Merge branch 'linux-3.10.33' into dev-kernel-3.10

Bug 1456092

Change-Id: I3021247ec68a3c2dddd9e98cde13d70a45191d53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

19 files changed, 312 insertions, 59 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 7ddfd8a00a2a..6def25f1b351 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -103,7 +103,8 @@ static int	audit_rate_limit;
 
 /* Number of outstanding audit_buffers allowed. */
 static int	audit_backlog_limit = 64;
-static int	audit_backlog_wait_time = 60 * HZ;
+#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static int	audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
 static int	audit_backlog_wait_overflow = 0;
 
 /* The identity of the user shutting down the audit system. */
@@ -1135,6 +1136,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 		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");
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e76e4959908c..f8eb2b154bdb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7421,14 +7421,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7452,11 +7452,11 @@ static void perf_event_exit_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/fork.c b/kernel/fork.c
index f9a15a265444..0aa1bb5c8d6e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -560,6 +560,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	clear_tlb_flush_pending(mm);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa197517..aa6a8aadb911 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 c3a1a55a5214..221a58fc62f7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -288,7 +288,7 @@ again:
 		put_page(page);
 		/* serialize against __split_huge_page_splitting() */
 		local_irq_disable();
-		if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+		if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
 			page_head = compound_head(page);
 			/*
 			 * page_head is valid pointer but we must pin
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302d6cfd..8ab8e9390297 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 59f7b55ba745..1f8d9382dbac 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
 
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
 /* Location of the reserved area for the crash kernel */
 struct resource crashk_res = {
 	.name  = "Crash kernel",
@@ -1678,6 +1681,7 @@ int kernel_kexec(void)
 	} else
 #endif
 	{
+		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 825447720620..960acc06a818 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1499,7 +1499,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	unsigned long flags;
 	int cpu, success = 0;
 
-	smp_wmb();
+	/*
+	 * If we are going to wake up a thread waiting for CONDITION we
+	 * need to ensure that CONDITION=1 done by the caller can not be
+	 * reordered with p->state check below. This pairs with mb() in
+	 * set_current_state() the waiting thread does.
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	if (!(p->state & state))
 		goto out;
@@ -3007,6 +3013,12 @@ need_resched:
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	/*
+	 * Make sure that signal_pending_state()->signal_pending() below
+	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+	 * done by the caller to avoid the race with signal_wake_up().
+	 */
+	smp_mb__before_spinlock();
 	raw_spin_lock_irq(&rq->lock);
 
 	switch_count = &prev->nivcsw;
@@ -7876,7 +7888,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	runtime_enabled = quota != RUNTIME_INF;
 	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
-	account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled);
+	/*
+	 * If we need to toggle cfs_bandwidth_used, off->on must occur
+	 * before making related changes, and on->off must occur afterwards
+	 */
+	if (runtime_enabled && !runtime_was_enabled)
+		cfs_bandwidth_usage_inc();
 	raw_spin_lock_irq(&cfs_b->lock);
 	cfs_b->period = ns_to_ktime(period);
 	cfs_b->quota = quota;
@@ -7902,6 +7919,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 			unthrottle_cfs_rq(cfs_rq);
 		raw_spin_unlock_irq(&rq->lock);
 	}
+	if (runtime_was_enabled && !runtime_enabled)
+		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 068ad55aa641..b38d50312e25 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -224,6 +224,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
 			atomic_read(&cfs_rq->tg->runnable_avg));
 #endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+			cfs_rq->tg->cfs_bandwidth.timer_active);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
+			cfs_rq->throttled);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
+			cfs_rq->throttle_count);
+#endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 009a62bb859d..305ef886219e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -936,6 +936,13 @@ void task_numa_work(struct callback_head *work)
 		if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 			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);
@@ -2022,13 +2029,14 @@ static inline bool cfs_bandwidth_used(void)
 	return static_key_false(&__cfs_bandwidth_used);
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled)
+void cfs_bandwidth_usage_inc(void)
+{
+	static_key_slow_inc(&__cfs_bandwidth_used);
+}
+
+void cfs_bandwidth_usage_dec(void)
 {
-	/* only need to count groups transitioning between enabled/!enabled */
-	if (enabled && !was_enabled)
-		static_key_slow_inc(&__cfs_bandwidth_used);
-	else if (!enabled && was_enabled)
-		static_key_slow_dec(&__cfs_bandwidth_used);
+	static_key_slow_dec(&__cfs_bandwidth_used);
 }
 #else /* HAVE_JUMP_LABEL */
 static bool cfs_bandwidth_used(void)
@@ -2036,7 +2044,8 @@ static bool cfs_bandwidth_used(void)
 	return true;
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
+void cfs_bandwidth_usage_inc(void) {}
+void cfs_bandwidth_usage_dec(void) {}
 #endif /* HAVE_JUMP_LABEL */
 
 /*
@@ -2288,6 +2297,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled_clock = rq->clock;
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (!cfs_b->timer_active)
+		__start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -2399,6 +2410,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (idle)
 		goto out_unlock;
 
+	/*
+	 * if we have relooped after returning idle once, we need to update our
+	 * status as actually running, so that other cpus doing
+	 * __start_cfs_bandwidth will stop trying to cancel us.
+	 */
+	cfs_b->timer_active = 1;
+
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -2459,7 +2477,13 @@ static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
 /* how long we wait to gather additional slack before distributing */
 static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
 
