Merge branch 'master' into for-next

98 files changed, 8298 insertions, 2990 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index bbaf7d5..bc010ee 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,9 +137,10 @@ $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
 ###############################################################################
 ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
 X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
-X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
-X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509
+X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
 				$(or $(realpath $(CERT)),$(CERT))))
+X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw))
 
 ifeq ($(X509_CERTIFICATES),)
 $(warning *** No X.509 certificates found ***)
@@ -164,9 +165,9 @@ $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
 targets += $(obj)/.x509.list
 $(obj)/.x509.list:
 	@echo $(X509_CERTIFICATES) >$@
+endif
 
 clean-files := x509_certificate_list .x509.list
-endif
 
 ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
diff --git a/kernel/audit.c b/kernel/audit.c
index 906ae5a0..34c5a23 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -41,6 +41,8 @@
  * Example user-space utilities: http://people.redhat.com/sgrubb/audit/
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <asm/types.h>
 #include <linux/atomic.h>
@@ -63,6 +65,7 @@
 #include <linux/freezer.h>
 #include <linux/tty.h>
 #include <linux/pid_namespace.h>
+#include <net/netns/generic.h>
 
 #include "audit.h"
 
@@ -76,16 +79,16 @@ static int	audit_initialized;
 #define AUDIT_OFF	0
 #define AUDIT_ON	1
 #define AUDIT_LOCKED	2
-int		audit_enabled;
-int		audit_ever_enabled;
+u32		audit_enabled;
+u32		audit_ever_enabled;
 
 EXPORT_SYMBOL_GPL(audit_enabled);
 
 /* Default state when kernel boots without any parameters. */
-static int	audit_default;
+static u32	audit_default;
 
 /* If auditing cannot proceed, audit_failure selects what happens. */
-static int	audit_failure = AUDIT_FAIL_PRINTK;
+static u32	audit_failure = AUDIT_FAIL_PRINTK;
 
 /*
  * If audit records are to be written to the netlink socket, audit_pid
@@ -93,17 +96,19 @@ static int	audit_failure = AUDIT_FAIL_PRINTK;
  * the portid to use to send netlink messages to that process.
  */
 int		audit_pid;
-static int	audit_nlk_portid;
+static __u32	audit_nlk_portid;
 
 /* If audit_rate_limit is non-zero, limit the rate of sending audit records
  * to that number per second.  This prevents DoS attacks, but results in
  * audit records being dropped. */
-static int	audit_rate_limit;
+static u32	audit_rate_limit;
 
-/* Number of outstanding audit_buffers allowed. */
-static int	audit_backlog_limit = 64;
-static int	audit_backlog_wait_time = 60 * HZ;
-static int	audit_backlog_wait_overflow = 0;
+/* Number of outstanding audit_buffers allowed.
+ * When set to zero, this means unlimited. */
+static u32	audit_backlog_limit = 64;
+#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static u32	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+static u32	audit_backlog_wait_overflow = 0;
 
 /* The identity of the user shutting down the audit system. */
 kuid_t		audit_sig_uid = INVALID_UID;
@@ -121,6 +126,7 @@ static atomic_t    audit_lost = ATOMIC_INIT(0);
 
 /* The netlink socket. */
 static struct sock *audit_sock;
+int audit_net_id;
 
 /* Hash for inode-based rules */
 struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -175,27 +181,27 @@ struct audit_buffer {
 };
 
 struct audit_reply {
-	int pid;
+	__u32 portid;
+	pid_t pid;
 	struct sk_buff *skb;
 };
 
-static void audit_set_pid(struct audit_buffer *ab, pid_t pid)
+static void audit_set_portid(struct audit_buffer *ab, __u32 portid)
 {
 	if (ab) {
 		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
-		nlh->nlmsg_pid = pid;
+		nlh->nlmsg_pid = portid;
 	}
 }
 
 void audit_panic(const char *message)
 {
-	switch (audit_failure)
-	{
+	switch (audit_failure) {
 	case AUDIT_FAIL_SILENT:
 		break;
 	case AUDIT_FAIL_PRINTK:
 		if (printk_ratelimit())
-			printk(KERN_ERR "audit: %s\n", message);
+			pr_err("%s\n", message);
 		break;
 	case AUDIT_FAIL_PANIC:
 		/* test audit_pid since printk is always losey, why bother? */
@@ -266,9 +272,7 @@ void audit_log_lost(const char *message)
 
 	if (print) {
 		if (printk_ratelimit())
-			printk(KERN_WARNING
-				"audit: audit_lost=%d audit_rate_limit=%d "
-				"audit_backlog_limit=%d\n",
+			pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n",
 				atomic_read(&audit_lost),
 				audit_rate_limit,
 				audit_backlog_limit);
@@ -276,7 +280,7 @@ void audit_log_lost(const char *message)
 	}
 }
 
-static int audit_log_config_change(char *function_name, int new, int old,
+static int audit_log_config_change(char *function_name, u32 new, u32 old,
 				   int allow_changes)
 {
 	struct audit_buffer *ab;
@@ -285,7 +289,7 @@ static int audit_log_config_change(char *function_name, int new, int old,
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
 	if (unlikely(!ab))
 		return rc;
-	audit_log_format(ab, "%s=%d old=%d", function_name, new, old);
+	audit_log_format(ab, "%s=%u old=%u", function_name, new, old);
 	audit_log_session_info(ab);
 	rc = audit_log_task_context(ab);
 	if (rc)
@@ -295,9 +299,10 @@ static int audit_log_config_change(char *function_name, int new, int old,
 	return rc;
 }
 
-static int audit_do_config_change(char *function_name, int *to_change, int new)
+static int audit_do_config_change(char *function_name, u32 *to_change, u32 new)
 {
-	int allow_changes, rc = 0, old = *to_change;
+	int allow_changes, rc = 0;
+	u32 old = *to_change;
 
 	/* check if we are locked */
 	if (audit_enabled == AUDIT_LOCKED)
@@ -320,17 +325,23 @@ static int audit_do_config_change(char *function_name, int *to_change, int new)
 	return rc;
 }
 
-static int audit_set_rate_limit(int limit)
+static int audit_set_rate_limit(u32 limit)
 {
 	return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit);
 }
 
-static int audit_set_backlog_limit(int limit)
+static int audit_set_backlog_limit(u32 limit)
 {
 	return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit);
 }
 
-static int audit_set_enabled(int state)
+static int audit_set_backlog_wait_time(u32 timeout)
+{
+	return audit_do_config_change("audit_backlog_wait_time",
+				      &audit_backlog_wait_time, timeout);
+}
+
+static int audit_set_enabled(u32 state)
 {
 	int rc;
 	if (state < AUDIT_OFF || state > AUDIT_LOCKED)
@@ -343,7 +354,7 @@ static int audit_set_enabled(int state)
 	return rc;
 }
 
-static int audit_set_failure(int state)
+static int audit_set_failure(u32 state)
 {
 	if (state != AUDIT_FAIL_SILENT
 	    && state != AUDIT_FAIL_PRINTK
@@ -365,7 +376,8 @@ static int audit_set_failure(int state)
 static void audit_hold_skb(struct sk_buff *skb)
 {
 	if (audit_default &&
-	    skb_queue_len(&audit_skb_hold_queue) < audit_backlog_limit)
+	    (!audit_backlog_limit ||
+	     skb_queue_len(&audit_skb_hold_queue) < audit_backlog_limit))
 		skb_queue_tail(&audit_skb_hold_queue, skb);
 	else
 		kfree_skb(skb);
@@ -382,7 +394,7 @@ static void audit_printk_skb(struct sk_buff *skb)
 
 	if (nlh->nlmsg_type != AUDIT_EOE) {
 		if (printk_ratelimit())
-			printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, data);
+			pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
 		else
 			audit_log_lost("printk limit exceeded\n");
 	}
@@ -398,9 +410,12 @@ static void kauditd_send_skb(struct sk_buff *skb)
 	err = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0);
 	if (err < 0) {
 		BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */
-		printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
-		audit_log_lost("auditd disappeared\n");
-		audit_pid = 0;
+		if (audit_pid) {
+			pr_err("*NO* daemon at audit_pid=%d\n", audit_pid);
+			audit_log_lost("auditd disappeared\n");
+			audit_pid = 0;
+			audit_sock = NULL;
+		}
 		/* we might get lucky and get this in the next auditd */
 		audit_hold_skb(skb);
 	} else
@@ -457,8 +472,10 @@ static int kauditd_thread(void *dummy)
 		flush_hold_queue();
 
 		skb = skb_dequeue(&audit_skb_queue);
-		wake_up(&audit_backlog_wait);
+
 		if (skb) {
+			if (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit)
+				wake_up(&audit_backlog_wait);
 			if (audit_pid)
 				kauditd_send_skb(skb);
 			else
@@ -482,22 +499,23 @@ static int kauditd_thread(void *dummy)
 int audit_send_list(void *_dest)
 {
 	struct audit_netlink_list *dest = _dest;
-	int pid = dest->pid;
 	struct sk_buff *skb;
+	struct net *net = get_net_ns_by_pid(dest->pid);
+	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	/* wait for parent to finish and send an ACK */
 	mutex_lock(&audit_cmd_mutex);
 	mutex_unlock(&audit_cmd_mutex);
 
 	while ((skb = __skb_dequeue(&dest->q)) != NULL)
-		netlink_unicast(audit_sock, skb, pid, 0);
+		netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
 
 	kfree(dest);
 
 	return 0;
 }
 
-struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
+struct sk_buff *audit_make_reply(__u32 portid, int seq, int type, int done,
 				 int multi, const void *payload, int size)
 {
 	struct sk_buff	*skb;
@@ -510,7 +528,7 @@ struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
 	if (!skb)
 		return NULL;
 
-	nlh	= nlmsg_put(skb, pid, seq, t, size, flags);
+	nlh	= nlmsg_put(skb, portid, seq, t, size, flags);
 	if (!nlh)
 		goto out_kfree_skb;
 	data = nlmsg_data(nlh);
@@ -525,19 +543,21 @@ out_kfree_skb:
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
+	struct net *net = get_net_ns_by_pid(reply->pid);
+	struct audit_net *aunet = net_generic(net, audit_net_id);
 
 	mutex_lock(&audit_cmd_mutex);
 	mutex_unlock(&audit_cmd_mutex);
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(audit_sock, reply->skb, reply->pid, 0);
+	netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
 	kfree(reply);
 	return 0;
 }
 /**
  * audit_send_reply - send an audit reply message via netlink
- * @pid: process id to send reply to
+ * @portid: netlink port to which to send reply
  * @seq: sequence number
  * @type: audit message type
  * @done: done (last) flag
@@ -545,11 +565,11 @@ static int audit_send_reply_thread(void *arg)
  * @payload: payload data
  * @size: payload size
  *
- * Allocates an skb, builds the netlink message, and sends it to the pid.
+ * Allocates an skb, builds the netlink message, and sends it to the port id.
  * No failure notifications.
  */
-static void audit_send_reply(int pid, int seq, int type, int done, int multi,
-			     const void *payload, int size)
+static void audit_send_reply(__u32 portid, int seq, int type, int done,
+			     int multi, const void *payload, int size)
 {
 	struct sk_buff *skb;
 	struct task_struct *tsk;
@@ -559,11 +579,12 @@ static void audit_send_reply(int pid, int seq, int type, int done, int multi,
 	if (!reply)
 		return;
 
-	skb = audit_make_reply(pid, seq, type, done, multi, payload, size);
+	skb = audit_make_reply(portid, seq, type, done, multi, payload, size);
 	if (!skb)
 		goto out;
 
-	reply->pid = pid;
+	reply->portid = portid;
+	reply->pid = task_pid_vnr(current);
 	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -663,8 +684,12 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
 {
 	struct audit_buffer *ab;
 
+	if (audit_enabled == AUDIT_OFF)
+		return;
+
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
-	audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d",
+	audit_log_task_info(ab, current);
+	audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
 			 audit_feature_names[which], !!old_feature, !!new_feature,
 			 !!old_lock, !!new_lock, res);
 	audit_log_end(ab);
@@ -694,7 +719,7 @@ static int audit_set_feature(struct sk_buff *skb)
 		old_lock = af.lock & feature;
 
 		/* are we changing a locked feature? */
-		if ((af.lock & feature) && (new_feature != old_feature)) {
+		if (old_lock && (new_feature != old_feature)) {
 			audit_log_feature_change(i, old_feature, new_feature,
 						 old_lock, new_lock, 0);
 			return -EPERM;
@@ -732,7 +757,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	u32			seq;
 	void			*data;
-	struct audit_status	*status_get, status_set;
 	int			err;
 	struct audit_buffer	*ab;
 	u16			msg_type = nlh->nlmsg_type;
@@ -758,48 +782,70 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	data = nlmsg_data(nlh);
 
 	switch (msg_type) {
-	case AUDIT_GET:
-		memset(&status_set, 0, sizeof(status_set));
-		status_set.enabled	 = audit_enabled;
-		status_set.failure	 = audit_failure;
-		status_set.pid		 = audit_pid;
-		status_set.rate_limit	 = audit_rate_limit;
-		status_set.backlog_limit = audit_backlog_limit;
-		status_set.lost		 = atomic_read(&audit_lost);
-		status_set.backlog	 = skb_queue_len(&audit_skb_queue);
+	case AUDIT_GET: {
+		struct audit_status	s;
+		memset(&s, 0, sizeof(s));
+		s.enabled		= audit_enabled;
+		s.failure		= audit_failure;
+		s.pid			= audit_pid;
+		s.rate_limit		= audit_rate_limit;
+		s.backlog_limit		= audit_backlog_limit;
+		s.lost			= atomic_read(&audit_lost);
+		s.backlog		= skb_queue_len(&audit_skb_queue);
+		s.version		= AUDIT_VERSION_LATEST;
+		s.backlog_wait_time	= audit_backlog_wait_time;
 		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-				 &status_set, sizeof(status_set));
+				 &s, sizeof(s));
 		break;
-	case AUDIT_SET:
-		if (nlmsg_len(nlh) < sizeof(struct audit_status))
-			return -EINVAL;
-		status_get   = (struct audit_status *)data;
-		if (status_get->mask & AUDIT_STATUS_ENABLED) {
-			err = audit_set_enabled(status_get->enabled);
+	}
+	case AUDIT_SET: {
+		struct audit_status	s;
+		memset(&s, 0, sizeof(s));
+		/* guard against past and future API changes */
+		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+		if (s.mask & AUDIT_STATUS_ENABLED) {
+			err = audit_set_enabled(s.enabled);
 			if (err < 0)
 				return err;
 		}
-		if (status_get->mask & AUDIT_STATUS_FAILURE) {
-			err = audit_set_failure(status_get->failure);
+		if (s.mask & AUDIT_STATUS_FAILURE) {
+			err = audit_set_failure(s.failure);
 			if (err < 0)
 				return err;
 		}
-		if (status_get->mask & AUDIT_STATUS_PID) {
-			int new_pid = status_get->pid;
+		if (s.mask & AUDIT_STATUS_PID) {
+			int new_pid = s.pid;
 
+			if ((!new_pid) && (task_tgid_vnr(current) != audit_pid))
+				return -EACCES;
 			if (audit_enabled != AUDIT_OFF)
 				audit_log_config_change("audit_pid", new_pid, audit_pid, 1);
 			audit_pid = new_pid;
 			audit_nlk_portid = NETLINK_CB(skb).portid;
+			audit_sock = skb->sk;
 		}
-		if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) {
-			err = audit_set_rate_limit(status_get->rate_limit);
+		if (s.mask & AUDIT_STATUS_RATE_LIMIT) {
+			err = audit_set_rate_limit(s.rate_limit);
+			if (err < 0)
+				return err;
+		}
+		if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) {
+			err = audit_set_backlog_limit(s.backlog_limit);
+			if (err < 0)
+				return err;
+		}
+		if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) {
+			if (sizeof(s) > (size_t)nlh->nlmsg_len)
+				return -EINVAL;
+			if (s.backlog_wait_time < 0 ||
+			    s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
+				return -EINVAL;
+			err = audit_set_backlog_wait_time(s.backlog_wait_time);
 			if (err < 0)
 				return err;
 		}
-		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
-			err = audit_set_backlog_limit(status_get->backlog_limit);
 		break;
+	}
 	case AUDIT_GET_FEATURE:
 		err = audit_get_feature(skb);
 		if (err)
@@ -817,13 +863,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			return 0;
 
 		err = audit_filter_user(msg_type);
-		if (err == 1) {
+		if (err == 1) { /* match or error */
 			err = 0;
 			if (msg_type == AUDIT_USER_TTY) {
 				err = tty_audit_push_current();
 				if (err)
 					break;
 			}
+			mutex_unlock(&audit_cmd_mutex);
 			audit_log_common_recv_msg(&ab, msg_type);
 			if (msg_type != AUDIT_USER_TTY)
 				audit_log_format(ab, " msg='%.*s'",
@@ -839,8 +886,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					size--;
 				audit_log_n_untrustedstring(ab, data, size);
 			}
-			audit_set_pid(ab, NETLINK_CB(skb).portid);
+			audit_set_portid(ab, NETLINK_CB(skb).portid);
 			audit_log_end(ab);
+			mutex_lock(&audit_cmd_mutex);
 		}
 		break;
 	case AUDIT_ADD_RULE:
@@ -853,11 +901,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			audit_log_end(ab);
 			return -EPERM;
 		}
-		/* fallthrough */
-	case AUDIT_LIST_RULES:
-		err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid,
+		err = audit_rule_change(msg_type, NETLINK_CB(skb).portid,
 					   seq, data, nlmsg_len(nlh));
 		break;
+	case AUDIT_LIST_RULES:
+		err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+		break;
 	case AUDIT_TRIM:
 		audit_trim_trees();
 		audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE);
@@ -939,20 +988,33 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		break;
 	}
 	case AUDIT_TTY_SET: {
-		struct audit_tty_status s;
+		struct audit_tty_status s, old;
 		struct task_struct *tsk = current;
+		struct audit_buffer	*ab;
 
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
 		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+		/* check if new data is valid */
 		if ((s.enabled != 0 && s.enabled != 1) ||
 		    (s.log_passwd != 0 && s.log_passwd != 1))
-			return -EINVAL;
+			err = -EINVAL;
 
 		spin_lock(&tsk->sighand->siglock);
-		tsk->signal->audit_tty = s.enabled;
-		tsk->signal->audit_tty_log_passwd = s.log_passwd;
+		old.enabled = tsk->signal->audit_tty;
+		old.log_passwd = tsk->signal->audit_tty_log_passwd;
+		if (!err) {
+			tsk->signal->audit_tty = s.enabled;
+			tsk->signal->audit_tty_log_passwd = s.log_passwd;
+		}
 		spin_unlock(&tsk->sighand->siglock);
+
+		audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE);
+		audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d"
+				 " old-log_passwd=%d new-log_passwd=%d res=%d",
+				 old.enabled, s.enabled, old.log_passwd,
+				 s.log_passwd, !err);
+		audit_log_end(ab);
 		break;
 	}
 	default:
@@ -998,24 +1060,55 @@ static void audit_receive(struct sk_buff  *skb)
 	mutex_unlock(&audit_cmd_mutex);
 }
 
-/* Initialize audit support at boot time. */
-static int __init audit_init(void)
+static int __net_init audit_net_init(struct net *net)
 {
-	int i;
 	struct netlink_kernel_cfg cfg = {
 		.input	= audit_receive,
 	};
 
+	struct audit_net *aunet = net_generic(net, audit_net_id);
+
+	aunet->nlsk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
+	if (aunet->nlsk == NULL) {
+		audit_panic("cannot initialize netlink socket in namespace");
+		return -ENOMEM;
+	}
+	aunet->nlsk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	return 0;
+}
+
+static void __net_exit audit_net_exit(struct net *net)
+{
+	struct audit_net *aunet = net_generic(net, audit_net_id);
+	struct sock *sock = aunet->nlsk;
+	if (sock == audit_sock) {
+		audit_pid = 0;
+		audit_sock = NULL;
+	}
+
+	rcu_assign_pointer(aunet->nlsk, NULL);
+	synchronize_net();
+	netlink_kernel_release(sock);
+}
+
+static struct pernet_operations audit_net_ops __net_initdata = {
+	.init = audit_net_init,
+	.exit = audit_net_exit,
+	.id = &audit_net_id,
+	.size = sizeof(struct audit_net),
+};
+
+/* Initialize audit support at boot time. */
+static int __init audit_init(void)
+{
+	int i;
+
 	if (audit_initialized == AUDIT_DISABLED)
 		return 0;
 
-	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
-	       audit_default ? "enabled" : "disabled");
-	audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, &cfg);
-	if (!audit_sock)
-		audit_panic("cannot initialize netlink socket");
-	else
-		audit_sock->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	pr_info("initializing netlink subsys (%s)\n",
+		audit_default ? "enabled" : "disabled");
+	register_pernet_subsys(&audit_net_ops);
 
 	skb_queue_head_init(&audit_skb_queue);
 	skb_queue_head_init(&audit_skb_hold_queue);
@@ -1039,22 +1132,32 @@ static int __init audit_enable(char *str)
 	if (!audit_default)
 		audit_initialized = AUDIT_DISABLED;
 
-	printk(KERN_INFO "audit: %s", audit_default ? "enabled" : "disabled");
+	pr_info("%s\n", audit_default ?
+		"enabled (after initialization)" : "disabled (until reboot)");
 
-	if (audit_initialized == AUDIT_INITIALIZED) {
-		audit_enabled = audit_default;
-		audit_ever_enabled |= !!audit_default;
-	} else if (audit_initialized == AUDIT_UNINITIALIZED) {
-		printk(" (after initialization)");
-	} else {
-		printk(" (until reboot)");
+	return 1;
+}
+__setup("audit=", audit_enable);
+
+/* Process kernel command-line parameter at boot time.
+ * audit_backlog_limit=<n> */
+static int __init audit_backlog_limit_set(char *str)
+{
+	u32 audit_backlog_limit_arg;
+
+	pr_info("audit_backlog_limit: ");
+	if (kstrtouint(str, 0, &audit_backlog_limit_arg)) {
+		pr_cont("using default of %u, unable to parse %s\n",
+			audit_backlog_limit, str);
+		return 1;
 	}
-	printk("\n");
+
+	audit_backlog_limit = audit_backlog_limit_arg;
+	pr_cont("%d\n", audit_backlog_limit);
 
 	return 1;
 }
-
-__setup("audit=", audit_enable);
+__setup("audit_backlog_limit=", audit_backlog_limit_set);
 
 static void audit_buffer_free(struct audit_buffer *ab)
 {
@@ -1165,18 +1268,20 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 /*
  * Wait for auditd to drain the queue a little
  */
-static void wait_for_auditd(unsigned long sleep_time)
+static long wait_for_auditd(long sleep_time)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	set_current_state(TASK_UNINTERRUPTIBLE);
-	add_wait_queue(&audit_backlog_wait, &wait);
+	add_wait_queue_exclusive(&audit_backlog_wait, &wait);
 
 	if (audit_backlog_limit &&
 	    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
-		schedule_timeout(sleep_time);
+		sleep_time = schedule_timeout(sleep_time);
 
 	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&audit_backlog_wait, &wait);
+
+	return sleep_time;
 }
 
 /**
@@ -1200,7 +1305,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	struct audit_buffer	*ab	= NULL;
 	struct timespec		t;
 	unsigned int		uninitialized_var(serial);
-	int reserve;
+	int reserve = 5; /* Allow atomic callers to go up to five
+			    entries over the normal backlog limit */
 	unsigned long timeout_start = jiffies;
 
 	if (audit_initialized != AUDIT_INITIALIZED)
@@ -1209,36 +1315,37 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	if (unlikely(audit_filter_type(type)))
 		return NULL;
 
-	if (gfp_mask & __GFP_WAIT)
-		reserve = 0;
-	else
-		reserve = 5; /* Allow atomic callers to go up to five
-				entries over the normal backlog limit */
+	if (gfp_mask & __GFP_WAIT) {
+		if (audit_pid && audit_pid == current->pid)
+			gfp_mask &= ~__GFP_WAIT;
+		else
+			reserve = 0;
+	}
 
 	while (audit_backlog_limit
 	       && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
 		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) {
-			unsigned long sleep_time;
+			long sleep_time;
 
-			sleep_time = timeout_start + audit_backlog_wait_time -
-					jiffies;
-			if ((long)sleep_time > 0) {
-				wait_for_auditd(sleep_time);
-				continue;
+			sleep_time = timeout_start + audit_backlog_wait_time - jiffies;
+			if (sleep_time > 0) {
+				sleep_time = wait_for_auditd(sleep_time);
+				if (sleep_time > 0)
+					continue;
 			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
-			printk(KERN_WARNING
-			       "audit: audit_backlog=%d > "
-			       "audit_backlog_limit=%d\n",
-			       skb_queue_len(&audit_skb_queue),
-			       audit_backlog_limit);
+			pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n",
+				skb_queue_len(&audit_skb_queue),
+				audit_backlog_limit);
 		audit_log_lost("backlog limit exceeded");
 		audit_backlog_wait_time = audit_backlog_wait_overflow;
 		wake_up(&audit_backlog_wait);
 		return NULL;
 	}
 
+	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+
 	ab = audit_buffer_alloc(ctx, gfp_mask, type);
 	if (!ab) {
 		audit_log_lost("out of memory in audit_log_start");
@@ -1356,7 +1463,6 @@ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf,
 	int i, avail, new_len;
 	unsigned char *ptr;
 	struct sk_buff *skb;
-	static const unsigned char *hex = "0123456789ABCDEF";
 
 	if (!ab)
 		return;
@@ -1374,10 +1480,8 @@ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf,
 	}
 
 	ptr = skb_tail_pointer(skb);
-	for (i=0; i<len; i++) {
-		*ptr++ = hex[(buf[i] & 0xF0)>>4]; /* Upper nibble */
-		*ptr++ = hex[buf[i] & 0x0F];	  /* Lower nibble */
-	}
+	for (i = 0; i < len; i++)
+		ptr = hex_byte_pack_upper(ptr, buf[i]);
 	*ptr = 0;
 	skb_put(skb, len << 1); /* new string is twice the old string */
 }
@@ -1491,7 +1595,7 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
 
 void audit_log_session_info(struct audit_buffer *ab)
 {
-	u32 sessionid = audit_get_sessionid(current);
+	unsigned int sessionid = audit_get_sessionid(current);
 	uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
 
 	audit_log_format(ab, " auid=%u ses=%u", auid, sessionid);
@@ -1716,7 +1820,7 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 	audit_log_format(ab,
 			 " ppid=%ld pid=%d auid=%u uid=%u gid=%u"
 			 " euid=%u suid=%u fsuid=%u"
-			 " egid=%u sgid=%u fsgid=%u ses=%u tty=%s",
+			 " egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
 			 sys_getppid(),
 			 tsk->pid,
 			 from_kuid(&init_user_ns, audit_get_loginuid(tsk)),
@@ -1728,7 +1832,7 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 			 from_kgid(&init_user_ns, cred->egid),
 			 from_kgid(&init_user_ns, cred->sgid),
 			 from_kgid(&init_user_ns, cred->fsgid),
-			 audit_get_sessionid(tsk), tty);
+			 tty, audit_get_sessionid(tsk));
 
 	get_task_comm(name, tsk);
 	audit_log_format(ab, " comm=");
@@ -1739,7 +1843,8 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 		if (mm->exe_file)
 			audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
 		up_read(&mm->mmap_sem);
-	}
+	} else
+		audit_log_format(ab, " exe=(null)");
 	audit_log_task_context(ab);
 }
 EXPORT_SYMBOL(audit_log_task_info);
diff --git a/kernel/audit.h b/kernel/audit.h
index b779642..57cc64d 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -209,7 +209,7 @@ struct audit_context {
 #endif
 };
 
-extern int audit_ever_enabled;
+extern u32 audit_ever_enabled;
 
 extern void audit_copy_inode(struct audit_names *name,
 			     const struct dentry *dentry,
@@ -240,18 +240,23 @@ extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right);
 extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right);
 extern int parent_len(const char *path);
 extern int audit_compare_dname_path(const char *dname, const char *path, int plen);
-extern struct sk_buff *	    audit_make_reply(int pid, int seq, int type,
-					     int done, int multi,
-					     const void *payload, int size);
+extern struct sk_buff *audit_make_reply(__u32 portid, int seq, int type,
+					int done, int multi,
+					const void *payload, int size);
 extern void		    audit_panic(const char *message);
 
 struct audit_netlink_list {
-	int pid;
+	__u32 portid;
+	pid_t pid;
 	struct sk_buff_head q;
 };
 
 int audit_send_list(void *);
 
+struct audit_net {
+	struct sock *nlsk;
+};
+
 extern int selinux_audit_rule_update(void);
 
 extern struct mutex audit_filter_mutex;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307d..67ccf0e 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -912,12 +912,13 @@ static void evict_chunk(struct audit_chunk *chunk)
 }
 
 static int audit_tree_handle_event(struct fsnotify_group *group,
+				   struct inode *to_tell,
 				   struct fsnotify_mark *inode_mark,
-				   struct fsnotify_mark *vfsmonut_mark,
-				   struct fsnotify_event *event)
+				   struct fsnotify_mark *vfsmount_mark,
+				   u32 mask, void *data, int data_type,
+				   const unsigned char *file_name)
 {
-	BUG();
-	return -EOPNOTSUPP;
+	return 0;
 }
 
 static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group)
@@ -933,19 +934,8 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
 	BUG_ON(atomic_read(&entry->refcnt) < 1);
 }
 
-static bool audit_tree_send_event(struct fsnotify_group *group, struct inode *inode,
-				  struct fsnotify_mark *inode_mark,
-				  struct fsnotify_mark *vfsmount_mark,
-				  __u32 mask, void *data, int data_type)
-{
-	return false;
-}
-
 static const struct fsnotify_ops audit_tree_ops = {
 	.handle_event = audit_tree_handle_event,
-	.should_send_event = audit_tree_send_event,
-	.free_group_priv = NULL,
-	.free_event_priv = NULL,
 	.freeing_mark = audit_tree_freeing_mark,
 };
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 22831c4..2596fac 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -465,35 +465,27 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 	}
 }
 
-static bool audit_watch_should_send_event(struct fsnotify_group *group, struct inode *inode,
-					  struct fsnotify_mark *inode_mark,
-					  struct fsnotify_mark *vfsmount_mark,
-					  __u32 mask, void *data, int data_type)
-{
-       return true;
-}
-
 /* Update watch data in audit rules based on fsnotify events. */
 static int audit_watch_handle_event(struct fsnotify_group *group,
+				    struct inode *to_tell,
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
-				    struct fsnotify_event *event)
+				    u32 mask, void *data, int data_type,
+				    const unsigned char *dname)
 {
 	struct inode *inode;
-	__u32 mask = event->mask;
-	const char *dname = event->file_name;
 	struct audit_parent *parent;
 
 	parent = container_of(inode_mark, struct audit_parent, mark);
 
 	BUG_ON(group != audit_watch_group);
 
-	switch (event->data_type) {
+	switch (data_type) {
 	case (FSNOTIFY_EVENT_PATH):
-		inode = event->path.dentry->d_inode;
+		inode = ((struct path *)data)->dentry->d_inode;
 		break;
 	case (FSNOTIFY_EVENT_INODE):
-		inode = event->inode;
+		inode = (struct inode *)data;
 		break;
 	default:
 		BUG();
@@ -512,11 +504,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 }
 
 static const struct fsnotify_ops audit_watch_fsnotify_ops = {
-	.should_send_event = 	audit_watch_should_send_event,
 	.handle_event = 	audit_watch_handle_event,
-	.free_group_priv = 	NULL,
-	.freeing_mark = 	NULL,
-	.free_event_priv = 	NULL,
 };
 
 static int __init audit_watch_init(void)
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 51f3fd4..14a78cc 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -972,7 +972,7 @@ out:
 }
 
 /* List rules using struct audit_rule_data. */
-static void audit_list_rules(int pid, int seq, struct sk_buff_head *q)
+static void audit_list_rules(__u32 portid, int seq, struct sk_buff_head *q)
 {
 	struct sk_buff *skb;
 	struct audit_krule *r;
@@ -987,14 +987,15 @@ static void audit_list_rules(int pid, int seq, struct sk_buff_head *q)
 			data = audit_krule_to_data(r);
 			if (unlikely(!data))
 				break;
-			skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1,
-					 data, sizeof(*data) + data->buflen);
+			skb = audit_make_reply(portid, seq, AUDIT_LIST_RULES,
+					       0, 1, data,
+					       sizeof(*data) + data->buflen);
 			if (skb)
 				skb_queue_tail(q, skb);
 			kfree(data);
 		}
 	}
-	skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 1, 1, NULL, 0);
+	skb = audit_make_reply(portid, seq, AUDIT_LIST_RULES, 1, 1, NULL, 0);
 	if (skb)
 		skb_queue_tail(q, skb);
 }
@@ -1004,7 +1005,7 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re
 {
 	struct audit_buffer *ab;
 	uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current));
-	u32 sessionid = audit_get_sessionid(current);
+	unsigned int sessionid = audit_get_sessionid(current);
 
 	if (!audit_enabled)
 		return;
@@ -1022,45 +1023,20 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re
 }
 
 /**
- * audit_receive_filter - apply all rules to the specified message type
+ * audit_rule_change - apply all rules to the specified message type
  * @type: audit message type
- * @pid: target pid for netlink audit messages
+ * @portid: target port id for netlink audit messages
  * @seq: netlink audit message sequence (serial) number
  * @data: payload data
  * @datasz: size of payload data
  */
-int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz)
+int audit_rule_change(int type, __u32 portid, int seq, void *data,
+			size_t datasz)
 {
-	struct task_struct *tsk;
-	struct audit_netlink_list *dest;
 	int err = 0;
 	struct audit_entry *entry;
 
 	switch (type) {
-	case AUDIT_LIST_RULES:
-		/* We can't just spew out the rules here because we might fill
-		 * the available socket buffer space and deadlock waiting for
-		 * auditctl to read from it... which isn't ever going to
-		 * happen if we're actually running in the context of auditctl
-		 * trying to _send_ the stuff */
-
-		dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
-		if (!dest)
-			return -ENOMEM;
-		dest->pid = pid;
-		skb_queue_head_init(&dest->q);
-
-		mutex_lock(&audit_filter_mutex);
-		audit_list_rules(pid, seq, &dest->q);
-		mutex_unlock(&audit_filter_mutex);
-
-		tsk = kthread_run(audit_send_list, dest, "audit_send_list");
-		if (IS_ERR(tsk)) {
-			skb_queue_purge(&dest->q);
-			kfree(dest);
-			err = PTR_ERR(tsk);
-		}
-		break;
 	case AUDIT_ADD_RULE:
 		entry = audit_data_to_entry(data, datasz);
 		if (IS_ERR(entry))
@@ -1087,6 +1063,44 @@ int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz)
 	return err;
 }
 
+/**
+ * audit_list_rules_send - list the audit rules
+ * @portid: target portid for netlink audit messages
+ * @seq: netlink audit message sequence (serial) number
+ */
+int audit_list_rules_send(__u32 portid, int seq)
+{
+	struct task_struct *tsk;
+	struct audit_netlink_list *dest;
+	int err = 0;
+
+	/* We can't just spew out the rules here because we might fill
+	 * the available socket buffer space and deadlock waiting for
+	 * auditctl to read from it... which isn't ever going to
+	 * happen if we're actually running in the context of auditctl
+	 * trying to _send_ the stuff */
+
+	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
+	if (!dest)
+		return -ENOMEM;
+	dest->portid = portid;
+	dest->pid = task_pid_vnr(current);
+	skb_queue_head_init(&dest->q);
+
+	mutex_lock(&audit_filter_mutex);
+	audit_list_rules(portid, seq, &dest->q);
+	mutex_unlock(&audit_filter_mutex);
+
+	tsk = kthread_run(audit_send_list, dest, "audit_send_list");
+	if (IS_ERR(tsk)) {
+		skb_queue_purge(&dest->q);
+		kfree(dest);
+		err = PTR_ERR(tsk);
+	}
+
+	return err;
+}
+
 int audit_comparator(u32 left, u32 op, u32 right)
 {
 	switch (op) {
@@ -1276,19 +1290,22 @@ int audit_filter_user(int type)
 {
 	enum audit_state state = AUDIT_DISABLED;
 	struct audit_entry *e;
-	int ret = 1;
+	int rc, ret;
+
+	ret = 1; /* Audit by default */
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
-		if (audit_filter_user_rules(&e->rule, type, &state)) {
-			if (state == AUDIT_DISABLED)
+		rc = audit_filter_user_rules(&e->rule, type, &state);
+		if (rc) {
+			if (rc > 0 && state == AUDIT_DISABLED)
 				ret = 0;
 			break;
 		}
 	}
 	rcu_read_unlock();
 
-	return ret; /* Audit by default */
+	return ret;
 }
 
 int audit_filter_type(int type)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 90594c9..7aef2f4 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1719,7 +1719,7 @@ void audit_putname(struct filename *name)
 	struct audit_context *context = current->audit_context;
 
 	BUG_ON(!context);
-	if (!context->in_syscall) {
+	if (!name->aname || !context->in_syscall) {
 #if AUDIT_DEBUG == 2
 		printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n",
 		       __FILE__, __LINE__, context->serial, name);
@@ -1969,18 +1969,24 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
 				   int rc)
 {
 	struct audit_buffer *ab;
-	uid_t uid, ologinuid, nloginuid;
+	uid_t uid, oldloginuid, loginuid;
+
+	if (!audit_enabled)
+		return;
 
 	uid = from_kuid(&init_user_ns, task_uid(current));
-	ologinuid = from_kuid(&init_user_ns, koldloginuid);
-	nloginuid = from_kuid(&init_user_ns, kloginuid),
+	oldloginuid = from_kuid(&init_user_ns, koldloginuid);
+	loginuid = from_kuid(&init_user_ns, kloginuid),
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
 	if (!ab)
 		return;
-	audit_log_format(ab, "pid=%d uid=%u old auid=%u new auid=%u old "
-			 "ses=%u new ses=%u res=%d", current->pid, uid, ologinuid,
-			 nloginuid, oldsessionid, sessionid, !rc);
+	audit_log_format(ab, "pid=%d uid=%u"
+			 " old-auid=%u new-auid=%u old-ses=%u new-ses=%u"
+			 " res=%d",
+			 current->pid, uid,
+			 oldloginuid, loginuid, oldsessionid, sessionid,
+			 !rc);
 	audit_log_end(ab);
 }
 
@@ -2008,7 +2014,7 @@ int audit_set_loginuid(kuid_t loginuid)
 
 	/* are we setting or clearing? */
 	if (uid_valid(loginuid))
-		sessionid = atomic_inc_return(&session_id);
+		sessionid = (unsigned int)atomic_inc_return(&session_id);
 
 	task->sessionid = sessionid;
 	task->loginuid = loginuid;
@@ -2321,18 +2327,16 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 
 /**
  * __audit_log_capset - store information about the arguments to the capset syscall
- * @pid: target pid of the capset call
  * @new: the new credentials
  * @old: the old (current) credentials
  *
  * Record the aguments userspace sent to sys_capset for later printing by the
  * audit system if applicable
  */
-void __audit_log_capset(pid_t pid,
-		       const struct cred *new, const struct cred *old)
+void __audit_log_capset(const struct cred *new, const struct cred *old)
 {
 	struct audit_context *context = current->audit_context;
-	context->capset.pid = pid;
+	context->capset.pid = task_pid_nr(current);
 	context->capset.cap.effective   = new->cap_effective;
 	context->capset.cap.inheritable = new->cap_effective;
 	context->capset.cap.permitted   = new->cap_permitted;
@@ -2352,6 +2356,7 @@ static void audit_log_task(struct audit_buffer *ab)
 	kuid_t auid, uid;
 	kgid_t gid;
 	unsigned int sessionid;
+	struct mm_struct *mm = current->mm;
 
 	auid = audit_get_loginuid(current);
 	sessionid = audit_get_sessionid(current);
@@ -2365,15 +2370,15 @@ static void audit_log_task(struct audit_buffer *ab)
 	audit_log_task_context(ab);
 	audit_log_format(ab, " pid=%d comm=", current->pid);
 	audit_log_untrustedstring(ab, current->comm);
+	if (mm) {
+		down_read(&mm->mmap_sem);
+		if (mm->exe_file)
+			audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
+		up_read(&mm->mmap_sem);
+	} else
+		audit_log_format(ab, " exe=(null)");
 }
 
-static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
-{
-	audit_log_task(ab);
-	audit_log_format(ab, " reason=");
-	audit_log_string(ab, reason);
-	audit_log_format(ab, " sig=%ld", signr);
-}
 /**
  * audit_core_dumps - record information about processes that end abnormally
  * @signr: signal value
@@ -2394,7 +2399,8 @@ void audit_core_dumps(long signr)
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
 	if (unlikely(!ab))
 		return;
-	audit_log_abend(ab, "memory violation", signr);
+	audit_log_task(ab);
+	audit_log_format(ab, " sig=%ld", signr);
 	audit_log_end(ab);
 }
 
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 5253204..9fd4246 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -22,6 +22,6 @@ void foo(void)
 #ifdef CONFIG_SMP
 	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
 #endif
-	DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int));
+	DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
 	/* End of constants */
 }
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e66bf9..34019c5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -277,7 +277,7 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 	if (ret < 0)
 		goto error;
 
-	audit_log_capset(pid, new, current_cred());
+	audit_log_capset(new, current_cred());
 
 	return commit_creds(new);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b729c2..e2f46ba 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -41,7 +41,6 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/backing-dev.h>
-#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/magic.h>
 #include <linux/spinlock.h>
@@ -56,15 +55,20 @@
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/eventfd.h>
-#include <linux/poll.h>
 #include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
-#include <linux/file.h>
 
 #include <linux/atomic.h>
 
 /*
+ * pidlists linger the following amount before being destroyed.  The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#define CGROUP_PIDLIST_DESTROY_DELAY	HZ
+
+/*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
@@ -89,6 +93,19 @@ static DEFINE_MUTEX(cgroup_mutex);
 
 static DEFINE_MUTEX(cgroup_root_mutex);
 
+#define cgroup_assert_mutex_or_rcu_locked()				\
+	rcu_lockdep_assert(rcu_read_lock_held() ||			\
+			   lockdep_is_held(&cgroup_mutex),		\
+			   "cgroup_mutex or RCU read lock required");
+
+#ifdef CONFIG_LOCKDEP
+#define cgroup_assert_mutex_or_root_locked()				\
+	WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) &&	\
+				     !lockdep_is_held(&cgroup_root_mutex)))
+#else
+#define cgroup_assert_mutex_or_root_locked()	do { } while (0)
+#endif
+
 /*
  * cgroup destruction makes heavy use of work items and there can be a lot
  * of concurrent destructions.  Use a separate workqueue so that cgroup
@@ -98,6 +115,12 @@ static DEFINE_MUTEX(cgroup_root_mutex);
 static struct workqueue_struct *cgroup_destroy_wq;
 
 /*
+ * pidlist destructions need to be flushed on cgroup destruction.  Use a
+ * separate workqueue as flush domain.
+ */
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
+/*
  * Generate an array of cgroup subsystem pointers. At boot time, this is
  * populated with the built in subsystems, and modular subsystems are
  * registered after that. The mutable section of this array is protected by
@@ -119,49 +142,6 @@ static struct cgroupfs_root cgroup_dummy_root;
 /* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
 static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
 
-/*
- * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
- */
-struct cfent {
-	struct list_head		node;
-	struct dentry			*dentry;
-	struct cftype			*type;
-	struct cgroup_subsys_state	*css;
-
-	/* file xattrs */
-	struct simple_xattrs		xattrs;
-};
-
-/*
- * cgroup_event represents events which userspace want to receive.
- */
-struct cgroup_event {
-	/*
-	 * css which the event belongs to.
-	 */
-	struct cgroup_subsys_state *css;
-	/*
-	 * Control file which the event associated.
-	 */
-	struct cftype *cft;
-	/*
-	 * eventfd to signal userspace about the event.
-	 */
-	struct eventfd_ctx *eventfd;
-	/*
-	 * Each of these stored in a list by the cgroup.
-	 */
-	struct list_head list;
-	/*
-	 * All fields below needed to unregister event when
-	 * userspace closes eventfd.
-	 */
-	poll_table pt;
-	wait_queue_head_t *wqh;
-	wait_queue_t wait;
-	struct work_struct remove;
-};
-
 /* The list of hierarchy roots */
 
 static LIST_HEAD(cgroup_roots);
@@ -200,6 +180,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
 static int cgroup_file_release(struct inode *inode, struct file *file);
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /**
  * cgroup_css - obtain a cgroup's css for the specified subsystem
@@ -262,16 +243,32 @@ static int notify_on_release(const struct cgroup *cgrp)
 }
 
 /**
+ * for_each_css - iterate all css's of a cgroup
+ * @css: the iteration cursor
+ * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
+ * @cgrp: the target cgroup to iterate css's of
+ *
+ * Should be called under cgroup_mutex.
+ */
+#define for_each_css(css, ssid, cgrp)					\
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
+		if (!((css) = rcu_dereference_check(			\
+				(cgrp)->subsys[(ssid)],			\
+				lockdep_is_held(&cgroup_mutex)))) { }	\
+		else
+
+/**
  * for_each_subsys - iterate all loaded cgroup subsystems
  * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
  *
- * Should be called under cgroup_mutex.
+ * Iterates through all loaded subsystems.  Should be called under
+ * cgroup_mutex or cgroup_root_mutex.
  */
-#define for_each_subsys(ss, i)						\
-	for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++)			\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       !((ss) = cgroup_subsys[i]); })) { }		\
+#define for_each_subsys(ss, ssid)					\
+	for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; });	\
+	     (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)			\
+		if (!((ss) = cgroup_subsys[(ssid)])) { }		\
 		else
 
 /**
@@ -286,10 +283,6 @@ static int notify_on_release(const struct cgroup *cgrp)
 	for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT &&		\
 	     (((ss) = cgroup_subsys[i]) || true); (i)++)
 
-/* iterate each subsystem attached to a hierarchy */
-#define for_each_root_subsys(root, ss)					\
-	list_for_each_entry((ss), &(root)->subsys_list, sibling)
-
 /* iterate across the active hierarchies */
 #define for_each_active_root(root)					\
 	list_for_each_entry((root), &cgroup_roots, root_list)
@@ -863,11 +856,7 @@ static void cgroup_free_fn(struct work_struct *work)
 	 */
 	deactivate_super(cgrp->root->sb);
 
-	/*
-	 * if we're getting rid of the cgroup, refcount should ensure
-	 * that there are no pidlists left.
-	 */
-	BUG_ON(!list_empty(&cgrp->pidlists));
+	cgroup_pidlist_destroy_all(cgrp);
 
 	simple_xattrs_free(&cgrp->xattrs);
 
@@ -890,6 +879,16 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		struct cgroup *cgrp = dentry->d_fsdata;
 
 		BUG_ON(!(cgroup_is_dead(cgrp)));
+
+		/*
+		 * XXX: cgrp->id is only used to look up css's.  As cgroup
+		 * and css's lifetimes will be decoupled, it should be made
+		 * per-subsystem and moved to css->id so that lookups are
+		 * successful until the target css is released.
+		 */
+		idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+		cgrp->id = -1;
+
 		call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
@@ -1040,7 +1039,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 					   cgroup_css(cgroup_dummy_top, ss));
 			cgroup_css(cgrp, ss)->cgroup = cgrp;
 
-			list_move(&ss->sibling, &root->subsys_list);
 			ss->root = root;
 			if (ss->bind)
 				ss->bind(cgroup_css(cgrp, ss));
@@ -1059,7 +1057,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			RCU_INIT_POINTER(cgrp->subsys[i], NULL);
 
 			cgroup_subsys[i]->root = &cgroup_dummy_root;
-			list_move(&ss->sibling, &cgroup_dummy_root.subsys_list);
 
 			/* subsystem is now free - drop reference on module */
 			module_put(ss->module);
@@ -1086,10 +1083,12 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 {
 	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
 	struct cgroup_subsys *ss;
+	int ssid;
 
 	mutex_lock(&cgroup_root_mutex);
-	for_each_root_subsys(root, ss)
-		seq_printf(seq, ",%s", ss->name);
+	for_each_subsys(ss, ssid)
+		if (root->subsys_mask & (1 << ssid))
+			seq_printf(seq, ",%s", ss->name);
 	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
 		seq_puts(seq, ",sane_behavior");
 	if (root->flags & CGRP_ROOT_NOPREFIX)
@@ -1352,8 +1351,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->dummy_css.cgroup = cgrp;
-	INIT_LIST_HEAD(&cgrp->event_list);
-	spin_lock_init(&cgrp->event_list_lock);
 	simple_xattrs_init(&cgrp->xattrs);
 }
 
@@ -1361,7 +1358,6 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 
-	INIT_LIST_HEAD(&root->subsys_list);
 	INIT_LIST_HEAD(&root->root_list);
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
@@ -1683,7 +1679,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	return ERR_PTR(ret);
 }
 
-static void cgroup_kill_sb(struct super_block *sb) {
+static void cgroup_kill_sb(struct super_block *sb)
+{
 	struct cgroupfs_root *root = sb->s_fs_info;
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgrp_cset_link *link, *tmp_link;
@@ -1966,8 +1963,8 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 			      bool threadgroup)
 {
 	int retval, i, group_size;
-	struct cgroup_subsys *ss, *failed_ss = NULL;
 	struct cgroupfs_root *root = cgrp->root;
+	struct cgroup_subsys_state *css, *failed_css = NULL;
 	/* threadgroup list cursor and array */
 	struct task_struct *leader = tsk;
 	struct task_and_cgroup *tc;
@@ -2040,13 +2037,11 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 	/*
 	 * step 1: check that we can legitimately attach to the cgroup.
 	 */
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
-		if (ss->can_attach) {
-			retval = ss->can_attach(css, &tset);
+	for_each_css(css, i, cgrp) {
+		if (css->ss->can_attach) {
+			retval = css->ss->can_attach(css, &tset);
 			if (retval) {
-				failed_ss = ss;
+				failed_css = css;
 				goto out_cancel_attach;
 			}
 		}
@@ -2082,12 +2077,9 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 	/*
 	 * step 4: do subsystem attach callbacks.
 	 */
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
-		if (ss->attach)
-			ss->attach(css, &tset);
-	}
+	for_each_css(css, i, cgrp)
+		if (css->ss->attach)
+			css->ss->attach(css, &tset);
 
 	/*
 	 * step 5: success! and cleanup
@@ -2104,13 +2096,11 @@ out_put_css_set_refs:
 	}
 out_cancel_attach:
 	if (retval) {
-		for_each_root_subsys(root, ss) {
-			struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
-			if (ss == failed_ss)
+		for_each_css(css, i, cgrp) {
+			if (css == failed_css)
 				break;
-			if (ss->cancel_attach)
-				ss->cancel_attach(css, &tset);
+			if (css->ss->cancel_attach)
+				css->ss->cancel_attach(css, &tset);
 		}
 	}
 out_free_group_list:
@@ -2138,7 +2128,7 @@ retry_find_task:
 		tsk = find_task_by_vpid(pid);
 		if (!tsk) {
 			rcu_read_unlock();
-			ret= -ESRCH;
+			ret = -ESRCH;
 			goto out_unlock_cgroup;
 		}
 		/*
@@ -2250,10 +2240,9 @@ static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *seq)
+static int cgroup_release_agent_show(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgrp = css->cgroup;
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
 
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
@@ -2263,174 +2252,129 @@ static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *seq)
+static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
 {
-	seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup));
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
 	return 0;
 }
 
 /* A buffer size big enough for numbers or short strings */
 #define CGROUP_LOCAL_BUFFER_SIZE 64
 
-static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css,
-				struct cftype *cft, struct file *file,
-				const char __user *userbuf, size_t nbytes,
-				loff_t *unused_ppos)
+static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
+				 size_t nbytes, loff_t *ppos)
 {
-	char buffer[CGROUP_LOCAL_BUFFER_SIZE];
-	int retval = 0;
-	char *end;
+	struct cfent *cfe = __d_cfe(file->f_dentry);
+	struct cftype *cft = __d_cft(file->f_dentry);
+	struct cgroup_subsys_state *css = cfe->css;
+	size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1;
+	char *buf;
+	int ret;
 
-	if (!nbytes)
-		return -EINVAL;
-	if (nbytes >= sizeof(buffer))
+	if (nbytes >= max_bytes)
 		return -E2BIG;
-	if (copy_from_user(buffer, userbuf, nbytes))
-		return -EFAULT;
 
-	buffer[nbytes] = 0;     /* nul-terminate */
-	if (cft->write_u64) {
-		u64 val = simple_strtoull(strstrip(buffer), &end, 0);
-		if (*end)
-			return -EINVAL;
-		retval = cft->write_u64(css, cft, val);
+	buf = kmalloc(nbytes + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, userbuf, nbytes)) {
+		ret = -EFAULT;
+		goto out_free;
+	}
+
+	buf[nbytes] = '\0';
+
+	if (cft->write_string) {
+		ret = cft->write_string(css, cft, strstrip(buf));
+	} else if (cft->write_u64) {
+		unsigned long long v;
+		ret = kstrtoull(buf, 0, &v);
+		if (!ret)
+			ret = cft->write_u64(css, cft, v);
+	} else if (cft->write_s64) {
+		long long v;
+		ret = kstrtoll(buf, 0, &v);
+		if (!ret)
+			ret = cft->write_s64(css, cft, v);
+	} else if (cft->trigger) {
+		ret = cft->trigger(css, (unsigned int)cft->private);
 	} else {
-		s64 val = simple_strtoll(strstrip(buffer), &end, 0);
-		if (*end)
-			return -EINVAL;
-		retval = cft->write_s64(css, cft, val);
+		ret = -EINVAL;
 	}
-	if (!retval)
-		retval = nbytes;
-	return retval;
+out_free:
+	kfree(buf);
+	return ret ?: nbytes;
 }
 
-static ssize_t cgroup_write_string(struct cgroup_subsys_state *css,
-				   struct cftype *cft, struct file *file,
-				   const char __user *userbuf, size_t nbytes,
-				   loff_t *unused_ppos)
+/*
+ * seqfile ops/methods for returning structured data. Currently just
+ * supports string->u64 maps, but can be extended in future.
+ */
+
+static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
 {
-	char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
-	int retval = 0;
-	size_t max_bytes = cft->max_write_len;
-	char *buffer = local_buffer;
+	struct cftype *cft = seq_cft(seq);
 
-	if (!max_bytes)
-		max_bytes = sizeof(local_buffer) - 1;
-	if (nbytes >= max_bytes)
-		return -E2BIG;
-	/* Allocate a dynamic buffer if we need one */
-	if (nbytes >= sizeof(local_buffer)) {
-		buffer = kmalloc(nbytes + 1, GFP_KERNEL);
-		if (buffer == NULL)
-			return -ENOMEM;
-	}
-	if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
-		retval = -EFAULT;
-		goto out;
+	if (cft->seq_start) {
+		return cft->seq_start(seq, ppos);
+	} else {
+		/*
+		 * The same behavior and code as single_open().  Returns
+		 * !NULL if pos is at the beginning; otherwise, NULL.
+		 */
+		return NULL + !*ppos;
 	}
-
-	buffer[nbytes] = 0;     /* nul-terminate */
-	retval = cft->write_string(css, cft, strstrip(buffer));
-	if (!retval)
-		retval = nbytes;
-out:
-	if (buffer != local_buffer)
-		kfree(buffer);
-	return retval;
 }
 
-static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
-				 size_t nbytes, loff_t *ppos)
+static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
-	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cftype *cft = __d_cft(file->f_dentry);
-	struct cgroup_subsys_state *css = cfe->css;
+	struct cftype *cft = seq_cft(seq);
 
