Merge tag 'v3.10.24' into HEAD

This is the 3.10.24 stable release

Change-Id: Ibd2734f93d44385ab86867272a1359158635133b

21 files changed, 304 insertions, 175 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 7b0e23a740ce..7ddfd8a00a2a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -613,7 +613,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
 	int rc = 0;
 	uid_t uid = from_kuid(&init_user_ns, current_uid());
 
-	if (!audit_enabled) {
+	if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
 		*ab = NULL;
 		return rc;
 	}
@@ -659,6 +659,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	switch (msg_type) {
 	case AUDIT_GET:
+		status_set.mask		 = 0;
 		status_set.enabled	 = audit_enabled;
 		status_set.failure	 = audit_failure;
 		status_set.pid		 = audit_pid;
@@ -670,7 +671,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				 &status_set, sizeof(status_set));
 		break;
 	case AUDIT_SET:
-		if (nlh->nlmsg_len < sizeof(struct audit_status))
+		if (nlmsg_len(nlh) < sizeof(struct audit_status))
 			return -EINVAL;
 		status_get   = (struct audit_status *)data;
 		if (status_get->mask & AUDIT_STATUS_ENABLED) {
@@ -832,7 +833,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
-		memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
 		if ((s.enabled != 0 && s.enabled != 1) ||
 		    (s.log_passwd != 0 && s.log_passwd != 1))
 			return -EINVAL;
@@ -1536,6 +1537,26 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
 		}
 	}
 
+	/* log the audit_names record type */
+	audit_log_format(ab, " nametype=");
+	switch(n->type) {
+	case AUDIT_TYPE_NORMAL:
+		audit_log_format(ab, "NORMAL");
+		break;
+	case AUDIT_TYPE_PARENT:
+		audit_log_format(ab, "PARENT");
+		break;
+	case AUDIT_TYPE_CHILD_DELETE:
+		audit_log_format(ab, "DELETE");
+		break;
+	case AUDIT_TYPE_CHILD_CREATE:
+		audit_log_format(ab, "CREATE");
+		break;
+	default:
+		audit_log_format(ab, "UNKNOWN");
+		break;
+	}
+
 	audit_log_fcaps(ab, n);
 	audit_log_end(ab);
 }
diff --git a/kernel/audit.h b/kernel/audit.h
index 1c95131ef760..123c9b7c3979 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -85,6 +85,7 @@ struct audit_names {
 
 	struct filename		*name;
 	int			name_len;	/* number of chars to log */
+	bool			hidden;		/* don't log this record */
 	bool			name_put;	/* call __putname()? */
 
 	unsigned long		ino;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3c8a601324a2..9845cb32b60a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1399,8 +1399,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	}
 
 	i = 0;
-	list_for_each_entry(n, &context->names_list, list)
+	list_for_each_entry(n, &context->names_list, list) {
+		if (n->hidden)
+			continue;
 		audit_log_name(context, n, NULL, i++, &call_panic);
+	}
 
 	/* Send end of event record to help user space know we are finished */
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
@@ -1769,14 +1772,15 @@ void audit_putname(struct filename *name)
  * __audit_inode - store the inode and device from a lookup
  * @name: name being audited
  * @dentry: dentry being audited
- * @parent: does this dentry represent the parent?
+ * @flags: attributes for this particular entry
  */
 void __audit_inode(struct filename *name, const struct dentry *dentry,
-		   unsigned int parent)
+		   unsigned int flags)
 {
 	struct audit_context *context = current->audit_context;
 	const struct inode *inode = dentry->d_inode;
 	struct audit_names *n;
+	bool parent = flags & AUDIT_INODE_PARENT;
 
 	if (!context->in_syscall)
 		return;
@@ -1831,6 +1835,8 @@ out:
 	if (parent) {
 		n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_PARENT;
+		if (flags & AUDIT_INODE_HIDDEN)
+			n->hidden = true;
 	} else {
 		n->name_len = AUDIT_NAME_FULL;
 		n->type = AUDIT_TYPE_NORMAL;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 6111ef77cfdf..05b36e7b9e6b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -92,6 +92,14 @@ static DEFINE_MUTEX(cgroup_mutex);
 static DEFINE_MUTEX(cgroup_root_mutex);
 
