In the tcp sendmsg handler, permit a write in LISTENING state if
a MSG_PRELOAD flag is used. Copy from iovec to a linear sk_buff
for placement on the socket write queue.
Signed-off-by: Jeremy Harris <jgh@xxxxxxxx>
---
include/linux/socket.h | 1 +
net/ipv4/tcp.c | 17 +++++++++++++----
tools/perf/trace/beauty/include/linux/socket.h | 1 +
tools/perf/trace/beauty/msg_flags.c | 3 +++
4 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 3b262487ec06..b41f4cd4dc97 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -330,6 +330,7 @@ struct ucred {
#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */
#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */
#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */
+#define MSG_PRELOAD 0x10000000 /* Preload tx data while listening */
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
#define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file
descriptor received through
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b7b6ab41b496..72b5d7cad351 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1136,12 +1136,13 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
tcp_rate_check_app_limited(sk); /* is sending application-limited? */
- /* Wait for a connection to finish. One exception is TCP Fast Open
+ /* Wait for a connection to finish. Exceptions are TCP Fast Open
* (passive side) where data is allowed to be sent before a connection
- * is fully established.
+ * is fully established, and a message marked as preload which is
+ * allowed to be placed in the send queue of a listening socket.
*/
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
- !tcp_passive_fastopen(sk)) {
+ !tcp_passive_fastopen(sk) && !(flags & MSG_PRELOAD)) {
err = sk_stream_wait_connect(sk, &timeo);
if (err != 0)
goto do_error;
@@ -1226,7 +1227,13 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
if (copy > msg_data_left(msg))
copy = msg_data_left(msg);
- if (zc == 0) {
+ if (unlikely(flags & MSG_PRELOAD)) {
+ copy = min_t(int, copy, skb_tailroom(skb));
+ err = skb_add_data_nocache(sk, skb, &msg->msg_iter,
+ copy);
+ if (err)
+ goto do_error;
+ } else if (zc == 0) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
@@ -1330,6 +1337,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
if (!msg_data_left(msg)) {
if (unlikely(flags & MSG_EOR))
TCP_SKB_CB(skb)->eor = 1;
+ if (unlikely(flags & MSG_PRELOAD))
+ goto out_nopush;
goto out;
}
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index c3322eb3d686..e9ea498169f3 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -330,6 +330,7 @@ struct ucred {
#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */
#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */
#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */
+#define MSG_PRELOAD 0x10000000 /* Preload tx data while listening */
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
#define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file
descriptor received through
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index 2da581ff0c80..27e40da9b02d 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -20,6 +20,9 @@
#ifndef MSG_SPLICE_PAGES
#define MSG_SPLICE_PAGES 0x8000000
#endif
+#ifndef MSG_PRELOAD
+#define MSG_PRELOAD 0x10000000
+#endif
#ifndef MSG_FASTOPEN
#define MSG_FASTOPEN 0x20000000
#endif
--
2.49.0