-	if (cft->write)
-		return cft->write(css, cft, file, buf, nbytes, ppos);
-	if (cft->write_u64 || cft->write_s64)
-		return cgroup_write_X64(css, cft, file, buf, nbytes, ppos);
-	if (cft->write_string)
-		return cgroup_write_string(css, cft, file, buf, nbytes, ppos);
-	if (cft->trigger) {
-		int ret = cft->trigger(css, (unsigned int)cft->private);
-		return ret ? ret : nbytes;
+	if (cft->seq_next) {
+		return cft->seq_next(seq, v, ppos);
+	} else {
+		/*
+		 * The same behavior and code as single_open(), always
+		 * terminate after the initial read.
+		 */
+		++*ppos;
+		return NULL;
 	}
-	return -EINVAL;
 }
 
-static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css,
-			       struct cftype *cft, struct file *file,
-			       char __user *buf, size_t nbytes, loff_t *ppos)
+static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
 {
-	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
-	u64 val = cft->read_u64(css, cft);
-	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
+	struct cftype *cft = seq_cft(seq);
 
-	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+	if (cft->seq_stop)
+		cft->seq_stop(seq, v);
 }
 
-static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css,
-			       struct cftype *cft, struct file *file,
-			       char __user *buf, size_t nbytes, loff_t *ppos)
+static int cgroup_seqfile_show(struct seq_file *m, void *arg)
 {
-	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
-	s64 val = cft->read_s64(css, cft);
-	int len = sprintf(tmp, "%lld\n", (long long) val);
+	struct cftype *cft = seq_cft(m);
+	struct cgroup_subsys_state *css = seq_css(m);
 
-	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
-}
+	if (cft->seq_show)
+		return cft->seq_show(m, arg);
 
-static ssize_t cgroup_file_read(struct file *file, char __user *buf,
-				size_t nbytes, loff_t *ppos)
-{
-	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cftype *cft = __d_cft(file->f_dentry);
-	struct cgroup_subsys_state *css = cfe->css;
-
-	if (cft->read)
-		return cft->read(css, cft, file, buf, nbytes, ppos);
 	if (cft->read_u64)
-		return cgroup_read_u64(css, cft, file, buf, nbytes, ppos);
-	if (cft->read_s64)
-		return cgroup_read_s64(css, cft, file, buf, nbytes, ppos);
-	return -EINVAL;
-}
-
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
-static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
-{
-	struct seq_file *sf = cb->state;
-	return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
-}
-
-static int cgroup_seqfile_show(struct seq_file *m, void *arg)
-{
-	struct cfent *cfe = m->private;
-	struct cftype *cft = cfe->type;
-	struct cgroup_subsys_state *css = cfe->css;
-
-	if (cft->read_map) {
-		struct cgroup_map_cb cb = {
-			.fill = cgroup_map_add,
-			.state = m,
-		};
-		return cft->read_map(css, cft, &cb);
-	}
-	return cft->read_seq_string(css, cft, m);
+		seq_printf(m, "%llu\n", cft->read_u64(css, cft));
+	else if (cft->read_s64)
+		seq_printf(m, "%lld\n", cft->read_s64(css, cft));
+	else
+		return -EINVAL;
+	return 0;
 }
 
-static const struct file_operations cgroup_seqfile_operations = {
-	.read = seq_read,
-	.write = cgroup_file_write,
-	.llseek = seq_lseek,
-	.release = cgroup_file_release,
+static struct seq_operations cgroup_seq_operations = {
+	.start		= cgroup_seqfile_start,
+	.next		= cgroup_seqfile_next,
+	.stop		= cgroup_seqfile_stop,
+	.show		= cgroup_seqfile_show,
 };
 
 static int cgroup_file_open(struct inode *inode, struct file *file)
@@ -2439,6 +2383,7 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
 	struct cgroup_subsys_state *css;
+	struct cgroup_open_file *of;
 	int err;
 
 	err = generic_file_open(inode, file);
@@ -2468,32 +2413,26 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
 	WARN_ON_ONCE(cfe->css && cfe->css != css);
 	cfe->css = css;
 
-	if (cft->read_map || cft->read_seq_string) {
-		file->f_op = &cgroup_seqfile_operations;
-		err = single_open(file, cgroup_seqfile_show, cfe);
-	} else if (cft->open) {
-		err = cft->open(inode, file);
+	of = __seq_open_private(file, &cgroup_seq_operations,
+				sizeof(struct cgroup_open_file));
+	if (of) {
+		of->cfe = cfe;
+		return 0;
 	}
 
-	if (css->ss && err)
+	if (css->ss)
 		css_put(css);
-	return err;
+	return -ENOMEM;
 }
 
 static int cgroup_file_release(struct inode *inode, struct file *file)
 {
 	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup_subsys_state *css = cfe->css;
-	int ret = 0;
 
-	if (cft->release)
-		ret = cft->release(inode, file);
 	if (css->ss)
 		css_put(css);
-	if (file->f_op == &cgroup_seqfile_operations)
-		single_release(inode, file);
-	return ret;
+	return seq_release_private(inode, file);
 }
 
 /*
@@ -2604,7 +2543,7 @@ static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
 }
 
 static const struct file_operations cgroup_file_operations = {
-	.read = cgroup_file_read,
+	.read = seq_read,
 	.write = cgroup_file_write,
 	.llseek = generic_file_llseek,
 	.open = cgroup_file_open,
@@ -2629,16 +2568,6 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.removexattr = cgroup_removexattr,
 };
 
-/*
- * Check if a file is a control file
- */
-static inline struct cftype *__file_cft(struct file *file)
-{
-	if (file_inode(file)->i_fop != &cgroup_file_operations)
-		return ERR_PTR(-EINVAL);
-	return __d_cft(file->f_dentry);
-}
-
 static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 				struct super_block *sb)
 {
@@ -2696,12 +2625,11 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 	if (cft->mode)
 		return cft->mode;
 
-	if (cft->read || cft->read_u64 || cft->read_s64 ||
-	    cft->read_map || cft->read_seq_string)
+	if (cft->read_u64 || cft->read_s64 || cft->seq_show)
 		mode |= S_IRUGO;
 
-	if (cft->write || cft->write_u64 || cft->write_s64 ||
-	    cft->write_string || cft->trigger)
+	if (cft->write_u64 || cft->write_s64 || cft->write_string ||
+	    cft->trigger)
 		mode |= S_IWUSR;
 
 	return mode;
@@ -2997,9 +2925,9 @@ static void cgroup_enable_task_cg_lists(void)
  * @parent_css: css whose children to walk
  *
  * This function returns the next child of @parent_css and should be called
- * under RCU read lock.  The only requirement is that @parent_css and
- * @pos_css are accessible.  The next sibling is guaranteed to be returned
- * regardless of their states.
+ * under either cgroup_mutex or RCU read lock.  The only requirement is
+ * that @parent_css and @pos_css are accessible.  The next sibling is
+ * guaranteed to be returned regardless of their states.
  */
 struct cgroup_subsys_state *
 css_next_child(struct cgroup_subsys_state *pos_css,
@@ -3009,7 +2937,7 @@ css_next_child(struct cgroup_subsys_state *pos_css,
 	struct cgroup *cgrp = parent_css->cgroup;
 	struct cgroup *next;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/*
 	 * @pos could already have been removed.  Once a cgroup is removed,
@@ -3056,10 +2984,10 @@ EXPORT_SYMBOL_GPL(css_next_child);
  * to visit for pre-order traversal of @root's descendants.  @root is
  * included in the iteration and the first node to be visited.
  *
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section.  This
- * function will return the correct next descendant as long as both @pos
- * and @root are accessible and @pos is a descendant of @root.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section.  This function will return the correct next descendant as long
+ * as both @pos and @root are accessible and @pos is a descendant of @root.
  */
 struct cgroup_subsys_state *
 css_next_descendant_pre(struct cgroup_subsys_state *pos,
@@ -3067,7 +2995,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
 {
 	struct cgroup_subsys_state *next;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/* if first iteration, visit @root */
 	if (!pos)
@@ -3098,17 +3026,17 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre);
  * is returned.  This can be used during pre-order traversal to skip
  * subtree of @pos.
  *
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section.  This
- * function will return the correct rightmost descendant as long as @pos is
- * accessible.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section.  This function will return the correct rightmost descendant as
+ * long as @pos is accessible.
  */
 struct cgroup_subsys_state *
 css_rightmost_descendant(struct cgroup_subsys_state *pos)
 {
 	struct cgroup_subsys_state *last, *tmp;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	cgroup_assert_mutex_or_rcu_locked();
 
 	do {
 		last = pos;
@@ -3144,10 +3072,11 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
  * to visit for post-order traversal of @root's descendants.  @root is
  * included in the iteration and the last node to be visited.
  *
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section.  This
- * function will return the correct next descendant as long as both @pos
- * and @cgroup are accessible and @pos is a descendant of @cgroup.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section.  This function will return the correct next descendant as long
+ * as both @pos and @cgroup are accessible and @pos is a descendant of
+ * @cgroup.
  */
 struct cgroup_subsys_state *
 css_next_descendant_post(struct cgroup_subsys_state *pos,
@@ -3155,7 +3084,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 {
 	struct cgroup_subsys_state *next;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/* if first iteration, visit leftmost descendant which may be @root */
 	if (!pos)
@@ -3494,14 +3423,12 @@ struct cgroup_pidlist {
 	pid_t *list;
 	/* how many elements the above list has */
 	int length;
-	/* how many files are using the current array */
-	int use_count;
 	/* each of these stored in a list by its cgroup */
 	struct list_head links;
 	/* pointer to the cgroup we belong to, for list removal purposes */
 	struct cgroup *owner;
-	/* protects the other fields */
-	struct rw_semaphore rwsem;
+	/* for delayed destruction */
+	struct delayed_work destroy_dwork;
 };
 
 /*
@@ -3517,6 +3444,7 @@ static void *pidlist_allocate(int count)
 	else
 		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
 }
+
 static void pidlist_free(void *p)
 {
 	if (is_vmalloc_addr(p))
@@ -3526,6 +3454,47 @@ static void pidlist_free(void *p)
 }
 
 /*
+ * Used to destroy all pidlists lingering waiting for destroy timer.  None
+ * should be left afterwards.
+ */
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+{
+	struct cgroup_pidlist *l, *tmp_l;
+
+	mutex_lock(&cgrp->pidlist_mutex);
+	list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
+		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+	mutex_unlock(&cgrp->pidlist_mutex);
+
+	flush_workqueue(cgroup_pidlist_destroy_wq);
+	BUG_ON(!list_empty(&cgrp->pidlists));
+}
+
+static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
+						destroy_dwork);
+	struct cgroup_pidlist *tofree = NULL;
+
+	mutex_lock(&l->owner->pidlist_mutex);
+
+	/*
+	 * Destroy iff we didn't get queued again.  The state won't change
+	 * as destroy_dwork can only be queued while locked.
+	 */
+	if (!delayed_work_pending(dwork)) {
+		list_del(&l->links);
+		pidlist_free(l->list);
+		put_pid_ns(l->key.ns);
+		tofree = l;
+	}
+
+	mutex_unlock(&l->owner->pidlist_mutex);
+	kfree(tofree);
+}
+
+/*
  * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
  * Returns the number of unique elements.
  */
@@ -3555,52 +3524,92 @@ after:
 	return dest;
 }
 
+/*
+ * The two pid files - task and cgroup.procs - guaranteed that the result
+ * is sorted, which forced this whole pidlist fiasco.  As pid order is
+ * different per namespace, each namespace needs differently sorted list,
+ * making it impossible to use, for example, single rbtree of member tasks
+ * sorted by task pointer.  As pidlists can be fairly large, allocating one
+ * per open file is dangerous, so cgroup had to implement shared pool of
+ * pidlists keyed by cgroup and namespace.
+ *
+ * All this extra complexity was caused by the original implementation
+ * committing to an entirely unnecessary property.  In the long term, we
+ * want to do away with it.  Explicitly scramble sort order if
+ * sane_behavior so that no such expectation exists in the new interface.
+ *
+ * Scrambling is done by swapping every two consecutive bits, which is
+ * non-identity one-to-one mapping which disturbs sort order sufficiently.
+ */
+static pid_t pid_fry(pid_t pid)
+{
+	unsigned a = pid & 0x55555555;
+	unsigned b = pid & 0xAAAAAAAA;
+
+	return (a << 1) | (b >> 1);
+}
+
+static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
+{
+	if (cgroup_sane_behavior(cgrp))
+		return pid_fry(pid);
+	else
+		return pid;
+}
+
 static int cmppid(const void *a, const void *b)
 {
 	return *(pid_t *)a - *(pid_t *)b;
 }
 
+static int fried_cmppid(const void *a, const void *b)
+{
+	return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
+}
+
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+						  enum cgroup_filetype type)
+{
+	struct cgroup_pidlist *l;
+	/* don't need task_nsproxy() if we're looking at ourself */
+	struct pid_namespace *ns = task_active_pid_ns(current);
+
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
+	list_for_each_entry(l, &cgrp->pidlists, links)
+		if (l->key.type == type && l->key.ns == ns)
+			return l;
+	return NULL;
+}
+
 /*
  * find the appropriate pidlist for our purpose (given procs vs tasks)
  * returns with the lock on that pidlist already held, and takes care
  * of the use count, or returns NULL with no locks held if we're out of
  * memory.
  */
-static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
-						  enum cgroup_filetype type)
+static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
+						enum cgroup_filetype type)
 {
 	struct cgroup_pidlist *l;
-	/* don't need task_nsproxy() if we're looking at ourself */
-	struct pid_namespace *ns = task_active_pid_ns(current);
 
-	/*
-	 * We can't drop the pidlist_mutex before taking the l->rwsem in case
-	 * the last ref-holder is trying to remove l from the list at the same
-	 * time. Holding the pidlist_mutex precludes somebody taking whichever
-	 * list we find out from under us - compare release_pid_array().
-	 */
-	mutex_lock(&cgrp->pidlist_mutex);
-	list_for_each_entry(l, &cgrp->pidlists, links) {
-		if (l->key.type == type && l->key.ns == ns) {
-			/* make sure l doesn't vanish out from under us */
-			down_write(&l->rwsem);
-			mutex_unlock(&cgrp->pidlist_mutex);
-			return l;
-		}
-	}
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
+	l = cgroup_pidlist_find(cgrp, type);
+	if (l)
+		return l;
+
 	/* entry not found; create a new one */
 	l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
-	if (!l) {
-		mutex_unlock(&cgrp->pidlist_mutex);
+	if (!l)
 		return l;
-	}
-	init_rwsem(&l->rwsem);
-	down_write(&l->rwsem);
+
+	INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
 	l->key.type = type;
-	l->key.ns = get_pid_ns(ns);
+	/* don't need task_nsproxy() if we're looking at ourself */
+	l->key.ns = get_pid_ns(task_active_pid_ns(current));
 	l->owner = cgrp;
 	list_add(&l->links, &cgrp->pidlists);
-	mutex_unlock(&cgrp->pidlist_mutex);
 	return l;
 }
 
@@ -3617,6 +3626,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	struct task_struct *tsk;
 	struct cgroup_pidlist *l;
 
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
 	/*
 	 * If cgroup gets more users after we read count, we won't have
 	 * enough space - tough.  This race is indistinguishable to the
@@ -3643,20 +3654,24 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	css_task_iter_end(&it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
-	sort(array, length, sizeof(pid_t), cmppid, NULL);
+	if (cgroup_sane_behavior(cgrp))
+		sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
+	else
+		sort(array, length, sizeof(pid_t), cmppid, NULL);
 	if (type == CGROUP_FILE_PROCS)
 		length = pidlist_uniq(array, length);
-	l = cgroup_pidlist_find(cgrp, type);
+
+	l = cgroup_pidlist_find_create(cgrp, type);
 	if (!l) {
+		mutex_unlock(&cgrp->pidlist_mutex);
 		pidlist_free(array);
 		return -ENOMEM;
 	}
-	/* store array, freeing old if necessary - lock already held */
+
+	/* store array, freeing old if necessary */
 	pidlist_free(l->list);
 	l->list = array;
 	l->length = length;
-	l->use_count++;
-	up_write(&l->rwsem);
 	*lp = l;
 	return 0;
 }
@@ -3730,20 +3745,45 @@ static void *cgroup_pidlist_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_pidlist *l = s->private;
+	struct cgroup_open_file *of = s->private;
+	struct cgroup *cgrp = seq_css(s)->cgroup;
+	struct cgroup_pidlist *l;
+	enum cgroup_filetype type = seq_cft(s)->private;
 	int index = 0, pid = *pos;
-	int *iter;
+	int *iter, ret;
+
+	mutex_lock(&cgrp->pidlist_mutex);
+
+	/*
+	 * !NULL @of->priv indicates that this isn't the first start()
+	 * after open.  If the matching pidlist is around, we can use that.
+	 * Look for it.  Note that @of->priv can't be used directly.  It
+	 * could already have been destroyed.
+	 */
+	if (of->priv)
+		of->priv = cgroup_pidlist_find(cgrp, type);
+
+	/*
+	 * Either this is the first start() after open or the matching
+	 * pidlist has been destroyed inbetween.  Create a new one.
+	 */
+	if (!of->priv) {
+		ret = pidlist_array_load(cgrp, type,
+					 (struct cgroup_pidlist **)&of->priv);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+	l = of->priv;
 
-	down_read(&l->rwsem);
 	if (pid) {
 		int end = l->length;
 
 		while (index < end) {
 			int mid = (index + end) / 2;
-			if (l->list[mid] == pid) {
+			if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
 				index = mid;
 				break;
-			} else if (l->list[mid] <= pid)
+			} else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
 				index = mid + 1;
 			else
 				end = mid;
@@ -3754,19 +3794,25 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 		return NULL;
 	/* Update the abstract position to be the actual pid that we found */
 	iter = l->list + index;
-	*pos = *iter;
+	*pos = cgroup_pid_fry(cgrp, *iter);
 	return iter;
 }
 
 static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-	struct cgroup_pidlist *l = s->private;
-	up_read(&l->rwsem);
+	struct cgroup_open_file *of = s->private;
+	struct cgroup_pidlist *l = of->priv;
+
+	if (l)
+		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
+				 CGROUP_PIDLIST_DESTROY_DELAY);
+	mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
 }
 
 static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct cgroup_pidlist *l = s->private;
+	struct cgroup_open_file *of = s->private;
+	struct cgroup_pidlist *l = of->priv;
 	pid_t *p = v;
 	pid_t *end = l->list + l->length;
 	/*
@@ -3777,7 +3823,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	if (p >= end) {
 		return NULL;
 	} else {
-		*pos = *p;
+		*pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
 		return p;
 	}
 }
@@ -3798,92 +3844,6 @@ static const struct seq_operations cgroup_pidlist_seq_operations = {
 	.show = cgroup_pidlist_show,
 };
 
-static void cgroup_release_pid_array(struct cgroup_pidlist *l)
-{
-	/*
-	 * the case where we're the last user of this particular pidlist will
-	 * have us remove it from the cgroup's list, which entails taking the
-	 * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
-	 * pidlist_mutex, we have to take pidlist_mutex first.
-	 */
-	mutex_lock(&l->owner->pidlist_mutex);
-	down_write(&l->rwsem);
-	BUG_ON(!l->use_count);
-	if (!--l->use_count) {
-		/* we're the last user if refcount is 0; remove and free */
-		list_del(&l->links);
-		mutex_unlock(&l->owner->pidlist_mutex);
-		pidlist_free(l->list);
-		put_pid_ns(l->key.ns);
-		up_write(&l->rwsem);
-		kfree(l);
-		return;
-	}
-	mutex_unlock(&l->owner->pidlist_mutex);
-	up_write(&l->rwsem);
-}
-
-static int cgroup_pidlist_release(struct inode *inode, struct file *file)
-{
-	struct cgroup_pidlist *l;
-	if (!(file->f_mode & FMODE_READ))
-		return 0;
-	/*
-	 * the seq_file will only be initialized if the file was opened for
-	 * reading; hence we check if it's not null only in that case.
-	 */
-	l = ((struct seq_file *)file->private_data)->private;
-	cgroup_release_pid_array(l);
-	return seq_release(inode, file);
-}
-
-static const struct file_operations cgroup_pidlist_operations = {
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = cgroup_file_write,
-	.release = cgroup_pidlist_release,
-};
-
-/*
- * The following functions handle opens on a file that displays a pidlist
- * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
- * in the cgroup.
- */
-/* helper function for the two below it */
-static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
-{
-	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-	struct cgroup_pidlist *l;
-	int retval;
-
-	/* Nothing to do for write-only files */
-	if (!(file->f_mode & FMODE_READ))
-		return 0;
-
-	/* have the array populated */
-	retval = pidlist_array_load(cgrp, type, &l);
-	if (retval)
-		return retval;
-	/* configure file information */
-	file->f_op = &cgroup_pidlist_operations;
-
-	retval = seq_open(file, &cgroup_pidlist_seq_operations);
-	if (retval) {
-		cgroup_release_pid_array(l);
-		return retval;
-	}
-	((struct seq_file *)file->private_data)->private = l;
-	return 0;
-}
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
-{
-	return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
-}
-static int cgroup_procs_open(struct inode *unused, struct file *file)
-{
-	return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
-}
-
 static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
 					 struct cftype *cft)
 {
@@ -3918,202 +3878,6 @@ static void cgroup_dput(struct cgroup *cgrp)
 	deactivate_super(sb);
 }
 
-/*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
-static void cgroup_event_remove(struct work_struct *work)
-{
-	struct cgroup_event *event = container_of(work, struct cgroup_event,
-			remove);
-	struct cgroup_subsys_state *css = event->css;
-
-	remove_wait_queue(event->wqh, &event->wait);
-
-	event->cft->unregister_event(css, event->cft, event->eventfd);
-
-	/* Notify userspace the event is going away. */
-	eventfd_signal(event->eventfd, 1);
-
-	eventfd_ctx_put(event->eventfd);
-	kfree(event);
-	css_put(css);
-}
-
-/*
- * Gets called on POLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
-static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
-		int sync, void *key)
-{
-	struct cgroup_event *event = container_of(wait,
-			struct cgroup_event, wait);
-	struct cgroup *cgrp = event->css->cgroup;
-	unsigned long flags = (unsigned long)key;
-
-	if (flags & POLLHUP) {
-		/*
-		 * If the event has been detached at cgroup removal, we
-		 * can simply return knowing the other side will cleanup
-		 * for us.
-		 *
-		 * We can't race against event freeing since the other
-		 * side will require wqh->lock via remove_wait_queue(),
-		 * which we hold.
-		 */
-		spin_lock(&cgrp->event_list_lock);
-		if (!list_empty(&event->list)) {
-			list_del_init(&event->list);
-			/*
-			 * We are in atomic context, but cgroup_event_remove()
-			 * may sleep, so we have to call it in workqueue.
-			 */
-			schedule_work(&event->remove);
-		}
-		spin_unlock(&cgrp->event_list_lock);
-	}
-
-	return 0;
-}
-
-static void cgroup_event_ptable_queue_proc(struct file *file,
-		wait_queue_head_t *wqh, poll_table *pt)
-{
-	struct cgroup_event *event = container_of(pt,
-			struct cgroup_event, pt);
-
-	event->wqh = wqh;
-	add_wait_queue(wqh, &event->wait);
-}
-
-/*
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
-static int cgroup_write_event_control(struct cgroup_subsys_state *dummy_css,
-				      struct cftype *cft, const char *buffer)
-{
-	struct cgroup *cgrp = dummy_css->cgroup;
-	struct cgroup_event *event;
-	struct cgroup_subsys_state *cfile_css;
-	unsigned int efd, cfd;
-	struct fd efile;
-	struct fd cfile;
-	char *endp;
-	int ret;
-
-	efd = simple_strtoul(buffer, &endp, 10);
-	if (*endp != ' ')
-		return -EINVAL;
-	buffer = endp + 1;
-
-	cfd = simple_strtoul(buffer, &endp, 10);
-	if ((*endp != ' ') && (*endp != '\0'))
-		return -EINVAL;
-	buffer = endp + 1;
-
-	event = kzalloc(sizeof(*event), GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&event->list);
-	init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
-	init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
-	INIT_WORK(&event->remove, cgroup_event_remove);
-
-	efile = fdget(efd);
-	if (!efile.file) {
-		ret = -EBADF;
-		goto out_kfree;
-	}
-
-	event->eventfd = eventfd_ctx_fileget(efile.file);
-	if (IS_ERR(event->eventfd)) {
-		ret = PTR_ERR(event->eventfd);
-		goto out_put_efile;
-	}
-
-	cfile = fdget(cfd);
-	if (!cfile.file) {
-		ret = -EBADF;
-		goto out_put_eventfd;
-	}
-
-	/* the process need read permission on control file */
-	/* AV: shouldn't we check that it's been opened for read instead? */
-	ret = inode_permission(file_inode(cfile.file), MAY_READ);
-	if (ret < 0)
-		goto out_put_cfile;
-
-	event->cft = __file_cft(cfile.file);
-	if (IS_ERR(event->cft)) {
-		ret = PTR_ERR(event->cft);
-		goto out_put_cfile;
-	}
-
-	if (!event->cft->ss) {
-		ret = -EBADF;
-		goto out_put_cfile;
-	}
-
-	/*
-	 * Determine the css of @cfile, verify it belongs to the same
-	 * cgroup as cgroup.event_control, and associate @event with it.
-	 * Remaining events are automatically removed on cgroup destruction
-	 * but the removal is asynchronous, so take an extra ref.
-	 */
-	rcu_read_lock();
-
-	ret = -EINVAL;
-	event->css = cgroup_css(cgrp, event->cft->ss);
-	cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, event->cft->ss);
-	if (event->css && event->css == cfile_css && css_tryget(event->css))
-		ret = 0;
-
-	rcu_read_unlock();
-	if (ret)
-		goto out_put_cfile;
-
-	if (!event->cft->register_event || !event->cft->unregister_event) {
-		ret = -EINVAL;
-		goto out_put_css;
-	}
-
-	ret = event->cft->register_event(event->css, event->cft,
-			event->eventfd, buffer);
-	if (ret)
-		goto out_put_css;
-
-	efile.file->f_op->poll(efile.file, &event->pt);
-
-	spin_lock(&cgrp->event_list_lock);
-	list_add(&event->list, &cgrp->event_list);
-	spin_unlock(&cgrp->event_list_lock);
-
-	fdput(cfile);
-	fdput(efile);
-
-	return 0;
-
-out_put_css:
-	css_put(event->css);
-out_put_cfile:
-	fdput(cfile);
-out_put_eventfd:
-	eventfd_ctx_put(event->eventfd);
-out_put_efile:
-	fdput(efile);
-out_kfree:
-	kfree(event);
-
-	return ret;
-}
-
 static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
 				      struct cftype *cft)
 {
@@ -4133,17 +3897,15 @@ static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
 static struct cftype cgroup_base_files[] = {
 	{
 		.name = "cgroup.procs",
-		.open = cgroup_procs_open,
+		.seq_start = cgroup_pidlist_start,
+		.seq_next = cgroup_pidlist_next,
+		.seq_stop = cgroup_pidlist_stop,
+		.seq_show = cgroup_pidlist_show,
+		.private = CGROUP_FILE_PROCS,
 		.write_u64 = cgroup_procs_write,
-		.release = cgroup_pidlist_release,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
-		.name = "cgroup.event_control",
-		.write_string = cgroup_write_event_control,
-		.mode = S_IWUGO,
-	},
-	{
 		.name = "cgroup.clone_children",
 		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_clone_children_read,
@@ -4152,7 +3914,7 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "cgroup.sane_behavior",
 		.flags = CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cgroup_sane_behavior_show,
+		.seq_show = cgroup_sane_behavior_show,
 	},
 
 	/*
@@ -4163,9 +3925,12 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "tasks",
 		.flags = CFTYPE_INSANE,		/* use "procs" instead */
-		.open = cgroup_tasks_open,
+		.seq_start = cgroup_pidlist_start,
+		.seq_next = cgroup_pidlist_next,
+		.seq_stop = cgroup_pidlist_stop,
+		.seq_show = cgroup_pidlist_show,
+		.private = CGROUP_FILE_TASKS,
 		.write_u64 = cgroup_tasks_write,
-		.release = cgroup_pidlist_release,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
@@ -4177,7 +3942,7 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "release_agent",
 		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cgroup_release_agent_show,
+		.seq_show = cgroup_release_agent_show,
 		.write_string = cgroup_release_agent_write,
 		.max_write_len = PATH_MAX,
 	},
@@ -4268,6 +4033,7 @@ static void css_release(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
+	rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
 	call_rcu(&css->rcu_head, css_free_rcu_fn);
 }
 
@@ -4322,6 +4088,62 @@ static void offline_css(struct cgroup_subsys_state *css)
 	RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
 }
 
+/**
+ * create_css - create a cgroup_subsys_state
+ * @cgrp: the cgroup new css will be associated with
+ * @ss: the subsys of new css
+ *
+ * Create a new css associated with @cgrp - @ss pair.  On success, the new
+ * css is online and installed in @cgrp with all interface files created.
+ * Returns 0 on success, -errno on failure.
+ */
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct cgroup *parent = cgrp->parent;
+	struct cgroup_subsys_state *css;
+	int err;
+
+	lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
+	lockdep_assert_held(&cgroup_mutex);
+
+	css = ss->css_alloc(cgroup_css(parent, ss));
+	if (IS_ERR(css))
+		return PTR_ERR(css);
+
+	err = percpu_ref_init(&css->refcnt, css_release);
+	if (err)
+		goto err_free;
+
+	init_css(css, ss, cgrp);
+
+	err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
+	if (err)
+		goto err_free;
+
+	err = online_css(css);
+	if (err)
+		goto err_free;
+
+	dget(cgrp->dentry);
+	css_get(css->parent);
+
+	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
+	    parent->parent) {
+		pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
+			   current->comm, current->pid, ss->name);
+		if (!strcmp(ss->name, "memory"))
+			pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
+		ss->warned_broken_hierarchy = true;
+	}
+
+	return 0;
+
+err_free:
+	percpu_ref_cancel_init(&css->refcnt);
+	ss->css_free(css);
+	return err;
+}
+
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -4333,11 +4155,10 @@ static void offline_css(struct cgroup_subsys_state *css)
 static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			     umode_t mode)
 {
-	struct cgroup_subsys_state *css_ar[CGROUP_SUBSYS_COUNT] = { };
 	struct cgroup *cgrp;
 	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
-	int err = 0;
+	int ssid, err = 0;
 	struct cgroup_subsys *ss;
 	struct super_block *sb = root->sb;
 
@@ -4393,23 +4214,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css;
-
-		css = ss->css_alloc(cgroup_css(parent, ss));
-		if (IS_ERR(css)) {
-			err = PTR_ERR(css);
-			goto err_free_all;
-		}
-		css_ar[ss->subsys_id] = css;
-
-		err = percpu_ref_init(&css->refcnt, css_release);
-		if (err)
-			goto err_free_all;
-
-		init_css(css, ss, cgrp);
-	}
-
 	/*
 	 * Create directory.  cgroup_create_file() returns with the new
 	 * directory locked on success so that it can be populated without
@@ -4417,7 +4221,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	 */
 	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
 	if (err < 0)
-		goto err_free_all;
+		goto err_unlock;
 	lockdep_assert_held(&dentry->d_inode->i_mutex);
 
 	cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4426,59 +4230,34 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
 
-	/* each css holds a ref to the cgroup's dentry and the parent css */
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-		dget(dentry);
-		css_get(css->parent);
-	}
-
 	/* hold a ref to the parent's dentry */
 	dget(parent->dentry);
 
-	/* creation succeeded, notify subsystems */
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-		err = online_css(css);
-		if (err)
-			goto err_destroy;
-
-		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
-		    parent->parent) {
-			pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
-				   current->comm, current->pid, ss->name);
-			if (!strcmp(ss->name, "memory"))
-				pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
-			ss->warned_broken_hierarchy = true;
-		}
-	}
-
+	/*
+	 * @cgrp is now fully operational.  If something fails after this
+	 * point, it'll be released via the normal destruction path.
+	 */
 	idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
 
 	err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
 	if (err)
 		goto err_destroy;
 
-	err = cgroup_populate_dir(cgrp, root->subsys_mask);
-	if (err)
-		goto err_destroy;
+	/* let's create and online css's */
+	for_each_subsys(ss, ssid) {
+		if (root->subsys_mask & (1 << ssid)) {
+			err = create_css(cgrp, ss);
+			if (err)
+				goto err_destroy;
+		}
+	}
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 
 	return 0;
 
-err_free_all:
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-		if (css) {
-			percpu_ref_cancel_init(&css->refcnt);
-			ss->css_free(css);
-		}
-	}
+err_unlock:
 	mutex_unlock(&cgroup_mutex);
 	/* Release the reference count that we took on the superblock */
 	deactivate_super(sb);
@@ -4613,10 +4392,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
 	struct dentry *d = cgrp->dentry;
-	struct cgroup_event *event, *tmp;
-	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
 	struct cgroup *child;
 	bool empty;
+	int ssid;
 
 	lockdep_assert_held(&d->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_mutex);
@@ -4652,8 +4431,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 * will be invoked to perform the rest of destruction once the
 	 * percpu refs of all css's are confirmed to be killed.
 	 */
-	for_each_root_subsys(cgrp->root, ss)
-		kill_css(cgroup_css(cgrp, ss));
+	for_each_css(css, ssid, cgrp)
+		kill_css(css);
 
 	/*
 	 * Mark @cgrp dead.  This prevents further task migration and child
@@ -4688,18 +4467,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	dget(d);
 	cgroup_d_remove_dir(d);
 
-	/*
-	 * Unregister events and notify userspace.
-	 * Notify userspace about cgroup removing only after rmdir of cgroup
-	 * directory to avoid race between userspace and kernelspace.
-	 */
-	spin_lock(&cgrp->event_list_lock);
-	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
-		list_del_init(&event->list);
-		schedule_work(&event->remove);
-	}
-	spin_unlock(&cgrp->event_list_lock);
-
 	return 0;
 };
 
@@ -4722,14 +4489,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 	/* delete this cgroup from parent->children */
 	list_del_rcu(&cgrp->sibling);
 
-	/*
-	 * We should remove the cgroup object from idr before its grace
-	 * period starts, so we won't be looking up a cgroup while the
-	 * cgroup is being freed.
-	 */
-	idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-	cgrp->id = -1;
-
 	dput(d);
 
 	set_bit(CGRP_RELEASABLE, &parent->flags);
@@ -4778,7 +4537,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	cgroup_init_cftsets(ss);
 
 	/* Create the top cgroup state for this subsystem */
-	list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
 	ss->root = &cgroup_dummy_root;
 	css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
 	/* We don't handle early failures gracefully */
@@ -4852,6 +4610,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	cgroup_init_cftsets(ss);
 
 	mutex_lock(&cgroup_mutex);
+	mutex_lock(&cgroup_root_mutex);
 	cgroup_subsys[ss->subsys_id] = ss;
 
 	/*
@@ -4863,11 +4622,11 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	if (IS_ERR(css)) {
 		/* failure case - need to deassign the cgroup_subsys[] slot. */
 		cgroup_subsys[ss->subsys_id] = NULL;
+		mutex_unlock(&cgroup_root_mutex);
 		mutex_unlock(&cgroup_mutex);
 		return PTR_ERR(css);
 	}
 
-	list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
 	ss->root = &cgroup_dummy_root;
 
 	/* our new subsystem will be attached to the dummy hierarchy. */
@@ -4897,14 +4656,18 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	ret = online_css(css);
-	if (ret)
+	if (ret) {
+		ss->css_free(css);
 		goto err_unload;
+	}
 
 	/* success! */
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 
 err_unload:
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 	/* @ss can't be mounted here as try_module_get() would fail */
 	cgroup_unload_subsys(ss);
@@ -4923,6 +4686,7 @@ EXPORT_SYMBOL_GPL(cgroup_load_subsys);
 void cgroup_unload_subsys(struct cgroup_subsys *ss)
 {
 	struct cgrp_cset_link *link;
+	struct cgroup_subsys_state *css;
 
 	BUG_ON(ss->module == NULL);
 
@@ -4934,15 +4698,15 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	BUG_ON(ss->root != &cgroup_dummy_root);
 
 	mutex_lock(&cgroup_mutex);
+	mutex_lock(&cgroup_root_mutex);
 
-	offline_css(cgroup_css(cgroup_dummy_top, ss));
+	css = cgroup_css(cgroup_dummy_top, ss);
+	if (css)
+		offline_css(css);
 
 	/* deassign the subsys_id */
 	cgroup_subsys[ss->subsys_id] = NULL;
 
-	/* remove subsystem from the dummy root's list of subsystems */
-	list_del_init(&ss->sibling);
-
 	/*
 	 * disentangle the css from all css_sets attached to the dummy
 	 * top. as in loading, we need to pay our respects to the hashtable
@@ -4965,9 +4729,11 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	 * need to free before marking as null because ss->css_free needs
 	 * the cgrp->subsys pointer to find their state.
 	 */
-	ss->css_free(cgroup_css(cgroup_dummy_top, ss));
+	if (css)
+		ss->css_free(css);
 	RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
 
+	mutex_unlock(&cgroup_root_mutex);
 	mutex_unlock(&cgroup_mutex);
 }
 EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
@@ -5086,6 +4852,15 @@ static int __init cgroup_wq_init(void)
 	 */
 	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
 	BUG_ON(!cgroup_destroy_wq);
+
+	/*
+	 * Used to destroy pidlists and separate to serve as flush domain.
+	 * Cap @max_active to 1 too.
+	 */
+	cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
+						    0, 1);
+	BUG_ON(!cgroup_pidlist_destroy_wq);
+
 	return 0;
 }
 core_initcall(cgroup_wq_init);
@@ -5129,11 +4904,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 	for_each_active_root(root) {
 		struct cgroup_subsys *ss;
 		struct cgroup *cgrp;
-		int count = 0;
+		int ssid, count = 0;
 
 		seq_printf(m, "%d:", root->hierarchy_id);
-		for_each_root_subsys(root, ss)
-			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+		for_each_subsys(ss, ssid)
+			if (root->subsys_mask & (1 << ssid))
+				seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
 		if (strlen(root->name))
 			seq_printf(m, "%sname=%s", count ? "," : "",
 				   root->name);
@@ -5474,16 +5250,16 @@ __setup("cgroup_disable=", cgroup_disable);
  * @dentry: directory dentry of interest
  * @ss: subsystem of interest
  *
- * Must be called under RCU read lock.  The caller is responsible for
- * pinning the returned css if it needs to be accessed outside the RCU
- * critical section.
+ * Must be called under cgroup_mutex or RCU read lock.  The caller is
+ * responsible for pinning the returned css if it needs to be accessed
+ * outside the critical section.
  */
 struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
 					 struct cgroup_subsys *ss)
 {
 	struct cgroup *cgrp;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/* is @dentry a cgroup dir? */
 	if (!dentry->d_inode ||
@@ -5506,9 +5282,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 {
 	struct cgroup *cgrp;
 
-	rcu_lockdep_assert(rcu_read_lock_held() ||
-			   lockdep_is_held(&cgroup_mutex),
-			   "css_from_id() needs proper protection");
+	cgroup_assert_mutex_or_rcu_locked();
 
 	cgrp = idr_find(&ss->root->cgroup_idr, id);
 	if (cgrp)
@@ -5556,9 +5330,7 @@ static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
 	return count;
 }
 
-static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
-					 struct cftype *cft,
-					 struct seq_file *seq)
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 {
 	struct cgrp_cset_link *link;
 	struct css_set *cset;
@@ -5583,9 +5355,9 @@ static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
 }
 
 #define MAX_TASKS_SHOWN_PER_CSS 25
-static int cgroup_css_links_read(struct cgroup_subsys_state *css,
-				 struct cftype *cft, struct seq_file *seq)
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
 {
+	struct cgroup_subsys_state *css = seq_css(seq);
 	struct cgrp_cset_link *link;
 
 	read_lock(&css_set_lock);
@@ -5631,12 +5403,12 @@ static struct cftype debug_files[] =  {
 
 	{
 		.name = "current_css_set_cg_links",
-		.read_seq_string = current_css_set_cg_links_read,
+		.seq_show = current_css_set_cg_links_read,
 	},
 
 	{
 		.name = "cgroup_css_links",
-		.read_seq_string = cgroup_css_links_read,
+		.seq_show = cgroup_css_links_read,
 	},
 
 	{
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index f0ff64d..6c3154e 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -301,10 +301,9 @@ out_unlock:
 	spin_unlock_irq(&freezer->lock);
 }
 
-static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
-			struct seq_file *m)
+static int freezer_read(struct seq_file *m, void *v)
 {
-	struct cgroup_subsys_state *pos;
+	struct cgroup_subsys_state *css = seq_css(m), *pos;
 
 	rcu_read_lock();
 
@@ -458,7 +457,7 @@ static struct cftype files[] = {
 	{
 		.name = "state",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.read_seq_string = freezer_read,
+		.seq_show = freezer_read,
 		.write_string = freezer_write,
 	},
 	{
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index e5f3917..6cb20d2 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -53,10 +53,10 @@ void context_tracking_user_enter(void)
 	/*
 	 * Repeat the user_enter() check here because some archs may be calling
 	 * this from asm and if no CPU needs context tracking, they shouldn't
-	 * go further. Repeat the check here until they support the static key
-	 * check.
+	 * go further. Repeat the check here until they support the inline static
+	 * key check.
 	 */
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	/*
@@ -160,7 +160,7 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	if (in_interrupt())
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 988573a..277f494 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -105,14 +105,17 @@ static void cpu_idle_loop(void)
 				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
-			/*
-			 * We need to test and propagate the TIF_NEED_RESCHED
-			 * bit here because we might not have send the
-			 * reschedule IPI to idle tasks.
-			 */
-			if (tif_need_resched())
-				set_preempt_need_resched();
 		}
+
+		/*
+		 * Since we fell out of the loop above, we know
+		 * TIF_NEED_RESCHED must be set, propagate it into
+		 * PREEMPT_NEED_RESCHED.
+		 *
+		 * This is required because for polling idle loops we will
+		 * not have had an IPI to fold the state for us.
+		 */
+		preempt_set_need_resched();
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
 	}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4772034..4410ac6 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1731,66 +1731,41 @@ out_unlock:
  * used, list of ranges of sequential numbers, is variable length,
  * and since these maps can change value dynamically, one could read
  * gibberish by doing partial reads while a list was changing.
- * A single large read to a buffer that crosses a page boundary is
- * ok, because the result being copied to user land is not recomputed
- * across a page fault.
  */
-
-static size_t cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
+static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 {
-	size_t count;
-
-	mutex_lock(&callback_mutex);
-	count = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
-	mutex_unlock(&callback_mutex);
+	struct cpuset *cs = css_cs(seq_css(sf));
+	cpuset_filetype_t type = seq_cft(sf)->private;
+	ssize_t count;
+	char *buf, *s;
+	int ret = 0;
 
-	return count;
-}
-
-static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs)
-{
-	size_t count;
+	count = seq_get_buf(sf, &buf);
+	s = buf;
 
 	mutex_lock(&callback_mutex);
-	count = nodelist_scnprintf(page, PAGE_SIZE, cs->mems_allowed);
-	mutex_unlock(&callback_mutex);
-
-	return count;
-}
-
-static ssize_t cpuset_common_file_read(struct cgroup_subsys_state *css,
-				       struct cftype *cft, struct file *file,
-				       char __user *buf, size_t nbytes,
-				       loff_t *ppos)
-{
-	struct cpuset *cs = css_cs(css);
-	cpuset_filetype_t type = cft->private;
-	char *page;
-	ssize_t retval = 0;
-	char *s;
-
-	if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
-		return -ENOMEM;
-
-	s = page;
 
 	switch (type) {
 	case FILE_CPULIST:
-		s += cpuset_sprintf_cpulist(s, cs);
+		s += cpulist_scnprintf(s, count, cs->cpus_allowed);
 		break;
 	case FILE_MEMLIST:
-		s += cpuset_sprintf_memlist(s, cs);
+		s += nodelist_scnprintf(s, count, cs->mems_allowed);
 		break;
 	default:
-		retval = -EINVAL;
-		goto out;
+		ret = -EINVAL;
+		goto out_unlock;
 	}
-	*s++ = '\n';
 
-	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
-out:
-	free_page((unsigned long)page);
-	return retval;
+	if (s < buf + count - 1) {
+		*s++ = '\n';
+		seq_commit(sf, s - buf);
+	} else {
+		seq_commit(sf, -1);
+	}
+out_unlock:
+	mutex_unlock(&callback_mutex);
+	return ret;
 }
 
 static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -1847,7 +1822,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
 static struct cftype files[] = {
 	{
 		.name = "cpus",
-		.read = cpuset_common_file_read,
+		.seq_show = cpuset_common_seq_show,
 		.write_string = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * NR_CPUS),
 		.private = FILE_CPULIST,
@@ -1855,7 +1830,7 @@ static struct cftype files[] = {
 
 	{
 		.name = "mems",
-		.read = cpuset_common_file_read,
+		.seq_show = cpuset_common_seq_show,
 		.write_string = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * MAX_NUMNODES),
 		.private = FILE_MEMLIST,
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 7d2f35e..334b398 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -736,7 +736,8 @@ int kgdb_nmicallback(int cpu, void *regs)
 	return 1;
 }
 
-int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
+int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code,
+							atomic_t *send_ready)
 {
 #ifdef CONFIG_SMP
 	if (!kgdb_io_ready(0) || !send_ready)
@@ -750,7 +751,7 @@ int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
 		ks->cpu			= cpu;
 		ks->ex_vector		= trapnr;
 		ks->signo		= SIGTRAP;
-		ks->err_code		= KGDB_KDB_REASON_SYSTEM_NMI;
+		ks->err_code		= err_code;
 		ks->linux_regs		= regs;
 		ks->send_ready		= send_ready;
 		kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 572aa4f..127d9bc 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -75,13 +75,11 @@ extern int kdb_stub(struct kgdb_state *ks);
 extern int kdb_parse(const char *cmdstr);
 extern int kdb_common_init_state(struct kgdb_state *ks);
 extern int kdb_common_deinit_state(void);
-#define KGDB_KDB_REASON_SYSTEM_NMI KDB_REASON_SYSTEM_NMI
 #else /* ! CONFIG_KGDB_KDB */
 static inline int kdb_stub(struct kgdb_state *ks)
 {
 	return DBG_PASS_EVENT;
 }
-#define KGDB_KDB_REASON_SYSTEM_NMI 0
 #endif /* CONFIG_KGDB_KDB */
 
 #endif /* _DEBUG_CORE_H_ */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc..56003c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
-		       PERF_FLAG_PID_CGROUP)
+		       PERF_FLAG_PID_CGROUP |\
+		       PERF_FLAG_FD_CLOEXEC)
 
 /*
  * branch priv levels that need permission checks
@@ -1396,6 +1397,8 @@ event_sched_out(struct perf_event *event,
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return;
 
+	perf_pmu_disable(event->pmu);
+
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -1412,6 +1415,8 @@ event_sched_out(struct perf_event *event,
 		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
+
+	perf_pmu_enable(event->pmu);
 }
 
 static void
@@ -1652,6 +1657,7 @@ event_sched_in(struct perf_event *event,
 		 struct perf_event_context *ctx)
 {
 	u64 tstamp = perf_event_time(event);
+	int ret = 0;
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
@@ -1674,10 +1680,13 @@ event_sched_in(struct perf_event *event,
 	 */
 	smp_wmb();
 
+	perf_pmu_disable(event->pmu);
+
 	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
-		return -EAGAIN;
+		ret = -EAGAIN;
+		goto out;
 	}
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1693,7 +1702,10 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
-	return 0;
+out:
+	perf_pmu_enable(event->pmu);
+
+	return ret;
 }
 
 static int
@@ -2743,6 +2755,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		perf_pmu_disable(event->pmu);
+
 		hwc = &event->hw;
 
 		if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2752,7 +2766,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
-			continue;
+			goto next;
 
 		/*
 		 * stop the event and update event->count
@@ -2774,6 +2788,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+	next:
+		perf_pmu_enable(event->pmu);
 	}
 
 	perf_pmu_enable(ctx->pmu);
@@ -3527,7 +3543,7 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	int ret = 0;
+	int ret = 0, active;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -3551,6 +3567,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->attr.sample_period = value;
 		event->hw.sample_period = value;
 	}
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(ctx->pmu);
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	local64_set(&event->hw.period_left, 0);
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(ctx->pmu);
+	}
+
 unlock:
 	raw_spin_unlock_irq(&ctx->lock);
 
@@ -6655,6 +6685,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
+	INIT_LIST_HEAD(&event->active_entry);
+	INIT_HLIST_NODE(&event->hlist_entry);
+
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
@@ -6965,6 +6998,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int event_fd;
 	int move_group = 0;
 	int err;
+	int f_flags = O_RDWR;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -6993,7 +7027,10 @@ SYSCALL_DEFINE5(perf_event_open,
 	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
 		return -EINVAL;
 
-	event_fd = get_unused_fd();
+	if (flags & PERF_FLAG_FD_CLOEXEC)
+		f_flags |= O_CLOEXEC;
+
+	event_fd = get_unused_fd_flags(f_flags);
 	if (event_fd < 0)
 		return event_fd;
 
@@ -7115,7 +7152,8 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 	}
 
-	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
 		goto err_context;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8b168a..146a579 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -61,19 +61,20 @@ again:
 	 *
 	 *   kernel				user
 	 *
-	 *   READ ->data_tail			READ ->data_head
-	 *   smp_mb()	(A)			smp_rmb()	(C)
-	 *   WRITE $data			READ $data
-	 *   smp_wmb()	(B)			smp_mb()	(D)
-	 *   STORE ->data_head			WRITE ->data_tail
+	 *   if (LOAD ->data_tail) {		LOAD ->data_head
+	 *			(A)		smp_rmb()	(C)
+	 *	STORE $data			LOAD $data
+	 *	smp_wmb()	(B)		smp_mb()	(D)
+	 *	STORE ->data_head		STORE ->data_tail
+	 *   }
 	 *
 	 * Where A pairs with D, and B pairs with C.
 	 *
-	 * I don't think A needs to be a full barrier because we won't in fact
-	 * write data until we see the store from userspace. So we simply don't
-	 * issue the data WRITE until we observe it. Be conservative for now.
+	 * In our case (A) is a control dependency that separates the load of
+	 * the ->data_tail and the stores of $data. In case ->data_tail
+	 * indicates there is no room in the buffer to store $data we do not.
 	 *
-	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * D needs to be a full barrier since it separates the data READ
 	 * from the tail WRITE.
 	 *
 	 * For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -81,7 +82,7 @@ again:
 	 *
 	 * See perf_output_begin().
 	 */
-	smp_wmb();
+	smp_wmb(); /* B, matches C */
 	rb->user_page->data_head = head;
 
 	/*
@@ -144,17 +145,26 @@ int perf_output_begin(struct perf_output_handle *handle,
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
 			goto fail;
+
+		/*
+		 * The above forms a control dependency barrier separating the
+		 * @tail load above from the data stores below. Since the @tail
+		 * load is required to compute the branch to fail below.
+		 *
+		 * A, matches D; the full memory barrier userspace SHOULD issue
+		 * after reading the data and before storing the new tail
+		 * position.
+		 *
+		 * See perf_output_put_handle().
+		 */
+
 		head += size;
 	} while (local_cmpxchg(&rb->head, offset, head) != offset);
 
 	/*
-	 * Separate the userpage->tail read from the data stores below.
-	 * Matches the MB userspace SHOULD issue after reading the data
-	 * and before storing the new tail position.
-	 *
-	 * See perf_output_put_handle().
+	 * We rely on the implied barrier() by local_cmpxchg() to ensure
+	 * none of the data stores below can be lifted up by the compiler.
 	 */
-	smp_mb();
 
 	if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
 		local_add(rb->watermark, &rb->wakeup);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 24b7d6c..307d87c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,17 @@ struct uprobe {
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
 	unsigned long		flags;
+
+	/*
+	 * The generic code assumes that it has two members of unknown type
+	 * owned by the arch-specific code:
+	 *
+	 * 	insn -	copy_insn() saves the original instruction here for
+	 *		arch_uprobe_analyze_insn().
+	 *
+	 *	ixol -	potentially modified instruction to execute out of
+	 *		line, copied to xol_area by xol_get_insn_slot().
+	 */
 	struct arch_uprobe	arch;
 };
 
@@ -86,6 +97,29 @@ struct return_instance {
 };
 
 /*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
+ * On a breakpoint hit, thread contests for a slot.  It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+	wait_queue_head_t 	wq;		/* if all slots are busy */
+	atomic_t 		slot_count;	/* number of in-use slots */
+	unsigned long 		*bitmap;	/* 0 = free slot */
+	struct page 		*page;
+
+	/*
+	 * We keep the vma's vm_start rather than a pointer to the vma
+	 * itself.  The probed process or a naughty kernel module could make
+	 * the vma go away, and we must handle that reasonably gracefully.
+	 */
+	unsigned long 		vaddr;		/* Page(s) of instruction slots */
+};
+
+/*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
  * changed after breakpoint was inserted.
@@ -330,7 +364,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -529,8 +563,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
 {
 	struct address_space *mapping = uprobe->inode->i_mapping;
 	loff_t offs = uprobe->offset;
-	void *insn = uprobe->arch.insn;
-	int size = MAX_UINSN_BYTES;
+	void *insn = &uprobe->arch.insn;
+	int size = sizeof(uprobe->arch.insn);
 	int len, err = -EIO;
 
 	/* Copy only available bytes, -EIO if nothing was read */
@@ -569,7 +603,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 		goto out;
 
 	ret = -ENOTSUPP;
-	if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+	if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
 		goto out;
 
 	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -1264,7 +1298,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 
 	/* Initialize the slot */
 	copy_to_page(area->page, xol_vaddr,
-			uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
+			&uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
 	/*
 	 * We probably need flush_icache_user_range() but it needs vma.
 	 * This should work on supported architectures too.
@@ -1403,12 +1437,10 @@ static void uprobe_warn(struct task_struct *t, const char *msg)
 
 static void dup_xol_work(struct callback_head *work)
 {
-	kfree(work);
-
 	if (current->flags & PF_EXITING)
 		return;
 
-	if (!__create_xol_area(current->utask->vaddr))
+	if (!__create_xol_area(current->utask->dup_xol_addr))
 		uprobe_warn(current, "dup xol area");
 }
 
@@ -1419,7 +1451,6 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 	struct uprobe_task *utask = current->utask;
 	struct mm_struct *mm = current->mm;
-	struct callback_head *work;
 	struct xol_area *area;
 
 	t->utask = NULL;
@@ -1441,14 +1472,9 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 	if (mm == t->mm)
 		return;
 
-	/* TODO: move it into the union in uprobe_task */
-	work = kmalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return uprobe_warn(t, "dup xol area");
-
-	t->utask->vaddr = area->vaddr;
-	init_task_work(work, dup_xol_work);
-	task_work_add(t, work, true);
+	t->utask->dup_xol_addr = area->vaddr;
+	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+	task_work_add(t, &t->utask->dup_xol_work, true);
 }
 
 /*
@@ -1828,6 +1854,10 @@ static void handle_swbp(struct pt_regs *regs)
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
 		goto out;
 
+	/* Tracing handlers use ->utask to communicate with fetch methods */
+	if (!get_utask())
+		goto out;
+
 	handler_chain(uprobe, regs);
 	if (can_skip_sstep(uprobe, regs))
 		goto out;
diff --git a/kernel/exit.c b/kernel/exit.c
index a949819..1e77fc6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		__this_cpu_dec(process_counts);
 	}
 	list_del_rcu(&p->thread_group);
+	list_del_rcu(&p->thread_node);
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be..a17621c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	spin_lock_init(&mm->page_table_lock);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	clear_tlb_flush_pending(mm);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
@@ -799,14 +800,11 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
  * Allocate a new mm structure and copy contents from the
  * mm structure of the passed in task structure.
  */
-struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk)
 {
 	struct mm_struct *mm, *oldmm = current->mm;
 	int err;
 
