[net-next,v7,1/3] sock: support copying cmsgs to the user space in sendmsg

Commit Message

Zijian Zhang July 8, 2024, 9:04 p.m. UTC

From: Zijian Zhang <[e-mail]>

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
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 <[e-mail]>
Signed-off-by: Xiaochun Lu <[e-mail]>
---
 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(-)

Comments

Simon Horman July 9, 2024, 9:14 a.m. UTC | #1

+ Dave Miller, Jakub Kicinski, Paolo Abeni, David Ahern, and Jens Axboe

  Please generate the CC list Networking for patches using
  get_maintainer.pl --git-min-percent=25 this.patch
  but omitting LKML.


On Mon, Jul 08, 2024 at 09:04:03PM +0000, [e-mail] wrote:
> From: Zijian Zhang <[e-mail]>
> 
> 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
> 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 <[e-mail]>
> Signed-off-by: Xiaochun Lu <[e-mail]>

...

> diff --git a/net/socket.c b/net/socket.c
> index e416920e9399..6a9c9e24d781 100644
> --- a/net/socket.c
> +++ b/net/socket.c
> @@ -2525,8 +2525,43 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
>  	return err < 0 ? err : 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;

nit: Sparse seems unhappy about the use of a __user pointer here.

     net/socket.c:2540:37: warning: dereference of noderef expression

> +	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));

nit: The line above could be trivially line-wrapped so that it is
     no more than 80 columns wide, as is still preferred in Networking code.

     Flagged by: checkpatch.pl --max-line-length=80

> +	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;
> +}

...

Willem de Bruijn July 9, 2024, 4:40 p.m. UTC | #2

zijianzhang@ wrote:
> From: Zijian Zhang <[e-mail]>
> 
> 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 <[e-mail]>
> Signed-off-by: Xiaochun Lu <[e-mail]>

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
>

Zijian Zhang July 9, 2024, 5:17 p.m. UTC | #3

On 7/9/24 2:14 AM, Simon Horman wrote:
> + Dave Miller, Jakub Kicinski, Paolo Abeni, David Ahern, and Jens Axboe
> 
>    Please generate the CC list Networking for patches using
>    get_maintainer.pl --git-min-percent=25 this.patch
>    but omitting LKML.
> 
> 
> On Mon, Jul 08, 2024 at 09:04:03PM +0000, [e-mail] wrote:
>> From: Zijian Zhang <[e-mail]>
>>
>> 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
>> 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 <[e-mail]>
>> Signed-off-by: Xiaochun Lu <[e-mail]>
> 
> ...
> 
>> diff --git a/net/socket.c b/net/socket.c
>> index e416920e9399..6a9c9e24d781 100644
>> --- a/net/socket.c
>> +++ b/net/socket.c
>> @@ -2525,8 +2525,43 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
>>   	return err < 0 ? err : 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;
> 
> nit: Sparse seems unhappy about the use of a __user pointer here.
> 
>       net/socket.c:2540:37: warning: dereference of noderef expression
> 
>> +	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));
> 
> nit: The line above could be trivially line-wrapped so that it is
>       no more than 80 columns wide, as is still preferred in Networking code.
> 
>       Flagged by: checkpatch.pl --max-line-length=80
> 
>> +	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;
>> +}
> 
> ...

Thanks for the suggestions, will update in the next version.

Zijian Zhang July 9, 2024, 5:42 p.m. UTC | #4

On 7/9/24 9:40 AM, Willem de Bruijn wrote:
> zijianzhang@ wrote:
>> From: Zijian Zhang <[e-mail]>
>>
>> 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 <[e-mail]>
>> Signed-off-by: Xiaochun Lu <[e-mail]>
> 
> Overall this approach follows what I had in mind, thanks.
> 
> Looking forward to the discussion with a wider audience at netdevconf
> next week.
> 

No problem, see you 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?

