
 	bool
 
-config HAVE_FTRACE_SYSCALLS
+config HAVE_SYSCALL_TRACEPOINTS
 	bool
 
 config TRACER_MAX_TRACE
@@ -53,9 +60,14 @@ config EVENT_TRACING
 	bool
 
 config CONTEXT_SWITCH_TRACER
-	select MARKERS
 	bool
 
+config RING_BUFFER_ALLOW_SWAP
+	bool
+	help
+	 Allow the use of ring_buffer_swap_cpu.
+	 Adds a very slight overhead to tracing when enabled.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
@@ -121,6 +133,7 @@ config FUNCTION_GRAPH_TRACER
 	bool "Kernel Function Graph Tracer"
 	depends on HAVE_FUNCTION_GRAPH_TRACER
 	depends on FUNCTION_TRACER
+	depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
 	default y
 	help
 	  Enable the kernel to trace a function at both its return
@@ -139,6 +152,7 @@ config IRQSOFF_TRACER
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -160,6 +174,7 @@ config PREEMPT_TRACER
 	depends on PREEMPT
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in preemption off critical
 	  sections, with microsecond accuracy.
@@ -203,7 +218,7 @@ config ENABLE_DEFAULT_TRACERS
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
-	depends on HAVE_FTRACE_SYSCALLS
+	depends on HAVE_SYSCALL_TRACEPOINTS
 	select GENERIC_TRACER
 	select KALLSYMS
 	help
@@ -218,13 +233,13 @@ config BOOT_TRACER
 	  the timings of the initcalls and traces key events and the identity
 	  of tasks that can cause boot delays, such as context-switches.
 
-	  Its aim is to be parsed by the /scripts/bootgraph.pl tool to
+	  Its aim is to be parsed by the scripts/bootgraph.pl tool to
 	  produce pretty graphics about boot inefficiencies, giving a visual
 	  representation of the delays during initcalls - but the raw
 	  /debug/tracing/trace text output is readable too.
 
-	  You must pass in ftrace=initcall to the kernel command line
-	  to enable this on bootup.
+	  You must pass in initcall_debug and ftrace=initcall to the kernel
+	  command line to enable this on bootup.
 
 config TRACE_BRANCH_PROFILING
 	bool
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 39af8af6fc3..3eb159c277c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
+#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
@@ -64,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
 						  0, pc);
 		if (!event)
@@ -95,7 +98,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 	}
 }
 
@@ -178,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
@@ -203,8 +207,9 @@ 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;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
 						  0, pc);
 		if (!event)
@@ -251,7 +256,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 			return;
 		}
 	}
@@ -266,8 +271,8 @@ static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
-	debugfs_remove(bt->dir);
 	relay_close(bt->rchan);
+	debugfs_remove(bt->dir);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
@@ -377,18 +382,8 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
-	struct dentry *parent = dentry->d_parent;
 	debugfs_remove(dentry);
 
-	/*
-	* this will fail for all but the last file, but that is ok. what we
-	* care about is the top level buts->name directory going away, when
-	* the last trace file is gone. Then we don't have to rmdir() that
-	* manually on trace stop, so it nicely solves the issue with
-	* force killing of running traces.
-	*/
-
-	debugfs_remove(parent);
 	return 0;
 }
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bb60732ade0..8c804e24f96 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -291,7 +291,9 @@ function_stat_next(void *v, int idx)
 	pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
 
  again:
-	rec++;
+	if (idx != 0)
+		rec++;
+
 	if ((void *)rec >= (void *)&pg->records[pg->index]) {
 		pg = pg->next;
 		if (!pg)
@@ -766,7 +768,7 @@ static struct tracer_stat function_stats __initdata = {
 	.stat_show	= function_stat_show
 };
 
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
 	struct ftrace_profile_stat *stat;
 	struct dentry *entry;
@@ -784,7 +786,6 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
 			 * The files created are permanent, if something happens
 			 * we still do not free memory.
 			 */
-			kfree(stat);
 			WARN(1,
 			     "Could not allocate stat file for cpu %d\n",
 			     cpu);
@@ -811,7 +812,7 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
 }
 
 #else /* CONFIG_FUNCTION_PROFILER */
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
 }
 #endif /* CONFIG_FUNCTION_PROFILER */
@@ -1015,71 +1016,35 @@ static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
-	unsigned long ip, fl;
+	unsigned long flag = 0UL;
 
 	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
-	ip = rec->ip;
-
 	/*
-	 * If this record is not to be traced and
-	 * it is not enabled then do nothing.
+	 * If this record is not to be traced or we want to disable it,
+	 * then disable it.
 	 *
-	 * If this record is not to be traced and
-	 * it is enabled then disable it.
+	 * If we want to enable it and filtering is off, then enable it.
 	 *
+	 * If we want to enable it and filtering is on, enable it only if
+	 * it's filtered
 	 */
-	if (rec->flags & FTRACE_FL_NOTRACE) {
-		if (rec->flags & FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-			return 0;
-
-	} else if (ftrace_filtered && enable) {
-		/*
-		 * Filtering is on:
-		 */
-
-		fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);
-
-		/* Record is filtered and enabled, do nothing */
-		if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED))
-			return 0;
-
-		/* Record is not filtered or enabled, do nothing */
-		if (!fl)
-			return 0;
-
-		/* Record is not filtered but enabled, disable it */
-		if (fl == FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-		/* Otherwise record is filtered but not enabled, enable it */
-			rec->flags |= FTRACE_FL_ENABLED;
-	} else {
-		/* Disable or not filtered */
-
-		if (enable) {
-			/* if record is enabled, do nothing */
-			if (rec->flags & FTRACE_FL_ENABLED)
-				return 0;
-
-			rec->flags |= FTRACE_FL_ENABLED;
-
-		} else {
+	if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
+		if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
+			flag = FTRACE_FL_ENABLED;
+	}
 
-			/* if record is not enabled, do nothing */
-			if (!(rec->flags & FTRACE_FL_ENABLED))
-				return 0;
+	/* If the state of this record hasn't changed, then do nothing */
+	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
+		return 0;
 
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		}
+	if (flag) {
+		rec->flags |= FTRACE_FL_ENABLED;
+		return ftrace_make_call(rec, ftrace_addr);
 	}
 
-	if (rec->flags & FTRACE_FL_ENABLED)
-		return ftrace_make_call(rec, ftrace_addr);
-	else
-		return ftrace_make_nop(NULL, rec, ftrace_addr);
+	rec->flags &= ~FTRACE_FL_ENABLED;
+	return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
@@ -1224,6 +1189,13 @@ static void ftrace_shutdown(int command)
 		return;
 
 	ftrace_start_up--;
+	/*
+	 * Just warn in case of unbalance, no need to kill ftrace, it's not
+	 * critical but the ftrace_call callers may be never nopped again after
+	 * further ftrace uses.
+	 */
+	WARN_ON_ONCE(ftrace_start_up < 0);
+
 	if (!ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
@@ -1367,7 +1339,6 @@ struct ftrace_iterator {
 	unsigned		flags;
 	unsigned char		buffer[FTRACE_BUFF_MAX+1];
 	unsigned		buffer_idx;
-	unsigned		filtered;
 };
 
 static void *
@@ -1410,28 +1381,33 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
 	void *p = NULL;
+	loff_t l;
+
+	if (!(iter->flags & FTRACE_ITER_HASH))
+		*pos = 0;
 
 	iter->flags |= FTRACE_ITER_HASH;
 
-	return t_hash_next(m, p, pos);
+	iter->hidx = 0;
+	for (l = 0; l <= *pos; ) {
+		p = t_hash_next(m, p, &l);
+		if (!p)
+			break;
+	}
+	return p;
 }
 
 static int t_hash_show(struct seq_file *m, void *v)
 {
 	struct ftrace_func_probe *rec;
 	struct hlist_node *hnd = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	rec = hlist_entry(hnd, struct ftrace_func_probe, node);
 
 	if (rec->ops->print)
 		return rec->ops->print(m, rec->ip, rec->ops, rec->data);
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
-
-	kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str);
-	seq_printf(m, "%s", str);
+	seq_printf(m, "%pf:%pf", (void *)rec->ip, (void *)rec->ops->func);
 
 	if (rec->data)
 		seq_printf(m, ":%p", rec->data);
@@ -1460,8 +1436,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 			iter->pg = iter->pg->next;
 			iter->idx = 0;
 			goto retry;
-		} else {
-			iter->idx = -1;
 		}
 	} else {
 		rec = &iter->pg->records[iter->idx++];
@@ -1490,6 +1464,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
 	void *p = NULL;
+	loff_t l;
 
 	mutex_lock(&ftrace_lock);
 	/*
@@ -1501,23 +1476,21 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
-		(*pos)++;
 		return iter;
 	}
 
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_start(m, pos);
 
-	if (*pos > 0) {
-		if (iter->idx < 0)
-			return p;
-		(*pos)--;
-		iter->idx--;
+	iter->pg = ftrace_pages_start;
+	iter->idx = 0;
+	for (l = 0; l <= *pos; ) {
+		p = t_next(m, p, &l);
+		if (!p)
+			break;
 	}
 
-	p = t_next(m, p, pos);
-
-	if (!p)
+	if (!p && iter->flags & FTRACE_ITER_FILTER)
 		return t_hash_start(m, pos);
 
 	return p;
@@ -1532,7 +1505,6 @@ static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
 	struct dyn_ftrace *rec = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_show(m, v);
@@ -1545,9 +1517,7 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%pf\n", (void *)rec->ip);
 
 	return 0;
 }
@@ -1586,17 +1556,6 @@ ftrace_avail_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-int ftrace_avail_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *m = (struct seq_file *)file->private_data;
-	struct ftrace_iterator *iter = m->private;
-
-	seq_release(inode, file);
-	kfree(iter);
-
-	return 0;
-}
-
 static int
 ftrace_failures_open(struct inode *inode, struct file *file)
 {
@@ -1647,7 +1606,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 
 	mutex_lock(&ftrace_regex_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND))
+	    (file->f_flags & O_TRUNC))
 		ftrace_filter_reset(enable);
 
 	if (file->f_mode & FMODE_READ) {
@@ -2263,7 +2222,11 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	read++;
 	cnt--;
 
-	if (!(iter->flags & ~FTRACE_ITER_CONT)) {
+	/*
+	 * If the parser haven't finished with the last write,
+	 * continue reading the user input without skipping spaces.
+	 */
+	if (!(iter->flags & FTRACE_ITER_CONT)) {
 		/* skip white space */
 		while (cnt && isspace(ch)) {
 			ret = get_user(ch, ubuf++);
@@ -2273,8 +2236,9 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 			cnt--;
 		}
 
+		/* only spaces were written */
 		if (isspace(ch)) {
-			file->f_pos += read;
+			*ppos += read;
 			ret = read;
 			goto out;
 		}
@@ -2297,19 +2261,18 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	}
 
 	if (isspace(ch)) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ret = ftrace_process_regex(iter->buffer,
 					   iter->buffer_idx, enable);
 		if (ret)
 			goto out;
 		iter->buffer_idx = 0;
-	} else
+	} else {
 		iter->flags |= FTRACE_ITER_CONT;
+		iter->buffer[iter->buffer_idx++] = ch;
+	}
 
-
-	file->f_pos += read;
-
+	*ppos += read;
 	ret = read;
  out:
 	mutex_unlock(&ftrace_regex_lock);
@@ -2428,7 +2391,6 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 		iter = file->private_data;
 
 	if (iter->buffer_idx) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ftrace_match_records(iter->buffer, iter->buffer_idx, enable);
 	}
@@ -2459,14 +2421,14 @@ static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_avail_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_failures_fops = {
 	.open = ftrace_failures_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_filter_fops = {
@@ -2493,32 +2455,31 @@ int ftrace_graph_count;
 unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 
 static void *
-g_next(struct seq_file *m, void *v, loff_t *pos)
+__g_next(struct seq_file *m, loff_t *pos)
 {
 	unsigned long *array = m->private;
-	int index = *pos;
-
-	(*pos)++;
 
-	if (index >= ftrace_graph_count)
+	if (*pos >= ftrace_graph_count)
 		return NULL;
+	return &array[*pos];
+}
 
-	return &array[index];
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return __g_next(m, pos);
 }
 
 static void *g_start(struct seq_file *m, loff_t *pos)
 {
-	void *p = NULL;
-
 	mutex_lock(&graph_lock);
 
 	/* Nothing, tell g_show to print all functions are enabled */
 	if (!ftrace_graph_count && !*pos)
 		return (void *)1;
 
-	p = g_next(m, p, pos);
-
-	return p;
+	return __g_next(m, pos);
 }
 
 static void g_stop(struct seq_file *m, void *p)
@@ -2529,7 +2490,6 @@ static void g_stop(struct seq_file *m, void *p)
 static int g_show(struct seq_file *m, void *v)
 {
 	unsigned long *ptr = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (!ptr)
 		return 0;
@@ -2539,9 +2499,7 @@ static int g_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
-	kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%pf\n", v);
 
 	return 0;
 }
@@ -2563,7 +2521,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 
 	mutex_lock(&graph_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND)) {
+	    (file->f_flags & O_TRUNC)) {
 		ftrace_graph_count = 0;
 		memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
 	}
@@ -2582,6 +2540,14 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 }
 
 static int
+ftrace_graph_release(struct inode *inode, struct file *file)
+{
+	if (file->f_mode & FMODE_READ)
+		seq_release(inode, file);
+	return 0;
+}
+
+static int
 ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 {
 	struct dyn_ftrace *rec;
@@ -2710,9 +2676,10 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 }
 
 static const struct file_operations ftrace_graph_fops = {
-	.open = ftrace_graph_open,
-	.read = seq_read,
-	.write = ftrace_graph_write,
+	.open		= ftrace_graph_open,
+	.read		= seq_read,
+	.write		= ftrace_graph_write,
+	.release	= ftrace_graph_release,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -3145,10 +3112,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 	ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
 
-	if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
+	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
 		goto out;
 
-	last_ftrace_enabled = ftrace_enabled;
+	last_ftrace_enabled = !!ftrace_enabled;
 
 	if (ftrace_enabled) {
 
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 86cdf671d7e..81b1645c854 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void)
 
 static int kmem_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	kmemtrace_start_probes();
 
@@ -239,12 +237,52 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter,
-			   struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 {
-	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
+	    "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	    entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
+	    (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
+	    (unsigned long)entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
+			       entry->type_id, (void *)entry->call_site,
+			       (unsigned long)entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
 	struct kmemtrace_user_event *ev;
+	struct kmemtrace_user_event_alloc *ev_alloc;
+
+	trace_assign_type(entry, iter->ent);
 
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
@@ -271,12 +309,14 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter,
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter,
-			  struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
 {
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
 	struct kmemtrace_user_event *ev;
 
+	trace_assign_type(entry, iter->ent);
+
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -294,12 +334,14 @@ kmemtrace_print_free_user(struct trace_iterator *iter,
 
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter,
-					struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_alloc_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Alloc entry */
 	ret = trace_seq_printf(s, "  +      ");
 	if (!ret)
@@ -345,29 +387,24 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Node */
-	ret = trace_seq_printf(s, "%4d   ", entry->node);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	/* Node and call site*/
+	ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
+						 (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter,
-			      struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_free_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Free entry */
 	ret = trace_seq_printf(s, "  -      ");
 	if (!ret)
@@ -401,19 +438,11 @@ kmemtrace_print_free_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Skip node */
-	ret = trace_seq_printf(s, "       ");
+	/* Skip node and print call site*/
+	ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -421,32 +450,31 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 {
 	struct trace_entry *entry = iter->ent;
 
-	switch (entry->type) {
-	case TRACE_KMEM_ALLOC: {
-		struct kmemtrace_alloc_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_alloc_compress(iter, field);
-		else
-			return kmemtrace_print_alloc_user(iter, field);
-	}
-
-	case TRACE_KMEM_FREE: {
-		struct kmemtrace_free_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_free_compress(iter, field);
-		else
-			return kmemtrace_print_free_user(iter, field);
-	}
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return TRACE_TYPE_UNHANDLED;
 
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC:
+		return kmemtrace_print_alloc_compress(iter);
+	case TRACE_KMEM_FREE:
+		return kmemtrace_print_free_compress(iter);
 	default:
 		return TRACE_TYPE_UNHANDLED;
 	}
 }
 
+static struct trace_event kmem_trace_alloc = {
+	.type			= TRACE_KMEM_ALLOC,
+	.trace			= kmemtrace_print_alloc,
+	.binary			= kmemtrace_print_alloc_user,
+};
+
+static struct trace_event kmem_trace_free = {
+	.type			= TRACE_KMEM_FREE,
+	.trace			= kmemtrace_print_free,
+	.binary			= kmemtrace_print_free_user,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
 	.name			= "kmemtrace",
 	.init			= kmem_trace_init,
@@ -463,6 +491,21 @@ void kmemtrace_init(void)
 
 static int __init init_kmem_tracer(void)
 {
-	return register_tracer(&kmem_tracer);
+	if (!register_ftrace_event(&kmem_trace_alloc)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_ftrace_event(&kmem_trace_free)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_tracer(&kmem_tracer)) {
+		pr_warning("Warning: could not register the kmem tracer\n");
+		return 1;
+	}
+
+	return 0;
 }
 device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index dc4dc70171c..454e74e718c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -206,6 +206,7 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+#define RB_EVNT_MIN_SIZE	8U	/* two 32bit words */
 
 /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
 #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
@@ -217,17 +218,12 @@ enum {
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	return event->type_len == RINGBUF_TYPE_PADDING
-			&& event->time_delta == 0;
-}
-
-static inline int rb_discarded_event(struct ring_buffer_event *event)
-{
-	return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
+	return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
+	/* padding has a NULL time_delta */
 	event->type_len = RINGBUF_TYPE_PADDING;
 	event->time_delta = 0;
 }
@@ -321,6 +317,14 @@ struct buffer_data_page {
 	unsigned char	 data[];	/* data of buffer page */
 };
 
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
 struct buffer_page {
 	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
@@ -329,6 +333,21 @@ struct buffer_page {
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK		0xfffff
+#define RB_WRITE_INTCNT		(1 << 20)
+
 static void rb_init_page(struct buffer_data_page *bpage)
 {
 	local_set(&bpage->commit, 0);
@@ -402,19 +421,20 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			reader_lock; /* serialize readers */
+	spinlock_t			reader_lock;	/* serialize readers */
 	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
-	struct list_head		pages;
+	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
-	unsigned long			nmi_dropped;
-	unsigned long			commit_overrun;
-	unsigned long			overrun;
-	unsigned long			read;
+	local_t				commit_overrun;
+	local_t				overrun;
 	local_t				entries;
+	local_t				committing;
+	local_t				commits;
+	unsigned long			read;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -447,14 +467,19 @@ struct ring_buffer_iter {
 };
 
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
-#define RB_WARN_ON(buffer, cond)				\
-	({							\
-		int _____ret = unlikely(cond);			\
-		if (_____ret) {					\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-		}						\
-		_____ret;					\
+#define RB_WARN_ON(b, cond)						\
+	({								\
+		int _____ret = unlikely(cond);				\
+		if (_____ret) {						\
+			if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
+				struct ring_buffer_per_cpu *__b =	\
+					(void *)b;			\
+				atomic_inc(&__b->buffer->record_disabled); \
+			} else						\
+				atomic_inc(&b->record_disabled);	\
+			WARN_ON(1);					\
+		}							\
+		_____ret;						\
 	})
 
