Merge branch 'linus' into perf/core, to refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 194 insertions, 92 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 09c65640cad6..e85bdfd15fed 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1021,8 +1021,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 	 * for strings that are too long, we should not have created
 	 * any.
 	 */
-	if (unlikely((len == 0) || len > MAX_ARG_STRLEN - 1)) {
-		WARN_ON(1);
+	if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
 		send_sig(SIGKILL, current, 0);
 		return -1;
 	}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9c9c9fab16cc..5644ec5582b9 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -21,6 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
 #include <linux/tick.h>
+#include <linux/irq.h>
 #include <trace/events/power.h>
 
 #include "smpboot.h"
@@ -392,13 +393,19 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	smpboot_park_threads(cpu);
 
 	/*
-	 * So now all preempt/rcu users must observe !cpu_active().
+	 * Prevent irq alloc/free while the dying cpu reorganizes the
+	 * interrupt affinities.
 	 */
+	irq_lock_sparse();
 
+	/*
+	 * So now all preempt/rcu users must observe !cpu_active().
+	 */
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
+		irq_unlock_sparse();
 		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -415,6 +422,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
 	per_cpu(cpu_dead_idle, cpu) = false;
 
+	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
+	irq_unlock_sparse();
+
 	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
@@ -519,6 +529,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen)
 
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
+
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
diff --git a/kernel/fork.c b/kernel/fork.c
index 1bfefc6f96a4..dbd9b8d7b7cc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -287,6 +287,11 @@ static void set_max_threads(unsigned int max_threads_suggested)
 	max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
 }
 
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+/* Initialized by the architecture: */
+int arch_task_struct_size __read_mostly;
+#endif
+
 void __init fork_init(void)
 {
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
@@ -295,7 +300,7 @@ void __init fork_init(void)
 #endif
 	/* create a slab on which task_structs can be allocated */
 	task_struct_cachep =
-		kmem_cache_create("task_struct", sizeof(struct task_struct),
+		kmem_cache_create("task_struct", arch_task_struct_size,
 			ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
 #endif
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4834ee828c41..61008b8433ab 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -76,12 +76,8 @@ extern void unmask_threaded_irq(struct irq_desc *desc);
 
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
-extern void irq_lock_sparse(void);
-extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
-static inline void irq_lock_sparse(void) { }
-static inline void irq_unlock_sparse(void) { }
 #endif
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 9065107f083e..7a5237a1bce5 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -75,13 +75,21 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/*
-			 * If the interrupt has a parent irq and runs
-			 * in the thread context of the parent irq,
-			 * retrigger the parent.
+			 * If the interrupt is running in the thread
+			 * context of the parent irq we need to be
+			 * careful, because we cannot trigger it
+			 * directly.
 			 */
-			if (desc->parent_irq &&
-			    irq_settings_is_nested_thread(desc))
+			if (irq_settings_is_nested_thread(desc)) {
+				/*
+				 * If the parent_irq is valid, we
+				 * retrigger the parent, otherwise we
+				 * do nothing.
+				 */
+				if (!desc->parent_irq)
+					return;
 				irq = desc->parent_irq;
+			}
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
 			tasklet_schedule(&resend_tasklet);
diff --git a/kernel/module.c b/kernel/module.c
index 3e0e19763d24..4d2b82e610e2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3557,6 +3557,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	mod_tree_remove(mod);
 	wake_up_all(&module_wq);
 	/* Wait for RCU-sched synchronizing before releasing mod->list. */
 	synchronize_sched();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 65c8f3ebdc3c..d113c3ba8bc4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3683,7 +3683,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
-	empty = list_empty(&cfs_rq->throttled_list);
+	empty = list_empty(&cfs_b->throttled_cfs_rq);
 
 	/*
 	 * Add to the _head_ of the list, so that an already-started
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 08ccc3da3ca0..50eb107f1198 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -120,19 +120,25 @@ static int __clockevents_switch_state(struct clock_event_device *dev,
 		/* The clockevent device is getting replaced. Shut it down. */
 
