14 files changed, 106 insertions, 33 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ff2578ecf17..2b8d7a5db383 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -815,6 +815,10 @@ void __init cpuhp_threads_init(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+#ifndef arch_clear_mm_cpumask_cpu
+#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
+#endif
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
@@ -850,7 +854,7 @@ void clear_tasks_mm_cpumask(int cpu)
 		t = find_lock_task_mm(p);
 		if (!t)
 			continue;
-		cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+		arch_clear_mm_cpumask_cpu(cpu, t->mm);
 		task_unlock(t);
 	}
 	rcu_read_unlock();
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf8b374b892d..e4ca69608f3b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -624,17 +624,19 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
 
 /**
- * irq_create_mapping() - Map a hardware interrupt into linux irq space
+ * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
  * @domain: domain owning this hardware interrupt or NULL for default domain
  * @hwirq: hardware irq number in that domain space
+ * @affinity: irq affinity
  *
  * Only one mapping per hardware interrupt is permitted. Returns a linux
  * irq number.
  * If the sense/trigger is to be specified, set_irq_type() should be called
  * on the number returned from that call.
  */
-unsigned int irq_create_mapping(struct irq_domain *domain,
-				irq_hw_number_t hwirq)
+unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
+				       irq_hw_number_t hwirq,
+				       const struct irq_affinity_desc *affinity)
 {
 	struct device_node *of_node;
 	int virq;
@@ -660,7 +662,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 	}
 
 	/* Allocate a virtual interrupt number */
-	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
+	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node),
+				      affinity);
 	if (virq <= 0) {
 		pr_debug("-> virq allocation failed\n");
 		return 0;
@@ -676,7 +679,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 
 	return virq;
 }
-EXPORT_SYMBOL_GPL(irq_create_mapping);
+EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
 
 /**
  * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index c1ff7fa030ab..1358fa4abfa8 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -52,6 +52,17 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
+static int em_debug_units_show(struct seq_file *s, void *unused)
+{
+	struct em_perf_domain *pd = s->private;
+	char *units = pd->milliwatts ? "milliWatts" : "bogoWatts";
+
+	seq_printf(s, "%s\n", units);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_units);
+
 static void em_debug_create_pd(struct device *dev)
 {
 	struct dentry *d;
@@ -64,6 +75,8 @@ static void em_debug_create_pd(struct device *dev)
 		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
 				    &em_debug_cpus_fops);
 
+	debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops);
+
 	/* Create a sub-directory for each performance state */
 	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
 		em_debug_create_ps(&dev->em_pd->table[i], d);
@@ -130,7 +143,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 
 		/*
 		 * The power returned by active_state() is expected to be
-		 * positive, in milli-watts and to fit into 16 bits.
+		 * positive and to fit into 16 bits.
 		 */
 		if (!power || power > EM_MAX_POWER) {
 			dev_err(dev, "EM: invalid power: %lu\n",
@@ -250,17 +263,24 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  * @cpus	: Pointer to cpumask_t, which in case of a CPU device is
  *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
  *		type of devices this should be set to NULL.
+ * @milliwatts	: Flag indicating that the power values are in milliWatts or
+ *		in some other scale. It must be set properly.
  *
  * Create Energy Model tables for a performance domain using the callbacks
  * defined in cb.
  *
+ * The @milliwatts is important to set with correct value. Some kernel
+ * sub-systems might rely on this flag and check if all devices in the EM are
+ * using the same scale.
+ *
  * If multiple clients register the same performance domain, all but the first
  * registration will be ignored.
  *
  * Return 0 on success
  */
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *cpus)
+				struct em_data_callback *cb, cpumask_t *cpus,
+				bool milliwatts)
 {
 	unsigned long cap, prev_cap = 0;
 	int cpu, ret;
@@ -313,6 +333,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 	if (ret)
 		goto unlock;
 
+	dev->em_pd->milliwatts = milliwatts;
+
 	em_debug_create_pd(dev);
 	dev_info(dev, "EM: created perf domain\n");
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 32391acc806b..d8cae434f9eb 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -224,6 +224,7 @@ EXPORT_SYMBOL_GPL(suspend_set_ops);
 
 /**
  * suspend_valid_only_mem - Generic memory-only valid callback.
+ * @state: Target system sleep state.
  *
  * Platform drivers that implement mem suspend only and only need to check for
  * that in their .valid() callback can use this instead of rolling their own
@@ -335,6 +336,7 @@ static int suspend_test(int level)
 
 /**
  * suspend_prepare - Prepare for entering system sleep state.
+ * @state: Target system sleep state.
  *
  * Common code run for every system sleep state that can be entered (except for
  * hibernation).  Run suspend notifiers, allocate the "suspend" console and
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index fe64a49344bf..bc1e3b5a97bd 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -528,8 +528,8 @@ static int log_store(u32 caller_id, int facility, int level,
 	if (dev_info)
 		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
 