-	if (!oldmm)
-		return NULL;
-
 	mm = allocate_mm();
 	if (!mm)
 		goto fail_nomem;
@@ -1034,6 +1032,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
+
+	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
@@ -1086,8 +1089,10 @@ static void rt_mutex_init_task(struct task_struct *p)
 {
 	raw_spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters);
+	p->pi_waiters = RB_ROOT;
+	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
+	p->pi_top_task = NULL;
 #endif
 }
 
@@ -1171,7 +1176,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * do not allow it to share a thread group or signal handlers or
 	 * parent with the forking task.
 	 */
-	if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+	if (clone_flags & CLONE_SIGHAND) {
 		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
 		    (task_active_pid_ns(current) !=
 				current->nsproxy->pid_ns_for_children))
@@ -1221,7 +1226,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!try_module_get(task_thread_info(p)->exec_domain->module))
 		goto bad_fork_cleanup_count;
 
-	p->did_exec = 0;
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	copy_flags(clone_flags, p);
 	INIT_LIST_HEAD(&p->children);
@@ -1310,7 +1314,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(clone_flags, p);
+	retval = sched_fork(clone_flags, p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1402,13 +1408,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->tgid = p->pid;
 	}
 
-	p->pdeath_signal = 0;
-	p->exit_state = 0;
-
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
 	p->dirty_paused_when = 0;
 
+	p->pdeath_signal = 0;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
@@ -1471,6 +1475,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			atomic_inc(&current->signal->sigcnt);
 			list_add_tail_rcu(&p->thread_group,
 					  &p->group_leader->thread_group);
+			list_add_tail_rcu(&p->thread_node,
+					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;
@@ -1644,7 +1650,7 @@ SYSCALL_DEFINE0(fork)
 	return do_fork(SIGCHLD, 0, 0, NULL, NULL);
 #else
 	/* can not support in nommu mode */
-	return(-EINVAL);
+	return -EINVAL;
 #endif
 }
 #endif
@@ -1652,7 +1658,7 @@ SYSCALL_DEFINE0(fork)
 #ifdef __ARCH_WANT_SYS_VFORK
 SYSCALL_DEFINE0(vfork)
 {
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, 
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
 			0, NULL, NULL);
 }
 #endif
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa1..aa6a8aa 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt);
 bool pm_freezing;
 bool pm_nosig_freezing;
 
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
 /* protects freezing and frozen transitions */
 static DEFINE_SPINLOCK(freezer_lock);
 
diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff019..44a1261 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,101 @@
 #include <linux/sched/rt.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
+#include <linux/bootmem.h>
 
 #include <asm/futex.h>
 
 #include "locking/rtmutex_common.h"
 
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       if (queue_empty())
+ *                                         return;
+ *   if (uval == val)
+ *      lock(hash_bucket(futex));
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0                                 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *
+ *   waiters++;
+ *   mb(); (A) <-- paired with -.
+ *                              |
+ *   lock(hash_bucket(futex));  |
+ *                              |
+ *   uval = *futex;             |
+ *                              |        *futex = newval;
+ *                              |        sys_futex(WAKE, futex);
+ *                              |          futex_wake(futex);
+ *                              |
+ *                              `------->  mb(); (B)
+ *   if (uval == val)
+ *     queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();                         if (waiters)
+ *                                           lock(hash_bucket(futex));
+ *                                           wake_waiters(futex);
+ *                                           unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ *	X = Y = 0
+ *
+ *	w[X]=1		w[Y]=1
+ *	MB		MB
+ *	r[Y]=y		r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
 
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+int __read_mostly futex_cmpxchg_enabled;
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -149,9 +236,41 @@ static const struct futex_q futex_q_init = {
 struct futex_hash_bucket {
 	spinlock_t lock;
 	struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
 
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+	atomic_inc(&key->private.mm->mm_count);
+	/*
+	 * Ensure futex_get_mm() implies a full barrier such that
+	 * get_futex_key() implies a full barrier. This is relied upon
+	 * as full barrier (B), see the ordering comment above.
+	 */
+	smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Tasks trying to enter the critical region are most likely
+	 * potential waiters that will be added to the plist. Ensure
+	 * that wakers won't miss to-be-slept tasks in the window between
+	 * the wait call and the actual plist_add.
+	 */
+	if (spin_is_locked(&hb->lock))
+		return true;
+	smp_rmb(); /* Make sure we check the lock state first */
+
+	return !plist_head_empty(&hb->chain);
+#else
+	return true;
+#endif
+}
 
 /*
  * We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +280,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
 	u32 hash = jhash2((u32*)&key->both.word,
 			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
 			  key->both.offset);
-	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
 /*
@@ -187,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode);
+		ihold(key->shared.inode); /* implies MB (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		atomic_inc(&key->private.mm->mm_count);
+		futex_get_mm(key); /* implies MB (B) */
 		break;
 	}
 }
@@ -264,7 +383,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);
+		get_futex_key_refs(key);  /* implies MB (B) */
 		return 0;
 	}
 
@@ -371,7 +490,7 @@ again:
 		key->shared.pgoff = basepage_index(page);
 	}
 
-	get_futex_key_refs(key);
+	get_futex_key_refs(key); /* implies MB (B) */
 
 out:
 	unlock_page(page_head);
@@ -598,13 +717,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex(&this->key, key)) {
 			/*
 			 * Another waiter already exists - bump up
@@ -986,7 +1102,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
@@ -998,10 +1113,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 		goto out;
 
 	hb = hash_futex(&key);
+
+	/* Make sure we really have tasks to wakeup */
+	if (!hb_waiters_pending(hb))
+		goto out_put_key;
+
 	spin_lock(&hb->lock);
-	head = &hb->chain;
 
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex (&this->key, &key)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1019,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	}
 
 	spin_unlock(&hb->lock);
+out_put_key:
 	put_futex_key(&key);
 out:
 	return ret;
@@ -1034,7 +1154,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret;
 
@@ -1082,9 +1201,7 @@ retry_private:
 		goto retry;
 	}
 
-	head = &hb1->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (match_futex (&this->key, &key1)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1097,10 +1214,8 @@ retry_private:
 	}
 
 	if (op_ret > 0) {
-		head = &hb2->chain;
-
 		op_ret = 0;
-		plist_for_each_entry_safe(this, next, head, list) {
+		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
 			if (match_futex (&this->key, &key2)) {
 				if (this->pi_state || this->rt_waiter) {
 					ret = -EINVAL;
@@ -1270,7 +1385,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	int drop_count = 0, task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head1;
 	struct futex_q *this, *next;
 	u32 curval2;
 
@@ -1393,8 +1507,7 @@ retry_private:
 		}
 	}
 
-	head1 = &hb1->chain;
-	plist_for_each_entry_safe(this, next, head1, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (task_count - nr_wake >= nr_requeue)
 			break;
 
@@ -1489,12 +1602,12 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock);
+	spin_lock(&hb->lock); /* implies MB (A) */
 	return hb;
 }
 
 static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
@@ -1867,7 +1980,7 @@ retry_private:
 	ret = get_futex_value_locked(&uval, uaddr);
 
 	if (ret) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
@@ -1881,7 +1994,7 @@ retry_private:
 	}
 
 	if (uval != val) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 		ret = -EWOULDBLOCK;
 	}
 
@@ -2029,7 +2142,7 @@ retry_private:
 			 * Task is exiting and we just wait for the
 			 * exit to complete.
 			 */
-			queue_unlock(&q, hb);
+			queue_unlock(hb);
 			put_futex_key(&q.key);
 			cond_resched();
 			goto retry;
@@ -2081,7 +2194,7 @@ retry_private:
 	goto out_put_key;
 
 out_unlock_put_key:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 out_put_key:
 	put_futex_key(&q.key);
@@ -2091,7 +2204,7 @@ out:
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 	ret = fault_in_user_writeable(uaddr);
 	if (ret)
@@ -2113,7 +2226,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
@@ -2153,9 +2265,7 @@ retry:
 	 * Ok, other tasks may need to be woken up - check waiters
 	 * and do the wakeup if necessary:
 	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (!match_futex (&this->key, &key))
 			continue;
 		ret = wake_futex_pi(uaddr, uval, this);
@@ -2316,6 +2426,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * code while we sleep on uaddr.
 	 */
 	debug_rt_mutex_init_waiter(&rt_waiter);
+	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&rt_waiter.tree_entry);
 	rt_waiter.task = NULL;
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
@@ -2734,8 +2846,21 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 static int __init futex_init(void)
 {
 	u32 curval;
-	int i;
+	unsigned int futex_shift;
+	unsigned long i;
+
+#if CONFIG_BASE_SMALL
+	futex_hashsize = 16;
+#else
+	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
 
+	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+					       futex_hashsize, 0,
+					       futex_hashsize < 256 ? HASH_SMALL : 0,
+					       &futex_shift, NULL,
+					       futex_hashsize, futex_hashsize);
+	futex_hashsize = 1UL << futex_shift;
 	/*
 	 * This will fail and we want it. Some arch implementations do
 	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
@@ -2749,7 +2874,7 @@ static int __init futex_init(void)
 	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
-	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+	for (i = 0; i < futex_hashsize; i++) {
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319b..0909436 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
@@ -1610,7 +1611,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 9328b80..0b9c169 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -37,7 +37,7 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
  */
 unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
 
-unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+int __read_mostly sysctl_hung_task_warnings = 10;
 
 static int __read_mostly did_panic;
 
@@ -98,7 +98,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 
 	if (!sysctl_hung_task_warnings)
 		return;
-	sysctl_hung_task_warnings--;
+
+	if (sysctl_hung_task_warnings > 0)
+		sysctl_hung_task_warnings--;
 
 	/*
 	 * Ok, the task did not get scheduled for more than 2 minutes,
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 4a1fef0..07cbdfe 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -40,6 +40,7 @@ config IRQ_EDGE_EOI_HANDLER
 # Generic configurable interrupt chip implementation
 config GENERIC_IRQ_CHIP
        bool
+       select IRQ_DOMAIN
 
 # Generic irq_domain hw <--> linux irq number translation
 config IRQ_DOMAIN
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index bd8e788..1ef0606 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -73,6 +73,51 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq,
 EXPORT_SYMBOL(devm_request_threaded_irq);
 
 /**
+ *	devm_request_any_context_irq - allocate an interrupt line for a managed device
+ *	@dev: device to request interrupt for
+ *	@irq: Interrupt line to allocate
+ *	@handler: Function to be called when the IRQ occurs
+ *	@thread_fn: function to be called in a threaded interrupt context. NULL
+ *		    for devices which handle everything in @handler
+ *	@irqflags: Interrupt type flags
+ *	@devname: An ascii name for the claiming device
+ *	@dev_id: A cookie passed back to the handler function
+ *
+ *	Except for the extra @dev argument, this function takes the
+ *	same arguments and performs the same function as
+ *	request_any_context_irq().  IRQs requested with this function will be
+ *	automatically freed on driver detach.
+ *
+ *	If an IRQ allocated with this function needs to be freed
+ *	separately, devm_free_irq() must be used.
+ */
+int devm_request_any_context_irq(struct device *dev, unsigned int irq,
+			      irq_handler_t handler, unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	struct irq_devres *dr;
+	int rc;
+
+	dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres),
+			  GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
+	if (rc) {
+		devres_free(dr);
+		return rc;
+	}
+
+	dr->irq = irq;
+	dr->dev_id = dev_id;
+	devres_add(dev, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_request_any_context_irq);
+
+/**
  *	devm_free_irq - free an interrupt
  *	@dev: device to free interrupt for
  *	@irq: Interrupt line to free
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302..8ab8e93 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -274,6 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
+EXPORT_SYMBOL(irq_to_desc);
 
 static void free_desc(unsigned int irq)
 {
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d0d8fca..60bafbe 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -932,6 +932,7 @@ static int kimage_load_segment(struct kimage *image,
  */
 struct kimage *kexec_image;
 struct kimage *kexec_crash_image;
+int kexec_load_disabled;
 
 static DEFINE_MUTEX(kexec_mutex);
 
@@ -942,7 +943,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
 	int result;
 
 	/* We only trust the superuser with rebooting the system. */
-	if (!capable(CAP_SYS_BOOT))
+	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
 		return -EPERM;
 
 	/*
@@ -1536,7 +1537,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	size_t r;
 
 	va_start(args, fmt);
-	r = vsnprintf(buf, sizeof(buf), fmt, args);
+	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
 	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
@@ -1680,6 +1681,7 @@ int kernel_kexec(void)
 	{
 		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
+		migrate_to_reboot_cpu();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index b086006..6b375af 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -239,7 +239,7 @@ static int ____call_usermodehelper(void *data)
 
 	commit_creds(new);
 
-	retval = do_execve(sub_info->path,
+	retval = do_execve(getname_kernel(sub_info->path),
 			   (const char __user *const __user *)sub_info->argv,
 			   (const char __user *const __user *)sub_info->envp);
 	if (!retval)
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 9659d38..d945a94 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -126,7 +126,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	return sprintf(buf, "%lx %x\n",
 		       paddr_vmcoreinfo_note(),
-		       (unsigned int)vmcoreinfo_max_size);
+		       (unsigned int)sizeof(vmcoreinfo_note));
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba75..eb8a547 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
 /*
  * Is this the address of a static object:
  */
+#ifdef __KERNEL__
 static int static_obj(void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
 	 */
 	return is_module_address(addr) || is_module_percpu_address(addr);
 }
+#endif
 
 /*
  * To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
+#ifdef __KERNEL__
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
 		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
 
 /*
  * Careful: only use this function if you are sure that
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443f..faf6f5b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+	if (!lock->owner)
+		DEBUG_LOCKS_WARN_ON(!lock->owner);
+	else
+		DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a..49b2ed3 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
 #include <linux/kallsyms.h>
 #include <linux/syscalls.h>
 #include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/fs.h>
 #include <linux/debug_locks.h>
 
@@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
 	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 }
 
@@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
 void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	memset(waiter, 0x11, sizeof(*waiter));
-	plist_node_init(&waiter->list_entry, MAX_PRIO);
-	plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
 	waiter->deadlock_task_pid = NULL;
 }
 
 void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec..2e960a2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
@@ -91,10 +92,107 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 }
 #endif
 
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+		     struct rt_mutex_waiter *right)
+{
+	if (left->prio < right->prio)
+		return 1;
+
+	/*
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 1 above,
+	 * then right waiter has a dl_prio() too.
+	 */
+	if (dl_prio(left->prio))
+		return (left->task->dl.deadline < right->task->dl.deadline);
+
+	return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &lock->waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		lock->waiters_leftmost = &waiter->tree_entry;
+
+	rb_link_node(&waiter->tree_entry, parent, link);
+	rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->tree_entry))
+		return;
+
+	if (lock->waiters_leftmost == &waiter->tree_entry)
+		lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+	rb_erase(&waiter->tree_entry, &lock->waiters);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &task->pi_waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+	rb_link_node(&waiter->pi_tree_entry, parent, link);
+	rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+		return;
+
+	if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+		task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+	rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
 /*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
  *
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
  * the waiter is not allowed to do priority boosting
  */
 int rt_mutex_getprio(struct task_struct *task)
@@ -102,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task)
 	if (likely(!task_has_pi_waiters(task)))
 		return task->normal_prio;
 
-	return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+	return min(task_top_pi_waiter(task)->prio,
 		   task->normal_prio);
 }
 
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+	if (likely(!task_has_pi_waiters(task)))
+		return NULL;
+
+	return task_top_pi_waiter(task)->task;
+}
+
 /*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
@@ -115,7 +221,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
 {
 	int prio = rt_mutex_getprio(task);
 
-	if (task->prio != prio)
+	if (task->prio != prio || dl_prio(prio))
 		rt_mutex_setprio(task, prio);
 }
 
@@ -233,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * When deadlock detection is off then we check, if further
 	 * priority adjustment is necessary.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+	if (!detect_deadlock && waiter->prio == task->prio)
 		goto out_unlock_pi;
 
 	lock = waiter->lock;
@@ -254,9 +360,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
+	waiter->prio = task->prio;
+	rt_mutex_enqueue(lock, waiter);
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +386,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
 	} else if (top_waiter == waiter) {
 		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 	}
 
@@ -355,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 * 3) it is top waiter
 	 */
 	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
 			if (!waiter || waiter != rt_mutex_top_waiter(lock))
 				return 0;
 		}
@@ -369,7 +473,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 
 		/* remove the queued waiter. */
 		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
+			rt_mutex_dequeue(lock, waiter);
 			task->pi_blocked_on = NULL;
 		}
 
@@ -379,8 +483,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		 */
 		if (rt_mutex_has_waiters(lock)) {
 			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			rt_mutex_enqueue_pi(task, top);
 		}
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
@@ -416,13 +519,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, task->prio);
-	plist_node_init(&waiter->pi_list_entry, task->prio);
+	waiter->prio = task->prio;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -433,8 +535,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
@@ -486,7 +588,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	rt_mutex_set_owner(lock, NULL);
 
@@ -510,7 +612,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
@@ -521,13 +623,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, waiter);
 
 		if (rt_mutex_has_waiters(lock)) {
 			struct rt_mutex_waiter *next;
 
 			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
+			rt_mutex_enqueue_pi(owner, next);
 		}
 		__rt_mutex_adjust_prio(owner);
 
@@ -537,8 +639,6 @@ static void remove_waiter(struct rt_mutex *lock,
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
 	if (!chain_walk)
 		return;
 
@@ -565,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
+	if (!waiter || (waiter->prio == task->prio &&
+			!dl_prio(task->prio))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -638,6 +739,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
+	RB_CLEAR_NODE(&waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&waiter.tree_entry);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -904,7 +1007,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 {
 	lock->owner = NULL;
 	raw_spin_lock_init(&lock->wait_lock);
-	plist_head_init(&lock->wait_list);
+	lock->waiters = RB_ROOT;
+	lock->waiters_leftmost = NULL;
 
 	debug_rt_mutex_init(lock, name);
 }
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c8..7431a9c 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
  * This is the control structure for tasks blocked on a rt_mutex,
  * which is allocated on the kernel stack on of the blocked task.
  *
- * @list_entry:		pi node to enqueue into the mutex waiters list
- * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @tree_entry:		pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  */
 struct rt_mutex_waiter {
-	struct plist_node	list_entry;
-	struct plist_node	pi_list_entry;
+	struct rb_node          tree_entry;
+	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -54,14 +54,15 @@ struct rt_mutex_waiter {
 	struct pid		*deadlock_task_pid;
 	struct rt_mutex		*deadlock_lock;
 #endif
+	int prio;
 };
 
 /*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
  */
 static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
 {
-	return !plist_head_empty(&lock->wait_list);
+	return !RB_EMPTY_ROOT(&lock->waiters);
 }
 
 static inline struct rt_mutex_waiter *
@@ -69,8 +70,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *w;
 
-	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
-			       list_entry);
+	w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+		     tree_entry);
 	BUG_ON(w->lock != lock);
 
 	return w;
@@ -78,14 +79,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 
 static inline int task_has_pi_waiters(struct task_struct *p)
 {
-	return !plist_head_empty(&p->pi_waiters);
+	return !RB_EMPTY_ROOT(&p->pi_waiters);
 }
 
 static inline struct rt_mutex_waiter *
 task_top_pi_waiter(struct task_struct *p)
 {
-	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
-				  pi_list_entry);
+	return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+			pi_tree_entry);
 }
 
 /*
diff --git a/kernel/module.c b/kernel/module.c
index f5a3b1e..d24fcf2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -815,10 +815,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	if (!(flags & O_NONBLOCK)) {
-		printk(KERN_WARNING
-		       "waiting module removal not supported: please upgrade");
-	}
+	if (!(flags & O_NONBLOCK))
+		pr_warn("waiting module removal not supported: please upgrade\n");
 
 	if (mutex_lock_interruptible(&module_mutex) != 0)
 		return -EINTR;
diff --git a/kernel/padata.c b/kernel/padata.c
index 2abd25d..161402f 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -112,7 +112,7 @@ int padata_do_parallel(struct padata_instance *pinst,
 
 	rcu_read_lock_bh();
 
-	pd = rcu_dereference(pinst->pd);
+	pd = rcu_dereference_bh(pinst->pd);
 
 	err = -EINVAL;
 	if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
diff --git a/kernel/panic.c b/kernel/panic.c
index c00b4ce..6d63003 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
 
 ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
diff --git a/kernel/params.c b/kernel/params.c
index c00d5b5..b00142e 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -227,17 +227,10 @@ int parse_args(const char *doing,
 }
 
 /* Lazy bastard, eh? */
-#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn)      	\
+#define STANDARD_PARAM_DEF(name, type, format, strtolfn)      		\
 	int param_set_##name(const char *val, const struct kernel_param *kp) \
 	{								\
-		tmptype l;						\
-		int ret;						\
-									\
-		ret = strtolfn(val, 0, &l);				\
-		if (ret < 0 || ((type)l != l))				\
-			return ret < 0 ? ret : -EINVAL;			\
-		*((type *)kp->arg) = l;					\
-		return 0;						\
+		return strtolfn(val, 0, (type *)kp->arg);		\
 	}								\
 	int param_get_##name(char *buffer, const struct kernel_param *kp) \
 	{								\
@@ -253,13 +246,13 @@ int parse_args(const char *doing,
 	EXPORT_SYMBOL(param_ops_##name)
 
 
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8);
+STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16);
+STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16);
+STANDARD_PARAM_DEF(int, int, "%i", kstrtoint);
+STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint);
+STANDARD_PARAM_DEF(long, long, "%li", kstrtol);
+STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
 {
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c7f31aa..3b89464 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -233,7 +233,8 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 
 /*
  * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_clock_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -260,30 +261,53 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 	return 0;
 }
 
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+				    const clockid_t which_clock,
+				    struct timespec *tp)
+{
+	int err = -EINVAL;
+	unsigned long long rtn;
+
+	if (CPUCLOCK_PERTHREAD(which_clock)) {
+		if (same_thread_group(tsk, current))
+			err = cpu_clock_sample(which_clock, tsk, &rtn);
+	} else {
+		unsigned long flags;
+		struct sighand_struct *sighand;
+
+		/*
+		 * while_each_thread() is not yet entirely RCU safe,
+		 * keep locking the group while sampling process
+		 * clock for now.
+		 */
+		sighand = lock_task_sighand(tsk, &flags);
+		if (!sighand)
+			return err;
+
+		if (tsk == current || thread_group_leader(tsk))
+			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+		unlock_task_sighand(tsk, &flags);
+	}
+
+	if (!err)
+		sample_to_timespec(which_clock, rtn, tp);
+
+	return err;
+}
+
 
 static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
-	int error = -EINVAL;
-	unsigned long long rtn;
+	int err = -EINVAL;
 
 	if (pid == 0) {
 		/*
 		 * Special case constant value for our own clocks.
 		 * We don't have to do any lookup to find ourselves.
 		 */
-		if (CPUCLOCK_PERTHREAD(which_clock)) {
-			/*
-			 * Sampling just ourselves we can do with no locking.
-			 */
-			error = cpu_clock_sample(which_clock,
-						 current, &rtn);
-		} else {
-			read_lock(&tasklist_lock);
-			error = cpu_clock_sample_group(which_clock,
-						       current, &rtn);
-			read_unlock(&tasklist_lock);
-		}
+		err = posix_cpu_clock_get_task(current, which_clock, tp);
 	} else {
 		/*
 		 * Find the given PID, and validate that the caller
@@ -292,29 +316,12 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 		struct task_struct *p;
 		rcu_read_lock();
 		p = find_task_by_vpid(pid);
-		if (p) {
-			if (CPUCLOCK_PERTHREAD(which_clock)) {
-				if (same_thread_group(p, current)) {
-					error = cpu_clock_sample(which_clock,
-								 p, &rtn);
-				}
-			} else {
-				read_lock(&tasklist_lock);
-				if (thread_group_leader(p) && p->sighand) {
-					error =
-					    cpu_clock_sample_group(which_clock,
-							           p, &rtn);
-				}
-				read_unlock(&tasklist_lock);
-			}
-		}
+		if (p)
+			err = posix_cpu_clock_get_task(p, which_clock, tp);
 		rcu_read_unlock();
 	}
 
-	if (error)
-		return error;
-	sample_to_timespec(which_clock, rtn, tp);
-	return 0;
+	return err;
 }
 
 
@@ -371,36 +378,40 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
  */
 static int posix_cpu_timer_del(struct k_itimer *timer)
 {
-	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
+	unsigned long flags;
+	struct sighand_struct *sighand;
+	struct task_struct *p = timer->it.cpu.task;
 
-	if (likely(p != NULL)) {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
-			/*
-			 * We raced with the reaping of the task.
-			 * The deletion should have cleared us off the list.
-			 */
-			BUG_ON(!list_empty(&timer->it.cpu.entry));
-		} else {
-			spin_lock(&p->sighand->siglock);
-			if (timer->it.cpu.firing)
-				ret = TIMER_RETRY;
-			else
-				list_del(&timer->it.cpu.entry);
-			spin_unlock(&p->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
+	WARN_ON_ONCE(p == NULL);
 
-		if (!ret)
-			put_task_struct(p);
+	/*
+	 * Protect against sighand release/switch in exit/exec and process/
+	 * thread timer list entry concurrent read/writes.
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	if (unlikely(sighand == NULL)) {
+		/*
+		 * We raced with the reaping of the task.
+		 * The deletion should have cleared us off the list.
+		 */
+		WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+	} else {
+		if (timer->it.cpu.firing)
+			ret = TIMER_RETRY;
+		else
+			list_del(&timer->it.cpu.entry);
+
+		unlock_task_sighand(p, &flags);
 	}
 
+	if (!ret)
+		put_task_struct(p);
+
 	return ret;
 }
 
-static void cleanup_timers_list(struct list_head *head,
-				unsigned long long curr)
+static void cleanup_timers_list(struct list_head *head)
 {
 	struct cpu_timer_list *timer, *next;
 
@@ -414,16 +425,11 @@ static void cleanup_timers_list(struct list_head *head,
  * time for later timer_gettime calls to return.
  * This must be called with the siglock held.
  */
-static void cleanup_timers(struct list_head *head,
-			   cputime_t utime, cputime_t stime,
-			   unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
 {
-
-	cputime_t ptime = utime + stime;
-
-	cleanup_timers_list(head, cputime_to_expires(ptime));
-	cleanup_timers_list(++head, cputime_to_expires(utime));
-	cleanup_timers_list(++head, sum_exec_runtime);
+	cleanup_timers_list(head);
+	cleanup_timers_list(++head);
+	cleanup_timers_list(++head);
 }
 
 /*
@@ -433,41 +439,14 @@ static void cleanup_timers(struct list_head *head,
  */
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
-	cputime_t utime, stime;
-
 	add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
 						sizeof(unsigned long long));
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->cpu_timers,
-		       utime, stime, tsk->se.sum_exec_runtime);
+	cleanup_timers(tsk->cpu_timers);
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, stime;
-
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->signal->cpu_timers,
-		       utime + sig->utime, stime + sig->stime,
-		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
-}
-
-static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
-{
-	struct cpu_timer_list *timer = &itimer->it.cpu;
-
-	/*
-	 * That's all for this thread or process.
-	 * We leave our residual in expires to be reported.
-	 */
-	put_task_struct(timer->task);
-	timer->task = NULL;
-	if (timer->expires < now) {
-		timer->expires = 0;
-	} else {
-		timer->expires -= now;
-	}
+	cleanup_timers(tsk->signal->cpu_timers);
 }
 
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
@@ -477,8 +456,7 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 
 /*
  * Insert the timer on the appropriate list before any timers that
- * expire later.  This must be called with the tasklist_lock held
- * for reading, interrupts disabled and p->sighand->siglock taken.
+ * expire later.  This must be called with the sighand lock held.
  */
 static void arm_timer(struct k_itimer *timer)
 {
@@ -569,7 +547,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
 
 /*
  * Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_timer_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -608,7 +587,8 @@ static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
  */
 static void posix_cpu_timer_kick_nohz(void)
 {
-	schedule_work(&nohz_kick_work);
+	if (context_tracking_is_enabled())
+		schedule_work(&nohz_kick_work);
 }
 
 bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
@@ -631,43 +611,39 @@ static inline void posix_cpu_timer_kick_nohz(void) { }
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			       struct itimerspec *new, struct itimerspec *old)
 {
+	unsigned long flags;
+	struct sighand_struct *sighand;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * Timer refers to a dead task's clock.
-		 */
-		return -ESRCH;
-	}
+	WARN_ON_ONCE(p == NULL);
 
 	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
 
-	read_lock(&tasklist_lock);
 	/*
-	 * We need the tasklist_lock to protect against reaping that
-	 * clears p->sighand.  If p has just been reaped, we can no
+	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
+	 * and p->signal->cpu_timers read/write in arm_timer()
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	/*
+	 * If p has just been reaped, we can no
 	 * longer get any information about it at all.
 	 */
-	if (unlikely(p->sighand == NULL)) {
-		read_unlock(&tasklist_lock);
-		put_task_struct(p);
-		timer->it.cpu.task = NULL;
+	if (unlikely(sighand == NULL)) {
 		return -ESRCH;
 	}
 
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
-	spin_lock(&p->sighand->siglock);
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
 		timer->it.cpu.firing = -1;
@@ -724,12 +700,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
-		spin_unlock(&p->sighand->siglock);
-		read_unlock(&tasklist_lock);
+		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
 		new_expires += val;
 	}
 
@@ -743,9 +718,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		arm_timer(timer);
 	}
 
-	spin_unlock(&p->sighand->siglock);
-	read_unlock(&tasklist_lock);
-
+	unlock_task_sighand(p, &flags);
 	/*
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
@@ -787,7 +760,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
-	int clear_dead;
+
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Easy part: convert the reload time.
@@ -800,52 +774,34 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		return;
 	}
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * This task already died and the timer will never fire.
-		 * In this case, expires is actually the dead value.
-		 */
-	dead:
-		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
-				   &itp->it_value);
-		return;
-	}
-
 	/*
 	 * Sample the clock to take the difference with the expiry time.
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
-		clear_dead = p->exit_state;
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		struct sighand_struct *sighand;
+		unsigned long flags;
+
+		/*
+		 * Protect against sighand release/switch in exit/exec and
+		 * also make timer sampling safe if it ends up calling
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 * Call the timer disarmed, nothing else to do.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = NULL;
 			timer->it.cpu.expires = 0;
-			read_unlock(&tasklist_lock);
-			goto dead;
+			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+					   &itp->it_value);
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead = (unlikely(p->exit_state) &&
-				      thread_group_empty(p));
+			unlock_task_sighand(p, &flags);
 		}
-		read_unlock(&tasklist_lock);
-	}
-
-	if (unlikely(clear_dead)) {
-		/*
-		 * We've noticed that the thread is dead, but
-		 * not yet reaped.  Take this opportunity to
-		 * drop our task ref.
-		 */
-		clear_dead_task(timer, now);
-		goto dead;
 	}
 
 	if (now < timer->it.cpu.expires) {
@@ -1059,14 +1015,12 @@ static void check_process_timers(struct task_struct *tsk,
  */
 void posix_cpu_timer_schedule(struct k_itimer *timer)
 {
+	struct sighand_struct *sighand;
+	unsigned long flags;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long now;
 
-	if (unlikely(p == NULL))
-		/*
-		 * The task was cleaned up already, no future firings.
-		 */
-		goto out;
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1074,49 +1028,45 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		if (unlikely(p->exit_state)) {
-			clear_dead_task(timer, now);
+		if (unlikely(p->exit_state))
+			goto out;
+
+		/* Protect timer list r/w in arm_timer() */
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
 			goto out;
-		}
-		read_lock(&tasklist_lock); /* arm_timer needs it.  */
-		spin_lock(&p->sighand->siglock);
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		/*
+		 * Protect arm_timer() and timer sampling in case of call to
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = p = NULL;
 			timer->it.cpu.expires = 0;
-			goto out_unlock;
+			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			/*
-			 * We've noticed that the thread is dead, but
-			 * not yet reaped.  Take this opportunity to
-			 * drop our task ref.
-			 */
-			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead_task(timer, now);
-			goto out_unlock;
+			unlock_task_sighand(p, &flags);
+			/* Optimizations: if the process is dying, no need to rearm */
+			goto out;
 		}
-		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		/* Leave the tasklist_lock locked for the call below.  */
+		/* Leave the sighand locked for the call below.  */
 	}
 
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 	arm_timer(timer);
-	spin_unlock(&p->sighand->siglock);
-
-out_unlock:
-	read_unlock(&tasklist_lock);
+	unlock_task_sighand(p, &flags);
 
+	/* Kick full dynticks CPUs in case they need to tick on the new timer */
+	posix_cpu_timer_kick_nohz();
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1200,7 +1150,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1256,13 +1206,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 			cpu_timer_fire(timer);
 		spin_unlock(&timer->it_lock);
 	}
-
-	/*
-	 * In case some timers were rescheduled after the queue got emptied,
-	 * wake up full dynticks CPUs.
-	 */
-	if (tsk->signal->cputimer.running)
-		posix_cpu_timer_kick_nohz();
 }
 
 /*
@@ -1274,7 +1217,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 {
 	unsigned long long now;
 
-	BUG_ON(clock_idx == CPUCLOCK_SCHED);
+	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c
index d09dd10..9a58bc2 100644
--- a/kernel/power/block_io.c
+++ b/kernel/power/block_io.c
@@ -32,7 +32,7 @@ static int submit(int rw, struct block_device *bdev, sector_t sector,
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
-	bio->bi_sector = sector;
+	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = bdev;
 	bio->bi_end_io = end_swap_bio_read;
 
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 463aa673..eacb8bd 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -81,6 +81,7 @@ void pm_vt_switch_unregister(struct device *dev)
 	list_for_each_entry(tmp, &pm_vt_switch_list, head) {
 		if (tmp->dev == dev) {
 			list_del(&tmp->head);
+			kfree(tmp);
 			break;
 		}
 	}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 0121dab..37170d4 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -82,6 +82,7 @@ void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 
 	unlock_system_sleep();
 }
+EXPORT_SYMBOL_GPL(hibernation_set_ops);
 
 static bool entering_platform_hibernation;
 
@@ -293,10 +294,10 @@ static int create_image(int platform_mode)
 			error);
 	/* Restore control flow magically appears here */
 	restore_processor_state();
-	if (!in_suspend) {
+	if (!in_suspend)
 		events_check_enabled = false;
-		platform_leave(platform_mode);
-	}
+
+	platform_leave(platform_mode);
 
  Power_up:
 	syscore_resume();
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b38109e..d9f61a1 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -637,7 +637,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
 		BUG_ON(!region);
 	} else
 		/* This allocation cannot fail */
-		region = alloc_bootmem(sizeof(struct nosave_region));
+		region = memblock_virt_alloc(sizeof(struct nosave_region), 0);
 	region->start_pfn = start_pfn;
 	region->end_pfn = end_pfn;
 	list_add_tail(&region->list, &nosave_regions);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index be7c86b..b1d255f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -757,14 +757,10 @@ void __init setup_log_buf(int early)
 		return;
 
 	if (early) {
-		unsigned long mem;
-
-		mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
-		if (!mem)
-			return;
-		new_log_buf = __va(mem);
+		new_log_buf =
+			memblock_virt_alloc(new_log_buf_len, PAGE_SIZE);
 	} else {
-		new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
+		new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, 0);
 	}
 
 	if (unlikely(!new_log_buf)) {
@@ -1599,10 +1595,13 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 * either merge it with the current buffer and flush, or if
 		 * there was a race with interrupts (prefix == true) then just
 		 * flush it out and store this line separately.
+		 * If the preceding printk was from a different task and missed
+		 * a newline, flush and append the newline.
 		 */
-		if (cont.len && cont.owner == current) {
-			if (!(lflags & LOG_PREFIX))
-				stored = cont_add(facility, level, text, text_len);
+		if (cont.len) {
+			if (cont.owner == current && !(lflags & LOG_PREFIX))
+				stored = cont_add(facility, level, text,
+						  text_len);
 			cont_flush(LOG_NEWLINE);
 		}
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7859a0a..79c3877 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -96,19 +96,22 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-extern void kfree(const void *);
+void kfree(const void *);
 
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
 
+	rcu_lock_acquire(&rcu_callback_map);
 	if (__is_kfree_rcu_offset(offset)) {
 		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
 		kfree((void *)head - offset);
+		rcu_lock_release(&rcu_callback_map);
 		return 1;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
 		head->func(head);
+		rcu_lock_release(&rcu_callback_map);
 		return 0;
 	}
 }
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb..3318d82 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -363,6 +363,29 @@ static void srcu_flip(struct srcu_struct *sp)
 /*
  * Enqueue an SRCU callback on the specified srcu_struct structure,
  * initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section.  On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu().  It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
  */
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head))
@@ -459,7 +482,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  * Note that it is illegal to call synchronize_srcu() from the corresponding
  * SRCU read-side critical section; doing so will result in deadlock.
  * However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu().  In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section.  Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu().  This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
@@ -476,12 +522,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  * Wait for an SRCU grace period to elapse, but be more aggressive about
  * spinning rather than blocking when waiting.
  *
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock.  However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
@@ -491,6 +533,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
  */
 void srcu_barrier(struct srcu_struct *sp)
 {
diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
index 3929cd4..732f8ae 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/torture.c
@@ -139,8 +139,6 @@ MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
 #define VERBOSE_PRINTK_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
 
-static char printk_buf[4096];
-
 static int nrealreaders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
@@ -376,7 +374,7 @@ struct rcu_torture_ops {
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
-	int (*stats)(char *page);
+	void (*stats)(char *page);
 	int irq_capable;
 	int can_boost;
 	const char *name;
@@ -578,21 +576,19 @@ static void srcu_torture_barrier(void)
 	srcu_barrier(&srcu_ctl);
 }
 
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
-	cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+	page += sprintf(page, "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+		page += sprintf(page, " %d(%lu,%lu)", cpu,
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
 	}
-	cnt += sprintf(&page[cnt], "\n");
-	return cnt;
+	sprintf(page, "\n");
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -1052,10 +1048,9 @@ rcu_torture_reader(void *arg)
 /*
  * Create an RCU-torture statistics message in the specified buffer.
  */
-static int
+static void
 rcu_torture_printk(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1071,8 +1066,8 @@ rcu_torture_printk(char *page)
 		if (pipesummary[i] != 0)
 			break;
 	}
-	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page,
 		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
@@ -1080,53 +1075,52 @@ rcu_torture_printk(char *page)
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
 		       atomic_read(&n_rcu_torture_free));
-	cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
 		       n_rcu_torture_boost_rterror);
-	cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page,
 		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
 		       n_online_successes, n_online_attempts,
 		       n_offline_successes, n_offline_attempts,
 		       min_online, max_online,
 		       min_offline, max_offline,
 		       sum_online, sum_offline, HZ);
-	cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+	page += sprintf(page, "barrier: %ld/%ld:%ld",
 		       n_barrier_successes,
 		       n_barrier_attempts,
 		       n_rcu_torture_barrier_error);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_barrier_error != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
 	    n_rcu_torture_boost_failure != 0 ||
 	    i > 1) {
-		cnt += sprintf(&page[cnt], "!!! ");
+		page += sprintf(page, "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
 	}
-	cnt += sprintf(&page[cnt], "Reader Pipe: ");
+	page += sprintf(page, "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Reader Batch: ");
+		page += sprintf(page, " %ld", pipesummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Reader Batch: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+		page += sprintf(page, " %ld", batchsummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Free-Block Circulation: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		cnt += sprintf(&page[cnt], " %d",
+		page += sprintf(page, " %d",
 			       atomic_read(&rcu_torture_wcount[i]));
 	}
-	cnt += sprintf(&page[cnt], "\n");
+	page += sprintf(page, "\n");
 	if (cur_ops->stats)
-		cnt += cur_ops->stats(&page[cnt]);
-	return cnt;
+		cur_ops->stats(page);
 }
 
 /*
@@ -1140,10 +1134,17 @@ rcu_torture_printk(char *page)
 static void
 rcu_torture_stats_print(void)
 {
-	int cnt;
+	int size = nr_cpu_ids * 200 + 8192;
+	char *buf;
 
-	cnt = rcu_torture_printk(printk_buf);
-	pr_alert("%s", printk_buf);
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		pr_err("rcu-torture: Out of memory, need: %d", size);
+		return;
+	}
+	rcu_torture_printk(buf);
+	pr_alert("%s", buf);
+	kfree(buf);
 }
 
 /*
@@ -1578,6 +1579,7 @@ static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
 	bool lastphase = 0;
+	bool newphase;
 	struct rcu_head rcu;
 
 	init_rcu_head_on_stack(&rcu);
@@ -1585,10 +1587,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 	set_user_nice(current, 19);
 	do {
 		wait_event(barrier_cbs_wq[myid],
-			   barrier_phase != lastphase ||
+			   (newphase =
+			    ACCESS_ONCE(barrier_phase)) != lastphase ||
 			   kthread_should_stop() ||
 			   fullstop != FULLSTOP_DONTSTOP);
-		lastphase = barrier_phase;
+		lastphase = newphase;
 		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
@@ -1625,7 +1628,7 @@ static int rcu_torture_barrier(void *arg)
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
 		n_barrier_attempts++;
-		cur_ops->cb_barrier();
+		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
 			WARN_ON_ONCE(1);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd08198..b3d116c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -369,6 +369,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
+	struct rcu_state *rsp;
+	struct rcu_data *rdp;
+
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
@@ -380,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		do_nocb_deferred_wakeup(rdp);
+	}
 	rcu_prepare_for_idle(smp_processor_id());
 	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
 	smp_mb__before_atomic_inc();  /* See above. */
@@ -411,11 +418,12 @@ static void rcu_eqs_enter(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
-	else
+		rcu_eqs_enter_common(rdtp, oldval, user);
+	} else {
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	rcu_eqs_enter_common(rdtp, oldval, user);
+	}
 }
 
 /**
@@ -533,11 +541,12 @@ static void rcu_eqs_exit(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(oldval < 0);
-	if (oldval & DYNTICK_TASK_NEST_MASK)
+	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
+	} else {
 		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_eqs_exit_common(rdtp, oldval, user);
+		rcu_eqs_exit_common(rdtp, oldval, user);
+	}
 }
 
 /**
@@ -716,7 +725,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	bool ret;
 
 	if (in_nmi())
-		return 1;
+		return true;
 	preempt_disable();
 	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
@@ -755,6 +764,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 }
 
 /*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -812,16 +827,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 */
 	rcu_kick_nohz_cpu(rdp->cpu);
 
+	/*
+	 * Alternatively, the CPU might be running in the kernel
+	 * for an extended period of time without a quiescent state.
+	 * Attempt to force the CPU through the scheduler to gain the
+	 * needed quiescent state, but only if the grace period has gone
+	 * on for an uncommonly long time.  If there are many stuck CPUs,
+	 * we will beat on the first one until it gets unstuck, then move
+	 * to the next.  Only do this for the primary flavor of RCU.
+	 */
+	if (rdp->rsp == rcu_state &&
+	    ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+		rdp->rsp->jiffies_resched += 5;
+		resched_cpu(rdp->cpu);
+	}
+
 	return 0;
 }
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	unsigned long j = ACCESS_ONCE(jiffies);
+	unsigned long j1;
 
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
-	rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+	j1 = rcu_jiffies_till_stall_check();
+	rsp->jiffies_stall = j + j1;
+	rsp->jiffies_resched = j + j1 / 2;
 }
 
 /*
@@ -1133,8 +1166,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root)
+	if (rnp != rnp_root) {
 		raw_spin_lock(&rnp_root->lock);
+		smp_mb__after_unlock_lock();
+	}
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1354,6 +1389,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		local_irq_restore(flags);
 		return;
 	}
+	smp_mb__after_unlock_lock();
 	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1368,6 +1404,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	if (rsp->gp_flags == 0) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1446,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1501,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
@@ -1480,6 +1519,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1505,16 +1545,19 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			__note_gp_changes(rsp, rnp, rdp);
+		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1553,6 +1596,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
+			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched();
@@ -1582,6 +1626,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					(!ACCESS_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
+			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
 			if (!ACCESS_ONCE(rnp->qsmask) &&
 			    !rcu_preempt_blocked_readers_cgp(rnp))
@@ -1749,6 +1794,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -1778,6 +1824,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
 	    rnp->completed == rnp->gpnum) {
 
@@ -1901,13 +1948,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
  * Adopt the RCU callbacks from the specified rcu_state structure's
  * orphanage.  The caller must hold the ->orphan_lock.
  */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 {
 	int i;
 	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -1986,12 +2033,13 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp);
+	rcu_adopt_orphan_cbs(rsp, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
@@ -2202,6 +2250,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		if (!rcu_gp_in_progress(rsp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
@@ -2231,6 +2280,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rnp = rcu_get_root(rsp);
 	if (rnp->qsmask == 0) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 	}
 }
@@ -2263,6 +2313,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2303,6 +2354,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	/* If there are callbacks ready, invoke them. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
 		invoke_rcu_callbacks(rsp, rdp);
+
+	/* Do any needed deferred wakeups of rcuo kthreads. */
+	do_nocb_deferred_wakeup(rdp);
 }
 
 /*
@@ -2378,6 +2432,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
 			raw_spin_lock(&rnp_root->lock);
+			smp_mb__after_unlock_lock();
 			rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 		} else {
@@ -2437,7 +2492,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy);
+		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
 		WARN_ON_ONCE(offline);
 		/* _call_rcu() is illegal on offline CPU; leak the callback. */
 		local_irq_restore(flags);
@@ -2757,6 +2812,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* Check for CPU stalls, if enabled. */
 	check_cpu_stall(rsp, rdp);
 
+	/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+	if (rcu_nohz_full_cpu(rsp))
+		return 0;
+
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
 	    rdp->qs_pending && !rdp->passed_quiesce) {
@@ -2790,6 +2849,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* Does this CPU need a deferred NOCB wakeup? */
+	if (rcu_nocb_need_deferred_wakeup(rdp)) {
+		rdp->n_rp_nocb_defer_wakeup++;
+		return 1;
+	}
+
 	/* nothing to do */
 	rdp->n_rp_need_nothing++;
 	return 0;
@@ -3214,9 +3279,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	for (i = rcu_num_lvls - 1; i > 0; i--)
+	rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+	for (i = rcu_num_lvls - 2; i >= 0; i--)
 		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
-	rsp->levelspread[0] = rcu_fanout_leaf;
 }
 #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
@@ -3346,6 +3411,8 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
+	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
 	 * Compute number of nodes that can be handled an rcu_node tree
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957..8c19873 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -317,6 +317,7 @@ struct rcu_data {
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
 	unsigned long n_rp_gp_started;
+	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
 	/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
+	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -453,6 +455,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
+	unsigned long jiffies_resched;		/* Time at which to resched */
+						/*  a reluctant CPU. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	const char *name;			/* Name of structure. */
@@ -548,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy);
+			    bool lazy, unsigned long flags);
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-				      struct rcu_data *rdp);
+				      struct rcu_data *rdp,
+				      unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
@@ -564,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 				  unsigned long maxj);
 static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 08a7652..6e2ef4b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -361,10 +363,14 @@ void rcu_read_unlock_special(struct task_struct *t)
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
 		rcu_preempt_qs(smp_processor_id());
+		if (!t->rcu_read_unlock_special) {
+			local_irq_restore(flags);
+			return;
+		}
 	}
 
-	/* Hardware IRQ handlers cannot block. */
-	if (in_irq() || in_serving_softirq()) {
+	/* Hardware IRQ handlers cannot block, complain if they get here. */
+	if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -381,6 +387,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		for (;;) {
 			rnp = t->rcu_blocked_node;
 			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
+			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +612,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	while (!list_empty(lp)) {
 		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
 		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		list_del(&t->rcu_node_entry);
 		t->rcu_blocked_node = rnp_root;
 		list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +637,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	 * in this case.
 	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	smp_mb__after_unlock_lock();
 	if (rnp_root->boost_tasks != NULL &&
 	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
 	    rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +781,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 	unsigned long mask;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -779,14 +789,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			if (wake)
+			if (wake) {
+				smp_mb(); /* EGP done before wake_up(). */
 				wake_up(&sync_rcu_preempt_exp_wq);
+			}
 			break;
 		}
 		mask = rnp->grpmask;
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		rnp->expmask &= ~mask;
 	}
 }
@@ -806,6 +819,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (list_empty(&rnp->blkd_tasks)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
@@ -886,6 +900,7 @@ void synchronize_rcu_expedited(void)
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rnp->expmask = rnp->qsmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
@@ -1191,6 +1206,7 @@ static int rcu_boost(struct rcu_node *rnp)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1393,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1786,7 @@ static void rcu_prepare_for_idle(int cpu)
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
@@ -1852,6 +1870,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 
 	/* Wait for callbacks from earlier instance to complete. */
 	wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+	smp_mb(); /* Ensure callback reuse happens after callback invocation. */
 
 	/*
 	 * Prevent premature wakeup: ensure that all increments happen
@@ -2101,7 +2120,8 @@ bool rcu_is_nocb_cpu(int cpu)
 static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 				    struct rcu_head *rhp,
 				    struct rcu_head **rhtp,
-				    int rhcount, int rhcount_lazy)
+				    int rhcount, int rhcount_lazy,
+				    unsigned long flags)
 {
 	int len;
 	struct rcu_head **old_rhpp;
@@ -2122,9 +2142,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
-		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+		if (!irqs_disabled_flags(flags)) {
+			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmpty"));
+		} else {
+			rdp->nocb_defer_wakeup = true;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmptyIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = 0;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2145,12 +2172,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
  * "rcuo" kthread can find it.
  */
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return 0;
-	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
 					 (unsigned long)rhp->func,
@@ -2168,7 +2195,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * not a no-CBs CPU.
  */
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	long ql = rsp->qlen;
 	long qll = rsp->qlen_lazy;
@@ -2182,14 +2210,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
 	if (rsp->orphan_donelist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
-					rsp->orphan_donetail, ql, qll);
+					rsp->orphan_donetail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_donelist = NULL;
 		rsp->orphan_donetail = &rsp->orphan_donelist;
 	}
 	if (rsp->orphan_nxtlist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
-					rsp->orphan_nxttail, ql, qll);
+					rsp->orphan_nxttail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_nxtlist = NULL;
 		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2209,6 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	c = rcu_start_future_gp(rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
@@ -2250,6 +2279,7 @@ static int rcu_nocb_kthread(void *arg)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("Sleep"));
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+			/* Memory barrier provide by xchg() below. */
 		} else if (firsttime) {
 			firsttime = 0;
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
@@ -2310,6 +2340,22 @@ static int rcu_nocb_kthread(void *arg)
 	return 0;
 }
 
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+	if (!rcu_nocb_need_deferred_wakeup(rdp))
+		return;
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+	wake_up(&rdp->nocb_wq);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
@@ -2365,13 +2411,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 }
 
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 	return 0;
 }
 
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	return 0;
 }
@@ -2380,6 +2427,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 }
@@ -2829,3 +2885,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
 }
 
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_cpu(smp_processor_id()) &&
+	    (!rcu_gp_in_progress(rsp) ||
+	     ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+		return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+	return 0;
+}
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797..4def475 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);
-	seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+	seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
 		   rdp->n_rp_gp_completed,
 		   rdp->n_rp_gp_started,
+		   rdp->n_rp_nocb_defer_wakeup,
 		   rdp->n_rp_need_nothing);
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff..c54609f 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -128,6 +128,11 @@ struct lockdep_map rcu_sched_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
 int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active && debug_locks &&
@@ -195,17 +200,6 @@ void wait_rcu_gp(call_rcu_func_t crf)
 }
 EXPORT_SYMBOL_GPL(wait_rcu_gp);
 
-#ifdef CONFIG_PROVE_RCU
-/*
- * wrapper function to avoid #include problems.
- */
-int rcu_my_thread_group_empty(void)
-{
-	return thread_group_empty(current);
-}
-EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 static inline void debug_init_rcu_head(struct rcu_head *head)
 {
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b34..662c83f 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
 {
 	/* The boot cpu is always logical cpu 0 */
 	int cpu = reboot_cpu;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7b62140..9a95c8c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,9 +11,10 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae144..43c2bcc 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
  * at 0 on boot (but people really shouldn't rely on that).
  *
  * cpu_clock(i)       -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
  * local_clock()      -- is cpu_clock() on the current cpu.
  *
+ * sched_clock_cpu(i)
+ *
  * How:
  *
  * The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
  */
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
@@ -66,6 +58,8 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -82,7 +76,52 @@ EXPORT_SYMBOL_GPL(sched_clock);
 __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+static int __sched_clock_stable_early;
+
+int sched_clock_stable(void)
+{
+	return static_key_false(&__sched_clock_stable);
+}
+
+static void __set_sched_clock_stable(void)
+{
+	if (!sched_clock_stable())
+		static_key_slow_inc(&__sched_clock_stable);
+}
+
+void set_sched_clock_stable(void)
+{
+	__sched_clock_stable_early = 1;
+
+	smp_mb(); /* matches sched_clock_init() */
+
+	if (!sched_clock_running)
+		return;
+
+	__set_sched_clock_stable();
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+	/* XXX worry about clock continuity */
+	if (sched_clock_stable())
+		static_key_slow_dec(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+	__sched_clock_stable_early = 0;
+
+	smp_mb(); /* matches sched_clock_init() */
+
+	if (!sched_clock_running)
+		return;
+
+	schedule_work(&sched_clock_work);
+}
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -116,6 +155,20 @@ void sched_clock_init(void)
 	}
 
 	sched_clock_running = 1;
+
+	/*
+	 * Ensure that it is impossible to not do a static_key update.
+	 *
+	 * Either {set,clear}_sched_clock_stable() must see sched_clock_running
+	 * and do the update, or we must see their __sched_clock_stable_early
+	 * and do the update, or both.
+	 */
+	smp_mb(); /* matches {set,clear}_sched_clock_stable() */
+
+	if (__sched_clock_stable_early)
+		__set_sched_clock_stable();
+	else
+		__clear_sched_clock_stable(NULL);
 }
 
 /*
@@ -242,20 +295,20 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd;
 	u64 clock;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return sched_clock();
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
+	preempt_disable();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
+	preempt_enable();
 
 	return clock;
 }
@@ -265,7 +318,7 @@ void sched_clock_tick(void)
 	struct sched_clock_data *scd;
 	u64 now, now_gtod;
 
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return;
 
 	if (unlikely(!sched_clock_running))
@@ -316,14 +369,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
  */
 u64 cpu_clock(int cpu)
 {
-	u64 clock;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	clock = sched_clock_cpu(cpu);
-	local_irq_restore(flags);
+	if (!sched_clock_stable())
+		return sched_clock_cpu(cpu);
 
-	return clock;
+	return sched_clock();
 }
 
 /*
@@ -335,14 +384,10 @@ u64 cpu_clock(int cpu)
  */
 u64 local_clock(void)
 {
-	u64 clock;
-	unsigned long flags;
+	if (!sched_clock_stable())
+		return sched_clock_cpu(raw_smp_processor_id());
 
-	local_irq_save(flags);
-	clock = sched_clock_cpu(smp_processor_id());
-	local_irq_restore(flags);
-
-	return clock;
+	return sched_clock();
 }
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +407,12 @@ u64 sched_clock_cpu(int cpu)
 
 u64 cpu_clock(int cpu)
 {
-	return sched_clock_cpu(cpu);
+	return sched_clock();
 }
 
 u64 local_clock(void)
 {
-	return sched_clock_cpu(0);
+	return sched_clock();
 }
 
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e85cda2..b46131e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -296,8 +296,6 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-
-
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -899,7 +897,9 @@ static inline int normal_prio(struct task_struct *p)
 {
 	int prio;
 
