2022-07-07 12:03:34

by Pavel Begunkov

Subject: [PATCH net-next v4 22/27] io_uring: sendzc with fixed buffers

Allow zerocopy sends to use fixed buffers. There is an optimisation for
this case, the network layer don't need to reference the pages, see
SKBFL_MANAGED_FRAG_REFS, so io_uring have to ensure validity of fixed
buffers until the notifier is released.

Signed-off-by: Pavel Begunkov <[email protected]>
---
include/uapi/linux/io_uring.h | 6 +++++-
io_uring/net.c | 29 ++++++++++++++++++++++++-----
2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 25278c9ac6d2..8d050c247d6b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -269,9 +269,13 @@ enum io_uring_op {
* IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if
* the handler will continue to report
* CQEs on behalf of the same SQE.
+ *
+ * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in
+ * the buf_index field.
*/
#define IORING_RECVSEND_POLL_FIRST (1U << 0)
-#define IORING_RECV_MULTISHOT (1U << 1)
+#define IORING_RECV_MULTISHOT (1U << 1)
+#define IORING_RECVSEND_FIXED_BUF (1U << 2)

/*
* accept flags stored in sqe->ioprio
diff --git a/io_uring/net.c b/io_uring/net.c
index 2172cf3facd8..0259fbbad591 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -14,6 +14,7 @@
#include "kbuf.h"
#include "net.h"
#include "notif.h"
+#include "rsrc.h"

#if defined(CONFIG_NET)
struct io_shutdown {
@@ -667,13 +668,23 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_sendzc *zc = io_kiocb_to_cmd(req);
+ struct io_ring_ctx *ctx = req->ctx;

if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))
return -EINVAL;

zc->flags = READ_ONCE(sqe->ioprio);
- if (zc->flags & ~IORING_RECVSEND_POLL_FIRST)
+ if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF))
return -EINVAL;
+ if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
+ unsigned idx = READ_ONCE(sqe->buf_index);
+
+ if (unlikely(idx >= ctx->nr_user_bufs))
+ return -EFAULT;
+ idx = array_index_nospec(idx, ctx->nr_user_bufs);
+ req->imu = READ_ONCE(ctx->user_bufs[idx]);
+ io_req_set_rsrc_node(req, ctx, 0);
+ }

zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
zc->len = READ_ONCE(sqe->len);
@@ -727,10 +738,18 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
msg.msg_controllen = 0;
msg.msg_namelen = 0;

- ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter);
- if (unlikely(ret))
- return ret;
- mm_account_pinned_pages(&notif->uarg.mmp, zc->len);
+ if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
+ ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu,
+ (u64)zc->buf, zc->len);
+ if (unlikely(ret))
+ return ret;
+ } else {
+ ret = import_single_range(WRITE, zc->buf, zc->len, &iov,
+ &msg.msg_iter);
+ if (unlikely(ret))
+ return ret;
+ mm_account_pinned_pages(&notif->uarg.mmp, zc->len);
+ }

if (zc->addr) {
ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address);
--
2.36.1