If I directly set this bit in SCM_ZC_... and delete this if code block,
I may have to add "msg" argument to __sock_cmsg_send in the second
commit, because if I still keep it in this commit, there will be an
"unused argument" warning.

However, I think the change to __sock_cmsg_send function declaration is
generic, so I would like to make it in the first commit, but it is truly
a bit roundabout. Not sure which way is better?

>>   	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?

I did this in the previous patchset. The problem is that the msg_control
of msg_sys is either a stack pointer or kmalloc-ed pointer (in
____sys_sendmsg), after returning of it, the msg_control of msg_sys is
either invalid or freed. I may have to do the copy_to_user at the end of
____sys_sendmsg.

>>   	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
>>
> 
>

Willem de Bruijn July 9, 2024, 9:30 p.m. UTC | #5

Zijian Zhang wrote:
> On 7/9/24 9:40 AM, Willem de Bruijn wrote:
> > zijianzhang@ wrote:
> >> From: Zijian Zhang <[e-mail]>
> >>
> >> 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 <[e-mail]>
> >> Signed-off-by: Xiaochun Lu <[e-mail]>
> > 
> > Overall this approach follows what I had in mind, thanks.
> > 
> > Looking forward to the discussion with a wider audience at netdevconf
> > next week.
> > 
> 
> No problem, see you 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?
> 
> If I directly set this bit in SCM_ZC_... and delete this if code block,
> I may have to add "msg" argument to __sock_cmsg_send in the second
> commit, because if I still keep it in this commit, there will be an
> "unused argument" warning.
> 
> However, I think the change to __sock_cmsg_send function declaration is
> generic, so I would like to make it in the first commit, but it is truly
> a bit roundabout. Not sure which way is better?

A temporary __attribute__((unused))
 
> >>   	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?
> 
> I did this in the previous patchset. The problem is that the msg_control
> of msg_sys is either a stack pointer or kmalloc-ed pointer (in
> ____sys_sendmsg), after returning of it, the msg_control of msg_sys is
> either invalid or freed. I may have to do the copy_to_user at the end of
> ____sys_sendmsg.

I see. Ack.

Zijian Zhang July 25, 2024, 1:11 a.m. UTC | #6

On 7/9/24 9:40 AM, Willem de Bruijn wrote:
> zijianzhang@ wrote:
>> From: Zijian Zhang <[e-mail]>
>>
>> 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 <[e-mail]>
>> Signed-off-by: Xiaochun Lu <[e-mail]>
> 
> Overall this approach follows what I had in mind, thanks.
> 
> Looking forward to the discussion with a wider audience at netdevconf
> next week.


After wider exposure to netdev, besides the comments in this email
series, I want to align the next step with you :)

Shall I also make this a config and add conditional compilation in the
hot path？

>> ---
>>   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(-)
>>

Willem de Bruijn July 25, 2024, 3:08 a.m. UTC | #7

Zijian Zhang wrote:
> On 7/9/24 9:40 AM, Willem de Bruijn wrote:
> > zijianzhang@ wrote:
> >> From: Zijian Zhang <[e-mail]>
> >>
> >> 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 <[e-mail]>
> >> Signed-off-by: Xiaochun Lu <[e-mail]>
> > 
> > Overall this approach follows what I had in mind, thanks.
> > 
> > Looking forward to the discussion with a wider audience at netdevconf
> > next week.
> 
> 
> After wider exposure to netdev, besides the comments in this email
> series, I want to align the next step with you :)
> 
> Shall I also make this a config and add conditional compilation in the
> hot path？

At netdev there appeared to be some support for your original approach
of the application passing a user address as CMSG_DATA and the kernel
writing directly there.

That has the benefit of no modifications to net/socket.c and lower
overhead.

But there evidently hasn't been much other feedback on either approach.
Since this is an ABI change, SubmittingPatches suggests "User-space
API changes should also be copied to [e-mail]." That
might give you more opinions, and is probably a good idea for
something this invasive.

