Message-ID: <668d680cc7cfc_1c18c329414@willemb.c.googlers.com.notmuch>
Date: Tue, 09 Jul 2024 12:40:44 -0400
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: zijianzhang@...edance.com, 
 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: Re: [PATCH net-next v7 1/3] sock: support copying cmsgs to the user
 space in sendmsg

zijianzhang@ wrote:
> From: Zijian Zhang <zijianzhang@...edance.com>
> 
> Users can pass msg_control as a placeholder to recvmsg, and get some info
> from the kernel upon returning of it, but it's not available for sendmsg.
> Recvmsg uses put_cmsg to copy info back to the user, while ____sys_sendmsg
> creates a kernel copy of msg_control and passes that to the callees,
> put_cmsg in sendmsg path will write into this kernel buffer.
> 
> If users want to get info after returning of sendmsg, they typically have
> to call recvmsg on the ERRMSG_QUEUE of the socket, incurring extra system

nit: error queue or MSG_ERRQUEUE

> call overhead. This commit supports copying cmsg from the kernel space to
> the user space upon returning of sendmsg to mitigate this overhead.
>
> Signed-off-by: Zijian Zhang <zijianzhang@...edance.com>
> Signed-off-by: Xiaochun Lu <xiaochun.lu@...edance.com>

Overall this approach follows what I had in mind, thanks.

Looking forward to the discussion with a wider audience at netdevconf
next week.

> ---
>  include/linux/socket.h |  6 +++++
>  include/net/sock.h     |  2 +-
>  net/core/sock.c        |  6 +++--
>  net/ipv4/ip_sockglue.c |  2 +-
>  net/ipv6/datagram.c    |  2 +-
>  net/socket.c           | 54 ++++++++++++++++++++++++++++++++++++++----
>  6 files changed, 62 insertions(+), 10 deletions(-)
> 
> diff --git a/include/linux/socket.h b/include/linux/socket.h
> index 2a1ff91d1914..75461812a7a3 100644
> --- a/include/linux/socket.h
> +++ b/include/linux/socket.h
> @@ -71,6 +71,7 @@ struct msghdr {
>  		void __user	*msg_control_user;
>  	};
>  	bool		msg_control_is_user : 1;
> +	bool		msg_control_copy_to_user : 1;
>  	bool		msg_get_inq : 1;/* return INQ after receive */
>  	unsigned int	msg_flags;	/* flags on received message */
>  	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
> @@ -168,6 +169,11 @@ 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);
> diff --git a/include/net/sock.h b/include/net/sock.h
> index cce23ac4d514..9c728287d21d 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1804,7 +1804,7 @@ static inline void sockcm_init(struct sockcm_cookie *sockc,
>  	};
>  }
>  
> -int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
> +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
>  		     struct sockcm_cookie *sockc);
>  int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
>  		   struct sockcm_cookie *sockc);
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 9abc4fe25953..efb30668dac3 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -2826,7 +2826,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
>  }
>  EXPORT_SYMBOL(sock_alloc_send_pskb);
>  
> -int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
> +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
>  		     struct sockcm_cookie *sockc)
>  {
>  	u32 tsflags;
> @@ -2866,6 +2866,8 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
>  	default:
>  		return -EINVAL;
>  	}
> +	if (cmsg_copy_to_user(cmsg))
> +		msg->msg_control_copy_to_user = true;

This seems a bit roundabout.

Just have case SCM_ZC_NOTIFICATION set this bit directly?

>  	return 0;
>  }

> -static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
> -			   unsigned int flags, struct used_address *used_address,
> +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 int flags = msg_sys->msg_flags;
> +	struct msghdr msg_user = *msg_sys;
> +	unsigned long cmsg_ptr;
> +	struct cmsghdr *cmsg;
> +	int err;
> +
> +	msg_user.msg_control_is_user = true;
> +	msg_user.msg_control_user = umsg->msg_control;
> +	cmsg_ptr = (unsigned long)msg_user.msg_control;
> +	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,
>  			   unsigned int allowed_msghdr_flags)
>  {
>  	unsigned char ctl[sizeof(struct cmsghdr) + 20]
> @@ -2537,6 +2572,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
>  	ssize_t err;
>  
>  	err = -ENOBUFS;
> +	msg_sys->msg_control_copy_to_user = false;
>  
>  	if (msg_sys->msg_controllen > INT_MAX)
>  		goto out;
> @@ -2594,6 +2630,14 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
>  			       used_address->name_len);
>  	}
>  
> +	if (msg && msg_sys->msg_control_copy_to_user && err >= 0) {
> +		ssize_t len = err;
> +
> +		err = sendmsg_copy_cmsg_to_user(msg_sys, msg);
> +		if (!err)
> +			err = len;
> +	}
> +

The main issue is adding the above initialization and this branch in
the hot path, adding a minor cost to every other send call only for
this use case (and potentially tx timestamps eventually).

>  out_freectl:
>  	if (ctl_buf != ctl)
>  		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
> @@ -2636,8 +2680,8 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
>  	if (err < 0)
>  		return err;
>  
> -	err = ____sys_sendmsg(sock, msg_sys, flags, used_address,
> -				allowed_msghdr_flags);
> +	err = ____sys_sendmsg(sock, msg, msg_sys, flags, used_address,
> +			      allowed_msghdr_flags);

Does it make more sense to do the copy_to_user here, so as not to have to plumb
msg down to the callee?
>  	kfree(iov);
>  	return err;
>  }
> @@ -2648,7 +2692,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
>  long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg,
>  			unsigned int flags)
>  {
> -	return ____sys_sendmsg(sock, msg, flags, NULL, 0);
> +	return ____sys_sendmsg(sock, NULL, msg, flags, NULL, 0);
>  }
>  
>  long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
> -- 
> 2.20.1
> 

Powered by blists - more mailing lists