-	if (task_has_rt_policy(p))
+	if (task_has_dl_policy(p))
+		prio = MAX_DL_PRIO-1;
+	else if (task_has_rt_policy(p))
 		prio = MAX_RT_PRIO-1 - p->rt_priority;
 	else
 		prio = __normal_prio(p);
@@ -945,7 +945,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		if (prev_class->switched_from)
 			prev_class->switched_from(rq, p);
 		p->sched_class->switched_to(rq, p);
-	} else if (oldprio != p->prio)
+	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
@@ -1108,6 +1108,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 	if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
 		goto out;
 
+	trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
 	ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
 
 out:
@@ -1499,8 +1500,7 @@ void scheduler_ipi(void)
 	 * TIF_NEED_RESCHED remotely (for the first time) will also send
 	 * this IPI.
 	 */
-	if (tif_need_resched())
-		set_preempt_need_resched();
+	preempt_fold_need_resched();
 
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
@@ -1717,6 +1717,13 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
+	RB_CLEAR_NODE(&p->dl.rb_node);
+	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	p->dl.dl_runtime = p->dl.runtime = 0;
+	p->dl.dl_deadline = p->dl.deadline = 0;
+	p->dl.dl_period = 0;
+	p->dl.flags = 0;
+
 	INIT_LIST_HEAD(&p->rt.run_list);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1763,12 +1770,34 @@ void set_numabalancing_state(bool enabled)
 	numabalancing_enabled = enabled;
 }
 #endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_numa_balancing(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = numabalancing_enabled;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_numabalancing_state(state);
+	return err;
+}
+#endif
+#endif
 
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(unsigned long clone_flags, struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
@@ -1790,7 +1819,7 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Revert to default priority/policy on fork if requested.
 	 */
 	if (unlikely(p->sched_reset_on_fork)) {
-		if (task_has_rt_policy(p)) {
+		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 			p->policy = SCHED_NORMAL;
 			p->static_prio = NICE_TO_PRIO(0);
 			p->rt_priority = 0;
@@ -1807,8 +1836,14 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (!rt_prio(p->prio))
+	if (dl_prio(p->prio)) {
+		put_cpu();
+		return -EAGAIN;
+	} else if (rt_prio(p->prio)) {
+		p->sched_class = &rt_sched_class;
+	} else {
 		p->sched_class = &fair_sched_class;
+	}
 
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
@@ -1834,12 +1869,125 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_task_preempt_count(p);
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
 
 	put_cpu();
+	return 0;
+}
+
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+	if (runtime == RUNTIME_INF)
+		return 1ULL << 20;
+
+	/*
+	 * Doing this here saves a lot of checks in all
+	 * the calling paths, and returning zero seems
+	 * safe for them anyway.
+	 */
+	if (period == 0)
+		return 0;
+
+	return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
 /*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+		       const struct sched_attr *attr)
+{
+
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus, err = -1;
+
+	if (new_bw == p->dl.dl_bw)
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
+/*
  * wake_up_new_task - wake up a newly created task for the first time.
  *
  * This function will do some initial scheduler statistics housekeeping
@@ -2003,6 +2151,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (unlikely(prev_state == TASK_DEAD)) {
 		task_numa_free(prev);
 
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -2296,7 +2447,7 @@ void scheduler_tick(void)
 
 #ifdef CONFIG_SMP
 	rq->idle_balance = idle_cpu(cpu);
-	trigger_load_balance(rq, cpu);
+	trigger_load_balance(rq);
 #endif
 	rq_last_tick_reset(rq);
 }
@@ -2325,7 +2476,7 @@ u64 scheduler_tick_max_deferment(void)
 	if (time_before_eq(next, now))
 		return 0;
 
-	return jiffies_to_usecs(next - now) * NSEC_PER_USEC;
+	return jiffies_to_nsecs(next - now);
 }
 #endif
 
@@ -2414,10 +2565,10 @@ static inline void schedule_debug(struct task_struct *prev)
 {
 	/*
 	 * Test if we are atomic. Since do_exit() needs to call into
-	 * schedule() atomically, we ignore that path for now.
-	 * Otherwise, whine if we are scheduling when we should not be.
+	 * schedule() atomically, we ignore that path. Otherwise whine
+	 * if we are scheduling when we should not.
 	 */
-	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+	if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
 		__schedule_bug(prev);
 	rcu_sleep_check();
 
@@ -2761,11 +2912,11 @@ EXPORT_SYMBOL(sleep_on_timeout);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, on_rq, running;
+	int oldprio, on_rq, running, enqueue_flag = 0;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
-	BUG_ON(prio < 0 || prio > MAX_PRIO);
+	BUG_ON(prio > MAX_PRIO);
 
 	rq = __task_rq_lock(p);
 
@@ -2788,6 +2939,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	}
 
 	trace_sched_pi_setprio(p, prio);
+	p->pi_top_task = rt_mutex_get_top_task(p);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->on_rq;
@@ -2797,23 +2949,49 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	if (rt_prio(prio))
+	/*
+	 * Boosting condition are:
+	 * 1. -rt task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A
+	 *
+	 * 2. -dl task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A and could preempt the
+	 *          running task
+	 */
+	if (dl_prio(prio)) {
+		if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+			dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+			p->dl.dl_boosted = 1;
+			p->dl.dl_throttled = 0;
+			enqueue_flag = ENQUEUE_REPLENISH;
+		} else
+			p->dl.dl_boosted = 0;
+		p->sched_class = &dl_sched_class;
+	} else if (rt_prio(prio)) {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
+		if (oldprio < prio)
+			enqueue_flag = ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
-	else
+	} else {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
 		p->sched_class = &fair_sched_class;
+	}
 
 	p->prio = prio;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+		enqueue_task(rq, p, enqueue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
 	__task_rq_unlock(rq);
 }
 #endif
+
 void set_user_nice(struct task_struct *p, long nice)
 {
 	int old_prio, delta, on_rq;
@@ -2831,9 +3009,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
 	 * it wont have any effect on scheduling until the task is
-	 * SCHED_FIFO/SCHED_RR:
+	 * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
 	 */
-	if (task_has_rt_policy(p)) {
+	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
@@ -2988,22 +3166,95 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
-/* Actually do priority change: must hold rq lock. */
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
 static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	init_dl_task_timer(dl_se);
+	dl_se->dl_runtime = attr->sched_runtime;
+	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+	dl_se->flags = attr->sched_flags;
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	dl_se->dl_throttled = 0;
+	dl_se->dl_new = 1;
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+			   const struct sched_attr *attr)
 {
+	int policy = attr->sched_policy;
+
+	if (policy == -1) /* setparam */
+		policy = p->policy;
+
 	p->policy = policy;
-	p->rt_priority = prio;
+
+	if (dl_policy(policy))
+		__setparam_dl(p, attr);
+	else if (fair_policy(policy))
+		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
+	/*
+	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
+	 * !rt_policy. Always setting this ensures that things like
+	 * getparam()/getattr() don't report silly values for !rt tasks.
+	 */
+	p->rt_priority = attr->sched_priority;
+
 	p->normal_prio = normal_prio(p);
-	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
-	if (rt_prio(p->prio))
+
+	if (dl_prio(p->prio))
+		p->sched_class = &dl_sched_class;
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
+
 	set_load_weight(p);
 }
 
+static void
+__getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	attr->sched_priority = p->rt_priority;
+	attr->sched_runtime = dl_se->dl_runtime;
+	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_period = dl_se->dl_period;
+	attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution (1us); we
+ * check sched_runtime only since it is always the smaller one.
+ */
+static bool
+__checkparam_dl(const struct sched_attr *attr)
+{
+	return attr && attr->sched_deadline != 0 &&
+		(attr->sched_period == 0 ||
+		(s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
+		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
+		attr->sched_runtime >= (2 << (DL_SCALE - 1));
+}
+
 /*
  * check the target process has a UID that matches the current process's
  */
@@ -3020,10 +3271,12 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static int __sched_setscheduler(struct task_struct *p, int policy,
-				const struct sched_param *param, bool user)
+static int __sched_setscheduler(struct task_struct *p,
+				const struct sched_attr *attr,
+				bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
+	int policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
 	struct rq *rq;
@@ -3037,31 +3290,40 @@ recheck:
 		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
 	} else {
-		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
-		policy &= ~SCHED_RESET_ON_FORK;
+		reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
 
-		if (policy != SCHED_FIFO && policy != SCHED_RR &&
+		if (policy != SCHED_DEADLINE &&
+				policy != SCHED_FIFO && policy != SCHED_RR &&
 				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
 				policy != SCHED_IDLE)
 			return -EINVAL;
 	}
 
+	if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+		return -EINVAL;
+
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
 	 * SCHED_BATCH and SCHED_IDLE is 0.
 	 */
-	if (param->sched_priority < 0 ||
-	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
-	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+	if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
-	if (rt_policy(policy) != (param->sched_priority != 0))
+	if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+	    (rt_policy(policy) != (attr->sched_priority != 0)))
 		return -EINVAL;
 
 	/*
 	 * Allow unprivileged RT tasks to decrease priority:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
+		if (fair_policy(policy)) {
+			if (attr->sched_nice < TASK_NICE(p) &&
+			    !can_nice(p, attr->sched_nice))
+				return -EPERM;
+		}
+
 		if (rt_policy(policy)) {
 			unsigned long rlim_rtprio =
 					task_rlimit(p, RLIMIT_RTPRIO);
@@ -3071,8 +3333,8 @@ recheck:
 				return -EPERM;
 
 			/* can't increase priority */
-			if (param->sched_priority > p->rt_priority &&
-			    param->sched_priority > rlim_rtprio)
+			if (attr->sched_priority > p->rt_priority &&
+			    attr->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
 
@@ -3120,14 +3382,21 @@ recheck:
 	/*
 	 * If not changing anything there's no need to proceed further:
 	 */
-	if (unlikely(policy == p->policy && (!rt_policy(policy) ||
-			param->sched_priority == p->rt_priority))) {
+	if (unlikely(policy == p->policy)) {
+		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+			goto change;
+		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+			goto change;
+		if (dl_policy(policy))
+			goto change;
+
 		task_rq_unlock(rq, p, &flags);
 		return 0;
 	}
+change:
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
 		/*
 		 * Do not allow realtime tasks into groups that have no runtime
 		 * assigned.
@@ -3138,8 +3407,24 @@ recheck:
 			task_rq_unlock(rq, p, &flags);
 			return -EPERM;
 		}
-	}
 #endif
+#ifdef CONFIG_SMP
+		if (dl_bandwidth_enabled() && dl_policy(policy)) {
+			cpumask_t *span = rq->rd->span;
+
+			/*
+			 * Don't allow tasks with an affinity mask smaller than
+			 * the entire root_domain to become SCHED_DEADLINE. We
+			 * will also fail if there's no bandwidth available.
+			 */
+			if (!cpumask_subset(span, &p->cpus_allowed) ||
+			    rq->rd->dl_bw.bw == 0) {
+				task_rq_unlock(rq, p, &flags);
+				return -EPERM;
+			}
+		}
+#endif
+	}
 
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
@@ -3147,6 +3432,17 @@ recheck:
 		task_rq_unlock(rq, p, &flags);
 		goto recheck;
 	}
+
+	/*
+	 * If setscheduling to SCHED_DEADLINE (or changing the parameters
+	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
+	 * is available.
+	 */
+	if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+		task_rq_unlock(rq, p, &flags);
+		return -EBUSY;
+	}
+
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -3158,7 +3454,7 @@ recheck:
 
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	__setscheduler(rq, p, policy, param->sched_priority);
+	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -3173,6 +3469,26 @@ recheck:
 	return 0;
 }
 
+static int _sched_setscheduler(struct task_struct *p, int policy,
+			       const struct sched_param *param, bool check)
+{
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority,
+		.sched_nice	= PRIO_TO_NICE(p->static_prio),
+	};
+
+	/*
+	 * Fixup the legacy SCHED_RESET_ON_FORK hack
+	 */
+	if (policy & SCHED_RESET_ON_FORK) {
+		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		policy &= ~SCHED_RESET_ON_FORK;
+		attr.sched_policy = policy;
+	}
+
+	return __sched_setscheduler(p, &attr, check);
+}
 /**
  * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
  * @p: the task in question.
@@ -3186,10 +3502,16 @@ recheck:
 int sched_setscheduler(struct task_struct *p, int policy,
 		       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, true);
+	return _sched_setscheduler(p, policy, param, true);
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+	return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
  * @p: the task in question.
@@ -3206,7 +3528,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 			       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, false);
+	return _sched_setscheduler(p, policy, param, false);
 }
 
 static int
@@ -3231,6 +3553,79 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 	return retval;
 }
 
+/*
+ * Mimics kernel/events/core.c perf_copy_attr().
+ */
+static int sched_copy_attr(struct sched_attr __user *uattr,
+			   struct sched_attr *attr)
+{
+	u32 size;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * zero the full structure, so that a short copy will be nice.
+	 */
+	memset(attr, 0, sizeof(*attr));
+
+	ret = get_user(size, &uattr->size);
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (!size)		/* abi compat */
+		size = SCHED_ATTR_SIZE_VER0;
+
+	if (size < SCHED_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+		size = sizeof(*attr);
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+	/*
+	 * XXX: do we want to be lenient like existing syscalls; or do we want
+	 * to be strict and return an error on out-of-bounds values?
+	 */
+	attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
 /**
  * sys_sched_setscheduler - set/change the scheduler policy and RT priority
  * @pid: the pid in question.
@@ -3262,6 +3657,33 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 }
 
 /**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+{
+	struct sched_attr attr;
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0)
+		return -EINVAL;
+
+	if (sched_copy_attr(uattr, &attr))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setattr(p, &attr);
+	rcu_read_unlock();
+
+	return retval;
+}
+
+/**
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
  *
@@ -3316,6 +3738,10 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (retval)
 		goto out_unlock;
 
+	if (task_has_dl_policy(p)) {
+		retval = -EINVAL;
+		goto out_unlock;
+	}
 	lp.sched_priority = p->rt_priority;
 	rcu_read_unlock();
 
@@ -3331,6 +3757,96 @@ out_unlock:
 	return retval;
 }
 
+static int sched_read_attr(struct sched_attr __user *uattr,
+			   struct sched_attr *attr,
+			   unsigned int usize)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, usize))
+		return -EFAULT;
+
+	/*
+	 * If we're handed a smaller struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. old
+	 * user-space does not get uncomplete information.
+	 */
+	if (usize < sizeof(*attr)) {
+		unsigned char *addr;
+		unsigned char *end;
+
+		addr = (void *)attr + usize;
+		end  = (void *)attr + sizeof(*attr);
+
+		for (; addr < end; addr++) {
+			if (*addr)
+				goto err_size;
+		}
+
+		attr->size = usize;
+	}
+
+	ret = copy_to_user(uattr, attr, usize);
+	if (ret)
+		return -EFAULT;
+
+out:
+	return ret;
+
+err_size:
+	ret = -E2BIG;
+	goto out;
+}
+
+/**
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size)
+{
+	struct sched_attr attr = {
+		.size = sizeof(struct sched_attr),
+	};
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0 || size > PAGE_SIZE ||
+	    size < SCHED_ATTR_SIZE_VER0)
+		return -EINVAL;
+
+	rcu_read_lock();
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	attr.sched_policy = p->policy;
+	if (p->sched_reset_on_fork)
+		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+	if (task_has_dl_policy(p))
+		__getparam_dl(p, &attr);
+	else if (task_has_rt_policy(p))
+		attr.sched_priority = p->rt_priority;
+	else
+		attr.sched_nice = TASK_NICE(p);
+
+	rcu_read_unlock();
+
+	retval = sched_read_attr(uattr, &attr, size);
+	return retval;
+
+out_unlock:
+	rcu_read_unlock();
+	return retval;
+}
+
 long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
 	cpumask_var_t cpus_allowed, new_mask;
@@ -3375,8 +3891,26 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_unlock;
 
+
 	cpuset_cpus_allowed(p, cpus_allowed);
 	cpumask_and(new_mask, in_mask, cpus_allowed);
+
+	/*
+	 * Since bandwidth control happens on root_domain basis,
+	 * if admission test is enabled, we only admit -deadline
+	 * tasks allowed to run on all the CPUs in the task's
+	 * root_domain.
+	 */
+#ifdef CONFIG_SMP
+	if (task_has_dl_policy(p)) {
+		const struct cpumask *span = task_rq(p)->rd->span;
+
+		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+			retval = -EBUSY;
+			goto out_unlock;
+		}
+	}
+#endif
 again:
 	retval = set_cpus_allowed_ptr(p, new_mask);
 
@@ -3653,7 +4187,7 @@ again:
 	}
 
 	double_rq_lock(rq, p_rq);
-	while (task_rq(p) != p_rq) {
+	if (task_rq(p) != p_rq) {
 		double_rq_unlock(rq, p_rq);
 		goto again;
 	}
@@ -3742,6 +4276,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 	case SCHED_RR:
 		ret = MAX_USER_RT_PRIO-1;
 		break;
+	case SCHED_DEADLINE:
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
@@ -3768,6 +4303,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 	case SCHED_RR:
 		ret = 1;
 		break;
+	case SCHED_DEADLINE:
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
@@ -3811,7 +4347,9 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 		goto out_unlock;
 
 	rq = task_rq_lock(p, &flags);
-	time_slice = p->sched_class->get_rr_interval(rq, p);
+	time_slice = 0;
+	if (p->sched_class->get_rr_interval)
+		time_slice = p->sched_class->get_rr_interval(rq, p);
 	task_rq_unlock(rq, p, &flags);
 
 	rcu_read_unlock();
@@ -4090,6 +4628,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 
 	/* TODO: This is not properly updating schedstats */
 
+	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
 
@@ -4514,13 +5053,31 @@ static int sched_cpu_active(struct notifier_block *nfb,
 static int sched_cpu_inactive(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
+	unsigned long flags;
+	long cpu = (long)hcpu;
+
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
-		set_cpu_active((long)hcpu, false);
+		set_cpu_active(cpu, false);
+
+		/* explicitly allow suspend */
+		if (!(action & CPU_TASKS_FROZEN)) {
+			struct dl_bw *dl_b = dl_bw_of(cpu);
+			bool overflow;
+			int cpus;
+
+			raw_spin_lock_irqsave(&dl_b->lock, flags);
+			cpus = dl_bw_cpus(cpu);
+			overflow = __dl_overflow(dl_b, cpus, 0, 0);
+			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+			if (overflow)
+				return notifier_from_errno(-EBUSY);
+		}
 		return NOTIFY_OK;
-	default:
-		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_DONE;
 }
 
 static int __init migration_init(void)
@@ -4739,6 +5296,8 @@ static void free_rootdomain(struct rcu_head *rcu)
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
+	cpudl_cleanup(&rd->cpudl);
+	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -4790,8 +5349,14 @@ static int init_rootdomain(struct root_domain *rd)
 		goto out;
 	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_dlo_mask;
+
+	init_dl_bw(&rd->dl_bw);
+	if (cpudl_init(&rd->cpudl) != 0)
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
@@ -4799,6 +5364,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 free_rto_mask:
 	free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+	free_cpumask_var(rd->dlo_mask);
 free_online:
 	free_cpumask_var(rd->online);
 free_span:
@@ -4902,6 +5469,7 @@ DEFINE_PER_CPU(struct sched_domain *, sd_asym);
 static void update_top_cache_domain(int cpu)
 {
 	struct sched_domain *sd;
+	struct sched_domain *busy_sd = NULL;
 	int id = cpu;
 	int size = 1;
 
@@ -4909,9 +5477,9 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
-		sd = sd->parent; /* sd_busy */
+		busy_sd = sd->parent; /* sd_busy */
 	}
-	rcu_assign_pointer(per_cpu(sd_busy, cpu), sd);
+	rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
@@ -5112,6 +5680,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		 * die on a /0 trap.
 		 */
 		sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+		sg->sgp->power_orig = sg->sgp->power;
 
 		/*
 		 * Make sure the first group of this domain contains the
@@ -6148,6 +6717,7 @@ void __init sched_init_smp(void)
 	free_cpumask_var(non_isolated_cpus);
 
 	init_sched_rt_class();
+	init_sched_dl_class();
 }
 #else
 void __init sched_init_smp(void)
@@ -6217,13 +6787,15 @@ void __init sched_init(void)
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
+	init_rt_bandwidth(&def_rt_bandwidth,
+			global_rt_period(), global_rt_runtime());
+	init_dl_bandwidth(&def_dl_bandwidth,
+			global_rt_period(), global_rt_runtime());
+
 #ifdef CONFIG_SMP
 	init_defrootdomain();
 #endif
 
-	init_rt_bandwidth(&def_rt_bandwidth,
-			global_rt_period(), global_rt_runtime());
-
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_rt_bandwidth(&root_task_group.rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
@@ -6247,6 +6819,7 @@ void __init sched_init(void)
 		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs);
 		init_rt_rq(&rq->rt, rq);
+		init_dl_rq(&rq->dl, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -6318,10 +6891,6 @@ void __init sched_init(void)
 	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
 #endif
 
-#ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&init_task.pi_waiters);
-#endif
-
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */
@@ -6395,13 +6964,16 @@ EXPORT_SYMBOL(__might_sleep);
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
 	const struct sched_class *prev_class = p->sched_class;
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+	};
 	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
-	__setscheduler(rq, p, SCHED_NORMAL, 0);
+	__setscheduler(rq, p, &attr);
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
 		resched_task(rq->curr);
@@ -6431,7 +7003,7 @@ void normalize_rt_tasks(void)
 		p->se.statistics.block_start	= 0;
 #endif
 
-		if (!rt_task(p)) {
+		if (!dl_task(p) && !rt_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
@@ -6626,16 +7198,6 @@ void sched_move_task(struct task_struct *tsk)
 }
 #endif /* CONFIG_CGROUP_SCHED */
 
-#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
-static unsigned long to_ratio(u64 period, u64 runtime)
-{
-	if (runtime == RUNTIME_INF)
-		return 1ULL << 20;
-
-	return div64_u64(runtime << 20, period);
-}
-#endif
-
 #ifdef CONFIG_RT_GROUP_SCHED
 /*
  * Ensure that the real time constraints are schedulable.
@@ -6809,24 +7371,13 @@ static long sched_group_rt_period(struct task_group *tg)
 	do_div(rt_period_us, NSEC_PER_USEC);
 	return rt_period_us;
 }
+#endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_RT_GROUP_SCHED
 static int sched_rt_global_constraints(void)
 {
-	u64 runtime, period;
 	int ret = 0;
 
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	runtime = global_rt_runtime();
-	period = global_rt_period();
-
-	/*
-	 * Sanity check on the sysctl variables.
-	 */
-	if (runtime > period && runtime != RUNTIME_INF)
-		return -EINVAL;
-
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	ret = __rt_schedulable(NULL, 0, 0);
@@ -6849,17 +7400,7 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
-	int i;
-
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	/*
-	 * There's always some RT tasks in the root group
-	 * -- migration, kstopmachine etc..
-	 */
-	if (sysctl_sched_rt_runtime == 0)
-		return -EBUSY;
+	int i, ret = 0;
 
 	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
 	for_each_possible_cpu(i) {
@@ -6871,36 +7412,88 @@ static int sched_rt_global_constraints(void)
 	}
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+static int sched_dl_global_constraints(void)
 {
-	int ret;
-	static DEFINE_MUTEX(mutex);
+	u64 runtime = global_rt_runtime();
+	u64 period = global_rt_period();
+	u64 new_bw = to_ratio(period, runtime);
+	int cpu, ret = 0;
 
-	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/* make sure that internally we keep jiffies */
-	/* also, writing zero resets timeslice to default */
-	if (!ret && write) {
-		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
-			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+	/*
+	 * Here we want to check the bandwidth not being set to some
+	 * value smaller than the currently allocated bandwidth in
+	 * any of the root_domains.
+	 *
+	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+	 * cycling on root_domains... Discussion on different/better
+	 * solutions is welcome!
+	 */
+	for_each_possible_cpu(cpu) {
+		struct dl_bw *dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock(&dl_b->lock);
+		if (new_bw < dl_b->total_bw)
+			ret = -EBUSY;
+		raw_spin_unlock(&dl_b->lock);
+
+		if (ret)
+			break;
 	}
-	mutex_unlock(&mutex);
+
 	return ret;
 }
 
+static void sched_dl_do_global(void)
+{
+	u64 new_bw = -1;
+	int cpu;
+
+	def_dl_bandwidth.dl_period = global_rt_period();
+	def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+	if (global_rt_runtime() != RUNTIME_INF)
+		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+	/*
+	 * FIXME: As above...
+	 */
+	for_each_possible_cpu(cpu) {
+		struct dl_bw *dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock(&dl_b->lock);
+		dl_b->bw = new_bw;
+		raw_spin_unlock(&dl_b->lock);
+	}
+}
+
+static int sched_rt_global_validate(void)
+{
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+	def_rt_bandwidth.rt_runtime = global_rt_runtime();
+	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
 int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int ret;
 	int old_period, old_runtime;
 	static DEFINE_MUTEX(mutex);
+	int ret;
 
 	mutex_lock(&mutex);
 	old_period = sysctl_sched_rt_period;
@@ -6909,21 +7502,50 @@ int sched_rt_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
+		ret = sched_rt_global_validate();
+		if (ret)
+			goto undo;
+
 		ret = sched_rt_global_constraints();
-		if (ret) {
-			sysctl_sched_rt_period = old_period;
-			sysctl_sched_rt_runtime = old_runtime;
-		} else {
-			def_rt_bandwidth.rt_runtime = global_rt_runtime();
-			def_rt_bandwidth.rt_period =
-				ns_to_ktime(global_rt_period());
-		}
+		if (ret)
+			goto undo;
+
+		ret = sched_dl_global_constraints();
+		if (ret)
+			goto undo;
+
+		sched_rt_do_global();
+		sched_dl_do_global();
+	}
+	if (0) {
+undo:
+		sysctl_sched_rt_period = old_period;
+		sysctl_sched_rt_runtime = old_runtime;
 	}
 	mutex_unlock(&mutex);
 
 	return ret;
 }
 
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/* make sure that internally we keep jiffies */
+	/* also, writing zero resets timeslice to default */
+	if (!ret && write) {
+		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
+
 #ifdef CONFIG_CGROUP_SCHED
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -7256,15 +7878,14 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
 	return ret;
 }
 
-static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft,
-		struct cgroup_map_cb *cb)
+static int cpu_stats_show(struct seq_file *sf, void *v)
 {
-	struct task_group *tg = css_tg(css);
+	struct task_group *tg = css_tg(seq_css(sf));
 	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
 
-	cb->fill(cb, "nr_periods", cfs_b->nr_periods);
-	cb->fill(cb, "nr_throttled", cfs_b->nr_throttled);
-	cb->fill(cb, "throttled_time", cfs_b->throttled_time);
+	seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
+	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
+	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
 	return 0;
 }
@@ -7318,7 +7939,7 @@ static struct cftype cpu_files[] = {
 	},
 	{
 		.name = "stat",
-		.read_map = cpu_stats_show,
+		.seq_show = cpu_stats_show,
 	},
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index f64722f..622e081 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -163,10 +163,9 @@ out:
 	return err;
 }
 
-static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css,
-				   struct cftype *cft, struct seq_file *m)
+static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
 {
-	struct cpuacct *ca = css_ca(css);
+	struct cpuacct *ca = css_ca(seq_css(m));
 	u64 percpu;
 	int i;
 
@@ -183,10 +182,9 @@ static const char * const cpuacct_stat_desc[] = {
 	[CPUACCT_STAT_SYSTEM] = "system",
 };
 
-static int cpuacct_stats_show(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct cgroup_map_cb *cb)
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
 {
-	struct cpuacct *ca = css_ca(css);
+	struct cpuacct *ca = css_ca(seq_css(sf));
 	int cpu;
 	s64 val = 0;
 
@@ -196,7 +194,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
 		val += kcpustat->cpustat[CPUTIME_NICE];
 	}
 	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
 
 	val = 0;
 	for_each_online_cpu(cpu) {
@@ -207,7 +205,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
 	}
 
 	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
 
 	return 0;
 }
@@ -220,11 +218,11 @@ static struct cftype files[] = {
 	},
 	{
 		.name = "usage_percpu",
-		.read_seq_string = cpuacct_percpu_seq_read,
+		.seq_show = cpuacct_percpu_seq_show,
 	},
 	{
 		.name = "stat",
-		.read_map = cpuacct_stats_show,
+		.seq_show = cpuacct_stats_show,
 	},
 	{ }	/* terminate */
 };
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
new file mode 100644
index 0000000..045fc74
--- /dev/null
+++ b/kernel/sched/cpudeadline.c
@@ -0,0 +1,216 @@
+/*
+ *  kernel/sched/cpudl.c
+ *
+ *  Global CPU deadline management
+ *
+ *  Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ *  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; version 2
+ *  of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+	return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+	return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+	return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+static void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+	swap(cp->elements[a], cp->elements[b]);
+	swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+}
+
+static void cpudl_heapify(struct cpudl *cp, int idx)
+{
+	int l, r, largest;
+
+	/* adapted from lib/prio_heap.c */
+	while(1) {
+		l = left_child(idx);
+		r = right_child(idx);
+		largest = idx;
+
+		if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+							cp->elements[l].dl))
+			largest = l;
+		if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+							cp->elements[r].dl))
+			largest = r;
+		if (largest == idx)
+			break;
+
+		/* Push idx down the heap one level and bump one up */
+		cpudl_exchange(cp, largest, idx);
+		idx = largest;
+	}
+}
+
+static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+	WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+
+	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+		cp->elements[idx].dl = new_dl;
+		cpudl_heapify(cp, idx);
+	} else {
+		cp->elements[idx].dl = new_dl;
+		while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+					cp->elements[idx].dl)) {
+			cpudl_exchange(cp, idx, parent(idx));
+			idx = parent(idx);
+		}
+	}
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+	return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask)
+{
+	int best_cpu = -1;
+	const struct sched_dl_entity *dl_se = &p->dl;
+
+	if (later_mask && cpumask_and(later_mask, cp->free_cpus,
+			&p->cpus_allowed) && cpumask_and(later_mask,
+			later_mask, cpu_active_mask)) {
+		best_cpu = cpumask_any(later_mask);
+		goto out;
+	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+			dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+		best_cpu = cpudl_maximum(cp);
+		if (later_mask)
+			cpumask_set_cpu(best_cpu, later_mask);
+	}
+
+out:
+	WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+
+	return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+	int old_idx, new_cpu;
+	unsigned long flags;
+
+	WARN_ON(cpu > num_present_cpus());
+
+	raw_spin_lock_irqsave(&cp->lock, flags);
+	old_idx = cp->cpu_to_idx[cpu];
+	if (!is_valid) {
+		/* remove item */
+		if (old_idx == IDX_INVALID) {
+			/*
+			 * Nothing to remove if old_idx was invalid.
+			 * This could happen if a rq_offline_dl is
+			 * called for a CPU without -dl tasks running.
+			 */
+			goto out;
+		}
+		new_cpu = cp->elements[cp->size - 1].cpu;
+		cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+		cp->elements[old_idx].cpu = new_cpu;
+		cp->size--;
+		cp->cpu_to_idx[new_cpu] = old_idx;
+		cp->cpu_to_idx[cpu] = IDX_INVALID;
+		while (old_idx > 0 && dl_time_before(
+				cp->elements[parent(old_idx)].dl,
+				cp->elements[old_idx].dl)) {
+			cpudl_exchange(cp, old_idx, parent(old_idx));
+			old_idx = parent(old_idx);
+		}
+		cpumask_set_cpu(cpu, cp->free_cpus);
+                cpudl_heapify(cp, old_idx);
+
+		goto out;
+	}
+
+	if (old_idx == IDX_INVALID) {
+		cp->size++;
+		cp->elements[cp->size - 1].dl = 0;
+		cp->elements[cp->size - 1].cpu = cpu;
+		cp->cpu_to_idx[cpu] = cp->size - 1;
+		cpudl_change_key(cp, cp->size - 1, dl);
+		cpumask_clear_cpu(cpu, cp->free_cpus);
+	} else {
+		cpudl_change_key(cp, old_idx, dl);
+	}
+
+out:
+	raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+	int i;
+
+	memset(cp, 0, sizeof(*cp));
+	raw_spin_lock_init(&cp->lock);
+	cp->size = 0;
+	for (i = 0; i < NR_CPUS; i++)
+		cp->cpu_to_idx[i] = IDX_INVALID;
+	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_setall(cp->free_cpus);
+
+	return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+	/*
+	 * nothing to do for the moment
+	 */
+}
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
new file mode 100644
index 0000000..a202789
--- /dev/null
+++ b/kernel/sched/cpudeadline.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID     -1
+
+struct array_item {
+	u64 dl;
+	int cpu;
+};
+
+struct cpudl {
+	raw_spinlock_t lock;
+	int size;
+	int cpu_to_idx[NR_CPUS];
+	struct array_item elements[NR_CPUS];
+	cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
new file mode 100644
index 0000000..0dd5e09
--- /dev/null
+++ b/kernel/sched/deadline.c
@@ -0,0 +1,1641 @@
+/*
+ * Deadline Scheduling Class (SCHED_DEADLINE)
+ *
+ * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
+ *
+ * Tasks that periodically executes their instances for less than their
+ * runtime won't miss any of their deadlines.
+ * Tasks that are not periodic or sporadic or that tries to execute more
+ * than their reserved bandwidth will be slowed down (and may potentially
+ * miss some of their deadlines), and won't affect any other task.
+ *
+ * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ *                    Juri Lelli <juri.lelli@gmail.com>,
+ *                    Michael Trimarchi <michael@amarulasolutions.com>,
+ *                    Fabio Checconi <fchecconi@gmail.com>
+ */
+#include "sched.h"
+
+#include <linux/slab.h>
+
+struct dl_bandwidth def_dl_bandwidth;
+
+static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
+{
+	return container_of(dl_se, struct task_struct, dl);
+}
+
+static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
+{
+	return container_of(dl_rq, struct rq, dl);
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = task_rq(p);
+
+	return &rq->dl;
+}
+
+static inline int on_dl_rq(struct sched_dl_entity *dl_se)
+{
+	return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	return dl_rq->rb_leftmost == &dl_se->rb_node;
+}
+
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
+{
+	raw_spin_lock_init(&dl_b->dl_runtime_lock);
+	dl_b->dl_period = period;
+	dl_b->dl_runtime = runtime;
+}
+
+extern unsigned long to_ratio(u64 period, u64 runtime);
+
+void init_dl_bw(struct dl_bw *dl_b)
+{
+	raw_spin_lock_init(&dl_b->lock);
+	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
+	if (global_rt_runtime() == RUNTIME_INF)
+		dl_b->bw = -1;
+	else
+		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
+	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
+	dl_b->total_bw = 0;
+}
+
+void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+{
+	dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+	/* zero means no -deadline tasks */
+	dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+	dl_rq->dl_nr_migratory = 0;
+	dl_rq->overloaded = 0;
+	dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#else
+	init_dl_bw(&dl_rq->dl_bw);
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+	return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+	if (!rq->online)
+		return;
+
+	cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+	/*
+	 * Must be visible before the overload count is
+	 * set (as in sched_rt.c).
+	 *
+	 * Matched by the barrier in pull_dl_task().
+	 */
+	smp_wmb();
+	atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+	if (!rq->online)
+		return;
+
+	atomic_dec(&rq->rd->dlo_count);
+	cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+		if (!dl_rq->overloaded) {
+			dl_set_overload(rq_of_dl_rq(dl_rq));
+			dl_rq->overloaded = 1;
+		}
+	} else if (dl_rq->overloaded) {
+		dl_clear_overload(rq_of_dl_rq(dl_rq));
+		dl_rq->overloaded = 0;
+	}
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+	dl_rq->dl_nr_total++;
+	if (p->nr_cpus_allowed > 1)
+		dl_rq->dl_nr_migratory++;
+
+	update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+	dl_rq->dl_nr_total--;
+	if (p->nr_cpus_allowed > 1)
+		dl_rq->dl_nr_migratory--;
+
+	update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+	struct dl_rq *dl_rq = &rq->dl;
+	struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct task_struct *entry;
+	int leftmost = 1;
+
+	BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct task_struct,
+				 pushable_dl_tasks);
+		if (dl_entity_preempt(&p->dl, &entry->dl))
+			link = &parent->rb_left;
+		else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+	rb_link_node(&p->pushable_dl_tasks, parent, link);
+	rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+}
+
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+	struct dl_rq *dl_rq = &rq->dl;
+
+	if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+		return;
+
+	if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+		struct rb_node *next_node;
+
+		next_node = rb_next(&p->pushable_dl_tasks);
+		dl_rq->pushable_dl_tasks_leftmost = next_node;
+	}
+
+	rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+	return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+				  int flags);
+
+/*
+ * We are being explicitly informed that a new instance is starting,
+ * and this means that:
+ *  - the absolute deadline of the entity has to be placed at
+ *    current time + relative deadline;
+ *  - the runtime of the entity has to be set to the maximum value.
+ *
+ * The capability of specifying such event is useful whenever a -deadline
+ * entity wants to (try to!) synchronize its behaviour with the scheduler's
+ * one, and to (try to!) reconcile itself with its own scheduling
+ * parameters.
+ */
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+				       struct sched_dl_entity *pi_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+
+	/*
+	 * We use the regular wall clock time to set deadlines in the
+	 * future; in fact, we must consider execution overheads (time
+	 * spent on hardirq context, etc.).
+	 */
+	dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+	dl_se->runtime = pi_se->dl_runtime;
+	dl_se->dl_new = 0;
+}
+
+/*
+ * Pure Earliest Deadline First (EDF) scheduling does not deal with the
+ * possibility of a entity lasting more than what it declared, and thus
+ * exhausting its runtime.
+ *
+ * Here we are interested in making runtime overrun possible, but we do
+ * not want a entity which is misbehaving to affect the scheduling of all
+ * other entities.
+ * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
+ * is used, in order to confine each entity within its own bandwidth.
+ *
+ * This function deals exactly with that, and ensures that when the runtime
+ * of a entity is replenished, its deadline is also postponed. That ensures
+ * the overrunning entity can't interfere with other entity in the system and
+ * can't make them miss their deadlines. Reasons why this kind of overruns
+ * could happen are, typically, a entity voluntarily trying to overcome its
+ * runtime, or it just underestimated it during sched_setscheduler_ex().
+ */
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+				struct sched_dl_entity *pi_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	BUG_ON(pi_se->dl_runtime <= 0);
+
+	/*
+	 * This could be the case for a !-dl task that is boosted.
+	 * Just go with full inherited parameters.
+	 */
+	if (dl_se->dl_deadline == 0) {
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
+	}
+
+	/*
+	 * We keep moving the deadline away until we get some
+	 * available runtime for the entity. This ensures correct
+	 * handling of situations where the runtime overrun is
+	 * arbitrary large.
+	 */
+	while (dl_se->runtime <= 0) {
+		dl_se->deadline += pi_se->dl_period;
+		dl_se->runtime += pi_se->dl_runtime;
+	}
+
+	/*
+	 * At this point, the deadline really should be "in
+	 * the future" with respect to rq->clock. If it's
+	 * not, we are, for some reason, lagging too much!
+	 * Anyway, after having warn userspace abut that,
+	 * we still try to keep the things running by
+	 * resetting the deadline and the budget of the
+	 * entity.
+	 */
+	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
+		static bool lag_once = false;
+
+		if (!lag_once) {
+			lag_once = true;
+			printk_sched("sched: DL replenish lagged to much\n");
+		}
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
+	}
+}
+
+/*
+ * Here we check if --at time t-- an entity (which is probably being
+ * [re]activated or, in general, enqueued) can use its remaining runtime
+ * and its current deadline _without_ exceeding the bandwidth it is
+ * assigned (function returns true if it can't). We are in fact applying
+ * one of the CBS rules: when a task wakes up, if the residual runtime
+ * over residual deadline fits within the allocated bandwidth, then we
+ * can keep the current (absolute) deadline and residual budget without
+ * disrupting the schedulability of the system. Otherwise, we should
+ * refill the runtime and set the deadline a period in the future,
+ * because keeping the current (absolute) deadline of the task would
+ * result in breaking guarantees promised to other tasks (refer to
+ * Documentation/scheduler/sched-deadline.txt for more informations).
+ *
+ * This function returns true if:
+ *
+ *   runtime / (deadline - t) > dl_runtime / dl_period ,
+ *
+ * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
+ */
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+			       struct sched_dl_entity *pi_se, u64 t)
+{
+	u64 left, right;
+
+	/*
+	 * left and right are the two sides of the equation above,
+	 * after a bit of shuffling to use multiplications instead
+	 * of divisions.
+	 *
+	 * Note that none of the time values involved in the two
+	 * multiplications are absolute: dl_deadline and dl_runtime
+	 * are the relative deadline and the maximum runtime of each
+	 * instance, runtime is the runtime left for the last instance
+	 * and (deadline - t), since t is rq->clock, is the time left
+	 * to the (absolute) deadline. Even if overflowing the u64 type
+	 * is very unlikely to occur in both cases, here we scale down
+	 * as we want to avoid that risk at all. Scaling down by 10
+	 * means that we reduce granularity to 1us. We are fine with it,
+	 * since this is only a true/false check and, anyway, thinking
+	 * of anything below microseconds resolution is actually fiction
+	 * (but still we want to give the user that illusion >;).
+	 */
+	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	right = ((dl_se->deadline - t) >> DL_SCALE) *
+		(pi_se->dl_runtime >> DL_SCALE);
+
+	return dl_time_before(right, left);
+}
+
+/*
+ * When a -deadline entity is queued back on the runqueue, its runtime and
+ * deadline might need updating.
+ *
+ * The policy here is that we update the deadline of the entity only if:
+ *  - the current deadline is in the past,
+ *  - using the remaining runtime with the current deadline would make
+ *    the entity exceed its bandwidth.
+ */
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+			     struct sched_dl_entity *pi_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	/*
+	 * The arrival of a new instance needs special treatment, i.e.,
+	 * the actual scheduling parameters have to be "renewed".
+	 */
+	if (dl_se->dl_new) {
+		setup_new_dl_entity(dl_se, pi_se);
+		return;
+	}
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
+	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
+	}
+}
+
+/*
+ * If the entity depleted all its runtime, and if we want it to sleep
+ * while waiting for some new execution time to become available, we
+ * set the bandwidth enforcement timer to the replenishment instant
+ * and try to activate it.
+ *
+ * Notice that it is important for the caller to know if the timer
+ * actually started or not (i.e., the replenishment instant is in
+ * the future or in the past).
+ */
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+	ktime_t now, act;
+	ktime_t soft, hard;
+	unsigned long range;
+	s64 delta;
+
+	if (boosted)
+		return 0;
+	/*
+	 * We want the timer to fire at the deadline, but considering
+	 * that it is actually coming from rq->clock and not from
+	 * hrtimer's time base reading.
+	 */
+	act = ns_to_ktime(dl_se->deadline);
+	now = hrtimer_cb_get_time(&dl_se->dl_timer);
+	delta = ktime_to_ns(now) - rq_clock(rq);
+	act = ktime_add_ns(act, delta);
+
+	/*
+	 * If the expiry time already passed, e.g., because the value
+	 * chosen as the deadline is too small, don't even try to
+	 * start the timer in the past!
+	 */
+	if (ktime_us_delta(act, now) < 0)
+		return 0;
+
+	hrtimer_set_expires(&dl_se->dl_timer, act);
+
+	soft = hrtimer_get_softexpires(&dl_se->dl_timer);
+	hard = hrtimer_get_expires(&dl_se->dl_timer);
+	range = ktime_to_ns(ktime_sub(hard, soft));
+	__hrtimer_start_range_ns(&dl_se->dl_timer, soft,
+				 range, HRTIMER_MODE_ABS, 0);
+
+	return hrtimer_active(&dl_se->dl_timer);
+}
+
+/*
+ * This is the bandwidth enforcement timer callback. If here, we know
+ * a task is not on its dl_rq, since the fact that the timer was running
+ * means the task is throttled and needs a runtime replenishment.
+ *
+ * However, what we actually do depends on the fact the task is active,
+ * (it is on its rq) or has been removed from there by a call to
+ * dequeue_task_dl(). In the former case we must issue the runtime
+ * replenishment and add the task back to the dl_rq; in the latter, we just
+ * do nothing but clearing dl_throttled, so that runtime and deadline
+ * updating (and the queueing back to dl_rq) will be done by the
+ * next call to enqueue_task_dl().
+ */
+static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
+{
+	struct sched_dl_entity *dl_se = container_of(timer,
+						     struct sched_dl_entity,
+						     dl_timer);
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = task_rq(p);
+	raw_spin_lock(&rq->lock);
+
+	/*
+	 * We need to take care of a possible races here. In fact, the
+	 * task might have changed its scheduling policy to something
+	 * different from SCHED_DEADLINE or changed its reservation
+	 * parameters (through sched_setscheduler()).
+	 */
+	if (!dl_task(p) || dl_se->dl_new)
+		goto unlock;
+
+	sched_clock_tick();
+	update_rq_clock(rq);
+	dl_se->dl_throttled = 0;
+	if (p->on_rq) {
+		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+		if (task_has_dl_policy(rq->curr))
+			check_preempt_curr_dl(rq, p, 0);
+		else
+			resched_task(rq->curr);
+#ifdef CONFIG_SMP
+		/*
+		 * Queueing this task back might have overloaded rq,
+		 * check if we need to kick someone away.
+		 */
+		if (has_pushable_dl_tasks(rq))
+			push_dl_task(rq);
+#endif
+	}
+unlock:
+	raw_spin_unlock(&rq->lock);
+
+	return HRTIMER_NORESTART;
+}
+
+void init_dl_task_timer(struct sched_dl_entity *dl_se)
+{
+	struct hrtimer *timer = &dl_se->dl_timer;
+
+	if (hrtimer_active(timer)) {
+		hrtimer_try_to_cancel(timer);
+		return;
+	}
+
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	timer->function = dl_task_timer;
+}
+
+static
+int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
+	int rorun = dl_se->runtime <= 0;
+
+	if (!rorun && !dmiss)
+		return 0;
+
+	/*
+	 * If we are beyond our current deadline and we are still
+	 * executing, then we have already used some of the runtime of
+	 * the next instance. Thus, if we do not account that, we are
+	 * stealing bandwidth from the system at each deadline miss!
+	 */
+	if (dmiss) {
+		dl_se->runtime = rorun ? dl_se->runtime : 0;
+		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
+	}
+
+	return 1;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct sched_dl_entity *dl_se = &curr->dl;
+	u64 delta_exec;
+
+	if (!dl_task(curr) || !on_dl_rq(dl_se))
+		return;
+
+	/*
+	 * Consumed budget is computed considering the time as
+	 * observed by schedulable tasks (excluding time spent
+	 * in hardirq context, etc.). Deadlines are instead
+	 * computed using hard walltime. This seems to be the more
+	 * natural solution, but the full ramifications of this
+	 * approach need further study.
+	 */
+	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+	if (unlikely((s64)delta_exec < 0))
+		delta_exec = 0;
+
+	schedstat_set(curr->se.statistics.exec_max,
+		      max(curr->se.statistics.exec_max, delta_exec));
+
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = rq_clock_task(rq);
+	cpuacct_charge(curr, delta_exec);
+
+	sched_rt_avg_update(rq, delta_exec);
+
+	dl_se->runtime -= delta_exec;
+	if (dl_runtime_exceeded(rq, dl_se)) {
+		__dequeue_task_dl(rq, curr, 0);
+		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
+			dl_se->dl_throttled = 1;
+		else
+			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+
+		if (!is_leftmost(curr, &rq->dl))
+			resched_task(curr);
+	}
+
+	/*
+	 * Because -- for now -- we share the rt bandwidth, we need to
+	 * account our runtime there too, otherwise actual rt tasks
+	 * would be able to exceed the shared quota.
+	 *
+	 * Account to the root rt group for now.
+	 *
+	 * The solution we're working towards is having the RT groups scheduled
+	 * using deadline servers -- however there's a few nasties to figure
+	 * out before that can happen.
+	 */
+	if (rt_bandwidth_enabled()) {
+		struct rt_rq *rt_rq = &rq->rt;
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_time += delta_exec;
+		/*
+		 * We'll let actual RT tasks worry about the overflow here, we
+		 * have our own CBS to keep us inline -- see above.
+		 */
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+}
+
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+	struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+	if (next && dl_prio(next->prio))
+		return next->dl.deadline;
+	else
+		return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	if (dl_rq->earliest_dl.curr == 0 ||
+	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+		/*
+		 * If the dl_rq had no -deadline tasks, or if the new task
+		 * has shorter deadline than the current one on dl_rq, we
+		 * know that the previous earliest becomes our next earliest,
+		 * as the new task becomes the earliest itself.
+		 */
+		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+		dl_rq->earliest_dl.curr = deadline;
+		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
+	} else if (dl_rq->earliest_dl.next == 0 ||
+		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+		/*
+		 * On the other hand, if the new -deadline task has a
+		 * a later deadline than the earliest one on dl_rq, but
+		 * it is earlier than the next (if any), we must
+		 * recompute the next-earliest.
+		 */
+		dl_rq->earliest_dl.next = next_deadline(rq);
+	}
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	/*
+	 * Since we may have removed our earliest (and/or next earliest)
+	 * task we must recompute them.
+	 */
+	if (!dl_rq->dl_nr_running) {
+		dl_rq->earliest_dl.curr = 0;
+		dl_rq->earliest_dl.next = 0;
+		cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+	} else {
+		struct rb_node *leftmost = dl_rq->rb_leftmost;
+		struct sched_dl_entity *entry;
+
+		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+		dl_rq->earliest_dl.curr = entry->deadline;
+		dl_rq->earliest_dl.next = next_deadline(rq);
+		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
+	}
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	int prio = dl_task_of(dl_se)->prio;
+	u64 deadline = dl_se->deadline;
+
+	WARN_ON(!dl_prio(prio));
+	dl_rq->dl_nr_running++;
+
+	inc_dl_deadline(dl_rq, deadline);
+	inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	int prio = dl_task_of(dl_se)->prio;
+
+	WARN_ON(!dl_prio(prio));
+	WARN_ON(!dl_rq->dl_nr_running);
+	dl_rq->dl_nr_running--;
+
+	dec_dl_deadline(dl_rq, dl_se->deadline);
+	dec_dl_migration(dl_se, dl_rq);
+}
+
+static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rb_node **link = &dl_rq->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct sched_dl_entity *entry;
+	int leftmost = 1;
+
+	BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct sched_dl_entity, rb_node);
+		if (dl_time_before(dl_se->deadline, entry->deadline))
+			link = &parent->rb_left;
+		else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		dl_rq->rb_leftmost = &dl_se->rb_node;
+
+	rb_link_node(&dl_se->rb_node, parent, link);
+	rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+
+	inc_dl_tasks(dl_se, dl_rq);
+}
+
+static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+	if (RB_EMPTY_NODE(&dl_se->rb_node))
+		return;
+
+	if (dl_rq->rb_leftmost == &dl_se->rb_node) {
+		struct rb_node *next_node;
+
+		next_node = rb_next(&dl_se->rb_node);
+		dl_rq->rb_leftmost = next_node;
+	}
+
+	rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+	RB_CLEAR_NODE(&dl_se->rb_node);
+
+	dec_dl_tasks(dl_se, dl_rq);
+}
+
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+		  struct sched_dl_entity *pi_se, int flags)
+{
+	BUG_ON(on_dl_rq(dl_se));
+
+	/*
+	 * If this is a wakeup or a new instance, the scheduling
+	 * parameters of the task might need updating. Otherwise,
+	 * we want a replenishment of its runtime.
+	 */
+	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se, pi_se);
+	else
+		update_dl_entity(dl_se, pi_se);
+
+	__enqueue_dl_entity(dl_se);
+}
+
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	__dequeue_dl_entity(dl_se);
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	struct task_struct *pi_task = rt_mutex_get_top_task(p);
+	struct sched_dl_entity *pi_se = &p->dl;
+
+	/*
+	 * Use the scheduling parameters of the top pi-waiter
+	 * task if we have one and its (relative) deadline is
+	 * smaller than our one... OTW we keep our runtime and
+	 * deadline.
+	 */
+	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+		pi_se = &pi_task->dl;
+
+	/*
+	 * If p is throttled, we do nothing. In fact, if it exhausted
+	 * its budget it needs a replenishment and, since it now is on
+	 * its rq, the bandwidth timer callback (which clearly has not
+	 * run yet) will take care of this.
+	 */
+	if (p->dl.dl_throttled)
+		return;
+
+	enqueue_dl_entity(&p->dl, pi_se, flags);
+
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+		enqueue_pushable_dl_task(rq, p);
+
+	inc_nr_running(rq);
+}
+
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	dequeue_dl_entity(&p->dl);
+	dequeue_pushable_dl_task(rq, p);
+}
+
+static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	update_curr_dl(rq);
+	__dequeue_task_dl(rq, p, flags);
+
+	dec_nr_running(rq);
+}
+
+/*
+ * Yield task semantic for -deadline tasks is:
+ *
+ *   get off from the CPU until our next instance, with
+ *   a new runtime. This is of little use now, since we
+ *   don't have a bandwidth reclaiming mechanism. Anyway,
+ *   bandwidth reclaiming is planned for the future, and
+ *   yield_task_dl will indicate that some spare budget
+ *   is available for other task instances to use it.
+ */
+static void yield_task_dl(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	/*
+	 * We make the task go to sleep until its current deadline by
+	 * forcing its runtime to zero. This way, update_curr_dl() stops
+	 * it and the bandwidth timer will wake it up and will give it
+	 * new scheduling parameters (thanks to dl_new=1).
+	 */
+	if (p->dl.runtime > 0) {
+		rq->curr->dl.dl_new = 1;
+		p->dl.runtime = 0;
+	}
+	update_curr_dl(rq);
+}
+
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+	struct task_struct *curr;
+	struct rq *rq;
+
+	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+		goto out;
+
+	rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+	/*
+	 * If we are dealing with a -deadline task, we must
+	 * decide where to wake it up.
+	 * If it has a later deadline and the current task
+	 * on this rq can't move (provided the waking task
+	 * can!) we prefer to send it somewhere else. On the
+	 * other hand, if it has a shorter deadline, we
+	 * try to make it stay here, it might be important.
+	 */
+	if (unlikely(dl_task(curr)) &&
+	    (curr->nr_cpus_allowed < 2 ||
+	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+	    (p->nr_cpus_allowed > 1)) {
+		int target = find_later_rq(p);
+
+		if (target != -1)
+			cpu = target;
+	}
+	rcu_read_unlock();
+
+out:
+	return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+	/*
+	 * Current can't be migrated, useless to reschedule,
+	 * let's hope p can move out.
+	 */
+	if (rq->curr->nr_cpus_allowed == 1 ||
+	    cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
+		return;
+
+	/*
+	 * p is migratable, so let's not schedule it and
+	 * see if it is pushed or pulled somewhere else.
+	 */
+	if (p->nr_cpus_allowed != 1 &&
+	    cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
+		return;
+
+	resched_task(rq->curr);
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Only called when both the current and waking task are -deadline
+ * tasks.
+ */
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+				  int flags)
+{
+	if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
+		resched_task(rq->curr);
+		return;
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * In the unlikely case current and p have the same deadline
+	 * let us try to decide what's the best thing to do...
+	 */
+	if ((p->dl.deadline == rq->curr->dl.deadline) &&
+	    !test_tsk_need_resched(rq->curr))
+		check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+	s64 delta = p->dl.dl_runtime - p->dl.runtime;
+
+	if (delta > 10000)
+		hrtick_start(rq, p->dl.runtime);
+}
+#endif
+
+static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
+						   struct dl_rq *dl_rq)
+{
+	struct rb_node *left = dl_rq->rb_leftmost;
+
+	if (!left)
+		return NULL;
+
+	return rb_entry(left, struct sched_dl_entity, rb_node);
+}
+
+struct task_struct *pick_next_task_dl(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se;
+	struct task_struct *p;
+	struct dl_rq *dl_rq;
+
+	dl_rq = &rq->dl;
+
+	if (unlikely(!dl_rq->dl_nr_running))
+		return NULL;
+
+	dl_se = pick_next_dl_entity(rq, dl_rq);
+	BUG_ON(!dl_se);
+
+	p = dl_task_of(dl_se);
+	p->se.exec_start = rq_clock_task(rq);
+
+	/* Running task will never be pushed. */
+       dequeue_pushable_dl_task(rq, p);
+
+#ifdef CONFIG_SCHED_HRTICK
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, p);
+#endif
+
+#ifdef CONFIG_SMP
+	rq->post_schedule = has_pushable_dl_tasks(rq);
+#endif /* CONFIG_SMP */
+
+	return p;
+}
+
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+{
+	update_curr_dl(rq);
+
+	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+		enqueue_pushable_dl_task(rq, p);
+}
+
+static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
+{
+	update_curr_dl(rq);
+
+#ifdef CONFIG_SCHED_HRTICK
+	if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+		start_hrtick_dl(rq, p);
+#endif
+}
+
+static void task_fork_dl(struct task_struct *p)
+{
+	/*
+	 * SCHED_DEADLINE tasks cannot fork and this is achieved through
+	 * sched_fork()
+	 */
+}
+
+static void task_dead_dl(struct task_struct *p)
+{
+	struct hrtimer *timer = &p->dl.dl_timer;
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+	/*
+	 * Since we are TASK_DEAD we won't slip out of the domain!
+	 */
+	raw_spin_lock_irq(&dl_b->lock);
+	dl_b->total_bw -= p->dl.dl_bw;
+	raw_spin_unlock_irq(&dl_b->lock);
+
+	hrtimer_cancel(timer);
+}
+
+static void set_curr_task_dl(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	p->se.exec_start = rq_clock_task(rq);
+
+	/* You can't push away the running task */
+	dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+	if (!task_running(rq, p) &&
+	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+	    (p->nr_cpus_allowed > 1))
+		return 1;
+
+	return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+	struct rb_node *next_node = rq->dl.rb_leftmost;
+	struct sched_dl_entity *dl_se;
+	struct task_struct *p = NULL;
+
+next_node:
+	next_node = rb_next(next_node);
+	if (next_node) {
+		dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+		p = dl_task_of(dl_se);
+
+		if (pick_dl_task(rq, p, cpu))
+			return p;
+
+		goto next_node;
+	}
+
+	return NULL;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+	struct sched_domain *sd;
+	struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+	int this_cpu = smp_processor_id();
+	int best_cpu, cpu = task_cpu(task);
+
+	/* Make sure the mask is initialized first */
+	if (unlikely(!later_mask))
+		return -1;
+
+	if (task->nr_cpus_allowed == 1)
+		return -1;
+
+	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
+			task, later_mask);
+	if (best_cpu == -1)
+		return -1;
+
+	/*
+	 * If we are here, some target has been found,
+	 * the most suitable of which is cached in best_cpu.
+	 * This is, among the runqueues where the current tasks
+	 * have later deadlines than the task's one, the rq
+	 * with the latest possible one.
+	 *
+	 * Now we check how well this matches with task's
+	 * affinity and system topology.
+	 *
+	 * The last cpu where the task run is our first
+	 * guess, since it is most likely cache-hot there.
+	 */
+	if (cpumask_test_cpu(cpu, later_mask))
+		return cpu;
+	/*
+	 * Check if this_cpu is to be skipped (i.e., it is
+	 * not in the mask) or not.
+	 */
+	if (!cpumask_test_cpu(this_cpu, later_mask))
+		this_cpu = -1;
+
+	rcu_read_lock();
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_AFFINE) {
+
+			/*
+			 * If possible, preempting this_cpu is
+			 * cheaper than migrating.
+			 */
+			if (this_cpu != -1 &&
+			    cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+				rcu_read_unlock();
+				return this_cpu;
+			}
+
+			/*
+			 * Last chance: if best_cpu is valid and is
+			 * in the mask, that becomes our choice.
+			 */
+			if (best_cpu < nr_cpu_ids &&
+			    cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+				rcu_read_unlock();
+				return best_cpu;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * At this point, all our guesses failed, we just return
+	 * 'something', and let the caller sort the things out.
+	 */
+	if (this_cpu != -1)
+		return this_cpu;
+
+	cpu = cpumask_any(later_mask);
+	if (cpu < nr_cpu_ids)
+		return cpu;
+
+	return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+	struct rq *later_rq = NULL;
+	int tries;
+	int cpu;
+
+	for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+		cpu = find_later_rq(task);
+
+		if ((cpu == -1) || (cpu == rq->cpu))
+			break;
+
+		later_rq = cpu_rq(cpu);
+
+		/* Retry if something changed. */
+		if (double_lock_balance(rq, later_rq)) {
+			if (unlikely(task_rq(task) != rq ||
+				     !cpumask_test_cpu(later_rq->cpu,
+				                       &task->cpus_allowed) ||
+				     task_running(rq, task) || !task->on_rq)) {
+				double_unlock_balance(rq, later_rq);
+				later_rq = NULL;
+				break;
+			}
+		}
+
+		/*
+		 * If the rq we found has no -deadline task, or
+		 * its earliest one has a later deadline than our
+		 * task, the rq is a good one.
+		 */
+		if (!later_rq->dl.dl_nr_running ||
+		    dl_time_before(task->dl.deadline,
+				   later_rq->dl.earliest_dl.curr))
+			break;
+
+		/* Otherwise we try again. */
+		double_unlock_balance(rq, later_rq);
+		later_rq = NULL;
+	}
+
+	return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+	struct task_struct *p;
+
+	if (!has_pushable_dl_tasks(rq))
+		return NULL;
+
+	p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+		     struct task_struct, pushable_dl_tasks);
+
+	BUG_ON(rq->cpu != task_cpu(p));
+	BUG_ON(task_current(rq, p));
+	BUG_ON(p->nr_cpus_allowed <= 1);
+
+	BUG_ON(!p->on_rq);
+	BUG_ON(!dl_task(p));
+
+	return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+	struct task_struct *next_task;
+	struct rq *later_rq;
+
+	if (!rq->dl.overloaded)
+		return 0;
+
+	next_task = pick_next_pushable_dl_task(rq);
+	if (!next_task)
+		return 0;
+
+retry:
+	if (unlikely(next_task == rq->curr)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	/*
+	 * If next_task preempts rq->curr, and rq->curr
+	 * can move away, it makes sense to just reschedule
+	 * without going further in pushing next_task.
+	 */
+	if (dl_task(rq->curr) &&
+	    dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+	    rq->curr->nr_cpus_allowed > 1) {
+		resched_task(rq->curr);
+		return 0;
+	}
+
+	/* We might release rq lock */
+	get_task_struct(next_task);
+
+	/* Will lock the rq it'll find */
+	later_rq = find_lock_later_rq(next_task, rq);
+	if (!later_rq) {
+		struct task_struct *task;
+
+		/*
+		 * We must check all this again, since
+		 * find_lock_later_rq releases rq->lock and it is
+		 * then possible that next_task has migrated.
+		 */
+		task = pick_next_pushable_dl_task(rq);
+		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+			/*
+			 * The task is still there. We don't try
+			 * again, some other cpu will pull it when ready.
+			 */
+			dequeue_pushable_dl_task(rq, next_task);
+			goto out;
+		}
+
+		if (!task)
+			/* No more tasks */
+			goto out;
+
+		put_task_struct(next_task);
+		next_task = task;
+		goto retry;
+	}
+
+	deactivate_task(rq, next_task, 0);
+	set_task_cpu(next_task, later_rq->cpu);
+	activate_task(later_rq, next_task, 0);
+
+	resched_task(later_rq->curr);
+
+	double_unlock_balance(rq, later_rq);
+
+out:
+	put_task_struct(next_task);
+
+	return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+	/* Terminates as it moves a -deadline task */
+	while (push_dl_task(rq))
+		;
+}
+
+static int pull_dl_task(struct rq *this_rq)
+{
+	int this_cpu = this_rq->cpu, ret = 0, cpu;
+	struct task_struct *p;
+	struct rq *src_rq;
+	u64 dmin = LONG_MAX;
+
+	if (likely(!dl_overloaded(this_rq)))
+		return 0;
+
+	/*
+	 * Match the barrier from dl_set_overloaded; this guarantees that if we
+	 * see overloaded we must also see the dlo_mask bit.
+	 */
+	smp_rmb();
+
+	for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+		if (this_cpu == cpu)
+			continue;
+
+		src_rq = cpu_rq(cpu);
+
+		/*
+		 * It looks racy, abd it is! However, as in sched_rt.c,
+		 * we are fine with this.
+		 */
+		if (this_rq->dl.dl_nr_running &&
+		    dl_time_before(this_rq->dl.earliest_dl.curr,
+				   src_rq->dl.earliest_dl.next))
+			continue;
+
+		/* Might drop this_rq->lock */
+		double_lock_balance(this_rq, src_rq);
+
+		/*
+		 * If there are no more pullable tasks on the
+		 * rq, we're done with it.
+		 */
+		if (src_rq->dl.dl_nr_running <= 1)
+			goto skip;
+
+		p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+		/*
+		 * We found a task to be pulled if:
+		 *  - it preempts our current (if there's one),
+		 *  - it will preempt the last one we pulled (if any).
+		 */
+		if (p && dl_time_before(p->dl.deadline, dmin) &&
+		    (!this_rq->dl.dl_nr_running ||
+		     dl_time_before(p->dl.deadline,
+				    this_rq->dl.earliest_dl.curr))) {
+			WARN_ON(p == src_rq->curr);
+			WARN_ON(!p->on_rq);
+
+			/*
+			 * Then we pull iff p has actually an earlier
+			 * deadline than the current task of its runqueue.
+			 */
+			if (dl_time_before(p->dl.deadline,
+					   src_rq->curr->dl.deadline))
+				goto skip;
+
+			ret = 1;
+
+			deactivate_task(src_rq, p, 0);
+			set_task_cpu(p, this_cpu);
+			activate_task(this_rq, p, 0);
+			dmin = p->dl.deadline;
+
+			/* Is there any other task even earlier? */
+		}
+skip:
+		double_unlock_balance(this_rq, src_rq);
+	}
+
+	return ret;
+}
+
+static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
+{
+	/* Try to pull other tasks here */
+	if (dl_task(prev))
+		pull_dl_task(rq);
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+	push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+	if (!task_running(rq, p) &&
+	    !test_tsk_need_resched(rq->curr) &&
+	    has_pushable_dl_tasks(rq) &&
+	    p->nr_cpus_allowed > 1 &&
+	    dl_task(rq->curr) &&
+	    (rq->curr->nr_cpus_allowed < 2 ||
+	     dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+		push_dl_tasks(rq);
+	}
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+				const struct cpumask *new_mask)
+{
+	struct rq *rq;
+	int weight;
+
+	BUG_ON(!dl_task(p));
+
+	/*
+	 * Update only if the task is actually running (i.e.,
+	 * it is on the rq AND it is not throttled).
+	 */
+	if (!on_dl_rq(&p->dl))
+		return;
+
+	weight = cpumask_weight(new_mask);
+
+	/*
+	 * Only update if the process changes its state from whether it
+	 * can migrate or not.
+	 */
+	if ((p->nr_cpus_allowed > 1) == (weight > 1))
+		return;
+
+	rq = task_rq(p);
+
+	/*
+	 * The process used to be able to migrate OR it can now migrate
+	 */
+	if (weight <= 1) {
+		if (!task_current(rq, p))
+			dequeue_pushable_dl_task(rq, p);
+		BUG_ON(!rq->dl.dl_nr_migratory);
+		rq->dl.dl_nr_migratory--;
+	} else {
+		if (!task_current(rq, p))
+			enqueue_pushable_dl_task(rq, p);
+		rq->dl.dl_nr_migratory++;
+	}
+
+	update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+	if (rq->dl.overloaded)
+		dl_set_overload(rq);
+
+	if (rq->dl.dl_nr_running > 0)
+		cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+	if (rq->dl.overloaded)
+		dl_clear_overload(rq);
+
+	cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+}
+
+void init_sched_dl_class(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+					GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
+static void switched_from_dl(struct rq *rq, struct task_struct *p)
+{
+	if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
+		hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+	/*
+	 * Since this might be the only -deadline task on the rq,
+	 * this is the right place to try to pull some other one
+	 * from an overloaded cpu, if any.
+	 */
+	if (!rq->dl.dl_nr_running)
+		pull_dl_task(rq);
+#endif
+}
+
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
+static void switched_to_dl(struct rq *rq, struct task_struct *p)
+{
+	int check_resched = 1;
+
+	/*
+	 * If p is throttled, don't consider the possibility
+	 * of preempting rq->curr, the check will be done right
+	 * after its runtime will get replenished.
+	 */
+	if (unlikely(p->dl.dl_throttled))
+		return;
+
+	if (p->on_rq || rq->curr != p) {
+#ifdef CONFIG_SMP
+		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+			/* Only reschedule if pushing failed */
+			check_resched = 0;
+#endif /* CONFIG_SMP */
+		if (check_resched && task_has_dl_policy(rq->curr))
+			check_preempt_curr_dl(rq, p, 0);
+	}
+}
+
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
+static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+			    int oldprio)
+{
+	if (p->on_rq || rq->curr == p) {
+#ifdef CONFIG_SMP
+		/*
+		 * This might be too much, but unfortunately
+		 * we don't have the old deadline value, and
+		 * we can't argue if the task is increasing
+		 * or lowering its prio, so...
+		 */
+		if (!rq->dl.overloaded)
+			pull_dl_task(rq);
+
+		/*
+		 * If we now have a earlier deadline task than p,
+		 * then reschedule, provided p is still on this
+		 * runqueue.
+		 */
+		if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+		    rq->curr == p)
+			resched_task(p);
+#else
+		/*
+		 * Again, we don't know if p has a earlier
+		 * or later deadline, so let's blindly set a
+		 * (maybe not needed) rescheduling point.
+		 */
+		resched_task(p);
+#endif /* CONFIG_SMP */
+	} else
+		switched_to_dl(rq, p);
+}
+
+const struct sched_class dl_sched_class = {
+	.next			= &rt_sched_class,
+	.enqueue_task		= enqueue_task_dl,
+	.dequeue_task		= dequeue_task_dl,
+	.yield_task		= yield_task_dl,
+
+	.check_preempt_curr	= check_preempt_curr_dl,
+
+	.pick_next_task		= pick_next_task_dl,
+	.put_prev_task		= put_prev_task_dl,
+
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_dl,
+	.set_cpus_allowed       = set_cpus_allowed_dl,
+	.rq_online              = rq_online_dl,
+	.rq_offline             = rq_offline_dl,
+	.pre_schedule		= pre_schedule_dl,
+	.post_schedule		= post_schedule_dl,
+	.task_woken		= task_woken_dl,
+#endif
+
+	.set_curr_task		= set_curr_task_dl,
+	.task_tick		= task_tick_dl,
+	.task_fork              = task_fork_dl,
+	.task_dead		= task_dead_dl,
+
+	.prio_changed           = prio_changed_dl,
+	.switched_from		= switched_from_dl,
+	.switched_to		= switched_to_dl,
+};
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5c34d18..dd52e7f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -139,7 +139,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+	SEQ_printf(m, " %d", task_node(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
@@ -371,7 +371,7 @@ static void sched_debug_header(struct seq_file *m)
 	PN(cpu_clk);
 	P(jiffies);
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-	P(sched_clock_stable);
+	P(sched_clock_stable());
 #endif
 #undef PN
 #undef P
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fd773ad..966cc2b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,59 +178,61 @@ void sched_init_granularity(void)
 	update_sysctl();
 }
 