If you choose to go with the current approach, a static_branch in
____sys_sendmsg would make the branch a noop in the common case.
Could be enabled on first setsockopt SO_ZEROCOPY. And never
disabled: no need for refcounting it.

Either way, no need for a CONFIG. Distros ship with defaults, so that
is what matters. And you would not want this default off.

Zijian Zhang July 25, 2024, 4:18 a.m. UTC | #8

On 7/24/24 8:08 PM, Willem de Bruijn wrote:
> Zijian Zhang wrote:
>> On 7/9/24 9:40 AM, Willem de Bruijn wrote:
>>> zijianzhang@ wrote:
>>>> From: Zijian Zhang <[e-mail]>
>>>>
>>>> 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 <[e-mail]>
>>>> Signed-off-by: Xiaochun Lu <[e-mail]>
>>>
>>> Overall this approach follows what I had in mind, thanks.
>>>
>>> Looking forward to the discussion with a wider audience at netdevconf
>>> next week.
>>
>>
>> After wider exposure to netdev, besides the comments in this email
>> series, I want to align the next step with you :)
>>
>> Shall I also make this a config and add conditional compilation in the
>> hot path？
> 
> At netdev there appeared to be some support for your original approach
> of the application passing a user address as CMSG_DATA and the kernel
> writing directly there.
> 
> That has the benefit of no modifications to net/socket.c and lower
> overhead.
> 
> But there evidently hasn't been much other feedback on either approach.
> Since this is an ABI change, SubmittingPatches suggests "User-space
> API changes should also be copied to [e-mail]." That
> might give you more opinions, and is probably a good idea for
> something this invasive.
> 
> If you choose to go with the current approach, a static_branch in
> ____sys_sendmsg would make the branch a noop in the common case.
> Could be enabled on first setsockopt SO_ZEROCOPY. And never
> disabled: no need for refcounting it.
> 
> Either way, no need for a CONFIG. Distros ship with defaults, so that
> is what matters. And you would not want this default off.
> 

Agree, the ABI change should be the main concern. I think I will go with
the current method firstly, and the original one as backup.

Thanks for the quick reply and clarification!

Mina Almasry July 25, 2024, 9:34 p.m. UTC | #9

On Mon, Jul 08, 2024 at 09:04:03PM +0000, [e-mail] wrote:
> From: Zijian Zhang <[e-mail]>
>
> 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
> 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 <[e-mail]>
> Signed-off-by: Xiaochun Lu <[e-mail]>
> ---
>  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;

Please add some docs explaining what this does if possible. From reading the
code, it seems if this is true then we should copy cmsg to user. Not sure where
or how it's set though.

>  	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;
>  	return 0;
>  }
>  EXPORT_SYMBOL(__sock_cmsg_send);
> @@ -2881,7 +2883,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
>  			return -EINVAL;
>  		if (cmsg->cmsg_level != SOL_SOCKET)
>  			continue;
> -		ret = __sock_cmsg_send(sk, cmsg, sockc);
> +		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
>  		if (ret)
>  			return ret;
>  	}
> diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
> index cf377377b52d..6360b8ba9c84 100644
> --- a/net/ipv4/ip_sockglue.c
> +++ b/net/ipv4/ip_sockglue.c
> @@ -267,7 +267,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
>  		}
>  #endif
>  		if (cmsg->cmsg_level == SOL_SOCKET) {
> -			err = __sock_cmsg_send(sk, cmsg, &ipc->sockc);
> +			err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
>  			if (err)
>  				return err;
>  			continue;
> diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
> index fff78496803d..c9ae30acf895 100644
> --- a/net/ipv6/datagram.c
> +++ b/net/ipv6/datagram.c
> @@ -777,7 +777,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
>  		}
>
>  		if (cmsg->cmsg_level == SOL_SOCKET) {
> -			err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
> +			err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
>  			if (err)
>  				return err;
>  			continue;
> diff --git a/net/socket.c b/net/socket.c
> index e416920e9399..6a9c9e24d781 100644
> --- a/net/socket.c
> +++ b/net/socket.c
> @@ -2525,8 +2525,43 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
>  	return err < 0 ? err : 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));

put_cmsg() can fail as far as I can tell. Any reason we don't have to check for
failure here?

