Merge tag 'io_uring-5.8-2020-06-19' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:

 - Catch a case where io_sq_thread() didn't do proper mm acquire

 - Ensure poll completions are reaped on shutdown

 - Async cancelation and run fixes (Pavel)

 - io-poll race fixes (Xiaoguang)

 - Request cleanup race fix (Xiaoguang)

* tag 'io_uring-5.8-2020-06-19' of git://git.kernel.dk/linux-block:
  io_uring: fix possible race condition against REQ_F_NEED_CLEANUP
  io_uring: reap poll completions while waiting for refs to drop on exit
  io_uring: acquire 'mm' for task_work for SQPOLL
  io_uring: add memory barrier to synchronize io_kiocb's result and iopoll_completed
  io_uring: don't fail links for EAGAIN error in IOPOLL mode
  io_uring: cancel by ->task not pid
  io_uring: lazy get task
  io_uring: batch cancel in io_uring_cancel_files()
  io_uring: cancel all task's requests on exit
  io-wq: add an option to cancel all matched reqs
  io-wq: reorder cancellation pending -> running
  io_uring: fix lazy work init

fs/io-wq.c

@@ -903,13 +903,15 @@ void io_wq_cancel_all(struct io_wq *wq)
 struct io_cb_cancel_data {
 	work_cancel_fn *fn;
 	void *data;
+	int nr_running;
+	int nr_pending;
+	bool cancel_all;
 };
 
 static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 {
 	struct io_cb_cancel_data *match = data;
 	unsigned long flags;
-	bool ret = false;
 
 	/*
 	 * Hold the lock to avoid ->cur_work going out of scope, caller
@@ -920,74 +922,90 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
 	    match->fn(worker->cur_work, match->data)) {
 		send_sig(SIGINT, worker->task, 1);
-		ret = true;
+		match->nr_running++;
 	}
 	spin_unlock_irqrestore(&worker->lock, flags);
 
-	return ret;
+	return match->nr_running && !match->cancel_all;
 }
 
-static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
-					    struct io_cb_cancel_data *match)
+static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
+				       struct io_cb_cancel_data *match)
 {
 	struct io_wq_work_node *node, *prev;
 	struct io_wq_work *work;
 	unsigned long flags;
-	bool found = false;
 
-	/*
-	 * First check pending list, if we're lucky we can just remove it
-	 * from there. CANCEL_OK means that the work is returned as-new,
-	 * no completion will be posted for it.
-	 */
+retry:
 	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;
 
-		if (match->fn(work, match->data)) {
-			wq_list_del(&wqe->work_list, node, prev);
-			found = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&wqe->lock, flags);
-
-	if (found) {
+		wq_list_del(&wqe->work_list, node, prev);
+		spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
-		return IO_WQ_CANCEL_OK;
+		match->nr_pending++;
+		if (!match->cancel_all)
+			return;
+
+		/* not safe to continue after unlock */
+		goto retry;
 	}
+	spin_unlock_irqrestore(&wqe->lock, flags);
+}
 
-	/*
-	 * Now check if a free (going busy) or busy worker has the work
-	 * currently running. If we find it there, we'll return CANCEL_RUNNING
-	 * as an indication that we attempt to signal cancellation. The
-	 * completion will run normally in this case.
-	 */
+static void io_wqe_cancel_running_work(struct io_wqe *wqe,
+				       struct io_cb_cancel_data *match)
+{
 	rcu_read_lock();
-	found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
+	io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
 	rcu_read_unlock();
-	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
 }
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
-				  void *data)
+				  void *data, bool cancel_all)
 {
 	struct io_cb_cancel_data match = {
-		.fn	= cancel,
-		.data	= data,
+		.fn		= cancel,
+		.data		= data,
+		.cancel_all	= cancel_all,
 	};
-	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
 	int node;
 
+	/*
+	 * First check pending list, if we're lucky we can just remove it
+	 * from there. CANCEL_OK means that the work is returned as-new,
+	 * no completion will be posted for it.
+	 */
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
-		ret = io_wqe_cancel_work(wqe, &match);
-		if (ret != IO_WQ_CANCEL_NOTFOUND)
-			break;
+		io_wqe_cancel_pending_work(wqe, &match);
+		if (match.nr_pending && !match.cancel_all)
+			return IO_WQ_CANCEL_OK;
 	}
 
-	return ret;
+	/*
+	 * Now check if a free (going busy) or busy worker has the work
+	 * currently running. If we find it there, we'll return CANCEL_RUNNING
+	 * as an indication that we attempt to signal cancellation. The
+	 * completion will run normally in this case.
+	 */
+	for_each_node(node) {
+		struct io_wqe *wqe = wq->wqes[node];
+
+		io_wqe_cancel_running_work(wqe, &match);
+		if (match.nr_running && !match.cancel_all)
+			return IO_WQ_CANCEL_RUNNING;
+	}
+
+	if (match.nr_running)
+		return IO_WQ_CANCEL_RUNNING;
+	if (match.nr_pending)
+		return IO_WQ_CANCEL_OK;
+	return IO_WQ_CANCEL_NOTFOUND;
 }
 
 static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
@@ -997,21 +1015,7 @@ static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
 
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
 {
-	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork);
-}
-
-static bool io_wq_pid_match(struct io_wq_work *work, void *data)
-{
-	pid_t pid = (pid_t) (unsigned long) data;
-
-	return work->task_pid == pid;
-}
-
-enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
-{
-	void *data = (void *) (unsigned long) pid;
-
-	return io_wq_cancel_cb(wq, io_wq_pid_match, data);
+	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork, false);
 }
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)

fs/io-wq.h

@@ -90,7 +90,6 @@ struct io_wq_work {
 	const struct cred *creds;
 	struct fs_struct *fs;
 	unsigned flags;
-	pid_t task_pid;
 };
 
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
@@ -125,12 +124,11 @@ static inline bool io_wq_is_hashed(struct io_wq_work *work)
 
 void io_wq_cancel_all(struct io_wq *wq);
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
-enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid);
 
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
-					void *data);
+					void *data, bool cancel_all);
 
 struct task_struct *io_wq_get_task(struct io_wq *wq);