-#if BITS_PER_LONG == 32
-# define WMULT_CONST	(~0UL)
-#else
-# define WMULT_CONST	(1UL << 32)
-#endif
-
+#define WMULT_CONST	(~0U)
 #define WMULT_SHIFT	32
 
-/*
- * Shift right and round:
- */
-#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+static void __update_inv_weight(struct load_weight *lw)
+{
+	unsigned long w;
+
+	if (likely(lw->inv_weight))
+		return;
+
+	w = scale_load_down(lw->weight);
+
+	if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
+		lw->inv_weight = 1;
+	else if (unlikely(!w))
+		lw->inv_weight = WMULT_CONST;
+	else
+		lw->inv_weight = WMULT_CONST / w;
+}
 
 /*
- * delta *= weight / lw
+ * delta_exec * weight / lw.weight
+ *   OR
+ * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
+ *
+ * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
+ * we're guaranteed shift stays positive because inv_weight is guaranteed to
+ * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
+ *
+ * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
+ * weight/lw.weight <= 1, and therefore our shift will also be positive.
  */
-static unsigned long
-calc_delta_mine(unsigned long delta_exec, unsigned long weight,
-		struct load_weight *lw)
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
 {
-	u64 tmp;
+	u64 fact = scale_load_down(weight);
+	int shift = WMULT_SHIFT;
 
-	/*
-	 * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
-	 * entities since MIN_SHARES = 2. Treat weight as 1 if less than
-	 * 2^SCHED_LOAD_RESOLUTION.
-	 */
-	if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
-		tmp = (u64)delta_exec * scale_load_down(weight);
-	else
-		tmp = (u64)delta_exec;
-
-	if (!lw->inv_weight) {
-		unsigned long w = scale_load_down(lw->weight);
+	__update_inv_weight(lw);
 
-		if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
-			lw->inv_weight = 1;
-		else if (unlikely(!w))
-			lw->inv_weight = WMULT_CONST;
-		else
-			lw->inv_weight = WMULT_CONST / w;
+	if (unlikely(fact >> 32)) {
+		while (fact >> 32) {
+			fact >>= 1;
+			shift--;
+		}
 	}
 
-	/*
-	 * Check whether we'd overflow the 64-bit multiplication:
-	 */
-	if (unlikely(tmp > WMULT_CONST))
-		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
-			WMULT_SHIFT/2);
-	else
-		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+	/* hint to use a 32x32->64 mul */
+	fact = (u64)(u32)fact * lw->inv_weight;
+
+	while (fact >> 32) {
+		fact >>= 1;
+		shift--;
+	}
 
-	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+	return mul_u64_u32_shr(delta_exec, fact, shift);
 }
 
 
@@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 /*
  * delta /= w
  */
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
 {
 	if (unlikely(se->load.weight != NICE_0_LOAD))
-		delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+		delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
 
 	return delta;
 }
@@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 			update_load_add(&lw, se->load.weight);
 			load = &lw;
 		}
-		slice = calc_delta_mine(slice, se->load.weight, load);
+		slice = __calc_delta(slice, se->load.weight, load);
 	}
 	return slice;
 }
@@ -703,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p)
 #endif
 
 /*
- * Update the current task's runtime statistics. Skip current tasks that
- * are not in our scheduling class.
+ * Update the current task's runtime statistics.
  */
-static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
-	      unsigned long delta_exec)
-{
-	unsigned long delta_exec_weighted;
-
-	schedstat_set(curr->statistics.exec_max,
-		      max((u64)delta_exec, curr->statistics.exec_max));
-
-	curr->sum_exec_runtime += delta_exec;
-	schedstat_add(cfs_rq, exec_clock, delta_exec);
-	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
-
-	curr->vruntime += delta_exec_weighted;
-	update_min_vruntime(cfs_rq);
-}
-
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
 	u64 now = rq_clock_task(rq_of(cfs_rq));
-	unsigned long delta_exec;
+	u64 delta_exec;
 
 	if (unlikely(!curr))
 		return;
 
-	/*
-	 * Get the amount of time the current task was running
-	 * since the last time we changed load (this cannot
-	 * overflow on 32 bits):
-	 */
-	delta_exec = (unsigned long)(now - curr->exec_start);
-	if (!delta_exec)
+	delta_exec = now - curr->exec_start;
+	if (unlikely((s64)delta_exec <= 0))
 		return;
 
-	__update_curr(cfs_rq, curr, delta_exec);
 	curr->exec_start = now;
 
+	schedstat_set(curr->statistics.exec_max,
+		      max(delta_exec, curr->statistics.exec_max));
+
+	curr->sum_exec_runtime += delta_exec;
+	schedstat_add(cfs_rq, exec_clock, delta_exec);
+
+	curr->vruntime += calc_delta_fair(delta_exec, curr);
+	update_min_vruntime(cfs_rq);
+
 	if (entity_is_task(curr)) {
 		struct task_struct *curtask = task_of(curr);
 
@@ -886,15 +872,6 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
-/*
- * Once a preferred node is selected the scheduler balancer will prefer moving
- * a task to that node for sysctl_numa_balancing_settle_count number of PTE
- * scans. This will give the process the chance to accumulate more faults on
- * the preferred node but still allow the scheduler to move the task again if
- * the nodes CPUs are overloaded.
- */
-unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
-
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -944,7 +921,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+	return p->numa_group->faults[task_faults_idx(nid, 0)] +
+		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
 /*
@@ -1037,7 +1015,7 @@ struct task_numa_env {
 
 	struct numa_stats src_stats, dst_stats;
 
-	int imbalance_pct, idx;
+	int imbalance_pct;
 
 	struct task_struct *best_task;
 	long best_imp;
@@ -1225,7 +1203,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+		p->numa_preferred_nid = task_node(p);
 		return -EINVAL;
 	}
 
@@ -1272,11 +1250,15 @@ static int task_numa_migrate(struct task_struct *p)
 	p->numa_scan_period = task_scan_min(p);
 
 	if (env.best_task == NULL) {
-		int ret = migrate_task_to(p, env.best_cpu);
+		ret = migrate_task_to(p, env.best_cpu);
+		if (ret != 0)
+			trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
 		return ret;
 	}
 
 	ret = migrate_swap(p, env.best_task);
+	if (ret != 0)
+		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
 	put_task_struct(env.best_task);
 	return ret;
 }
@@ -1292,7 +1274,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 	p->numa_migrate_retry = jiffies + HZ;
 
 	/* Success if task is already running on preferred CPU */
-	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+	if (task_node(p) == p->numa_preferred_nid)
 		return;
 
 	/* Otherwise, try migrate to a CPU on the preferred node */
@@ -1364,7 +1346,6 @@ static void update_task_scan_period(struct task_struct *p,
 		 * scanning faster if shared accesses dominate as it may
 		 * simply bounce migrations uselessly
 		 */
-		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
 		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
 		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
 	}
@@ -1752,6 +1733,13 @@ void task_numa_work(struct callback_head *work)
 		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
 			continue;
 
+		/*
+		 * Skip inaccessible VMAs to avoid any confusion between
+		 * PROT_NONE and NUMA hinting ptes
+		 */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
@@ -2372,13 +2360,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 		}
 		wakeup = 0;
 	} else {
-		/*
-		 * Task re-woke on same cpu (or else migrate_task_rq_fair()
-		 * would have made count negative); we must be careful to avoid
-		 * double-accounting blocked time after synchronizing decays.
-		 */
-		se->avg.last_runnable_update += __synchronize_entity_decay(se)
-							<< 20;
+		__synchronize_entity_decay(se);
 	}
 
 	/* migrated tasks did not contribute to our blocked load */
@@ -3015,8 +2997,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	}
 }
 
-static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				     unsigned long delta_exec)
+static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
 	/* dock delta_exec before expiring quota (as it could span periods) */
 	cfs_rq->runtime_remaining -= delta_exec;
@@ -3034,7 +3015,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 }
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
 	if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
 		return;
@@ -3574,8 +3555,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 	return rq_clock_task(rq_of(cfs_rq));
 }
 
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-				     unsigned long delta_exec) {}
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -3932,7 +3912,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
+	if (!tg->parent)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
@@ -4110,12 +4090,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
  */
 static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int load_idx)
+		  int this_cpu, int sd_flag)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int load_idx = sd->forkexec_idx;
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
+	if (sd_flag & SD_BALANCE_WAKE)
+		load_idx = sd->wake_idx;
+
 	do {
 		unsigned long load, avg_load;
 		int local_group;
@@ -4283,7 +4267,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	}
 
 	while (sd) {
-		int load_idx = sd->forkexec_idx;
 		struct sched_group *group;
 		int weight;
 
@@ -4292,10 +4275,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			continue;
 		}
 
-		if (sd_flag & SD_BALANCE_WAKE)
-			load_idx = sd->wake_idx;
-
-		group = find_idlest_group(sd, p, cpu, load_idx);
+		group = find_idlest_group(sd, p, cpu, sd_flag);
 		if (!group) {
 			sd = sd->child;
 			continue;
@@ -5521,7 +5501,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
 			int local_group, struct sg_lb_stats *sgs)
 {
-	unsigned long nr_running;
 	unsigned long load;
 	int i;
 
@@ -5530,8 +5509,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
-		nr_running = rq->nr_running;
-
 		/* Bias balancing toward cpus of our domain */
 		if (local_group)
 			load = target_load(i, load_idx);
@@ -5539,7 +5516,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += nr_running;
+		sgs->sum_nr_running += rq->nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
 		sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -6530,7 +6507,7 @@ static struct {
 	unsigned long next_balance;     /* in jiffy units */
 } nohz ____cacheline_aligned;
 
-static inline int find_new_ilb(int call_cpu)
+static inline int find_new_ilb(void)
 {
 	int ilb = cpumask_first(nohz.idle_cpus_mask);
 
@@ -6545,13 +6522,13 @@ static inline int find_new_ilb(int call_cpu)
  * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
  * CPU (if there is one).
  */
-static void nohz_balancer_kick(int cpu)
+static void nohz_balancer_kick(void)
 {
 	int ilb_cpu;
 
 	nohz.next_balance++;
 
-	ilb_cpu = find_new_ilb(cpu);
+	ilb_cpu = find_new_ilb();
 
 	if (ilb_cpu >= nr_cpu_ids)
 		return;
@@ -6661,10 +6638,10 @@ void update_max_interval(void)
  *
  * Balancing parameters are set up in init_sched_domains.
  */
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 {
 	int continue_balancing = 1;
-	struct rq *rq = cpu_rq(cpu);
+	int cpu = rq->cpu;
 	unsigned long interval;
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
@@ -6761,9 +6738,9 @@ out:
  * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
  * rebalancing for all the cpus for whom scheduler ticks are stopped.
  */
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 {
-	struct rq *this_rq = cpu_rq(this_cpu);
+	int this_cpu = this_rq->cpu;
 	struct rq *rq;
 	int balance_cpu;
 
@@ -6790,7 +6767,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
 		update_idle_cpu_load(rq);
 		raw_spin_unlock_irq(&rq->lock);
 
-		rebalance_domains(balance_cpu, CPU_IDLE);
+		rebalance_domains(rq, CPU_IDLE);
 
 		if (time_after(this_rq->next_balance, rq->next_balance))
 			this_rq->next_balance = rq->next_balance;
@@ -6809,14 +6786,14 @@ end:
  *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
  *     domain span are idle.
  */
-static inline int nohz_kick_needed(struct rq *rq, int cpu)
+static inline int nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
 	struct sched_group_power *sgp;
-	int nr_busy;
+	int nr_busy, cpu = rq->cpu;
 
-	if (unlikely(idle_cpu(cpu)))
+	if (unlikely(rq->idle_balance))
 		return 0;
 
        /*
@@ -6865,7 +6842,7 @@ need_kick:
 	return 1;
 }
 #else
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
 #endif
 
 /*
@@ -6874,38 +6851,39 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
  */
 static void run_rebalance_domains(struct softirq_action *h)
 {
-	int this_cpu = smp_processor_id();
-	struct rq *this_rq = cpu_rq(this_cpu);
+	struct rq *this_rq = this_rq();
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
-	rebalance_domains(this_cpu, idle);
+	rebalance_domains(this_rq, idle);
 
 	/*
 	 * If this cpu has a pending nohz_balance_kick, then do the
 	 * balancing on behalf of the other idle cpus whose ticks are
 	 * stopped.
 	 */
-	nohz_idle_balance(this_cpu, idle);
+	nohz_idle_balance(this_rq, idle);
 }
 
-static inline int on_null_domain(int cpu)
+static inline int on_null_domain(struct rq *rq)
 {
-	return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+	return !rcu_dereference_sched(rq->sd);
 }
 
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
-void trigger_load_balance(struct rq *rq, int cpu)
+void trigger_load_balance(struct rq *rq)
 {
 	/* Don't need to rebalance while attached to NULL domain */
-	if (time_after_eq(jiffies, rq->next_balance) &&
-	    likely(!on_null_domain(cpu)))
+	if (unlikely(on_null_domain(rq)))
+		return;
+
+	if (time_after_eq(jiffies, rq->next_balance))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
-	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
-		nohz_balancer_kick(cpu);
+	if (nohz_kick_needed(rq))
+		nohz_balancer_kick();
 #endif
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7d57275..a2740b7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -901,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Change rq's cpupri only if rt_rq is the top queue.
+	 */
+	if (&rq->rt != rt_rq)
+		return;
+#endif
 	if (rq->online && prio < prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
@@ -910,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Change rq's cpupri only if rt_rq is the top queue.
+	 */
+	if (&rq->rt != rt_rq)
+		return;
+#endif
 	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
@@ -1724,7 +1738,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
 	    p->nr_cpus_allowed > 1 &&
-	    rt_task(rq->curr) &&
+	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b2..c2119fd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -9,6 +10,7 @@
 #include <linux/slab.h>
 
 #include "cpupri.h"
+#include "cpudeadline.h"
 #include "cpuacct.h"
 
 struct rq;
@@ -73,6 +75,13 @@ extern void update_cpu_load_active(struct rq *this_rq);
 #define NICE_0_SHIFT		SCHED_LOAD_SHIFT
 
 /*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9  -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
  * These are the 'tuning knobs' of the scheduler:
  */
 
@@ -81,11 +90,19 @@ extern void update_cpu_load_active(struct rq *this_rq);
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+static inline int fair_policy(int policy)
+{
+	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
 static inline int rt_policy(int policy)
 {
-	if (policy == SCHED_FIFO || policy == SCHED_RR)
-		return 1;
-	return 0;
+	return policy == SCHED_FIFO || policy == SCHED_RR;
+}
+
+static inline int dl_policy(int policy)
+{
+	return policy == SCHED_DEADLINE;
 }
 
 static inline int task_has_rt_policy(struct task_struct *p)
@@ -93,6 +110,25 @@ static inline int task_has_rt_policy(struct task_struct *p)
 	return rt_policy(p->policy);
 }
 
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+	return dl_policy(p->policy);
+}
+
+static inline bool dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+	return dl_time_before(a->deadline, b->deadline);
+}
+
 /*
  * This is the priority-queue data structure of the RT scheduling class:
  */
@@ -108,6 +144,47 @@ struct rt_bandwidth {
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
 };
+/*
+ * To keep the bandwidth of -deadline tasks and groups under control
+ * we need some place where:
+ *  - store the maximum -deadline bandwidth of the system (the group);
+ *  - cache the fraction of that bandwidth that is currently allocated.
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * meaning that:
+ *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
+ *  - dl_total_bw array contains, in the i-eth element, the currently
+ *    allocated bandwidth on the i-eth CPU.
+ * Moreover, groups consume bandwidth on each CPU, while tasks only
+ * consume bandwidth on the CPU they're running on.
+ * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
+ * that will be shown the next time the proc or cgroup controls will
+ * be red. It on its turn can be changed by writing on its own
+ * control.
+ */
+struct dl_bandwidth {
+	raw_spinlock_t dl_runtime_lock;
+	u64 dl_runtime;
+	u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+	return sysctl_sched_rt_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+	raw_spinlock_t lock;
+	u64 bw, total_bw;
+};
 
 extern struct mutex sched_domains_mutex;
 
@@ -364,6 +441,42 @@ struct rt_rq {
 #endif
 };
 
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+	/* runqueue is an rbtree, ordered by deadline */
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+
+	unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Deadline values of the currently executing and the
+	 * earliest ready task on this rq. Caching these facilitates
+	 * the decision wether or not a ready but not running task
+	 * should migrate somewhere else.
+	 */
+	struct {
+		u64 curr;
+		u64 next;
+	} earliest_dl;
+
+	unsigned long dl_nr_migratory;
+	unsigned long dl_nr_total;
+	int overloaded;
+
+	/*
+	 * Tasks on this rq that can be pushed away. They are kept in
+	 * an rb-tree, ordered by tasks' deadlines, with caching
+	 * of the leftmost (earliest deadline) element.
+	 */
+	struct rb_root pushable_dl_tasks_root;
+	struct rb_node *pushable_dl_tasks_leftmost;
+#else
+	struct dl_bw dl_bw;
+#endif
+};
+
 #ifdef CONFIG_SMP
 
 /*
@@ -382,6 +495,15 @@ struct root_domain {
 	cpumask_var_t online;
 
 	/*
+	 * The bit corresponding to a CPU gets set here if such CPU has more
+	 * than one runnable -deadline task (as it is below for RT tasks).
+	 */
+	cpumask_var_t dlo_mask;
+	atomic_t dlo_count;
+	struct dl_bw dl_bw;
+	struct cpudl cpudl;
+
+	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
 	 */
@@ -432,6 +554,7 @@ struct rq {
 
 	struct cfs_rq cfs;
 	struct rt_rq rt;
+	struct dl_rq dl;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
@@ -827,8 +950,6 @@ static inline u64 global_rt_runtime(void)
 	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-
-
 static inline int task_current(struct rq *rq, struct task_struct *p)
 {
 	return rq->curr == p;
@@ -988,6 +1109,7 @@ static const u32 prio_to_wmult[40] = {
 #else
 #define ENQUEUE_WAKING		0
 #endif
+#define ENQUEUE_REPLENISH	8
 
 #define DEQUEUE_SLEEP		1
 
@@ -1023,6 +1145,7 @@ struct sched_class {
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
+	void (*task_dead) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
@@ -1042,6 +1165,7 @@ struct sched_class {
    for (class = sched_class_highest; class; class = class->next)
 
 extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
 extern const struct sched_class rt_sched_class;
 extern const struct sched_class fair_sched_class;
 extern const struct sched_class idle_sched_class;
@@ -1051,7 +1175,7 @@ extern const struct sched_class idle_sched_class;
 
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
-extern void trigger_load_balance(struct rq *rq, int cpu);
+extern void trigger_load_balance(struct rq *rq);
 extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
@@ -1068,8 +1192,11 @@ static inline void idle_balance(int cpu, struct rq *rq)
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
 
 extern void resched_task(struct task_struct *p);
 extern void resched_cpu(int cpu);
@@ -1077,6 +1204,12 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
+extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+
+unsigned long to_ratio(u64 period, u64 runtime);
+
 extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
@@ -1353,6 +1486,7 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
 
 extern void cfs_bandwidth_usage_inc(void);
 extern void cfs_bandwidth_usage_dec(void);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 47197de..fdb6bb0 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -103,7 +103,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 const struct sched_class stop_sched_class = {
-	.next			= &rt_sched_class,
+	.next			= &dl_sched_class,
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
diff --git a/kernel/signal.c b/kernel/signal.c
index f481228..5d4b05a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2047,8 +2047,8 @@ static bool do_signal_stop(int signr)
 		if (task_set_jobctl_pending(current, signr | gstop))
 			sig->group_stop_count++;
 
-		for (t = next_thread(current); t != current;
-		     t = next_thread(t)) {
+		t = current;
+		while_each_thread(current, t) {
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
@@ -3125,8 +3125,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 			rm_from_queue_full(&mask, &t->signal->shared_pending);
 			do {
 				rm_from_queue_full(&mask, &t->pending);
-				t = next_thread(t);
-			} while (t != current);
+			} while_each_thread(current, t);
 		}
 	}
 
diff --git a/kernel/smp.c b/kernel/smp.c
index bd9f940..ffee35b 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -23,17 +23,11 @@ enum {
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
-	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
 
-struct call_single_queue {
-	struct list_head	list;
-	raw_spinlock_t		lock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -47,14 +41,8 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				cpu_to_node(cpu)))
 			return notifier_from_errno(-ENOMEM);
-		if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
-				cpu_to_node(cpu))) {
-			free_cpumask_var(cfd->cpumask);
-			return notifier_from_errno(-ENOMEM);
-		}
 		cfd->csd = alloc_percpu(struct call_single_data);
 		if (!cfd->csd) {
-			free_cpumask_var(cfd->cpumask_ipi);
 			free_cpumask_var(cfd->cpumask);
 			return notifier_from_errno(-ENOMEM);
 		}
@@ -67,7 +55,6 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
-		free_cpumask_var(cfd->cpumask_ipi);
 		free_percpu(cfd->csd);
 		break;
 #endif
@@ -85,12 +72,8 @@ void __init call_function_init(void)
 	void *cpu = (void *)(long)smp_processor_id();
 	int i;
 
-	for_each_possible_cpu(i) {
-		struct call_single_queue *q = &per_cpu(call_single_queue, i);
-
-		raw_spin_lock_init(&q->lock);
-		INIT_LIST_HEAD(&q->list);
-	}
+	for_each_possible_cpu(i)
+		init_llist_head(&per_cpu(call_single_queue, i));
 
 	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
 	register_cpu_notifier(&hotplug_cfd_notifier);
@@ -141,18 +124,9 @@ static void csd_unlock(struct call_single_data *csd)
  */
 static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 {
-	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
-	unsigned long flags;
-	int ipi;
-
 	if (wait)
 		csd->flags |= CSD_FLAG_WAIT;
 
-	raw_spin_lock_irqsave(&dst->lock, flags);
-	ipi = list_empty(&dst->list);
-	list_add_tail(&csd->list, &dst->list);
-	raw_spin_unlock_irqrestore(&dst->lock, flags);
-
 	/*
 	 * The list addition should be visible before sending the IPI
 	 * handler locks the list to pull the entry off it because of
@@ -164,7 +138,7 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 	 * locking and barrier primitives. Generic code isn't really
 	 * equipped to do the right thing...
 	 */
-	if (ipi)
+	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
 		arch_send_call_function_single_ipi(cpu);
 
 	if (wait)
@@ -177,27 +151,26 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
  */
 void generic_smp_call_function_single_interrupt(void)
 {
-	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
-	LIST_HEAD(list);
+	struct llist_node *entry, *next;
 
 	/*
 	 * Shouldn't receive this interrupt on a cpu that is not yet online.
 	 */
 	WARN_ON_ONCE(!cpu_online(smp_processor_id()));
 
-	raw_spin_lock(&q->lock);
-	list_replace_init(&q->list, &list);
-	raw_spin_unlock(&q->lock);
+	entry = llist_del_all(&__get_cpu_var(call_single_queue));
+	entry = llist_reverse_order(entry);
 
-	while (!list_empty(&list)) {
+	while (entry) {
 		struct call_single_data *csd;
 
-		csd = list_entry(list.next, struct call_single_data, list);
-		list_del(&csd->list);
+		next = entry->next;
 
+		csd = llist_entry(entry, struct call_single_data, llist);
 		csd->func(csd->info);
-
 		csd_unlock(csd);
+
+		entry = next;
 	}
 }
 
@@ -402,30 +375,17 @@ void smp_call_function_many(const struct cpumask *mask,
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
-	/*
-	 * After we put an entry into the list, cfd->cpumask may be cleared
-	 * again when another CPU sends another IPI for a SMP function call, so
-	 * cfd->cpumask will be zero.
-	 */
-	cpumask_copy(cfd->cpumask_ipi, cfd->cpumask);
-
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
-		struct call_single_queue *dst =
-					&per_cpu(call_single_queue, cpu);
-		unsigned long flags;
 
 		csd_lock(csd);
 		csd->func = func;
 		csd->info = info;
-
-		raw_spin_lock_irqsave(&dst->lock, flags);
-		list_add_tail(&csd->list, &dst->list);
-		raw_spin_unlock_irqrestore(&dst->lock, flags);
+		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
+	arch_send_call_function_ipi_mask(cfd->cpumask);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025cc..490fcbb 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -8,6 +8,8 @@
  *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
@@ -54,7 +56,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
 
 DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
-char *softirq_to_name[NR_SOFTIRQS] = {
+const char * const softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
 	"TASKLET", "SCHED", "HRTIMER", "RCU"
 };
@@ -89,7 +91,7 @@ static void wakeup_softirqd(void)
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip, unsigned int cnt)
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
 
@@ -107,33 +109,21 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 	/*
 	 * Were softirqs turned off above:
 	 */
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
 
 	if (preempt_count() == cnt)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
-#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
-{
-	preempt_count_add(cnt);
-	barrier();
-}
+EXPORT_SYMBOL(__local_bh_disable_ip);
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
-void local_bh_disable(void)
-{
-	__local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
-}
-
-EXPORT_SYMBOL(local_bh_disable);
-
 static void __local_bh_enable(unsigned int cnt)
 {
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_on(_RET_IP_);
 	preempt_count_sub(cnt);
 }
@@ -148,10 +138,9 @@ void _local_bh_enable(void)
 	WARN_ON_ONCE(in_irq());
 	__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
 }
-
 EXPORT_SYMBOL(_local_bh_enable);
 
-static inline void _local_bh_enable_ip(unsigned long ip)
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 {
 	WARN_ON_ONCE(in_irq() || irqs_disabled());
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -165,8 +154,8 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 	/*
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
- 	 */
-	preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
+	 */
+	preempt_count_sub(cnt - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending())) {
 		/*
@@ -182,18 +171,7 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 #endif
 	preempt_check_resched();
 }
-
-void local_bh_enable(void)
-{
-	_local_bh_enable_ip(_RET_IP_);
-}
-EXPORT_SYMBOL(local_bh_enable);
-
-void local_bh_enable_ip(unsigned long ip)
-{
-	_local_bh_enable_ip(ip);
-}
-EXPORT_SYMBOL(local_bh_enable_ip);
+EXPORT_SYMBOL(__local_bh_enable_ip);
 
 /*
  * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
@@ -211,14 +189,49 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+	bool in_hardirq = false;
+
+	if (trace_hardirq_context(current)) {
+		in_hardirq = true;
+		trace_hardirq_exit();
+	}
+
+	lockdep_softirq_enter();
+
+	return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+	lockdep_softirq_exit();
+
+	if (in_hardirq)
+		trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
-	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
-	int cpu;
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
+	struct softirq_action *h;
+	bool in_hardirq;
+	__u32 pending;
+	int softirq_bit;
+	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -230,8 +243,8 @@ asmlinkage void __do_softirq(void)
 	pending = local_softirq_pending();
 	account_irq_enter_time(current);
 
-	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+	in_hardirq = lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -242,30 +255,30 @@ restart:
 
 	h = softirq_vec;
 
-	do {
-		if (pending & 1) {
-			unsigned int vec_nr = h - softirq_vec;
-			int prev_count = preempt_count();
-
-			kstat_incr_softirqs_this_cpu(vec_nr);
-
-			trace_softirq_entry(vec_nr);
-			h->action(h);
-			trace_softirq_exit(vec_nr);
-			if (unlikely(prev_count != preempt_count())) {
-				printk(KERN_ERR "huh, entered softirq %u %s %p"
-				       "with preempt_count %08x,"
-				       " exited with %08x?\n", vec_nr,
-				       softirq_to_name[vec_nr], h->action,
-				       prev_count, preempt_count());
-				preempt_count_set(prev_count);
-			}
+	while ((softirq_bit = ffs(pending))) {
+		unsigned int vec_nr;
+		int prev_count;
+
+		h += softirq_bit - 1;
+
+		vec_nr = h - softirq_vec;
+		prev_count = preempt_count();
+
+		kstat_incr_softirqs_this_cpu(vec_nr);
 
-			rcu_bh_qs(cpu);
+		trace_softirq_entry(vec_nr);
+		h->action(h);
+		trace_softirq_exit(vec_nr);
+		if (unlikely(prev_count != preempt_count())) {
+			pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
+			       vec_nr, softirq_to_name[vec_nr], h->action,
+			       prev_count, preempt_count());
+			preempt_count_set(prev_count);
 		}
+		rcu_bh_qs(cpu);
 		h++;
-		pending >>= 1;
-	} while (pending);
+		pending >>= softirq_bit;
+	}
 
 	local_irq_disable();
 
@@ -278,16 +291,13 @@ restart:
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
-
+	lockdep_softirq_end(in_hardirq);
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-
-
 asmlinkage void do_softirq(void)
 {
 	__u32 pending;
@@ -311,8 +321,6 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-	int cpu = smp_processor_id();
-
 	rcu_irq_enter();
 	if (is_idle_task(current) && !in_interrupt()) {
 		/*
@@ -320,7 +328,7 @@ void irq_enter(void)
 		 * here, as softirq will be serviced on return from interrupt.
 		 */
 		local_bh_disable();
-		tick_check_idle(cpu);
+		tick_irq_enter();
 		_local_bh_enable();
 	}
 
@@ -375,13 +383,13 @@ void irq_exit(void)
 #endif
 
 	account_irq_exit_time(current);
-	trace_hardirq_exit();
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 }
 
 /*
@@ -427,8 +435,7 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
 /*
  * Tasklets
  */
-struct tasklet_head
-{
+struct tasklet_head {
 	struct tasklet_struct *head;
 	struct tasklet_struct **tail;
 };
@@ -447,7 +454,6 @@ void __tasklet_schedule(struct tasklet_struct *t)
 	raise_softirq_irqoff(TASKLET_SOFTIRQ);
 	local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL(__tasklet_schedule);
 
 void __tasklet_hi_schedule(struct tasklet_struct *t)
@@ -461,7 +467,6 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
 	raise_softirq_irqoff(HI_SOFTIRQ);
 	local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL(__tasklet_hi_schedule);
 
 void __tasklet_hi_schedule_first(struct tasklet_struct *t)
@@ -472,7 +477,6 @@ void __tasklet_hi_schedule_first(struct tasklet_struct *t)
 	__this_cpu_write(tasklet_hi_vec.head, t);
 	__raise_softirq_irqoff(HI_SOFTIRQ);
 }
-
 EXPORT_SYMBOL(__tasklet_hi_schedule_first);
 
 static void tasklet_action(struct softirq_action *a)
@@ -492,7 +496,8 @@ static void tasklet_action(struct softirq_action *a)
 
 		if (tasklet_trylock(t)) {
 			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
+							&t->state))
 					BUG();
 				t->func(t->data);
 				tasklet_unlock(t);
@@ -527,7 +532,8 @@ static void tasklet_hi_action(struct softirq_action *a)
 
 		if (tasklet_trylock(t)) {
 			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
+							&t->state))
 					BUG();
 				t->func(t->data);
 				tasklet_unlock(t);
@@ -545,7 +551,6 @@ static void tasklet_hi_action(struct softirq_action *a)
 	}
 }
 
-
 void tasklet_init(struct tasklet_struct *t,
 		  void (*func)(unsigned long), unsigned long data)
 {
@@ -555,13 +560,12 @@ void tasklet_init(struct tasklet_struct *t,
 	t->func = func;
 	t->data = data;
 }
-
 EXPORT_SYMBOL(tasklet_init);
 
 void tasklet_kill(struct tasklet_struct *t)
 {
 	if (in_interrupt())
-		printk("Attempt to kill tasklet from interrupt\n");
+		pr_notice("Attempt to kill tasklet from interrupt\n");
 
 	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
 		do {
@@ -571,7 +575,6 @@ void tasklet_kill(struct tasklet_struct *t)
 	tasklet_unlock_wait(t);
 	clear_bit(TASKLET_STATE_SCHED, &t->state);
 }
-
 EXPORT_SYMBOL(tasklet_kill);
 
 /*
@@ -721,9 +724,8 @@ static void takeover_tasklets(unsigned int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int cpu_callback(struct notifier_block *nfb,
-				  unsigned long action,
-				  void *hcpu)
+static int cpu_callback(struct notifier_block *nfb, unsigned long action,
+			void *hcpu)
 {
 	switch (action) {
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/sys.c b/kernel/sys.c
index c723113..c0a58be 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -895,8 +895,7 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
  * only important on a multi-user system anyway, to make sure one user
  * can't send a signal to a process owned by another.  -TYT, 12/12/91
  *
- * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
- * LBT 04.03.94
+ * !PF_FORKNOEXEC check to conform completely to POSIX.
  */
 SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 {
@@ -932,7 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 		if (task_session(p) != task_session(group_leader))
 			goto out;
 		err = -EACCES;
-		if (p->did_exec)
+		if (!(p->flags & PF_FORKNOEXEC))
 			goto out;
 	} else {
 		err = -ESRCH;
@@ -1572,8 +1571,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			t = p;
 			do {
 				accumulate_thread_rusage(t, r);
-				t = next_thread(t);
-			} while (t != p);
+			} while_each_thread(p, t);
 			break;
 
 		default:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a6047..49e13e1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -62,6 +62,7 @@
 #include <linux/capability.h>
 #include <linux/binfmts.h>
 #include <linux/sched/sysctl.h>
+#include <linux/kexec.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -95,8 +96,6 @@
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
 extern int max_threads;
 extern int suid_dumpable;
 #ifdef CONFIG_COREDUMP
@@ -122,6 +121,8 @@ extern int blk_iopoll_enabled;
 static int sixty = 60;
 #endif
 
+static int __maybe_unused neg_one = -1;
+
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
@@ -385,19 +386,21 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname       = "numa_balancing_settle_count",
-		.data           = &sysctl_numa_balancing_settle_count,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{
 		.procname       = "numa_balancing_migrate_deferred",
 		.data           = &sysctl_numa_balancing_migrate_deferred,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_numa_balancing,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
@@ -614,6 +617,18 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_KEXEC
+	{
+		.procname	= "kexec_load_disabled",
+		.data		= &kexec_load_disabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		/* only handle a transition from default "0" to "1" */
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &one,
+	},
+#endif
 #ifdef CONFIG_MODULES
 	{
 		.procname	= "modprobe",
@@ -984,9 +999,10 @@ static struct ctl_table kern_table[] = {
 	{
 		.procname	= "hung_task_warnings",
 		.data		= &sysctl_hung_task_warnings,
-		.maxlen		= sizeof(unsigned long),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &neg_one,
 	},
 #endif
 #ifdef CONFIG_COMPAT
@@ -1128,7 +1144,14 @@ static struct ctl_table vm_table[] = {
 		.data		= &sysctl_overcommit_ratio,
 		.maxlen		= sizeof(sysctl_overcommit_ratio),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= overcommit_ratio_handler,
+	},
+	{
+		.procname	= "overcommit_kbytes",
+		.data		= &sysctl_overcommit_kbytes,
+		.maxlen		= sizeof(sysctl_overcommit_kbytes),
+		.mode		= 0644,
+		.proc_handler	= overcommit_kbytes_handler,
 	},
 	{
 		.procname	= "page-cluster", 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba..a6a5bf5 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
  * HZ shrinks, so values greater than 8 overflow 32bits when
  * HZ=100.
  */
+#if HZ < 34
+#define JIFFIES_SHIFT	6
+#elif HZ < 67
+#define JIFFIES_SHIFT	7
+#else
 #define JIFFIES_SHIFT	8
+#endif
 
 static cycle_t jiffies_read(struct clocksource *cs)
 {
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 68b7993..0abb364 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -74,7 +74,7 @@ unsigned long long notrace sched_clock(void)
 		return cd.epoch_ns;
 
 	do {
-		seq = read_seqcount_begin(&cd.seq);
+		seq = raw_read_seqcount_begin(&cd.seq);
 		epoch_cyc = cd.epoch_cyc;
 		epoch_ns = cd.epoch_ns;
 	} while (read_seqcount_retry(&cd.seq, seq));
@@ -99,10 +99,10 @@ static void notrace update_sched_clock(void)
 			  cd.mult, cd.shift);
 
 	raw_local_irq_save(flags);
-	write_seqcount_begin(&cd.seq);
+	raw_write_seqcount_begin(&cd.seq);
 	cd.epoch_ns = ns;
 	cd.epoch_cyc = cyc;
-	write_seqcount_end(&cd.seq);
+	raw_write_seqcount_end(&cd.seq);
 	raw_local_irq_restore(flags);
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690..98977a5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -538,10 +538,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  * Called from irq_enter() when idle was interrupted to reenable the
  * per cpu device.
  */
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
 {
-	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
-		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+	if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+		struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 
 		/*
 		 * We might be in the middle of switching over from
@@ -756,6 +756,7 @@ out:
 static void tick_broadcast_clear_oneshot(int cpu)
 {
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 }
 
 static void tick_broadcast_init_next_event(struct cpumask *mask,
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 162b03a..20b2fe3 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -85,6 +85,7 @@ static void tick_periodic(int cpu)
 
 		do_timer(1);
 		write_sequnlock(&jiffies_lock);
+		update_wall_time();
 	}
 
 	update_process_times(user_mode(get_irq_regs()));
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7..8329669 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -51,7 +51,7 @@ extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
@@ -62,7 +62,7 @@ static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
@@ -155,3 +155,4 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 #endif
 
 extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ea20f7d..9f8af69 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -86,6 +86,7 @@ static void tick_do_update_jiffies64(ktime_t now)
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	}
 	write_sequnlock(&jiffies_lock);
+	update_wall_time();
 }
 
 /*
@@ -177,7 +178,7 @@ static bool can_stop_full_tick(void)
 	 * TODO: kick full dynticks CPUs when
 	 * sched_clock_stable is set.
 	 */
-	if (!sched_clock_stable) {
+	if (!sched_clock_stable()) {
 		trace_tick_stop(0, "unstable sched clock\n");
 		/*
 		 * Don't allow the user to think they can get
@@ -391,11 +392,9 @@ __setup("nohz=", setup_tick_nohz);
  */
 static void tick_nohz_update_jiffies(ktime_t now)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long flags;
 
-	ts->idle_waketime = now;
+	__this_cpu_write(tick_cpu_sched.idle_waketime, now);
 
 	local_irq_save(flags);
 	tick_do_update_jiffies64(now);
@@ -426,17 +425,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
 
 }
 
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
-	update_ts_time_stats(cpu, ts, now, NULL);
+	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
 }
 
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
 	ktime_t now = ktime_get();
 
@@ -536,12 +533,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
 
+	time_delta = timekeeping_max_deferment();
+
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&jiffies_lock);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
-		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&jiffies_lock, seq));
 
 	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
@@ -681,18 +679,18 @@ out:
 static void tick_nohz_full_stop_tick(struct tick_sched *ts)
 {
 #ifdef CONFIG_NO_HZ_FULL
-       int cpu = smp_processor_id();
+	int cpu = smp_processor_id();
 
-       if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
-               return;
+	if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+		return;
 
-       if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
-	       return;
+	if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+		return;
 
-       if (!can_stop_full_tick())
-               return;
+	if (!can_stop_full_tick())
+		return;
 
-       tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+	tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
 #endif
 }
 
@@ -754,7 +752,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
-	now = tick_nohz_start_idle(cpu, ts);
+	now = tick_nohz_start_idle(ts);
 
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
@@ -911,8 +909,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	local_irq_disable();
@@ -925,7 +922,7 @@ void tick_nohz_idle_exit(void)
 		now = ktime_get();
 
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 
 	if (ts->tick_stopped) {
 		tick_nohz_restart_sched_tick(ts, now);
@@ -1009,12 +1006,10 @@ static void tick_nohz_switch_to_nohz(void)
  * timer and do not touch the other magic bits which need to be done
  * when idle is left.
  */
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 {
 #if 0
 	/* Switch back to 2.6.27 behaviour */
-
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t delta;
 
 	/*
@@ -1029,36 +1024,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
 #endif
 }
 
-static inline void tick_check_nohz(int cpu)
+static inline void tick_nohz_irq_enter(void)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	if (!ts->idle_active && !ts->tick_stopped)
 		return;
 	now = ktime_get();
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 	if (ts->tick_stopped) {
 		tick_nohz_update_jiffies(now);
-		tick_nohz_kick_tick(cpu, now);
+		tick_nohz_kick_tick(ts, now);
 	}
 }
 
