Merge tag 'v4.1.11' into toradex_vf_4.1-next

This is the 4.1.11 stable release

13 files changed, 216 insertions, 83 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e8a5491be756..4d65b66ae60d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1319,7 +1319,7 @@ static int cgroup_show_options(struct seq_file *seq,
 
 	for_each_subsys(ss, ssid)
 		if (root->subsys_mask & (1 << ssid))
-			seq_printf(seq, ",%s", ss->name);
+			seq_show_option(seq, ss->name, NULL);
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)
@@ -1327,13 +1327,14 @@ static int cgroup_show_options(struct seq_file *seq,
 
 	spin_lock(&release_agent_path_lock);
 	if (strlen(root->release_agent_path))
-		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+		seq_show_option(seq, "release_agent",
+				root->release_agent_path);
 	spin_unlock(&release_agent_path_lock);
 
 	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
 		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
-		seq_printf(seq, ",name=%s", root->name);
+		seq_show_option(seq, "name", root->name);
 	return 0;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ee14e3a35a29..f0acff0f66c9 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1223,7 +1223,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->mems_allowed as a temp variable */
-	update_nodemasks_hier(cs, &cs->mems_allowed);
+	update_nodemasks_hier(cs, &trialcs->mems_allowed);
 done:
 	return retval;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0ceb386777ae..e1af58e23bee 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1886,8 +1886,6 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
 	perf_set_shadow_time(event, ctx, tstamp);
 
 	perf_log_itrace_start(event);
@@ -1899,6 +1897,8 @@ event_sched_in(struct perf_event *event,
 		goto out;
 	}
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -3976,28 +3976,21 @@ static void perf_event_for_each(struct perf_event *event,
 		perf_event_for_each_child(sibling, func);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
-{
-	struct perf_event_context *ctx = event->ctx;
-	int ret = 0, active;
+struct period_event {
+	struct perf_event *event;
 	u64 value;
+};
 
-	if (!is_sampling_event(event))
-		return -EINVAL;
-
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
-	if (!value)
-		return -EINVAL;
+static int __perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	struct perf_event_context *ctx = event->ctx;
+	u64 value = pe->value;
+	bool active;
 
-	raw_spin_lock_irq(&ctx->lock);
+	raw_spin_lock(&ctx->lock);
 	if (event->attr.freq) {
-		if (value > sysctl_perf_event_sample_rate) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
 		event->attr.sample_freq = value;
 	} else {
 		event->attr.sample_period = value;
@@ -4016,11 +4009,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->pmu->start(event, PERF_EF_RELOAD);
 		perf_pmu_enable(ctx->pmu);
 	}
+	raw_spin_unlock(&ctx->lock);
 
-unlock:
+	return 0;
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+	struct period_event pe = { .event = event, };
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task;
+	u64 value;
+
+	if (!is_sampling_event(event))
+		return -EINVAL;
+
+	if (copy_from_user(&value, arg, sizeof(value)))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
+		return -EINVAL;
+
+	task = ctx->task;
+	pe.value = value;
+
+	if (!task) {
+		cpu_function_call(event->cpu, __perf_event_period, &pe);
+		return 0;
+	}
+
+retry:
+	if (!task_function_call(task, __perf_event_period, &pe))
+		return 0;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		task = ctx->task;
+		goto retry;
+	}
+
+	__perf_event_period(&pe);
 	raw_spin_unlock_irq(&ctx->lock);
 
-	return ret;
+	return 0;
 }
 
 static const struct file_operations perf_fops;
@@ -4376,14 +4411,6 @@ static void ring_buffer_wakeup(struct perf_event *event)
 	rcu_read_unlock();
 }
 
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
-	struct ring_buffer *rb;
-
-	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
-	rb_free(rb);
-}
-
 struct ring_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct ring_buffer *rb;
@@ -4766,12 +4793,20 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -6117,7 +6152,7 @@ static int __perf_event_overflow(struct perf_event *event,
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 9f6ce9ba4a04..a6adc36a3732 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
 struct ring_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
+	struct irq_work			irq_work;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
 	int				page_order;	/* allocation order  */
@@ -55,6 +56,15 @@ struct ring_buffer {
 };
 
 extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct ring_buffer *rb;
+
+	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+	rb_free(rb);
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 725c416085e3..7f63ad978cb8 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@ void perf_output_end(struct perf_output_handle *handle)
 	rcu_read_unlock();
 }
 
