Merge back earlier 'pm-sleep' material.

19 files changed, 105 insertions, 75 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
index b3097bde4e9..790d83c7d16 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -5,3 +5,4 @@ config_data.h
 config_data.gz
 timeconst.h
 hz.bc
+x509_certificate_list
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d724e7757cd..72348dc192c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5680,11 +5680,6 @@ static void swevent_hlist_put(struct perf_event *event)
 {
 	int cpu;
 
-	if (event->cpu != -1) {
-		swevent_hlist_put_cpu(event, event->cpu);
-		return;
-	}
-
 	for_each_possible_cpu(cpu)
 		swevent_hlist_put_cpu(event, cpu);
 }
@@ -5718,9 +5713,6 @@ static int swevent_hlist_get(struct perf_event *event)
 	int err;
 	int cpu, failed_cpu;
 
-	if (event->cpu != -1)
-		return swevent_hlist_get_cpu(event, event->cpu);
-
 	get_online_cpus();
 	for_each_possible_cpu(cpu) {
 		err = swevent_hlist_get_cpu(event, cpu);
diff --git a/kernel/futex.c b/kernel/futex.c
index 80ba086f021..f6ff0191ecf 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -251,6 +251,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 		return -EINVAL;
 	address -= key->both.offset;
 
+	if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
+		return -EFAULT;
+
 	/*
 	 * PROCESS_PRIVATE futexes are fast.
 	 * As the mm cannot disappear under us and the 'key' only needs
@@ -259,8 +262,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	 *        but access_ok() should be faster than find_vma()
 	 */
 	if (!fshared) {
-		if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
-			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
 		get_futex_key_refs(key);
@@ -288,7 +289,7 @@ 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/pm.c b/kernel/irq/pm.c
index cb228bf2176..abcd6ca86cb 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@ 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/kexec.c b/kernel/kexec.c
index 490afc03627..d0d8fca5406 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",
@@ -1675,6 +1678,7 @@ 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/power/console.c b/kernel/power/console.c
index 463aa673675..eacb8bd8cab 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/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6abb03dff5c..08a76523243 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1632,7 +1632,7 @@ module_param(rcu_idle_gp_delay, int, 0644);
 static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
 module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
-extern int tick_nohz_enabled;
+extern int tick_nohz_active;
 
 /*
  * Try to advance callbacks for all flavors of RCU on the current CPU, but
@@ -1729,7 +1729,7 @@ static void rcu_prepare_for_idle(int cpu)
 	int tne;
 
 	/* Handle nohz enablement switches conservatively. */
-	tne = ACCESS_ONCE(tick_nohz_enabled);
+	tne = ACCESS_ONCE(tick_nohz_active);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
 		if (rcu_cpu_has_callbacks(cpu, NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1808606ee5..e85cda20ab2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2660,6 +2660,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
 	} while (need_resched());
 }
 EXPORT_SYMBOL(preempt_schedule);
+#endif /* CONFIG_PREEMPT */
 
 /*
  * this is the entry point to schedule() from kernel preemption
@@ -2693,8 +2694,6 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	exception_exit(prev_state);
 }
 
-#endif /* CONFIG_PREEMPT */
-
 int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
@@ -4762,7 +4761,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
 		/*
-		 * If we dont want to free the old_rt yet then
+		 * If we dont want to free the old_rd yet then
 		 * set old_rd to NULL to skip the freeing later
 		 * in this function:
 		 */
@@ -4910,8 +4909,9 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
-		rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent);
+		sd = sd->parent; /* sd_busy */
 	}
+	rcu_assign_pointer(per_cpu(sd_busy, cpu), sd);
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e8b652ebe02..fd773ade1a3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5379,10 +5379,31 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		 */
 
 		for_each_cpu(cpu, sched_group_cpus(sdg)) {
-			struct sched_group *sg = cpu_rq(cpu)->sd->groups;
+			struct sched_group_power *sgp;
+			struct rq *rq = cpu_rq(cpu);
 