What happens when these failures happen. Do we end up putting the ZC
notification later, or is the zc notification lost forever because we did not
detect the failure to put_cmsg() it?

> +	}
> +
> +	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;


This may be a lack of knowledge on my part, but i'm very confused that
msg_control_copy_to_user is set to false here, and then checked below, and it's
not touched in between. How could it evaluate to true below? Is it because something
overwrites the value in msg_sys between this set and the check?

If something is overwriting it, is the initialization to false necessary?
I don't see other fields of msg_sys initialized this way.

>
>  	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;

I'm a bit surprised there isn't any cleanup here if copying the cmsg to user
fails. It seems that that __sock_sendmsg() is executed, then if we fail here,
we just return an error without unrolling what __sock_sendmsg() did. Why is
this ok?

Should sendmsg_copy_cmsg_to_user() be done before __sock_sendms() with a goto
out if it fails?

> +	}
> +
>  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);
>  	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
>

Zijian Zhang July 25, 2024, 11:50 p.m. UTC | #10

Firstly, thanks for your attention to this patch set :)

On 7/25/24 2:34 PM, Mina Almasry wrote:
> On Mon, Jul 08, 2024 at 09:04:03PM +0000, [e-mail] wrote:
>> From: Zijian Zhang <[e-mail]>
>>
>> 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
>> 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 <[e-mail]>
>> Signed-off-by: Xiaochun Lu <[e-mail]>
>> ---
>>   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;
> 
> Please add some docs explaining what this does if possible. From reading the
> code, it seems if this is true then we should copy cmsg to user. Not sure where
> or how it's set though.
> 

Agree!

>>   	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;
>>   	return 0;
>>   }
>>   EXPORT_SYMBOL(__sock_cmsg_send);
>> @@ -2881,7 +2883,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
>>   			return -EINVAL;
>>   		if (cmsg->cmsg_level != SOL_SOCKET)
>>   			continue;
>> -		ret = __sock_cmsg_send(sk, cmsg, sockc);
>> +		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
>>   		if (ret)
>>   			return ret;
>>   	}
>> diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
>> index cf377377b52d..6360b8ba9c84 100644
>> --- a/net/ipv4/ip_sockglue.c
>> +++ b/net/ipv4/ip_sockglue.c
>> @@ -267,7 +267,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
>>   		}
>>   #endif
>>   		if (cmsg->cmsg_level == SOL_SOCKET) {
>> -			err = __sock_cmsg_send(sk, cmsg, &ipc->sockc);
>> +			err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
>>   			if (err)
>>   				return err;
>>   			continue;
>> diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
>> index fff78496803d..c9ae30acf895 100644
>> --- a/net/ipv6/datagram.c
>> +++ b/net/ipv6/datagram.c
>> @@ -777,7 +777,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
>>   		}
>>
>>   		if (cmsg->cmsg_level == SOL_SOCKET) {
>> -			err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
>> +			err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
>>   			if (err)
>>   				return err;
>>   			continue;
>> diff --git a/net/socket.c b/net/socket.c
>> index e416920e9399..6a9c9e24d781 100644
>> --- a/net/socket.c
>> +++ b/net/socket.c
>> @@ -2525,8 +2525,43 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
>>   	return err < 0 ? err : 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));
> 
> put_cmsg() can fail as far as I can tell. Any reason we don't have to check for
> failure here?
> 
> What happens when these failures happen. Do we end up putting the ZC
> notification later, or is the zc notification lost forever because we did not
> detect the failure to put_cmsg() it?
> 

That's a good question,

The reason why I don't have check here is that I refered to net/socket.c 
and sock.c. It turns out there is no failure check for put_cmsgs in
these files.