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_nohz_irq_enter(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
  * Called from irq_enter to notify about the possible interruption of idle()
  */
-void tick_check_idle(int cpu)
+void tick_irq_enter(void)
 {
-	tick_check_oneshot_broadcast(cpu);
-	tick_check_nohz(cpu);
+	tick_check_oneshot_broadcast_this_cpu();
+	tick_nohz_irq_enter();
 }
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 87b4f00..0aa4ce81 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -77,7 +77,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec_to_ktime(tmp);
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
 }
 
 static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -90,8 +90,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
 }
 
 /**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
  *
+ * @tk:		The target timekeeper to setup.
  * @clock:		Pointer to clocksource.
  *
  * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
@@ -595,7 +596,7 @@ s32 timekeeping_get_tai_offset(void)
 static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
 {
 	tk->tai_offset = tai_offset;
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
 }
 
 /**
@@ -610,6 +611,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&timekeeper_seq);
 	__timekeeping_set_tai_offset(tk, tai_offset);
+	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	clock_was_set();
@@ -1023,6 +1025,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
+
+	timekeeping_update(tk, TK_MIRROR);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
@@ -1130,16 +1134,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 		 * we can adjust by 1.
 		 */
 		error >>= 2;
-		/*
-		 * XXX - In update_wall_time, we round up to the next
-		 * nanosecond, and store the amount rounded up into
-		 * the error. This causes the likely below to be unlikely.
-		 *
-		 * The proper fix is to avoid rounding up by using
-		 * the high precision tk->xtime_nsec instead of
-		 * xtime.tv_nsec everywhere. Fixing this will take some
-		 * time.
-		 */
 		if (likely(error <= interval))
 			adj = 1;
 		else
@@ -1255,7 +1249,7 @@ out_adjust:
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
-	unsigned int action = 0;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1277,11 +1271,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
-			action = TK_CLOCK_WAS_SET;
+			clock_set = TK_CLOCK_WAS_SET;
 		}
 	}
-	return action;
+	return clock_set;
 }
 
 /**
@@ -1294,7 +1287,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1308,7 +1302,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1359,14 +1353,14 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
  */
-static void update_wall_time(void)
+void update_wall_time(void)
 {
 	struct clocksource *clock;
 	struct timekeeper *real_tk = &timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
-	unsigned int action;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1401,7 +1395,8 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1419,7 +1414,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	action = accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1435,10 +1430,12 @@ static void update_wall_time(void)
 	 * updating.
 	 */
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, action);
+	timekeeping_update(real_tk, clock_set);
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_set)
+		clock_was_set();
 }
 
 /**
@@ -1583,7 +1580,6 @@ struct timespec get_monotonic_coarse(void)
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	update_wall_time();
 	calc_global_load(ticks);
 }
 
@@ -1698,12 +1694,14 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
-		update_pvclock_gtod(tk, true);
-		clock_was_set_delayed();
+		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	}
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	if (tai != orig_tai)
+		clock_was_set();
+
 	ntp_notify_cmos_timer();
 
 	return ret;
@@ -1739,4 +1737,5 @@ void xtime_update(unsigned long ticks)
 	write_seqlock(&jiffies_lock);
 	do_timer(ticks);
 	write_sequnlock(&jiffies_lock);
+	update_wall_time();
 }
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d7e2068..1378e84 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM_RUNTIME),y)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index f785aef..b418cb0 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -781,8 +781,8 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 	if (!error && !bio_flagged(bio, BIO_UPTODATE))
 		error = EIO;
 
-	__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
-			error, 0, NULL);
+	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
+			bio->bi_rw, what, error, 0, NULL);
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
@@ -885,8 +885,9 @@ static void blk_add_trace_split(void *ignore,
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(pdu);
 
-		__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
-				BLK_TA_SPLIT, !bio_flagged(bio, BIO_UPTODATE),
+		__blk_add_trace(bt, bio->bi_iter.bi_sector,
+				bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
+				!bio_flagged(bio, BIO_UPTODATE),
 				sizeof(rpdu), &rpdu);
 	}
 }
@@ -918,9 +919,9 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.device_to   = cpu_to_be32(bio->bi_bdev->bd_dev);
 	r.sector_from = cpu_to_be64(from);
 
-	__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
-			BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
-			sizeof(r), &r);
+	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
+			bio->bi_rw, BLK_TA_REMAP,
+			!bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
 }
 
 /**
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0e9f9ea..cd7f76d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@ int function_trace_stop __read_mostly;
 
 /* Current function tracing op */
 struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
 
 /* List for set_ftrace_pid's pids. */
 LIST_HEAD(ftrace_pids);
@@ -278,6 +280,29 @@ static void update_global_ops(void)
 	global_ops.func = func;
 }
 
+static void ftrace_sync(struct work_struct *work)
+{
+	/*
+	 * This function is just a stub to implement a hard force
+	 * of synchronize_sched(). This requires synchronizing
+	 * tasks even in userspace and idle.
+	 *
+	 * Yes, function tracing is rude.
+	 */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+	/* Probably not needed, but do it anyway */
+	smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
 static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
@@ -296,16 +321,61 @@ static void update_ftrace_function(void)
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
 		if (ftrace_ops_list == &global_ops)
-			function_trace_op = ftrace_global_list;
+			set_function_trace_op = ftrace_global_list;
 		else
-			function_trace_op = ftrace_ops_list;
+			set_function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
 	} else {
 		/* Just use the default ftrace_ops */
-		function_trace_op = &ftrace_list_end;
+		set_function_trace_op = &ftrace_list_end;
 		func = ftrace_ops_list_func;
 	}
 
+	/* If there's no change, then do nothing more here */
+	if (ftrace_trace_function == func)
+		return;
+
+	update_function_graph_func();
+
+	/*
+	 * If we are using the list function, it doesn't care
+	 * about the function_trace_ops.
+	 */
+	if (func == ftrace_ops_list_func) {
+		ftrace_trace_function = func;
+		/*
+		 * Don't even bother setting function_trace_ops,
+		 * it would be racy to do so anyway.
+		 */
+		return;
+	}
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+	/*
+	 * For static tracing, we need to be a bit more careful.
+	 * The function change takes affect immediately. Thus,
+	 * we need to coorditate the setting of the function_trace_ops
+	 * with the setting of the ftrace_trace_function.
+	 *
+	 * Set the function to the list ops, which will call the
+	 * function we want, albeit indirectly, but it handles the
+	 * ftrace_ops and doesn't depend on function_trace_op.
+	 */
+	ftrace_trace_function = ftrace_ops_list_func;
+	/*
+	 * Make sure all CPUs see this. Yes this is slow, but static
+	 * tracing is slow and nasty to have enabled.
+	 */
+	schedule_on_each_cpu(ftrace_sync);
+	/* Now all cpus are using the list ops. */
+	function_trace_op = set_function_trace_op;
+	/* Make sure the function_trace_op is visible on all CPUs */
+	smp_wmb();
+	/* Nasty way to force a rmb on all cpus */
+	smp_call_function(ftrace_sync_ipi, NULL, 1);
+	/* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
 	ftrace_trace_function = func;
 }
 
@@ -410,17 +480,6 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	return 0;
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_sched(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
@@ -439,20 +498,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
-		if (!ret) {
-			/*
-			 * The ftrace_ops is now removed from the list,
-			 * so there'll be no new users. We must ensure
-			 * all current users are done before we free
-			 * the control data.
-			 * Note synchronize_sched() is not enough, as we
-			 * use preempt_disable() to do RCU, but the function
-			 * tracer can be called where RCU is not active
-			 * (before user_exit()).
-			 */
-			schedule_on_each_cpu(ftrace_sync);
-			control_ops_free(ops);
-		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -462,17 +507,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (ftrace_enabled)
 		update_ftrace_function();
 
-	/*
-	 * Dynamic ops may be freed, we must make sure that all
-	 * callers are done before leaving this function.
-	 *
-	 * Again, normal synchronize_sched() is not good enough.
-	 * We need to do a hard force of sched synchronization.
-	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		schedule_on_each_cpu(ftrace_sync);
-
-
 	return 0;
 }
 
@@ -775,7 +809,7 @@ static int ftrace_profile_init(void)
 	int cpu;
 	int ret = 0;
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		ret = ftrace_profile_init_cpu(cpu);
 		if (ret)
 			break;
@@ -1082,19 +1116,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
-loff_t
-ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
-{
-	loff_t ret;
-
-	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, whence);
-	else
-		file->f_pos = ret = 1;
-
-	return ret;
-}
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -1992,8 +2013,14 @@ void ftrace_modify_all_code(int command)
 	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (update && ftrace_trace_function != ftrace_ops_list_func)
+	if (update && ftrace_trace_function != ftrace_ops_list_func) {
+		function_trace_op = set_function_trace_op;
+		smp_wmb();
+		/* If irqs are disabled, we are in stop machine */
+		if (!irqs_disabled())
+			smp_call_function(ftrace_sync_ipi, NULL, 1);
 		ftrace_update_ftrace_func(ftrace_trace_function);
+	}
 
 	if (command & FTRACE_START_FUNC_RET)
 		ftrace_enable_ftrace_graph_caller();
@@ -2156,10 +2183,41 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		command |= FTRACE_UPDATE_TRACE_FUNC;
 	}
 
-	if (!command || !ftrace_enabled)
+	if (!command || !ftrace_enabled) {
+		/*
+		 * If these are control ops, they still need their
+		 * per_cpu field freed. Since, function tracing is
+		 * not currently active, we can just free them
+		 * without synchronizing all CPUs.
+		 */
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
 		return 0;
+	}
 
 	ftrace_run_update_code(command);
+
+	/*
+	 * Dynamic ops may be freed, we must make sure that all
+	 * callers are done before leaving this function.
+	 * The same goes for freeing the per_cpu data of the control
+	 * ops.
+	 *
+	 * Again, normal synchronize_sched() is not good enough.
+	 * We need to do a hard force of sched synchronization.
+	 * This is because we use preempt_disable() to do RCU, but
+	 * the function tracers can be called where RCU is not watching
+	 * (like before user_exit()). We can not rely on the RCU
+	 * infrastructure to do the synchronization, thus we must do it
+	 * ourselves.
+	 */
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+		schedule_on_each_cpu(ftrace_sync);
+
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
+	}
+
 	return 0;
 }
 
@@ -2739,7 +2797,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_filter_lseek() should be used as the lseek routine, and
+ * tracing_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -3767,7 +3825,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_filter_lseek,
+	.llseek = tracing_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3775,7 +3833,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
 	.read = seq_read,
 	.write = ftrace_notrace_write,
-	.llseek = ftrace_filter_lseek,
+	.llseek = tracing_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -4038,7 +4096,7 @@ static const struct file_operations ftrace_graph_fops = {
 	.open		= ftrace_graph_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
-	.llseek		= ftrace_filter_lseek,
+	.llseek		= tracing_lseek,
 	.release	= ftrace_graph_release,
 };
 
@@ -4046,7 +4104,7 @@ static const struct file_operations ftrace_graph_notrace_fops = {
 	.open		= ftrace_graph_notrace_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
-	.llseek		= ftrace_filter_lseek,
+	.llseek		= tracing_lseek,
 	.release	= ftrace_graph_release,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -4719,7 +4777,7 @@ static const struct file_operations ftrace_pid_fops = {
 	.open		= ftrace_pid_open,
 	.write		= ftrace_pid_write,
 	.read		= seq_read,
-	.llseek		= ftrace_filter_lseek,
+	.llseek		= tracing_lseek,
 	.release	= ftrace_pid_release,
 };
 
@@ -4862,6 +4920,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 trace_func_graph_ret_t ftrace_graph_return =
 			(trace_func_graph_ret_t)ftrace_stub;
 trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -5003,6 +5062,30 @@ static struct ftrace_ops fgraph_ops __read_mostly = {
 				FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+	if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+		return 0;
+	return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+	if (ftrace_ops_list == &ftrace_list_end ||
+	    (ftrace_ops_list == &global_ops &&
+	     global_ops.next == &ftrace_list_end))
+		ftrace_graph_entry = __ftrace_graph_entry;
+	else
+		ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -5027,7 +5110,16 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	}
 
 	ftrace_graph_return = retfunc;
-	ftrace_graph_entry = entryfunc;
+
+	/*
+	 * Update the indirect function to the entryfunc, and the
+	 * function that gets called to the entry_test first. Then
+	 * call the update fgraph entry function to determine if
+	 * the entryfunc should be called directly or not.
+	 */
+	__ftrace_graph_entry = entryfunc;
+	ftrace_graph_entry = ftrace_graph_entry_test;
+	update_function_graph_func();
 
 	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
@@ -5046,6 +5138,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
+	__ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cc2f66f..fc4da2d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2397,6 +2397,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	write &= RB_WRITE_MASK;
 	tail = write - length;
 
+	/*
+	 * If this is the first commit on the page, then it has the same
+	 * timestamp as the page itself.
+	 */
+	if (!tail)
+		delta = 0;
+
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE))
 		return rb_move_tail(cpu_buffer, length, tail,
@@ -2558,7 +2565,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 		if (unlikely(test_time_stamp(delta))) {
 			int local_clock_stable = 1;
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-			local_clock_stable = sched_clock_stable;
+			local_clock_stable = sched_clock_stable();
 #endif
 			WARN_ONCE(delta > (1ULL << 59),
 				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d20cd9..815c878 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -455,6 +455,9 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	unsigned long irq_flags;
 	int alloc;
 
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
+
 	alloc = sizeof(*entry) + size + 2; /* possible \n added */
 
 	local_save_flags(irq_flags);
@@ -495,6 +498,9 @@ int __trace_bputs(unsigned long ip, const char *str)
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
 
+	if (unlikely(tracing_selftest_running || tracing_disabled))
+		return 0;
+
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
@@ -595,6 +601,28 @@ void free_snapshot(struct trace_array *tr)
 }
 
 /**
+ * tracing_alloc_snapshot - allocate snapshot buffer.
+ *
+ * This only allocates the snapshot buffer if it isn't already
+ * allocated - it doesn't also take a snapshot.
+ *
+ * This is meant to be used in cases where the snapshot buffer needs
+ * to be set up for events that can't sleep but need to be able to
+ * trigger a snapshot.
+ */
+int tracing_alloc_snapshot(void)
+{
+	struct trace_array *tr = &global_trace;
+	int ret;
+
+	ret = alloc_snapshot(tr);
+	WARN_ON(ret < 0);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
+
+/**
  * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
  *
  * This is similar to trace_snapshot(), but it will allocate the
@@ -607,11 +635,10 @@ void free_snapshot(struct trace_array *tr)
  */
 void tracing_snapshot_alloc(void)
 {
-	struct trace_array *tr = &global_trace;
 	int ret;
 
-	ret = alloc_snapshot(tr);
-	if (WARN_ON(ret < 0))
+	ret = tracing_alloc_snapshot();
+	if (ret < 0)
 		return;
 
 	tracing_snapshot();
@@ -623,6 +650,12 @@ void tracing_snapshot(void)
 	WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
 }
 EXPORT_SYMBOL_GPL(tracing_snapshot);
+int tracing_alloc_snapshot(void)
+{
+	WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used");
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
 void tracing_snapshot_alloc(void)
 {
 	/* Give warning */
@@ -3156,19 +3189,23 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
 	return count;
 }
 
-static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence)
 {
+	int ret;
+
 	if (file->f_mode & FMODE_READ)
-		return seq_lseek(file, offset, origin);
+		ret = seq_lseek(file, offset, whence);
 	else
-		return 0;
+		file->f_pos = ret = 0;
+
+	return ret;
 }
 
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
 	.write		= tracing_write_stub,
-	.llseek		= tracing_seek,
+	.llseek		= tracing_lseek,
 	.release	= tracing_release,
 };
 
@@ -3488,60 +3525,103 @@ static const char readme_msg[] =
 	"  instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
 	"\t\t\t  Remove sub-buffer with rmdir\n"
 	"  trace_options\t\t- Set format or modify how tracing happens\n"
-	"\t\t\t  Disable an option by adding a suffix 'no' to the option name\n"
+	"\t\t\t  Disable an option by adding a suffix 'no' to the\n"
+	"\t\t\t  option name\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
-	"  set_ftrace_filter\t- echo function name in here to only trace these functions\n"
-	"            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
-	"            modules: Can select a group via module\n"
-	"             Format: :mod:<module-name>\n"
-	"             example: echo :mod:ext3 > set_ftrace_filter\n"
-	"            triggers: a command to perform when function is hit\n"
-	"              Format: <function>:<trigger>[:count]\n"
-	"             trigger: traceon, traceoff\n"
-	"                      enable_event:<system>:<event>\n"
-	"                      disable_event:<system>:<event>\n"
+	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
+	"\t\t\t  functions\n"
+	"\t     accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"\t     modules: Can select a group via module\n"
+	"\t      Format: :mod:<module-name>\n"
+	"\t     example: echo :mod:ext3 > set_ftrace_filter\n"
+	"\t    triggers: a command to perform when function is hit\n"
+	"\t      Format: <function>:<trigger>[:count]\n"
+	"\t     trigger: traceon, traceoff\n"
+	"\t\t      enable_event:<system>:<event>\n"
+	"\t\t      disable_event:<system>:<event>\n"
 #ifdef CONFIG_STACKTRACE
-	"                      stacktrace\n"
+	"\t\t      stacktrace\n"
 #endif
 #ifdef CONFIG_TRACER_SNAPSHOT
-	"                      snapshot\n"
+	"\t\t      snapshot\n"
 #endif
-	"             example: echo do_fault:traceoff > set_ftrace_filter\n"
-	"                      echo do_trap:traceoff:3 > set_ftrace_filter\n"
-	"             The first one will disable tracing every time do_fault is hit\n"
-	"             The second will disable tracing at most 3 times when do_trap is hit\n"
-	"               The first time do trap is hit and it disables tracing, the counter\n"
-	"               will decrement to 2. If tracing is already disabled, the counter\n"
-	"               will not decrement. It only decrements when the trigger did work\n"
-	"             To remove trigger without count:\n"
-	"               echo '!<function>:<trigger> > set_ftrace_filter\n"
-	"             To remove trigger with a count:\n"
-	"               echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
+	"\t     example: echo do_fault:traceoff > set_ftrace_filter\n"
+	"\t              echo do_trap:traceoff:3 > set_ftrace_filter\n"
+	"\t     The first one will disable tracing every time do_fault is hit\n"
+	"\t     The second will disable tracing at most 3 times when do_trap is hit\n"
+	"\t       The first time do trap is hit and it disables tracing, the\n"
+	"\t       counter will decrement to 2. If tracing is already disabled,\n"
+	"\t       the counter will not decrement. It only decrements when the\n"
+	"\t       trigger did work\n"
+	"\t     To remove trigger without count:\n"
+	"\t       echo '!<function>:<trigger> > set_ftrace_filter\n"
+	"\t     To remove trigger with a count:\n"
+	"\t       echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
 	"  set_ftrace_notrace\t- echo function name in here to never trace.\n"
-	"            accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
-	"            modules: Can select a group via module command :mod:\n"
-	"            Does not accept triggers\n"
+	"\t    accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"\t    modules: Can select a group via module command :mod:\n"
+	"\t    Does not accept triggers\n"
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #ifdef CONFIG_FUNCTION_TRACER
-	"  set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n"
+	"  set_ftrace_pid\t- Write pid(s) to only function trace those pids\n"
+	"\t\t    (function)\n"
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	"  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
 	"  max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
 #endif
 #ifdef CONFIG_TRACER_SNAPSHOT
-	"\n  snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
-	"\t\t\t  Read the contents for more information\n"
+	"\n  snapshot\t\t- Like 'trace' but shows the content of the static\n"
+	"\t\t\t  snapshot buffer. Read the contents for more\n"
+	"\t\t\t  information\n"
 #endif
 #ifdef CONFIG_STACK_TRACER
 	"  stack_trace\t\t- Shows the max stack trace when active\n"
 	"  stack_max_size\t- Shows current max stack size that was traced\n"
-	"\t\t\t  Write into this file to reset the max size (trigger a new trace)\n"
+	"\t\t\t  Write into this file to reset the max size (trigger a\n"
+	"\t\t\t  new trace)\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
-	"  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
+	"  stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace\n"
+	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
+	"  events/\t\t- Directory containing all trace event subsystems:\n"
+	"      enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
+	"  events/<system>/\t- Directory containing all trace events for <system>:\n"
+	"      enable\t\t- Write 0/1 to enable/disable tracing of all <system>\n"
+	"\t\t\t  events\n"
+	"      filter\t\t- If set, only events passing filter are traced\n"
+	"  events/<system>/<event>/\t- Directory containing control files for\n"
+	"\t\t\t  <event>:\n"
+	"      enable\t\t- Write 0/1 to enable/disable tracing of <event>\n"
+	"      filter\t\t- If set, only events passing filter are traced\n"
+	"      trigger\t\t- If set, a command to perform when event is hit\n"
+	"\t    Format: <trigger>[:count][if <filter>]\n"
+	"\t   trigger: traceon, traceoff\n"
+	"\t            enable_event:<system>:<event>\n"
+	"\t            disable_event:<system>:<event>\n"
+#ifdef CONFIG_STACKTRACE
+	"\t\t    stacktrace\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+	"\t\t    snapshot\n"
+#endif
+	"\t   example: echo traceoff > events/block/block_unplug/trigger\n"
+	"\t            echo traceoff:3 > events/block/block_unplug/trigger\n"
+	"\t            echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n"
+	"\t                  events/block/block_unplug/trigger\n"
+	"\t   The first disables tracing every time block_unplug is hit.\n"
+	"\t   The second disables tracing the first 3 times block_unplug is hit.\n"
+	"\t   The third enables the kmalloc event the first 3 times block_unplug\n"
+	"\t     is hit and has value of greater than 1 for the 'nr_rq' event field.\n"
+	"\t   Like function triggers, the counter is only decremented if it\n"
+	"\t    enabled or disabled tracing.\n"
+	"\t   To remove a trigger without a count:\n"
+	"\t     echo '!<trigger> > <system>/<event>/trigger\n"
+	"\t   To remove a trigger with a count:\n"
+	"\t     echo '!<trigger>:0 > <system>/<event>/trigger\n"
+	"\t   Filters can be ignored when removing a trigger.\n"
 ;
 
 static ssize_t
@@ -4212,12 +4292,6 @@ out:
 	return sret;
 }
 
-static void tracing_pipe_buf_release(struct pipe_inode_info *pipe,
-				     struct pipe_buffer *buf)
-{
-	__free_page(buf->page);
-}
-
 static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 				     unsigned int idx)
 {
@@ -4229,7 +4303,7 @@ static const struct pipe_buf_operations tracing_pipe_buf_ops = {
 	.map			= generic_pipe_buf_map,
 	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
-	.release		= tracing_pipe_buf_release,
+	.release		= generic_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
 	.get			= generic_pipe_buf_get,
 };
@@ -4913,7 +4987,7 @@ static const struct file_operations snapshot_fops = {
 	.open		= tracing_snapshot_open,
 	.read		= seq_read,
 	.write		= tracing_snapshot_write,
-	.llseek		= tracing_seek,
+	.llseek		= tracing_lseek,
 	.release	= tracing_snapshot_release,
 };
 
@@ -5883,6 +5957,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 
 	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
 
+	buf->tr = tr;
+
 	buf->buffer = ring_buffer_alloc(size, rb_flags);
 	if (!buf->buffer)
 		return -ENOMEM;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ea189e0..02b592f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,3 +1,4 @@
+
 #ifndef _LINUX_KERNEL_TRACE_H
 #define _LINUX_KERNEL_TRACE_H
 
@@ -587,6 +588,8 @@ void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 int is_tracing_stopped(void);
 
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence);
+
 extern cpumask_var_t __read_mostly tracing_buffer_mask;
 
 #define for_each_tracing_cpu(cpu)	\
@@ -1020,6 +1023,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 extern void print_subsystem_event_filter(struct event_subsystem *system,
 					 struct trace_seq *s);
 extern int filter_assign_type(const char *type);
+extern int create_event_filter(struct ftrace_event_call *call,
+			       char *filter_str, bool set_str,
+			       struct event_filter **filterp);
+extern void free_event_filter(struct event_filter *filter);
 
 struct ftrace_event_field *
 trace_find_event_field(struct ftrace_event_call *call, char *name);
@@ -1028,9 +1035,195 @@ extern void trace_event_enable_cmd_record(bool enable);
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
 
+extern struct ftrace_event_file *find_event_file(struct trace_array *tr,
+						 const char *system,
+						 const char *event);
+
+static inline void *event_file_data(struct file *filp)
+{
+	return ACCESS_ONCE(file_inode(filp)->i_private);
+}
+
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
+extern const struct file_operations event_trigger_fops;
+
+extern int register_trigger_cmds(void);
+extern void clear_event_triggers(struct trace_array *tr);
+
+struct event_trigger_data {
+	unsigned long			count;
+	int				ref;
+	struct event_trigger_ops	*ops;
+	struct event_command		*cmd_ops;
+	struct event_filter __rcu	*filter;
+	char				*filter_str;
+	void				*private_data;
+	struct list_head		list;
+};
+
+/**
+ * struct event_trigger_ops - callbacks for trace event triggers
+ *
+ * The methods in this structure provide per-event trigger hooks for
+ * various trigger operations.
+ *
+ * All the methods below, except for @init() and @free(), must be
+ * implemented.
+ *
+ * @func: The trigger 'probe' function called when the triggering
+ *	event occurs.  The data passed into this callback is the data
+ *	that was supplied to the event_command @reg() function that
+ *	registered the trigger (see struct event_command).
+ *
+ * @init: An optional initialization function called for the trigger
+ *	when the trigger is registered (via the event_command reg()
+ *	function).  This can be used to perform per-trigger
+ *	initialization such as incrementing a per-trigger reference
+ *	count, for instance.  This is usually implemented by the
+ *	generic utility function @event_trigger_init() (see
+ *	trace_event_triggers.c).
+ *
+ * @free: An optional de-initialization function called for the
+ *	trigger when the trigger is unregistered (via the
+ *	event_command @reg() function).  This can be used to perform
+ *	per-trigger de-initialization such as decrementing a
+ *	per-trigger reference count and freeing corresponding trigger
+ *	data, for instance.  This is usually implemented by the
+ *	generic utility function @event_trigger_free() (see
+ *	trace_event_triggers.c).
+ *
+ * @print: The callback function invoked to have the trigger print
+ *	itself.  This is usually implemented by a wrapper function
+ *	that calls the generic utility function @event_trigger_print()
+ *	(see trace_event_triggers.c).
+ */
+struct event_trigger_ops {
+	void			(*func)(struct event_trigger_data *data);
+	int			(*init)(struct event_trigger_ops *ops,
+					struct event_trigger_data *data);
+	void			(*free)(struct event_trigger_ops *ops,
+					struct event_trigger_data *data);
+	int			(*print)(struct seq_file *m,
+					 struct event_trigger_ops *ops,
+					 struct event_trigger_data *data);
+};
+
+/**
+ * struct event_command - callbacks and data members for event commands
+ *
+ * Event commands are invoked by users by writing the command name
+ * into the 'trigger' file associated with a trace event.  The
+ * parameters associated with a specific invocation of an event
+ * command are used to create an event trigger instance, which is
+ * added to the list of trigger instances associated with that trace
+ * event.  When the event is hit, the set of triggers associated with
+ * that event is invoked.
+ *
+ * The data members in this structure provide per-event command data
+ * for various event commands.
+ *
+ * All the data members below, except for @post_trigger, must be set
+ * for each event command.
+ *
+ * @name: The unique name that identifies the event command.  This is
+ *	the name used when setting triggers via trigger files.
+ *
+ * @trigger_type: A unique id that identifies the event command
+ *	'type'.  This value has two purposes, the first to ensure that
+ *	only one trigger of the same type can be set at a given time
+ *	for a particular event e.g. it doesn't make sense to have both
+ *	a traceon and traceoff trigger attached to a single event at
+ *	the same time, so traceon and traceoff have the same type
+ *	though they have different names.  The @trigger_type value is
+ *	also used as a bit value for deferring the actual trigger
+ *	action until after the current event is finished.  Some
+ *	commands need to do this if they themselves log to the trace
+ *	buffer (see the @post_trigger() member below).  @trigger_type
+ *	values are defined by adding new values to the trigger_type
+ *	enum in include/linux/ftrace_event.h.
+ *
+ * @post_trigger: A flag that says whether or not this command needs
+ *	to have its action delayed until after the current event has
+ *	been closed.  Some triggers need to avoid being invoked while
+ *	an event is currently in the process of being logged, since
+ *	the trigger may itself log data into the trace buffer.  Thus
+ *	we make sure the current event is committed before invoking
+ *	those triggers.  To do that, the trigger invocation is split
+ *	in two - the first part checks the filter using the current
+ *	trace record; if a command has the @post_trigger flag set, it
+ *	sets a bit for itself in the return value, otherwise it
+ *	directly invokes the trigger.  Once all commands have been
+ *	either invoked or set their return flag, the current record is
+ *	either committed or discarded.  At that point, if any commands
+ *	have deferred their triggers, those commands are finally
+ *	invoked following the close of the current event.  In other
+ *	words, if the event_trigger_ops @func() probe implementation
+ *	itself logs to the trace buffer, this flag should be set,
+ *	otherwise it can be left unspecified.
+ *
+ * All the methods below, except for @set_filter(), must be
+ * implemented.
+ *
+ * @func: The callback function responsible for parsing and
+ *	registering the trigger written to the 'trigger' file by the
+ *	user.  It allocates the trigger instance and registers it with
+ *	the appropriate trace event.  It makes use of the other
+ *	event_command callback functions to orchestrate this, and is
+ *	usually implemented by the generic utility function
+ *	@event_trigger_callback() (see trace_event_triggers.c).
+ *
+ * @reg: Adds the trigger to the list of triggers associated with the
+ *	event, and enables the event trigger itself, after
+ *	initializing it (via the event_trigger_ops @init() function).
+ *	This is also where commands can use the @trigger_type value to
+ *	make the decision as to whether or not multiple instances of
+ *	the trigger should be allowed.  This is usually implemented by
+ *	the generic utility function @register_trigger() (see
+ *	trace_event_triggers.c).
+ *
+ * @unreg: Removes the trigger from the list of triggers associated
+ *	with the event, and disables the event trigger itself, after
+ *	initializing it (via the event_trigger_ops @free() function).
+ *	This is usually implemented by the generic utility function
+ *	@unregister_trigger() (see trace_event_triggers.c).
+ *
+ * @set_filter: An optional function called to parse and set a filter
+ *	for the trigger.  If no @set_filter() method is set for the
+ *	event command, filters set by the user for the command will be
+ *	ignored.  This is usually implemented by the generic utility
+ *	function @set_trigger_filter() (see trace_event_triggers.c).
+ *
+ * @get_trigger_ops: The callback function invoked to retrieve the
+ *	event_trigger_ops implementation associated with the command.
+ */
+struct event_command {
+	struct list_head	list;
+	char			*name;
+	enum event_trigger_type	trigger_type;
+	bool			post_trigger;
+	int			(*func)(struct event_command *cmd_ops,
+					struct ftrace_event_file *file,
+					char *glob, char *cmd, char *params);
+	int			(*reg)(char *glob,
+				       struct event_trigger_ops *ops,
+				       struct event_trigger_data *data,
+				       struct ftrace_event_file *file);
+	void			(*unreg)(char *glob,
+					 struct event_trigger_ops *ops,
+					 struct event_trigger_data *data,
+					 struct ftrace_event_file *file);
+	int			(*set_filter)(char *filter_str,
+					      struct event_trigger_data *data,
+					      struct ftrace_event_file *file);
+	struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
+};
+
+extern int trace_event_enable_disable(struct ftrace_event_file *file,
+				      int enable, int soft_disable);
+extern int tracing_alloc_snapshot(void);
+
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a11800a..e71ffd4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
 	return ret;
 }
 
+int trace_event_enable_disable(struct ftrace_event_file *file,
+			       int enable, int soft_disable)
+{
+	return __ftrace_event_enable_disable(file, enable, soft_disable);
+}
+
 static int ftrace_event_enable_disable(struct ftrace_event_file *file,
 				       int enable)
 {
@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir)
 	}
 }
 
-static void *event_file_data(struct file *filp)
-{
-	return ACCESS_ONCE(file_inode(filp)->i_private);
-}
-
 static void remove_event_file_dir(struct ftrace_event_file *file)
 {
 	struct dentry *dir = file->dir;
@@ -1549,6 +1550,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 	trace_create_file("filter", 0644, file->dir, file,
 			  &ftrace_event_filter_fops);
 
+	trace_create_file("trigger", 0644, file->dir, file,
+			  &event_trigger_fops);
+
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);
 
@@ -1645,6 +1649,8 @@ trace_create_new_event(struct ftrace_event_call *call,
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);
+	atomic_set(&file->tm_ref, 0);
+	INIT_LIST_HEAD(&file->triggers);
 	list_add(&file->list, &tr->events);
 
 	return file;
@@ -1849,20 +1855,7 @@ __trace_add_event_dirs(struct trace_array *tr)
 	}
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-/* Avoid typos */
-#define ENABLE_EVENT_STR	"enable_event"
-#define DISABLE_EVENT_STR	"disable_event"
-
-struct event_probe_data {
-	struct ftrace_event_file	*file;
-	unsigned long			count;
-	int				ref;
-	bool				enable;
-};
-
-static struct ftrace_event_file *
+struct ftrace_event_file *
 find_event_file(struct trace_array *tr, const char *system,  const char *event)
 {
 	struct ftrace_event_file *file;
@@ -1885,6 +1878,19 @@ find_event_file(struct trace_array *tr, const char *system,  const char *event)
 	return NULL;
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR	"enable_event"
+#define DISABLE_EVENT_STR	"disable_event"
+
+struct event_probe_data {
+	struct ftrace_event_file	*file;
+	unsigned long			count;
+	int				ref;
+	bool				enable;
+};
+
 static void
 event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
 {
@@ -2311,6 +2317,9 @@ int event_trace_del_tracer(struct trace_array *tr)
 {
 	mutex_lock(&event_mutex);
 
+	/* Disable any event triggers and associated soft-disabled events */
+	clear_event_triggers(tr);
+
 	/* Disable any running events */
 	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
 
@@ -2377,6 +2386,8 @@ static __init int event_trace_enable(void)
 
 	register_event_cmds();
 
+	register_trigger_cmds();
+
 	return 0;
 }
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 2468f56..8a86319 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -799,6 +799,11 @@ static void __free_filter(struct event_filter *filter)
 	kfree(filter);
 }
 
+void free_event_filter(struct event_filter *filter)
+{
+	__free_filter(filter);
+}
+
 void destroy_call_preds(struct ftrace_event_call *call)
 {
 	__free_filter(call->filter);
@@ -1938,6 +1943,13 @@ static int create_filter(struct ftrace_event_call *call,
 	return err;
 }
 
+int create_event_filter(struct ftrace_event_call *call,
+			char *filter_str, bool set_str,
+			struct event_filter **filterp)
+{
+	return create_filter(call, filter_str, set_str, filterp);
+}
+
 /**
  * create_system_filter - create a filter for an event_subsystem
  * @system: event_subsystem to create a filter for
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
new file mode 100644
index 0000000..8efbb69
--- /dev/null
+++ b/kernel/trace/trace_events_trigger.c
@@ -0,0 +1,1437 @@
+/*
+ * trace_events_trigger - trace event triggers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "trace.h"
+
+static LIST_HEAD(trigger_commands);
+static DEFINE_MUTEX(trigger_cmd_mutex);
+
+static void
+trigger_data_free(struct event_trigger_data *data)
+{
+	if (data->cmd_ops->set_filter)
+		data->cmd_ops->set_filter(NULL, data, NULL);
+
+	synchronize_sched(); /* make sure current triggers exit before free */
+	kfree(data);
+}
+
+/**
+ * event_triggers_call - Call triggers associated with a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @rec: The trace entry for the event, NULL for unconditional invocation
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command.  If rec is
+ * non-NULL, it means that the trigger requires further processing and
+ * shouldn't be unconditionally invoked.  If rec is non-NULL and the
+ * trigger has a filter associated with it, rec will checked against
+ * the filter and if the record matches the trigger will be invoked.
+ * If the trigger is a 'post_trigger', meaning it shouldn't be invoked
+ * in any case until the current event is written, the trigger
+ * function isn't invoked but the bit associated with the deferred
+ * trigger is set in the return value.
+ *
+ * Returns an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ *
+ * Return: an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ */
+enum event_trigger_type
+event_triggers_call(struct ftrace_event_file *file, void *rec)
+{
+	struct event_trigger_data *data;
+	enum event_trigger_type tt = ETT_NONE;
+	struct event_filter *filter;
+
+	if (list_empty(&file->triggers))
+		return tt;
+
+	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (!rec) {
+			data->ops->func(data);
+			continue;
+		}
+		filter = rcu_dereference(data->filter);
+		if (filter && !filter_match_preds(filter, rec))
+			continue;
+		if (data->cmd_ops->post_trigger) {
+			tt |= data->cmd_ops->trigger_type;
+			continue;
+		}
+		data->ops->func(data);
+	}
+	return tt;
+}
+EXPORT_SYMBOL_GPL(event_triggers_call);
+
+/**
+ * event_triggers_post_call - Call 'post_triggers' for a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command, if the
+ * corresponding bit is set in the tt enum passed into this function.
+ * See @event_triggers_call for details on how those bits are set.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ */
+void
+event_triggers_post_call(struct ftrace_event_file *file,
+			 enum event_trigger_type tt)
+{
+	struct event_trigger_data *data;
+
+	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (data->cmd_ops->trigger_type & tt)
+			data->ops->func(data);
+	}
+}
+EXPORT_SYMBOL_GPL(event_triggers_post_call);
+
+#define SHOW_AVAILABLE_TRIGGERS	(void *)(1UL)
+
+static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
+{
+	struct ftrace_event_file *event_file = event_file_data(m->private);
+
+	if (t == SHOW_AVAILABLE_TRIGGERS)
+		return NULL;
+
+	return seq_list_next(t, &event_file->triggers, pos);
+}
+
+static void *trigger_start(struct seq_file *m, loff_t *pos)
+{
+	struct ftrace_event_file *event_file;
+
+	/* ->stop() is called even if ->start() fails */
+	mutex_lock(&event_mutex);
+	event_file = event_file_data(m->private);
+	if (unlikely(!event_file))
+		return ERR_PTR(-ENODEV);
+
+	if (list_empty(&event_file->triggers))
+		return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL;
+
+	return seq_list_start(&event_file->triggers, *pos);
+}
+
+static void trigger_stop(struct seq_file *m, void *t)
+{
+	mutex_unlock(&event_mutex);
+}
+
+static int trigger_show(struct seq_file *m, void *v)
+{
+	struct event_trigger_data *data;
+	struct event_command *p;
+
+	if (v == SHOW_AVAILABLE_TRIGGERS) {
+		seq_puts(m, "# Available triggers:\n");
+		seq_putc(m, '#');
+		mutex_lock(&trigger_cmd_mutex);
+		list_for_each_entry_reverse(p, &trigger_commands, list)
+			seq_printf(m, " %s", p->name);
+		seq_putc(m, '\n');
+		mutex_unlock(&trigger_cmd_mutex);
+		return 0;
+	}
+
+	data = list_entry(v, struct event_trigger_data, list);
+	data->ops->print(m, data->ops, data);
+
+	return 0;
+}
+
+static const struct seq_operations event_triggers_seq_ops = {
+	.start = trigger_start,
+	.next = trigger_next,
+	.stop = trigger_stop,
+	.show = trigger_show,
+};
+
+static int event_trigger_regex_open(struct inode *inode, struct file *file)
+{
+	int ret = 0;
+
+	mutex_lock(&event_mutex);
+
+	if (unlikely(!event_file_data(file))) {
+		mutex_unlock(&event_mutex);
+		return -ENODEV;
+	}
+
+	if (file->f_mode & FMODE_READ) {
+		ret = seq_open(file, &event_triggers_seq_ops);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = file;
+		}
+	}
+
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int trigger_process_regex(struct ftrace_event_file *file, char *buff)
+{
+	char *command, *next = buff;
+	struct event_command *p;
+	int ret = -EINVAL;
+
+	command = strsep(&next, ": \t");
+	command = (command[0] != '!') ? command : command + 1;
+
+	mutex_lock(&trigger_cmd_mutex);
+	list_for_each_entry(p, &trigger_commands, list) {
+		if (strcmp(p->name, command) == 0) {
+			ret = p->func(p, file, buff, command, next);
+			goto out_unlock;
+		}
+	}
+ out_unlock:
+	mutex_unlock(&trigger_cmd_mutex);
+
+	return ret;
+}
+
+static ssize_t event_trigger_regex_write(struct file *file,
+					 const char __user *ubuf,
+					 size_t cnt, loff_t *ppos)
+{
+	struct ftrace_event_file *event_file;
+	ssize_t ret;
+	char *buf;
+
+	if (!cnt)
+		return 0;
+
+	if (cnt >= PAGE_SIZE)
+		return -EINVAL;
+
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long)buf);
+		return -EFAULT;
+	}
+	buf[cnt] = '\0';
+	strim(buf);
+
+	mutex_lock(&event_mutex);
+	event_file = event_file_data(file);
+	if (unlikely(!event_file)) {
+		mutex_unlock(&event_mutex);
+		free_page((unsigned long)buf);
+		return -ENODEV;
+	}
+	ret = trigger_process_regex(event_file, buf);
+	mutex_unlock(&event_mutex);
+
+	free_page((unsigned long)buf);
+	if (ret < 0)
+		goto out;
+
+	*ppos += cnt;
+	ret = cnt;
+ out:
+	return ret;
+}
+
+static int event_trigger_regex_release(struct inode *inode, struct file *file)
+{
+	mutex_lock(&event_mutex);
+
+	if (file->f_mode & FMODE_READ)
+		seq_release(inode, file);
+
+	mutex_unlock(&event_mutex);
+
+	return 0;
+}
+
+static ssize_t
+event_trigger_write(struct file *filp, const char __user *ubuf,
+		    size_t cnt, loff_t *ppos)
+{
+	return event_trigger_regex_write(filp, ubuf, cnt, ppos);
+}
+
+static int
+event_trigger_open(struct inode *inode, struct file *filp)
+{
+	return event_trigger_regex_open(inode, filp);
+}
+
+static int
+event_trigger_release(struct inode *inode, struct file *file)
+{
+	return event_trigger_regex_release(inode, file);
+}
+
+const struct file_operations event_trigger_fops = {
+	.open = event_trigger_open,
+	.read = seq_read,
+	.write = event_trigger_write,
+	.llseek = tracing_lseek,
+	.release = event_trigger_release,
+};
+
+/*
+ * Currently we only register event commands from __init, so mark this
+ * __init too.
+ */
+static __init int register_event_command(struct event_command *cmd)
+{
+	struct event_command *p;
+	int ret = 0;
+
+	mutex_lock(&trigger_cmd_mutex);
+	list_for_each_entry(p, &trigger_commands, list) {
+		if (strcmp(cmd->name, p->name) == 0) {
+			ret = -EBUSY;
+			goto out_unlock;
+		}
+	}
+	list_add(&cmd->list, &trigger_commands);
+ out_unlock:
+	mutex_unlock(&trigger_cmd_mutex);
+
+	return ret;
+}
+
+/*
+ * Currently we only unregister event commands from __init, so mark
+ * this __init too.
+ */
+static __init int unregister_event_command(struct event_command *cmd)
+{
+	struct event_command *p, *n;
+	int ret = -ENODEV;
+
+	mutex_lock(&trigger_cmd_mutex);
+	list_for_each_entry_safe(p, n, &trigger_commands, list) {
+		if (strcmp(cmd->name, p->name) == 0) {
+			ret = 0;
+			list_del_init(&p->list);
+			goto out_unlock;
+		}
+	}
+ out_unlock:
+	mutex_unlock(&trigger_cmd_mutex);
+
+	return ret;
+}
+
+/**
+ * event_trigger_print - Generic event_trigger_ops @print implementation
+ * @name: The name of the event trigger
+ * @m: The seq_file being printed to
+ * @data: Trigger-specific data
+ * @filter_str: filter_str to print, if present
+ *
+ * Common implementation for event triggers to print themselves.
+ *
+ * Usually wrapped by a function that simply sets the @name of the
+ * trigger command and then invokes this.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_print(const char *name, struct seq_file *m,
+		    void *data, char *filter_str)
+{
+	long count = (long)data;
+
+	seq_printf(m, "%s", name);
+
+	if (count == -1)
+		seq_puts(m, ":unlimited");
+	else
+		seq_printf(m, ":count=%ld", count);
+
+	if (filter_str)
+		seq_printf(m, " if %s\n", filter_str);
+	else
+		seq_puts(m, "\n");
+
+	return 0;
+}
+
+/**
+ * event_trigger_init - Generic event_trigger_ops @init implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger initialization.
+ *
+ * Usually used directly as the @init method in event trigger
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_init(struct event_trigger_ops *ops,
+		   struct event_trigger_data *data)
+{
+	data->ref++;
+	return 0;
+}
+
+/**
+ * event_trigger_free - Generic event_trigger_ops @free implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger de-initialization.
+ *
+ * Usually used directly as the @free method in event trigger
+ * implementations.
+ */
+static void
+event_trigger_free(struct event_trigger_ops *ops,
+		   struct event_trigger_data *data)
+{
+	if (WARN_ON_ONCE(data->ref <= 0))
+		return;
+
+	data->ref--;
+	if (!data->ref)
+		trigger_data_free(data);
+}
+
+static int trace_event_trigger_enable_disable(struct ftrace_event_file *file,
+					      int trigger_enable)
+{
+	int ret = 0;
+
+	if (trigger_enable) {
+		if (atomic_inc_return(&file->tm_ref) > 1)
+			return ret;
+		set_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+		ret = trace_event_enable_disable(file, 1, 1);
+	} else {
+		if (atomic_dec_return(&file->tm_ref) > 0)
+			return ret;
+		clear_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+		ret = trace_event_enable_disable(file, 0, 1);
+	}
+
+	return ret;
+}
+
+/**
+ * clear_event_triggers - Clear all triggers associated with a trace array
+ * @tr: The trace array to clear
+ *
+ * For each trigger, the triggering event has its tm_ref decremented
+ * via trace_event_trigger_enable_disable(), and any associated event
+ * (in the case of enable/disable_event triggers) will have its sm_ref
+ * decremented via free()->trace_event_enable_disable().  That
+ * combination effectively reverses the soft-mode/trigger state added
+ * by trigger registration.
+ *
+ * Must be called with event_mutex held.
+ */
+void
+clear_event_triggers(struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
+
+	list_for_each_entry(file, &tr->events, list) {
+		struct event_trigger_data *data;
+		list_for_each_entry_rcu(data, &file->triggers, list) {
+			trace_event_trigger_enable_disable(file, 0);
+			if (data->ops->free)
+				data->ops->free(data->ops, data);
+		}
+	}
+}
+
+/**
+ * update_cond_flag - Set or reset the TRIGGER_COND bit
+ * @file: The ftrace_event_file associated with the event
+ *
+ * If an event has triggers and any of those triggers has a filter or
+ * a post_trigger, trigger invocation needs to be deferred until after
+ * the current event has logged its data, and the event should have
+ * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
+ * cleared.
+ */
+static void update_cond_flag(struct ftrace_event_file *file)
+{
+	struct event_trigger_data *data;
+	bool set_cond = false;
+
+	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (data->filter || data->cmd_ops->post_trigger) {
+			set_cond = true;
+			break;
+		}
+	}
+
+	if (set_cond)
+		set_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+	else
+		clear_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+}
+
+/**
+ * register_trigger - Generic event_command @reg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data to associate with the trigger
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger registration.
+ *
+ * Usually used directly as the @reg method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int register_trigger(char *glob, struct event_trigger_ops *ops,
+			    struct event_trigger_data *data,
+			    struct ftrace_event_file *file)
+{
+	struct event_trigger_data *test;
+	int ret = 0;
+
+	list_for_each_entry_rcu(test, &file->triggers, list) {
+		if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
+	if (data->ops->init) {
+		ret = data->ops->init(data->ops, data);
+		if (ret < 0)
+			goto out;
+	}
+
+	list_add_rcu(&data->list, &file->triggers);
+	ret++;
+
+	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+		list_del_rcu(&data->list);
+		ret--;
+	}
+	update_cond_flag(file);
+out:
+	return ret;
+}
+
+/**
+ * unregister_trigger - Generic event_command @unreg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @test: Trigger-specific data used to find the trigger to remove
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger unregistration.
+ *
+ * Usually used directly as the @unreg method in event command
+ * implementations.
+ */
+static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+			       struct event_trigger_data *test,
+			       struct ftrace_event_file *file)
+{
+	struct event_trigger_data *data;
+	bool unregistered = false;
+
+	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+			unregistered = true;
+			list_del_rcu(&data->list);
+			update_cond_flag(file);
+			trace_event_trigger_enable_disable(file, 0);
+			break;
+		}
+	}
+
+	if (unregistered && data->ops->free)
+		data->ops->free(data->ops, data);
+}
+
+/**
+ * event_trigger_callback - Generic event_command @func implementation
+ * @cmd_ops: The command ops, used for trigger registration
+ * @file: The ftrace_event_file associated with the event
+ * @glob: The raw string used to register the trigger
+ * @cmd: The cmd portion of the string used to register the trigger
+ * @param: The params portion of the string used to register the trigger
+ *
+ * Common implementation for event command parsing and trigger
+ * instantiation.
+ *
+ * Usually used directly as the @func method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_callback(struct event_command *cmd_ops,
+		       struct ftrace_event_file *file,
+		       char *glob, char *cmd, char *param)
+{
+	struct event_trigger_data *trigger_data;
+	struct event_trigger_ops *trigger_ops;
+	char *trigger = NULL;
+	char *number;
+	int ret;
+
+	/* separate the trigger from the filter (t:n [if filter]) */
+	if (param && isdigit(param[0]))
+		trigger = strsep(&param, " \t");
+
+	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+	ret = -ENOMEM;
+	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	if (!trigger_data)
+		goto out;
+
+	trigger_data->count = -1;
+	trigger_data->ops = trigger_ops;
+	trigger_data->cmd_ops = cmd_ops;
+	INIT_LIST_HEAD(&trigger_data->list);
+
+	if (glob[0] == '!') {
+		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		kfree(trigger_data);
+		ret = 0;
+		goto out;
+	}
+
+	if (trigger) {
+		number = strsep(&trigger, ":");
+
+		ret = -EINVAL;
+		if (!strlen(number))
+			goto out_free;
+
+		/*
+		 * We use the callback data field (which is a pointer)
+		 * as our counter.
+		 */
+		ret = kstrtoul(number, 0, &trigger_data->count);
+		if (ret)
+			goto out_free;
+	}
+
+	if (!param) /* if param is non-empty, it's supposed to be a filter */
+		goto out_reg;
+
+	if (!cmd_ops->set_filter)
+		goto out_reg;
+
+	ret = cmd_ops->set_filter(param, trigger_data, file);
+	if (ret < 0)
+		goto out_free;
+
+ out_reg:
+	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+	/*
+	 * The above returns on success the # of functions enabled,
+	 * but if it didn't find any functions it returns zero.
+	 * Consider no functions a failure too.
+	 */
+	if (!ret) {
+		ret = -ENOENT;
+		goto out_free;
+	} else if (ret < 0)
+		goto out_free;
+	ret = 0;
+ out:
+	return ret;
+
+ out_free:
+	if (cmd_ops->set_filter)
+		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	kfree(trigger_data);
+	goto out;
+}
+
+/**
+ * set_trigger_filter - Generic event_command @set_filter implementation
+ * @filter_str: The filter string for the trigger, NULL to remove filter
+ * @trigger_data: Trigger-specific data
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event command filter parsing and filter
+ * instantiation.
+ *
+ * Usually used directly as the @set_filter method in event command
+ * implementations.
+ *
+ * Also used to remove a filter (if filter_str = NULL).
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int set_trigger_filter(char *filter_str,
+			      struct event_trigger_data *trigger_data,
+			      struct ftrace_event_file *file)
+{
+	struct event_trigger_data *data = trigger_data;
+	struct event_filter *filter = NULL, *tmp;
+	int ret = -EINVAL;
+	char *s;
+
+	if (!filter_str) /* clear the current filter */
+		goto assign;
+
+	s = strsep(&filter_str, " \t");
+
+	if (!strlen(s) || strcmp(s, "if") != 0)
+		goto out;
+
+	if (!filter_str)
+		goto out;
+
+	/* The filter is for the 'trigger' event, not the triggered event */
+	ret = create_event_filter(file->event_call, filter_str, false, &filter);
+	if (ret)
+		goto out;
+ assign:
+	tmp = rcu_access_pointer(data->filter);
+
+	rcu_assign_pointer(data->filter, filter);
+
+	if (tmp) {
+		/* Make sure the call is done with the filter */
+		synchronize_sched();
+		free_event_filter(tmp);
+	}
+
+	kfree(data->filter_str);
+	data->filter_str = NULL;
+
+	if (filter_str) {
+		data->filter_str = kstrdup(filter_str, GFP_KERNEL);
+		if (!data->filter_str) {
+			free_event_filter(rcu_access_pointer(data->filter));
+			data->filter = NULL;
+			ret = -ENOMEM;
+		}
+	}
+ out:
+	return ret;
+}
+
+static void
+traceon_trigger(struct event_trigger_data *data)
+{
+	if (tracing_is_on())
+		return;
+
+	tracing_on();
+}
+
+static void
+traceon_count_trigger(struct event_trigger_data *data)
+{
+	if (tracing_is_on())
+		return;
+
+	if (!data->count)
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	tracing_on();
+}
+
+static void
+traceoff_trigger(struct event_trigger_data *data)
+{
+	if (!tracing_is_on())
+		return;
+
+	tracing_off();
+}
+
+static void
+traceoff_count_trigger(struct event_trigger_data *data)
+{
+	if (!tracing_is_on())
+		return;
+
+	if (!data->count)
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	tracing_off();
+}
+
+static int
+traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+		      struct event_trigger_data *data)
+{
+	return event_trigger_print("traceon", m, (void *)data->count,
+				   data->filter_str);
+}
+
+static int
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+		       struct event_trigger_data *data)
+{
+	return event_trigger_print("traceoff", m, (void *)data->count,
+				   data->filter_str);
+}
+
+static struct event_trigger_ops traceon_trigger_ops = {
+	.func			= traceon_trigger,
+	.print			= traceon_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops traceon_count_trigger_ops = {
+	.func			= traceon_count_trigger,
+	.print			= traceon_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_trigger_ops = {
+	.func			= traceoff_trigger,
+	.print			= traceoff_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_count_trigger_ops = {
+	.func			= traceoff_count_trigger,
+	.print			= traceoff_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops *
+onoff_get_trigger_ops(char *cmd, char *param)
+{
+	struct event_trigger_ops *ops;
+
+	/* we register both traceon and traceoff to this callback */
+	if (strcmp(cmd, "traceon") == 0)
+		ops = param ? &traceon_count_trigger_ops :
+			&traceon_trigger_ops;
+	else
+		ops = param ? &traceoff_count_trigger_ops :
+			&traceoff_trigger_ops;
+
+	return ops;
+}
+
+static struct event_command trigger_traceon_cmd = {
+	.name			= "traceon",
+	.trigger_type		= ETT_TRACE_ONOFF,
+	.func			= event_trigger_callback,
+	.reg			= register_trigger,
+	.unreg			= unregister_trigger,
+	.get_trigger_ops	= onoff_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+static struct event_command trigger_traceoff_cmd = {
+	.name			= "traceoff",
+	.trigger_type		= ETT_TRACE_ONOFF,
+	.func			= event_trigger_callback,
+	.reg			= register_trigger,
+	.unreg			= unregister_trigger,
+	.get_trigger_ops	= onoff_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+static void
+snapshot_trigger(struct event_trigger_data *data)
+{
+	tracing_snapshot();
+}
+
+static void
+snapshot_count_trigger(struct event_trigger_data *data)
+{
+	if (!data->count)
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	snapshot_trigger(data);
+}
+
+static int
+register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
+			  struct event_trigger_data *data,
+			  struct ftrace_event_file *file)
+{
+	int ret = register_trigger(glob, ops, data, file);
+
+	if (ret > 0 && tracing_alloc_snapshot() != 0) {
+		unregister_trigger(glob, ops, data, file);
+		ret = 0;
+	}
+
+	return ret;
+}
+
+static int
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+		       struct event_trigger_data *data)
+{
+	return event_trigger_print("snapshot", m, (void *)data->count,
+				   data->filter_str);
+}
+
+static struct event_trigger_ops snapshot_trigger_ops = {
+	.func			= snapshot_trigger,
+	.print			= snapshot_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops snapshot_count_trigger_ops = {
+	.func			= snapshot_count_trigger,
+	.print			= snapshot_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops *
+snapshot_get_trigger_ops(char *cmd, char *param)
+{
+	return param ? &snapshot_count_trigger_ops : &snapshot_trigger_ops;
+}
+
+static struct event_command trigger_snapshot_cmd = {
+	.name			= "snapshot",
+	.trigger_type		= ETT_SNAPSHOT,
+	.func			= event_trigger_callback,
+	.reg			= register_snapshot_trigger,
+	.unreg			= unregister_trigger,
+	.get_trigger_ops	= snapshot_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+static __init int register_trigger_snapshot_cmd(void)
+{
+	int ret;
+
+	ret = register_event_command(&trigger_snapshot_cmd);
+	WARN_ON(ret < 0);
+
+	return ret;
+}
+#else
+static __init int register_trigger_snapshot_cmd(void) { return 0; }
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+#ifdef CONFIG_STACKTRACE
+/*
+ * Skip 3:
+ *   stacktrace_trigger()
+ *   event_triggers_post_call()
+ *   ftrace_raw_event_xxx()
+ */
+#define STACK_SKIP 3
+
+static void
+stacktrace_trigger(struct event_trigger_data *data)
+{
+	trace_dump_stack(STACK_SKIP);
+}
+
+static void
+stacktrace_count_trigger(struct event_trigger_data *data)
+{
+	if (!data->count)
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	stacktrace_trigger(data);
+}
+
+static int
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+			 struct event_trigger_data *data)
+{
+	return event_trigger_print("stacktrace", m, (void *)data->count,
+				   data->filter_str);
+}
+
+static struct event_trigger_ops stacktrace_trigger_ops = {
+	.func			= stacktrace_trigger,
+	.print			= stacktrace_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops stacktrace_count_trigger_ops = {
+	.func			= stacktrace_count_trigger,
+	.print			= stacktrace_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_trigger_free,
+};
+
+static struct event_trigger_ops *
+stacktrace_get_trigger_ops(char *cmd, char *param)
+{
+	return param ? &stacktrace_count_trigger_ops : &stacktrace_trigger_ops;
+}
+
+static struct event_command trigger_stacktrace_cmd = {
+	.name			= "stacktrace",
+	.trigger_type		= ETT_STACKTRACE,
+	.post_trigger		= true,
+	.func			= event_trigger_callback,
+	.reg			= register_trigger,
+	.unreg			= unregister_trigger,
+	.get_trigger_ops	= stacktrace_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+static __init int register_trigger_stacktrace_cmd(void)
+{
+	int ret;
+
+	ret = register_event_command(&trigger_stacktrace_cmd);
+	WARN_ON(ret < 0);
+
+	return ret;
+}
+#else
+static __init int register_trigger_stacktrace_cmd(void) { return 0; }
+#endif /* CONFIG_STACKTRACE */
+
+static __init void unregister_trigger_traceon_traceoff_cmds(void)
+{
+	unregister_event_command(&trigger_traceon_cmd);
+	unregister_event_command(&trigger_traceoff_cmd);
+}
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR	"enable_event"
+#define DISABLE_EVENT_STR	"disable_event"
+
+struct enable_trigger_data {
+	struct ftrace_event_file	*file;
+	bool				enable;
+};
+
+static void
+event_enable_trigger(struct event_trigger_data *data)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+
+	if (enable_data->enable)
+		clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+	else
+		set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+}
+
+static void
+event_enable_count_trigger(struct event_trigger_data *data)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+
+	if (!data->count)
+		return;
+
+	/* Skip if the event is in a state we want to switch to */
+	if (enable_data->enable == !(enable_data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+		return;
+
+	if (data->count != -1)
+		(data->count)--;
+
+	event_enable_trigger(data);
+}
+
+static int
+event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+			   struct event_trigger_data *data)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+
+	seq_printf(m, "%s:%s:%s",
+		   enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+		   enable_data->file->event_call->class->system,
+		   enable_data->file->event_call->name);
+
+	if (data->count == -1)
+		seq_puts(m, ":unlimited");
+	else
+		seq_printf(m, ":count=%ld", data->count);
+
+	if (data->filter_str)
+		seq_printf(m, " if %s\n", data->filter_str);
+	else
+		seq_puts(m, "\n");
+
+	return 0;
+}
+
+static void
+event_enable_trigger_free(struct event_trigger_ops *ops,
+			  struct event_trigger_data *data)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+
+	if (WARN_ON_ONCE(data->ref <= 0))
+		return;
+
+	data->ref--;
+	if (!data->ref) {
+		/* Remove the SOFT_MODE flag */
+		trace_event_enable_disable(enable_data->file, 0, 1);
+		module_put(enable_data->file->event_call->mod);
+		trigger_data_free(data);
+		kfree(enable_data);
+	}
+}
+
+static struct event_trigger_ops event_enable_trigger_ops = {
+	.func			= event_enable_trigger,
+	.print			= event_enable_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_enable_count_trigger_ops = {
+	.func			= event_enable_count_trigger,
+	.print			= event_enable_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_trigger_ops = {
+	.func			= event_enable_trigger,
+	.print			= event_enable_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_count_trigger_ops = {
+	.func			= event_enable_count_trigger,
+	.print			= event_enable_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_enable_trigger_free,
+};
+
+static int
+event_enable_trigger_func(struct event_command *cmd_ops,
+			  struct ftrace_event_file *file,
+			  char *glob, char *cmd, char *param)
+{
+	struct ftrace_event_file *event_enable_file;
+	struct enable_trigger_data *enable_data;
+	struct event_trigger_data *trigger_data;
+	struct event_trigger_ops *trigger_ops;
+	struct trace_array *tr = file->tr;
+	const char *system;
+	const char *event;
+	char *trigger;
+	char *number;
+	bool enable;
+	int ret;
+
+	if (!param)
+		return -EINVAL;
+
+	/* separate the trigger from the filter (s:e:n [if filter]) */
+	trigger = strsep(&param, " \t");
+	if (!trigger)
+		return -EINVAL;
+
+	system = strsep(&trigger, ":");
+	if (!trigger)
+		return -EINVAL;
+
+	event = strsep(&trigger, ":");
+
+	ret = -EINVAL;
+	event_enable_file = find_event_file(tr, system, event);
+	if (!event_enable_file)
+		goto out;
+
+	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+	ret = -ENOMEM;
+	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	if (!trigger_data)
+		goto out;
+
+	enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
+	if (!enable_data) {
+		kfree(trigger_data);
+		goto out;
+	}
+
+	trigger_data->count = -1;
+	trigger_data->ops = trigger_ops;
+	trigger_data->cmd_ops = cmd_ops;
+	INIT_LIST_HEAD(&trigger_data->list);
+	RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+	enable_data->enable = enable;
+	enable_data->file = event_enable_file;
+	trigger_data->private_data = enable_data;
+
+	if (glob[0] == '!') {
+		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		kfree(trigger_data);
+		kfree(enable_data);
+		ret = 0;
+		goto out;
+	}
+
+	if (trigger) {
+		number = strsep(&trigger, ":");
+
+		ret = -EINVAL;
+		if (!strlen(number))
+			goto out_free;
+
+		/*
+		 * We use the callback data field (which is a pointer)
+		 * as our counter.
+		 */
+		ret = kstrtoul(number, 0, &trigger_data->count);
+		if (ret)
+			goto out_free;
+	}
+
+	if (!param) /* if param is non-empty, it's supposed to be a filter */
+		goto out_reg;
+
+	if (!cmd_ops->set_filter)
+		goto out_reg;
+
+	ret = cmd_ops->set_filter(param, trigger_data, file);
+	if (ret < 0)
+		goto out_free;
+
+ out_reg:
+	/* Don't let event modules unload while probe registered */
+	ret = try_module_get(event_enable_file->event_call->mod);
+	if (!ret) {
+		ret = -EBUSY;
+		goto out_free;
+	}
+
+	ret = trace_event_enable_disable(event_enable_file, 1, 1);
+	if (ret < 0)
+		goto out_put;
+	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+	/*
+	 * The above returns on success the # of functions enabled,
+	 * but if it didn't find any functions it returns zero.
+	 * Consider no functions a failure too.
+	 */
+	if (!ret) {
+		ret = -ENOENT;
+		goto out_disable;
+	} else if (ret < 0)
+		goto out_disable;
+	/* Just return zero, not the number of enabled functions */
+	ret = 0;
+ out:
+	return ret;
+
+ out_disable:
+	trace_event_enable_disable(event_enable_file, 0, 1);
+ out_put:
+	module_put(event_enable_file->event_call->mod);
+ out_free:
+	if (cmd_ops->set_filter)
+		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	kfree(trigger_data);
+	kfree(enable_data);
+	goto out;
+}
+
+static int event_enable_register_trigger(char *glob,
+					 struct event_trigger_ops *ops,
+					 struct event_trigger_data *data,
+					 struct ftrace_event_file *file)
+{
+	struct enable_trigger_data *enable_data = data->private_data;
+	struct enable_trigger_data *test_enable_data;
+	struct event_trigger_data *test;
+	int ret = 0;
+
+	list_for_each_entry_rcu(test, &file->triggers, list) {
+		test_enable_data = test->private_data;
+		if (test_enable_data &&
+		    (test_enable_data->file == enable_data->file)) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
+	if (data->ops->init) {
+		ret = data->ops->init(data->ops, data);
+		if (ret < 0)
+			goto out;
+	}
+
+	list_add_rcu(&data->list, &file->triggers);
+	ret++;
+
+	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+		list_del_rcu(&data->list);
+		ret--;
+	}
+	update_cond_flag(file);
+out:
+	return ret;
+}
+
+static void event_enable_unregister_trigger(char *glob,
+					    struct event_trigger_ops *ops,
+					    struct event_trigger_data *test,
+					    struct ftrace_event_file *file)
+{
+	struct enable_trigger_data *test_enable_data = test->private_data;
+	struct enable_trigger_data *enable_data;
+	struct event_trigger_data *data;
+	bool unregistered = false;
+
+	list_for_each_entry_rcu(data, &file->triggers, list) {
+		enable_data = data->private_data;
+		if (enable_data &&
+		    (enable_data->file == test_enable_data->file)) {
+			unregistered = true;
+			list_del_rcu(&data->list);
+			update_cond_flag(file);
+			trace_event_trigger_enable_disable(file, 0);
+			break;
+		}
+	}
+
+	if (unregistered && data->ops->free)
+		data->ops->free(data->ops, data);
+}
+
+static struct event_trigger_ops *
+event_enable_get_trigger_ops(char *cmd, char *param)
+{
+	struct event_trigger_ops *ops;
+	bool enable;
+
+	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+	if (enable)
+		ops = param ? &event_enable_count_trigger_ops :
+			&event_enable_trigger_ops;
+	else
+		ops = param ? &event_disable_count_trigger_ops :
+			&event_disable_trigger_ops;
+
+	return ops;
+}
+
+static struct event_command trigger_enable_cmd = {
+	.name			= ENABLE_EVENT_STR,
+	.trigger_type		= ETT_EVENT_ENABLE,
+	.func			= event_enable_trigger_func,
+	.reg			= event_enable_register_trigger,
+	.unreg			= event_enable_unregister_trigger,
+	.get_trigger_ops	= event_enable_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+static struct event_command trigger_disable_cmd = {
+	.name			= DISABLE_EVENT_STR,
+	.trigger_type		= ETT_EVENT_ENABLE,
+	.func			= event_enable_trigger_func,
+	.reg			= event_enable_register_trigger,
+	.unreg			= event_enable_unregister_trigger,
+	.get_trigger_ops	= event_enable_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+static __init void unregister_trigger_enable_disable_cmds(void)
+{
+	unregister_event_command(&trigger_enable_cmd);
+	unregister_event_command(&trigger_disable_cmd);
+}
+
+static __init int register_trigger_enable_disable_cmds(void)
+{
+	int ret;
+
+	ret = register_event_command(&trigger_enable_cmd);
+	if (WARN_ON(ret < 0))
+		return ret;
+	ret = register_event_command(&trigger_disable_cmd);
+	if (WARN_ON(ret < 0))
+		unregister_trigger_enable_disable_cmds();
+
+	return ret;
+}
+
+static __init int register_trigger_traceon_traceoff_cmds(void)
+{
+	int ret;
+
+	ret = register_event_command(&trigger_traceon_cmd);
+	if (WARN_ON(ret < 0))
+		return ret;
+	ret = register_event_command(&trigger_traceoff_cmd);
+	if (WARN_ON(ret < 0))
+		unregister_trigger_traceon_traceoff_cmds();
+
+	return ret;
+}
+
+__init int register_trigger_cmds(void)
+{
+	register_trigger_traceon_traceoff_cmds();
+	register_trigger_snapshot_cmd();
+	register_trigger_stacktrace_cmd();
+	register_trigger_enable_disable_cmds();
+
+	return 0;
+}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index dae9541..bdbae45 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -27,18 +27,12 @@
 /**
  * Kprobe event core functions
  */
-struct trace_probe {
+struct trace_kprobe {
 	struct list_head	list;
 	struct kretprobe	rp;	/* Use rp.kp for kprobe use */
 	unsigned long 		nhit;
-	unsigned int		flags;	/* For TP_FLAG_* */
 	const char		*symbol;	/* symbol name */
-	struct ftrace_event_class	class;
-	struct ftrace_event_call	call;
-	struct list_head	files;
-	ssize_t			size;		/* trace entry size */
-	unsigned int		nr_args;
-	struct probe_arg	args[];
+	struct trace_probe	tp;
 };
 