-			power_orig += sg->sgp->power_orig;
-			power += sg->sgp->power;
+			/*
+			 * build_sched_domains() -> init_sched_groups_power()
+			 * gets here before we've attached the domains to the
+			 * runqueues.
+			 *
+			 * Use power_of(), which is set irrespective of domains
+			 * in update_cpu_power().
+			 *
+			 * This avoids power/power_orig from being 0 and
+			 * causing divide-by-zero issues on boot.
+			 *
+			 * Runtime updates will correct power_orig.
+			 */
+			if (unlikely(!rq->sd)) {
+				power_orig += power_of(cpu);
+				power += power_of(cpu);
+				continue;
+			}
+
+			sgp = rq->sd->groups->sgp;
+			power_orig += sgp->power_orig;
+			power += sgp->power;
 		}
 	} else  {
 		/*
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
index 4aef390671c..3e9868d4753 100644
--- a/kernel/system_certificates.S
+++ b/kernel/system_certificates.S
@@ -3,8 +3,18 @@
 
 	__INITRODATA
 
+	.align 8
 	.globl VMLINUX_SYMBOL(system_certificate_list)
 VMLINUX_SYMBOL(system_certificate_list):
+__cert_list_start:
 	.incbin "kernel/x509_certificate_list"
-	.globl VMLINUX_SYMBOL(system_certificate_list_end)
-VMLINUX_SYMBOL(system_certificate_list_end):
+__cert_list_end:
+
+	.align 8
+	.globl VMLINUX_SYMBOL(system_certificate_list_size)
+VMLINUX_SYMBOL(system_certificate_list_size):
+#ifdef CONFIG_64BIT
+	.quad __cert_list_end - __cert_list_start
+#else
+	.long __cert_list_end - __cert_list_start
+#endif
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
index 564dd93430a..52ebc70263f 100644
--- a/kernel/system_keyring.c
+++ b/kernel/system_keyring.c
@@ -22,7 +22,7 @@ struct key *system_trusted_keyring;
 EXPORT_SYMBOL_GPL(system_trusted_keyring);
 
 extern __initconst const u8 system_certificate_list[];
-extern __initconst const u8 system_certificate_list_end[];
+extern __initconst const unsigned long system_certificate_list_size;
 
 /*
  * Load the compiled-in keys
@@ -60,8 +60,8 @@ static __init int load_system_certificate_list(void)
 
 	pr_notice("Loading compiled-in X.509 certificates\n");
 
-	end = system_certificate_list_end;
 	p = system_certificate_list;
+	end = p + system_certificate_list_size;
 	while (p < end) {
 		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
 		 * than 256 bytes in size.
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0..162b03ab0ad 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,6 +33,21 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ *    timekeeping lock all at once. Only the CPU which is assigned to do the
+ *    update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ *    at it will take over and keep the time keeping alive.  The handover
+ *    procedure also covers cpu hotplug.
+ */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3612fc77f83..ea20f7d1ac2 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -361,8 +361,8 @@ void __init tick_nohz_init(void)
 /*
  * NO HZ enabled ?
  */
-int tick_nohz_enabled __read_mostly  = 1;
-
+static int tick_nohz_enabled __read_mostly  = 1;
+int tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
@@ -465,7 +465,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t now, idle;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return -1;
 
 	now = ktime_get();
@@ -506,7 +506,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t now, iowait;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return -1;
 
 	now = ktime_get();
@@ -711,8 +711,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 	}
 
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+		ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
 		return false;
+	}
 
 	if (need_resched())
 		return false;
@@ -799,11 +801,6 @@ void tick_nohz_idle_enter(void)
 	local_irq_disable();
 
 	ts = &__get_cpu_var(tick_cpu_sched);
-	/*
-	 * set ts->inidle unconditionally. even if the system did not
-	 * switch to nohz mode the cpu frequency governers rely on the
-	 * update of the idle time accounting in tick_nohz_start_idle().
-	 */
 	ts->inidle = 1;
 	__tick_nohz_idle_enter(ts);
 