 /*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions.  Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_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
@@ -873,7 +881,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
 {
 	struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
 
-	schedule_work(&cgrp->free_work);
+	queue_work(cgroup_destroy_wq, &cgrp->free_work);
 }
 
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -2011,7 +2019,6 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
 		BUG_ON(retval != 0);
 		i++;
-
 next:
 		if (!threadgroup)
 			break;
@@ -4714,6 +4721,22 @@ out:
 	return err;
 }
 
+static int __init cgroup_wq_init(void)
+{
+	/*
+	 * There isn't much point in executing destruction path in
+	 * parallel.  Good chunk is serialized with cgroup_mutex anyway.
+	 * Use 1 for @max_active.
+	 *
+	 * We would prefer to do this in cgroup_init() above, but that
+	 * is called before init_workqueues(): so leave this until after.
+	 */
+	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+	BUG_ON(!cgroup_destroy_wq);
+	return 0;
+}
+core_initcall(cgroup_wq_init);
+
 /*
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
@@ -5024,7 +5047,7 @@ void __css_put(struct cgroup_subsys_state *css)
 
 	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
 	if (v == 0)
-		schedule_work(&css->dput_work);
+		queue_work(cgroup_destroy_wq, &css->dput_work);
 }
 EXPORT_SYMBOL_GPL(__css_put);
 
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a0bcb5..c261409500e4 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!need_resched())
+	while (!tif_need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
 			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
-				current_clr_polling();
-				if (!need_resched()) {
+				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
 					arch_cpu_idle();
@@ -103,7 +102,7 @@ static void cpu_idle_loop(void)
 				} else {
 					local_irq_enable();
 				}
-				current_set_polling();
+				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
 		}
@@ -129,7 +128,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	current_set_polling();
+	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6948e9476b42..d313870dcd02 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -984,8 +984,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop)
+	if (need_loop) {
+		local_irq_disable();
 		write_seqcount_begin(&tsk->mems_allowed_seq);
+	}
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -993,8 +995,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop)
+	if (need_loop) {
 		write_seqcount_end(&tsk->mems_allowed_seq);
+		local_irq_enable();
+	}
 
 	task_unlock(tsk);
 }
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index cd55144270b5..9c2ddfbf4525 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -87,10 +87,31 @@ again:
 		goto out;
 
 	/*
-	 * Publish the known good head. Rely on the full barrier implied
-	 * by atomic_dec_and_test() order the rb->head read and this
-	 * write.
+	 * Since the mmap() consumer (userspace) can run on a different CPU:
+	 *
+	 *   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
+	 *
+	 * 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.
+	 *
+	 * OTOH, 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
+	 * an RMB is sufficient since it separates two READs.
+	 *
+	 * See perf_output_begin().
 	 */
+	smp_wmb();
 	rb->user_page->data_head = head;
 
 	/*
@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle,
 		 * Userspace could choose to issue a mb() before updating the
 		 * tail pointer. So that all reads will be completed before the
 		 * write is issued.
+		 *
+		 * See perf_output_put_handle().
 		 */
 		tail = ACCESS_ONCE(rb->user_page->data_tail);
-		smp_rmb();
+		smp_mb();
 		offset = head = local_read(&rb->head);
 		head += size;
 		if (unlikely(!perf_output_space(rb, tail, offset, head)))
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 92d49eddd7da..1e78f577df3d 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -53,7 +53,7 @@ static void resume_irqs(bool want_early)
 		bool is_early = desc->action &&
 			desc->action->flags & IRQF_EARLY_RESUME;
 
