Merge tag 'for-5.16/io_uring-2021-10-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Light on new features - basically just the hybrid mode support.

  Outside of that it's just fixes, cleanups, and performance
  improvements.

  In detail:

   - Add ring related information to the fdinfo output (Hao)

   - Hybrid async mode (Hao)

   - Support for batched issue on block (me)

   - sqe error trace improvement (me)

   - IOPOLL efficiency improvements (Pavel)

   - submit state cleanups and improvements (Pavel)

   - Completion side improvements (Pavel)

   - Drain improvements (Pavel)

   - Buffer selection cleanups (Pavel)

   - Fixed file node improvements (Pavel)

   - io-wq setup cancelation fix (Pavel)

   - Various other performance improvements and cleanups (Pavel)

   - Misc fixes (Arnd, Bixuan, Changcheng, Hao, me, Noah)"

* tag 'for-5.16/io_uring-2021-10-29' of git://git.kernel.dk/linux-block: (97 commits)
  io-wq: remove worker to owner tw dependency
  io_uring: harder fdinfo sq/cq ring iterating
  io_uring: don't assign write hint in the read path
  io_uring: clusterise ki_flags access in rw_prep
  io_uring: kill unused param from io_file_supports_nowait
  io_uring: clean up timeout async_data allocation
  io_uring: don't try io-wq polling if not supported
  io_uring: check if opcode needs poll first on arming
  io_uring: clean iowq submit work cancellation
  io_uring: clean io_wq_submit_work()'s main loop
  io-wq: use helper for worker refcounting
  io_uring: implement async hybrid mode for pollable requests
  io_uring: Use ERR_CAST() instead of ERR_PTR(PTR_ERR())
  io_uring: split logic of force_nonblock
  io_uring: warning about unused-but-set parameter
  io_uring: inform block layer of how many requests we are submitting
  io_uring: simplify io_file_supports_nowait()
  io_uring: combine REQ_F_NOWAIT_{READ,WRITE} flags
  io_uring: arm poll for non-nowait files
  fs/io_uring: Prioritise checking faster conditions first in io_write
  ...

1 files changed, 42 insertions, 16 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 422a7ed6a9bd..38b33ad9e8cf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker);
 static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
 					struct io_wqe_acct *acct,
 					struct io_cb_cancel_data *match);
+static void create_worker_cb(struct callback_head *cb);
 
 static bool io_worker_get(struct io_worker *worker)
 {
@@ -174,12 +175,46 @@ static void io_worker_ref_put(struct io_wq *wq)
 		complete(&wq->worker_done);
 }
 
+static void io_worker_cancel_cb(struct io_worker *worker)
+{
+	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
+	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
+
+	atomic_dec(&acct->nr_running);
+	raw_spin_lock(&worker->wqe->lock);
+	acct->nr_workers--;
+	raw_spin_unlock(&worker->wqe->lock);
+	io_worker_ref_put(wq);
+	clear_bit_unlock(0, &worker->create_state);
+	io_worker_release(worker);
+}
+
+static bool io_task_worker_match(struct callback_head *cb, void *data)
+{
+	struct io_worker *worker;
+
+	if (cb->func != create_worker_cb)
+		return false;
+	worker = container_of(cb, struct io_worker, create_work);
+	return worker == data;
+}
+
 static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
+	struct io_wq *wq = wqe->wq;
 
-	if (refcount_dec_and_test(&worker->ref))
-		complete(&worker->ref_done);
+	while (1) {
+		struct callback_head *cb = task_work_cancel_match(wq->task,
+						io_task_worker_match, worker);
+
+		if (!cb)
+			break;
+		io_worker_cancel_cb(worker);
+	}
+
+	io_worker_release(worker);
 	wait_for_completion(&worker->ref_done);
 
 	raw_spin_lock(&wqe->lock);
@@ -323,8 +358,10 @@ static bool io_queue_worker_create(struct io_worker *worker,
 
 	init_task_work(&worker->create_work, func);
 	worker->create_index = acct->index;
-	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL))
+	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
+		clear_bit_unlock(0, &worker->create_state);
 		return true;
+	}
 	clear_bit_unlock(0, &worker->create_state);
 fail_release:
 	io_worker_release(worker);
@@ -716,11 +753,8 @@ static void io_workqueue_create(struct work_struct *work)
 	struct io_worker *worker = container_of(work, struct io_worker, work);
 	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
 
-	if (!io_queue_worker_create(worker, acct, create_worker_cont)) {
-		clear_bit_unlock(0, &worker->create_state);
-		io_worker_release(worker);
+	if (!io_queue_worker_create(worker, acct, create_worker_cont))
 		kfree(worker);
-	}
 }
 
 static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
@@ -1150,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq)
 
 	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
 		struct io_worker *worker;
-		struct io_wqe_acct *acct;
 
 		worker = container_of(cb, struct io_worker, create_work);
-		acct = io_wqe_get_acct(worker);
-		atomic_dec(&acct->nr_running);
-		raw_spin_lock(&worker->wqe->lock);
-		acct->nr_workers--;
-		raw_spin_unlock(&worker->wqe->lock);
-		io_worker_ref_put(wq);
-		clear_bit_unlock(0, &worker->create_state);
-		io_worker_release(worker);
+		io_worker_cancel_cb(worker);
 	}
 
 	rcu_read_lock();