+static void rb_irq_work(struct irq_work *work);
+
 static void
 ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 {
@@ -241,6 +243,16 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+	init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+	if (!atomic_dec_and_test(&rb->refcount))
+		return;
+
+	rb->rcu_head.next = (void *)rb;
+	irq_work_queue(&rb->irq_work);
 }
 
 /*
@@ -319,7 +331,7 @@ err_put:
 	rb_free_aux(rb);
 
 err:
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 	handle->event = NULL;
 
 	return NULL;
@@ -370,7 +382,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 
 	local_set(&rb->aux_nest, 0);
 	rb_free_aux(rb);
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 }
 
 /*
@@ -547,17 +559,30 @@ static void __rb_free_aux(struct ring_buffer *rb)
 		rb->aux_priv = NULL;
 	}
 
-	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		rb_free_aux_page(rb, pg);
+	if (rb->aux_nr_pages) {
+		for (pg = 0; pg < rb->aux_nr_pages; pg++)
+			rb_free_aux_page(rb, pg);
 
-	kfree(rb->aux_pages);
-	rb->aux_nr_pages = 0;
+		kfree(rb->aux_pages);
+		rb->aux_nr_pages = 0;
+	}
 }
 
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
+		irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+	struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+	if (!atomic_read(&rb->aux_refcount))
 		__rb_free_aux(rb);
+
+	if (rb->rcu_head.next == (void *)rb)
+		call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/fork.c b/kernel/fork.c
index 03c1eaaa6ef5..8209fa2d36ef 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1854,13 +1854,21 @@ static int check_unshare_flags(unsigned long unshare_flags)
 				CLONE_NEWUSER|CLONE_NEWPID))
 		return -EINVAL;
 	/*
-	 * Not implemented, but pretend it works if there is nothing to
-	 * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND
-	 * needs to unshare vm.
+	 * Not implemented, but pretend it works if there is nothing
+	 * to unshare.  Note that unsharing the address space or the
+	 * signal handlers also need to unshare the signal queues (aka
+	 * CLONE_THREAD).
 	 */
 	if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
-		/* FIXME: get_task_mm() increments ->mm_users */
-		if (atomic_read(&current->mm->mm_users) > 1)
+		if (!thread_group_empty(current))
+			return -EINVAL;
+	}
+	if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) {
+		if (atomic_read(&current->sighand->count) > 1)
+			return -EINVAL;
+	}
+	if (unshare_flags & CLONE_VM) {
+		if (!current_is_single_threaded())
 			return -EINVAL;
 	}
 
@@ -1929,16 +1937,16 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	if (unshare_flags & CLONE_NEWUSER)
 		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
-	 * If unsharing a thread from a thread group, must also unshare vm.
-	 */
-	if (unshare_flags & CLONE_THREAD)
-		unshare_flags |= CLONE_VM;
-	/*
 	 * If unsharing vm, must also unshare signal handlers.
 	 */
 	if (unshare_flags & CLONE_VM)
 		unshare_flags |= CLONE_SIGHAND;
 	/*
+	 * If unsharing a signal handlers, must also unshare the signal queues.
+	 */
+	if (unshare_flags & CLONE_SIGHAND)
+		unshare_flags |= CLONE_THREAD;
+	/*
 	 * If unsharing namespace, must also unshare filesystem information.
 	 */
 	if (unshare_flags & CLONE_NEWNS)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 2456fe89719c..0ec0298ad999 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -962,6 +962,23 @@ int irq_chip_set_affinity_parent(struct irq_data *data,
 }
 
 /**
+ * irq_chip_set_type_parent - Set IRQ type on the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ * @type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
+ *
+ * Conditional, as the underlying parent chip might not implement it.
+ */
+int irq_chip_set_type_parent(struct irq_data *data, unsigned int type)
+{
+	data = data->parent_data;
+
+	if (data->chip->irq_set_type)
+		return data->chip->irq_set_type(data, type);
+
+	return -ENOSYS;
+}
+
+/**
  * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware
  * @data:	Pointer to interrupt specific data
  *
@@ -974,7 +991,7 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
 		if (data->chip && data->chip->irq_retrigger)
 			return data->chip->irq_retrigger(data);
 
-	return -ENOSYS;
+	return 0;
 }
 
 /**
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index df2f4642d1e7..5c38f59741e2 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 
 #include "internals.h"
 
