[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240626193403.3854451-3-zijianzhang@bytedance.com>
Date: Wed, 26 Jun 2024 19:34:01 +0000
From: zijianzhang@...edance.com
To: netdev@...r.kernel.org
Cc: edumazet@...gle.com,
willemdebruijn.kernel@...il.com,
cong.wang@...edance.com,
xiaochun.lu@...edance.com,
Zijian Zhang <zijianzhang@...edance.com>
Subject: [PATCH net-next v6 2/4] sock: support copy cmsg to userspace in TX path
From: Zijian Zhang <zijianzhang@...edance.com>
Since ____sys_sendmsg creates a kernel copy of msg_control and passes
that to the callees, put_cmsg will write into this kernel buffer. If
people want to piggyback some information like timestamps upon returning
of sendmsg. ____sys_sendmsg will have to copy_to_user to the original buf,
which is not supported. As a result, users typically have to call recvmsg
on the ERRMSG_QUEUE of the socket, incurring extra system call overhead.
This commit supports copying cmsg to userspace in TX path by introducing
a flag MSG_CMSG_COPY_TO_USER in struct msghdr to guide the copy logic
upon returning of ___sys_sendmsg.
Signed-off-by: Zijian Zhang <zijianzhang@...edance.com>
Signed-off-by: Xiaochun Lu <xiaochun.lu@...edance.com>
---
include/linux/socket.h | 6 ++++++
net/core/sock.c | 2 ++
net/ipv4/ip_sockglue.c | 2 ++
net/ipv6/datagram.c | 3 +++
net/socket.c | 45 ++++++++++++++++++++++++++++++++++++++++++
5 files changed, 58 insertions(+)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 89d16b90370b..35adc30c9db6 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -168,6 +168,11 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr
return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
}
+static inline bool cmsg_copy_to_user(struct cmsghdr *__cmsg)
+{
+ return 0;
+}
+
static inline size_t msg_data_left(struct msghdr *msg)
{
return iov_iter_count(&msg->msg_iter);
@@ -329,6 +334,7 @@ struct ucred {
#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_CMSG_COPY_TO_USER 0x10000000 /* Copy cmsg to user space */
#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/core/sock.c b/net/core/sock.c
index 9abc4fe25953..4a766a91ff5c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2879,6 +2879,8 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
+ if (cmsg_copy_to_user(cmsg))
+ msg->msg_flags |= MSG_CMSG_COPY_TO_USER;
if (cmsg->cmsg_level != SOL_SOCKET)
continue;
ret = __sock_cmsg_send(sk, cmsg, sockc);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cf377377b52d..464d08b27fa8 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
+ if (cmsg_copy_to_user(cmsg))
+ msg->msg_flags |= MSG_CMSG_COPY_TO_USER;
#if IS_ENABLED(CONFIG_IPV6)
if (allow_ipv6 &&
cmsg->cmsg_level == SOL_IPV6 &&
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fff78496803d..b0341faf7f83 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -776,6 +776,9 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
goto exit_f;
}
+ if (cmsg_copy_to_user(cmsg))
+ msg->msg_flags |= MSG_CMSG_COPY_TO_USER;
+
if (cmsg->cmsg_level == SOL_SOCKET) {
err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
if (err)
diff --git a/net/socket.c b/net/socket.c
index e416920e9399..6523cf5a7f32 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2621,6 +2621,39 @@ static int sendmsg_copy_msghdr(struct msghdr *msg,
return 0;
}
+static int sendmsg_copy_cmsg_to_user(struct msghdr *msg_sys,
+ struct user_msghdr __user *umsg)
+{
+ struct compat_msghdr __user *umsg_compat =
+ (struct compat_msghdr __user *)umsg;
+ unsigned long cmsg_ptr = (unsigned long)umsg->msg_control;
+ unsigned int flags = msg_sys->msg_flags;
+ struct msghdr msg_user = *msg_sys;
+ struct cmsghdr *cmsg;
+ int err;
+
+ msg_user.msg_control = umsg->msg_control;
+ msg_user.msg_control_is_user = true;
+ for_each_cmsghdr(cmsg, msg_sys) {
+ if (!CMSG_OK(msg_sys, cmsg))
+ break;
+ if (cmsg_copy_to_user(cmsg))
+ put_cmsg(&msg_user, cmsg->cmsg_level, cmsg->cmsg_type,
+ cmsg->cmsg_len - sizeof(*cmsg), CMSG_DATA(cmsg));
+ }
+
+ err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(umsg));
+ if (err)
+ return err;
+ if (MSG_CMSG_COMPAT & flags)
+ err = __put_user((unsigned long)msg_user.msg_control - cmsg_ptr,
+ &umsg_compat->msg_controllen);
+ else
+ err = __put_user((unsigned long)msg_user.msg_control - cmsg_ptr,
+ &umsg->msg_controllen);
+ return err;
+}
+
static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
struct used_address *used_address,
@@ -2638,6 +2671,18 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
err = ____sys_sendmsg(sock, msg_sys, flags, used_address,
allowed_msghdr_flags);
+ if (err < 0)
+ goto out;
+
+ if (msg_sys->msg_flags & MSG_CMSG_COPY_TO_USER) {
+ ssize_t len = err;
+
+ err = sendmsg_copy_cmsg_to_user(msg_sys, msg);
+ if (err)
+ goto out;
+ err = len;
+ }
+out:
kfree(iov);
return err;
}
--
2.20.1
Powered by blists - more mailing lists