Merge tag 'io_uring-5.9-2020-09-22' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "A few fixes - most of them regression fixes from this cycle, but also
  a few stable heading fixes, and a build fix for the included demo tool
  since some systems now actually have gettid() available"

* tag 'io_uring-5.9-2020-09-22' of git://git.kernel.dk/linux-block:
  io_uring: fix openat/openat2 unified prep handling
  io_uring: mark statx/files_update/epoll_ctl as non-SQPOLL
  tools/io_uring: fix compile breakage
  io_uring: don't use retry based buffered reads for non-async bdev
  io_uring: don't re-setup vecs/iter in io_resumit_prep() is already there
  io_uring: don't run task work on an exiting task
  io_uring: drop 'ctx' ref on task work cancelation
  io_uring: grab any needed state during defer prep

1 files changed, 38 insertions, 11 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3790c7fe9fee..8b426aa29668 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1753,6 +1753,9 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb,
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret, notify;
 
+	if (tsk->flags & PF_EXITING)
+		return -ESRCH;
+
 	/*
 	 * SQPOLL kernel thread doesn't need notification, just a wakeup. For
 	 * all other cases, use TWA_SIGNAL unconditionally to ensure we're
@@ -1787,8 +1790,10 @@ static void __io_req_task_cancel(struct io_kiocb *req, int error)
 static void io_req_task_cancel(struct callback_head *cb)
 {
 	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+	struct io_ring_ctx *ctx = req->ctx;
 
 	__io_req_task_cancel(req, -ECANCELED);
+	percpu_ref_put(&ctx->refs);
 }
 
 static void __io_req_task_submit(struct io_kiocb *req)
@@ -2010,6 +2015,12 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
 
 static inline bool io_run_task_work(void)
 {
+	/*
+	 * Not safe to run on exiting task, and the task_work handling will
+	 * not add work to such a task.
+	 */
+	if (unlikely(current->flags & PF_EXITING))
+		return false;
 	if (current->task_works) {
 		__set_current_state(TASK_RUNNING);
 		task_work_run();
@@ -2283,13 +2294,17 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error)
 		goto end_req;
 	}
 
-	ret = io_import_iovec(rw, req, &iovec, &iter, false);
-	if (ret < 0)
-		goto end_req;
-	ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
-	if (!ret)
+	if (!req->io) {
+		ret = io_import_iovec(rw, req, &iovec, &iter, false);
+		if (ret < 0)
+			goto end_req;
+		ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
+		if (!ret)
+			return true;
+		kfree(iovec);
+	} else {
 		return true;
-	kfree(iovec);
+	}
 end_req:
 	req_set_fail_links(req);
 	io_req_complete(req, ret);
@@ -3115,6 +3130,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	struct iov_iter __iter, *iter = &__iter;
 	ssize_t io_size, ret, ret2;
 	size_t iov_count;
+	bool no_async;
 
 	if (req->io)
 		iter = &req->io->rw.iter;
@@ -3132,7 +3148,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 		kiocb->ki_flags &= ~IOCB_NOWAIT;
 
 	/* If the file doesn't support async, just async punt */
-	if (force_nonblock && !io_file_supports_async(req->file, READ))
+	no_async = force_nonblock && !io_file_supports_async(req->file, READ);
+	if (no_async)
 		goto copy_iov;
 
 	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count);
@@ -3176,6 +3193,8 @@ copy_iov:
 		ret = ret2;
 		goto out_free;
 	}
+	if (no_async)
+		return -EAGAIN;
 	/* it's copied and will be cleaned with ->io */
 	iovec = NULL;
 	/* now use our persistent iterator, if we aren't already */
@@ -3508,8 +3527,6 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	const char __user *fname;
 	int ret;
 
-	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
-		return -EINVAL;
 	if (unlikely(sqe->ioprio || sqe->buf_index))
 		return -EINVAL;
 	if (unlikely(req->flags & REQ_F_FIXED_FILE))
@@ -3536,6 +3553,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	u64 flags, mode;
 
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 	mode = READ_ONCE(sqe->len);
@@ -3550,6 +3569,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	size_t len;
 	int ret;
 
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
@@ -3767,7 +3788,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req,
 #if defined(CONFIG_EPOLL)
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL)))
 		return -EINVAL;
 
 	req->epoll.epfd = READ_ONCE(sqe->fd);
@@ -3882,7 +3903,7 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
 
 static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL)))
 		return -EINVAL;
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
@@ -5399,6 +5420,8 @@ static int io_async_cancel(struct io_kiocb *req)
 static int io_files_update_prep(struct io_kiocb *req,
 				const struct io_uring_sqe *sqe)
 {
+	if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL))
+		return -EINVAL;
 	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
 		return -EINVAL;
 	if (sqe->ioprio || sqe->rw_flags)
@@ -5449,6 +5472,8 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	if (unlikely(ret))
 		return ret;
 
+	io_prep_async_work(req);
+
 	switch (req->opcode) {
 	case IORING_OP_NOP:
 		break;
@@ -8180,6 +8205,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		/* cancel this request, or head link requests */
 		io_attempt_cancel(ctx, cancel_req);
 		io_put_req(cancel_req);
+		/* cancellations _may_ trigger task work */
+		io_run_task_work();
 		schedule();
 		finish_wait(&ctx->inflight_wait, &wait);
 	}