 	case CLOCK_EVT_STATE_SHUTDOWN:
-		return dev->set_state_shutdown(dev);
+		if (dev->set_state_shutdown)
+			return dev->set_state_shutdown(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_PERIODIC:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
 			return -ENOSYS;
-		return dev->set_state_periodic(dev);
+		if (dev->set_state_periodic)
+			return dev->set_state_periodic(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
 			return -ENOSYS;
-		return dev->set_state_oneshot(dev);
+		if (dev->set_state_oneshot)
+			return dev->set_state_oneshot(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
 		/* Core internal bug */
@@ -471,18 +477,6 @@ static int clockevents_sanity_check(struct clock_event_device *dev)
 	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
-	/* New state-specific callbacks */
-	if (!dev->set_state_shutdown)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
-	    !dev->set_state_periodic)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-	    !dev->set_state_oneshot)
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index d39f32cdd1b5..f6aae7977824 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -159,7 +159,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -221,13 +221,14 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 			 * If we kept the cpu in the broadcast mask,
 			 * tell the caller to leave the per cpu device
 			 * in shutdown state. The periodic interrupt
-			 * is delivered by the broadcast device.
+			 * is delivered by the broadcast device, if
+			 * the broadcast device exists and is not
+			 * hrtimer based.
 			 */
-			ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+				ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
 			break;
 		default:
-			/* Nothing to do */
-			ret = 0;
 			break;
 		}
 	}
@@ -265,8 +266,22 @@ static bool tick_do_broadcast(struct cpumask *mask)
 	 * Check, if the current cpu is in the mask
 	 */
 	if (cpumask_test_cpu(cpu, mask)) {
+		struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
 		cpumask_clear_cpu(cpu, mask);
-		local = true;
+		/*
+		 * We only run the local handler, if the broadcast
+		 * device is not hrtimer based. Otherwise we run into
+		 * a hrtimer recursion.
+		 *
+		 * local timer_interrupt()
+		 *   local_handler()
+		 *     expire_hrtimers()
+		 *       bc_handler()
+		 *         local_handler()
+		 *	     expire_hrtimers()
+		 */
+		local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER);
 	}
 
 	if (!cpumask_empty(mask)) {
@@ -301,6 +316,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+
+	/* Handle spurious interrupts gracefully */
+	if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) {
+		raw_spin_unlock(&tick_broadcast_lock);
+		return;
+	}
+
 	bc_local = tick_do_periodic_broadcast();
 
 	if (clockevent_state_oneshot(dev)) {
@@ -359,8 +381,16 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
-			if (tick_broadcast_device.mode ==
-			    TICKDEV_MODE_PERIODIC)
+			/*
+			 * Only shutdown the cpu local device, if:
+			 *
+			 * - the broadcast device exists
+			 * - the broadcast device is not a hrtimer based one
+			 * - the broadcast device is in periodic mode to
+			 *   avoid a hickup during switch to oneshot mode
+			 */
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) &&
+			    tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
 		}
 		break;
@@ -379,14 +409,16 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 		break;
 	}
 
-	if (cpumask_empty(tick_broadcast_mask)) {
-		if (!bc_stopped)
-			clockevents_shutdown(bc);
-	} else if (bc_stopped) {
-		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-			tick_broadcast_start_periodic(bc);
-		else
-			tick_broadcast_setup_oneshot(bc);
+	if (bc) {
+		if (cpumask_empty(tick_broadcast_mask)) {
+			if (!bc_stopped)
+				clockevents_shutdown(bc);
+		} else if (bc_stopped) {
+			if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+				tick_broadcast_start_periodic(bc);
+			else
+				tick_broadcast_setup_oneshot(bc);
+		}
 	}
 	raw_spin_unlock(&tick_broadcast_lock);
 }
@@ -662,71 +694,82 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-/**
- * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
- * @state:	The target state (enter/exit)
- *
- * The system enters/leaves a state, where affected devices might stop
- * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
- *
- * Called with interrupts disabled, so clockevents_lock is not
- * required here because the local clock event device cannot go away
- * under us.
- */
-int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
 	struct clock_event_device *bc, *dev;
-	struct tick_device *td;
 	int cpu, ret = 0;
 	ktime_t now;
 
 	/*
-	 * Periodic mode does not care about the enter/exit of power
-	 * states
+	 * If there is no broadcast device, tell the caller not to go
+	 * into deep idle.
 	 */
-	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return 0;
+	if (!tick_broadcast_device.evtdev)
+		return -EBUSY;
 
-	/*
-	 * We are called with preemtion disabled from the depth of the
-	 * idle code, so we can't be moved away.
-	 */
-	td = this_cpu_ptr(&tick_cpu_device);
-	dev = td->evtdev;
-
-	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	dev = this_cpu_ptr(&tick_cpu_device)->evtdev;
 
 	raw_spin_lock(&tick_broadcast_lock);
 	bc = tick_broadcast_device.evtdev;
 	cpu = smp_processor_id();
 
