1 files changed, 355 insertions, 87 deletions

diff --git a/kernel/kthread.c b/kernel/kthread.c
index c55afba990a..c2390f41307 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -12,10 +12,12 @@
 #include <linux/cpuset.h>
 #include <linux/unistd.h>
 #include <linux/file.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/freezer.h>
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -27,22 +29,45 @@ struct kthread_create_info
 	/* Information passed to kthread() from kthreadd. */
 	int (*threadfn)(void *data);
 	void *data;
+	int node;
 
 	/* Result passed back to kthread_create() from kthreadd. */
 	struct task_struct *result;
-	struct completion done;
+	struct completion *done;
 
 	struct list_head list;
 };
 
 struct kthread {
-	int should_stop;
+	unsigned long flags;
+	unsigned int cpu;
 	void *data;
+	struct completion parked;
 	struct completion exited;
 };
 
-#define to_kthread(tsk)	\
-	container_of((tsk)->vfork_done, struct kthread, exited)
+enum KTHREAD_BITS {
+	KTHREAD_IS_PER_CPU = 0,
+	KTHREAD_SHOULD_STOP,
+	KTHREAD_SHOULD_PARK,
+	KTHREAD_IS_PARKED,
+};
+
+#define __to_kthread(vfork)	\
+	container_of(vfork, struct kthread, exited)
+
+static inline struct kthread *to_kthread(struct task_struct *k)
+{
+	return __to_kthread(k->vfork_done);
+}
+
+static struct kthread *to_live_kthread(struct task_struct *k)
+{
+	struct completion *vfork = ACCESS_ONCE(k->vfork_done);
+	if (likely(vfork))
+		return __to_kthread(vfork);
+	return NULL;
+}
 
 /**
  * kthread_should_stop - should this kthread return now?
@@ -51,13 +76,54 @@ struct kthread {
  * and this will return true.  You should then return, and your return
  * value will be passed through to kthread_stop().
  */
-int kthread_should_stop(void)
+bool kthread_should_stop(void)
 {
-	return to_kthread(current)->should_stop;
+	return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
 }
 EXPORT_SYMBOL(kthread_should_stop);
 
 /**
+ * kthread_should_park - should this kthread park now?
+ *
+ * When someone calls kthread_park() on your kthread, it will be woken
+ * and this will return true.  You should then do the necessary
+ * cleanup and call kthread_parkme()
+ *
+ * Similar to kthread_should_stop(), but this keeps the thread alive
+ * and in a park position. kthread_unpark() "restarts" the thread and
+ * calls the thread function again.
+ */
+bool kthread_should_park(void)
+{
+	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+}
+
+/**
+ * kthread_freezable_should_stop - should this freezable kthread return now?
+ * @was_frozen: optional out parameter, indicates whether %current was frozen
+ *
+ * kthread_should_stop() for freezable kthreads, which will enter
+ * refrigerator if necessary.  This function is safe from kthread_stop() /
+ * freezer deadlock and freezable kthreads should use this function instead
+ * of calling try_to_freeze() directly.
+ */
+bool kthread_freezable_should_stop(bool *was_frozen)
+{
+	bool frozen = false;
+
+	might_sleep();
+
+	if (unlikely(freezing(current)))
+		frozen = __refrigerator(true);
+
+	if (was_frozen)
+		*was_frozen = frozen;
+
+	return kthread_should_stop();
+}
+EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
+
+/**
  * kthread_data - return data value specified on kthread creation
  * @task: kthread task in question
  *
@@ -70,101 +136,206 @@ void *kthread_data(struct task_struct *task)
 	return to_kthread(task)->data;
 }
 
+/**
+ * probe_kthread_data - speculative version of kthread_data()
+ * @task: possible kthread task in question
+ *
+ * @task could be a kthread task.  Return the data value specified when it
+ * was created if accessible.  If @task isn't a kthread task or its data is
+ * inaccessible for any reason, %NULL is returned.  This function requires
+ * that @task itself is safe to dereference.
+ */
+void *probe_kthread_data(struct task_struct *task)
+{
+	struct kthread *kthread = to_kthread(task);
+	void *data = NULL;
+
+	probe_kernel_read(&data, &kthread->data, sizeof(data));
+	return data;
+}
+
+static void __kthread_parkme(struct kthread *self)
+{
+	__set_current_state(TASK_PARKED);
+	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
+		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);
+}
+
+void kthread_parkme(void)
+{
+	__kthread_parkme(to_kthread(current));
+}
+
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
 	struct kthread_create_info *create = _create;
 	int (*threadfn)(void *data) = create->threadfn;
 	void *data = create->data;
+	struct completion *done;
 	struct kthread self;
 	int ret;
 
