io_uring: correctly handle non ->{read,write}_iter() file_operations

Currently we just -EINVAL a read or write to an fd that isn't backed
by ->read_iter() or ->write_iter(). But we can handle them just fine,
as long as we punt fo async context first.

Implement a simple loop function for doing ->read() or ->write()
instead, and ensure we call it appropriately.

Reported-by: 李通洲 <carter.li@eoitek.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 9d8e703..ca7570a 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1298,6 +1298,51 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
        }
 }
 
+/*
+ * For files that don't have ->read_iter() and ->write_iter(), handle them
+ * by looping over ->read() or ->write() manually.
+ */
+static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
+                          struct iov_iter *iter)
+{
+       ssize_t ret = 0;
+
+       /*
+        * Don't support polled IO through this interface, and we can't
+        * support non-blocking either. For the latter, this just causes
+        * the kiocb to be handled from an async context.
+        */
+       if (kiocb->ki_flags & IOCB_HIPRI)
+               return -EOPNOTSUPP;
+       if (kiocb->ki_flags & IOCB_NOWAIT)
+               return -EAGAIN;
+
+       while (iov_iter_count(iter)) {
+               struct iovec iovec = iov_iter_iovec(iter);
+               ssize_t nr;
+
+               if (rw == READ) {
+                       nr = file->f_op->read(file, iovec.iov_base,
+                                             iovec.iov_len, &kiocb->ki_pos);
+               } else {
+                       nr = file->f_op->write(file, iovec.iov_base,
+                                              iovec.iov_len, &kiocb->ki_pos);
+               }
+
+               if (nr < 0) {
+                       if (!ret)
+                               ret = nr;
+                       break;
+               }
+               ret += nr;
+               if (nr != iovec.iov_len)
+                       break;
+               iov_iter_advance(iter, nr);
+       }
+
+       return ret;
+}
+
 static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
                   bool force_nonblock)
 {
@@ -1315,8 +1360,6 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 
        if (unlikely(!(file->f_mode & FMODE_READ)))
                return -EBADF;
-       if (unlikely(!file->f_op->read_iter))
-               return -EINVAL;
 
        ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
        if (ret < 0)
@@ -1331,7 +1374,11 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
        if (!ret) {
                ssize_t ret2;
 
-               ret2 = call_read_iter(file, kiocb, &iter);
+               if (file->f_op->read_iter)
+                       ret2 = call_read_iter(file, kiocb, &iter);
+               else
+                       ret2 = loop_rw_iter(READ, file, kiocb, &iter);
+
                /*
                 * In case of a short read, punt to async. This can happen
                 * if we have data partially cached. Alternatively we can
@@ -1376,8 +1423,6 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
        file = kiocb->ki_filp;
        if (unlikely(!(file->f_mode & FMODE_WRITE)))
                return -EBADF;
-       if (unlikely(!file->f_op->write_iter))
-               return -EINVAL;
 
        ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
        if (ret < 0)
@@ -1415,7 +1460,10 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
                }
                kiocb->ki_flags |= IOCB_WRITE;
 
-               ret2 = call_write_iter(file, kiocb, &iter);
+               if (file->f_op->write_iter)
+                       ret2 = call_write_iter(file, kiocb, &iter);
+               else
+                       ret2 = loop_rw_iter(WRITE, file, kiocb, &iter);
                if (!force_nonblock || ret2 != -EAGAIN) {
                        io_rw_done(kiocb, ret2);
                } else {