 	if (state == TICK_BROADCAST_ENTER) {
+		/*
+		 * If the current CPU owns the hrtimer broadcast
+		 * mechanism, it cannot go deep idle and we do not add
+		 * the CPU to the broadcast mask. We don't have to go
+		 * through the EXIT path as the local timer is not
+		 * shutdown.
+		 */
+		ret = broadcast_needs_cpu(bc, cpu);
+		if (ret)
+			goto out;
+
+		/*
+		 * If the broadcast device is in periodic mode, we
+		 * return.
+		 */
+		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+			/* If it is a hrtimer based broadcast, return busy */
+			if (bc->features & CLOCK_EVT_FEAT_HRTIMER)
+				ret = -EBUSY;
+			goto out;
+		}
+
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+
+			/* Conditionally shut down the local timer. */
 			broadcast_shutdown_local(bc, dev);
+
 			/*
 			 * We only reprogram the broadcast timer if we
 			 * did not mark ourself in the force mask and
 			 * if the cpu local event is earlier than the
 			 * broadcast event. If the current CPU is in
 			 * the force mask, then we are going to be
-			 * woken by the IPI right away.
+			 * woken by the IPI right away; we return
+			 * busy, so the CPU does not try to go deep
+			 * idle.
 			 */
-			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
-			    dev->next_event.tv64 < bc->next_event.tv64)
+			if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) {
+				ret = -EBUSY;
+			} else if (dev->next_event.tv64 < bc->next_event.tv64) {
 				tick_broadcast_set_event(bc, cpu, dev->next_event);
+				/*
+				 * In case of hrtimer broadcasts the
+				 * programming might have moved the
+				 * timer to this cpu. If yes, remove
+				 * us from the broadcast mask and
+				 * return busy.
+				 */
+				ret = broadcast_needs_cpu(bc, cpu);
+				if (ret) {
+					cpumask_clear_cpu(cpu,
+						tick_broadcast_oneshot_mask);
+				}
+			}
 		}
-		/*
-		 * If the current CPU owns the hrtimer broadcast
-		 * mechanism, it cannot go deep idle and we remove the
-		 * CPU from the broadcast mask. We don't have to go
-		 * through the EXIT path as the local timer is not
-		 * shutdown.
-		 */
-		ret = broadcast_needs_cpu(bc, cpu);
-		if (ret)
-			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
@@ -796,7 +839,6 @@ out:
 	raw_spin_unlock(&tick_broadcast_lock);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
 /*
  * Reset the one shot broadcast for a cpu
@@ -938,6 +980,16 @@ bool tick_broadcast_oneshot_available(void)
 	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
 }
 
+#else
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER))
+		return -EBUSY;
+
+	return 0;
+}
 #endif
 
 void __init tick_broadcast_init(void)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 76446cb5dfe1..f8bf47571dda 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -343,6 +343,28 @@ out_bc:
 	tick_install_broadcast_device(newdev);
 }
 
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
+ */
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
+	if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	return __tick_broadcast_oneshot_control(state);
+}
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Transfer the do_timer job away from a dying cpu.
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 42fdf4958bcc..a4a8d4e9baa1 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -71,4 +71,14 @@ extern void tick_cancel_sched_timer(int cpu);
 static inline void tick_cancel_sched_timer(int cpu) { }
 #endif
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
+#else
+static inline int
+__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return -EBUSY;
+}
+#endif
+
 #endif
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f060716b02ae..74bde81601a9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -444,6 +444,7 @@ enum {
 
 	TRACE_CONTROL_BIT,
 
+	TRACE_BRANCH_BIT,
 /*
  * Abuse of the trace_recursion.
  * As we need a way to maintain state if we are tracing the function
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index a87b43f49eb4..e2e12ad3186f 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -36,9 +36,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	struct trace_branch *entry;
 	struct ring_buffer *buffer;
 	unsigned long flags;
-	int cpu, pc;
+	int pc;
 	const char *p;
 
+	if (current->trace_recursion & TRACE_BRANCH_BIT)
+		return;
+
 	/*
 	 * I would love to save just the ftrace_likely_data pointer, but
 	 * this code can also be used by modules. Ugly things can happen
@@ -49,10 +52,10 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	if (unlikely(!tr))
 		return;
 
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
-	if (atomic_inc_return(&data->disabled) != 1)
+	raw_local_irq_save(flags);
+	current->trace_recursion |= TRACE_BRANCH_BIT;
+	data = this_cpu_ptr(tr->trace_buffer.data);
+	if (atomic_read(&data->disabled))
 		goto out;
 
 	pc = preempt_count();
@@ -81,8 +84,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 		__buffer_unlock_commit(buffer, event);
 
  out:
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+	current->trace_recursion &= ~TRACE_BRANCH_BIT;
+	raw_local_irq_restore(flags);
 }
 
 static inline