 struct event_file_link {
@@ -46,56 +40,46 @@ struct event_file_link {
 	struct list_head		list;
 };
 
-#define SIZEOF_TRACE_PROBE(n)			\
-	(offsetof(struct trace_probe, args) +	\
+#define SIZEOF_TRACE_KPROBE(n)				\
+	(offsetof(struct trace_kprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
 
-static __kprobes bool trace_probe_is_return(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
-	return tp->rp.handler != NULL;
+	return tk->rp.handler != NULL;
 }
 
-static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
+static __kprobes const char *trace_kprobe_symbol(struct trace_kprobe *tk)
 {
-	return tp->symbol ? tp->symbol : "unknown";
+	return tk->symbol ? tk->symbol : "unknown";
 }
 
-static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+static __kprobes unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
 {
-	return tp->rp.kp.offset;
+	return tk->rp.kp.offset;
 }
 
-static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_has_gone(struct trace_kprobe *tk)
 {
-	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+	return !!(kprobe_gone(&tk->rp.kp));
 }
 
-static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
-{
-	return !!(tp->flags & TP_FLAG_REGISTERED);
-}
-
-static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
-{
-	return !!(kprobe_gone(&tp->rp.kp));
-}
-
-static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
-						struct module *mod)
+static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk,
+						 struct module *mod)
 {
 	int len = strlen(mod->name);
-	const char *name = trace_probe_symbol(tp);
+	const char *name = trace_kprobe_symbol(tk);
 	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
 }
 
-static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
 {
-	return !!strchr(trace_probe_symbol(tp), ':');
+	return !!strchr(trace_kprobe_symbol(tk), ':');
 }
 
-static int register_probe_event(struct trace_probe *tp);
-static int unregister_probe_event(struct trace_probe *tp);
+static int register_kprobe_event(struct trace_kprobe *tk);
+static int unregister_kprobe_event(struct trace_kprobe *tk);
 
 static DEFINE_MUTEX(probe_lock);
 static LIST_HEAD(probe_list);
@@ -104,45 +88,224 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
+/* Memory fetching by symbol */
+struct symbol_cache {
+	char		*symbol;
+	long		offset;
+	unsigned long	addr;
+};
+
+unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+	sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+
+	if (sc->addr)
+		sc->addr += sc->offset;
+
+	return sc->addr;
+}
+
+void free_symbol_cache(struct symbol_cache *sc)
+{
+	kfree(sc->symbol);
+	kfree(sc);
+}
+
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+	struct symbol_cache *sc;
+
+	if (!sym || strlen(sym) == 0)
+		return NULL;
+
+	sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+	if (!sc)
+		return NULL;
+
+	sc->symbol = kstrdup(sym, GFP_KERNEL);
+	if (!sc->symbol) {
+		kfree(sc);
+		return NULL;
+	}
+	sc->offset = offset;
+	update_symbol_cache(sc);
+
+	return sc;
+}
+
+/*
+ * Kprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type)					\
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
+				(unsigned int)((unsigned long)offset));	\
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string	NULL
+#define fetch_stack_string_size	NULL
+
+#define DEFINE_FETCH_memory(type)					\
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+					  void *addr, void *dest)	\
+{									\
+	type retval;							\
+	if (probe_kernel_address(addr, retval))				\
+		*(type *)dest = 0;					\
+	else								\
+		*(type *)dest = retval;					\
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+						      void *addr, void *dest)
+{
+	long ret;
+	int maxlen = get_rloc_len(*(u32 *)dest);
+	u8 *dst = get_rloc_data(dest);
+	u8 *src = addr;
+	mm_segment_t old_fs = get_fs();
+
+	if (!maxlen)
+		return;
+
+	/*
+	 * Try to get string again, since the string can be changed while
+	 * probing.
+	 */
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+
+	do
+		ret = __copy_from_user_inatomic(dst++, src++, 1);
+	while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+
+	dst[-1] = '\0';
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret < 0) {	/* Failed to fetch string */
+		((u8 *)get_rloc_data(dest))[0] = '\0';
+		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+	} else {
+		*(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+					      get_rloc_offs(*(u32 *)dest));
+	}
+}
+
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+							void *addr, void *dest)
+{
+	mm_segment_t old_fs;
+	int ret, len = 0;
+	u8 c;
+
+	old_fs = get_fs();
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+
+	do {
+		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+		len++;
+	} while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret < 0)	/* Failed to check the length */
+		*(u32 *)dest = 0;
+	else
+		*(u32 *)dest = len;
+}
+
+#define DEFINE_FETCH_symbol(type)					\
+__kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,	\
+					  void *data, void *dest)	\
+{									\
+	struct symbol_cache *sc = data;					\
+	if (sc->addr)							\
+		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
+	else								\
+		*(type *)dest = 0;					\
+}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
+
+/* kprobes don't support file_offset fetch methods */
+#define fetch_file_offset_u8		NULL
+#define fetch_file_offset_u16		NULL
+#define fetch_file_offset_u32		NULL
+#define fetch_file_offset_u64		NULL
+#define fetch_file_offset_string	NULL
+#define fetch_file_offset_string_size	NULL
+
+/* Fetch type information table */
+const struct fetch_type kprobes_fetch_type_table[] = {
+	/* Special types */
+	[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+					sizeof(u32), 1, "__data_loc char[]"),
+	[FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+					string_size, sizeof(u32), 0, "u32"),
+	/* Basic types */
+	ASSIGN_FETCH_TYPE(u8,  u8,  0),
+	ASSIGN_FETCH_TYPE(u16, u16, 0),
+	ASSIGN_FETCH_TYPE(u32, u32, 0),
+	ASSIGN_FETCH_TYPE(u64, u64, 0),
+	ASSIGN_FETCH_TYPE(s8,  u8,  1),
+	ASSIGN_FETCH_TYPE(s16, u16, 1),
+	ASSIGN_FETCH_TYPE(s32, u32, 1),
+	ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+	ASSIGN_FETCH_TYPE_END
+};
+
 /*
  * Allocate new trace_probe and initialize it (including kprobes).
  */
-static struct trace_probe *alloc_trace_probe(const char *group,
+static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 					     const char *event,
 					     void *addr,
 					     const char *symbol,
 					     unsigned long offs,
 					     int nargs, bool is_return)
 {
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 	int ret = -ENOMEM;
 
-	tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
-	if (!tp)
+	tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL);
+	if (!tk)
 		return ERR_PTR(ret);
 
 	if (symbol) {
-		tp->symbol = kstrdup(symbol, GFP_KERNEL);
-		if (!tp->symbol)
+		tk->symbol = kstrdup(symbol, GFP_KERNEL);
+		if (!tk->symbol)
 			goto error;
-		tp->rp.kp.symbol_name = tp->symbol;
-		tp->rp.kp.offset = offs;
+		tk->rp.kp.symbol_name = tk->symbol;
+		tk->rp.kp.offset = offs;
 	} else
-		tp->rp.kp.addr = addr;
+		tk->rp.kp.addr = addr;
 
 	if (is_return)
-		tp->rp.handler = kretprobe_dispatcher;
+		tk->rp.handler = kretprobe_dispatcher;
 	else
-		tp->rp.kp.pre_handler = kprobe_dispatcher;
+		tk->rp.kp.pre_handler = kprobe_dispatcher;
 
 	if (!event || !is_good_name(event)) {
 		ret = -EINVAL;
 		goto error;
 	}
 
-	tp->call.class = &tp->class;
-	tp->call.name = kstrdup(event, GFP_KERNEL);
-	if (!tp->call.name)
+	tk->tp.call.class = &tk->tp.class;
+	tk->tp.call.name = kstrdup(event, GFP_KERNEL);
+	if (!tk->tp.call.name)
 		goto error;
 
 	if (!group || !is_good_name(group)) {
@@ -150,42 +313,42 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 		goto error;
 	}
 
-	tp->class.system = kstrdup(group, GFP_KERNEL);
-	if (!tp->class.system)
+	tk->tp.class.system = kstrdup(group, GFP_KERNEL);
+	if (!tk->tp.class.system)
 		goto error;
 
-	INIT_LIST_HEAD(&tp->list);
-	INIT_LIST_HEAD(&tp->files);
-	return tp;
+	INIT_LIST_HEAD(&tk->list);
+	INIT_LIST_HEAD(&tk->tp.files);
+	return tk;
 error:
-	kfree(tp->call.name);
-	kfree(tp->symbol);
-	kfree(tp);
+	kfree(tk->tp.call.name);
+	kfree(tk->symbol);
+	kfree(tk);
 	return ERR_PTR(ret);
 }
 
-static void free_trace_probe(struct trace_probe *tp)
+static void free_trace_kprobe(struct trace_kprobe *tk)
 {
 	int i;
 
-	for (i = 0; i < tp->nr_args; i++)
-		traceprobe_free_probe_arg(&tp->args[i]);
+	for (i = 0; i < tk->tp.nr_args; i++)
+		traceprobe_free_probe_arg(&tk->tp.args[i]);
 
-	kfree(tp->call.class->system);
-	kfree(tp->call.name);
-	kfree(tp->symbol);
-	kfree(tp);
+	kfree(tk->tp.call.class->system);
+	kfree(tk->tp.call.name);
+	kfree(tk->symbol);
+	kfree(tk);
 }
 
-static struct trace_probe *find_trace_probe(const char *event,
-					    const char *group)
+static struct trace_kprobe *find_trace_kprobe(const char *event,
+					      const char *group)
 {
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 
-	list_for_each_entry(tp, &probe_list, list)
-		if (strcmp(tp->call.name, event) == 0 &&
-		    strcmp(tp->call.class->system, group) == 0)
-			return tp;
+	list_for_each_entry(tk, &probe_list, list)
+		if (strcmp(tk->tp.call.name, event) == 0 &&
+		    strcmp(tk->tp.call.class->system, group) == 0)
+			return tk;
 	return NULL;
 }
 
@@ -194,7 +357,7 @@ static struct trace_probe *find_trace_probe(const char *event,
  * if the file is NULL, enable "perf" handler, or enable "trace" handler.
  */
 static int
-enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
 {
 	int ret = 0;
 
@@ -208,17 +371,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 		}
 
 		link->file = file;
-		list_add_tail_rcu(&link->list, &tp->files);
+		list_add_tail_rcu(&link->list, &tk->tp.files);
 
-		tp->flags |= TP_FLAG_TRACE;
+		tk->tp.flags |= TP_FLAG_TRACE;
 	} else
-		tp->flags |= TP_FLAG_PROFILE;
+		tk->tp.flags |= TP_FLAG_PROFILE;
 
-	if (trace_probe_is_registered(tp) && !trace_probe_has_gone(tp)) {
-		if (trace_probe_is_return(tp))
-			ret = enable_kretprobe(&tp->rp);
+	if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
+		if (trace_kprobe_is_return(tk))
+			ret = enable_kretprobe(&tk->rp);
 		else
-			ret = enable_kprobe(&tp->rp.kp);
+			ret = enable_kprobe(&tk->rp.kp);
 	}
  out:
 	return ret;
@@ -241,14 +404,14 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
  * if the file is NULL, disable "perf" handler, or disable "trace" handler.
  */
 static int
-disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+disable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
 {
 	struct event_file_link *link = NULL;
 	int wait = 0;
 	int ret = 0;
 
 	if (file) {
-		link = find_event_file_link(tp, file);
+		link = find_event_file_link(&tk->tp, file);
 		if (!link) {
 			ret = -EINVAL;
 			goto out;
@@ -256,18 +419,18 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 
 		list_del_rcu(&link->list);
 		wait = 1;
-		if (!list_empty(&tp->files))
+		if (!list_empty(&tk->tp.files))
 			goto out;
 
-		tp->flags &= ~TP_FLAG_TRACE;
+		tk->tp.flags &= ~TP_FLAG_TRACE;
 	} else
-		tp->flags &= ~TP_FLAG_PROFILE;
+		tk->tp.flags &= ~TP_FLAG_PROFILE;
 
-	if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
-		if (trace_probe_is_return(tp))
-			disable_kretprobe(&tp->rp);
+	if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) {
+		if (trace_kprobe_is_return(tk))
+			disable_kretprobe(&tk->rp);
 		else
-			disable_kprobe(&tp->rp.kp);
+			disable_kprobe(&tk->rp.kp);
 		wait = 1;
 	}
  out:
@@ -288,40 +451,40 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 }
 
 /* Internal register function - just handle k*probes and flags */
-static int __register_trace_probe(struct trace_probe *tp)
+static int __register_trace_kprobe(struct trace_kprobe *tk)
 {
 	int i, ret;
 
-	if (trace_probe_is_registered(tp))
+	if (trace_probe_is_registered(&tk->tp))
 		return -EINVAL;
 
-	for (i = 0; i < tp->nr_args; i++)
-		traceprobe_update_arg(&tp->args[i]);
+	for (i = 0; i < tk->tp.nr_args; i++)
+		traceprobe_update_arg(&tk->tp.args[i]);
 
 	/* Set/clear disabled flag according to tp->flag */
-	if (trace_probe_is_enabled(tp))
-		tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+	if (trace_probe_is_enabled(&tk->tp))
+		tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
 	else
-		tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+		tk->rp.kp.flags |= KPROBE_FLAG_DISABLED;
 
-	if (trace_probe_is_return(tp))
-		ret = register_kretprobe(&tp->rp);
+	if (trace_kprobe_is_return(tk))
+		ret = register_kretprobe(&tk->rp);
 	else
-		ret = register_kprobe(&tp->rp.kp);
+		ret = register_kprobe(&tk->rp.kp);
 
 	if (ret == 0)
-		tp->flags |= TP_FLAG_REGISTERED;
+		tk->tp.flags |= TP_FLAG_REGISTERED;
 	else {
 		pr_warning("Could not insert probe at %s+%lu: %d\n",
-			   trace_probe_symbol(tp), trace_probe_offset(tp), ret);
-		if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+			   trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
+		if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
 			pr_warning("This probe might be able to register after"
 				   "target module is loaded. Continue.\n");
 			ret = 0;
 		} else if (ret == -EILSEQ) {
 			pr_warning("Probing address(0x%p) is not an "
 				   "instruction boundary.\n",
-				   tp->rp.kp.addr);
+				   tk->rp.kp.addr);
 			ret = -EINVAL;
 		}
 	}
@@ -330,67 +493,67 @@ static int __register_trace_probe(struct trace_probe *tp)
 }
 
 /* Internal unregister function - just handle k*probes and flags */
-static void __unregister_trace_probe(struct trace_probe *tp)
+static void __unregister_trace_kprobe(struct trace_kprobe *tk)
 {
-	if (trace_probe_is_registered(tp)) {
-		if (trace_probe_is_return(tp))
-			unregister_kretprobe(&tp->rp);
+	if (trace_probe_is_registered(&tk->tp)) {
+		if (trace_kprobe_is_return(tk))
+			unregister_kretprobe(&tk->rp);
 		else
-			unregister_kprobe(&tp->rp.kp);
-		tp->flags &= ~TP_FLAG_REGISTERED;
+			unregister_kprobe(&tk->rp.kp);
+		tk->tp.flags &= ~TP_FLAG_REGISTERED;
 		/* Cleanup kprobe for reuse */
-		if (tp->rp.kp.symbol_name)
-			tp->rp.kp.addr = NULL;
+		if (tk->rp.kp.symbol_name)
+			tk->rp.kp.addr = NULL;
 	}
 }
 
 /* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static int unregister_trace_probe(struct trace_probe *tp)
+static int unregister_trace_kprobe(struct trace_kprobe *tk)
 {
 	/* Enabled event can not be unregistered */
-	if (trace_probe_is_enabled(tp))
+	if (trace_probe_is_enabled(&tk->tp))
 		return -EBUSY;
 
 	/* Will fail if probe is being used by ftrace or perf */
-	if (unregister_probe_event(tp))
+	if (unregister_kprobe_event(tk))
 		return -EBUSY;
 
-	__unregister_trace_probe(tp);
-	list_del(&tp->list);
+	__unregister_trace_kprobe(tk);
+	list_del(&tk->list);
 
 	return 0;
 }
 
 /* Register a trace_probe and probe_event */
-static int register_trace_probe(struct trace_probe *tp)
+static int register_trace_kprobe(struct trace_kprobe *tk)
 {
-	struct trace_probe *old_tp;
+	struct trace_kprobe *old_tk;
 	int ret;
 
 	mutex_lock(&probe_lock);
 
 	/* Delete old (same name) event if exist */
-	old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
-	if (old_tp) {
-		ret = unregister_trace_probe(old_tp);
+	old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system);
+	if (old_tk) {
+		ret = unregister_trace_kprobe(old_tk);
 		if (ret < 0)
 			goto end;
-		free_trace_probe(old_tp);
+		free_trace_kprobe(old_tk);
 	}
 
 	/* Register new event */
-	ret = register_probe_event(tp);
+	ret = register_kprobe_event(tk);
 	if (ret) {
 		pr_warning("Failed to register probe event(%d)\n", ret);
 		goto end;
 	}
 
 	/* Register k*probe */
-	ret = __register_trace_probe(tp);
+	ret = __register_trace_kprobe(tk);
 	if (ret < 0)
-		unregister_probe_event(tp);
+		unregister_kprobe_event(tk);
 	else
-		list_add_tail(&tp->list, &probe_list);
+		list_add_tail(&tk->list, &probe_list);
 
 end:
 	mutex_unlock(&probe_lock);
@@ -398,11 +561,11 @@ end:
 }
 
 /* Module notifier call back, checking event on the module */
-static int trace_probe_module_callback(struct notifier_block *nb,
+static int trace_kprobe_module_callback(struct notifier_block *nb,
 				       unsigned long val, void *data)
 {
 	struct module *mod = data;
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 	int ret;
 
 	if (val != MODULE_STATE_COMING)
@@ -410,15 +573,15 @@ static int trace_probe_module_callback(struct notifier_block *nb,
 
 	/* Update probes on coming module */
 	mutex_lock(&probe_lock);
-	list_for_each_entry(tp, &probe_list, list) {
-		if (trace_probe_within_module(tp, mod)) {
+	list_for_each_entry(tk, &probe_list, list) {
+		if (trace_kprobe_within_module(tk, mod)) {
 			/* Don't need to check busy - this should have gone. */
-			__unregister_trace_probe(tp);
-			ret = __register_trace_probe(tp);
+			__unregister_trace_kprobe(tk);
+			ret = __register_trace_kprobe(tk);
 			if (ret)
 				pr_warning("Failed to re-register probe %s on"
 					   "%s: %d\n",
-					   tp->call.name, mod->name, ret);
+					   tk->tp.call.name, mod->name, ret);
 		}
 	}
 	mutex_unlock(&probe_lock);
@@ -426,12 +589,12 @@ static int trace_probe_module_callback(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block trace_probe_module_nb = {
-	.notifier_call = trace_probe_module_callback,
+static struct notifier_block trace_kprobe_module_nb = {
+	.notifier_call = trace_kprobe_module_callback,
 	.priority = 1	/* Invoked after kprobe module callback */
 };
 
-static int create_trace_probe(int argc, char **argv)
+static int create_trace_kprobe(int argc, char **argv)
 {
 	/*
 	 * Argument syntax:
@@ -451,7 +614,7 @@ static int create_trace_probe(int argc, char **argv)
 	 * Type of args:
 	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
 	 */
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 	int i, ret = 0;
 	bool is_return = false, is_delete = false;
 	char *symbol = NULL, *event = NULL, *group = NULL;
@@ -498,16 +661,16 @@ static int create_trace_probe(int argc, char **argv)
 			return -EINVAL;
 		}
 		mutex_lock(&probe_lock);
-		tp = find_trace_probe(event, group);
-		if (!tp) {
+		tk = find_trace_kprobe(event, group);
+		if (!tk) {
 			mutex_unlock(&probe_lock);
 			pr_info("Event %s/%s doesn't exist.\n", group, event);
 			return -ENOENT;
 		}
 		/* delete an event */
-		ret = unregister_trace_probe(tp);
+		ret = unregister_trace_kprobe(tk);
 		if (ret == 0)
-			free_trace_probe(tp);
+			free_trace_kprobe(tk);
 		mutex_unlock(&probe_lock);
 		return ret;
 	}
@@ -554,47 +717,49 @@ static int create_trace_probe(int argc, char **argv)
 				 is_return ? 'r' : 'p', addr);
 		event = buf;
 	}
-	tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc,
 			       is_return);
-	if (IS_ERR(tp)) {
+	if (IS_ERR(tk)) {
 		pr_info("Failed to allocate trace_probe.(%d)\n",
-			(int)PTR_ERR(tp));
-		return PTR_ERR(tp);
+			(int)PTR_ERR(tk));
+		return PTR_ERR(tk);
 	}
 
 	/* parse arguments */
 	ret = 0;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		struct probe_arg *parg = &tk->tp.args[i];
+
 		/* Increment count for freeing args in error case */
-		tp->nr_args++;
+		tk->tp.nr_args++;
 
 		/* Parse argument name */
 		arg = strchr(argv[i], '=');
 		if (arg) {
 			*arg++ = '\0';
-			tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+			parg->name = kstrdup(argv[i], GFP_KERNEL);
 		} else {
 			arg = argv[i];
 			/* If argument name is omitted, set "argN" */
 			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
-			tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+			parg->name = kstrdup(buf, GFP_KERNEL);
 		}
 
-		if (!tp->args[i].name) {
+		if (!parg->name) {
 			pr_info("Failed to allocate argument[%d] name.\n", i);
 			ret = -ENOMEM;
 			goto error;
 		}
 
-		if (!is_good_name(tp->args[i].name)) {
+		if (!is_good_name(parg->name)) {
 			pr_info("Invalid argument[%d] name: %s\n",
-				i, tp->args[i].name);
+				i, parg->name);
 			ret = -EINVAL;
 			goto error;
 		}
 
-		if (traceprobe_conflict_field_name(tp->args[i].name,
-							tp->args, i)) {
+		if (traceprobe_conflict_field_name(parg->name,
+							tk->tp.args, i)) {
 			pr_info("Argument[%d] name '%s' conflicts with "
 				"another field.\n", i, argv[i]);
 			ret = -EINVAL;
@@ -602,7 +767,7 @@ static int create_trace_probe(int argc, char **argv)
 		}
 
 		/* Parse fetch argument */
-		ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i],
+		ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
 						is_return, true);
 		if (ret) {
 			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
@@ -610,35 +775,35 @@ static int create_trace_probe(int argc, char **argv)
 		}
 	}
 
-	ret = register_trace_probe(tp);
+	ret = register_trace_kprobe(tk);
 	if (ret)
 		goto error;
 	return 0;
 
 error:
-	free_trace_probe(tp);
+	free_trace_kprobe(tk);
 	return ret;
 }
 
-static int release_all_trace_probes(void)
+static int release_all_trace_kprobes(void)
 {
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 	int ret = 0;
 
 	mutex_lock(&probe_lock);
 	/* Ensure no probe is in use. */
-	list_for_each_entry(tp, &probe_list, list)
-		if (trace_probe_is_enabled(tp)) {
+	list_for_each_entry(tk, &probe_list, list)
+		if (trace_probe_is_enabled(&tk->tp)) {
 			ret = -EBUSY;
 			goto end;
 		}
 	/* TODO: Use batch unregistration */
 	while (!list_empty(&probe_list)) {
-		tp = list_entry(probe_list.next, struct trace_probe, list);
-		ret = unregister_trace_probe(tp);
+		tk = list_entry(probe_list.next, struct trace_kprobe, list);
+		ret = unregister_trace_kprobe(tk);
 		if (ret)
 			goto end;
-		free_trace_probe(tp);
+		free_trace_kprobe(tk);
 	}
 
 end:
@@ -666,22 +831,22 @@ static void probes_seq_stop(struct seq_file *m, void *v)
 
 static int probes_seq_show(struct seq_file *m, void *v)
 {
-	struct trace_probe *tp = v;
+	struct trace_kprobe *tk = v;
 	int i;
 
-	seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
-	seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
+	seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p');
+	seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name);
 
-	if (!tp->symbol)
-		seq_printf(m, " 0x%p", tp->rp.kp.addr);
-	else if (tp->rp.kp.offset)
-		seq_printf(m, " %s+%u", trace_probe_symbol(tp),
-			   tp->rp.kp.offset);
+	if (!tk->symbol)
+		seq_printf(m, " 0x%p", tk->rp.kp.addr);
+	else if (tk->rp.kp.offset)
+		seq_printf(m, " %s+%u", trace_kprobe_symbol(tk),
+			   tk->rp.kp.offset);
 	else
-		seq_printf(m, " %s", trace_probe_symbol(tp));
+		seq_printf(m, " %s", trace_kprobe_symbol(tk));
 
-	for (i = 0; i < tp->nr_args; i++)
-		seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
+	for (i = 0; i < tk->tp.nr_args; i++)
+		seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm);
 	seq_printf(m, "\n");
 
 	return 0;
@@ -699,7 +864,7 @@ static int probes_open(struct inode *inode, struct file *file)
 	int ret;
 
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
-		ret = release_all_trace_probes();
+		ret = release_all_trace_kprobes();
 		if (ret < 0)
 			return ret;
 	}
@@ -711,7 +876,7 @@ static ssize_t probes_write(struct file *file, const char __user *buffer,
 			    size_t count, loff_t *ppos)
 {
 	return traceprobe_probes_write(file, buffer, count, ppos,
-			create_trace_probe);
+			create_trace_kprobe);
 }
 
 static const struct file_operations kprobe_events_ops = {
@@ -726,10 +891,10 @@ static const struct file_operations kprobe_events_ops = {
 /* Probes profiling interfaces */
 static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
-	struct trace_probe *tp = v;
+	struct trace_kprobe *tk = v;
 
-	seq_printf(m, "  %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
-		   tp->rp.kp.nmissed);
+	seq_printf(m, "  %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit,
+		   tk->rp.kp.nmissed);
 
 	return 0;
 }
@@ -754,57 +919,9 @@ static const struct file_operations kprobe_profile_ops = {
 	.release        = seq_release,
 };
 
-/* Sum up total data length for dynamic arraies (strings) */
-static __kprobes int __get_data_size(struct trace_probe *tp,
-				     struct pt_regs *regs)
-{
-	int i, ret = 0;
-	u32 len;
-
-	for (i = 0; i < tp->nr_args; i++)
-		if (unlikely(tp->args[i].fetch_size.fn)) {
-			call_fetch(&tp->args[i].fetch_size, regs, &len);
-			ret += len;
-		}
-
-	return ret;
-}
-
-/* Store the value of each argument */
-static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp,
-				       struct pt_regs *regs,
-				       u8 *data, int maxlen)
-{
-	int i;
-	u32 end = tp->size;
-	u32 *dl;	/* Data (relative) location */
-
-	for (i = 0; i < tp->nr_args; i++) {
-		if (unlikely(tp->args[i].fetch_size.fn)) {
-			/*
-			 * First, we set the relative location and
-			 * maximum data length to *dl
-			 */
-			dl = (u32 *)(data + tp->args[i].offset);
-			*dl = make_data_rloc(maxlen, end - tp->args[i].offset);
-			/* Then try to fetch string or dynamic array data */
-			call_fetch(&tp->args[i].fetch, regs, dl);
-			/* Reduce maximum length */
-			end += get_rloc_len(*dl);
-			maxlen -= get_rloc_len(*dl);
-			/* Trick here, convert data_rloc to data_loc */
-			*dl = convert_rloc_to_loc(*dl,
-				 ent_size + tp->args[i].offset);
-		} else
-			/* Just fetching data normally */
-			call_fetch(&tp->args[i].fetch, regs,
-				   data + tp->args[i].offset);
-	}
-}
-
 /* Kprobe handler */
 static __kprobes void
-__kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
+__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 		    struct ftrace_event_file *ftrace_file)
 {
 	struct kprobe_trace_entry_head *entry;
@@ -812,18 +929,18 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 	struct ring_buffer *buffer;
 	int size, dsize, pc;
 	unsigned long irq_flags;
-	struct ftrace_event_call *call = &tp->call;
+	struct ftrace_event_call *call = &tk->tp.call;
 
 	WARN_ON(call != ftrace_file->event_call);
 
-	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	dsize = __get_data_size(tp, regs);
-	size = sizeof(*entry) + tp->size + dsize;
+	dsize = __get_data_size(&tk->tp, regs);
+	size = sizeof(*entry) + tk->tp.size + dsize;
 
 	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
 						call->event.type,
@@ -832,26 +949,25 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->ip = (unsigned long)tp->rp.kp.addr;
-	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+	entry->ip = (unsigned long)tk->rp.kp.addr;
+	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 
-	if (!filter_check_discard(ftrace_file, entry, buffer, event))
-		trace_buffer_unlock_commit_regs(buffer, event,
-						irq_flags, pc, regs);
+	event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+					 entry, irq_flags, pc, regs);
 }
 
 static __kprobes void
-kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct event_file_link *link;
 
-	list_for_each_entry_rcu(link, &tp->files, list)
-		__kprobe_trace_func(tp, regs, link->file);
+	list_for_each_entry_rcu(link, &tk->tp.files, list)
+		__kprobe_trace_func(tk, regs, link->file);
 }
 
 /* Kretprobe handler */
 static __kprobes void
-__kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+__kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		       struct pt_regs *regs,
 		       struct ftrace_event_file *ftrace_file)
 {
@@ -860,18 +976,18 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	struct ring_buffer *buffer;
 	int size, pc, dsize;
 	unsigned long irq_flags;
-	struct ftrace_event_call *call = &tp->call;
+	struct ftrace_event_call *call = &tk->tp.call;
 
 	WARN_ON(call != ftrace_file->event_call);
 
-	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
-	dsize = __get_data_size(tp, regs);
-	size = sizeof(*entry) + tp->size + dsize;
+	dsize = __get_data_size(&tk->tp, regs);
+	size = sizeof(*entry) + tk->tp.size + dsize;
 
 	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
 						call->event.type,
@@ -880,23 +996,22 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 		return;
 
 	entry = ring_buffer_event_data(event);
-	entry->func = (unsigned long)tp->rp.kp.addr;
+	entry->func = (unsigned long)tk->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
-	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 
-	if (!filter_check_discard(ftrace_file, entry, buffer, event))
-		trace_buffer_unlock_commit_regs(buffer, event,
-						irq_flags, pc, regs);
+	event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+					 entry, irq_flags, pc, regs);
 }
 
 static __kprobes void
-kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		     struct pt_regs *regs)
 {
 	struct event_file_link *link;
 
-	list_for_each_entry_rcu(link, &tp->files, list)
-		__kretprobe_trace_func(tp, ri, regs, link->file);
+	list_for_each_entry_rcu(link, &tk->tp.files, list)
+		__kretprobe_trace_func(tk, ri, regs, link->file);
 }
 
 /* Event entry printers */
@@ -983,16 +1098,18 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
 	struct kprobe_trace_entry_head field;
-	struct trace_probe *tp = (struct trace_probe *)event_call->data;
+	struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++) {
-		ret = trace_define_field(event_call, tp->args[i].type->fmttype,
-					 tp->args[i].name,
-					 sizeof(field) + tp->args[i].offset,
-					 tp->args[i].type->size,
-					 tp->args[i].type->is_signed,
+	for (i = 0; i < tk->tp.nr_args; i++) {
+		struct probe_arg *parg = &tk->tp.args[i];
+
+		ret = trace_define_field(event_call, parg->type->fmttype,
+					 parg->name,
+					 sizeof(field) + parg->offset,
+					 parg->type->size,
+					 parg->type->is_signed,
 					 FILTER_OTHER);
 		if (ret)
 			return ret;
@@ -1004,17 +1121,19 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 {
 	int ret, i;
 	struct kretprobe_trace_entry_head field;
-	struct trace_probe *tp = (struct trace_probe *)event_call->data;
+	struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
 
 	DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
 	DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
 	/* Set argument names as fields */
-	for (i = 0; i < tp->nr_args; i++) {
-		ret = trace_define_field(event_call, tp->args[i].type->fmttype,
-					 tp->args[i].name,
-					 sizeof(field) + tp->args[i].offset,
-					 tp->args[i].type->size,
-					 tp->args[i].type->is_signed,
+	for (i = 0; i < tk->tp.nr_args; i++) {
+		struct probe_arg *parg = &tk->tp.args[i];
+
+		ret = trace_define_field(event_call, parg->type->fmttype,
+					 parg->name,
+					 sizeof(field) + parg->offset,
+					 parg->type->size,
+					 parg->type->is_signed,
 					 FILTER_OTHER);
 		if (ret)
 			return ret;
@@ -1022,74 +1141,13 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 	return 0;
 }
 
-static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
-{
-	int i;
-	int pos = 0;
-
-	const char *fmt, *arg;
-
-	if (!trace_probe_is_return(tp)) {
-		fmt = "(%lx)";
-		arg = "REC->" FIELD_STRING_IP;
-	} else {
-		fmt = "(%lx <- %lx)";
-		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
-	}
-
-	/* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
-	for (i = 0; i < tp->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
-				tp->args[i].name, tp->args[i].type->fmt);
-	}
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
-	for (i = 0; i < tp->nr_args; i++) {
-		if (strcmp(tp->args[i].type->name, "string") == 0)
-			pos += snprintf(buf + pos, LEN_OR_ZERO,
-					", __get_str(%s)",
-					tp->args[i].name);
-		else
-			pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
-					tp->args[i].name);
-	}
-
-#undef LEN_OR_ZERO
-
-	/* return the length of print_fmt */
-	return pos;
-}
-
-static int set_print_fmt(struct trace_probe *tp)
-{
-	int len;
-	char *print_fmt;
-
-	/* First: called with 0 length to calculate the needed length */
-	len = __set_print_fmt(tp, NULL, 0);
-	print_fmt = kmalloc(len + 1, GFP_KERNEL);
-	if (!print_fmt)
-		return -ENOMEM;
-
-	/* Second: actually write the @print_fmt */
-	__set_print_fmt(tp, print_fmt, len + 1);
-	tp->call.print_fmt = print_fmt;
-
-	return 0;
-}
-
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
 static __kprobes void
-kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
-	struct ftrace_event_call *call = &tp->call;
+	struct ftrace_event_call *call = &tk->tp.call;
 	struct kprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
@@ -1099,8 +1157,8 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
 	if (hlist_empty(head))
 		return;
 
-	dsize = __get_data_size(tp, regs);
-	__size = sizeof(*entry) + tp->size + dsize;
+	dsize = __get_data_size(&tk->tp, regs);
+	__size = sizeof(*entry) + tk->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
@@ -1108,18 +1166,18 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
 	if (!entry)
 		return;
 
-	entry->ip = (unsigned long)tp->rp.kp.addr;
+	entry->ip = (unsigned long)tk->rp.kp.addr;
 	memset(&entry[1], 0, dsize);
-	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
 
 /* Kretprobe profile handler */
 static __kprobes void
-kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		    struct pt_regs *regs)
 {
-	struct ftrace_event_call *call = &tp->call;
+	struct ftrace_event_call *call = &tk->tp.call;
 	struct kretprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
@@ -1129,8 +1187,8 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	if (hlist_empty(head))
 		return;
 
-	dsize = __get_data_size(tp, regs);
-	__size = sizeof(*entry) + tp->size + dsize;
+	dsize = __get_data_size(&tk->tp, regs);
+	__size = sizeof(*entry) + tk->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
@@ -1138,9 +1196,9 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	if (!entry)
 		return;
 
-	entry->func = (unsigned long)tp->rp.kp.addr;
+	entry->func = (unsigned long)tk->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
-	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
 #endif	/* CONFIG_PERF_EVENTS */
@@ -1155,20 +1213,20 @@ static __kprobes
 int kprobe_register(struct ftrace_event_call *event,
 		    enum trace_reg type, void *data)
 {
-	struct trace_probe *tp = (struct trace_probe *)event->data;
+	struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
 	struct ftrace_event_file *file = data;
 
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return enable_trace_probe(tp, file);
+		return enable_trace_kprobe(tk, file);
 	case TRACE_REG_UNREGISTER:
-		return disable_trace_probe(tp, file);
+		return disable_trace_kprobe(tk, file);
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return enable_trace_probe(tp, NULL);
+		return enable_trace_kprobe(tk, NULL);
 	case TRACE_REG_PERF_UNREGISTER:
-		return disable_trace_probe(tp, NULL);
+		return disable_trace_kprobe(tk, NULL);
 	case TRACE_REG_PERF_OPEN:
 	case TRACE_REG_PERF_CLOSE:
 	case TRACE_REG_PERF_ADD:
@@ -1182,15 +1240,15 @@ int kprobe_register(struct ftrace_event_call *event,
 static __kprobes
 int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
-	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
 
-	tp->nhit++;
+	tk->nhit++;
 
-	if (tp->flags & TP_FLAG_TRACE)
-		kprobe_trace_func(tp, regs);
+	if (tk->tp.flags & TP_FLAG_TRACE)
+		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (tp->flags & TP_FLAG_PROFILE)
-		kprobe_perf_func(tp, regs);
+	if (tk->tp.flags & TP_FLAG_PROFILE)
+		kprobe_perf_func(tk, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1198,15 +1256,15 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 static __kprobes
 int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
-	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+	struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
 
-	tp->nhit++;
+	tk->nhit++;
 
-	if (tp->flags & TP_FLAG_TRACE)
-		kretprobe_trace_func(tp, ri, regs);
+	if (tk->tp.flags & TP_FLAG_TRACE)
+		kretprobe_trace_func(tk, ri, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (tp->flags & TP_FLAG_PROFILE)
-		kretprobe_perf_func(tp, ri, regs);
+	if (tk->tp.flags & TP_FLAG_PROFILE)
+		kretprobe_perf_func(tk, ri, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1219,21 +1277,21 @@ static struct trace_event_functions kprobe_funcs = {
 	.trace		= print_kprobe_event
 };
 
-static int register_probe_event(struct trace_probe *tp)
+static int register_kprobe_event(struct trace_kprobe *tk)
 {
-	struct ftrace_event_call *call = &tp->call;
+	struct ftrace_event_call *call = &tk->tp.call;
 	int ret;
 
 	/* Initialize ftrace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
-	if (trace_probe_is_return(tp)) {
+	if (trace_kprobe_is_return(tk)) {
 		call->event.funcs = &kretprobe_funcs;
 		call->class->define_fields = kretprobe_event_define_fields;
 	} else {
 		call->event.funcs = &kprobe_funcs;
 		call->class->define_fields = kprobe_event_define_fields;
 	}
-	if (set_print_fmt(tp) < 0)
+	if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
 		return -ENOMEM;
 	ret = register_ftrace_event(&call->event);
 	if (!ret) {
@@ -1242,7 +1300,7 @@ static int register_probe_event(struct trace_probe *tp)
 	}
 	call->flags = 0;
 	call->class->reg = kprobe_register;
-	call->data = tp;
+	call->data = tk;
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n", call->name);
@@ -1252,14 +1310,14 @@ static int register_probe_event(struct trace_probe *tp)
 	return ret;
 }
 
-static int unregister_probe_event(struct trace_probe *tp)
+static int unregister_kprobe_event(struct trace_kprobe *tk)
 {
 	int ret;
 
 	/* tp->event is unregistered in trace_remove_event_call() */
-	ret = trace_remove_event_call(&tp->call);
+	ret = trace_remove_event_call(&tk->tp.call);
 	if (!ret)
-		kfree(tp->call.print_fmt);
+		kfree(tk->tp.call.print_fmt);
 	return ret;
 }
 
@@ -1269,7 +1327,7 @@ static __init int init_kprobe_trace(void)
 	struct dentry *d_tracer;
 	struct dentry *entry;
 
-	if (register_module_notifier(&trace_probe_module_nb))
+	if (register_module_notifier(&trace_kprobe_module_nb))
 		return -EINVAL;
 
 	d_tracer = tracing_init_dentry();
@@ -1309,26 +1367,26 @@ static __used int kprobe_trace_selftest_target(int a1, int a2, int a3,
 }
 
 static struct ftrace_event_file *
-find_trace_probe_file(struct trace_probe *tp, struct trace_array *tr)
+find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
 {
 	struct ftrace_event_file *file;
 
 	list_for_each_entry(file, &tr->events, list)
-		if (file->event_call == &tp->call)
+		if (file->event_call == &tk->tp.call)
 			return file;
 
 	return NULL;
 }
 
 /*
- * Nobody but us can call enable_trace_probe/disable_trace_probe at this
+ * Nobody but us can call enable_trace_kprobe/disable_trace_kprobe at this
  * stage, we can do this lockless.
  */
 static __init int kprobe_trace_self_tests_init(void)
 {
 	int ret, warn = 0;
 	int (*target)(int, int, int, int, int, int);
-	struct trace_probe *tp;
+	struct trace_kprobe *tk;
 	struct ftrace_event_file *file;
 
 	target = kprobe_trace_selftest_target;
@@ -1337,44 +1395,44 @@ static __init int kprobe_trace_self_tests_init(void)
 
 	ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
 				  "$stack $stack0 +0($stack)",
-				  create_trace_probe);
+				  create_trace_kprobe);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warn("error on probing function entry.\n");
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
-		if (WARN_ON_ONCE(tp == NULL)) {
+		tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+		if (WARN_ON_ONCE(tk == NULL)) {
 			pr_warn("error on getting new probe.\n");
 			warn++;
 		} else {
-			file = find_trace_probe_file(tp, top_trace_array());
+			file = find_trace_probe_file(tk, top_trace_array());
 			if (WARN_ON_ONCE(file == NULL)) {
 				pr_warn("error on getting probe file.\n");
 				warn++;
 			} else
-				enable_trace_probe(tp, file);
+				enable_trace_kprobe(tk, file);
 		}
 	}
 