 /* Up this if you want to test the TIME_EXTENTS and normalization */
@@ -486,6 +511,390 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next        bit 1          bit 0
+ *                              -------        -------
+ * Normal page                     0              0
+ * Points to head page             0              1
+ * New head page                   1              0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+       +-----+        +-----+
+ * |    |------>|  T  |---X--->|  N  |
+ * |    |<------|     |        |     |
+ * +----+       +-----+        +-----+
+ *   ^                           ^ |
+ *   |          +-----+          | |
+ *   +----------|  R  |----------+ |
+ *              |     |<-----------+
+ *              +-----+
+ *
+ * Key:  ---X-->  HEAD flag set in pointer
+ *         T      Tail page
+ *         R      Reader page
+ *         N      Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ *  What the above shows is that the reader just swapped out
+ *  the reader page with a page in the buffer, but before it
+ *  could make the new header point back to the new page added
+ *  it was preempted by a writer. The writer moved forward onto
+ *  the new page added by the reader and is about to move forward
+ *  again.
+ *
+ *  You can see, it is legitimate for the previous pointer of
+ *  the head (or any page) not to point back to itself. But only
+ *  temporarially.
+ */
+
+#define RB_PAGE_NORMAL		0UL
+#define RB_PAGE_HEAD		1UL
+#define RB_PAGE_UPDATE		2UL
+
+
+#define RB_FLAG_MASK		3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED		4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+	unsigned long val = (unsigned long)list;
+
+	return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the give page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		struct buffer_page *page, struct list_head *list)
+{
+	unsigned long val;
+
+	val = (unsigned long)list->next;
+
+	if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+		return RB_PAGE_MOVED;
+
+	return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+	struct list_head *list = page->list.prev;
+
+	return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+				struct list_head *list)
+{
+	unsigned long *ptr;
+
+	ptr = (unsigned long *)&list->next;
+	*ptr |= RB_PAGE_HEAD;
+	*ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+
+	head = cpu_buffer->head_page;
+	if (!head)
+		return;
+
+	/*
+	 * Set the previous list pointer to have the HEAD flag.
+	 */
+	rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+	unsigned long *ptr = (unsigned long *)&list->next;
+
+	*ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *hd;
+
+	/* Go through the whole list and clear any pointers found. */
+	rb_list_head_clear(cpu_buffer->pages);
+
+	list_for_each(hd, cpu_buffer->pages)
+		rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+			    struct buffer_page *head,
+			    struct buffer_page *prev,
+			    int old_flag, int new_flag)
+{
+	struct list_head *list;
+	unsigned long val = (unsigned long)&head->list;
+	unsigned long ret;
+
+	list = &prev->list;
+
+	val &= ~RB_FLAG_MASK;
+
+	ret = (unsigned long)cmpxchg(&list->next,
+				     val | old_flag, val | new_flag);
+
+	/* check if the reader took the page */
+	if ((ret & ~RB_FLAG_MASK) != val)
+		return RB_PAGE_MOVED;
+
+	return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+				 struct buffer_page *head,
+				 struct buffer_page *prev,
+				 int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page **bpage)
+{
+	struct list_head *p = rb_list_head((*bpage)->list.next);
+
+	*bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+	struct buffer_page *page;
+	struct list_head *list;
+	int i;
+
+	if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+		return NULL;
+
+	/* sanity check */
+	list = cpu_buffer->pages;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+		return NULL;
+
+	page = head = cpu_buffer->head_page;
+	/*
+	 * It is possible that the writer moves the header behind
+	 * where we started, and we miss in one loop.
+	 * A second loop should grab the header, but we'll do
+	 * three loops just because I'm paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		do {
+			if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+				cpu_buffer->head_page = page;
+				return page;
+			}
+			rb_inc_page(cpu_buffer, &page);
+		} while (page != head);
+	}
+
+	RB_WARN_ON(cpu_buffer, 1);
+
+	return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+				struct buffer_page *new)
+{
+	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+	unsigned long val;
+	unsigned long ret;
+
+	val = *ptr & ~RB_FLAG_MASK;
+	val |= RB_PAGE_HEAD;
+
+	ret = cmpxchg(ptr, val, &new->list);
+
+	return ret == val;
+}
+
+/*
+ * rb_tail_page_update - move the tail page forward
+ *
+ * Returns 1 if moved tail page, 0 if someone else did.
+ */
+static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page *tail_page,
+			       struct buffer_page *next_page)
+{
+	struct buffer_page *old_tail;
+	unsigned long old_entries;
+	unsigned long old_write;
+	int ret = 0;
+
+	/*
+	 * The tail page now needs to be moved forward.
+	 *
+	 * We need to reset the tail page, but without messing
+	 * with possible erasing of data brought in by interrupts
+	 * that have moved the tail page and are currently on it.
+	 *
+	 * We add a counter to the write field to denote this.
+	 */
+	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
+	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
+
+	/*
+	 * Just make sure we have seen our old_write and synchronize
+	 * with any interrupts that come in.
+	 */
+	barrier();
+
+	/*
+	 * If the tail page is still the same as what we think
+	 * it is, then it is up to us to update the tail
+	 * pointer.
+	 */
+	if (tail_page == cpu_buffer->tail_page) {
+		/* Zero the write counter */
+		unsigned long val = old_write & ~RB_WRITE_MASK;
+		unsigned long eval = old_entries & ~RB_WRITE_MASK;
+
+		/*
+		 * This will only succeed if an interrupt did
+		 * not come in and change it. In which case, we
+		 * do not want to modify it.
+		 *
+		 * We add (void) to let the compiler know that we do not care
+		 * about the return value of these functions. We use the
+		 * cmpxchg to only update if an interrupt did not already
+		 * do it for us. If the cmpxchg fails, we don't care.
+		 */
+		(void)local_cmpxchg(&next_page->write, old_write, val);
+		(void)local_cmpxchg(&next_page->entries, old_entries, eval);
+
+		/*
+		 * No need to worry about races with clearing out the commit.
+		 * it only can increment when a commit takes place. But that
+		 * only happens in the outer most nested commit.
+		 */
+		local_set(&next_page->page->commit, 0);
+
+		old_tail = cmpxchg(&cpu_buffer->tail_page,
+				   tail_page, next_page);
+
+		if (old_tail == tail_page)
+			ret = 1;
+	}
+
+	return ret;
+}
+
+static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+			  struct buffer_page *bpage)
+{
+	unsigned long val = (unsigned long)bpage;
+
+	if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * rb_check_list - make sure a pointer to a list has the last bits zero
+ */
+static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
+			 struct list_head *list)
+{
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
+		return 1;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
+		return 1;
+	return 0;
+}
+
 /**
  * check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
@@ -495,14 +904,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
  */
 static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = &cpu_buffer->pages;
+	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
 		return -1;
 	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
 		return -1;
 
+	if (rb_check_list(cpu_buffer, head))
+		return -1;
+
 	list_for_each_entry_safe(bpage, tmp, head, list) {
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.next->prev != &bpage->list))
@@ -510,25 +924,33 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.prev->next != &bpage->list))
 			return -1;
+		if (rb_check_list(cpu_buffer, &bpage->list))
+			return -1;
 	}
 
+	rb_head_page_activate(cpu_buffer);
+
 	return 0;
 }
 
 static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 			     unsigned nr_pages)
 {
-	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 	unsigned long addr;
 	LIST_HEAD(pages);
 	unsigned i;
 
+	WARN_ON(!nr_pages);
+
 	for (i = 0; i < nr_pages; i++) {
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 				    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
 		if (!bpage)
 			goto free_pages;
+
+		rb_check_bpage(cpu_buffer, bpage);
+
 		list_add(&bpage->list, &pages);
 
 		addr = __get_free_page(GFP_KERNEL);
@@ -538,7 +960,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_init_page(bpage->page);
 	}
 
-	list_splice(&pages, head);
+	/*
+	 * The ring buffer page list is a circular list that does not
+	 * start and end with a list head. All page list items point to
+	 * other pages.
+	 */
+	cpu_buffer->pages = pages.next;
+	list_del(&pages);
 
 	rb_check_pages(cpu_buffer);
 
@@ -570,13 +998,14 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	spin_lock_init(&cpu_buffer->reader_lock);
 	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-	INIT_LIST_HEAD(&cpu_buffer->pages);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
 	if (!bpage)
 		goto fail_free_buffer;
 
+	rb_check_bpage(cpu_buffer, bpage);
+
 	cpu_buffer->reader_page = bpage;
 	addr = __get_free_page(GFP_KERNEL);
 	if (!addr)
@@ -591,9 +1020,11 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 		goto fail_free_reader;
 
 	cpu_buffer->head_page
-		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
 
+	rb_head_page_activate(cpu_buffer);
+
 	return cpu_buffer;
 
  fail_free_reader:
@@ -606,24 +1037,25 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = &cpu_buffer->pages;
+	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	list_for_each_entry_safe(bpage, tmp, head, list) {
-		list_del_init(&bpage->list);
+	rb_head_page_deactivate(cpu_buffer);
+
+	if (head) {
+		list_for_each_entry_safe(bpage, tmp, head, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		bpage = list_entry(head, struct buffer_page, list);
 		free_buffer_page(bpage);
 	}
+
 	kfree(cpu_buffer);
 }
 
-/*
- * Causes compile errors if the struct buffer_page gets bigger
- * than the struct page.
- */
-extern int ring_buffer_page_too_big(void);
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int rb_cpu_notify(struct notifier_block *self,
 			 unsigned long action, void *hcpu);
@@ -646,11 +1078,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	int bsize;
 	int cpu;
 
-	/* Paranoid! Optimizes out when all is well */
-	if (sizeof(struct buffer_page) > sizeof(struct page))
-		ring_buffer_page_too_big();
-
-
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
 			 GFP_KERNEL);
@@ -666,8 +1093,8 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	buffer->reader_lock_key = key;
 
 	/* need at least two pages */
-	if (buffer->pages == 1)
-		buffer->pages++;
+	if (buffer->pages < 2)
+		buffer->pages = 2;
 
 	/*
 	 * In case of non-hotplug cpu, if the ring-buffer is allocated
@@ -743,6 +1170,7 @@ ring_buffer_free(struct ring_buffer *buffer)
 
 	put_online_cpus();
 
+	kfree(buffer->buffers);
 	free_cpumask_var(buffer->cpumask);
 
 	kfree(buffer);
@@ -767,15 +1195,17 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
-		if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
 			return;
-		p = cpu_buffer->pages.next;
+		p = cpu_buffer->pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
 		free_buffer_page(bpage);
 	}
-	if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+	if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
 		return;
 
 	rb_reset_cpu(cpu_buffer);
@@ -797,15 +1227,19 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	spin_lock_irq(&cpu_buffer->reader_lock);
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
 			return;
 		p = pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
-		list_add_tail(&bpage->list, &cpu_buffer->pages);
+		list_add_tail(&bpage->list, cpu_buffer->pages);
 	}
 	rb_reset_cpu(cpu_buffer);
+	spin_unlock_irq(&cpu_buffer->reader_lock);
 
 	rb_check_pages(cpu_buffer);
 
@@ -956,21 +1390,14 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static inline struct ring_buffer_event *
-rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return __rb_page_index(cpu_buffer->head_page,
-			       cpu_buffer->head_page->read);
-}
-
-static inline struct ring_buffer_event *
 rb_iter_head_event(struct ring_buffer_iter *iter)
 {
 	return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned rb_page_write(struct buffer_page *bpage)
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
 {
-	return local_read(&bpage->write);
+	return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
 static inline unsigned rb_page_commit(struct buffer_page *bpage)
@@ -978,6 +1405,11 @@ static inline unsigned rb_page_commit(struct buffer_page *bpage)
 	return local_read(&bpage->page->commit);
 }
 
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
+{
+	return local_read(&bpage->entries) & RB_WRITE_MASK;
+}
+
 /* Size is determined by what has been commited */
 static inline unsigned rb_page_size(struct buffer_page *bpage)
 {
@@ -990,33 +1422,17 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 	return rb_page_commit(cpu_buffer->commit_page);
 }
 
-static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return rb_page_commit(cpu_buffer->head_page);
-}
-
-static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
-			       struct buffer_page **bpage)
-{
-	struct list_head *p = (*bpage)->list.next;
-
-	if (p == &cpu_buffer->pages)
-		p = p->next;
-
-	*bpage = list_entry(p, struct buffer_page, list);
-}
-
 static inline unsigned
 rb_event_index(struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 
-	return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
+	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
 }
 
 static inline int
-rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
-	     struct ring_buffer_event *event)
+rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 	unsigned long index;
@@ -1029,33 +1445,10 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 }
 
 static void
-rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
-		    struct ring_buffer_event *event)
-{
-	unsigned long addr = (unsigned long)event;
-	unsigned long index;
-
-	index = rb_event_index(event);
-	addr &= PAGE_MASK;
-
-	while (cpu_buffer->commit_page->page != (void *)addr) {
-		if (RB_WARN_ON(cpu_buffer,
-			  cpu_buffer->commit_page == cpu_buffer->tail_page))
-			return;
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
-		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
-		cpu_buffer->write_stamp =
-			cpu_buffer->commit_page->page->time_stamp;
-	}
-
-	/* Now set the commit to the event's index */
-	local_set(&cpu_buffer->commit_page->page->commit, index);
-}
-
-static void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	unsigned long max_count;
+
 	/*
 	 * We only race with interrupts and NMIs on this CPU.
 	 * If we own the commit event, then we can commit
@@ -1065,9 +1458,16 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	 * assign the commit to the tail.
 	 */
  again:
+	max_count = cpu_buffer->buffer->pages * 100;
+
 	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
+			return;
+		if (RB_WARN_ON(cpu_buffer,
+			       rb_is_reader_page(cpu_buffer->tail_page)))
+			return;
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
 		cpu_buffer->write_stamp =
 			cpu_buffer->commit_page->page->time_stamp;
@@ -1076,8 +1476,12 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	}
 	while (rb_commit_index(cpu_buffer) !=
 	       rb_page_write(cpu_buffer->commit_page)) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
+		RB_WARN_ON(cpu_buffer,
+			   local_read(&cpu_buffer->commit_page->page->commit) &
+			   ~RB_WRITE_MASK);
 		barrier();
 	}
 
@@ -1110,7 +1514,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
 	 * to the head page instead of next.
 	 */
 	if (iter->head_page == cpu_buffer->reader_page)
-		iter->head_page = cpu_buffer->head_page;
+		iter->head_page = rb_set_head_page(cpu_buffer);
 	else
 		rb_inc_page(cpu_buffer, &iter->head_page);
 
@@ -1154,6 +1558,163 @@ rb_update_event(struct ring_buffer_event *event,
 	}
 }
 
+/*
+ * rb_handle_head_page - writer hit the head page
+ *
+ * Returns: +1 to retry page
+ *           0 to continue
+ *          -1 on error
+ */
+static int
+rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		    struct buffer_page *tail_page,
+		    struct buffer_page *next_page)
+{
+	struct buffer_page *new_head;
+	int entries;
+	int type;
+	int ret;
+
+	entries = rb_page_entries(next_page);
+
+	/*
+	 * The hard part is here. We need to move the head
+	 * forward, and protect against both readers on
+	 * other CPUs and writers coming in via interrupts.
+	 */
+	type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
+				       RB_PAGE_HEAD);
+
+	/*
+	 * type can be one of four:
+	 *  NORMAL - an interrupt already moved it for us
+	 *  HEAD   - we are the first to get here.
+	 *  UPDATE - we are the interrupt interrupting
+	 *           a current move.
+	 *  MOVED  - a reader on another CPU moved the next
+	 *           pointer to its reader page. Give up
+	 *           and try again.
+	 */
+
+	switch (type) {
+	case RB_PAGE_HEAD:
+		/*
+		 * We changed the head to UPDATE, thus
+		 * it is our responsibility to update
+		 * the counters.
+		 */
+		local_add(entries, &cpu_buffer->overrun);
+
+		/*
+		 * The entries will be zeroed out when we move the
+		 * tail page.
+		 */
+
+		/* still more to do */
+		break;
+
+	case RB_PAGE_UPDATE:
+		/*
+		 * This is an interrupt that interrupt the
+		 * previous update. Still more to do.
+		 */
+		break;
+	case RB_PAGE_NORMAL:
+		/*
+		 * An interrupt came in before the update
+		 * and processed this for us.
+		 * Nothing left to do.
+		 */
+		return 1;
+	case RB_PAGE_MOVED:
+		/*
+		 * The reader is on another CPU and just did
+		 * a swap with our next_page.
+		 * Try again.
+		 */
+		return 1;
+	default:
+		RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
+		return -1;
+	}
+
+	/*
+	 * Now that we are here, the old head pointer is
+	 * set to UPDATE. This will keep the reader from
+	 * swapping the head page with the reader page.
+	 * The reader (on another CPU) will spin till
+	 * we are finished.
+	 *
+	 * We just need to protect against interrupts
+	 * doing the job. We will set the next pointer
+	 * to HEAD. After that, we set the old pointer
+	 * to NORMAL, but only if it was HEAD before.
+	 * otherwise we are an interrupt, and only
+	 * want the outer most commit to reset it.
+	 */
+	new_head = next_page;
+	rb_inc_page(cpu_buffer, &new_head);
+
+	ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
+				    RB_PAGE_NORMAL);
+
+	/*
+	 * Valid returns are:
+	 *  HEAD   - an interrupt came in and already set it.
+	 *  NORMAL - One of two things:
+	 *            1) We really set it.
+	 *            2) A bunch of interrupts came in and moved
+	 *               the page forward again.
+	 */
+	switch (ret) {
+	case RB_PAGE_HEAD:
+	case RB_PAGE_NORMAL:
+		/* OK */
+		break;
+	default:
+		RB_WARN_ON(cpu_buffer, 1);
+		return -1;
+	}
+
+	/*
+	 * It is possible that an interrupt came in,
+	 * set the head up, then more interrupts came in
+	 * and moved it again. When we get back here,
+	 * the page would have been set to NORMAL but we
+	 * just set it back to HEAD.
+	 *
+	 * How do you detect this? Well, if that happened
+	 * the tail page would have moved.
+	 */
+	if (ret == RB_PAGE_NORMAL) {
+		/*
+		 * If the tail had moved passed next, then we need
+		 * to reset the pointer.
+		 */
+		if (cpu_buffer->tail_page != tail_page &&
+		    cpu_buffer->tail_page != next_page)
+			rb_head_page_set_normal(cpu_buffer, new_head,
+						next_page,
+						RB_PAGE_HEAD);
+	}
+
+	/*
+	 * If this was the outer most commit (the one that
+	 * changed the original pointer from HEAD to UPDATE),
+	 * then it is up to us to reset it to NORMAL.
+	 */
+	if (type == RB_PAGE_HEAD) {
+		ret = rb_head_page_set_normal(cpu_buffer, next_page,
+					      tail_page,
+					      RB_PAGE_UPDATE);
+		if (RB_WARN_ON(cpu_buffer,
+			       ret != RB_PAGE_UPDATE))
+			return -1;
+	}
+
+	return 0;
+}
+
 static unsigned rb_calculate_event_length(unsigned length)
 {
 	struct ring_buffer_event event; /* Used only for sizeof array */
@@ -1171,6 +1732,57 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
+static inline void
+rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
+	      struct buffer_page *tail_page,
+	      unsigned long tail, unsigned long length)
+{
+	struct ring_buffer_event *event;
+
+	/*
+	 * Only the event that crossed the page boundary
+	 * must fill the old tail_page with padding.
+	 */
+	if (tail >= BUF_PAGE_SIZE) {
+		local_sub(length, &tail_page->write);
+		return;
+	}
+
+	event = __rb_page_index(tail_page, tail);
+	kmemcheck_annotate_bitfield(event, bitfield);
+
+	/*
+	 * If this event is bigger than the minimum size, then
+	 * we need to be careful that we don't subtract the
+	 * write counter enough to allow another writer to slip
+	 * in on this page.
+	 * We put in a discarded commit instead, to make sure
+	 * that this space is not used again.
+	 *
+	 * If we are less than the minimum size, we don't need to
+	 * worry about it.
+	 */
+	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+		/* No room for any events */
+
+		/* Mark the rest of the page with padding */
+		rb_event_set_padding(event);
+
+		/* Set the write back to the previous setting */
+		local_sub(length, &tail_page->write);
+		return;
+	}
+
+	/* Put in a discarded event */
+	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+	event->type_len = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	event->time_delta = 1;
+
+	/* Set write to end of buffer */
+	length = (tail + length) - BUF_PAGE_SIZE;
+	local_sub(length, &tail_page->write);
+}
 
 static struct ring_buffer_event *
 rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1178,128 +1790,101 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct buffer_page *commit_page,
 	     struct buffer_page *tail_page, u64 *ts)
 {
-	struct buffer_page *next_page, *head_page, *reader_page;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
-	struct ring_buffer_event *event;
-	bool lock_taken = false;
-	unsigned long flags;
+	struct buffer_page *next_page;
+	int ret;
 
 	next_page = tail_page;
 
