[PATCH V4 6/8] io_uring: switch to kernel_worker

[Mike Christie <michael.christie@oracle.com>]

Convert io_uring and io-wq to use kernel_worker.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
---

Note: To avoid patch application conflicts this patch was made over
linux-next which has Jens Axboe's block tree's for-next branch and Paul
Moore's selinux tree's next branch because:

commit: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit
support to io_uring")

from Paul's tree had conflicts.

 fs/io-wq.c                 | 15 ++++++++-------
 fs/io_uring.c              | 11 +++++------
 include/linux/sched/task.h |  1 -
 3 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 962952951126..32b140754496 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -70,6 +70,9 @@ struct io_worker {
 
 #define IO_WQ_NR_HASH_BUCKETS	(1u << IO_WQ_HASH_ORDER)
 
+#define IO_WQ_CLONE_FLAGS	(CLONE_FS | CLONE_FILES | CLONE_SIGHAND | \
+				 CLONE_THREAD | CLONE_IO)
+
 struct io_wqe_acct {
 	unsigned nr_workers;
 	unsigned max_workers;
@@ -550,13 +553,9 @@ static int io_wqe_worker(void *data)
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
 	bool last_timeout = false;
-	char buf[TASK_COMM_LEN];
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 
-	snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid);
-	set_task_comm(current, buf);
-
 	audit_alloc_kernel(current);
 
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
@@ -654,7 +653,7 @@ static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker,
 	list_add_tail_rcu(&worker->all_list, &wqe->all_list);
 	worker->flags |= IO_WORKER_F_FREE;
 	raw_spin_unlock(&wqe->lock);
-	wake_up_new_task(tsk);
+	kernel_worker_start(tsk, "iou-wrk-%d", wqe->wq->task->pid);
 }
 
 static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
@@ -684,7 +683,8 @@ static void create_worker_cont(struct callback_head *cb)
 	worker = container_of(cb, struct io_worker, create_work);
 	clear_bit_unlock(0, &worker->create_state);
 	wqe = worker->wqe;
-	tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
+	tsk = kernel_worker(io_wqe_worker, worker, wqe->node,
+			    IO_WQ_CLONE_FLAGS, KERN_WORKER_IO);
 	if (!IS_ERR(tsk)) {
 		io_init_new_worker(wqe, worker, tsk);
 		io_worker_release(worker);
@@ -754,7 +754,8 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 	if (index == IO_WQ_ACCT_BOUND)
 		worker->flags |= IO_WORKER_F_BOUND;
 
-	tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
+	tsk = kernel_worker(io_wqe_worker, worker, wqe->node, IO_WQ_CLONE_FLAGS,
+			    KERN_WORKER_IO);
 	if (!IS_ERR(tsk)) {
 		io_init_new_worker(wqe, worker, tsk);
 	} else if (!io_should_retry_thread(PTR_ERR(tsk))) {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 488aa14da287..5e21ae6d4ff4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7440,12 +7440,8 @@ static int io_sq_thread(void *data)
 	struct io_sq_data *sqd = data;
 	struct io_ring_ctx *ctx;
 	unsigned long timeout = 0;
-	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
 
-	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
-	set_task_comm(current, buf);
-
 	if (sqd->sq_cpu != -1)
 		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
 	else
@@ -8669,6 +8665,8 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 		fdput(f);
 	}
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		unsigned long flags = CLONE_FS | CLONE_FILES | CLONE_SIGHAND |
+					CLONE_THREAD | CLONE_IO;
 		struct task_struct *tsk;
 		struct io_sq_data *sqd;
 		bool attached;
@@ -8710,7 +8708,8 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 
 		sqd->task_pid = current->pid;
 		sqd->task_tgid = current->tgid;
-		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
+		tsk = kernel_worker(io_sq_thread, sqd, NUMA_NO_NODE,
+				    flags, KERN_WORKER_IO);
 		if (IS_ERR(tsk)) {
 			ret = PTR_ERR(tsk);
 			goto err_sqpoll;
@@ -8718,7 +8717,7 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
 
 		sqd->thread = tsk;
 		ret = io_uring_alloc_task_context(tsk, ctx);
-		wake_up_new_task(tsk);
+		kernel_worker_start(tsk, "iou-sqp-%d", sqd->task_pid);
 		if (ret)
 			goto err;
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 2bfc0629c868..c8ab90e28f11 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -88,7 +88,6 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
-struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *kernel_worker(int (*fn)(void *), void *arg, int node,
 				  unsigned long clone_flags, u32 worker_flags);
 __printf(2, 3)
-- 
2.25.1