-	self.should_stop = 0;
+	self.flags = 0;
 	self.data = data;
 	init_completion(&self.exited);
+	init_completion(&self.parked);
 	current->vfork_done = &self.exited;
 
+	/* If user was SIGKILLed, I release the structure. */
+	done = xchg(&create->done, NULL);
+	if (!done) {
+		kfree(create);
+		do_exit(-EINTR);
+	}
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
-	complete(&create->done);
+	complete(done);
 	schedule();
 
 	ret = -EINTR;
-	if (!self.should_stop)
-		ret = threadfn(data);
 
+	if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+		__kthread_parkme(&self);
+		ret = threadfn(data);
+	}
 	/* we can't just return, we must preserve "self" on stack */
 	do_exit(ret);
 }
 
+/* called from do_fork() to get node information for about to be created task */
+int tsk_fork_get_node(struct task_struct *tsk)
+{
+#ifdef CONFIG_NUMA
+	if (tsk == kthreadd_task)
+		return tsk->pref_node_fork;
+#endif
+	return NUMA_NO_NODE;
+}
+
 static void create_kthread(struct kthread_create_info *create)
 {
 	int pid;
 
+#ifdef CONFIG_NUMA
+	current->pref_node_fork = create->node;
+#endif
 	/* We want our own signal handler (we take no signals by default). */
 	pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
 	if (pid < 0) {
+		/* If user was SIGKILLed, I release the structure. */
+		struct completion *done = xchg(&create->done, NULL);
+
+		if (!done) {
+			kfree(create);
+			return;
+		}
 		create->result = ERR_PTR(pid);
-		complete(&create->done);
+		complete(done);
 	}
 }
 
 /**
- * kthread_create - create a kthread.
+ * kthread_create_on_node - create a kthread.
  * @threadfn: the function to run until signal_pending(current).
  * @data: data ptr for @threadfn.
+ * @node: memory node number.
  * @namefmt: printf-style name for the thread.
  *
  * Description: This helper function creates and names a kernel
  * thread.  The thread will be stopped: use wake_up_process() to start
  * it.  See also kthread_run().
  *
+ * If thread is going to be bound on a particular cpu, give its node
+ * in @node, to get NUMA affinity for kthread stack, or else give -1.
  * When woken, the thread will run @threadfn() with @data as its
  * argument. @threadfn() can either call do_exit() directly if it is a
- * standalone thread for which noone will call kthread_stop(), or
+ * standalone thread for which no one will call kthread_stop(), or
  * return when 'kthread_should_stop()' is true (which means
  * kthread_stop() has been called).  The return value should be zero
  * or a negative error number; it will be passed to kthread_stop().
  *
- * Returns a task_struct or ERR_PTR(-ENOMEM).
+ * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR).
  */
-struct task_struct *kthread_create(int (*threadfn)(void *data),
-				   void *data,
-				   const char namefmt[],
-				   ...)
+struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
+					   void *data, int node,
+					   const char namefmt[],
+					   ...)
 {
-	struct kthread_create_info create;
-
-	create.threadfn = threadfn;
-	create.data = data;
-	init_completion(&create.done);
+	DECLARE_COMPLETION_ONSTACK(done);
+	struct task_struct *task;
+	struct kthread_create_info *create = kmalloc(sizeof(*create),
+						     GFP_KERNEL);
+
+	if (!create)
+		return ERR_PTR(-ENOMEM);
+	create->threadfn = threadfn;
+	create->data = data;
+	create->node = node;
+	create->done = &done;
 
 	spin_lock(&kthread_create_lock);
-	list_add_tail(&create.list, &kthread_create_list);
+	list_add_tail(&create->list, &kthread_create_list);
 	spin_unlock(&kthread_create_lock);
 
 	wake_up_process(kthreadd_task);
-	wait_for_completion(&create.done);
-
-	if (!IS_ERR(create.result)) {
+	/*
+	 * Wait for completion in killable state, for I might be chosen by
+	 * the OOM killer while kthreadd is trying to allocate memory for
+	 * new kernel thread.
+	 */
+	if (unlikely(wait_for_completion_killable(&done))) {
+		/*
+		 * If I was SIGKILLed before kthreadd (or new kernel thread)
+		 * calls complete(), leave the cleanup of this structure to
+		 * that thread.
+		 */
+		if (xchg(&create->done, NULL))
+			return ERR_PTR(-EINTR);
+		/*
+		 * kthreadd (or new kernel thread) will call complete()
+		 * shortly.
+		 */
+		wait_for_completion(&done);
+	}
+	task = create->result;
+	if (!IS_ERR(task)) {
 		static const struct sched_param param = { .sched_priority = 0 };
 		va_list args;
 