-	local_irq_save(flags);
-	/*
-	 * Since the write to the buffer is still not
-	 * fully lockless, we must be careful with NMIs.
-	 * The locks in the writers are taken when a write
-	 * crosses to a new page. The locks protect against
-	 * races with the readers (this will soon be fixed
-	 * with a lockless solution).
-	 *
-	 * Because we can not protect against NMIs, and we
-	 * want to keep traces reentrant, we need to manage
-	 * what happens when we are in an NMI.
-	 *
-	 * NMIs can happen after we take the lock.
-	 * If we are in an NMI, only take the lock
-	 * if it is not already taken. Otherwise
-	 * simply fail.
-	 */
-	if (unlikely(in_nmi())) {
-		if (!__raw_spin_trylock(&cpu_buffer->lock)) {
-			cpu_buffer->nmi_dropped++;
-			goto out_reset;
-		}
-	} else
-		__raw_spin_lock(&cpu_buffer->lock);
-
-	lock_taken = true;
-
 	rb_inc_page(cpu_buffer, &next_page);
 
-	head_page = cpu_buffer->head_page;
-	reader_page = cpu_buffer->reader_page;
-
-	/* we grabbed the lock before incrementing */
-	if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-		goto out_reset;
-
 	/*
 	 * If for some reason, we had an interrupt storm that made
 	 * it all the way around the buffer, bail, and warn
 	 * about it.
 	 */
 	if (unlikely(next_page == commit_page)) {
-		cpu_buffer->commit_overrun++;
+		local_inc(&cpu_buffer->commit_overrun);
 		goto out_reset;
 	}
 
-	if (next_page == head_page) {
-		if (!(buffer->flags & RB_FL_OVERWRITE))
-			goto out_reset;
-
-		/* tail_page has not moved yet? */
-		if (tail_page == cpu_buffer->tail_page) {
-			/* count overflows */
-			cpu_buffer->overrun +=
-				local_read(&head_page->entries);
-
-			rb_inc_page(cpu_buffer, &head_page);
-			cpu_buffer->head_page = head_page;
-			cpu_buffer->head_page->read = 0;
-		}
-	}
-
 	/*
-	 * If the tail page is still the same as what we think
-	 * it is, then it is up to us to update the tail
-	 * pointer.
+	 * This is where the fun begins!
+	 *
+	 * We are fighting against races between a reader that
+	 * could be on another CPU trying to swap its reader
+	 * page with the buffer head.
+	 *
+	 * We are also fighting against interrupts coming in and
+	 * moving the head or tail on us as well.
+	 *
+	 * If the next page is the head page then we have filled
+	 * the buffer, unless the commit page is still on the
+	 * reader page.
 	 */
-	if (tail_page == cpu_buffer->tail_page) {
-		local_set(&next_page->write, 0);
-		local_set(&next_page->entries, 0);
-		local_set(&next_page->page->commit, 0);
-		cpu_buffer->tail_page = next_page;
+	if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {
 
-		/* reread the time stamp */
-		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
-		cpu_buffer->tail_page->page->time_stamp = *ts;
+		/*
+		 * If the commit is not on the reader page, then
+		 * move the header page.
+		 */
+		if (!rb_is_reader_page(cpu_buffer->commit_page)) {
+			/*
+			 * If we are not in overwrite mode,
+			 * this is easy, just stop here.
+			 */
+			if (!(buffer->flags & RB_FL_OVERWRITE))
+				goto out_reset;
+
+			ret = rb_handle_head_page(cpu_buffer,
+						  tail_page,
+						  next_page);
+			if (ret < 0)
+				goto out_reset;
+			if (ret)
+				goto out_again;
+		} else {
+			/*
+			 * We need to be careful here too. The
+			 * commit page could still be on the reader
+			 * page. We could have a small buffer, and
+			 * have filled up the buffer with events
+			 * from interrupts and such, and wrapped.
+			 *
+			 * Note, if the tail page is also the on the
+			 * reader_page, we let it move out.
+			 */
+			if (unlikely((cpu_buffer->commit_page !=
+				      cpu_buffer->tail_page) &&
+				     (cpu_buffer->commit_page ==
+				      cpu_buffer->reader_page))) {
+				local_inc(&cpu_buffer->commit_overrun);
+				goto out_reset;
+			}
+		}
 	}
 
-	/*
-	 * The actual tail page has moved forward.
-	 */
-	if (tail < BUF_PAGE_SIZE) {
-		/* Mark the rest of the page with padding */
-		event = __rb_page_index(tail_page, tail);
-		kmemcheck_annotate_bitfield(event, bitfield);
-		rb_event_set_padding(event);
+	ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
+	if (ret) {
+		/*
+		 * Nested commits always have zero deltas, so
+		 * just reread the time stamp
+		 */
+		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+		next_page->page->time_stamp = *ts;
 	}
 
-	/* Set the write back to the previous setting */
-	local_sub(length, &tail_page->write);
+ out_again:
 
-	/*
-	 * If this was a commit entry that failed,
-	 * increment that too
-	 */
-	if (tail_page == cpu_buffer->commit_page &&
-	    tail == rb_commit_index(cpu_buffer)) {
-		rb_set_commit_to_write(cpu_buffer);
-	}
-
-	__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
+	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
 	/* fail and let the caller try again */
 	return ERR_PTR(-EAGAIN);
 
  out_reset:
 	/* reset write */
-	local_sub(length, &tail_page->write);
+	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
-	if (likely(lock_taken))
-		__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
 	return NULL;
 }
 
@@ -1316,6 +1901,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	barrier();
 	tail_page = cpu_buffer->tail_page;
 	write = local_add_return(length, &tail_page->write);
+
+	/* set write to only the index of the write */
+	write &= RB_WRITE_MASK;
 	tail = write - length;
 
 	/* See if we shot pass the end of this buffer page */
@@ -1325,9 +1913,6 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* We reserved something on the buffer */
 
-	if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
-		return NULL;
-
 	event = __rb_page_index(tail_page, tail);
 	kmemcheck_annotate_bitfield(event, bitfield);
 	rb_update_event(event, type, length);
@@ -1337,11 +1922,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		local_inc(&tail_page->entries);
 
 	/*
-	 * If this is a commit and the tail is zero, then update
-	 * this page's time stamp.
+	 * If this is the first commit on the page, then update
+	 * its timestamp.
 	 */
-	if (!tail && rb_is_commit(cpu_buffer, event))
-		cpu_buffer->commit_page->page->time_stamp = *ts;
+	if (!tail)
+		tail_page->page->time_stamp = *ts;
 
 	return event;
 }
@@ -1363,12 +1948,16 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	bpage = cpu_buffer->tail_page;
 
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		unsigned long write_mask =
+			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
 		 * and write to the next page. That is fine
 		 * because we just shorten what is on this page.
 		 */
+		old_index += write_mask;
+		new_index += write_mask;
 		index = local_cmpxchg(&bpage->write, old_index, new_index);
 		if (index == old_index)
 			return 1;
@@ -1410,16 +1999,16 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		return -EAGAIN;
 
 	/* Only a commited time event can update the write stamp */
-	if (rb_is_commit(cpu_buffer, event)) {
+	if (rb_event_is_commit(cpu_buffer, event)) {
 		/*
-		 * If this is the first on the page, then we need to
-		 * update the page itself, and just put in a zero.
+		 * If this is the first on the page, then it was
+		 * updated with the page itself. Try to discard it
+		 * and if we can't just make it zero.
 		 */
 		if (rb_event_index(event)) {
 			event->time_delta = *delta & TS_MASK;
 			event->array[0] = *delta >> TS_SHIFT;
 		} else {
-			cpu_buffer->commit_page->page->time_stamp = *ts;
 			/* try to discard, since we do not need this */
 			if (!rb_try_to_discard(cpu_buffer, event)) {
 				/* nope, just zero it */
@@ -1445,8 +2034,47 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 	return ret;
 }
 
+static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	local_inc(&cpu_buffer->committing);
+	local_inc(&cpu_buffer->commits);
+}
+
+static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	unsigned long commits;
+
+	if (RB_WARN_ON(cpu_buffer,
+		       !local_read(&cpu_buffer->committing)))
+		return;
+
+ again:
+	commits = local_read(&cpu_buffer->commits);
+	/* synchronize with interrupts */
+	barrier();
+	if (local_read(&cpu_buffer->committing) == 1)
+		rb_set_commit_to_write(cpu_buffer);
+
+	local_dec(&cpu_buffer->committing);
+
+	/* synchronize with interrupts */
+	barrier();
+
+	/*
+	 * Need to account for interrupts coming in between the
+	 * updating of the commit page and the clearing of the
+	 * committing counter.
+	 */
+	if (unlikely(local_read(&cpu_buffer->commits) != commits) &&
+	    !local_read(&cpu_buffer->committing)) {
+		local_inc(&cpu_buffer->committing);
+		goto again;
+	}
+}
+
 static struct ring_buffer_event *
-rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
+rb_reserve_next_event(struct ring_buffer *buffer,
+		      struct ring_buffer_per_cpu *cpu_buffer,
 		      unsigned long length)
 {
 	struct ring_buffer_event *event;
@@ -1454,6 +2082,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	int commit = 0;
 	int nr_loops = 0;
 
+	rb_start_commit(cpu_buffer);
+
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+	/*
+	 * Due to the ability to swap a cpu buffer from a buffer
+	 * it is possible it was swapped before we committed.
+	 * (committing stops a swap). We check for it here and
+	 * if it happened, we have to fail the write.
+	 */
+	barrier();
+	if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) {
+		local_dec(&cpu_buffer->committing);
+		local_dec(&cpu_buffer->commits);
+		return NULL;
+	}
+#endif
+
 	length = rb_calculate_event_length(length);
  again:
 	/*
@@ -1466,7 +2111,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * Bail!
 	 */
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
-		return NULL;
+		goto out_fail;
 
 	ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
 
@@ -1497,7 +2142,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 			commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
 			if (commit == -EBUSY)
-				return NULL;
+				goto out_fail;
 
 			if (commit == -EAGAIN)
 				goto again;
@@ -1511,30 +2156,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (unlikely(PTR_ERR(event) == -EAGAIN))
 		goto again;
 
-	if (!event) {
-		if (unlikely(commit))
-			/*
-			 * Ouch! We needed a timestamp and it was commited. But
-			 * we didn't get our event reserved.
-			 */
-			rb_set_commit_to_write(cpu_buffer);
-		return NULL;
-	}
+	if (!event)
+		goto out_fail;
 
-	/*
-	 * If the timestamp was commited, make the commit our entry
-	 * now so that we will update it when needed.
-	 */
-	if (unlikely(commit))
-		rb_set_commit_event(cpu_buffer, event);
-	else if (!rb_is_commit(cpu_buffer, event))
+	if (!rb_event_is_commit(cpu_buffer, event))
 		delta = 0;
 
 	event->time_delta = delta;
 
 	return event;
+
+ out_fail:
+	rb_end_commit(cpu_buffer);
+	return NULL;
 }
 
+#ifdef CONFIG_TRACING
+
 #define TRACE_RECURSIVE_DEPTH 16
 
 static int trace_recursive_lock(void)
@@ -1565,6 +2203,13 @@ static void trace_recursive_unlock(void)
 	current->trace_recursion--;
 }
 
+#else
+
+#define trace_recursive_lock()		(0)
+#define trace_recursive_unlock()	do { } while (0)
+
+#endif
+
 static DEFINE_PER_CPU(int, rb_need_resched);
 
 /**
@@ -1614,7 +2259,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, length);
+	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1637,18 +2282,24 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 
+static void
+rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		      struct ring_buffer_event *event)
+{
+	/*
+	 * The event first in the commit queue updates the
+	 * time stamp.
+	 */
+	if (rb_event_is_commit(cpu_buffer, event))
+		cpu_buffer->write_stamp += event->time_delta;
+}
+
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
 	local_inc(&cpu_buffer->entries);
-
-	/* Only process further if we own the commit */
-	if (!rb_is_commit(cpu_buffer, event))
-		return;
-
-	cpu_buffer->write_stamp += event->time_delta;
-
-	rb_set_commit_to_write(cpu_buffer);
+	rb_update_write_stamp(cpu_buffer, event);
+	rb_end_commit(cpu_buffer);
 }
 
 /**
@@ -1694,32 +2345,57 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-/**
- * ring_buffer_event_discard - discard any event in the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
+/*
+ * Decrement the entries to the page that an event is on.
+ * The event does not even need to exist, only the pointer
+ * to the page it is on. This may only be called before the commit
+ * takes place.
  */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
+static inline void
+rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct ring_buffer_event *event)
 {
-	rb_event_discard(event);
+	unsigned long addr = (unsigned long)event;
+	struct buffer_page *bpage = cpu_buffer->commit_page;
+	struct buffer_page *start;
+
+	addr &= PAGE_MASK;
+
+	/* Do the likely case first */
+	if (likely(bpage->page == (void *)addr)) {
+		local_dec(&bpage->entries);
+		return;
+	}
+
+	/*
+	 * Because the commit page may be on the reader page we
+	 * start with the next page and check the end loop there.
+	 */
+	rb_inc_page(cpu_buffer, &bpage);
+	start = bpage;
+	do {
+		if (bpage->page == (void *)addr) {
+			local_dec(&bpage->entries);
+			return;
+		}
+		rb_inc_page(cpu_buffer, &bpage);
+	} while (bpage != start);
+
+	/* commit not part of this buffer?? */
+	RB_WARN_ON(cpu_buffer, 1);
 }
-EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
 
 /**
  * ring_buffer_commit_discard - discard an event that has not been committed
  * @buffer: the ring buffer
  * @event: non committed event to discard
  *
- * This is similar to ring_buffer_event_discard but must only be
- * performed on an event that has not been committed yet. The difference
- * is that this will also try to free the event from the ring buffer
+ * Sometimes an event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * This function only works if it is called before the the item has been
+ * committed. It will try to free the event from the ring buffer
  * if another event has not been added behind it.
  *
  * If another event has been added behind it, it will set the event
@@ -1737,32 +2413,27 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 	/* The event is discarded regardless */
 	rb_event_discard(event);
 
+	cpu = smp_processor_id();
+	cpu_buffer = buffer->buffers[cpu];
+
 	/*
 	 * This must only be called if the event has not been
 	 * committed yet. Thus we can assume that preemption
 	 * is still disabled.
 	 */
-	RB_WARN_ON(buffer, preemptible());
+	RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
 
-	cpu = smp_processor_id();
-	cpu_buffer = buffer->buffers[cpu];
-
-	if (!rb_try_to_discard(cpu_buffer, event))
+	rb_decrement_entry(cpu_buffer, event);
+	if (rb_try_to_discard(cpu_buffer, event))
 		goto out;
 
 	/*
 	 * The commit is still visible by the reader, so we
-	 * must increment entries.
+	 * must still update the timestamp.
 	 */
-	local_inc(&cpu_buffer->entries);
+	rb_update_write_stamp(cpu_buffer, event);
  out:
-	/*
-	 * If a write came in and pushed the tail page
-	 * we still need to update the commit pointer
-	 * if we were the commit.
-	 */
-	if (rb_is_commit(cpu_buffer, event))
-		rb_set_commit_to_write(cpu_buffer);
+	rb_end_commit(cpu_buffer);
 
 	trace_recursive_unlock();
 
@@ -1821,7 +2492,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, length);
+	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1842,9 +2513,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_write);
 static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = cpu_buffer->reader_page;
-	struct buffer_page *head = cpu_buffer->head_page;
+	struct buffer_page *head = rb_set_head_page(cpu_buffer);
 	struct buffer_page *commit = cpu_buffer->commit_page;
 
+	/* In case of error, head will be NULL */
+	if (unlikely(!head))
+		return 1;
+
 	return reader->read == rb_page_commit(reader) &&
 		(commit == reader ||
 		 (commit == head &&
@@ -1935,7 +2610,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+	ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
 		- cpu_buffer->read;
 
 	return ret;
@@ -1956,33 +2631,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->overrun;
+	ret = local_read(&cpu_buffer->overrun);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
- * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
- * @buffer: The ring buffer
- * @cpu: The per CPU buffer to get the number of overruns from
- */
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long ret;
-
-	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return 0;
-
-	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->nmi_dropped;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
-
-/**
  * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the number of overruns from
@@ -1997,7 +2652,7 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->commit_overrun;
+	ret = local_read(&cpu_buffer->commit_overrun);
 
 	return ret;
 }
@@ -2020,7 +2675,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 		entries += (local_read(&cpu_buffer->entries) -
-			    cpu_buffer->overrun) - cpu_buffer->read;
+			    local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
 	}
 
 	return entries;
@@ -2043,7 +2698,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		overruns += cpu_buffer->overrun;
+		overruns += local_read(&cpu_buffer->overrun);
 	}
 
 	return overruns;
@@ -2056,8 +2711,10 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 
 	/* Iterator usage is expected to have record disabled */
 	if (list_empty(&cpu_buffer->reader_page->list)) {
-		iter->head_page = cpu_buffer->head_page;
-		iter->head = cpu_buffer->head_page->read;
+		iter->head_page = rb_set_head_page(cpu_buffer);
+		if (unlikely(!iter->head_page))
+			return;
+		iter->head = iter->head_page->read;
 	} else {
 		iter->head_page = cpu_buffer->reader_page;
 		iter->head = cpu_buffer->reader_page->read;
@@ -2174,6 +2831,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	struct buffer_page *reader = NULL;
 	unsigned long flags;
 	int nr_loops = 0;
+	int ret;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&cpu_buffer->lock);
@@ -2207,30 +2865,56 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto out;
 
 	/*
-	 * Splice the empty reader page into the list around the head.
 	 * Reset the reader page to size zero.
 	 */
+	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
+	local_set(&cpu_buffer->reader_page->page->commit, 0);
 
-	reader = cpu_buffer->head_page;
+ spin:
+	/*
+	 * Splice the empty reader page into the list around the head.
+	 */
+	reader = rb_set_head_page(cpu_buffer);
 	cpu_buffer->reader_page->list.next = reader->list.next;
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
-	local_set(&cpu_buffer->reader_page->write, 0);
-	local_set(&cpu_buffer->reader_page->entries, 0);
-	local_set(&cpu_buffer->reader_page->page->commit, 0);
+	/*
+	 * cpu_buffer->pages just needs to point to the buffer, it
+	 *  has no specific buffer page to point to. Lets move it out
+	 *  of our way so we don't accidently swap it.
+	 */
+	cpu_buffer->pages = reader->list.prev;
 
-	/* Make the reader page now replace the head */
-	reader->list.prev->next = &cpu_buffer->reader_page->list;
-	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	/* The reader page will be pointing to the new head */
+	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
+
+	/*
+	 * Here's the tricky part.
+	 *
+	 * We need to move the pointer past the header page.
+	 * But we can only do that if a writer is not currently
+	 * moving it. The page before the header page has the
+	 * flag bit '1' set if it is pointing to the page we want.
+	 * but if the writer is in the process of moving it
+	 * than it will be '2' or already moved '0'.
+	 */
+
+	ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
 
 	/*
-	 * If the tail is on the reader, then we must set the head
-	 * to the inserted page, otherwise we set it one before.
+	 * If we did not convert it, then we must try again.
 	 */
-	cpu_buffer->head_page = cpu_buffer->reader_page;
+	if (!ret)
+		goto spin;
 
-	if (cpu_buffer->commit_page != reader)
-		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+	/*
+	 * Yeah! We succeeded in replacing the page.
+	 *
+	 * Now make the new head point back to the reader page.
+	 */
+	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
@@ -2259,8 +2943,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
-			|| rb_discarded_event(event))
+	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 		cpu_buffer->read++;
 
 	rb_update_read_stamp(cpu_buffer, event);
@@ -2351,7 +3034,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 		 * the box. Return the padding, and we will release
 		 * the current locks, and try again.
 		 */
-		rb_advance_reader(cpu_buffer);
 		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
@@ -2446,6 +3128,21 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
 
+static inline int rb_ok_to_lock(void)
+{
+	/*
+	 * If an NMI die dumps out the content of the ring buffer
+	 * do not grab locks. We also permanently disable the ring
+	 * buffer too. A one time deal is all you get from reading
+	 * the ring buffer from an NMI.
+	 */
+	if (likely(!in_nmi()))
+		return 1;
+
+	tracing_off_permanent();
+	return 0;
+}
+
 /**
  * ring_buffer_peek - peek at the next event to be read
  * @buffer: The ring buffer to read
@@ -2461,19 +3158,25 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
 	unsigned long flags;
+	int dolock;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
+	dolock = rb_ok_to_lock();
  again:
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 	event = rb_buffer_peek(buffer, cpu, ts);
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
+		rb_advance_reader(cpu_buffer);
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2498,10 +3201,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2520,6 +3221,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
+	int dolock;
+
+	dolock = rb_ok_to_lock();
 
  again:
 	/* might be called in atomic */
@@ -2529,24 +3233,23 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 
 	event = rb_buffer_peek(buffer, cpu, ts);
-	if (!event)
-		goto out_unlock;
-
-	rb_advance_reader(cpu_buffer);
+	if (event)
+		rb_advance_reader(cpu_buffer);
 