@@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_MUTEX(register_lock);
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
 		return;
 
+	/*
+	 * irq directories are registered only when a handler is
+	 * added, not when the descriptor is created, so multiple
+	 * tasks might try to register at the same time.
+	 */
+	mutex_lock(&register_lock);
+
+	if (desc->dir)
+		goto out_unlock;
+
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
-		return;
+		goto out_unlock;
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
@@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	proc_create_data("spurious", 0444, desc->dir,
 			 &irq_spurious_proc_fops, (void *)(long)irq);
+
+out_unlock:
+	mutex_unlock(&register_lock);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 123673291ffb..8476206a1e19 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2217,11 +2217,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * running on another CPU and we could rave with its RUNNING -> DEAD
+	 * transition, resulting in a double drop.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
@@ -2358,13 +2358,20 @@ unsigned long nr_running(void)
 
 /*
  * Check if only the current task is running on the cpu.
+ *
+ * Caution: this function does not check that the caller has disabled
+ * preemption, thus the result might have a time-of-check-to-time-of-use
+ * race.  The caller is responsible to use it correctly, for example:
+ *
+ * - from a non-preemptable section (of course)
+ *
+ * - from a thread that is bound to a single CPU
+ *
+ * - in a loop with very short iterations (e.g. a polling loop)
  */
 bool single_task_running(void)
 {
-	if (cpu_rq(smp_processor_id())->nr_running == 1)
-		return true;
-	else
-		return false;
+	return raw_rq()->nr_running == 1;
 }
 EXPORT_SYMBOL(single_task_running);
 
@@ -5328,6 +5335,14 @@ static int sched_cpu_active(struct notifier_block *nfb,
 	case CPU_STARTING:
 		set_cpu_rq_start_time();
 		return NOTIFY_OK;
+	case CPU_ONLINE:
+		/*
+		 * At this point a starting CPU has marked itself as online via
+		 * set_cpu_online(). But it might not yet have marked itself
+		 * as active, which is essential from here on.
+		 *
+		 * Thus, fall-through and help the starting CPU along.
+		 */
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c2980e8733bc..77690b653ca9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5126,18 +5126,21 @@ again:
 		 * entity, update_curr() will update its vruntime, otherwise
 		 * forget we've ever seen it.
 		 */
-		if (curr && curr->on_rq)
-			update_curr(cfs_rq);
-		else
-			curr = NULL;
+		if (curr) {
+			if (curr->on_rq)
+				update_curr(cfs_rq);
+			else
+				curr = NULL;
 
-		/*
-		 * This call to check_cfs_rq_runtime() will do the throttle and
-		 * dequeue its entity in the parent(s). Therefore the 'simple'
-		 * nr_running test will indeed be correct.
-		 */
-		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
-			goto simple;
+			/*
+			 * This call to check_cfs_rq_runtime() will do the
+			 * throttle and dequeue its entity in the parent(s).
+			 * Therefore the 'simple' nr_running test will indeed
+			 * be correct.
+			 */
+			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+				goto simple;
+		}
 
 		se = pick_next_entity(cfs_rq, curr);
 		cfs_rq = group_cfs_rq(se);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e0e129993958..aa1f059de4f7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1068,9 +1068,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/signal.c b/kernel/signal.c
index d51c5ddd855c..0206be728dac 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2753,12 +2753,15 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 #ifdef SEGV_BNDERR
-		err |= __put_user(from->si_lower, &to->si_lower);
-		err |= __put_user(from->si_upper, &to->si_upper);
+		if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
+			err |= __put_user(from->si_lower, &to->si_lower);
+			err |= __put_user(from->si_upper, &to->si_upper);
+		}
 #endif
 		break;
 	case __SI_CHLD:
@@ -3022,7 +3025,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 	int ret = copy_siginfo_from_user32(&info, uinfo);
 	if (unlikely(ret))
 		return ret;
@@ -3066,7 +3069,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 
 	if (copy_siginfo_from_user32(&info, uinfo))
 		return -EFAULT;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 946acb72179f..414d9df94724 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1615,7 +1615,7 @@ static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
 	negative = (tick_error < 0);
 
 	/* Sort out the magnitude of the correction */
-	tick_error = abs(tick_error);
+	tick_error = abs64(tick_error);
 	for (adj = 0; tick_error > interval; adj++)
 		tick_error >>= 1;