Merge tag 'v4.14.52' into linux-linaro-lsk-v4.14lsk-v4.14-18.06

This is the 4.14.52 stable release

11 files changed, 73 insertions, 54 deletions

diff --git a/kernel/kthread.c b/kernel/kthread.c
index 1c19edf82427..1ef8f3a5b072 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -169,12 +169,13 @@ void *kthread_probe_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-	__set_current_state(TASK_PARKED);
-	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
+	for (;;) {
+		set_current_state(TASK_PARKED);
+		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
+			break;
 		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
 			complete(&self->parked);
 		schedule();
-		__set_current_state(TASK_PARKED);
 	}
 	clear_bit(KTHREAD_IS_PARKED, &self->flags);
 	__set_current_state(TASK_RUNNING);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index e795908f3607..a90336779375 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -352,16 +352,15 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	struct task_struct *owner;
 	bool ret = true;
 
+	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
+
 	if (need_resched())
 		return false;
 
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
-	if (!rwsem_owner_is_writer(owner)) {
-		/*
-		 * Don't spin if the rwsem is readers owned.
-		 */
-		ret = !rwsem_owner_is_reader(owner);
+	if (!owner || !is_rwsem_owner_spinnable(owner)) {
+		ret = !owner;	/* !owner is spinnable */
 		goto done;
 	}
 
@@ -382,11 +381,11 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner = READ_ONCE(sem->owner);
 
-	if (!rwsem_owner_is_writer(owner))
-		goto out;
+	if (!is_rwsem_owner_spinnable(owner))
+		return false;
 
 	rcu_read_lock();
-	while (sem->owner == owner) {
+	while (owner && (READ_ONCE(sem->owner) == owner)) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
 		 * checking sem->owner still matches owner, if that fails,
@@ -408,12 +407,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		cpu_relax();
 	}
 	rcu_read_unlock();
-out:
+
 	/*
 	 * If there is a new owner or the owner is not set, we continue
 	 * spinning.
 	 */
-	return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
+	return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
 }
 
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index a6c76a4832b4..22bd01a7dcaa 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -201,5 +201,3 @@ void up_read_non_owner(struct rw_semaphore *sem)
 EXPORT_SYMBOL(up_read_non_owner);
 
 #endif
-
-
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a883b8f1fdc6..410ee7b9ac2c 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,20 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
- * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
  * the owner field when it unlocks. A reader, on the other hand, will
  * not touch the owner field when it unlocks.
  *
- * In essence, the owner field now has the following 3 states:
+ * In essence, the owner field now has the following 4 states:
  *  1) 0
  *     - lock is free or the owner hasn't set the field yet
  *  2) RWSEM_READER_OWNED
  *     - lock is currently or previously owned by readers (lock is free
  *       or not set by owner yet)
- *  3) Other non-zero value
- *     - a writer owns the lock
+ *  3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
+ *     - lock is owned by an anonymous writer, so spinning on the lock
+ *       owner should be disabled.
+ *  4) Other non-zero value
+ *     - a writer owns the lock and other writers can spin on the lock owner.
  */
-#define RWSEM_READER_OWNED	((struct task_struct *)1UL)
+#define RWSEM_ANONYMOUSLY_OWNED	(1UL << 0)
+#define RWSEM_READER_OWNED	((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
@@ -45,14 +49,22 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 		WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
 }
 
-static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+/*
+ * Return true if the a rwsem waiter can spin on the rwsem's owner
+ * and steal the lock, i.e. the lock is not anonymously owned.
+ * N.B. !owner is considered spinnable.
+ */
+static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
 {
-	return owner && owner != RWSEM_READER_OWNED;
+	return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
 }
 
-static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+/*
+ * Return true if rwsem is owned by an anonymous writer or readers.
+ */
+static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
 {
-	return owner == RWSEM_READER_OWNED;
+	return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
 }
 #else
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
diff --git a/kernel/module.c b/kernel/module.c
index 690c0651c40f..321b0b1f87e7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3506,6 +3506,11 @@ static noinline int do_init_module(struct module *mod)
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_sched(), but we don't want to slow down the success
 	 * path, so use actual RCU here.
+	 * Note that module_alloc() on most architectures creates W+X page
+	 * mappings which won't be cleaned up until do_free_init() runs.  Any
+	 * code such as mark_rodata_ro() which depends on those mappings to
+	 * be cleaned up needs to sync with the queued work - ie
+	 * rcu_barrier_sched()
 	 */
 	call_rcu_sched(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8cf36b30a006..f287dcbe8cb2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3374,23 +3374,8 @@ static void __sched notrace __schedule(bool preempt)
 
