1 files changed, 88 insertions, 84 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index cb9e5a444fba..56a229621a83 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -60,6 +60,7 @@ struct io_worker {
 	const struct cred *cur_creds;
 	const struct cred *saved_creds;
 	struct files_struct *restore_files;
+	struct nsproxy *restore_nsproxy;
 	struct fs_struct *restore_fs;
 };
 
@@ -87,7 +88,7 @@ enum {
  */
 struct io_wqe {
 	struct {
-		spinlock_t lock;
+		raw_spinlock_t lock;
 		struct io_wq_work_list work_list;
 		unsigned long hash_map;
 		unsigned flags;
@@ -148,11 +149,12 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 
 	if (current->files != worker->restore_files) {
 		__acquire(&wqe->lock);
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		dropped_lock = true;
 
 		task_lock(current);
 		current->files = worker->restore_files;
+		current->nsproxy = worker->restore_nsproxy;
 		task_unlock(current);
 	}
 
@@ -166,7 +168,7 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 	if (worker->mm) {
 		if (!dropped_lock) {
 			__acquire(&wqe->lock);
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 			dropped_lock = true;
 		}
 		__set_current_state(TASK_RUNNING);
@@ -200,7 +202,6 @@ static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
-	unsigned nr_workers;
 
 	/*
 	 * If we're not at zero, someone else is holding a brief reference
@@ -220,23 +221,19 @@ static void io_worker_exit(struct io_worker *worker)
 	worker->flags = 0;
 	preempt_enable();
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	hlist_nulls_del_rcu(&worker->nulls_node);
 	list_del_rcu(&worker->all_list);
 	if (__io_worker_unuse(wqe, worker)) {
 		__release(&wqe->lock);
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 	}
 	acct->nr_workers--;
-	nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers +
-			wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers;
-	spin_unlock_irq(&wqe->lock);
-
-	/* all workers gone, wq exit can proceed */
-	if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs))
-		complete(&wqe->wq->done);
+	raw_spin_unlock_irq(&wqe->lock);
 
 	kfree_rcu(worker, rcu);
+	if (refcount_dec_and_test(&wqe->wq->refs))
+		complete(&wqe->wq->done);
 }
 
 static inline bool io_wqe_run_queue(struct io_wqe *wqe)
@@ -318,6 +315,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	worker->restore_files = current->files;
+	worker->restore_nsproxy = current->nsproxy;
 	worker->restore_fs = current->fs;
 	io_wqe_inc_running(wqe, worker);
 }
@@ -454,6 +452,7 @@ static void io_impersonate_work(struct io_worker *worker,
 	if (work->files && current->files != work->files) {
 		task_lock(current);
 		current->files = work->files;
+		current->nsproxy = work->nsproxy;
 		task_unlock(current);
 	}
 	if (work->fs && current->fs != work->fs)
@@ -504,7 +503,7 @@ get_next:
 		else if (!wq_list_empty(&wqe->work_list))
 			wqe->flags |= IO_WQE_FLAG_STALLED;
 
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		if (!work)
 			break;
 		io_assign_current_work(worker, work);
@@ -539,7 +538,7 @@ get_next:
 				io_wqe_enqueue(wqe, linked);
 
 			if (hash != -1U && !next_hashed) {
-				spin_lock_irq(&wqe->lock);
+				raw_spin_lock_irq(&wqe->lock);
 				wqe->hash_map &= ~BIT_ULL(hash);
 				wqe->flags &= ~IO_WQE_FLAG_STALLED;
 				/* dependent work is not hashed */
@@ -547,11 +546,11 @@ get_next:
 				/* skip unnecessary unlock-lock wqe->lock */
 				if (!work)
 					goto get_next;
-				spin_unlock_irq(&wqe->lock);
+				raw_spin_unlock_irq(&wqe->lock);
 			}
 		} while (work);
 