-	/* insert message */
-	if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE))
+	/* A message without a trailing newline can be continued. */
+	if (!(flags & LOG_NEWLINE))
 		prb_commit(&e);
 	else
 		prb_final_commit(&e);
diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
index 6b1525685277..74e25a1704f2 100644
--- a/kernel/printk/printk_ringbuffer.c
+++ b/kernel/printk/printk_ringbuffer.c
@@ -882,8 +882,6 @@ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out)
 	head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */
 
 	do {
-		desc = to_desc(desc_ring, head_id);
-
 		id = DESC_ID(head_id + 1);
 		id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id);
 
diff --git a/kernel/reboot.c b/kernel/reboot.c
index af6f23d8bea1..2a18b76ffc06 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -244,6 +244,8 @@ void migrate_to_reboot_cpu(void)
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
+	if (pm_power_off_prepare)
+		pm_power_off_prepare();
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 97d318b0cd0c..77736058d8e4 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,12 +102,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (!sg_policy->need_freq_update) {
-		if (sg_policy->next_freq == next_freq)
-			return false;
-	} else {
+	if (sg_policy->need_freq_update)
 		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
-	}
+	else if (sg_policy->next_freq == next_freq)
+		return false;
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 24d0ee26377d..c6932b8f4467 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -78,7 +78,7 @@ void __weak arch_cpu_idle_dead(void) { }
 void __weak arch_cpu_idle(void)
 {
 	cpu_idle_force_poll = 1;
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /**
@@ -94,9 +94,35 @@ void __cpuidle default_idle_call(void)
 
 		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
+
+		/*
+		 * arch_cpu_idle() is supposed to enable IRQs, however
+		 * we can't do that because of RCU and tracing.
+		 *
+		 * Trace IRQs enable here, then switch off RCU, and have
+		 * arch_cpu_idle() use raw_local_irq_enable(). Note that
+		 * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+		 * last -- this is very similar to the entry code.
+		 */
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(_THIS_IP_);
 		rcu_idle_enter();
+		lockdep_hardirqs_on(_THIS_IP_);
+
 		arch_cpu_idle();
+
+		/*
+		 * OK, so IRQs are enabled here, but RCU needs them disabled to
+		 * turn itself back on.. funny thing is that disabling IRQs
+		 * will cause tracing, which needs RCU. Jump through hoops to
+		 * make it 'work'.
+		 */
+		raw_local_irq_disable();
+		lockdep_hardirqs_off(_THIS_IP_);
 		rcu_idle_exit();
+		lockdep_hardirqs_on(_THIS_IP_);
+		raw_local_irq_enable();
+
 		start_critical_timings();
 		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a4020c0b4508..e1bf5228fb69 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -202,7 +202,7 @@ config DYNAMIC_FTRACE_WITH_REGS
 
 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	def_bool y
-	depends on DYNAMIC_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_REGS
 	depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 
 config FUNCTION_PROFILER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8185f7240095..9c1bba8cc51b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1629,6 +1629,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 static struct ftrace_ops *
 ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
 static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude);
+static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
 
 static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
@@ -1778,7 +1780,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			 * to it.
 			 */
 			if (ftrace_rec_count(rec) == 1 &&
-			    ftrace_find_tramp_ops_any(rec))
+			    ftrace_find_tramp_ops_any_other(rec, ops))
 				rec->flags |= FTRACE_FL_TRAMP;
 			else
 				rec->flags &= ~FTRACE_FL_TRAMP;
@@ -2245,6 +2247,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec)
 }
 
 static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude)
+{
+	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+
+		if (op == op_exclude || !op->trampoline)
+			continue;
+
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+	} while_for_each_ftrace_op(op);
+
+	return NULL;
+}
+
+static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 			   struct ftrace_ops *op)
 {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index dc83b3fa9fe7..a6268e09160a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3234,14 +3234,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE)) {
-		if (tail != w) {
-			/* before and after may now different, fix it up*/
-			b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-			if (a_ok && b_ok && info->before != info->after)
-				(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
-						      info->before, info->after);
-		}
+		/* before and after may now different, fix it up*/
+		b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		if (a_ok && b_ok && info->before != info->after)
+			(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
+					      info->before, info->after);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
 
@@ -3287,11 +3285,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		ts = rb_time_stamp(cpu_buffer->buffer);
 		barrier();
  /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
-		    info->after < ts) {
+		    info->after < ts &&
+		    rb_time_cmpxchg(&cpu_buffer->write_stamp,
+				    info->after, ts)) {
 			/* Nothing came after this event between C and E */
 			info->delta = ts - info->after;
-			(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
-					      info->after, info->ts);
 			info->ts = ts;
 		} else {
 			/*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 410cfeb16db5..7d53c5bdea3e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3534,7 +3534,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 }
 
 #define STATIC_TEMP_BUF_SIZE	128
-static char static_temp_buf[STATIC_TEMP_BUF_SIZE];
+static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4);
 
 /* Find the next real entry, without updating the iterator itself */
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index c9ad5c6fbaad..d071fc271eef 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -368,7 +368,7 @@ static int start_kthread(struct trace_array *tr)
 	struct task_struct *kthread;
 	int next_cpu;
 
-	if (WARN_ON(hwlat_kthread))
+	if (hwlat_kthread)
 		return 0;
 
 	/* Just pick the first CPU on first iteration */