-		if (is_early != want_early)
+		if (!is_early && want_early)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0de28576807d..91c04f16e79c 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1398,7 +1398,11 @@ int hibernate_preallocate_memory(void)
 	 * highmem and non-highmem zones separately.
 	 */
 	pages_highmem = preallocate_image_highmem(highmem / 2);
-	alloc = (count - max_size) - pages_highmem;
+	alloc = count - max_size;
+	if (alloc > pages_highmem)
+		alloc -= pages_highmem;
+	else
+		alloc = 0;
 	pages = preallocate_image_memory(alloc, avail_normal);
 	if (pages < alloc) {
 		/* We have exhausted non-highmem pages, try highmem. */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 335a7ae697f5..afadcf7b4a22 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -257,7 +257,8 @@ ok:
 	if (task->mm)
 		dumpable = get_dumpable(task->mm);
 	rcu_read_lock();
-	if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+	if (dumpable != SUID_DUMP_USER &&
+	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 682d3479cf19..0f69cecc93cd 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -480,7 +480,7 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
 
 	if (!alarmtimer_get_rtcdev())
-		return -ENOTSUPP;
+		return -EINVAL;
 
 	return hrtimer_get_res(baseid, tp);
 }
@@ -497,7 +497,7 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
 	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
 
 	if (!alarmtimer_get_rtcdev())
-		return -ENOTSUPP;
+		return -EINVAL;
 
 	*tp = ktime_to_timespec(base->gettime());
 	return 0;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c6d6400ee137..9df0e3b19f09 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,7 +15,6 @@
 #include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/notifier.h>
 #include <linux/smp.h>
 
 #include "tick-internal.h"
@@ -23,36 +22,67 @@
 /* The registered clock event devices */
 static LIST_HEAD(clockevent_devices);
 static LIST_HEAD(clockevents_released);
-
-/* Notification for clock events */
-static RAW_NOTIFIER_HEAD(clockevents_chain);
-
 /* Protection for the above */
 static DEFINE_RAW_SPINLOCK(clockevents_lock);
 
-/**
- * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
- * @latch:	value to convert
- * @evt:	pointer to clock event device descriptor
- *
- * Math helper, returns latch value converted to nanoseconds (bound checked)
- */
-u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+			bool ismax)
 {
 	u64 clc = (u64) latch << evt->shift;
+	u64 rnd;
 
 	if (unlikely(!evt->mult)) {
 		evt->mult = 1;
 		WARN_ON(1);
 	}
+	rnd = (u64) evt->mult - 1;
+
+	/*
+	 * Upper bound sanity check. If the backwards conversion is
+	 * not equal latch, we know that the above shift overflowed.
+	 */
+	if ((clc >> evt->shift) != (u64)latch)
+		clc = ~0ULL;
+
+	/*
+	 * Scaled math oddities:
+	 *
+	 * For mult <= (1 << shift) we can safely add mult - 1 to
+	 * prevent integer rounding loss. So the backwards conversion
+	 * from nsec to device ticks will be correct.
+	 *
+	 * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+	 * need to be careful. Adding mult - 1 will result in a value
+	 * which when converted back to device ticks can be larger
+	 * than latch by up to (mult - 1) >> shift. For the min_delta
+	 * calculation we still want to apply this in order to stay
+	 * above the minimum device ticks limit. For the upper limit
+	 * we would end up with a latch value larger than the upper
+	 * limit of the device, so we omit the add to stay below the
+	 * device upper boundary.
+	 *
+	 * Also omit the add if it would overflow the u64 boundary.
+	 */
+	if ((~0ULL - clc > rnd) &&
+	    (!ismax || evt->mult <= (1U << evt->shift)))
+		clc += rnd;
 
 	do_div(clc, evt->mult);
-	if (clc < 1000)
-		clc = 1000;
-	if (clc > KTIME_MAX)
-		clc = KTIME_MAX;
 
-	return clc;
+	/* Deltas less than 1usec are pointless noise */
+	return clc > 1000 ? clc : 1000;
+}
+
+/**
+ * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:	value to convert
+ * @evt:	pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+{
+	return cev_delta2ns(latch, evt, false);
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
@@ -232,30 +262,6 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
 }
 
-/**
- * clockevents_register_notifier - register a clock events change listener
- */
-int clockevents_register_notifier(struct notifier_block *nb)
-{
-	unsigned long flags;
-	int ret;
-
-	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-
-	return ret;
-}
-
-/*
- * Notify about a clock event change. Called with clockevents_lock
- * held.
- */
-static void clockevents_do_notify(unsigned long reason, void *dev)
-{
-	raw_notifier_call_chain(&clockevents_chain, reason, dev);
-}
-
 /*
  * Called after a notify add to make devices available which were
  * released from the notifier call.
@@ -269,7 +275,7 @@ static void clockevents_notify_released(void)
 				 struct clock_event_device, list);
 		list_del(&dev->list);
 		list_add(&dev->list, &clockevent_devices);
-		clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+		tick_check_new_device(dev);
 	}
 }
 