- out_unlock:
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
  out:
 	preempt_enable();
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
-	}
 
 	return event;
 }
@@ -2626,21 +3329,19 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
- again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ again:
 	event = rb_iter_peek(iter, ts);
 	if (!event)
 		goto out;
 
+	if (event->type_len == RINGBUF_TYPE_PADDING)
+		goto again;
+
 	rb_advance_iter(iter);
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-		cpu_relax();
-		goto again;
-	}
-
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);
@@ -2658,8 +3359,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_size);
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	rb_head_page_deactivate(cpu_buffer);
+
 	cpu_buffer->head_page
-		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	local_set(&cpu_buffer->head_page->write, 0);
 	local_set(&cpu_buffer->head_page->entries, 0);
 	local_set(&cpu_buffer->head_page->page->commit, 0);
@@ -2675,14 +3378,17 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
-	cpu_buffer->nmi_dropped = 0;
-	cpu_buffer->commit_overrun = 0;
-	cpu_buffer->overrun = 0;
-	cpu_buffer->read = 0;
+	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->overrun, 0);
 	local_set(&cpu_buffer->entries, 0);
+	local_set(&cpu_buffer->committing, 0);
+	local_set(&cpu_buffer->commits, 0);
+	cpu_buffer->read = 0;
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
+
+	rb_head_page_activate(cpu_buffer);
 }
 
 /**
@@ -2702,12 +3408,16 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
+	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+		goto out;
+
 	__raw_spin_lock(&cpu_buffer->lock);
 
 	rb_reset_cpu(cpu_buffer);
 
 	__raw_spin_unlock(&cpu_buffer->lock);
 
+ out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->record_disabled);
@@ -2734,12 +3444,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset);
 int ring_buffer_empty(struct ring_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long flags;
+	int dolock;
 	int cpu;
+	int ret;
+
+	dolock = rb_ok_to_lock();
 
 	/* yes this is racy, but if you don't like the race, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		if (!rb_per_cpu_empty(cpu_buffer))
+		local_irq_save(flags);
+		if (dolock)
+			spin_lock(&cpu_buffer->reader_lock);
+		ret = rb_per_cpu_empty(cpu_buffer);
+		if (dolock)
+			spin_unlock(&cpu_buffer->reader_lock);
+		local_irq_restore(flags);
+
+		if (!ret)
 			return 0;
 	}
 
@@ -2755,19 +3478,29 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty);
 int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long flags;
+	int dolock;
 	int ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 1;
 
+	dolock = rb_ok_to_lock();
+
 	cpu_buffer = buffer->buffers[cpu];
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 	ret = rb_per_cpu_empty(cpu_buffer);
-
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 /**
  * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
  * @buffer_a: One buffer to swap with
@@ -2822,20 +3555,28 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	atomic_inc(&cpu_buffer_a->record_disabled);
 	atomic_inc(&cpu_buffer_b->record_disabled);
 
+	ret = -EBUSY;
+	if (local_read(&cpu_buffer_a->committing))
+		goto out_dec;
+	if (local_read(&cpu_buffer_b->committing))
+		goto out_dec;
+
 	buffer_a->buffers[cpu] = cpu_buffer_b;
 	buffer_b->buffers[cpu] = cpu_buffer_a;
 
 	cpu_buffer_b->buffer = buffer_a;
 	cpu_buffer_a->buffer = buffer_b;
 
+	ret = 0;
+
+out_dec:
 	atomic_dec(&cpu_buffer_a->record_disabled);
 	atomic_dec(&cpu_buffer_b->record_disabled);
-
-	ret = 0;
 out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */
 
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
@@ -3008,7 +3749,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		read = 0;
 	} else {
 		/* update the entry counter */
-		cpu_buffer->read += local_read(&reader->entries);
+		cpu_buffer->read += rb_page_entries(reader);
 
 		/* swap the pages */
 		rb_init_page(bpage);
@@ -3029,6 +3770,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+#ifdef CONFIG_TRACING
 static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
@@ -3096,6 +3838,7 @@ static __init int rb_init_debugfs(void)
 }
 
 fs_initcall(rb_init_debugfs);
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 static int rb_cpu_notify(struct notifier_block *self,
@@ -3108,7 +3851,7 @@ static int rb_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (cpu_isset(cpu, *buffer->cpumask))
+		if (cpumask_test_cpu(cpu, buffer->cpumask))
 			return NOTIFY_OK;
 
 		buffer->buffers[cpu] =
@@ -3119,7 +3862,7 @@ static int rb_cpu_notify(struct notifier_block *self,
 			return NOTIFY_OK;
 		}
 		smp_wmb();
-		cpu_set(cpu, *buffer->cpumask);
+		cpumask_set_cpu(cpu, buffer->cpumask);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 8d68e149a8b..573d3cc762c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -102,8 +102,10 @@ static enum event_status read_page(int cpu)
 			event = (void *)&rpage->data[i];
 			switch (event->type_len) {
 			case RINGBUF_TYPE_PADDING:
-				/* We don't expect any padding */
-				KILL_TEST();
+				/* failed writes may be discarded events */
+				if (!event->time_delta)
+					KILL_TEST();
+				inc = event->array[0] + 4;
 				break;
 			case RINGBUF_TYPE_TIME_EXTEND:
 				inc = 8;
@@ -119,7 +121,7 @@ static enum event_status read_page(int cpu)
 					KILL_TEST();
 					break;
 				}
-				inc = event->array[0];
+				inc = event->array[0] + 4;
 				break;
 			default:
 				entry = ring_buffer_event_data(event);
@@ -201,7 +203,7 @@ static void ring_buffer_producer(void)
 	 * Hammer the buffer for 10 secs (this may
 	 * make the system stall)
 	 */
-	pr_info("Starting ring buffer hammer\n");
+	trace_printk("Starting ring buffer hammer\n");
 	do_gettimeofday(&start_tv);
 	do {
 		struct ring_buffer_event *event;
@@ -237,7 +239,7 @@ static void ring_buffer_producer(void)
 #endif
 
 	} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
-	pr_info("End ring buffer hammer\n");
+	trace_printk("End ring buffer hammer\n");
 
 	if (consumer) {
 		/* Init both completions here to avoid races */
@@ -260,49 +262,50 @@ static void ring_buffer_producer(void)
 	overruns = ring_buffer_overruns(buffer);
 
 	if (kill_test)
-		pr_info("ERROR!\n");
-	pr_info("Time:     %lld (usecs)\n", time);
-	pr_info("Overruns: %lld\n", overruns);
+		trace_printk("ERROR!\n");
+	trace_printk("Time:     %lld (usecs)\n", time);
+	trace_printk("Overruns: %lld\n", overruns);
 	if (disable_reader)
-		pr_info("Read:     (reader disabled)\n");
+		trace_printk("Read:     (reader disabled)\n");
 	else
-		pr_info("Read:     %ld  (by %s)\n", read,
+		trace_printk("Read:     %ld  (by %s)\n", read,
 			read_events ? "events" : "pages");
-	pr_info("Entries:  %lld\n", entries);
-	pr_info("Total:    %lld\n", entries + overruns + read);
-	pr_info("Missed:   %ld\n", missed);
-	pr_info("Hit:      %ld\n", hit);
+	trace_printk("Entries:  %lld\n", entries);
+	trace_printk("Total:    %lld\n", entries + overruns + read);
+	trace_printk("Missed:   %ld\n", missed);
+	trace_printk("Hit:      %ld\n", hit);
 
 	/* Convert time from usecs to millisecs */
 	do_div(time, USEC_PER_MSEC);
 	if (time)
 		hit /= (long)time;
 	else
-		pr_info("TIME IS ZERO??\n");
+		trace_printk("TIME IS ZERO??\n");
 
-	pr_info("Entries per millisec: %ld\n", hit);
+	trace_printk("Entries per millisec: %ld\n", hit);
 
 	if (hit) {
 		/* Calculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / hit;
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 
 	if (missed) {
 		if (time)
 			missed /= (long)time;
 
-		pr_info("Total iterations per millisec: %ld\n", hit + missed);
+		trace_printk("Total iterations per millisec: %ld\n",
+			     hit + missed);
 
 		/* it is possible that hit + missed will overflow and be zero */
 		if (!(hit + missed)) {
-			pr_info("hit + missed overflowed and totalled zero!\n");
+			trace_printk("hit + missed overflowed and totalled zero!\n");
 			hit--; /* make it non zero */
 		}
 
 		/* Caculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / (hit + missed);
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 }
 
@@ -353,7 +356,7 @@ static int ring_buffer_producer_thread(void *arg)
 
 		ring_buffer_producer();
 
-		pr_info("Sleeping for 10 secs\n");
+		trace_printk("Sleeping for 10 secs\n");
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(HZ * SLEEP_TIME);
 		__set_current_state(TASK_RUNNING);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c1878bfb2e1..5c75deeefe3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
@@ -42,14 +43,11 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency;
-unsigned long __read_mostly	tracing_thresh;
-
 /*
  * 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.
  */
-static int ring_buffer_expanded;
+int ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -63,7 +61,7 @@ static bool __read_mostly tracing_selftest_running;
 /*
  * If a tracer is running, we do not want to run SELFTEST.
  */
-static bool __read_mostly tracing_selftest_disabled;
+bool __read_mostly tracing_selftest_disabled;
 
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
@@ -88,7 +86,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
@@ -171,10 +169,11 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
-int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+int filter_current_check_discard(struct ring_buffer *buffer,
+				 struct ftrace_event_call *call, void *rec,
 				 struct ring_buffer_event *event)
 {
-	return filter_check_discard(call, rec, global_trace.buffer, event);
+	return filter_check_discard(call, rec, buffer, event);
 }
 EXPORT_SYMBOL_GPL(filter_current_check_discard);
 
@@ -265,6 +264,9 @@ 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;
 
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
@@ -284,13 +286,12 @@ void trace_wake_up(void)
 static int __init set_buf_size(char *str)
 {
 	unsigned long buf_size;
-	int ret;
 
 	if (!str)
 		return 0;
-	ret = strict_strtoul(str, 0, &buf_size);
+	buf_size = memparse(str, &str);
 	/* nr_entries can not be zero */
-	if (ret < 0 || buf_size == 0)
+	if (buf_size == 0)
 		return 0;
 	trace_buf_size = buf_size;
 	return 1;
@@ -323,50 +324,20 @@ static const char *trace_options[] = {
 	"printk-msg-only",
 	"context-info",
 	"latency-format",
-	"global-clock",
 	"sleep-time",
 	"graph-time",
 	NULL
 };
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a raw_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- */
-static raw_spinlock_t ftrace_max_lock =
-	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-
-/*
- * Copy the new maximum trace into the separate maximum-trace
- * structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
- */
-static void
-__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
-{
-	struct trace_array_cpu *data = tr->data[cpu];
-
-	max_tr.cpu = cpu;
-	max_tr.time_start = data->preempt_timestamp;
-
-	data = max_tr.data[cpu];
-	data->saved_latency = tracing_max_latency;
-
-	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
-	data->pid = tsk->pid;
-	data->uid = task_uid(tsk);
-	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
-	data->policy = tsk->policy;
-	data->rt_priority = tsk->rt_priority;
+static struct {
+	u64 (*func)(void);
+	const char *name;
+} trace_clocks[] = {
+	{ trace_clock_local,	"local" },
+	{ trace_clock_global,	"global" },
+};
 
-	/* record this tasks comm */
-	tracing_record_cmdline(tsk);
-}
+int trace_clock_id;
 
 ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 {
@@ -411,6 +382,56 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ *
+ * It is also used in other places outside the update_max_tr
+ * so it needs to be defined outside of the
+ * CONFIG_TRACER_MAX_TRACE.
+ */
+static raw_spinlock_t ftrace_max_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+unsigned long __read_mostly	tracing_max_latency;
+unsigned long __read_mostly	tracing_thresh;
+
+/*
+ * Copy the new maximum trace into the separate maximum-trace
+ * structure. (this way the maximum trace is permanently saved,
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ */
+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 = tr->data[cpu];
+
+	max_tr.cpu = cpu;
+	max_tr.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;
+
+	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+	max_data->pid = tsk->pid;
+	max_data->uid = task_uid(tsk);
+	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+	max_data->policy = tsk->policy;
+	max_data->rt_priority = tsk->rt_priority;
+
+	/* record this tasks comm */
+	tracing_record_cmdline(tsk);
+}
+
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -425,16 +446,15 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct ring_buffer *buf = tr->buffer;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
-	ftrace_disable_cpu();
-	ring_buffer_reset(tr->buffer);
-	ftrace_enable_cpu();
-
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
@@ -452,21 +472,35 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	int ret;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
 	ftrace_disable_cpu();
 
-	ring_buffer_reset(max_tr.buffer);
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
+	if (ret == -EBUSY) {
+		/*
+		 * We failed to swap the buffer due to a commit taking
+		 * place on this CPU. We fail to record, but we reset
+		 * the max trace buffer (no one writes directly to it)
+		 * and flag that it failed.
+		 */
+		trace_array_printk(&max_tr, _THIS_IP_,
+			"Failed to swap buffers due to commit in progress\n");
+	}
+
 	ftrace_enable_cpu();
 
-	WARN_ON_ONCE(ret && ret != -EAGAIN);
+	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -523,7 +557,6 @@ __acquires(kernel_lock)
 	if (type->selftest && !tracing_selftest_disabled) {
 		struct tracer *saved_tracer = current_trace;
 		struct trace_array *tr = &global_trace;
-		int i;
 
 		/*
 		 * Run a selftest on this tracer.
@@ -532,8 +565,7 @@ __acquires(kernel_lock)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
 		/* the test is responsible for initializing and enabling */
@@ -546,8 +578,7 @@ __acquires(kernel_lock)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		printk(KERN_CONT "PASSED\n");
 	}
@@ -622,21 +653,42 @@ void unregister_tracer(struct tracer *type)
 	mutex_unlock(&trace_types_lock);
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct trace_array *tr, int cpu)
 {
 	ftrace_disable_cpu();
 	ring_buffer_reset_cpu(tr->buffer, cpu);
 	ftrace_enable_cpu();
 }
 
+void tracing_reset(struct trace_array *tr, int cpu)
+{
+	struct ring_buffer *buffer = tr->buffer;
+
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+	__tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
+}
+
 void tracing_reset_online_cpus(struct trace_array *tr)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		tracing_reset(tr, cpu);
+		__tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
 }
 
 void tracing_reset_current(int cpu)
@@ -667,9 +719,6 @@ static void trace_init_cmdlines(void)
 	cmdline_idx = 0;
 }
 
-static int trace_stop_count;
-static DEFINE_SPINLOCK(tracing_start_lock);
-
 /**
  * ftrace_off_permanent - disable all ftrace code permanently
  *
@@ -848,15 +897,17 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
 }
+EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags, int pc)
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags, int pc)
 {
 	struct ring_buffer_event *event;
 
-	event = ring_buffer_lock_reserve(tr->buffer, len);
+	event = ring_buffer_lock_reserve(buffer, len);
 	if (event != NULL) {
 		struct trace_entry *ent = ring_buffer_event_data(event);
 
@@ -866,58 +917,60 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 
 	return event;
 }
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags, int skip, int pc);
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   unsigned long flags, int pc);
 
-static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc,
-					int wake)
+static inline void
+__trace_buffer_unlock_commit(struct ring_buffer *buffer,
+			     struct ring_buffer_event *event,
+			     unsigned long flags, int pc,
+			     int wake)
 {
-	ring_buffer_unlock_commit(tr->buffer, event);
+	ring_buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
+	ftrace_trace_stack(buffer, flags, 6, pc);
+	ftrace_trace_userstack(buffer, flags, pc);
 
 	if (wake)
 		trace_wake_up();
 }
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
-	return trace_buffer_lock_reserve(&global_trace,
+	*current_rb = global_trace.buffer;
+	return trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
+				       unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event)
 {
-	ring_buffer_discard_commit(global_trace.buffer, event);
+	ring_buffer_discard_commit(buffer, event);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
@@ -927,6 +980,7 @@ trace_function(struct trace_array *tr,
 	       int pc)
 {
 	struct ftrace_event_call *call = &event_function;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -934,7 +988,7 @@ trace_function(struct trace_array *tr,
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
+	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
 					  flags, pc);
 	if (!event)
 		return;
@@ -942,57 +996,9 @@ trace_function(struct trace_array *tr,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-}
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int __trace_graph_entry(struct trace_array *tr,
-				struct ftrace_graph_ent *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_entry;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ent_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return 0;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return 0;
-	entry	= ring_buffer_event_data(event);
-	entry->graph_ent			= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
-
-	return 1;
-}
-
-static void __trace_graph_return(struct trace_array *tr,
-				struct ftrace_graph_ret *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_exit;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ret_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->ret				= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
-#endif
 
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
@@ -1003,17 +1009,17 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 		trace_function(tr, ip, parent_ip, flags, pc);
 }
 
-static void __ftrace_trace_stack(struct trace_array *tr,
+#ifdef CONFIG_STACKTRACE
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
 				 int skip, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -1026,32 +1032,28 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags,
-			       int skip, int pc)
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+			int skip, int pc)
 {
 	if (!(trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(buffer, flags, skip, pc);
 }
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc)
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc)
 {
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(tr->buffer, flags, skip, pc);
 }
 
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   unsigned long flags, int pc)
+void
+ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
@@ -1060,7 +1062,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -1074,9 +1076,8 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
 #ifdef UNUSED
@@ -1086,6 +1087,8 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 }
 #endif /* UNUSED */
 
+#endif /* CONFIG_STACKTRACE */
+
 static void
 ftrace_trace_special(void *__tr,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
@@ -1093,9 +1096,10 @@ ftrace_trace_special(void *__tr,
 {
 	struct ring_buffer_event *event;
 	struct trace_array *tr = __tr;
+	struct ring_buffer *buffer = tr->buffer;
 	struct special_entry *entry;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL,
+	event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
 					  sizeof(*entry), 0, pc);
 	if (!event)
 		return;
@@ -1103,7 +1107,7 @@ ftrace_trace_special(void *__tr,
 	entry->arg1			= arg1;
 	entry->arg2			= arg2;
 	entry->arg3			= arg3;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void
@@ -1114,62 +1118,6 @@ __trace_special(void *__tr, void *__data,
 }
 
 void
-tracing_sched_switch_trace(struct trace_array *tr,
-			   struct task_struct *prev,
-			   struct task_struct *next,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_context_switch;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_CTX,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= prev->pid;
-	entry->prev_prio		= prev->prio;
-	entry->prev_state		= prev->state;
-	entry->next_pid			= next->pid;
-	entry->next_prio		= next->prio;
-	entry->next_state		= next->state;
-	entry->next_cpu	= task_cpu(next);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, flags, pc);
-}
-
-void
-tracing_sched_wakeup_trace(struct trace_array *tr,
-			   struct task_struct *wakee,
-			   struct task_struct *curr,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_wakeup;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= curr->pid;
-	entry->prev_prio		= curr->prio;
-	entry->prev_state		= curr->state;
-	entry->next_pid			= wakee->pid;
-	entry->next_prio		= wakee->prio;
-	entry->next_state		= wakee->state;
-	entry->next_cpu			= task_cpu(wakee);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
-}
-
-void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
 	struct trace_array *tr = &global_trace;
@@ -1193,68 +1141,6 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-int trace_graph_entry(struct ftrace_graph_ent *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int ret;
-	int cpu;
-	int pc;
-
-	if (!ftrace_trace_task(current))
-		return 0;
-
-	if (!ftrace_graph_addr(trace->func))
-		return 0;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		ret = __trace_graph_entry(tr, trace, flags, pc);
-	} else {
-		ret = 0;
-	}
-	/* Only do the atomic if it is not already set */
-	if (!test_tsk_trace_graph(current))
-		set_tsk_trace_graph(current);
-
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-void trace_graph_return(struct ftrace_graph_ret *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int cpu;
-	int pc;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		__trace_graph_return(tr, trace, flags, pc);
-	}
-	if (!trace->depth)
-		clear_tsk_trace_graph(current);
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
@@ -1267,6 +1153,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	struct bprint_entry *entry;
@@ -1299,7 +1186,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		goto out_unlock;
 
 	size = sizeof(*entry) + sizeof(u32) * len;
-	event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+					  flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1307,8 +1196,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
 out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
@@ -1323,14 +1212,30 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, const char *fmt, va_list 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_vprintk(struct trace_array *tr,
+			unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
 