 void __noreturn do_task_dead(void)
 {
-	/*
-	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
-	 * when the following two conditions become true.
-	 *   - There is race condition of mmap_sem (It is acquired by
-	 *     exit_mm()), and
-	 *   - SMI occurs before setting TASK_RUNINNG.
-	 *     (or hypervisor of virtual machine switches to other guest)
-	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
-	 *
-	 * To avoid it, we have to wait for releasing tsk->pi_lock which
-	 * is held by try_to_wake_up()
-	 */
-	raw_spin_lock_irq(&current->pi_lock);
-	raw_spin_unlock_irq(&current->pi_lock);
-
 	/* Causes final put_task_struct in finish_task_switch(): */
-	__set_current_state(TASK_DEAD);
+	set_special_state(TASK_DEAD);
 
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4ae5c1ea90e2..501f17c642ab 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1084,7 +1084,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
  * So, overflow is not an issue here.
  */
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 {
 	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
 	u64 u_act;
@@ -2655,8 +2655,6 @@ bool dl_cpu_busy(unsigned int cpu)
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
 void print_dl_stats(struct seq_file *m, int cpu)
 {
 	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 113eaeb6c0f8..bba2217652ff 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2689,8 +2689,6 @@ int sched_rr_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
 void print_rt_stats(struct seq_file *m, int cpu)
 {
 	rt_rq_iter_t iter;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 307c35d33660..b29376169f3f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1969,8 +1969,9 @@ extern bool sched_debug_enabled;
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);
diff --git a/kernel/signal.c b/kernel/signal.c
index 6895f6bb98a7..4439ba9dc5d9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1828,14 +1828,27 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 			return;
 	}
 
+	set_special_state(TASK_TRACED);
+
 	/*
 	 * We're committing to trapping.  TRACED should be visible before
 	 * TRAPPING is cleared; otherwise, the tracer might fail do_wait().
 	 * Also, transition to TRACED and updates to ->jobctl should be
 	 * atomic with respect to siglock and should be done after the arch
 	 * hook as siglock is released and regrabbed across it.
+	 *
+	 *     TRACER				    TRACEE
+	 *
+	 *     ptrace_attach()
+	 * [L]   wait_on_bit(JOBCTL_TRAPPING)	[S] set_special_state(TRACED)
+	 *     do_wait()
+	 *       set_current_state()                smp_wmb();
+	 *       ptrace_do_wait()
+	 *         wait_task_stopped()
+	 *           task_stopped_code()
+	 * [L]         task_is_traced()		[S] task_clear_jobctl_trapping();
 	 */
-	set_current_state(TASK_TRACED);
+	smp_wmb();
 
 	current->last_siginfo = info;
 	current->exit_code = exit_code;
@@ -2043,7 +2056,7 @@ static bool do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
-		__set_current_state(TASK_STOPPED);
+		set_special_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 
 		/*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b7591261652d..64c0291b579c 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
 #include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
 
 /*
  * Structure to determine completion condition and record errors.  May
@@ -65,27 +66,31 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
-					struct cpu_stop_work *work)
+					struct cpu_stop_work *work,
+					struct wake_q_head *wakeq)
 {
 	list_add_tail(&work->list, &stopper->works);
-	wake_up_process(stopper->thread);
+	wake_q_add(wakeq, stopper->thread);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	DEFINE_WAKE_Q(wakeq);
 	unsigned long flags;
 	bool enabled;
 
 	spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
-		__cpu_stop_queue_work(stopper, work);
+		__cpu_stop_queue_work(stopper, work, &wakeq);
 	else if (work->done)
 		cpu_stop_signal_done(work->done);
 	spin_unlock_irqrestore(&stopper->lock, flags);
 
+	wake_up_q(&wakeq);
+
 	return enabled;
 }
 
@@ -229,6 +234,7 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 {
 	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+	DEFINE_WAKE_Q(wakeq);
 	int err;
 retry:
 	spin_lock_irq(&stopper1->lock);
@@ -252,8 +258,8 @@ retry:
 			goto unlock;
 
 	err = 0;
-	__cpu_stop_queue_work(stopper1, work1);
-	__cpu_stop_queue_work(stopper2, work2);
+	__cpu_stop_queue_work(stopper1, work1, &wakeq);
+	__cpu_stop_queue_work(stopper2, work2, &wakeq);
 unlock:
 	spin_unlock(&stopper2->lock);
 	spin_unlock_irq(&stopper1->lock);
@@ -263,6 +269,9 @@ unlock:
 			cpu_relax();
 		goto retry;
 	}
+
+	wake_up_q(&wakeq);
+
 	return err;
 }
 /**