@@ -290,7 +296,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
-	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	tick_check_new_device(dev);
 	clockevents_notify_released();
 
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
@@ -317,8 +323,8 @@ void clockevents_config(struct clock_event_device *dev, u32 freq)
 		sec = 600;
 
 	clockevents_calc_mult_shift(dev, freq, sec);
-	dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
-	dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+	dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
+	dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
 }
 
 /**
@@ -386,6 +392,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		module_put(old->owner);
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
@@ -433,7 +440,7 @@ void clockevents_notify(unsigned long reason, void *arg)
 	int cpu;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	clockevents_do_notify(reason, arg);
+	tick_notify(reason, arg);
 
 	switch (reason) {
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index bb2215174f05..af8d1d4f3d55 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -475,6 +475,7 @@ static void sync_cmos_clock(struct work_struct *work)
 	 * called as close as possible to 500 ms before the new second starts.
 	 * This code is run on a timer.  If the clock is set, that timer
 	 * may not expire at the correct time.  Thus, we adjust...
+	 * We want the clock to be within a couple of ticks from the target.
 	 */
 	if (!ntp_synced()) {
 		/*
@@ -485,7 +486,7 @@ static void sync_cmos_clock(struct work_struct *work)
 	}
 
 	getnstimeofday(&now);
-	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
 		struct timespec adjust = now;
 
 		fail = -ENODEV;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 297b90b5277e..52d4827cf2d4 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -19,6 +19,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/module.h>
 
 #include "tick-internal.h"
 
@@ -65,17 +66,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
 /*
  * Check, if the device can be utilized as broadcast device:
  */
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+					struct clock_event_device *newdev)
+{
+	if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return false;
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+	    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return false;
+
+	return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
 {
 	struct clock_event_device *cur = tick_broadcast_device.evtdev;
 
-	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
-	    (tick_broadcast_device.evtdev &&
-	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
-	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	if (!tick_check_broadcast_device(cur, dev))
+		return;
+
+	if (!try_module_get(dev->owner))
+		return;
 
-	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	clockevents_exchange_device(cur, dev);
 	if (cur)
 		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
@@ -91,7 +109,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	 */
 	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_clock_notify();
-	return 1;
 }
 
 /*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 7ce5e5a4a4c5..086216c433fa 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -206,14 +207,50 @@ static void tick_setup_device(struct tick_device *td,
 		tick_setup_oneshot(newdev, handler, next_event);
 }
 
+static bool tick_check_percpu(struct clock_event_device *curdev,
+			      struct clock_event_device *newdev, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		return false;
+	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+		return true;
+	/* Check if irq affinity can be set */
+	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+		return false;
+	/* Prefer an existing cpu local device */
+	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+		return false;
+	return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+				 struct clock_event_device *newdev)
+{
+	/* Prefer oneshot capable device */
+	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return false;
+		if (tick_oneshot_mode_active())
+			return false;
+	}
+
+	/*
+	 * Use the higher rated one, but prefer a CPU local device with a lower
+	 * rating than a non-CPU local device
+	 */
+	return !curdev ||
+		newdev->rating > curdev->rating ||
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
 /*
  * Check, if the new registered device should be used.
  */
-static int tick_check_new_device(struct clock_event_device *newdev)
+void tick_check_new_device(struct clock_event_device *newdev)
 {
 	struct clock_event_device *curdev;
 	struct tick_device *td;
-	int cpu, ret = NOTIFY_OK;
+	int cpu;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&tick_device_lock, flags);
@@ -226,40 +263,15 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	curdev = td->evtdev;
 
 	/* cpu local device ? */
-	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
-
-		/*
-		 * If the cpu affinity of the device interrupt can not
-		 * be set, ignore it.
-		 */
-		if (!irq_can_set_affinity(newdev->irq))
-			goto out_bc;
+	if (!tick_check_percpu(curdev, newdev, cpu))
+		goto out_bc;
 