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
-	struct trace_array *tr = &global_trace;
+	struct ring_buffer *buffer;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
 	struct print_entry *entry;
@@ -1358,7 +1263,9 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	trace_buf[len] = 0;
 
 	size = sizeof(*entry) + len + 1;
-	event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					  irq_flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1366,8 +1273,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
  out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
@@ -1379,6 +1286,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	return len;
 }
+
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+{
+	return trace_array_printk(&global_trace, ip, fmt, args);
+}
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
 enum trace_file_type {
@@ -1518,6 +1430,37 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 	return ent;
 }
 
+static 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;
+
+	if (!iter->buffer_iter[cpu])
+		return;
+
+	buf_iter = iter->buffer_iter[cpu];
+	ring_buffer_iter_reset(buf_iter);
+
+	/*
+	 * We could have the case with the max latency tracers
+	 * that a reset never took place on a cpu. This is evident
+	 * 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)
+			break;
+		entries++;
+		ring_buffer_read(buf_iter, NULL);
+	}
+
+	tr->data[cpu]->skipped_entries = entries;
+}
+
 /*
  * No necessary locking here. The worst thing which can
  * happen is loosing events consumed at the same time
@@ -1556,10 +1499,9 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 		if (cpu_file == TRACE_PIPE_ALL_CPU) {
 			for_each_tracing_cpu(cpu)
-				ring_buffer_iter_reset(iter->buffer_iter[cpu]);
+				tracing_iter_reset(iter, cpu);
 		} else
-			ring_buffer_iter_reset(iter->buffer_iter[cpu_file]);
-
+			tracing_iter_reset(iter, cpu_file);
 
 		ftrace_enable_cpu();
 
@@ -1608,16 +1550,32 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	struct trace_array *tr = iter->tr;
 	struct trace_array_cpu *data = tr->data[tr->cpu];
 	struct tracer *type = current_trace;
-	unsigned long total;
-	unsigned long entries;
+	unsigned long entries = 0;
+	unsigned long total = 0;
+	unsigned long count;
 	const char *name = "preemption";
+	int cpu;
 
 	if (type)
 		name = type->name;
 
-	entries = ring_buffer_entries(iter->tr->buffer);
-	total = entries +
-		ring_buffer_overruns(iter->tr->buffer);
+
+	for_each_tracing_cpu(cpu) {
+		count = ring_buffer_entries_cpu(tr->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;
+			/* total is the same as the entries */
+			total += count;
+		} else
+			total += count +
+				ring_buffer_overrun_cpu(tr->buffer, cpu);
+		entries += count;
+	}
 
 	seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
 		   name, UTS_RELEASE);
@@ -1659,7 +1617,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		seq_puts(m, "\n#  => ended at:   ");
 		seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
 		trace_print_seq(m, &iter->seq);
-		seq_puts(m, "#\n");
+		seq_puts(m, "\n#\n");
 	}
 
 	seq_puts(m, "#\n");
@@ -1678,6 +1636,9 @@ 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)
+		return;
+
 	cpumask_set_cpu(iter->cpu, iter->started);
 
 	/* Don't print started cpu buffer for the first entry of the trace */
@@ -1940,19 +1901,23 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (ring_buffer_overruns(iter->tr->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+	/* stop the trace while dumping */
+	tracing_stop();
+
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
 
 			iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+		tracing_iter_reset(iter, cpu);
 	}
 
-	/* TODO stop tracer */
 	ret = seq_open(file, &tracer_seq_ops);
 	if (ret < 0) {
 		fail_ret = ERR_PTR(ret);
@@ -1962,9 +1927,6 @@ __tracing_open(struct inode *inode, struct file *file)
 	m = file->private_data;
 	m->private = iter;
 
-	/* stop the trace while dumping */
-	tracing_stop();
-
 	mutex_unlock(&trace_types_lock);
 
 	return iter;
@@ -1975,6 +1937,7 @@ __tracing_open(struct inode *inode, struct file *file)
 			ring_buffer_read_finish(iter->buffer_iter[cpu]);
 	}
 	free_cpumask_var(iter->started);
+	tracing_start();
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
@@ -2031,7 +1994,7 @@ 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_APPEND)) {
+	    (file->f_flags & O_TRUNC)) {
 		long cpu = (long) inode->i_private;
 
 		if (cpu == TRACE_PIPE_ALL_CPU)
@@ -2053,25 +2016,23 @@ static int tracing_open(struct inode *inode, struct file *file)
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t = v;
 
 	(*pos)++;
 
 	if (t)
 		t = t->next;
 
-	m->private = t;
-
 	return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t;
 	loff_t l = 0;
 
 	mutex_lock(&trace_types_lock);
-	for (; t && l < *pos; t = t_next(m, t, &l))
+	for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
 		;
 
 	return t;
@@ -2107,18 +2068,10 @@ static struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
 	if (tracing_disabled)
 		return -ENODEV;
 
-	ret = seq_open(file, &show_traces_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = trace_types;
-	}
-
-	return ret;
+	return seq_open(file, &show_traces_seq_ops);
 }
 
 static ssize_t
@@ -2191,11 +2144,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&tracing_cpumask_update_lock);
 	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
 	if (err)
 		goto err_unlock;
 
+	mutex_lock(&tracing_cpumask_update_lock);
+
 	local_irq_disable();
 	__raw_spin_lock(&ftrace_max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -2223,8 +2177,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	return count;
 
 err_unlock:
-	mutex_unlock(&tracing_cpumask_update_lock);
-	free_cpumask_var(tracing_cpumask);
+	free_cpumask_var(tracing_cpumask_new);
 
 	return err;
 }
@@ -2266,8 +2219,8 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 		len += 3; /* "no" and newline */
 	}
 
-	/* +2 for \n and \0 */
-	buf = kmalloc(len + 2, GFP_KERNEL);
+	/* +1 for \0 */
+	buf = kmalloc(len + 1, GFP_KERNEL);
 	if (!buf) {
 		mutex_unlock(&trace_types_lock);
 		return -ENOMEM;
@@ -2290,7 +2243,7 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 	}
 	mutex_unlock(&trace_types_lock);
 
-	WARN_ON(r >= len + 2);
+	WARN_ON(r >= len + 1);
 
 	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 
@@ -2301,23 +2254,23 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 /* Try to assign a tracer specific option */
 static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 {
-	struct tracer_flags *trace_flags = trace->flags;
+	struct tracer_flags *tracer_flags = trace->flags;
 	struct tracer_opt *opts = NULL;
 	int ret = 0, i = 0;
 	int len;
 
-	for (i = 0; trace_flags->opts[i].name; i++) {
-		opts = &trace_flags->opts[i];
+	for (i = 0; tracer_flags->opts[i].name; i++) {
+		opts = &tracer_flags->opts[i];
 		len = strlen(opts->name);
 
 		if (strncmp(cmp, opts->name, len) == 0) {
-			ret = trace->set_flag(trace_flags->val,
+			ret = trace->set_flag(tracer_flags->val,
 				opts->bit, !neg);
 			break;
 		}
 	}
 	/* Not found */
-	if (!trace_flags->opts[i].name)
+	if (!tracer_flags->opts[i].name)
 		return -EINVAL;
 
 	/* Refused to handle */
@@ -2325,9 +2278,9 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 		return ret;
 
 	if (neg)
-		trace_flags->val &= ~opts->bit;
+		tracer_flags->val &= ~opts->bit;
 	else
-		trace_flags->val |= opts->bit;
+		tracer_flags->val |= opts->bit;
 
 	return 0;
 }
@@ -2342,22 +2295,6 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 		trace_flags |= mask;
 	else
 		trace_flags &= ~mask;
-
-	if (mask == TRACE_ITER_GLOBAL_CLK) {
-		u64 (*func)(void);
-
-		if (enabled)
-			func = trace_clock_global;
-		else
-			func = trace_clock_local;
-
-		mutex_lock(&trace_types_lock);
-		ring_buffer_set_clock(global_trace.buffer, func);
-
-		if (max_tr.buffer)
-			ring_buffer_set_clock(max_tr.buffer, func);
-		mutex_unlock(&trace_types_lock);
-	}
 }
 
 static ssize_t
@@ -3095,7 +3032,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 			break;
 		}
 
-		trace_consume(iter);
+		if (ret != TRACE_TYPE_NO_CONSUME)
+			trace_consume(iter);
 		rem -= count;
 		if (!find_next_entry_inc(iter))	{
 			rem = 0;
@@ -3324,6 +3262,62 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int bufiter = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
+		bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter,
+			"%s%s%s%s", i ? " " : "",
+			i == trace_clock_id ? "[" : "", trace_clocks[i].name,
+			i == trace_clock_id ? "]" : "");
+	bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter);
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *fpos)
+{
+	char buf[64];
+	const char *clockstr;
+	int i;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	clockstr = strstrip(buf);
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
+		if (strcmp(trace_clocks[i].name, clockstr) == 0)
+			break;
+	}
+	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);
+
+	mutex_unlock(&trace_types_lock);
+
+	*fpos += cnt;
+
+	return cnt;
+}
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -3361,6 +3355,12 @@ static const struct file_operations tracing_mark_fops = {
 	.write		= tracing_mark_write,
 };
 
+static const struct file_operations trace_clock_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_clock_read,
+	.write		= tracing_clock_write,
+};
+
 struct ftrace_buffer_info {
 	struct trace_array	*tr;
 	void			*spare;
@@ -3626,7 +3626,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	struct trace_seq *s;
 	unsigned long cnt;
 
-	s = kmalloc(sizeof(*s), GFP_ATOMIC);
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
 		return ENOMEM;
 
@@ -3641,9 +3641,6 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
-	cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
-	trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
-
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -3904,17 +3901,9 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (ret < 0)
 		return ret;
 
-	switch (val) {
-	case 0:
-		trace_flags &= ~(1 << index);
-		break;
-	case 1:
-		trace_flags |= 1 << index;
-		break;
-
-	default:
+	if (val != 0 && val != 1)
 		return -EINVAL;
-	}
+	set_tracer_flags(1 << index, val);
 
 	*ppos += cnt;
 
@@ -4082,11 +4071,13 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("current_tracer", 0644, d_tracer,
 			&global_trace, &set_tracer_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tracing_max_latency, &tracing_max_lat_fops);
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
+#endif
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
@@ -4103,6 +4094,9 @@ static __init int tracer_init_debugfs(void)
 	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);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -4243,8 +4237,11 @@ static void __ftrace_dump(bool disable_tracing)
 		iter.pos = -1;
 
 		if (find_next_entry_inc(&iter) != NULL) {
-			print_trace_line(&iter);
-			trace_consume(&iter);
+			int ret;
+
+			ret = print_trace_line(&iter);
+			if (ret != TRACE_TYPE_NO_CONSUME)
+				trace_consume(&iter);
 		}
 
 		trace_printk_seq(&iter.seq);
@@ -4278,7 +4275,6 @@ void ftrace_dump(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	struct trace_array_cpu *data;
 	int ring_buf_size;
 	int i;
 	int ret = -ENOMEM;
@@ -4328,7 +4324,7 @@ __init static int tracer_alloc_buffers(void)
 
 	/* Allocate the first page for all buffers */
 	for_each_tracing_cpu(i) {
-		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 	}
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ff1ef411a17..ea7e0bcbd53 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -38,8 +38,6 @@ enum trace_type {
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
 	TRACE_HW_BRANCHES,
-	TRACE_SYSCALL_ENTER,
-	TRACE_SYSCALL_EXIT,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
 	TRACE_POWER,
@@ -251,9 +249,6 @@ struct trace_array_cpu {
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
-	/* these fields get copied into max-trace: */
-	unsigned long		trace_idx;
-	unsigned long		overrun;
 	unsigned long		saved_latency;
 	unsigned long		critical_start;
 	unsigned long		critical_end;
@@ -261,6 +256,7 @@ struct trace_array_cpu {
 	unsigned long		nice;
 	unsigned long		policy;
 	unsigned long		rt_priority;
+	unsigned long		skipped_entries;
 	cycle_t			preempt_timestamp;
 	pid_t			pid;
 	uid_t			uid;
@@ -334,10 +330,6 @@ extern void __ftrace_bad_type(void);
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
 			  TRACE_KMEM_FREE);	\
-		IF_ASSIGN(var, ent, struct syscall_trace_enter,		\
-			  TRACE_SYSCALL_ENTER);				\
-		IF_ASSIGN(var, ent, struct syscall_trace_exit,		\
-			  TRACE_SYSCALL_EXIT);				\
 		IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
 		__ftrace_bad_type();					\
 	} while (0)
@@ -439,12 +431,13 @@ void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags,
-						    int pc);
-void trace_buffer_unlock_commit(struct trace_array *tr,
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags,
+			  int pc);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
@@ -454,10 +447,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts);
 
-void tracing_generic_entry_update(struct trace_entry *entry,
-				  unsigned long flags,
-				  int pc);
-
 void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 
@@ -487,6 +476,7 @@ void trace_function(struct trace_array *tr,
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
+void set_graph_array(struct trace_array *tr);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -498,16 +488,40 @@ void unregister_tracer(struct tracer *type);
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
 extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
+#endif /* CONFIG_TRACER_MAX_TRACE */
+
+#ifdef CONFIG_STACKTRACE
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+			int skip, int pc);
+
+void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
+			    int pc);
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc);
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc);
+#else
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      unsigned long flags, int skip, int pc)
+{
+}
+
+static inline void ftrace_trace_userstack(struct trace_array *tr,
+					  unsigned long flags, int pc)
+{
+}
+
+static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
+				 int skip, int pc)
+{
+}
+#endif /* CONFIG_STACKTRACE */
 
 extern cycle_t ftrace_now(int cpu);
 
@@ -533,6 +547,10 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
+extern int ring_buffer_expanded;
+extern bool tracing_selftest_disabled;
+DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
 					   struct trace_array *tr);
@@ -566,9 +584,16 @@ extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
 trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+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, ...);
 
 extern unsigned long trace_flags;
 
+extern int trace_clock_id;
+
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern enum print_line_t print_graph_function(struct trace_iterator *iter);
@@ -615,6 +640,7 @@ print_graph_function(struct trace_iterator *iter)
 
 extern struct pid *ftrace_pid_trace;
 
+#ifdef CONFIG_FUNCTION_TRACER
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	if (!ftrace_pid_trace)
@@ -622,6 +648,12 @@ static inline int ftrace_trace_task(struct task_struct *task)
 
 	return test_tsk_trace_trace(task);
 }
+#else
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+	return 1;
+}
+#endif
 
 /*
  * trace_iterator_flags is an enumeration that defines bit
@@ -650,9 +682,8 @@ enum trace_iterator_flags {
 	TRACE_ITER_PRINTK_MSGONLY	= 0x10000,
 	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
-	TRACE_ITER_GLOBAL_CLK		= 0x80000,
-	TRACE_ITER_SLEEP_TIME		= 0x100000,
-	TRACE_ITER_GRAPH_TIME		= 0x200000,
+	TRACE_ITER_SLEEP_TIME		= 0x80000,
+	TRACE_ITER_GRAPH_TIME		= 0x100000,
 };
 
 /*
@@ -749,6 +780,7 @@ struct ftrace_event_field {
 	struct list_head	link;
 	char			*name;
 	char			*type;
+	int			filter_type;
 	int			offset;
 	int			size;
 	int			is_signed;
@@ -758,13 +790,15 @@ struct event_filter {
 	int			n_preds;
 	struct filter_pred	**preds;
 	char			*filter_string;
+	bool			no_reset;
 };
 
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
 	struct dentry		*entry;
-	void			*filter;
+	struct event_filter	*filter;
+	int			nr_events;
 };
 
 struct filter_pred;
@@ -792,6 +826,7 @@ extern int apply_subsystem_event_filter(struct event_subsystem *system,
 					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);
 
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index a29ef23ffb4..19bfc75d467 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -41,14 +41,12 @@ void disable_boot_trace(void)
 
 static int boot_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	boot_trace = tr;
 
 	if (!tr)
 		return 0;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	tracing_sched_switch_assign_trace(tr);
 	return 0;
@@ -132,6 +130,7 @@ struct tracer boot_tracer __read_mostly =
 void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_call *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -144,13 +143,14 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_call = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -158,6 +158,7 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_ret *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -167,13 +168,14 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_ret = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 5b5895afecf..11ba5bb4ed0 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -14,7 +14,7 @@ int ftrace_profile_enable(int event_id)
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id) {
+		if (event->id == event_id && event->profile_enable) {
 			ret = event->profile_enable(event);
 			break;
 		}
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index 5e32e375134..6db005e1248 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -26,6 +26,9 @@ TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
 		   ftrace_graph_ret_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, ret.func, func)
+		TRACE_FIELD(unsigned long long, ret.calltime, calltime)
+		TRACE_FIELD(unsigned long long, ret.rettime, rettime)
+		TRACE_FIELD(unsigned long, ret.overrun, overrun)
 		TRACE_FIELD(int, ret.depth, depth)
 	),
 	TP_RAW_FMT("<-- %lx (%d)")
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aa08be69a1b..78b1ed23017 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -17,6 +17,8 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 
+#include <asm/setup.h>
+
 #include "trace_output.h"
 
 #define TRACE_SYSTEM "TRACE_SYSTEM"
@@ -25,8 +27,9 @@ DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size, int is_signed)
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+		       const char *name, int offset, int size, int is_signed,
+		       int filter_type)
 {
 	struct ftrace_event_field *field;
 
@@ -42,9 +45,15 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
 	if (!field->type)
 		goto err;
 
+	if (filter_type == FILTER_OTHER)
+		field->filter_type = filter_assign_type(type);
+	else
+		field->filter_type = filter_type;
+
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
+
 	list_add(&field->link, &call->fields);
 
 	return 0;
@@ -60,6 +69,29 @@ err:
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
+#define __common_field(type, item)					\
+	ret = trace_define_field(call, #type, "common_" #item,		\
+				 offsetof(typeof(ent), item),		\
+				 sizeof(ent.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+int trace_define_common_fields(struct ftrace_event_call *call)
+{
+	int ret;
+	struct trace_entry ent;
+
+	__common_field(unsigned short, type);
+	__common_field(unsigned char, flags);
+	__common_field(unsigned char, preempt_count);
+	__common_field(int, pid);
+	__common_field(int, tgid);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(trace_define_common_fields);
+
 #ifdef CONFIG_MODULES
 
 static void trace_destroy_fields(struct ftrace_event_call *call)
@@ -84,14 +116,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 		if (call->enabled) {
 			call->enabled = 0;
 			tracing_stop_cmdline_record();
-			call->unregfunc();
+			call->unregfunc(call->data);
 		}
 		break;
 	case 1:
 		if (!call->enabled) {
 			call->enabled = 1;
 			tracing_start_cmdline_record();
-			call->regfunc();
+			call->regfunc(call->data);
 		}
 		break;
 	}
@@ -300,10 +332,18 @@ 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 = NULL;
+	loff_t l;
+
 	mutex_lock(&event_mutex);
-	if (*pos == 0)
-		m->private = ftrace_events.next;
-	return t_next(m, NULL, pos);
+
+	m->private = ftrace_events.next;
+	for (l = 0; l <= *pos; ) {
+		call = t_next(m, NULL, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 static void *
@@ -332,10 +372,18 @@ 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 = NULL;
+	loff_t l;
+
 	mutex_lock(&event_mutex);
-	if (*pos == 0)
-		m->private = ftrace_events.next;
-	return s_next(m, NULL, pos);
+
+	m->private = ftrace_events.next;
+	for (l = 0; l <= *pos; ) {
+		call = s_next(m, NULL, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 static int t_show(struct seq_file *m, void *v)
@@ -360,7 +408,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
 	const struct seq_operations *seq_ops;
 