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 	} while (1);
 }
 
@@ -566,7 +565,7 @@ static int io_wqe_worker(void *data)
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
 		set_current_state(TASK_INTERRUPTIBLE);
 loop:
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 		if (io_wqe_run_queue(wqe)) {
 			__set_current_state(TASK_RUNNING);
 			io_worker_handle_work(worker);
@@ -577,7 +576,7 @@ loop:
 			__release(&wqe->lock);
 			goto loop;
 		}
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		if (signal_pending(current))
 			flush_signals(current);
 		if (schedule_timeout(WORKER_IDLE_TIMEOUT))
@@ -589,11 +588,11 @@ loop:
 	}
 
 	if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 		if (!wq_list_empty(&wqe->work_list))
 			io_worker_handle_work(worker);
 		else
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 	}
 
 	io_worker_exit(worker);
@@ -633,14 +632,14 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
 
 	worker->flags &= ~IO_WORKER_F_RUNNING;
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	io_wqe_dec_running(wqe, worker);
-	spin_unlock_irq(&wqe->lock);
+	raw_spin_unlock_irq(&wqe->lock);
 }
 
 static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 {
-	struct io_wqe_acct *acct =&wqe->acct[index];
+	struct io_wqe_acct *acct = &wqe->acct[index];
 	struct io_worker *worker;
 
 	worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
@@ -659,7 +658,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 		return false;
 	}
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
 	list_add_tail_rcu(&worker->all_list, &wqe->all_list);
 	worker->flags |= IO_WORKER_F_FREE;
@@ -668,11 +667,12 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 	if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND))
 		worker->flags |= IO_WORKER_F_FIXED;
 	acct->nr_workers++;
-	spin_unlock_irq(&wqe->lock);
+	raw_spin_unlock_irq(&wqe->lock);
 
 	if (index == IO_WQ_ACCT_UNBOUND)
 		atomic_inc(&wq->user->processes);
 
+	refcount_inc(&wq->refs);
 	wake_up_process(worker->task);
 	return true;
 }
@@ -688,28 +688,63 @@ static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
 	return acct->nr_workers < acct->max_workers;
 }
 
+static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
+{
+	send_sig(SIGINT, worker->task, 1);
+	return false;
+}
+
+/*
+ * Iterate the passed in list and call the specific function for each
+ * worker that isn't exiting
+ */
+static bool io_wq_for_each_worker(struct io_wqe *wqe,
+				  bool (*func)(struct io_worker *, void *),
+				  void *data)
+{
+	struct io_worker *worker;
+	bool ret = false;
+
+	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
+		if (io_worker_get(worker)) {
+			/* no task if node is/was offline */
+			if (worker->task)
+				ret = func(worker, data);
+			io_worker_release(worker);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+static bool io_wq_worker_wake(struct io_worker *worker, void *data)
+{
+	wake_up_process(worker->task);
+	return false;
+}
+
 /*
  * Manager thread. Tasked with creating new workers, if we need them.
  */
 static int io_wq_manager(void *data)
 {
 	struct io_wq *wq = data;
-	int workers_to_create = num_possible_nodes();
 	int node;
 
 	/* create fixed workers */
-	refcount_set(&wq->refs, workers_to_create);
+	refcount_set(&wq->refs, 1);
 	for_each_node(node) {
 		if (!node_online(node))
 			continue;
-		if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
-			goto err;
-		workers_to_create--;
+		if (create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
+			continue;
+		set_bit(IO_WQ_BIT_ERROR, &wq->state);
+		set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		goto out;
 	}
 
-	while (workers_to_create--)
-		refcount_dec(&wq->refs);
-
 	complete(&wq->done);
 
 	while (!kthread_should_stop()) {
@@ -723,12 +758,12 @@ static int io_wq_manager(void *data)
 			if (!node_online(node))
 				continue;
 
-			spin_lock_irq(&wqe->lock);
+			raw_spin_lock_irq(&wqe->lock);
 			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
 				fork_worker[IO_WQ_ACCT_BOUND] = true;
 			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND))
 				fork_worker[IO_WQ_ACCT_UNBOUND] = true;
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 			if (fork_worker[IO_WQ_ACCT_BOUND])
 				create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND);
 			if (fork_worker[IO_WQ_ACCT_UNBOUND])
@@ -741,12 +776,18 @@ static int io_wq_manager(void *data)
 	if (current->task_works)
 		task_work_run();
 