 		va_start(args, namefmt);
-		vsnprintf(create.result->comm, sizeof(create.result->comm),
-			  namefmt, args);
+		vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
 		va_end(args);
 		/*
 		 * root may have changed our (kthreadd's) priority or CPU mask.
 		 * The kernel thread should not inherit these properties.
 		 */
-		sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(create.result, cpu_all_mask);
+		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
+		set_cpus_allowed_ptr(task, cpu_all_mask);
+	}
+	kfree(create);
+	return task;
+}
+EXPORT_SYMBOL(kthread_create_on_node);
+
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
+{
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, state)) {
+		WARN_ON(1);
+		return;
 	}
-	return create.result;
+	/* It's safe because the task is inactive. */
+	do_set_cpus_allowed(p, cpumask_of(cpu));
+	p->flags |= PF_NO_SETAFFINITY;
 }
-EXPORT_SYMBOL(kthread_create);
 
 /**
  * kthread_bind - bind a just-created kthread to a cpu.
@@ -177,17 +348,99 @@ EXPORT_SYMBOL(kthread_create);
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
+	__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(kthread_bind);
+
+/**
+ * kthread_create_on_cpu - Create a cpu bound kthread
+ * @threadfn: the function to run until signal_pending(current).
+ * @data: data ptr for @threadfn.
+ * @cpu: The cpu on which the thread should be bound,
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
+ *
+ * Description: This helper function creates and names a kernel thread
+ * The thread will be woken and put into park mode.
+ */
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+					  void *data, unsigned int cpu,
+					  const char *namefmt)
+{
+	struct task_struct *p;
+
+	p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
+				   cpu);
+	if (IS_ERR(p))
+		return p;
+	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
+	to_kthread(p)->cpu = cpu;
+	/* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
+	kthread_park(p);
+	return p;
+}
+
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
+{
+	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * We clear the IS_PARKED bit here as we don't wait
+	 * until the task has left the park code. So if we'd
+	 * park before that happens we'd see the IS_PARKED bit
+	 * which might be about to be cleared.
+	 */
+	if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+		if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+			__kthread_bind(k, kthread->cpu, TASK_PARKED);
+		wake_up_state(k, TASK_PARKED);
 	}
+}
 
-	p->cpus_allowed = cpumask_of_cpu(cpu);
-	p->rt.nr_cpus_allowed = 1;
-	p->flags |= PF_THREAD_BOUND;
+/**
+ * kthread_unpark - unpark a thread created by kthread_create().
+ * @k:		thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return false, wakes it, and
+ * waits for it to return. If the thread is marked percpu then its
+ * bound to the cpu again.
+ */
+void kthread_unpark(struct task_struct *k)
+{
+	struct kthread *kthread = to_live_kthread(k);
+
+	if (kthread)
+		__kthread_unpark(k, kthread);
+}
+
+/**
+ * kthread_park - park a thread created by kthread_create().
+ * @k: thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return true, wakes it, and
+ * waits for it to return. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will park without
+ * calling threadfn().
+ *
+ * Returns 0 if the thread is parked, -ENOSYS if the thread exited.
+ * If called by the kthread itself just the park bit is set.
+ */
+int kthread_park(struct task_struct *k)
+{
+	struct kthread *kthread = to_live_kthread(k);
+	int ret = -ENOSYS;
+
+	if (kthread) {
+		if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+			set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+			if (k != current) {
+				wake_up_process(k);
+				wait_for_completion(&kthread->parked);
+			}
+		}
+		ret = 0;
+	}
+	return ret;
 }
-EXPORT_SYMBOL(kthread_bind);
 
 /**
  * kthread_stop - stop a thread created by kthread_create().
@@ -210,20 +463,19 @@ int kthread_stop(struct task_struct *k)
 	int ret;
 
 	trace_sched_kthread_stop(k);
-	get_task_struct(k);
 
-	kthread = to_kthread(k);
-	barrier(); /* it might have exited */
-	if (k->vfork_done != NULL) {
-		kthread->should_stop = 1;
+	get_task_struct(k);
+	kthread = to_live_kthread(k);
+	if (kthread) {
+		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
+		__kthread_unpark(k, kthread);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}
 	ret = k->exit_code;
-
 	put_task_struct(k);
-	trace_sched_kthread_stop_ret(ret);
 
+	trace_sched_kthread_stop_ret(ret);
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);
@@ -236,9 +488,9 @@ int kthreadd(void *unused)
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
-	set_mems_allowed(node_states[N_HIGH_MEMORY]);
+	set_mems_allowed(node_states[N_MEMORY]);
 