-/* are we near the end of the current quota period? */
+/*
+ * Are we near the end of the current quota period?
+ *
+ * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
+ * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * migrate_hrtimers, base is never cleared, so we are fine.
+ */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 {
 	struct hrtimer *refresh_timer = &cfs_b->period_timer;
@@ -2535,10 +2559,12 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	u64 expires;
 
 	/* confirm we're still not at a refresh boundary */
-	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
+	raw_spin_lock(&cfs_b->lock);
+	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
+		raw_spin_unlock(&cfs_b->lock);
 		return;
+	}
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
 		runtime = cfs_b->runtime;
 		cfs_b->runtime = 0;
@@ -2663,11 +2689,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	 * (timer_active==0 becomes visible before the hrtimer call-back
 	 * terminates).  In either case we ensure that it's re-programmed
 	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+		/* bounce the lock to allow do_sched_cfs_period_timer to run */
 		raw_spin_unlock(&cfs_b->lock);
-		/* ensure cfs_b->lock is available while we wait */
-		hrtimer_cancel(&cfs_b->period_timer);
-
+		cpu_relax();
 		raw_spin_lock(&cfs_b->lock);
 		/* if someone else restarted the timer then we're done */
 		if (cfs_b->timer_active)
@@ -6065,7 +6091,8 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	update_load_set(&se->load, 0);
+	/* guarantee group entities always have weight */
+	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 111539a27757..8f4243e73423 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -924,6 +924,13 @@ 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);
 }
@@ -933,6 +940,13 @@ 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);
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0fc275c70d7d..aa23bd2294e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1354,7 +1354,8 @@ 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 account_cfs_bandwidth_used(int enabled, int was_enabled);
+extern void cfs_bandwidth_usage_inc(void);
+extern void cfs_bandwidth_usage_dec(void);
 
 #ifdef CONFIG_NO_HZ_COMMON
 enum rq_nohz_flag_bits {
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba456fb..a6a5bf53e86d 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/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 52d4827cf2d4..f681da32a2ff 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -745,6 +745,7 @@ 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/timekeeping.c b/kernel/time/timekeeping.c
index 14e2703d32e2..220774cf4aec 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -72,7 +72,7 @@ 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)
@@ -590,7 +590,7 @@ 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));
 }
 
 /**
@@ -605,6 +605,7 @@ 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, false, true);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	clock_was_set();
@@ -1007,6 +1008,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
+
+	timekeeping_update(tk, false, true);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
@@ -1236,9 +1239,10 @@ out_adjust:
  * It also calls into the NTP code to handle leapsecond processing.
  *
  */
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1260,9 +1264,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
+			clock_set = 1;
 		}
 	}
+	return clock_set;
 }
 
 /**
@@ -1275,7 +1280,8 @@ static inline void 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;
@@ -1289,7 +1295,7 @@ 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;
@@ -1347,6 +1353,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1381,7 +1388,8 @@ 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--;
 	}
@@ -1399,7 +1407,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	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 */
@@ -1419,6 +1427,10 @@ static void update_wall_time(void)
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_set)
+		/* have to call outside the timekeeper_seq */
+		clock_was_set_delayed();
+
 }
 
 /**
@@ -1678,11 +1690,14 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
-		clock_was_set_delayed();
+		timekeeping_update(tk, false, true);
 	}
 	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;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 331c102177a6..4b93b8412252 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;
 }
 
@@ -428,16 +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.
-			 */
-			synchronize_sched();
-			control_ops_free(ops);
-		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -447,13 +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.
-	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		synchronize_sched();
-
 	return 0;
 }
 
@@ -750,7 +803,7 @@ 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;
@@ -1952,8 +2005,14 @@ void ftrace_modify_all_code(int command)
 	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
+	if (command & FTRACE_UPDATE_TRACE_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();
@@ -2116,10 +2175,41 @@ 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;
 }
 
@@ -4728,6 +4818,7 @@ 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)
@@ -4869,6 +4960,30 @@ 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)
 {
@@ -4893,7 +5008,16 @@ 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);
 
@@ -4912,6 +5036,7 @@ 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 e444ff88f0a4..fd12cc56371f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2396,6 +2396,13 @@ __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,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3abfc7b31afb..4c41e22f162b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -424,6 +424,9 @@ 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);
@@ -464,6 +467,9 @@ 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,
@@ -5969,6 +5975,8 @@ 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/workqueue.c b/kernel/workqueue.c
index 68086a34b8ef..db7a6ac7c0a8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1823,6 +1823,12 @@ static void destroy_worker(struct worker *worker)
 	if (worker->flags & WORKER_IDLE)
 		pool->nr_idle--;
 
+	/*
+	 * Once WORKER_DIE is set, the kworker may destroy itself at any
+	 * point.  Pin to ensure the task stays until we're done with it.
+	 */
+	get_task_struct(worker->task);
+
 	list_del_init(&worker->entry);
 	worker->flags |= WORKER_DIE;
 
@@ -1831,6 +1837,7 @@ static void destroy_worker(struct worker *worker)
 	spin_unlock_irq(&pool->lock);
 
 	kthread_stop(worker->task);
+	put_task_struct(worker->task);
 	kfree(worker);
 
 	spin_lock_irq(&pool->lock);