-	return 0;
-err:
-	set_bit(IO_WQ_BIT_ERROR, &wq->state);
-	set_bit(IO_WQ_BIT_EXIT, &wq->state);
-	if (refcount_sub_and_test(workers_to_create, &wq->refs))
+out:
+	if (refcount_dec_and_test(&wq->refs)) {
 		complete(&wq->done);
+		return 0;
+	}
+	/* if ERROR is set and we get here, we have workers to wake */
+	if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) {
+		rcu_read_lock();
+		for_each_node(node)
+			io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
+		rcu_read_unlock();
+	}
 	return 0;
 }
 
@@ -825,10 +866,10 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 	}
 
 	work_flags = work->flags;
-	spin_lock_irqsave(&wqe->lock, flags);
+	raw_spin_lock_irqsave(&wqe->lock, flags);
 	io_wqe_insert_work(wqe, work);
 	wqe->flags &= ~IO_WQE_FLAG_STALLED;
-	spin_unlock_irqrestore(&wqe->lock, flags);
+	raw_spin_unlock_irqrestore(&wqe->lock, flags);
 
 	if ((work_flags & IO_WQ_WORK_CONCURRENT) ||
 	    !atomic_read(&acct->nr_running))
@@ -854,37 +895,6 @@ void io_wq_hash_work(struct io_wq_work *work, void *val)
 	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
 }
 
-static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
-{
-	send_sig(SIGINT, worker->task, 1);
-	return false;
-}
-
-/*
- * Iterate the passed in list and call the specific function for each
- * worker that isn't exiting
- */
-static bool io_wq_for_each_worker(struct io_wqe *wqe,
-				  bool (*func)(struct io_worker *, void *),
-				  void *data)
-{
-	struct io_worker *worker;
-	bool ret = false;
-
-	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
-		if (io_worker_get(worker)) {
-			/* no task if node is/was offline */
-			if (worker->task)
-				ret = func(worker, data);
-			io_worker_release(worker);
-			if (ret)
-				break;
-		}
-	}
-
-	return ret;
-}
-
 void io_wq_cancel_all(struct io_wq *wq)
 {
 	int node;
@@ -955,13 +965,13 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
 	unsigned long flags;
 
 retry:
-	spin_lock_irqsave(&wqe->lock, flags);
+	raw_spin_lock_irqsave(&wqe->lock, flags);
 	wq_list_for_each(node, prev, &wqe->work_list) {
 		work = container_of(node, struct io_wq_work, list);
 		if (!match->fn(work, match->data))
 			continue;
 		io_wqe_remove_pending(wqe, work, prev);
-		spin_unlock_irqrestore(&wqe->lock, flags);
+		raw_spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
 		match->nr_pending++;
 		if (!match->cancel_all)
@@ -970,7 +980,7 @@ retry:
 		/* not safe to continue after unlock */
 		goto retry;
 	}
-	spin_unlock_irqrestore(&wqe->lock, flags);
+	raw_spin_unlock_irqrestore(&wqe->lock, flags);
 }
 
 static void io_wqe_cancel_running_work(struct io_wqe *wqe,
@@ -1078,7 +1088,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 		}
 		atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
 		wqe->wq = wq;
-		spin_lock_init(&wqe->lock);
+		raw_spin_lock_init(&wqe->lock);
 		INIT_WQ_LIST(&wqe->work_list);
 		INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
 		INIT_LIST_HEAD(&wqe->all_list);
@@ -1117,12 +1127,6 @@ bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
 	return refcount_inc_not_zero(&wq->use_refs);
 }
 
-static bool io_wq_worker_wake(struct io_worker *worker, void *data)
-{
-	wake_up_process(worker->task);
-	return false;
-}
-
 static void __io_wq_destroy(struct io_wq *wq)
 {
 	int node;