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND))
+	    (file->f_flags & O_TRUNC))
 		ftrace_clear_events();
 
 	seq_ops = inode->i_private;
@@ -558,7 +606,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_printf(s, "format:\n");
 	trace_write_header(s);
 
-	r = call->show_format(s);
+	r = call->show_format(call, s);
 	if (!r) {
 		/*
 		 * ug!  The format output is bigger than a PAGE!!
@@ -833,8 +881,10 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0)
+		if (strcmp(system->name, name) == 0) {
+			system->nr_events++;
 			return system->entry;
+		}
 	}
 
 	/* need to create new entry */
@@ -853,6 +903,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 		return d_events;
 	}
 
+	system->nr_events = 1;
 	system->name = kstrdup(name, GFP_KERNEL);
 	if (!system->name) {
 		debugfs_remove(system->entry);
@@ -904,15 +955,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	if (strcmp(call->system, TRACE_SYSTEM) != 0)
 		d_events = event_subsystem_dir(call->system, d_events);
 
-	if (call->raw_init) {
-		ret = call->raw_init();
-		if (ret < 0) {
-			pr_warning("Could not initialize trace point"
-				   " events/%s\n", call->name);
-			return ret;
-		}
-	}
-
 	call->dir = debugfs_create_dir(call->name, d_events);
 	if (!call->dir) {
 		pr_warning("Could not create debugfs "
@@ -924,12 +966,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		entry = trace_create_file("enable", 0644, call->dir, call,
 					  enable);
 
-	if (call->id)
+	if (call->id && call->profile_enable)
 		entry = trace_create_file("id", 0444, call->dir, call,
 					  id);
 
 	if (call->define_fields) {
-		ret = call->define_fields();
+		ret = call->define_fields(call);
 		if (ret < 0) {
 			pr_warning("Could not initialize trace point"
 				   " events/%s\n", call->name);
@@ -971,6 +1013,32 @@ struct ftrace_module_file_ops {
 	struct file_operations		filter;
 };
 
+static void remove_subsystem_dir(const char *name)
+{
+	struct event_subsystem *system;
+
+	if (strcmp(name, TRACE_SYSTEM) == 0)
+		return;
+
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (strcmp(system->name, name) == 0) {
+			if (!--system->nr_events) {
+				struct event_filter *filter = system->filter;
+
+				debugfs_remove_recursive(system->entry);
+				list_del(&system->list);
+				if (filter) {
+					kfree(filter->filter_string);
+					kfree(filter);
+				}
+				kfree(system->name);
+				kfree(system);
+			}
+			break;
+		}
+	}
+}
+
 static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
@@ -1011,6 +1079,7 @@ static void trace_module_add_events(struct module *mod)
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call, *start, *end;
 	struct dentry *d_events;
+	int ret;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1026,7 +1095,15 @@ static void trace_module_add_events(struct module *mod)
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-
+		if (call->raw_init) {
+			ret = call->raw_init();
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
 		/*
 		 * This module has events, create file ops for this module
 		 * if not already done.
@@ -1061,6 +1138,7 @@ static void trace_module_remove_events(struct module *mod)
 			list_del(&call->list);
 			trace_destroy_fields(call);
 			destroy_preds(call);
+			remove_subsystem_dir(call->system);
 		}
 	}
 
@@ -1117,6 +1195,18 @@ struct notifier_block trace_module_nb = {
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+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;
+
+	return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
 static __init int event_trace_init(void)
 {
 	struct ftrace_event_call *call;
@@ -1124,6 +1214,8 @@ static __init int event_trace_init(void)
 	struct dentry *entry;
 	struct dentry *d_events;
 	int ret;
+	char *buf = bootup_event_buf;
+	char *token;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -1163,12 +1255,34 @@ static __init int event_trace_init(void)
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
+		if (call->raw_init) {
+			ret = call->raw_init();
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
 		list_add(&call->list, &ftrace_events);
 		event_create_dir(call, d_events, &ftrace_event_id_fops,
 				 &ftrace_enable_fops, &ftrace_event_filter_fops,
 				 &ftrace_event_format_fops);
 	}
 
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		ret = ftrace_set_clr_event(token, 1);
+		if (ret)
+			pr_warning("Failed to enable trace event: %s\n", token);
+	}
+
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
 		pr_warning("Failed to register trace events module notifier\n");
@@ -1324,6 +1438,7 @@ static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct ftrace_entry *entry;
 	unsigned long flags;
 	long disabled;
@@ -1341,7 +1456,8 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 
 	local_save_flags(flags);
 
-	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+	event = trace_current_buffer_lock_reserve(&buffer,
+						  TRACE_FN, sizeof(*entry),
 						  flags, pc);
 	if (!event)
 		goto out;
@@ -1349,7 +1465,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_nowake_buffer_unlock_commit(event, flags, pc);
+	trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
 	atomic_dec(&per_cpu(test_event_disable, cpu));
@@ -1376,10 +1492,10 @@ static __init void event_trace_self_test_with_function(void)
 
 static __init int event_trace_self_tests_init(void)
 {
-
-	event_trace_self_tests();
-
-	event_trace_self_test_with_function();
+	if (!tracing_selftest_disabled) {
+		event_trace_self_tests();
+		event_trace_self_test_with_function();
+	}
 
 	return 0;
 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index db6e54bdb59..93660fbbf62 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -27,8 +27,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-static DEFINE_MUTEX(filter_mutex);
-
 enum filter_op_ids
 {
 	OP_OR,
@@ -165,6 +163,20 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 	return match;
 }
 
+/* Filter predicate for char * pointers */
+static int filter_pred_pchar(struct filter_pred *pred, void *event,
+			     int val1, int val2)
+{
+	char **addr = (char **)(event + pred->offset);
+	int cmp, match;
+
+	cmp = strncmp(*addr, pred->str_val, pred->str_len);
+
+	match = (!cmp) ^ pred->not;
+
+	return match;
+}
+
 /*
  * Filter predicate for dynamic sized arrays of characters.
  * These are implemented through a list of strings at the end
@@ -178,11 +190,13 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 static int filter_pred_strloc(struct filter_pred *pred, void *event,
 			      int val1, int val2)
 {
-	int str_loc = *(int *)(event + pred->offset);
+	u32 str_item = *(u32 *)(event + pred->offset);
+	int str_loc = str_item & 0xffff;
+	int str_len = str_item >> 16;
 	char *addr = (char *)(event + str_loc);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, pred->str_len);
+	cmp = strncmp(addr, pred->str_val, str_len);
 
 	match = (!cmp) ^ pred->not;
 
@@ -294,12 +308,12 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
 {
 	struct event_filter *filter = call->filter;
 
-	mutex_lock(&filter_mutex);
-	if (filter->filter_string)
+	mutex_lock(&event_mutex);
+	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 }
 
 void print_subsystem_event_filter(struct event_subsystem *system,
@@ -307,12 +321,12 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 {
 	struct event_filter *filter = system->filter;
 
-	mutex_lock(&filter_mutex);
-	if (filter->filter_string)
+	mutex_lock(&event_mutex);
+	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
 	else
 		trace_seq_printf(s, "none\n");
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 }
 
 static struct ftrace_event_field *
@@ -376,26 +390,32 @@ void destroy_preds(struct ftrace_event_call *call)
 	struct event_filter *filter = call->filter;
 	int i;
 
+	if (!filter)
+		return;
+
 	for (i = 0; i < MAX_FILTER_PRED; i++) {
 		if (filter->preds[i])
 			filter_free_pred(filter->preds[i]);
 	}
 	kfree(filter->preds);
+	kfree(filter->filter_string);
 	kfree(filter);
 	call->filter = NULL;
 }
 
-int init_preds(struct ftrace_event_call *call)
+static int init_preds(struct ftrace_event_call *call)
 {
 	struct event_filter *filter;
 	struct filter_pred *pred;
 	int i;
 
+	if (call->filter)
+		return 0;
+
 	filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
 	if (!call->filter)
 		return -ENOMEM;
 
-	call->filter_active = 0;
 	filter->n_preds = 0;
 
 	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
@@ -417,33 +437,56 @@ oom:
 
 	return -ENOMEM;
 }
-EXPORT_SYMBOL_GPL(init_preds);
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static int init_subsystem_preds(struct event_subsystem *system)
 {
-	struct event_filter *filter = system->filter;
 	struct ftrace_event_call *call;
-	int i;
+	int err;
 
-	if (filter->n_preds) {
-		for (i = 0; i < filter->n_preds; i++)
-			filter_free_pred(filter->preds[i]);
-		kfree(filter->preds);
-		filter->preds = NULL;
-		filter->n_preds = 0;
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->define_fields)
+			continue;
+
+		if (strcmp(call->system, system->name) != 0)
+			continue;
+
+		err = init_preds(call);
+		if (err)
+			return err;
 	}
 
-	mutex_lock(&event_mutex);
+	return 0;
+}
+
+enum {
+	FILTER_DISABLE_ALL,
+	FILTER_INIT_NO_RESET,
+	FILTER_SKIP_NO_RESET,
+};
+
+static void filter_free_subsystem_preds(struct event_subsystem *system,
+					int flag)
+{
+	struct ftrace_event_call *call;
+
 	list_for_each_entry(call, &ftrace_events, list) {
 		if (!call->define_fields)
 			continue;
 
-		if (!strcmp(call->system, system->name)) {
-			filter_disable_preds(call);
-			remove_filter_string(call->filter);
+		if (strcmp(call->system, system->name) != 0)
+			continue;
+
+		if (flag == FILTER_INIT_NO_RESET) {
+			call->filter->no_reset = false;
+			continue;
 		}
+
+		if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
+			continue;
+
+		filter_disable_preds(call);
+		remove_filter_string(call->filter);
 	}
-	mutex_unlock(&event_mutex);
 }
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
@@ -471,12 +514,7 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
 	return 0;
 }
 
-enum {
-	FILTER_STATIC_STRING = 1,
-	FILTER_DYN_STRING
-};
-
-static int is_string_field(const char *type)
+int filter_assign_type(const char *type)
 {
 	if (strstr(type, "__data_loc") && strstr(type, "char"))
 		return FILTER_DYN_STRING;
@@ -484,12 +522,19 @@ static int is_string_field(const char *type)
 	if (strchr(type, '[') && strstr(type, "char"))
 		return FILTER_STATIC_STRING;
 
-	return 0;
+	return FILTER_OTHER;
+}
+
+static bool is_string_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_DYN_STRING ||
+	       field->filter_type == FILTER_STATIC_STRING ||
+	       field->filter_type == FILTER_PTR_STRING;
 }
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-	if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+	if (is_string_field(field) && (op != OP_EQ && op != OP_NE))
 		return 0;
 
 	return 1;
@@ -540,21 +585,24 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 
 static int filter_add_pred(struct filter_parse_state *ps,
 			   struct ftrace_event_call *call,
-			   struct filter_pred *pred)
+			   struct filter_pred *pred,
+			   bool dry_run)
 {
 	struct ftrace_event_field *field;
 	filter_pred_fn_t fn;
 	unsigned long long val;
-	int string_type;
+	int ret;
 
 	pred->fn = filter_pred_none;
 
 	if (pred->op == OP_AND) {
 		pred->pop_n = 2;
-		return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+		fn = filter_pred_and;
+		goto add_pred_fn;
 	} else if (pred->op == OP_OR) {
 		pred->pop_n = 2;
-		return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+		fn = filter_pred_or;
+		goto add_pred_fn;
 	}
 
 	field = find_event_field(call, pred->field_name);
@@ -570,62 +618,55 @@ static int filter_add_pred(struct filter_parse_state *ps,
 		return -EINVAL;
 	}
 
-	string_type = is_string_field(field->type);
-	if (string_type) {
-		if (string_type == FILTER_STATIC_STRING)
+	if (is_string_field(field)) {
+		pred->str_len = field->size;
+
+		if (field->filter_type == FILTER_STATIC_STRING)
 			fn = filter_pred_string;
-		else
+		else if (field->filter_type == FILTER_DYN_STRING)
 			fn = filter_pred_strloc;
-		pred->str_len = field->size;
-		if (pred->op == OP_NE)
-			pred->not = 1;
-		return filter_add_pred_fn(ps, call, pred, fn);
+		else {
+			fn = filter_pred_pchar;
+			pred->str_len = strlen(pred->str_val);
+		}
 	} else {
-		if (strict_strtoull(pred->str_val, 0, &val)) {
+		if (field->is_signed)
+			ret = strict_strtoll(pred->str_val, 0, &val);
+		else
+			ret = strict_strtoull(pred->str_val, 0, &val);
+		if (ret) {
 			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
 			return -EINVAL;
 		}
 		pred->val = val;
-	}
 
-	fn = select_comparison_fn(pred->op, field->size, field->is_signed);
-	if (!fn) {
-		parse_error(ps, FILT_ERR_INVALID_OP, 0);
-		return -EINVAL;
+		fn = select_comparison_fn(pred->op, field->size,
+					  field->is_signed);
+		if (!fn) {
+			parse_error(ps, FILT_ERR_INVALID_OP, 0);
+			return -EINVAL;
+		}
 	}
 
 	if (pred->op == OP_NE)
 		pred->not = 1;
 
-	return filter_add_pred_fn(ps, call, pred, fn);
+add_pred_fn:
+	if (!dry_run)
+		return filter_add_pred_fn(ps, call, pred, fn);
+	return 0;
 }
 
 static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 				     struct event_subsystem *system,
 				     struct filter_pred *pred,
-				     char *filter_string)
+				     char *filter_string,
+				     bool dry_run)
 {
-	struct event_filter *filter = system->filter;
 	struct ftrace_event_call *call;
 	int err = 0;
+	bool fail = true;
 
-	if (!filter->preds) {
-		filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-					GFP_KERNEL);
-
-		if (!filter->preds)
-			return -ENOMEM;
-	}
-
-	if (filter->n_preds == MAX_FILTER_PRED) {
-		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
-		return -ENOSPC;
-	}
-
-	filter->preds[filter->n_preds] = pred;
-	filter->n_preds++;
-
-	mutex_lock(&event_mutex);
 	list_for_each_entry(call, &ftrace_events, list) {
 
 		if (!call->define_fields)
@@ -634,18 +675,24 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 		if (strcmp(call->system, system->name))
 			continue;
 
-		err = filter_add_pred(ps, call, pred);
-		if (err) {
-			mutex_unlock(&event_mutex);
-			filter_free_subsystem_preds(system);
-			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-			goto out;
-		}
-		replace_filter_string(call->filter, filter_string);
+		if (call->filter->no_reset)
+			continue;
+
+		err = filter_add_pred(ps, call, pred, dry_run);
+		if (err)
+			call->filter->no_reset = true;
+		else
+			fail = false;
+
+		if (!dry_run)
+			replace_filter_string(call->filter, filter_string);
 	}
-	mutex_unlock(&event_mutex);
-out:
-	return err;
+
+	if (fail) {
+		parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+		return err;
+	}
+	return 0;
 }
 
 static void parse_init(struct filter_parse_state *ps,
@@ -1004,12 +1051,14 @@ static int check_preds(struct filter_parse_state *ps)
 static int replace_preds(struct event_subsystem *system,
 			 struct ftrace_event_call *call,
 			 struct filter_parse_state *ps,
-			 char *filter_string)
+			 char *filter_string,
+			 bool dry_run)
 {
 	char *operand1 = NULL, *operand2 = NULL;
 	struct filter_pred *pred;
 	struct postfix_elt *elt;
 	int err;
+	int n_preds = 0;
 
 	err = check_preds(ps);
 	if (err)
@@ -1028,19 +1077,14 @@ static int replace_preds(struct event_subsystem *system,
 			continue;
 		}
 
+		if (n_preds++ == MAX_FILTER_PRED) {
+			parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+			return -ENOSPC;
+		}
+
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			pred = create_logical_pred(elt->op);
-			if (call) {
-				err = filter_add_pred(ps, call, pred);
-				filter_free_pred(pred);
-			} else
-				err = filter_add_subsystem_pred(ps, system,
-							pred, filter_string);
-			if (err)
-				return err;
-
-			operand1 = operand2 = NULL;
-			continue;
+			goto add_pred;
 		}
 
 		if (!operand1 || !operand2) {
@@ -1049,12 +1093,15 @@ static int replace_preds(struct event_subsystem *system,
 		}
 
 		pred = create_pred(elt->op, operand1, operand2);
-		if (call) {
-			err = filter_add_pred(ps, call, pred);
-			filter_free_pred(pred);
-		} else
+add_pred:
+		if (!pred)
+			return -ENOMEM;
+		if (call)
+			err = filter_add_pred(ps, call, pred, false);
+		else
 			err = filter_add_subsystem_pred(ps, system, pred,
-							filter_string);
+						filter_string, dry_run);
+		filter_free_pred(pred);
 		if (err)
 			return err;
 
@@ -1070,12 +1117,16 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 
 	struct filter_parse_state *ps;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
+
+	err = init_preds(call);
+	if (err)
+		goto out_unlock;
 
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_disable_preds(call);
 		remove_filter_string(call->filter);
-		mutex_unlock(&filter_mutex);
+		mutex_unlock(&event_mutex);
 		return 0;
 	}
 
@@ -1094,7 +1145,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		goto out;
 	}
 
-	err = replace_preds(NULL, call, ps, filter_string);
+	err = replace_preds(NULL, call, ps, filter_string, false);
 	if (err)
 		append_filter_err(ps, call->filter);
 
@@ -1103,7 +1154,7 @@ out:
 	postfix_clear(ps);
 	kfree(ps);
 out_unlock:
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 
 	return err;
 }
@@ -1115,12 +1166,16 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
 	struct filter_parse_state *ps;
 
-	mutex_lock(&filter_mutex);
+	mutex_lock(&event_mutex);
+
+	err = init_subsystem_preds(system);
+	if (err)
+		goto out_unlock;
 
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_free_subsystem_preds(system);
+		filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
 		remove_filter_string(system->filter);
-		mutex_unlock(&filter_mutex);
+		mutex_unlock(&event_mutex);
 		return 0;
 	}
 
@@ -1129,7 +1184,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 	if (!ps)
 		goto out_unlock;
 
-	filter_free_subsystem_preds(system);
 	replace_filter_string(system->filter, filter_string);
 
 	parse_init(ps, filter_ops, filter_string);
@@ -1139,16 +1193,30 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 		goto out;
 	}
 
-	err = replace_preds(system, NULL, ps, filter_string);
-	if (err)
+	filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
+
+	/* try to see the filter can be applied to which events */
+	err = replace_preds(system, NULL, ps, filter_string, true);
+	if (err) {
 		append_filter_err(ps, system->filter);
+		goto out;
+	}
+
+	filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+
+	/* really apply the filter to the events */
+	err = replace_preds(system, NULL, ps, filter_string, false);
+	if (err) {
+		append_filter_err(ps, system->filter);
+		filter_free_subsystem_preds(system, 2);
+	}
 
 out:
 	filter_opstack_clear(ps);
 	postfix_clear(ps);
 	kfree(ps);
 out_unlock:
-	mutex_unlock(&filter_mutex);
+	mutex_unlock(&event_mutex);
 
 	return err;
 }
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d06cf898dc8..df1bf6e48bb 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -60,7 +60,8 @@ extern void __bad_type_size(void);
 #undef TRACE_EVENT_FORMAT
 #define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
 static int								\
-ftrace_format_##call(struct trace_seq *s)				\
+ftrace_format_##call(struct ftrace_event_call *unused,			\
+		      struct trace_seq *s)				\
 {									\
 	struct args field;						\
 	int ret;							\
@@ -76,7 +77,8 @@ ftrace_format_##call(struct trace_seq *s)				\
 #define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
 				    tpfmt)				\
 static int								\
-ftrace_format_##call(struct trace_seq *s)				\
+ftrace_format_##call(struct ftrace_event_call *unused,			\
+		      struct trace_seq *s)				\
 {									\
 	struct args field;						\
 	int ret;							\
@@ -117,7 +119,7 @@ ftrace_format_##call(struct trace_seq *s)				\
 
 #undef TRACE_EVENT_FORMAT
 #define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
-int ftrace_define_fields_##call(void);					\
+int ftrace_define_fields_##call(struct ftrace_event_call *event_call);	\
 static int ftrace_raw_init_event_##call(void);				\
 									\
 struct ftrace_event_call __used						\
@@ -133,7 +135,6 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 static int ftrace_raw_init_event_##call(void)				\
 {									\
 	INIT_LIST_HEAD(&event_##call.fields);				\
-	init_preds(&event_##call);					\
 	return 0;							\
 }									\
 