-		/*
-		 * If we have a cpu local device already, do not replace it
-		 * by a non cpu local device
-		 */
-		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
-			goto out_bc;
-	}
+	/* Preference decision */
+	if (!tick_check_preferred(curdev, newdev))
+		goto out_bc;
 
-	/*
-	 * If we have an active device, then check the rating and the oneshot
-	 * feature.
-	 */
-	if (curdev) {
-		/*
-		 * Prefer one shot capable devices !
-		 */
-		if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-		    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
-			goto out_bc;
-		/*
-		 * Check the rating
-		 */
-		if (curdev->rating >= newdev->rating)
-			goto out_bc;
-	}
+	if (!try_module_get(newdev->owner))
+		return;
 
 	/*
 	 * Replace the eventually existing device by the new
@@ -276,18 +288,14 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 		tick_oneshot_notify();
 
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-	return NOTIFY_STOP;
+	return;
 
 out_bc:
 	/*
 	 * Can the new device be used as a broadcast device ?
 	 */
-	if (tick_check_broadcast_device(newdev))
-		ret = NOTIFY_STOP;
-
+	tick_install_broadcast_device(newdev);
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
-	return ret;
 }
 
 /*
@@ -361,17 +369,10 @@ static void tick_resume(void)
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-/*
- * Notification about clock event devices
- */
-static int tick_notify(struct notifier_block *nb, unsigned long reason,
-			       void *dev)
+void tick_notify(unsigned long reason, void *dev)
 {
 	switch (reason) {
 
-	case CLOCK_EVT_NOTIFY_ADD:
-		return tick_check_new_device(dev);
-
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
@@ -405,21 +406,12 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
 	default:
 		break;
 	}
-
-	return NOTIFY_OK;
 }
 
-static struct notifier_block tick_notifier = {
-	.notifier_call = tick_notify,
-};
-
 /**
  * tick_init - initialize the tick control
- *
- * Register the notifier with the clockevents framework
  */
 void __init tick_init(void)
 {
-	clockevents_register_notifier(&tick_notifier);
 	tick_broadcast_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f0299eae4602..60742fe6f63d 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -18,6 +18,8 @@ extern int tick_do_timer_cpu __read_mostly;
 
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_notify(unsigned long reason, void *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
 
 extern void clockevents_shutdown(struct clock_event_device *dev);
 
@@ -90,7 +92,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; }
  */
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
 extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
 extern void tick_shutdown_broadcast(unsigned int *cpup);
@@ -102,9 +104,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
 
 #else /* !BROADCAST */
 
-static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 {
-	return 0;
 }
 
 static inline int tick_is_broadcast_device(struct clock_event_device *dev)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 303d1a96dc26..14e2703d32e2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1328,7 +1328,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	tk->xtime_nsec -= remainder;
 	tk->xtime_nsec += 1ULL << tk->shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-
+	tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f23449d0650e..331c102177a6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -367,9 +367,6 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
-
 	if (FTRACE_WARN_ON(ops == &global_ops))
 		return -EINVAL;
 
@@ -417,9 +414,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
 
-	if (ftrace_disabled)
-		return -ENODEV;
-
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
@@ -2048,10 +2042,15 @@ static void ftrace_startup_enable(int command)
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	bool hash_enable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
+	ret = __register_ftrace_function(ops);
+	if (ret)
+		return ret;
+
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
@@ -2073,12 +2072,17 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	return 0;
 }
 
-static void ftrace_shutdown(struct ftrace_ops *ops, int command)
+static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
 	bool hash_disable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
+
+	ret = __unregister_ftrace_function(ops);
+	if (ret)
+		return ret;
 
 	ftrace_start_up--;
 	/*
@@ -2113,9 +2117,10 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command)
 	}
 
 	if (!command || !ftrace_enabled)
-		return;
+		return 0;
 
 	ftrace_run_update_code(command);
+	return 0;
 }
 
 static void ftrace_startup_sysctl(void)
@@ -3020,16 +3025,13 @@ static void __enable_ftrace_function_probe(void)
 	if (i == FTRACE_FUNC_HASHSIZE)
 		return;
 
