From c599edd991fe089d1aa5f43b9a8e5b4dd2e04971 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 15 May 2019 13:53:07 -0600 Subject: [PATCH 0609/2944] io_uring: punt short reads to async context commit 9d93a3f5a0c0d0f79aebc597d47c7cedc852aeb5 upstream. We can encounter a short read when we're doing buffered reads and the data is partially cached. Right now we just return the short read, but that forces the application to read that CQE, then issue another SQE to finish the read. That read will not be cached, and hence will result in an async punt. It's more efficient to do that async punt from within the kernel, as that will the not need two round trips more to the kernel. Signed-off-by: Jens Axboe Signed-off-by: Joseph Qi Reviewed-by: Xiaoguang Wang --- fs/io_uring.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2a9d972..fc2101f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1089,7 +1089,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, struct iov_iter iter; struct file *file; size_t iov_count; - ssize_t ret; + ssize_t read_size, ret; ret = io_prep_rw(req, s, force_nonblock); if (ret) @@ -1105,13 +1105,24 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (ret < 0) return ret; + read_size = ret; iov_count = iov_iter_count(&iter); ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; - /* Catch -EAGAIN return for forced non-blocking submission */ ret2 = call_read_iter(file, kiocb, &iter); + /* + * In case of a short read, punt to async. This can happen + * if we have data partially cached. Alternatively we can + * return the short read, in which case the application will + * need to issue another SQE and wait for it. That SQE will + * need async punt anyway, so it's more efficient to do it + * here. + */ + if (force_nonblock && ret2 > 0 && ret2 < read_size) + ret2 = -EAGAIN; + /* Catch -EAGAIN return for forced non-blocking submission */ if (!force_nonblock || ret2 != -EAGAIN) { io_rw_done(kiocb, ret2); } else { -- 1.8.3.1