 	ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
-				  "$retval", create_trace_probe);
+				  "$retval", create_trace_kprobe);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warn("error on probing function return.\n");
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
-		if (WARN_ON_ONCE(tp == NULL)) {
+		tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+		if (WARN_ON_ONCE(tk == NULL)) {
 			pr_warn("error on getting 2nd new probe.\n");
 			warn++;
 		} else {
-			file = find_trace_probe_file(tp, top_trace_array());
+			file = find_trace_probe_file(tk, top_trace_array());
 			if (WARN_ON_ONCE(file == NULL)) {
 				pr_warn("error on getting probe file.\n");
 				warn++;
 			} else
-				enable_trace_probe(tp, file);
+				enable_trace_kprobe(tk, file);
 		}
 	}
 
@@ -1384,46 +1442,46 @@ static __init int kprobe_trace_self_tests_init(void)
 	ret = target(1, 2, 3, 4, 5, 6);
 
 	/* Disable trace points before removing it */
-	tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
-	if (WARN_ON_ONCE(tp == NULL)) {
+	tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tk == NULL)) {
 		pr_warn("error on getting test probe.\n");
 		warn++;
 	} else {
-		file = find_trace_probe_file(tp, top_trace_array());
+		file = find_trace_probe_file(tk, top_trace_array());
 		if (WARN_ON_ONCE(file == NULL)) {
 			pr_warn("error on getting probe file.\n");
 			warn++;
 		} else
-			disable_trace_probe(tp, file);
+			disable_trace_kprobe(tk, file);
 	}
 
-	tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
-	if (WARN_ON_ONCE(tp == NULL)) {
+	tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tk == NULL)) {
 		pr_warn("error on getting 2nd test probe.\n");
 		warn++;
 	} else {
-		file = find_trace_probe_file(tp, top_trace_array());
+		file = find_trace_probe_file(tk, top_trace_array());
 		if (WARN_ON_ONCE(file == NULL)) {
 			pr_warn("error on getting probe file.\n");
 			warn++;
 		} else
-			disable_trace_probe(tp, file);
+			disable_trace_kprobe(tk, file);
 	}
 
-	ret = traceprobe_command("-:testprobe", create_trace_probe);
+	ret = traceprobe_command("-:testprobe", create_trace_kprobe);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warn("error on deleting a probe.\n");
 		warn++;
 	}
 
-	ret = traceprobe_command("-:testprobe2", create_trace_probe);
+	ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warn("error on deleting a probe.\n");
 		warn++;
 	}
 
 end:
-	release_all_trace_probes();
+	release_all_trace_kprobes();
 	if (warn)
 		pr_cont("NG: Some tests are failed. Please check them.\n");
 	else
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 412e959..8364a42 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -35,46 +35,27 @@ const char *reserved_field_names[] = {
 	FIELD_STRING_FUNC,
 };
 
-/* Printing function type */
-#define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
-#define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
-
 /* Printing  in basic type function template */
-#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast)			\
-static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt)				\
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
 						const char *name,	\
-						void *data, void *ent)\
+						void *data, void *ent)	\
 {									\
-	return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+	return trace_seq_printf(s, " %s=" fmt, name, *(type *)data);	\
 }									\
-static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-
-DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
-
-static inline void *get_rloc_data(u32 *dl)
-{
-	return (u8 *)dl + get_rloc_offs(*dl);
-}
+const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
 
-/* For data_loc conversion */
-static inline void *get_loc_data(u32 *dl, void *ent)
-{
-	return (u8 *)ent + get_rloc_offs(*dl);
-}
-
-/* For defining macros, define string/string_size types */
-typedef u32 string;
-typedef u32 string_size;
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "0x%Lx")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8,  "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld")
 
 /* Print type function for string type */
-static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+__kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
 						  const char *name,
 						  void *data, void *ent)
 {
@@ -87,18 +68,7 @@ static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
 					(const char *)get_loc_data(data, ent));
 }
 
-static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
-
-#define FETCH_FUNC_NAME(method, type)	fetch_##method##_##type
-/*
- * Define macro for basic types - we don't need to define s* types, because
- * we have to care only about bitwidth at recording time.
- */
-#define DEFINE_BASIC_FETCH_FUNCS(method) \
-DEFINE_FETCH_##method(u8)		\
-DEFINE_FETCH_##method(u16)		\
-DEFINE_FETCH_##method(u32)		\
-DEFINE_FETCH_##method(u64)
+const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
 
 #define CHECK_FETCH_FUNCS(method, fn)			\
 	(((FETCH_FUNC_NAME(method, u8) == fn) ||	\
@@ -111,7 +81,7 @@ DEFINE_FETCH_##method(u64)
 
 /* Data fetch function templates */
 #define DEFINE_FETCH_reg(type)						\
-static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,	\
+__kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,		\
 					void *offset, void *dest)	\
 {									\
 	*(type *)dest = (type)regs_get_register(regs,			\
@@ -122,20 +92,8 @@ DEFINE_BASIC_FETCH_FUNCS(reg)
 #define fetch_reg_string	NULL
 #define fetch_reg_string_size	NULL
 
-#define DEFINE_FETCH_stack(type)					\
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
-					  void *offset, void *dest)	\
-{									\
-	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
-				(unsigned int)((unsigned long)offset));	\
-}
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string	NULL
-#define fetch_stack_string_size	NULL
-
 #define DEFINE_FETCH_retval(type)					\
-static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,	\
 					  void *dummy, void *dest)	\
 {									\
 	*(type *)dest = (type)regs_return_value(regs);			\
@@ -145,150 +103,16 @@ DEFINE_BASIC_FETCH_FUNCS(retval)
 #define fetch_retval_string		NULL
 #define fetch_retval_string_size	NULL
 
-#define DEFINE_FETCH_memory(type)					\
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
-					  void *addr, void *dest)	\
-{									\
-	type retval;							\
-	if (probe_kernel_address(addr, retval))				\
-		*(type *)dest = 0;					\
-	else								\
-		*(type *)dest = retval;					\
-}
-DEFINE_BASIC_FETCH_FUNCS(memory)
-/*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
- * length and relative data location.
- */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
-						      void *addr, void *dest)
-{
-	long ret;
-	int maxlen = get_rloc_len(*(u32 *)dest);
-	u8 *dst = get_rloc_data(dest);
-	u8 *src = addr;
-	mm_segment_t old_fs = get_fs();
-
-	if (!maxlen)
-		return;
-
-	/*
-	 * Try to get string again, since the string can be changed while
-	 * probing.
-	 */
-	set_fs(KERNEL_DS);
-	pagefault_disable();
-
-	do
-		ret = __copy_from_user_inatomic(dst++, src++, 1);
-	while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
-
-	dst[-1] = '\0';
-	pagefault_enable();
-	set_fs(old_fs);
-
-	if (ret < 0) {	/* Failed to fetch string */
-		((u8 *)get_rloc_data(dest))[0] = '\0';
-		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
-	} else {
-		*(u32 *)dest = make_data_rloc(src - (u8 *)addr,
-					      get_rloc_offs(*(u32 *)dest));
-	}
-}
-
-/* Return the length of string -- including null terminal byte */
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
-							void *addr, void *dest)
-{
-	mm_segment_t old_fs;
-	int ret, len = 0;
-	u8 c;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	pagefault_disable();
-
-	do {
-		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
-		len++;
-	} while (c && ret == 0 && len < MAX_STRING_SIZE);
-
-	pagefault_enable();
-	set_fs(old_fs);
-
-	if (ret < 0)	/* Failed to check the length */
-		*(u32 *)dest = 0;
-	else
-		*(u32 *)dest = len;
-}
-
-/* Memory fetching by symbol */
-struct symbol_cache {
-	char		*symbol;
-	long		offset;
-	unsigned long	addr;
-};
-
-static unsigned long update_symbol_cache(struct symbol_cache *sc)
-{
-	sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
-
-	if (sc->addr)
-		sc->addr += sc->offset;
-
-	return sc->addr;
-}
-
-static void free_symbol_cache(struct symbol_cache *sc)
-{
-	kfree(sc->symbol);
-	kfree(sc);
-}
-
-static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
-{
-	struct symbol_cache *sc;
-
-	if (!sym || strlen(sym) == 0)
-		return NULL;
-
-	sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
-	if (!sc)
-		return NULL;
-
-	sc->symbol = kstrdup(sym, GFP_KERNEL);
-	if (!sc->symbol) {
-		kfree(sc);
-		return NULL;
-	}
-	sc->offset = offset;
-	update_symbol_cache(sc);
-
-	return sc;
-}
-
-#define DEFINE_FETCH_symbol(type)					\
-static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
-					  void *data, void *dest)	\
-{									\
-	struct symbol_cache *sc = data;					\
-	if (sc->addr)							\
-		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
-	else								\
-		*(type *)dest = 0;					\
-}
-DEFINE_BASIC_FETCH_FUNCS(symbol)
-DEFINE_FETCH_symbol(string)
-DEFINE_FETCH_symbol(string_size)
-
 /* Dereference memory access function */
 struct deref_fetch_param {
 	struct fetch_param	orig;
 	long			offset;
+	fetch_func_t		fetch;
+	fetch_func_t		fetch_size;
 };
 
 #define DEFINE_FETCH_deref(type)					\
-static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,	\
 					    void *data, void *dest)	\
 {									\
 	struct deref_fetch_param *dprm = data;				\
@@ -296,13 +120,26 @@ static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
 	call_fetch(&dprm->orig, regs, &addr);				\
 	if (addr) {							\
 		addr += dprm->offset;					\
-		fetch_memory_##type(regs, (void *)addr, dest);		\
+		dprm->fetch(regs, (void *)addr, dest);			\
 	} else								\
 		*(type *)dest = 0;					\
 }
 DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
-DEFINE_FETCH_deref(string_size)
+
+__kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
+						   void *data, void *dest)
+{
+	struct deref_fetch_param *dprm = data;
+	unsigned long addr;
+
+	call_fetch(&dprm->orig, regs, &addr);
+	if (addr && dprm->fetch_size) {
+		addr += dprm->offset;
+		dprm->fetch_size(regs, (void *)addr, dest);
+	} else
+		*(string_size *)dest = 0;
+}
 
 static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
 {
@@ -329,7 +166,7 @@ struct bitfield_fetch_param {
 };
 
 #define DEFINE_FETCH_bitfield(type)					\
-static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,	\
 					    void *data, void *dest)	\
 {									\
 	struct bitfield_fetch_param *bprm = data;			\
@@ -374,58 +211,8 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 	kfree(data);
 }
 
-/* Default (unsigned long) fetch type */
-#define __DEFAULT_FETCH_TYPE(t) u##t
-#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
-#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
-#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
-
-#define ASSIGN_FETCH_FUNC(method, type)	\
-	[FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
-
-#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype)	\
-	{.name = _name,				\
-	 .size = _size,					\
-	 .is_signed = sign,				\
-	 .print = PRINT_TYPE_FUNC_NAME(ptype),		\
-	 .fmt = PRINT_TYPE_FMT_NAME(ptype),		\
-	 .fmttype = _fmttype,				\
-	 .fetch = {					\
-ASSIGN_FETCH_FUNC(reg, ftype),				\
-ASSIGN_FETCH_FUNC(stack, ftype),			\
-ASSIGN_FETCH_FUNC(retval, ftype),			\
-ASSIGN_FETCH_FUNC(memory, ftype),			\
-ASSIGN_FETCH_FUNC(symbol, ftype),			\
-ASSIGN_FETCH_FUNC(deref, ftype),			\
-ASSIGN_FETCH_FUNC(bitfield, ftype),			\
-	  }						\
-	}
-
-#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)			\
-	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
-
-#define FETCH_TYPE_STRING	0
-#define FETCH_TYPE_STRSIZE	1
-
-/* Fetch type information table */
-static const struct fetch_type fetch_type_table[] = {
-	/* Special types */
-	[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
-					sizeof(u32), 1, "__data_loc char[]"),
-	[FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
-					string_size, sizeof(u32), 0, "u32"),
-	/* Basic types */
-	ASSIGN_FETCH_TYPE(u8,  u8,  0),
-	ASSIGN_FETCH_TYPE(u16, u16, 0),
-	ASSIGN_FETCH_TYPE(u32, u32, 0),
-	ASSIGN_FETCH_TYPE(u64, u64, 0),
-	ASSIGN_FETCH_TYPE(s8,  u8,  1),
-	ASSIGN_FETCH_TYPE(s16, u16, 1),
-	ASSIGN_FETCH_TYPE(s32, u32, 1),
-	ASSIGN_FETCH_TYPE(s64, u64, 1),
-};
-
-static const struct fetch_type *find_fetch_type(const char *type)
+static const struct fetch_type *find_fetch_type(const char *type,
+						const struct fetch_type *ftbl)
 {
 	int i;
 
@@ -446,44 +233,52 @@ static const struct fetch_type *find_fetch_type(const char *type)
 
 		switch (bs) {
 		case 8:
-			return find_fetch_type("u8");
+			return find_fetch_type("u8", ftbl);
 		case 16:
-			return find_fetch_type("u16");
+			return find_fetch_type("u16", ftbl);
 		case 32:
-			return find_fetch_type("u32");
+			return find_fetch_type("u32", ftbl);
 		case 64:
-			return find_fetch_type("u64");
+			return find_fetch_type("u64", ftbl);
 		default:
 			goto fail;
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
-		if (strcmp(type, fetch_type_table[i].name) == 0)
-			return &fetch_type_table[i];
+	for (i = 0; ftbl[i].name; i++) {
+		if (strcmp(type, ftbl[i].name) == 0)
+			return &ftbl[i];
+	}
 
 fail:
 	return NULL;
 }
 
 /* Special function : only accept unsigned long */
-static __kprobes void fetch_stack_address(struct pt_regs *regs,
-					void *dummy, void *dest)
+static __kprobes void fetch_kernel_stack_address(struct pt_regs *regs,
+						 void *dummy, void *dest)
 {
 	*(unsigned long *)dest = kernel_stack_pointer(regs);
 }
 
+static __kprobes void fetch_user_stack_address(struct pt_regs *regs,
+					       void *dummy, void *dest)
+{
+	*(unsigned long *)dest = user_stack_pointer(regs);
+}
+
 static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
-					fetch_func_t orig_fn)
+					    fetch_func_t orig_fn,
+					    const struct fetch_type *ftbl)
 {
 	int i;
 
-	if (type != &fetch_type_table[FETCH_TYPE_STRING])
+	if (type != &ftbl[FETCH_TYPE_STRING])
 		return NULL;	/* Only string type needs size function */
 
 	for (i = 0; i < FETCH_MTD_END; i++)
 		if (type->fetch[i] == orig_fn)
-			return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+			return ftbl[FETCH_TYPE_STRSIZE].fetch[i];
 
 	WARN_ON(1);	/* This should not happen */
 
@@ -516,7 +311,8 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
 #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
 
 static int parse_probe_vars(char *arg, const struct fetch_type *t,
-			    struct fetch_param *f, bool is_return)
+			    struct fetch_param *f, bool is_return,
+			    bool is_kprobe)
 {
 	int ret = 0;
 	unsigned long param;
@@ -528,13 +324,16 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			ret = -EINVAL;
 	} else if (strncmp(arg, "stack", 5) == 0) {
 		if (arg[5] == '\0') {
-			if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
-				f->fn = fetch_stack_address;
+			if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR))
+				return -EINVAL;
+
+			if (is_kprobe)
+				f->fn = fetch_kernel_stack_address;
 			else
-				ret = -EINVAL;
+				f->fn = fetch_user_stack_address;
 		} else if (isdigit(arg[5])) {
 			ret = kstrtoul(arg + 5, 10, &param);
-			if (ret || param > PARAM_MAX_STACK)
+			if (ret || (is_kprobe && param > PARAM_MAX_STACK))
 				ret = -EINVAL;
 			else {
 				f->fn = t->fetch[FETCH_MTD_stack];
@@ -552,20 +351,18 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 static int parse_probe_arg(char *arg, const struct fetch_type *t,
 		     struct fetch_param *f, bool is_return, bool is_kprobe)
 {
+	const struct fetch_type *ftbl;
 	unsigned long param;
 	long offset;
 	char *tmp;
-	int ret;
-
-	ret = 0;
+	int ret = 0;
 
-	/* Until uprobe_events supports only reg arguments */
-	if (!is_kprobe && arg[0] != '%')
-		return -EINVAL;
+	ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+	BUG_ON(ftbl == NULL);
 
 	switch (arg[0]) {
 	case '$':
-		ret = parse_probe_vars(arg + 1, t, f, is_return);
+		ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
 		break;
 
 	case '%':	/* named register */
@@ -577,7 +374,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
 		}
 		break;
 
-	case '@':	/* memory or symbol */
+	case '@':	/* memory, file-offset or symbol */
 		if (isdigit(arg[1])) {
 			ret = kstrtoul(arg + 1, 0, &param);
 			if (ret)
@@ -585,7 +382,22 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
 
 			f->fn = t->fetch[FETCH_MTD_memory];
 			f->data = (void *)param;
+		} else if (arg[1] == '+') {
+			/* kprobes don't support file offsets */
+			if (is_kprobe)
+				return -EINVAL;
+
+			ret = kstrtol(arg + 2, 0, &offset);
+			if (ret)
+				break;
+
+			f->fn = t->fetch[FETCH_MTD_file_offset];
+			f->data = (void *)offset;
 		} else {
+			/* uprobes don't support symbols */
+			if (!is_kprobe)
+				return -EINVAL;
+
 			ret = traceprobe_split_symbol_offset(arg + 1, &offset);
 			if (ret)
 				break;
@@ -616,7 +428,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
 			struct deref_fetch_param	*dprm;
 			const struct fetch_type		*t2;
 
-			t2 = find_fetch_type(NULL);
+			t2 = find_fetch_type(NULL, ftbl);
 			*tmp = '\0';
 			dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
 
@@ -624,6 +436,9 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
 				return -ENOMEM;
 
 			dprm->offset = offset;
+			dprm->fetch = t->fetch[FETCH_MTD_memory];
+			dprm->fetch_size = get_fetch_size_function(t,
+							dprm->fetch, ftbl);
 			ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
 							is_kprobe);
 			if (ret)
@@ -685,9 +500,13 @@ static int __parse_bitfield_probe_arg(const char *bf,
 int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 		struct probe_arg *parg, bool is_return, bool is_kprobe)
 {
+	const struct fetch_type *ftbl;
 	const char *t;
 	int ret;
 
+	ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+	BUG_ON(ftbl == NULL);
+
 	if (strlen(arg) > MAX_ARGSTR_LEN) {
 		pr_info("Argument is too long.: %s\n",  arg);
 		return -ENOSPC;
@@ -702,7 +521,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 		arg[t - parg->comm] = '\0';
 		t++;
 	}
-	parg->type = find_fetch_type(t);
+	parg->type = find_fetch_type(t, ftbl);
 	if (!parg->type) {
 		pr_info("Unsupported type: %s\n", t);
 		return -EINVAL;
@@ -716,7 +535,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 
 	if (ret >= 0) {
 		parg->fetch_size.fn = get_fetch_size_function(parg->type,
-							      parg->fetch.fn);
+							      parg->fetch.fn,
+							      ftbl);
 		parg->fetch_size.data = parg->fetch.data;
 	}
 
@@ -837,3 +657,65 @@ out:
 
 	return ret;
 }
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
+			   bool is_return)
+{
+	int i;
+	int pos = 0;
+
+	const char *fmt, *arg;
+
+	if (!is_return) {
+		fmt = "(%lx)";
+		arg = "REC->" FIELD_STRING_IP;
+	} else {
+		fmt = "(%lx <- %lx)";
+		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+	}
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+				tp->args[i].name, tp->args[i].type->fmt);
+	}
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		if (strcmp(tp->args[i].type->name, "string") == 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", __get_str(%s)",
+					tp->args[i].name);
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+					tp->args[i].name);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+int set_print_fmt(struct trace_probe *tp, bool is_return)
+{
+	int len;
+	char *print_fmt;
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_print_fmt(tp, NULL, 0, is_return);
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_print_fmt(tp, print_fmt, len + 1, is_return);
+	tp->call.print_fmt = print_fmt;
+
+	return 0;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5c7e09d..b73574a 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -81,6 +81,17 @@
  */
 #define convert_rloc_to_loc(dl, offs)	((u32)(dl) + (offs))
 
+static inline void *get_rloc_data(u32 *dl)
+{
+	return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+	return (u8 *)ent + get_rloc_offs(*dl);
+}
+
 /* Data fetch function type */
 typedef	void (*fetch_func_t)(struct pt_regs *, void *, void *);
 /* Printing function type */
@@ -95,6 +106,7 @@ enum {
 	FETCH_MTD_symbol,
 	FETCH_MTD_deref,
 	FETCH_MTD_bitfield,
+	FETCH_MTD_file_offset,
 	FETCH_MTD_END,
 };
 
@@ -115,6 +127,148 @@ struct fetch_param {
 	void 			*data;
 };
 
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+#define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
+#define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
+
+/* Printing  in basic type function template */
+#define DECLARE_BASIC_PRINT_TYPE_FUNC(type)				\
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,		\
+					 const char *name,		\
+					 void *data, void *ent);	\
+extern const char PRINT_TYPE_FMT_NAME(type)[]
+
+DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(string);
+
+#define FETCH_FUNC_NAME(method, type)	fetch_##method##_##type
+
+/* Declare macro for basic types */
+#define DECLARE_FETCH_FUNC(method, type)				\
+extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, 	\
+					  void *data, void *dest)
+
+#define DECLARE_BASIC_FETCH_FUNCS(method) 	\
+DECLARE_FETCH_FUNC(method, u8);			\
+DECLARE_FETCH_FUNC(method, u16);		\
+DECLARE_FETCH_FUNC(method, u32);		\
+DECLARE_FETCH_FUNC(method, u64)
+
+DECLARE_BASIC_FETCH_FUNCS(reg);
+#define fetch_reg_string			NULL
+#define fetch_reg_string_size			NULL
+
+DECLARE_BASIC_FETCH_FUNCS(retval);
+#define fetch_retval_string			NULL
+#define fetch_retval_string_size		NULL
+
+DECLARE_BASIC_FETCH_FUNCS(symbol);
+DECLARE_FETCH_FUNC(symbol, string);
+DECLARE_FETCH_FUNC(symbol, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(deref);
+DECLARE_FETCH_FUNC(deref, string);
+DECLARE_FETCH_FUNC(deref, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(bitfield);
+#define fetch_bitfield_string			NULL
+#define fetch_bitfield_string_size		NULL
+
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8)		\
+DEFINE_FETCH_##method(u16)		\
+DEFINE_FETCH_##method(u32)		\
+DEFINE_FETCH_##method(u64)
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(method, type)	\
+	[FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype)	\
+	{.name = _name,				\
+	 .size = _size,					\
+	 .is_signed = sign,				\
+	 .print = PRINT_TYPE_FUNC_NAME(ptype),		\
+	 .fmt = PRINT_TYPE_FMT_NAME(ptype),		\
+	 .fmttype = _fmttype,				\
+	 .fetch = {					\
+ASSIGN_FETCH_FUNC(reg, ftype),				\
+ASSIGN_FETCH_FUNC(stack, ftype),			\
+ASSIGN_FETCH_FUNC(retval, ftype),			\
+ASSIGN_FETCH_FUNC(memory, ftype),			\
+ASSIGN_FETCH_FUNC(symbol, ftype),			\
+ASSIGN_FETCH_FUNC(deref, ftype),			\
+ASSIGN_FETCH_FUNC(bitfield, ftype),			\
+ASSIGN_FETCH_FUNC(file_offset, ftype),			\
+	  }						\
+	}
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)			\
+	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define ASSIGN_FETCH_TYPE_END {}
+
+#define FETCH_TYPE_STRING	0
+#define FETCH_TYPE_STRSIZE	1
+
+/*
+ * Fetch type information table.
+ * It's declared as a weak symbol due to conditional compilation.
+ */
+extern __weak const struct fetch_type kprobes_fetch_type_table[];
+extern __weak const struct fetch_type uprobes_fetch_type_table[];
+
+#ifdef CONFIG_KPROBE_EVENT
+struct symbol_cache;
+unsigned long update_symbol_cache(struct symbol_cache *sc);
+void free_symbol_cache(struct symbol_cache *sc);
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+#else
+/* uprobes do not support symbol fetch methods */
+#define fetch_symbol_u8			NULL
+#define fetch_symbol_u16		NULL
+#define fetch_symbol_u32		NULL
+#define fetch_symbol_u64		NULL
+#define fetch_symbol_string		NULL
+#define fetch_symbol_string_size	NULL
+
+struct symbol_cache {
+};
+static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc)
+{
+	return 0;
+}
+
+static inline void __used free_symbol_cache(struct symbol_cache *sc)
+{
+}
+
+static inline struct symbol_cache * __used
+alloc_symbol_cache(const char *sym, long offset)
+{
+	return NULL;
+}
+#endif /* CONFIG_KPROBE_EVENT */
+
 struct probe_arg {
 	struct fetch_param	fetch;
 	struct fetch_param	fetch_size;
@@ -124,6 +278,26 @@ struct probe_arg {
 	const struct fetch_type	*type;	/* Type of this argument */
 };
 
+struct trace_probe {
+	unsigned int			flags;	/* For TP_FLAG_* */
+	struct ftrace_event_class	class;
+	struct ftrace_event_call	call;
+	struct list_head 		files;
+	ssize_t				size;	/* trace entry size */
+	unsigned int			nr_args;
+	struct probe_arg		args[];
+};
+
+static inline bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static inline bool trace_probe_is_registered(struct trace_probe *tp)
+{
+	return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
 static inline __kprobes void call_fetch(struct fetch_param *fprm,
 				 struct pt_regs *regs, void *dest)
 {
@@ -158,3 +332,53 @@ extern ssize_t traceprobe_probes_write(struct file *file,
 		int (*createfn)(int, char**));
 
 extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
+
+/* Sum up total data length for dynamic arraies (strings) */
+static inline __kprobes int
+__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
+{
+	int i, ret = 0;
+	u32 len;
+
+	for (i = 0; i < tp->nr_args; i++)
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			call_fetch(&tp->args[i].fetch_size, regs, &len);
+			ret += len;
+		}
+
+	return ret;
+}
+
+/* Store the value of each argument */
+static inline __kprobes void
+store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
+		 u8 *data, int maxlen)
+{
+	int i;
+	u32 end = tp->size;
+	u32 *dl;	/* Data (relative) location */
+
+	for (i = 0; i < tp->nr_args; i++) {
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			/*
+			 * First, we set the relative location and
+			 * maximum data length to *dl
+			 */
+			dl = (u32 *)(data + tp->args[i].offset);
+			*dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+			/* Then try to fetch string or dynamic array data */
+			call_fetch(&tp->args[i].fetch, regs, dl);
+			/* Reduce maximum length */
+			end += get_rloc_len(*dl);
+			maxlen -= get_rloc_len(*dl);
+			/* Trick here, convert data_rloc to data_loc */
+			*dl = convert_rloc_to_loc(*dl,
+				 ent_size + tp->args[i].offset);
+		} else
+			/* Just fetching data normally */
+			call_fetch(&tp->args[i].fetch, regs,
+				   data + tp->args[i].offset);
+	}
+}
+
+extern int set_print_fmt(struct trace_probe *tp, bool is_return);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e1..6e32635 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <trace/events/sched.h>
 #include "trace.h"
 
@@ -27,6 +28,8 @@ static int			wakeup_cpu;
 static int			wakeup_current_cpu;
 static unsigned			wakeup_prio = -1;
 static int			wakeup_rt;
+static int			wakeup_dl;
+static int			tracing_dl = 0;
 
 static arch_spinlock_t wakeup_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -437,6 +440,7 @@ static void __wakeup_reset(struct trace_array *tr)
 {
 	wakeup_cpu = -1;
 	wakeup_prio = -1;
+	tracing_dl = 0;
 
 	if (wakeup_task)
 		put_task_struct(wakeup_task);
@@ -472,9 +476,17 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	tracing_record_cmdline(p);
 	tracing_record_cmdline(current);
 
-	if ((wakeup_rt && !rt_task(p)) ||
-			p->prio >= wakeup_prio ||
-			p->prio >= current->prio)
+	/*
+	 * Semantic is like this:
+	 *  - wakeup tracer handles all tasks in the system, independently
+	 *    from their scheduling class;
+	 *  - wakeup_rt tracer handles tasks belonging to sched_dl and
+	 *    sched_rt class;
+	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
+	 */
+	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 
 	pc = preempt_count();
@@ -486,7 +498,8 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	arch_spin_lock(&wakeup_lock);
 
 	/* check for races. */
-	if (!tracer_enabled || p->prio >= wakeup_prio)
+	if (!tracer_enabled || tracing_dl ||
+	    (!dl_task(p) && p->prio >= wakeup_prio))
 		goto out_locked;
 
 	/* reset the trace */
@@ -496,6 +509,15 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	wakeup_current_cpu = wakeup_cpu;
 	wakeup_prio = p->prio;
 
+	/*
+	 * Once you start tracing a -deadline task, don't bother tracing
+	 * another task until the first one wakes up.
+	 */
+	if (dl_task(p))
+		tracing_dl = 1;
+	else
+		tracing_dl = 0;
+
 	wakeup_task = p;
 	get_task_struct(wakeup_task);
 
@@ -597,16 +619,25 @@ static int __wakeup_tracer_init(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 0;
 	return __wakeup_tracer_init(tr);
 }
 
 static int wakeup_rt_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 1;
 	return __wakeup_tracer_init(tr);
 }
 
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+	wakeup_dl = 1;
+	wakeup_rt = 0;
+	return __wakeup_tracer_init(tr);
+}
+
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
 	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
@@ -674,6 +705,28 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.use_max_tr	= true,
 };
 
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+	.name		= "wakeup_dl",
+	.init		= wakeup_dl_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.wait_pipe	= poll_wait_pipe,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= wakeup_set_flag,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.use_max_tr	= true,
+};
+
 __init static int init_wakeup_tracer(void)
 {
 	int ret;
@@ -686,6 +739,10 @@ __init static int init_wakeup_tracer(void)
 	if (ret)
 		return ret;
 
+	ret = register_tracer(&wakeup_dl_tracer);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 core_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index a7329b7..e98fca6 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1022,11 +1022,16 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 #ifdef CONFIG_SCHED_TRACER
 static int trace_wakeup_test_thread(void *data)
 {
-	/* Make this a RT thread, doesn't need to be too high */
-	static const struct sched_param param = { .sched_priority = 5 };
+	/* Make this a -deadline thread */
+	static const struct sched_attr attr = {
+		.sched_policy = SCHED_DEADLINE,
+		.sched_runtime = 100000ULL,
+		.sched_deadline = 10000000ULL,
+		.sched_period = 10000000ULL
+	};
 	struct completion *x = data;
 
-	sched_setscheduler(current, SCHED_FIFO, &param);
+	sched_setattr(current, &attr);
 
 	/* Make it know we have a new prio */
 	complete(x);
@@ -1040,8 +1045,8 @@ static int trace_wakeup_test_thread(void *data)
 	/* we are awake, now wait to disappear */
 	while (!kthread_should_stop()) {
 		/*
-		 * This is an RT task, do short sleeps to let
-		 * others run.
+		 * This will likely be the system top priority
+		 * task, do short sleeps to let others run.
 		 */
 		msleep(100);
 	}
@@ -1054,21 +1059,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
 	unsigned long save_max = tracing_max_latency;
 	struct task_struct *p;
-	struct completion isrt;
+	struct completion is_ready;
 	unsigned long count;
 	int ret;
 
-	init_completion(&isrt);
+	init_completion(&is_ready);
 
-	/* create a high prio thread */
-	p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+	/* create a -deadline thread */
+	p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
 	if (IS_ERR(p)) {
 		printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
 		return -1;
 	}
 
-	/* make sure the thread is running at an RT prio */
-	wait_for_completion(&isrt);
+	/* make sure the thread is running at -deadline policy */
+	wait_for_completion(&is_ready);
 
 	/* start the tracing */
 	ret = tracer_init(trace, tr);
@@ -1082,19 +1087,19 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 
 	while (p->on_rq) {
 		/*
-		 * Sleep to make sure the RT thread is asleep too.
+		 * Sleep to make sure the -deadline thread is asleep too.
 		 * On virtual machines we can't rely on timings,
 		 * but we want to make sure this test still works.
 		 */
 		msleep(100);
 	}
 
-	init_completion(&isrt);
+	init_completion(&is_ready);
 
 	wake_up_process(p);
 
 	/* Wait for the task to wake up */
-	wait_for_completion(&isrt);
+	wait_for_completion(&is_ready);
 
 	/* stop the tracing. */
 	tracing_stop();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b20428c..e6be585 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -382,7 +382,7 @@ static const struct file_operations stack_trace_filter_fops = {
 	.open = stack_trace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_filter_lseek,
+	.llseek = tracing_lseek,
 	.release = ftrace_regex_release,
 };
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ea90eb5..759d5e0 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -321,7 +321,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	if (!ftrace_file)
 		return;
 
-	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -343,9 +343,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	if (!filter_check_discard(ftrace_file, entry, buffer, event))
-		trace_current_buffer_unlock_commit(buffer, event,
-						   irq_flags, pc);
+	event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+				    irq_flags, pc);
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -369,7 +368,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	if (!ftrace_file)
 		return;
 
-	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -390,9 +389,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	if (!filter_check_discard(ftrace_file, entry, buffer, event))
-		trace_current_buffer_unlock_commit(buffer, event,
-						   irq_flags, pc);
+	event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+				    irq_flags, pc);
 }
 
 static int reg_event_syscall_enter(struct ftrace_event_file *file,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index b6dcc42..79e52d9 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -51,22 +51,17 @@ struct trace_uprobe_filter {
  */
 struct trace_uprobe {
 	struct list_head		list;
-	struct ftrace_event_class	class;
-	struct ftrace_event_call	call;
 	struct trace_uprobe_filter	filter;
 	struct uprobe_consumer		consumer;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
 	unsigned long			nhit;
-	unsigned int			flags;	/* For TP_FLAG_* */
-	ssize_t				size;	/* trace entry size */
-	unsigned int			nr_args;
-	struct probe_arg		args[];
+	struct trace_probe		tp;
 };
 
-#define SIZEOF_TRACE_UPROBE(n)			\
-	(offsetof(struct trace_uprobe, args) +	\
+#define SIZEOF_TRACE_UPROBE(n)				\
+	(offsetof(struct trace_uprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
 static int register_uprobe_event(struct trace_uprobe *tu);
@@ -75,10 +70,151 @@ static int unregister_uprobe_event(struct trace_uprobe *tu);
 static DEFINE_MUTEX(uprobe_lock);
 static LIST_HEAD(uprobe_list);
 
+struct uprobe_dispatch_data {
+	struct trace_uprobe	*tu;
+	unsigned long		bp_addr;
+};
+
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
 				unsigned long func, struct pt_regs *regs);
 
+#ifdef CONFIG_STACK_GROWSUP
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+	return addr - (n * sizeof(long));
+}
+#else
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+	return addr + (n * sizeof(long));
+}
+#endif
+
+static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long ret;
+	unsigned long addr = user_stack_pointer(regs);
+
+	addr = adjust_stack_addr(addr, n);
+
+	if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret)))
+		return 0;
+
+	return ret;
+}
+
+/*
+ * Uprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type)					\
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+					  void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)get_user_stack_nth(regs,			\
+					      ((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string	NULL
+#define fetch_stack_string_size	NULL
+
+#define DEFINE_FETCH_memory(type)					\
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+						void *addr, void *dest) \
+{									\
+	type retval;							\
+	void __user *vaddr = (void __force __user *) addr;		\
+									\
+	if (copy_from_user(&retval, vaddr, sizeof(type)))		\
+		*(type *)dest = 0;					\
+	else								\
+		*(type *) dest = retval;				\
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+						      void *addr, void *dest)
+{
+	long ret;
+	u32 rloc = *(u32 *)dest;
+	int maxlen  = get_rloc_len(rloc);
+	u8 *dst = get_rloc_data(dest);
+	void __user *src = (void __force __user *) addr;
+
+	if (!maxlen)
+		return;
+
+	ret = strncpy_from_user(dst, src, maxlen);
+
+	if (ret < 0) {	/* Failed to fetch string */
+		((u8 *)get_rloc_data(dest))[0] = '\0';
+		*(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc));
+	} else {
+		*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc));
+	}
+}
+
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+						      void *addr, void *dest)
+{
+	int len;
+	void __user *vaddr = (void __force __user *) addr;
+
+	len = strnlen_user(vaddr, MAX_STRING_SIZE);
+
+	if (len == 0 || len > MAX_STRING_SIZE)  /* Failed to check length */
+		*(u32 *)dest = 0;
+	else
+		*(u32 *)dest = len;
+}
+
+static unsigned long translate_user_vaddr(void *file_offset)
+{
+	unsigned long base_addr;
+	struct uprobe_dispatch_data *udd;
+
+	udd = (void *) current->utask->vaddr;
+
+	base_addr = udd->bp_addr - udd->tu->offset;
+	return base_addr + (unsigned long)file_offset;
+}
+
+#define DEFINE_FETCH_file_offset(type)					\
+static __kprobes void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,\
+					void *offset, void *dest) 	\
+{									\
+	void *vaddr = (void *)translate_user_vaddr(offset);		\
+									\
+	FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest);		\
+}
+DEFINE_BASIC_FETCH_FUNCS(file_offset)
+DEFINE_FETCH_file_offset(string)
+DEFINE_FETCH_file_offset(string_size)
+
+/* Fetch type information table */
+const struct fetch_type uprobes_fetch_type_table[] = {
+	/* Special types */
+	[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+					sizeof(u32), 1, "__data_loc char[]"),
+	[FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+					string_size, sizeof(u32), 0, "u32"),
+	/* Basic types */
+	ASSIGN_FETCH_TYPE(u8,  u8,  0),
+	ASSIGN_FETCH_TYPE(u16, u16, 0),
+	ASSIGN_FETCH_TYPE(u32, u32, 0),
+	ASSIGN_FETCH_TYPE(u64, u64, 0),
+	ASSIGN_FETCH_TYPE(s8,  u8,  1),
+	ASSIGN_FETCH_TYPE(s16, u16, 1),
+	ASSIGN_FETCH_TYPE(s32, u32, 1),
+	ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+	ASSIGN_FETCH_TYPE_END
+};
+
 static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
 {
 	rwlock_init(&filter->rwlock);
@@ -114,13 +250,13 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (!tu)
 		return ERR_PTR(-ENOMEM);
 
-	tu->call.class = &tu->class;
-	tu->call.name = kstrdup(event, GFP_KERNEL);
-	if (!tu->call.name)
+	tu->tp.call.class = &tu->tp.class;
+	tu->tp.call.name = kstrdup(event, GFP_KERNEL);
+	if (!tu->tp.call.name)
 		goto error;
 
-	tu->class.system = kstrdup(group, GFP_KERNEL);
-	if (!tu->class.system)
+	tu->tp.class.system = kstrdup(group, GFP_KERNEL);
+	if (!tu->tp.class.system)
 		goto error;
 
 	INIT_LIST_HEAD(&tu->list);
@@ -128,11 +264,11 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (is_ret)
 		tu->consumer.ret_handler = uretprobe_dispatcher;
 	init_trace_uprobe_filter(&tu->filter);
-	tu->call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
+	tu->tp.call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
 	return tu;
 
 error:
-	kfree(tu->call.name);
+	kfree(tu->tp.call.name);
 	kfree(tu);
 
 	return ERR_PTR(-ENOMEM);
@@ -142,12 +278,12 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 {
 	int i;
 
-	for (i = 0; i < tu->nr_args; i++)
-		traceprobe_free_probe_arg(&tu->args[i]);
+	for (i = 0; i < tu->tp.nr_args; i++)
+		traceprobe_free_probe_arg(&tu->tp.args[i]);
 
 	iput(tu->inode);
-	kfree(tu->call.class->system);
-	kfree(tu->call.name);
+	kfree(tu->tp.call.class->system);
+	kfree(tu->tp.call.name);
 	kfree(tu->filename);
 	kfree(tu);
 }
@@ -157,8 +293,8 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou
 	struct trace_uprobe *tu;
 
 	list_for_each_entry(tu, &uprobe_list, list)
-		if (strcmp(tu->call.name, event) == 0 &&
-		    strcmp(tu->call.class->system, group) == 0)
+		if (strcmp(tu->tp.call.name, event) == 0 &&
+		    strcmp(tu->tp.call.class->system, group) == 0)
 			return tu;
 
 	return NULL;
@@ -181,16 +317,16 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
 /* Register a trace_uprobe and probe_event */
 static int register_trace_uprobe(struct trace_uprobe *tu)
 {
-	struct trace_uprobe *old_tp;
+	struct trace_uprobe *old_tu;
 	int ret;
 
 	mutex_lock(&uprobe_lock);
 
 	/* register as an event */
-	old_tp = find_probe_event(tu->call.name, tu->call.class->system);
-	if (old_tp) {
+	old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system);
+	if (old_tu) {
 		/* delete old event */
-		ret = unregister_trace_uprobe(old_tp);
+		ret = unregister_trace_uprobe(old_tu);
 		if (ret)
 			goto end;
 	}
@@ -211,7 +347,7 @@ end:
 
 /*
  * Argument syntax:
- *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS]
+ *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
  *
  *  - Remove uprobe: -:[GRP/]EVENT
  */
@@ -360,34 +496,36 @@ static int create_trace_uprobe(int argc, char **argv)
 	/* parse arguments */
 	ret = 0;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		struct probe_arg *parg = &tu->tp.args[i];
+
 		/* Increment count for freeing args in error case */
-		tu->nr_args++;
+		tu->tp.nr_args++;
 
 		/* Parse argument name */
 		arg = strchr(argv[i], '=');
 		if (arg) {
 			*arg++ = '\0';
-			tu->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+			parg->name = kstrdup(argv[i], GFP_KERNEL);
 		} else {
 			arg = argv[i];
 			/* If argument name is omitted, set "argN" */
 			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
-			tu->args[i].name = kstrdup(buf, GFP_KERNEL);
+			parg->name = kstrdup(buf, GFP_KERNEL);
 		}
 
-		if (!tu->args[i].name) {
+		if (!parg->name) {
 			pr_info("Failed to allocate argument[%d] name.\n", i);
 			ret = -ENOMEM;
 			goto error;
 		}
 
-		if (!is_good_name(tu->args[i].name)) {
-			pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name);
+		if (!is_good_name(parg->name)) {
+			pr_info("Invalid argument[%d] name: %s\n", i, parg->name);
 			ret = -EINVAL;
 			goto error;
 		}
 
-		if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) {
+		if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) {
 			pr_info("Argument[%d] name '%s' conflicts with "
 				"another field.\n", i, argv[i]);
 			ret = -EINVAL;
@@ -395,7 +533,8 @@ static int create_trace_uprobe(int argc, char **argv)
 		}
 
 		/* Parse fetch argument */
-		ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false);
+		ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg,
+						 is_return, false);
 		if (ret) {
 			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
 			goto error;
@@ -459,11 +598,11 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	char c = is_ret_probe(tu) ? 'r' : 'p';
 	int i;
 
-	seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name);
+	seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name);
 	seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
 
-	for (i = 0; i < tu->nr_args; i++)
-		seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm);
+	for (i = 0; i < tu->tp.nr_args; i++)
+		seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
 
 	seq_printf(m, "\n");
 	return 0;
@@ -509,7 +648,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_uprobe *tu = v;
 
-	seq_printf(m, "  %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit);
+	seq_printf(m, "  %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit);
 	return 0;
 }
 
@@ -533,21 +672,117 @@ static const struct file_operations uprobe_profile_ops = {
 	.release	= seq_release,
 };
 
+struct uprobe_cpu_buffer {
+	struct mutex mutex;
+	void *buf;
+};
+static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
+static int uprobe_buffer_refcnt;
+
+static int uprobe_buffer_init(void)
+{
+	int cpu, err_cpu;
+
+	uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer);
+	if (uprobe_cpu_buffer == NULL)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct page *p = alloc_pages_node(cpu_to_node(cpu),
+						  GFP_KERNEL, 0);
+		if (p == NULL) {
+			err_cpu = cpu;
+			goto err;
+		}
+		per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p);
+		mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex);
+	}
+
+	return 0;
+
+err:
+	for_each_possible_cpu(cpu) {
+		if (cpu == err_cpu)
+			break;
+		free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf);
+	}
+
+	free_percpu(uprobe_cpu_buffer);
+	return -ENOMEM;
+}
+
+static int uprobe_buffer_enable(void)
+{
+	int ret = 0;
+
+	BUG_ON(!mutex_is_locked(&event_mutex));
+
+	if (uprobe_buffer_refcnt++ == 0) {
+		ret = uprobe_buffer_init();
+		if (ret < 0)
+			uprobe_buffer_refcnt--;
+	}
+
+	return ret;
+}
+
+static void uprobe_buffer_disable(void)
+{
+	BUG_ON(!mutex_is_locked(&event_mutex));
+
+	if (--uprobe_buffer_refcnt == 0) {
+		free_percpu(uprobe_cpu_buffer);
+		uprobe_cpu_buffer = NULL;
+	}
+}
+
+static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
+{
+	struct uprobe_cpu_buffer *ucb;
+	int cpu;
+
+	cpu = raw_smp_processor_id();
+	ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu);
+
+	/*
+	 * Use per-cpu buffers for fastest access, but we might migrate
+	 * so the mutex makes sure we have sole access to it.
+	 */
+	mutex_lock(&ucb->mutex);
+
+	return ucb;
+}
+
+static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
+{
+	mutex_unlock(&ucb->mutex);
+}
+
 static void uprobe_trace_print(struct trace_uprobe *tu,
 				unsigned long func, struct pt_regs *regs)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	struct uprobe_cpu_buffer *ucb;
 	void *data;
-	int size, i;
-	struct ftrace_event_call *call = &tu->call;
+	int size, dsize, esize;
+	struct ftrace_event_call *call = &tu->tp.call;
+
+	dsize = __get_data_size(&tu->tp, regs);
+	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
-	size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+	if (WARN_ON_ONCE(!uprobe_cpu_buffer || tu->tp.size + dsize > PAGE_SIZE))
+		return;
+
+	ucb = uprobe_buffer_get();
+	store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
+	size = esize + tu->tp.size + dsize;
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
-						  size + tu->size, 0, 0);
+						  size, 0, 0);
 	if (!event)
-		return;
+		goto out;
 
 	entry = ring_buffer_event_data(event);
 	if (is_ret_probe(tu)) {
@@ -559,11 +794,13 @@ static void uprobe_trace_print(struct trace_uprobe *tu,
 		data = DATAOF_TRACE_ENTRY(entry, false);
 	}
 
-	for (i = 0; i < tu->nr_args; i++)
-		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+	memcpy(data, ucb->buf, tu->tp.size + dsize);
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, 0, 0);
+
+out:
+	uprobe_buffer_put(ucb);
 }
 
 /* uprobe handler */
@@ -591,23 +828,24 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
 	int i;
 
 	entry = (struct uprobe_trace_entry_head *)iter->ent;
-	tu = container_of(event, struct trace_uprobe, call.event);
+	tu = container_of(event, struct trace_uprobe, tp.call.event);
 
 	if (is_ret_probe(tu)) {
-		if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name,
+		if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name,
 					entry->vaddr[1], entry->vaddr[0]))
 			goto partial;
 		data = DATAOF_TRACE_ENTRY(entry, true);
 	} else {
-		if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name,
+		if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name,
 					entry->vaddr[0]))
 			goto partial;
 		data = DATAOF_TRACE_ENTRY(entry, false);
 	}
 
-	for (i = 0; i < tu->nr_args; i++) {
-		if (!tu->args[i].type->print(s, tu->args[i].name,
-					     data + tu->args[i].offset, entry))
+	for (i = 0; i < tu->tp.nr_args; i++) {
+		struct probe_arg *parg = &tu->tp.args[i];
+
+		if (!parg->type->print(s, parg->name, data + parg->offset, entry))
 			goto partial;
 	}
 
@@ -618,11 +856,6 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
-{
-	return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
-}
-
 typedef bool (*filter_func_t)(struct uprobe_consumer *self,
 				enum uprobe_filter_ctx ctx,
 				struct mm_struct *mm);
@@ -632,29 +865,35 @@ probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
 {
 	int ret = 0;
 
-	if (is_trace_uprobe_enabled(tu))
+	if (trace_probe_is_enabled(&tu->tp))
 		return -EINTR;
 
+	ret = uprobe_buffer_enable();
+	if (ret < 0)
+		return ret;
+
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
-	tu->flags |= flag;
+	tu->tp.flags |= flag;
 	tu->consumer.filter = filter;
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
 	if (ret)
-		tu->flags &= ~flag;
+		tu->tp.flags &= ~flag;
 
 	return ret;
 }
 
 static void probe_event_disable(struct trace_uprobe *tu, int flag)
 {
-	if (!is_trace_uprobe_enabled(tu))
+	if (!trace_probe_is_enabled(&tu->tp))
 		return;
 
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
-	tu->flags &= ~flag;
+	tu->tp.flags &= ~flag;
+
+	uprobe_buffer_disable();
 }
 
 static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
@@ -672,12 +911,12 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
 		size = SIZEOF_TRACE_ENTRY(false);
 	}
 	/* Set argument names as fields */
-	for (i = 0; i < tu->nr_args; i++) {
-		ret = trace_define_field(event_call, tu->args[i].type->fmttype,
-					 tu->args[i].name,
-					 size + tu->args[i].offset,
-					 tu->args[i].type->size,
-					 tu->args[i].type->is_signed,
+	for (i = 0; i < tu->tp.nr_args; i++) {
+		struct probe_arg *parg = &tu->tp.args[i];
+
+		ret = trace_define_field(event_call, parg->type->fmttype,
+					 parg->name, size + parg->offset,
+					 parg->type->size, parg->type->is_signed,
 					 FILTER_OTHER);
 
 		if (ret)
@@ -686,59 +925,6 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
 	return 0;
 }
 
-#define LEN_OR_ZERO		(len ? len - pos : 0)
-static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
-{
-	const char *fmt, *arg;
-	int i;
-	int pos = 0;
-
-	if (is_ret_probe(tu)) {
-		fmt = "(%lx <- %lx)";
-		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
-	} else {
-		fmt = "(%lx)";
-		arg = "REC->" FIELD_STRING_IP;
-	}
-
-	/* When len=0, we just calculate the needed length */
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
-	for (i = 0; i < tu->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
-				tu->args[i].name, tu->args[i].type->fmt);
-	}
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
-	for (i = 0; i < tu->nr_args; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
-				tu->args[i].name);
-	}
-
-	return pos;	/* return the length of print_fmt */
-}
-#undef LEN_OR_ZERO
-
-static int set_print_fmt(struct trace_uprobe *tu)
-{
-	char *print_fmt;
-	int len;
-
-	/* First: called with 0 length to calculate the needed length */
-	len = __set_print_fmt(tu, NULL, 0);
-	print_fmt = kmalloc(len + 1, GFP_KERNEL);
-	if (!print_fmt)
-		return -ENOMEM;
-
-	/* Second: actually write the @print_fmt */
-	__set_print_fmt(tu, print_fmt, len + 1);
-	tu->call.print_fmt = print_fmt;
-
-	return 0;
-}
-
 #ifdef CONFIG_PERF_EVENTS
 static bool
 __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
@@ -831,14 +1017,27 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
 static void uprobe_perf_print(struct trace_uprobe *tu,
 				unsigned long func, struct pt_regs *regs)
 {
-	struct ftrace_event_call *call = &tu->call;
+	struct ftrace_event_call *call = &tu->tp.call;
 	struct uprobe_trace_entry_head *entry;
 	struct hlist_head *head;
+	struct uprobe_cpu_buffer *ucb;
 	void *data;
-	int size, rctx, i;
+	int size, dsize, esize;
+	int rctx;
 
-	size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
-	size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+	dsize = __get_data_size(&tu->tp, regs);
+	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+		return;
+
+	size = esize + tu->tp.size + dsize;
+	size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
+		return;
+
+	ucb = uprobe_buffer_get();
+	store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
 
 	preempt_disable();
 	head = this_cpu_ptr(call->perf_events);
@@ -858,12 +1057,18 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
 		data = DATAOF_TRACE_ENTRY(entry, false);
 	}
 
-	for (i = 0; i < tu->nr_args; i++)
-		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+	memcpy(data, ucb->buf, tu->tp.size + dsize);
+
+	if (size - esize > tu->tp.size + dsize) {
+		int len = tu->tp.size + dsize;
+
+		memset(data + len, 0, size - esize - len);
+	}
 
 	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
  out:
 	preempt_enable();
+	uprobe_buffer_put(ucb);
 }
 
 /* uprobe profile handler */
@@ -921,16 +1126,22 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 {
 	struct trace_uprobe *tu;
+	struct uprobe_dispatch_data udd;
 	int ret = 0;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 	tu->nhit++;
 
-	if (tu->flags & TP_FLAG_TRACE)
+	udd.tu = tu;
+	udd.bp_addr = instruction_pointer(regs);
+
+	current->utask->vaddr = (unsigned long) &udd;
+
+	if (tu->tp.flags & TP_FLAG_TRACE)
 		ret |= uprobe_trace_func(tu, regs);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (tu->flags & TP_FLAG_PROFILE)
+	if (tu->tp.flags & TP_FLAG_PROFILE)
 		ret |= uprobe_perf_func(tu, regs);
 #endif
 	return ret;
@@ -940,14 +1151,20 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 				unsigned long func, struct pt_regs *regs)
 {
 	struct trace_uprobe *tu;
+	struct uprobe_dispatch_data udd;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 
-	if (tu->flags & TP_FLAG_TRACE)
+	udd.tu = tu;
+	udd.bp_addr = func;
+
+	current->utask->vaddr = (unsigned long) &udd;
+
+	if (tu->tp.flags & TP_FLAG_TRACE)
 		uretprobe_trace_func(tu, func, regs);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (tu->flags & TP_FLAG_PROFILE)
+	if (tu->tp.flags & TP_FLAG_PROFILE)
 		uretprobe_perf_func(tu, func, regs);
 #endif
 	return 0;
@@ -959,7 +1176,7 @@ static struct trace_event_functions uprobe_funcs = {
 
 static int register_uprobe_event(struct trace_uprobe *tu)
 {
-	struct ftrace_event_call *call = &tu->call;
+	struct ftrace_event_call *call = &tu->tp.call;
 	int ret;
 
 	/* Initialize ftrace_event_call */
@@ -967,7 +1184,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 	call->event.funcs = &uprobe_funcs;
 	call->class->define_fields = uprobe_event_define_fields;
 
-	if (set_print_fmt(tu) < 0)
+	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
 		return -ENOMEM;
 
 	ret = register_ftrace_event(&call->event);
@@ -994,11 +1211,11 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
 	int ret;
 
 	/* tu->event is unregistered in trace_remove_event_call() */
-	ret = trace_remove_event_call(&tu->call);
+	ret = trace_remove_event_call(&tu->tp.call);
 	if (ret)
 		return ret;
-	kfree(tu->call.print_fmt);
-	tu->call.print_fmt = NULL;
+	kfree(tu->tp.call.print_fmt);
+	tu->tp.call.print_fmt = NULL;
 	return 0;
 }
 
diff --git a/kernel/user.c b/kernel/user.c
index a3a0dbf..c006131 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,9 +51,9 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
-#ifdef CONFIG_KEYS_KERBEROS_CACHE
-	.krb_cache_register_sem =
-	__RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	.persistent_keyring_register_sem =
+	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
 #endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b010eac..82ef9f3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4789,6 +4789,7 @@ static int workqueue_cpu_down_callback(struct notifier_block *nfb,
 
 		/* wait for per-cpu unbinding to finish */
 		flush_work(&unbind_work);
+		destroy_work_on_stack(&unbind_work);
 		break;
 	}
 	return NOTIFY_OK;
@@ -4828,6 +4829,7 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
 	schedule_work_on(cpu, &wfc.work);
 	flush_work(&wfc.work);
+	destroy_work_on_stack(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);