-	ret = __register_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ret = ftrace_startup(&trace_probe_ops, 0);
+	ret = ftrace_startup(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 1;
 }
 
 static void __disable_ftrace_function_probe(void)
 {
-	int ret;
 	int i;
 
 	if (!ftrace_probe_registered)
@@ -3042,9 +3044,7 @@ static void __disable_ftrace_function_probe(void)
 	}
 
 	/* no more funcs left */
-	ret = __unregister_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ftrace_shutdown(&trace_probe_ops, 0);
+	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
 }
@@ -4241,12 +4241,15 @@ core_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)			\
-	({						\
-		(ops)->flags |= FTRACE_OPS_FL_ENABLED;	\
-		0;					\
+# define ftrace_startup(ops, command)					\
+	({								\
+		int ___ret = __register_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags |= FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
 	})
-# define ftrace_shutdown(ops, command)	do { } while (0)
+# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
 
@@ -4646,9 +4649,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_lock);
 
-	ret = __register_ftrace_function(ops);
-	if (!ret)
-		ret = ftrace_startup(ops, 0);
+	ret = ftrace_startup(ops, 0);
 
 	mutex_unlock(&ftrace_lock);
 
@@ -4667,9 +4668,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 	int ret;
 
 	mutex_lock(&ftrace_lock);
-	ret = __unregister_ftrace_function(ops);
-	if (!ret)
-		ftrace_shutdown(ops, 0);
+	ret = ftrace_shutdown(ops, 0);
 	mutex_unlock(&ftrace_lock);
 
 	return ret;
@@ -4863,6 +4862,13 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
 	return NOTIFY_DONE;
 }
 
+/* Just a place holder for function graph */
+static struct ftrace_ops fgraph_ops __read_mostly = {
+	.func		= ftrace_stub,
+	.flags		= FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
+				FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -4889,7 +4895,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_return = retfunc;
 	ftrace_graph_entry = entryfunc;
 
-	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -4906,7 +4912,7 @@ 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_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+	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/trace.c b/kernel/trace/trace.c
index c431a16f1866..3abfc7b31afb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -827,9 +827,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	if (isspace(ch)) {
 		parser->buffer[parser->idx] = 0;
 		parser->cont = false;
-	} else {
+	} else if (parser->idx < parser->size - 1) {
 		parser->cont = true;
 		parser->buffer[parser->idx++] = ch;
+	} else {
+		ret = -EINVAL;
+		goto out;
 	}
 
 	*ppos += read;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 84b1e045faba..8354dc81ae64 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -26,7 +26,7 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 {
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event) &&
-	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/* No tracing, just counting, so no obvious leak */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e52d002d3893..68086a34b8ef 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -295,6 +295,9 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
 /* I: attributes used when instantiating standard unbound pools on demand */
 static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
 struct workqueue_struct *system_wq __read_mostly;
 EXPORT_SYMBOL(system_wq);
 struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -4059,7 +4062,7 @@ out_unlock:
 static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 {
 	bool highpri = wq->flags & WQ_HIGHPRI;
-	int cpu;
+	int cpu, ret;
 
 	if (!(wq->flags & WQ_UNBOUND)) {
 		wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4079,6 +4082,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 			mutex_unlock(&wq->mutex);
 		}
 		return 0;
+	} else if (wq->flags & __WQ_ORDERED) {
+		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+		/* there should only be single pwq for ordering guarantee */
+		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+		     "ordering guarantee broken for workqueue %s\n", wq->name);
+		return ret;
 	} else {
 		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
@@ -4990,13 +5000,23 @@ static int __init init_workqueues(void)
 		}
 	}
 
-	/* create default unbound wq attrs */
+	/* create default unbound and ordered wq attrs */
 	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
 		struct workqueue_attrs *attrs;
 
 		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
 		attrs->nice = std_nice[i];
 		unbound_std_wq_attrs[i] = attrs;
+
+		/*
+		 * An ordered wq should have only one pwq as ordering is
+		 * guaranteed by max_active which is enforced by pwqs.
+		 * Turn off NUMA so that dfl_pwq is used for all nodes.
+		 */
+		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		attrs->nice = std_nice[i];
+		attrs->no_numa = true;
+		ordered_wq_attrs[i] = attrs;
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);