@@ -156,7 +157,8 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #define TRACE_FIELD(type, item, assign)					\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed_type(type));	\
+				 sizeof(field.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
 	if (ret)							\
 		return ret;
 
@@ -164,7 +166,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #define TRACE_FIELD_SPECIAL(type, item, len, cmd)			\
 	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), 0);		\
+				 sizeof(field.item), 0, FILTER_OTHER);	\
 	if (ret)							\
 		return ret;
 
@@ -172,7 +174,8 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #define TRACE_FIELD_SIGN(type, item, assign, is_signed)			\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed);	\
+				 sizeof(field.item), is_signed,		\
+				 FILTER_OTHER);				\
 	if (ret)							\
 		return ret;
 
@@ -182,17 +185,14 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef TRACE_EVENT_FORMAT
 #define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
 int									\
-ftrace_define_fields_##call(void)					\
+ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
-	struct ftrace_event_call *event_call = &event_##call;		\
 	struct args field;						\
 	int ret;							\
 									\
-	__common_field(unsigned char, type, 0);				\
-	__common_field(unsigned char, flags, 0);			\
-	__common_field(unsigned char, preempt_count, 0);		\
-	__common_field(int, pid, 1);					\
-	__common_field(int, tgid, 1);					\
+	ret = trace_define_common_fields(event_call);			\
+	if (ret)							\
+		return ret;						\
 									\
 	tstruct;							\
 									\
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index c9a0b7df44f..5b01b94518f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -193,9 +193,11 @@ static void tracing_start_function_trace(void)
 static void tracing_stop_function_trace(void)
 {
 	ftrace_function_enabled = 0;
-	/* OK if they are not registered */
-	unregister_ftrace_function(&trace_stack_ops);
-	unregister_ftrace_function(&trace_ops);
+
+	if (func_flags.val & TRACE_FUNC_OPT_STACK)
+		unregister_ftrace_function(&trace_stack_ops);
+	else
+		unregister_ftrace_function(&trace_ops);
 }
 
 static int func_set_flag(u32 old_flags, u32 bit, int set)
@@ -286,11 +288,9 @@ static int
 ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
 			 struct ftrace_probe_ops *ops, void *data)
 {
-	char str[KSYM_SYMBOL_LEN];
 	long count = (long)data;
 
-	kallsyms_lookup(ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
+	seq_printf(m, "%pf:", (void *)ip);
 
 	if (ops == &traceon_probe_ops)
 		seq_printf(m, "traceon");
@@ -300,8 +300,7 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
 	if (count == -1)
 		seq_printf(m, ":unlimited\n");
 	else
-		seq_printf(m, ":count=%ld", count);
-	seq_putc(m, '\n');
+		seq_printf(m, ":count=%ld\n", count);
 
 	return 0;
 }
@@ -362,7 +361,7 @@ ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
  out_reg:
 	ret = register_ftrace_function_probe(glob, ops, count);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 static struct ftrace_func_command ftrace_traceon_cmd = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 8b592418d8b..b3749a2c313 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -52,12 +52,13 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
-/* pid on the last trace processed */
+static struct trace_array *graph_array;
 
 
 /* Add a function return address to the trace stack on thread info.*/
 int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+			 unsigned long frame_pointer)
 {
 	unsigned long long calltime;
 	int index;
@@ -85,6 +86,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
 	current->ret_stack[index].subtime = 0;
+	current->ret_stack[index].fp = frame_pointer;
 	*depth = index;
 
 	return 0;
@@ -92,7 +94,8 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 
 /* Retrieve a function return address to the trace stack on thread info.*/
 static void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
+ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
+			unsigned long frame_pointer)
 {
 	int index;
 
@@ -106,6 +109,31 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 		return;
 	}
 
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+	/*
+	 * The arch may choose to record the frame pointer used
+	 * and check it here to make sure that it is what we expect it
+	 * to be. If gcc does not set the place holder of the return
+	 * address in the frame pointer, and does a copy instead, then
+	 * the function graph trace will fail. This test detects this
+	 * case.
+	 *
+	 * Currently, x86_32 with optimize for size (-Os) makes the latest
+	 * gcc do the above.
+	 */
+	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
+		ftrace_graph_stop();
+		WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
+		     "  from func %pF return to %lx\n",
+		     current->ret_stack[index].fp,
+		     frame_pointer,
+		     (void *)current->ret_stack[index].func,
+		     current->ret_stack[index].ret);
+		*ret = (unsigned long)panic;
+		return;
+	}
+#endif
+
 	*ret = current->ret_stack[index].ret;
 	trace->func = current->ret_stack[index].func;
 	trace->calltime = current->ret_stack[index].calltime;
@@ -117,12 +145,12 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-unsigned long ftrace_return_to_handler(void)
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 {
 	struct ftrace_graph_ret trace;
 	unsigned long ret;
 
-	ftrace_pop_return_trace(&trace, &ret);
+	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
 	barrier();
@@ -138,10 +166,123 @@ unsigned long ftrace_return_to_handler(void)
 	return ret;
 }
 
+static int __trace_graph_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_entry;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ftrace_graph_ent_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return 0;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return 0;
+	entry	= ring_buffer_event_data(event);
+	entry->graph_ent			= *trace;
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
+
+	return 1;
+}
+
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int ret;
+	int cpu;
+	int pc;
+
+	if (unlikely(!tr))
+		return 0;
+
+	if (!ftrace_trace_task(current))
+		return 0;
+
+	if (!ftrace_graph_addr(trace->func))
+		return 0;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else {
+		ret = 0;
+	}
+	/* Only do the atomic if it is not already set */
+	if (!test_tsk_trace_graph(current))
+		set_tsk_trace_graph(current);
+
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+				struct ftrace_graph_ret *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_exit;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ftrace_graph_ret_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->ret				= *trace;
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_graph_return(tr, trace, flags, pc);
+	}
+	if (!trace->depth)
+		clear_tsk_trace_graph(current);
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
-	int ret = register_ftrace_graph(&trace_graph_return,
-					&trace_graph_entry);
+	int ret;
+
+	graph_array = tr;
+	ret = register_ftrace_graph(&trace_graph_return,
+				    &trace_graph_entry);
 	if (ret)
 		return ret;
 	tracing_start_cmdline_record();
@@ -149,49 +290,30 @@ static int graph_trace_init(struct trace_array *tr)
 	return 0;
 }
 
+void set_graph_array(struct trace_array *tr)
+{
+	graph_array = tr;
+}
+
 static void graph_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_cmdline_record();
 	unregister_ftrace_graph();
 }
 
-static inline int log10_cpu(int nb)
-{
-	if (nb / 100)
-		return 3;
-	if (nb / 10)
-		return 2;
-	return 1;
-}
+static int max_bytes_for_cpu;
 
 static enum print_line_t
 print_graph_cpu(struct trace_seq *s, int cpu)
 {
-	int i;
 	int ret;
-	int log10_this = log10_cpu(cpu);
-	int log10_all = log10_cpu(cpumask_weight(cpu_online_mask));
-
 
 	/*
 	 * Start with a space character - to make it stand out
 	 * to the right a bit when trace output is pasted into
 	 * email:
 	 */
-	ret = trace_seq_printf(s, " ");
-
-	/*
-	 * Tricky - we space the CPU field according to the max
-	 * number of online CPUs. On a 2-cpu system it would take
-	 * a maximum of 1 digit - on a 128 cpu system it would
-	 * take up to 3 digits:
-	 */
-	for (i = 0; i < log10_all - log10_this; i++) {
-		ret = trace_seq_printf(s, " ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
-	ret = trace_seq_printf(s, "%d) ", cpu);
+	ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -537,11 +659,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = seq_print_ip_sym(s, call->func, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_printf(s, "();\n");
+	ret = trace_seq_printf(s, "%pf();\n", (void *)call->func);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -584,11 +702,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = seq_print_ip_sym(s, call->func, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_printf(s, "() {\n");
+	ret = trace_seq_printf(s, "%pf() {\n", (void *)call->func);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -815,9 +929,16 @@ print_graph_function(struct trace_iterator *iter)
 
 	switch (entry->type) {
 	case TRACE_GRAPH_ENT: {
-		struct ftrace_graph_ent_entry *field;
+		/*
+		 * print_graph_entry() may consume the current event,
+		 * thus @field may become invalid, so we need to save it.
+		 * sizeof(struct ftrace_graph_ent_entry) is very small,
+		 * it can be safely saved at the stack.
+		 */
+		struct ftrace_graph_ent_entry *field, saved;
 		trace_assign_type(field, entry);
-		return print_graph_entry(field, s, iter);
+		saved = *field;
+		return print_graph_entry(&saved, s, iter);
 	}
 	case TRACE_GRAPH_RET: {
 		struct ftrace_graph_ret_entry *field;
@@ -899,6 +1020,8 @@ static struct tracer graph_trace __read_mostly = {
 
 static __init int init_graph_trace(void)
 {
+	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
+
 	return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b923d13e2fa..5555b75a0d1 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -178,7 +178,6 @@ out_unlock:
 out:
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
-	tracing_reset(tr, cpu);
 	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
@@ -208,7 +207,6 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
 	data->critical_start = parent_ip ? : ip;
-	tracing_reset(tr, cpu);
 
 	local_save_flags(flags);
 
@@ -379,6 +377,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
+	tracing_reset_online_cpus(tr);
 	start_irqsoff_tracer(tr);
 }
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index d53b45ed080..c4c9bbda53d 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -307,11 +307,12 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -319,7 +320,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -333,11 +334,12 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -345,7 +347,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 7938f3ae93e..e0c2545622e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -27,8 +27,7 @@ void trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
 
-	s->buffer[len] = 0;
-	seq_puts(m, s->buffer);
+	seq_write(m, s->buffer, len);
 
 	trace_seq_init(s);
 }
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 8a30d9874cd..fe1a00f1445 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -38,6 +38,7 @@ static void probe_power_end(struct power_trace *it)
 {
 	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
 	struct trace_array *tr = power_trace;
@@ -45,18 +46,20 @@ static void probe_power_end(struct power_trace *it)
 	if (!trace_power_enabled)
 		return;
 
+	buffer = tr->buffer;
+
 	preempt_disable();
 	it->end = ktime_get();
 	data = tr->data[smp_processor_id()];
 
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
+	event = trace_buffer_lock_reserve(buffer, TRACE_POWER,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -66,6 +69,7 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 {
 	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
 	struct trace_array *tr = power_trace;
@@ -73,6 +77,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 	if (!trace_power_enabled)
 		return;
 
+	buffer = tr->buffer;
+
 	memset(it, 0, sizeof(struct power_trace));
 	it->state = level;
 	it->type = type;
@@ -81,14 +87,14 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 	it->end = it->stamp;
 	data = tr->data[smp_processor_id()];
 
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
+	event = trace_buffer_lock_reserve(buffer, TRACE_POWER,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -144,14 +150,12 @@ static void power_trace_reset(struct trace_array *tr)
 
 static int power_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	power_trace = tr;
 
 	trace_power_enabled = 1;
 	tracing_power_register();
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 	return 0;
 }
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 9bece9687b6..687699d365a 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -155,25 +155,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_start(struct seq_file *m, loff_t *pos)
 {
-	const char **fmt = m->private;
-	const char **next = fmt;
-
-	(*pos)++;
+	const char **fmt = __start___trace_bprintk_fmt + *pos;
 
 	if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
 		return NULL;
-
-	next = fmt;
-	m->private = ++next;
-
 	return fmt;
 }
 
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
 {
-	return t_next(m, NULL, pos);
+	(*pos)++;
+	return t_start(m, pos);
 }
 
 static int t_show(struct seq_file *m, void *v)
@@ -182,7 +176,7 @@ static int t_show(struct seq_file *m, void *v)
 	const char *str = *fmt;
 	int i;
 
-	seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
+	seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
 
 	/*
 	 * Tabs and new lines need to be converted.
@@ -224,15 +218,7 @@ static const struct seq_operations show_format_seq_ops = {
 static int
 ftrace_formats_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
-	ret = seq_open(file, &show_format_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = __start___trace_bprintk_fmt;
-	}
-	return ret;
+	return seq_open(file, &show_format_seq_ops);
 }
 
 static const struct file_operations ftrace_formats_fops = {
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a98106dd979..5fca0f51fde 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -20,6 +20,35 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 static int			sched_stopped;
 
+
+void
+tracing_sched_switch_trace(struct trace_array *tr,
+			   struct task_struct *prev,
+			   struct task_struct *next,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_context_switch;
+	struct ring_buffer *buffer = tr->buffer;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= prev->pid;
+	entry->prev_prio		= prev->prio;
+	entry->prev_state		= prev->state;
+	entry->next_pid			= next->pid;
+	entry->next_prio		= next->prio;
+	entry->next_state		= next->state;
+	entry->next_cpu	= task_cpu(next);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, flags, pc);
+}
+
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 			struct task_struct *next)
@@ -49,6 +78,36 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	local_irq_restore(flags);
 }
 
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_wakeup;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+	struct ring_buffer *buffer = tr->buffer;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= curr->pid;
+	entry->prev_prio		= curr->prio;
+	entry->prev_state		= curr->state;
+	entry->next_pid			= wakee->pid;
+	entry->next_prio		= wakee->prio;
+	entry->next_state		= wakee->state;
+	entry->next_cpu			= task_cpu(wakee);
+
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr->buffer, flags, 6, pc);
+	ftrace_trace_userstack(tr->buffer, flags, pc);
+}
+
 static void
 probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 {
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index eacb2722517..ad69f105a7c 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -186,11 +186,6 @@ out:
 
 static void __wakeup_reset(struct trace_array *tr)
 {
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		tracing_reset(tr, cpu);
-
 	wakeup_cpu = -1;
 	wakeup_prio = -1;
 
@@ -204,6 +199,8 @@ static void wakeup_reset(struct trace_array *tr)
 {
 	unsigned long flags;
 
+	tracing_reset_online_cpus(tr);
+
 	local_irq_save(flags);
 	__raw_spin_lock(&wakeup_lock);
 	__wakeup_reset(tr);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 71f2edb0fd8..7179c12e4f0 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -289,6 +289,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * to detect and recover from possible hangs
 	 */
 	tracing_reset_online_cpus(tr);
+	set_graph_array(tr);
 	ret = register_ftrace_graph(&trace_graph_return,
 				    &trace_graph_entry_watchdog);
 	if (ret) {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2d7aebd71db..0f6facb050a 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -186,43 +186,33 @@ static const struct file_operations stack_max_size_fops = {
 };
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+__next(struct seq_file *m, loff_t *pos)
 {
-	long i;
-
-	(*pos)++;
-
-	if (v == SEQ_START_TOKEN)
-		i = 0;
-	else {
-		i = *(long *)v;
-		i++;
-	}
+	long n = *pos - 1;
 
-	if (i >= max_stack_trace.nr_entries ||
-	    stack_dump_trace[i] == ULONG_MAX)
+	if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
 		return NULL;
 
-	m->private = (void *)i;
-
+	m->private = (void *)n;
 	return &m->private;
 }
 
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	void *t = SEQ_START_TOKEN;
-	loff_t l = 0;
+	(*pos)++;
+	return __next(m, pos);
+}
 
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
 	local_irq_disable();
 	__raw_spin_lock(&max_stack_lock);
 
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
 
-	for (; t && l < *pos; t = t_next(m, t, &l))
-		;
-
-	return t;
+	return __next(m, pos);
 }
 
 static void t_stop(struct seq_file *m, void *p)
@@ -234,15 +224,8 @@ static void t_stop(struct seq_file *m, void *p)
 static int trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
-#ifdef CONFIG_KALLSYMS
-	char str[KSYM_SYMBOL_LEN];
 
-	sprint_symbol(str, addr);
-
-	return seq_printf(m, "%s\n", str);
-#else
-	return seq_printf(m, "%p\n", (void*)addr);
-#endif
+	return seq_printf(m, "%pF\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)
@@ -301,17 +284,14 @@ static const struct seq_operations stack_trace_seq_ops = {
 
 static int stack_trace_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
-	ret = seq_open(file, &stack_trace_seq_ops);
-
-	return ret;
+	return seq_open(file, &stack_trace_seq_ops);
 }
 
 static const struct file_operations stack_trace_fops = {
 	.open		= stack_trace_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
+	.release	= seq_release,
 };
 
 int
@@ -326,10 +306,10 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 	ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
 
 	if (ret || !write ||
-	    (last_stack_tracer_enabled == stack_tracer_enabled))
+	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
 		goto out;
 
-	last_stack_tracer_enabled = stack_tracer_enabled;
+	last_stack_tracer_enabled = !!stack_tracer_enabled;
 
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index c00643733f4..a4bb239eb98 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -49,7 +49,8 @@ static struct dentry		*stat_dir;
  * but it will at least advance closer to the next one
  * to be released.
  */
-static struct rb_node *release_next(struct rb_node *node)
+static struct rb_node *release_next(struct tracer_stat *ts,
+				    struct rb_node *node)
 {
 	struct stat_node *snode;
 	struct rb_node *parent = rb_parent(node);
@@ -67,26 +68,35 @@ static struct rb_node *release_next(struct rb_node *node)
 			parent->rb_right = NULL;
 
 		snode = container_of(node, struct stat_node, node);
+		if (ts->stat_release)
+			ts->stat_release(snode->stat);
 		kfree(snode);
 
 		return parent;
 	}
 }
 
-static void reset_stat_session(struct stat_session *session)
+static void __reset_stat_session(struct stat_session *session)
 {
 	struct rb_node *node = session->stat_root.rb_node;
 
 	while (node)
-		node = release_next(node);
+		node = release_next(session->ts, node);
 
 	session->stat_root = RB_ROOT;
 }
 
+static void reset_stat_session(struct stat_session *session)
+{
+	mutex_lock(&session->stat_mutex);
+	__reset_stat_session(session);
+	mutex_unlock(&session->stat_mutex);
+}
+
 static void destroy_session(struct stat_session *session)
 {
 	debugfs_remove(session->file);
-	reset_stat_session(session);
+	__reset_stat_session(session);
 	mutex_destroy(&session->stat_mutex);
 	kfree(session);
 }
@@ -150,7 +160,7 @@ static int stat_seq_init(struct stat_session *session)
 	int i;
 
 	mutex_lock(&session->stat_mutex);
-	reset_stat_session(session);
+	__reset_stat_session(session);
 
 	if (!ts->stat_cmp)
 		ts->stat_cmp = dummy_cmp;
@@ -183,7 +193,7 @@ exit:
 	return ret;
 
 exit_free_rbtree:
-	reset_stat_session(session);
+	__reset_stat_session(session);
 	mutex_unlock(&session->stat_mutex);
 	return ret;
 }
@@ -193,23 +203,23 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct stat_session *session = s->private;
 	struct rb_node *node;
+	int n = *pos;
 	int i;
 
 	/* Prevent from tracer switch or rbtree modification */
 	mutex_lock(&session->stat_mutex);
 
 	/* If we are in the beginning of the file, print the headers */
-	if (!*pos && session->ts->stat_headers) {
-		(*pos)++;
-		return SEQ_START_TOKEN;
+	if (session->ts->stat_headers) {
+		if (n == 0)
+			return SEQ_START_TOKEN;
+		n--;
 	}
 
 	node = rb_first(&session->stat_root);
-	for (i = 0; node && i < *pos; i++)
+	for (i = 0; node && i < n; i++)
 		node = rb_next(node);
 
-	(*pos)++;
-
 	return node;
 }
 
@@ -254,16 +264,21 @@ static const struct seq_operations trace_stat_seq_ops = {
 static int tracing_stat_open(struct inode *inode, struct file *file)
 {
 	int ret;
-
+	struct seq_file *m;
 	struct stat_session *session = inode->i_private;
 
+	ret = stat_seq_init(session);
+	if (ret)
+		return ret;
+
 	ret = seq_open(file, &trace_stat_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = session;
-		ret = stat_seq_init(session);
+	if (ret) {
+		reset_stat_session(session);
+		return ret;
 	}
 
+	m = file->private_data;
+	m->private = session;
 	return ret;
 }
 
@@ -274,11 +289,9 @@ static int tracing_stat_release(struct inode *i, struct file *f)
 {
 	struct stat_session *session = i->i_private;
 