-	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
+	current->flags |= PF_NOFREEZE;
 
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -316,16 +568,12 @@ repeat:
 					struct kthread_work, node);
 		list_del_init(&work->node);
 	}
+	worker->current_work = work;
 	spin_unlock_irq(&worker->lock);
 
 	if (work) {
 		__set_current_state(TASK_RUNNING);
 		work->func(work);
-		smp_wmb();	/* wmb worker-b0 paired with flush-b1 */
-		work->done_seq = work->queue_seq;
-		smp_mb();	/* mb worker-b1 paired with flush-b0 */
-		if (atomic_read(&work->flushing))
-			wake_up_all(&work->done);
 	} else if (!freezing(current))
 		schedule();
 
@@ -334,6 +582,19 @@ repeat:
 }
 EXPORT_SYMBOL_GPL(kthread_worker_fn);
 
+/* insert @work before @pos in @worker */
+static void insert_kthread_work(struct kthread_worker *worker,
+			       struct kthread_work *work,
+			       struct list_head *pos)
+{
+	lockdep_assert_held(&worker->lock);
+
+	list_add_tail(&work->node, pos);
+	work->worker = worker;
+	if (likely(worker->task))
+		wake_up_process(worker->task);
+}
+
 /**
  * queue_kthread_work - queue a kthread_work
  * @worker: target kthread_worker
@@ -351,10 +612,7 @@ bool queue_kthread_work(struct kthread_worker *worker,
 
 	spin_lock_irqsave(&worker->lock, flags);
 	if (list_empty(&work->node)) {
-		list_add_tail(&work->node, &worker->work_list);
-		work->queue_seq++;
-		if (likely(worker->task))
-			wake_up_process(worker->task);
+		insert_kthread_work(worker, work, &worker->work_list);
 		ret = true;
 	}
 	spin_unlock_irqrestore(&worker->lock, flags);
@@ -362,6 +620,18 @@ bool queue_kthread_work(struct kthread_worker *worker,
 }
 EXPORT_SYMBOL_GPL(queue_kthread_work);
 
+struct kthread_flush_work {
+	struct kthread_work	work;
+	struct completion	done;
+};
+
+static void kthread_flush_work_fn(struct kthread_work *work)
+{
+	struct kthread_flush_work *fwork =
+		container_of(work, struct kthread_flush_work, work);
+	complete(&fwork->done);
+}
+
 /**
  * flush_kthread_work - flush a kthread_work
  * @work: work to flush
@@ -370,39 +640,37 @@ EXPORT_SYMBOL_GPL(queue_kthread_work);
  */
 void flush_kthread_work(struct kthread_work *work)
 {
-	int seq = work->queue_seq;
-
-	atomic_inc(&work->flushing);
+	struct kthread_flush_work fwork = {
+		KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
+		COMPLETION_INITIALIZER_ONSTACK(fwork.done),
+	};
+	struct kthread_worker *worker;
+	bool noop = false;
 
-	/*
-	 * mb flush-b0 paired with worker-b1, to make sure either
-	 * worker sees the above increment or we see done_seq update.
-	 */
-	smp_mb__after_atomic_inc();
+retry:
+	worker = work->worker;
+	if (!worker)
+		return;
 
-	/* A - B <= 0 tests whether B is in front of A regardless of overflow */
-	wait_event(work->done, seq - work->done_seq <= 0);
-	atomic_dec(&work->flushing);
+	spin_lock_irq(&worker->lock);
+	if (work->worker != worker) {
+		spin_unlock_irq(&worker->lock);
+		goto retry;
+	}
 
-	/*
-	 * rmb flush-b1 paired with worker-b0, to make sure our caller
-	 * sees every change made by work->func().
-	 */
-	smp_mb__after_atomic_dec();
-}
-EXPORT_SYMBOL_GPL(flush_kthread_work);
+	if (!list_empty(&work->node))
+		insert_kthread_work(worker, &fwork.work, work->node.next);
+	else if (worker->current_work == work)
+		insert_kthread_work(worker, &fwork.work, worker->work_list.next);
+	else
+		noop = true;
 
-struct kthread_flush_work {
-	struct kthread_work	work;
-	struct completion	done;
-};
+	spin_unlock_irq(&worker->lock);
 
-static void kthread_flush_work_fn(struct kthread_work *work)
-{
-	struct kthread_flush_work *fwork =
-		container_of(work, struct kthread_flush_work, work);
-	complete(&fwork->done);
+	if (!noop)
+		wait_for_completion(&fwork.done);
 }
+EXPORT_SYMBOL_GPL(flush_kthread_work);
 
 /**
  * flush_kthread_worker - flush all current works on a kthread_worker