@@ -973,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void)
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t next;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return;
 
 	local_irq_disable();
@@ -981,7 +978,7 @@ static void tick_nohz_switch_to_nohz(void)
 		local_irq_enable();
 		return;
 	}
-
+	tick_nohz_active = 1;
 	ts->nohz_mode = NOHZ_MODE_LOWRES;
 
 	/*
@@ -1139,8 +1136,10 @@ void tick_setup_sched_timer(void)
 	}
 
 #ifdef CONFIG_NO_HZ_COMMON
-	if (tick_nohz_enabled)
+	if (tick_nohz_enabled) {
 		ts->nohz_mode = NOHZ_MODE_HIGHRES;
+		tick_nohz_active = 1;
+	}
 #endif
 }
 #endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3abf53418b6..87b4f00284c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1347,7 +1347,7 @@ 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/timer.c b/kernel/timer.c
index 6582b82fa96..accfd241b9e 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1518,9 +1518,8 @@ static int init_timers_cpu(int cpu)
 			/*
 			 * The APs use this path later in boot
 			 */
-			base = kmalloc_node(sizeof(*base),
-						GFP_KERNEL | __GFP_ZERO,
-						cpu_to_node(cpu));
+			base = kzalloc_node(sizeof(*base), GFP_KERNEL,
+					    cpu_to_node(cpu));
 			if (!base)
 				return -ENOMEM;
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 78e27e3b52a..e854f420e03 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,12 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	if (tp_event->perf_perm) {
+		int ret = tp_event->perf_perm(tp_event, p_event);
+		if (ret)
+			return ret;
+	}
+
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event) &&
 	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
@@ -173,7 +179,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 int perf_trace_init(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event;
-	int event_id = p_event->attr.config;
+	u64 event_id = p_event->attr.config;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f919a2e21bf..a11800ae96d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2314,6 +2314,9 @@ int event_trace_del_tracer(struct trace_array *tr)
 	/* Disable any running events */
 	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
 
+	/* Access to events are within rcu_read_lock_sched() */
+	synchronize_sched();
+
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
 	debugfs_remove_recursive(tr->event_dir);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e4b6d11bdf7..ea90eb5f6f1 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -431,11 +431,6 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_enter)
 		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
-	/*
-	 * Callers expect the event to be completely disabled on
-	 * return, so wait for current handlers to finish.
-	 */
-	synchronize_sched();
 }
 
 static int reg_event_syscall_exit(struct ftrace_event_file *file,
@@ -474,11 +469,6 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_exit)
 		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
-	/*
-	 * Callers expect the event to be completely disabled on
-	 * return, so wait for current handlers to finish.
-	 */
-	synchronize_sched();
 }
 
 static int __init init_syscall_trace(struct ftrace_event_call *call)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c66912be990..b010eac595d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2851,19 +2851,6 @@ already_gone:
 	return false;
 }
 
-static bool __flush_work(struct work_struct *work)
-{
-	struct wq_barrier barr;
-
-	if (start_flush_work(work, &barr)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-		return true;
-	} else {
-		return false;
-	}
-}
-
 /**
  * flush_work - wait for a work to finish executing the last queueing instance
  * @work: the work to flush
@@ -2877,10 +2864,18 @@ static bool __flush_work(struct work_struct *work)
  */
 bool flush_work(struct work_struct *work)
 {
+	struct wq_barrier barr;
+
 	lock_map_acquire(&work->lockdep_map);
 	lock_map_release(&work->lockdep_map);
 
-	return __flush_work(work);
+	if (start_flush_work(work, &barr)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else {
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -4832,14 +4827,7 @@ 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);
-
-	/*
-	 * The work item is on-stack and can't lead to deadlock through
-	 * flushing.  Use __flush_work() to avoid spurious lockdep warnings
-	 * when work_on_cpu()s are nested.
-	 */
-	__flush_work(&wfc.work);
-
+	flush_work(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);