-	mutex_lock(&session->stat_mutex);
 	reset_stat_session(session);
-	mutex_unlock(&session->stat_mutex);
 
-	return 0;
+	return seq_release(i, f);
 }
 
 static const struct file_operations tracing_stat_fops = {
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index f3546a2cd82..8f03914b9a6 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -18,6 +18,8 @@ struct tracer_stat {
 	int			(*stat_cmp)(void *p1, void *p2);
 	/* Print a stat entry */
 	int			(*stat_show)(struct seq_file *s, void *p);
+	/* Release an entry */
+	void			(*stat_release)(void *stat);
 	/* Print the headers of your stat entries */
 	int			(*stat_headers)(struct seq_file *s);
 };
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e579645ac8..8712ce3c6a0 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,30 +1,18 @@
 #include <trace/syscall.h>
+#include <trace/events/syscalls.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/perf_counter.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
 #include "trace.h"
 
-/* Keep a counter of the syscall tracing users */
-static int refcount;
-
-/* Prevent from races on thread flags toggling */
 static DEFINE_MUTEX(syscall_trace_lock);
-
-/* Option to display the parameters types */
-enum {
-	TRACE_SYSCALLS_OPT_TYPES = 0x1,
-};
-
-static struct tracer_opt syscalls_opts[] = {
-	{ TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) },
-	{ }
-};
-
-static struct tracer_flags syscalls_flags = {
-	.val = 0, /* By default: no parameters types */
-	.opts = syscalls_opts
-};
+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);
 
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
@@ -35,35 +23,46 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
 	struct syscall_metadata *entry;
 	int i, ret, syscall;
 
-	trace_assign_type(trace, ent);
-
+	trace = (typeof(trace))ent;
 	syscall = trace->nr;
-
 	entry = syscall_nr_to_meta(syscall);
+
 	if (!entry)
 		goto end;
 
+	if (entry->enter_id != ent->type) {
+		WARN_ON_ONCE(1);
+		goto end;
+	}
+
 	ret = trace_seq_printf(s, "%s(", entry->name);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	for (i = 0; i < entry->nb_args; i++) {
 		/* parameter types */
-		if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) {
+		if (trace_flags & TRACE_ITER_VERBOSE) {
 			ret = trace_seq_printf(s, "%s ", entry->types[i]);
 			if (!ret)
 				return TRACE_TYPE_PARTIAL_LINE;
 		}
 		/* parameter values */
-		ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i],
+		ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i],
 				       trace->args[i],
-				       i == entry->nb_args - 1 ? ")" : ",");
+				       i == entry->nb_args - 1 ? "" : ", ");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
+	ret = trace_seq_putc(s, ')');
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
 end:
-	trace_seq_printf(s, "\n");
+	ret =  trace_seq_putc(s, '\n');
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -77,16 +76,20 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
 	struct syscall_metadata *entry;
 	int ret;
 
-	trace_assign_type(trace, ent);
-
+	trace = (typeof(trace))ent;
 	syscall = trace->nr;
-
 	entry = syscall_nr_to_meta(syscall);
+
 	if (!entry) {
 		trace_seq_printf(s, "\n");
 		return TRACE_TYPE_HANDLED;
 	}
 
+	if (entry->exit_id != ent->type) {
+		WARN_ON_ONCE(1);
+		return TRACE_TYPE_UNHANDLED;
+	}
+
 	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
 				trace->ret);
 	if (!ret)
@@ -95,62 +98,140 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
 	return TRACE_TYPE_HANDLED;
 }
 
-void start_ftrace_syscalls(void)
+extern char *__bad_type_size(void);
+
+#define SYSCALL_FIELD(type, name)					\
+	sizeof(type) != sizeof(trace.name) ?				\
+		__bad_type_size() :					\
+		#type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+
+int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	int i;
+	int nr;
+	int ret;
+	struct syscall_metadata *entry;
+	struct syscall_trace_enter trace;
+	int offset = offsetof(struct syscall_trace_enter, args);
 
-	mutex_lock(&syscall_trace_lock);
+	nr = syscall_name_to_nr(call->data);
+	entry = syscall_nr_to_meta(nr);
 
-	/* Don't enable the flag on the tasks twice */
-	if (++refcount != 1)
-		goto unlock;
+	if (!entry)
+		return 0;
 
-	arch_init_ftrace_syscalls();
-	read_lock_irqsave(&tasklist_lock, flags);
+	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+			       SYSCALL_FIELD(int, nr));
+	if (!ret)
+		return 0;
 
-	do_each_thread(g, t) {
-		set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-	} while_each_thread(g, t);
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
+				        entry->args[i]);
+		if (!ret)
+			return 0;
+		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
+				       sizeof(unsigned long));
+		if (!ret)
+			return 0;
+		offset += sizeof(unsigned long);
+	}
 
-	read_unlock_irqrestore(&tasklist_lock, flags);
+	trace_seq_puts(s, "\nprint fmt: \"");
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
+				        sizeof(unsigned long),
+					i == entry->nb_args - 1 ? "" : ", ");
+		if (!ret)
+			return 0;
+	}
+	trace_seq_putc(s, '"');
 
-unlock:
-	mutex_unlock(&syscall_trace_lock);
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
+				       entry->args[i]);
+		if (!ret)
+			return 0;
+	}
+
+	return trace_seq_putc(s, '\n');
 }
 
-void stop_ftrace_syscalls(void)
+int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	int ret;
+	struct syscall_trace_exit trace;
 
-	mutex_lock(&syscall_trace_lock);
+	ret = trace_seq_printf(s,
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
+			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+			       SYSCALL_FIELD(int, nr),
+			       SYSCALL_FIELD(unsigned long, ret));
+	if (!ret)
+		return 0;
 
-	/* There are perhaps still some users */
-	if (--refcount)
-		goto unlock;
+	return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+}
 
-	read_lock_irqsave(&tasklist_lock, flags);
+int syscall_enter_define_fields(struct ftrace_event_call *call)
+{
+	struct syscall_trace_enter trace;
+	struct syscall_metadata *meta;
+	int ret;
+	int nr;
+	int i;
+	int offset = offsetof(typeof(trace), args);
+
+	nr = syscall_name_to_nr(call->data);
+	meta = syscall_nr_to_meta(nr);
+
+	if (!meta)
+		return 0;
+
+	ret = trace_define_common_fields(call);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < meta->nb_args; i++) {
+		ret = trace_define_field(call, meta->types[i],
+					 meta->args[i], offset,
+					 sizeof(unsigned long), 0,
+					 FILTER_OTHER);
+		offset += sizeof(unsigned long);
+	}
 
-	do_each_thread(g, t) {
-		clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-	} while_each_thread(g, t);
+	return ret;
+}
 
-	read_unlock_irqrestore(&tasklist_lock, flags);
+int syscall_exit_define_fields(struct ftrace_event_call *call)
+{
+	struct syscall_trace_exit trace;
+	int ret;
 
-unlock:
-	mutex_unlock(&syscall_trace_lock);
+	ret = trace_define_common_fields(call);
+	if (ret)
+		return ret;
+
+	ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0,
+				 FILTER_OTHER);
+
+	return ret;
 }
 
-void ftrace_syscall_enter(struct pt_regs *regs)
+void ftrace_syscall_enter(struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int size;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
+	if (!test_bit(syscall_nr, enabled_enter_syscalls))
+		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
@@ -158,8 +239,8 @@ void ftrace_syscall_enter(struct pt_regs *regs)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size,
-							0, 0);
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
+						  size, 0, 0);
 	if (!event)
 		return;
 
@@ -167,24 +248,30 @@ void ftrace_syscall_enter(struct pt_regs *regs)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	trace_current_buffer_unlock_commit(event, 0, 0);
-	trace_wake_up();
+	if (!filter_current_check_discard(buffer, sys_data->enter_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(struct pt_regs *regs)
+void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 {
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
+	if (syscall_nr < 0)
+		return;
+	if (!test_bit(syscall_nr, enabled_exit_syscalls))
+		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
 		return;
 
-	event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT,
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
 				sizeof(*entry), 0, 0);
 	if (!event)
 		return;
@@ -193,58 +280,244 @@ void ftrace_syscall_exit(struct pt_regs *regs)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	trace_current_buffer_unlock_commit(event, 0, 0);
-	trace_wake_up();
+	if (!filter_current_check_discard(buffer, sys_data->exit_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-static int init_syscall_tracer(struct trace_array *tr)
+int reg_event_syscall_enter(void *ptr)
 {
-	start_ftrace_syscalls();
+	int ret = 0;
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_refcount_enter)
+		ret = register_trace_sys_enter(ftrace_syscall_enter);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_enter_syscalls);
+		sys_refcount_enter++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+void unreg_event_syscall_enter(void *ptr)
+{
+	int num;
+	char *name;
 
-	return 0;
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (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);
+	mutex_unlock(&syscall_trace_lock);
 }
 
-static void reset_syscall_tracer(struct trace_array *tr)
+int reg_event_syscall_exit(void *ptr)
 {
-	stop_ftrace_syscalls();
-	tracing_reset_online_cpus(tr);
+	int ret = 0;
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_refcount_exit)
+		ret = register_trace_sys_exit(ftrace_syscall_exit);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall exit trace point");
+	} else {
+		set_bit(num, enabled_exit_syscalls);
+		sys_refcount_exit++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
 }
 
-static struct trace_event syscall_enter_event = {
-	.type	 	= TRACE_SYSCALL_ENTER,
-	.trace		= print_syscall_enter,
-};
+void unreg_event_syscall_exit(void *ptr)
+{
+	int num;
+	char *name;
+
+	name = (char *)ptr;
+	num = syscall_name_to_nr(name);
+	if (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);
+	mutex_unlock(&syscall_trace_lock);
+}
 
-static struct trace_event syscall_exit_event = {
-	.type	 	= TRACE_SYSCALL_EXIT,
-	.trace		= print_syscall_exit,
+struct trace_event event_syscall_enter = {
+	.trace			= print_syscall_enter,
 };
 
-static struct tracer syscall_tracer __read_mostly = {
-	.name	     	= "syscall",
-	.init		= init_syscall_tracer,
-	.reset		= reset_syscall_tracer,
-	.flags		= &syscalls_flags,
+struct trace_event event_syscall_exit = {
+	.trace			= print_syscall_exit,
 };
 
-__init int register_ftrace_syscalls(void)
+#ifdef CONFIG_EVENT_PROFILE
+
+static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
+static int sys_prof_refcount_enter;
+static int sys_prof_refcount_exit;
+
+static void prof_syscall_enter(struct pt_regs *regs, long id)
 {
-	int ret;
+	struct syscall_trace_enter *rec;
+	struct syscall_metadata *sys_data;
+	int syscall_nr;
+	int size;
 
-	ret = register_ftrace_event(&syscall_enter_event);
-	if (!ret) {
-		printk(KERN_WARNING "event %d failed to register\n",
-		       syscall_enter_event.type);
-		WARN_ON_ONCE(1);
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	/* get the size after alignment with the u32 buffer size field */
+	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+	size = ALIGN(size + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+
+	do {
+		char raw_data[size];
+
+		/* zero the dead bytes from align to not leak stack to user */
+		*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+		rec = (struct syscall_trace_enter *) raw_data;
+		tracing_generic_entry_update(&rec->ent, 0, 0);
+		rec->ent.type = sys_data->enter_id;
+		rec->nr = syscall_nr;
+		syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+				       (unsigned long *)&rec->args);
+		perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size);
+	} while(0);
+}
+
+int reg_prof_syscall_enter(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_enter)
+		ret = register_trace_sys_enter(prof_syscall_enter);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_enter_syscalls);
+		sys_prof_refcount_enter++;
 	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
 
-	ret = register_ftrace_event(&syscall_exit_event);
-	if (!ret) {
-		printk(KERN_WARNING "event %d failed to register\n",
-		       syscall_exit_event.type);
-		WARN_ON_ONCE(1);
+void unreg_prof_syscall_enter(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_enter--;
+	clear_bit(num, enabled_prof_enter_syscalls);
+	if (!sys_prof_refcount_enter)
+		unregister_trace_sys_enter(prof_syscall_enter);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static void prof_syscall_exit(struct pt_regs *regs, long ret)
+{
+	struct syscall_metadata *sys_data;
+	struct syscall_trace_exit rec;
+	int syscall_nr;
+
+	syscall_nr = syscall_get_nr(current, regs);
+	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	tracing_generic_entry_update(&rec.ent, 0, 0);
+	rec.ent.type = sys_data->exit_id;
+	rec.nr = syscall_nr;
+	rec.ret = syscall_get_return_value(current, regs);
+
+	perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec));
+}
+
+int reg_prof_syscall_exit(char *name)
+{
+	int ret = 0;
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return -ENOSYS;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_prof_refcount_exit)
+		ret = register_trace_sys_exit(prof_syscall_exit);
+	if (ret) {
+		pr_info("event trace: Could not activate"
+				"syscall entry trace point");
+	} else {
+		set_bit(num, enabled_prof_exit_syscalls);
+		sys_prof_refcount_exit++;
 	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
 
-	return register_tracer(&syscall_tracer);
+void unreg_prof_syscall_exit(char *name)
+{
+	int num;
+
+	num = syscall_name_to_nr(name);
+	if (num < 0 || num >= NR_syscalls)
+		return;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_prof_refcount_exit--;
+	clear_bit(num, enabled_prof_exit_syscalls);
+	if (!sys_prof_refcount_exit)
+		unregister_trace_sys_exit(prof_syscall_exit);
+	mutex_unlock(&syscall_trace_lock);
 }
-device_initcall(register_ftrace_syscalls);
+
+#endif
+
+
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 97fcea4acce..40cafb07dff 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
 #include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/kref.h>
 #include "trace_stat.h"
 #include "trace.h"
 
@@ -16,6 +17,7 @@
 /* A cpu workqueue thread */
 struct cpu_workqueue_stats {
 	struct list_head            list;
+	struct kref                 kref;
 	int		            cpu;
 	pid_t			    pid;
 /* Can be inserted from interrupt or user context, need to be atomic */
@@ -39,6 +41,11 @@ struct workqueue_global_stats {
 static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
 #define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
 
+static void cpu_workqueue_stat_free(struct kref *kref)
+{
+	kfree(container_of(kref, struct cpu_workqueue_stats, kref));
+}
+
 /* Insertion of a work */
 static void
 probe_workqueue_insertion(struct task_struct *wq_thread,
@@ -96,8 +103,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 		return;
 	}
 	INIT_LIST_HEAD(&cws->list);
+	kref_init(&cws->kref);
 	cws->cpu = cpu;
-
 	cws->pid = wq_thread->pid;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
@@ -118,7 +125,7 @@ static void probe_workqueue_destruction(struct task_struct *wq_thread)
 							list) {
 		if (node->pid == wq_thread->pid) {
 			list_del(&node->list);
-			kfree(node);
+			kref_put(&node->kref, cpu_workqueue_stat_free);
 			goto found;
 		}
 	}
@@ -137,9 +144,11 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 
-	if (!list_empty(&workqueue_cpu_stat(cpu)->list))
+	if (!list_empty(&workqueue_cpu_stat(cpu)->list)) {
 		ret = list_entry(workqueue_cpu_stat(cpu)->list.next,
 				 struct cpu_workqueue_stats, list);
+		kref_get(&ret->kref);
+	}
 
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
@@ -162,9 +171,9 @@ static void *workqueue_stat_start(struct tracer_stat *trace)
 static void *workqueue_stat_next(void *prev, int idx)
 {
 	struct cpu_workqueue_stats *prev_cws = prev;
+	struct cpu_workqueue_stats *ret;
 	int cpu = prev_cws->cpu;
 	unsigned long flags;
-	void *ret = NULL;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 	if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) {
@@ -175,11 +184,14 @@ static void *workqueue_stat_next(void *prev, int idx)
 				return NULL;
 		} while (!(ret = workqueue_stat_start_cpu(cpu)));
 		return ret;
+	} else {
+		ret = list_entry(prev_cws->list.next,
+				 struct cpu_workqueue_stats, list);
+		kref_get(&ret->kref);
 	}
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
-	return list_entry(prev_cws->list.next, struct cpu_workqueue_stats,
-			  list);
+	return ret;
 }
 
 static int workqueue_stat_show(struct seq_file *s, void *p)
@@ -203,6 +215,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 	return 0;
 }
 
+static void workqueue_stat_release(void *stat)
+{
+	struct cpu_workqueue_stats *node = stat;
+
+	kref_put(&node->kref, cpu_workqueue_stat_free);
+}
+
 static int workqueue_stat_headers(struct seq_file *s)
 {
 	seq_printf(s, "# CPU  INSERTED  EXECUTED   NAME\n");
@@ -215,6 +234,7 @@ struct tracer_stat workqueue_stats __read_mostly = {
 	.stat_start = workqueue_stat_start,
 	.stat_next = workqueue_stat_next,
 	.stat_show = workqueue_stat_show,
+	.stat_release = workqueue_stat_release,
 	.stat_headers = workqueue_stat_headers
 };
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 1ef5d3a601c..9489a0a9b1b 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -24,6 +24,7 @@
 #include <linux/tracepoint.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 extern struct tracepoint __start___tracepoints[];
 extern struct tracepoint __stop___tracepoints[];
@@ -242,6 +243,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 {
 	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
 
+	if (elem->regfunc && !elem->state && active)
+		elem->regfunc();
+	else if (elem->unregfunc && elem->state && !active)
+		elem->unregfunc();
+
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
 	 * probe callbacks array is consistent before setting a pointer to it.
@@ -261,6 +267,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
  */
 static void disable_tracepoint(struct tracepoint *elem)
 {
+	if (elem->unregfunc && elem->state)
+		elem->unregfunc();
+
 	elem->state = 0;
 	rcu_assign_pointer(elem->funcs, NULL);
 }
@@ -554,9 +563,6 @@ int tracepoint_module_notify(struct notifier_block *self,
 
 	switch (val) {
 	case MODULE_STATE_COMING:
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
-		break;
 	case MODULE_STATE_GOING:
 		tracepoint_update_probe_range(mod->tracepoints,
 			mod->tracepoints + mod->num_tracepoints);
@@ -577,3 +583,41 @@ static int init_tracepoints(void)
 __initcall(init_tracepoints);
 
 #endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+static int sys_tracepoint_refcount;
+
+void syscall_regfunc(void)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+
+	if (!sys_tracepoint_refcount) {
+		read_lock_irqsave(&tasklist_lock, flags);
+		do_each_thread(g, t) {
+			/* Skip kernel threads. */
+			if (t->mm)
+				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		} while_each_thread(g, t);
+		read_unlock_irqrestore(&tasklist_lock, flags);
+	}
+	sys_tracepoint_refcount++;
+}
+
+void syscall_unregfunc(void)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+
+	sys_tracepoint_refcount--;
+	if (!sys_tracepoint_refcount) {
+		read_lock_irqsave(&tasklist_lock, flags);
+		do_each_thread(g, t) {
+			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		} while_each_thread(g, t);
+		read_unlock_irqrestore(&tasklist_lock, flags);
+	}
+}
+#endif
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 815237a55af..8a82b4b8ea5 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -15,6 +15,16 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
+static struct uts_namespace *create_uts_ns(void)
+{
+	struct uts_namespace *uts_ns;
+
+	uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+	if (uts_ns)
+		kref_init(&uts_ns->kref);
+	return uts_ns;
+}
+
 /*
  * Clone a new ns copying an original utsname, setting refcount to 1
  * @old_ns: namespace to clone
@@ -24,14 +34,13 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
 {
 	struct uts_namespace *ns;
 
-	ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+	ns = create_uts_ns();
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
 	up_read(&uts_sem);
-	kref_init(&ns->kref);
 	return ns;
 }
 
diff --git a/kernel/wait.c b/kernel/wait.c
index ea7c3b4275c..c4bd3d825f3 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -10,13 +10,14 @@
 #include <linux/wait.h>
 #include <linux/hash.h>
 
-void init_waitqueue_head(wait_queue_head_t *q)
+void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *key)
 {
 	spin_lock_init(&q->lock);
+	lockdep_set_class(&q->lock, key);
 	INIT_LIST_HEAD(&q->task_list);
 }
 
-EXPORT_SYMBOL(init_waitqueue_head);
+EXPORT_SYMBOL(__init_waitqueue_head);
 
 void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
 {