For example, in sock_recv_errqueue, it invokes put_cmsg without check,
and kfree_skb anyway. In this case, if put_cmsg fails, we will lose the
information forever. I find cases where sock_recv_errqueue is used for
TX_TIMESTAMP. Maybe loss for timestamp is okay?

However, I find that sock_recv_errqueue is also used in rds_recvmsg to
receive the zc notifications for rds socket. The zc notification could
also be lost forever in this case?

Not sure if anyone knows the reason why there is no failure check for
put_cmsg in net/socket.c and sock.c?

>> +	}
>> +
>> +	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;
> 
> 
> This may be a lack of knowledge on my part, but i'm very confused that
> msg_control_copy_to_user is set to false here, and then checked below, and it's
> not touched in between. How could it evaluate to true below? Is it because something
> overwrites the value in msg_sys between this set and the check?
> 
> If something is overwriting it, is the initialization to false necessary?
> I don't see other fields of msg_sys initialized this way.
> 

```
msg_sys->msg_control_copy_to_user = false;
...
err = __sock_sendmsg(sock, msg_sys); -> __sock_cmsg_send
...
if (msg && msg_sys->msg_control_copy_to_user && err >= 0)
```

The msg_control_copy_to_user maybe updated by the cmsg handler in
the function __sock_cmsg_send. In patch 2/3, we have
msg_control_copy_to_user updated to true in SCM_ZC_NOTIFICATION
handler.

As for the initialization,

msg_sys is allocated from the kernel stack, if we don't initialize
it to false, it might be randomly true, even though there is no
cmsg wants to be copied back.

Why is there only one initialization here? The existing bit 
msg_control_is_user only get initialized where the following code
path will use it. msg_control_is_user is initialized in multiple
locations in net/socket.c. However, In function hidp_send_frame,
msg_control_is_user is not initialized, because the following path will
not use this bit.

We only initialize msg_control_copy_to_user in function
____sys_sendmsg, because only in this function will we check this bit.

If the initialization here makes people confused, I will add some docs.

>>
>>   	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;
> 
> I'm a bit surprised there isn't any cleanup here if copying the cmsg to user
> fails. It seems that that __sock_sendmsg() is executed, then if we fail here,
> we just return an error without unrolling what __sock_sendmsg() did. Why is
> this ok?
> 
> Should sendmsg_copy_cmsg_to_user() be done before __sock_sendms() with a goto
> out if it fails?
> 

I did this refering to ____sys_recvmsg, in this function, if __put_user
fails, we do not unroll what sock_recvmsg did, and return the error code
of __put_user.

Before __sock_sendmsg, the content of msg_control is not updated by the
function __sock_cmsg_send, so sendmsg_copy_cmsg_to_user at this time
might be not expected.

>> +	}
>> +
>>   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);
>>   	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
>>

Zijian Zhang July 26, 2024, 12:05 a.m. UTC | #11

On 7/25/24 4:50 PM, Zijian Zhang wrote:
>>> 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;
>>>       return 0;
>>>   }

msg_control_copy_to_user is set to true here.

>>
>>
>> This may be a lack of knowledge on my part, but i'm very confused that
>> msg_control_copy_to_user is set to false here, and then checked below, 
>> and it's
>> not touched in between. How could it evaluate to true below? Is it 
>> because something
>> overwrites the value in msg_sys between this set and the check?
>>
>> If something is overwriting it, is the initialization to false necessary?
>> I don't see other fields of msg_sys initialized this way.
>>
> 
> ```
> msg_sys->msg_control_copy_to_user = false;
> ...
> err = __sock_sendmsg(sock, msg_sys); -> __sock_cmsg_send
> ...
> if (msg && msg_sys->msg_control_copy_to_user && err >= 0)
> ```
> 
> The msg_control_copy_to_user maybe updated by the cmsg handler in
> the function __sock_cmsg_send. In patch 2/3, we have
> msg_control_copy_to_user updated to true in SCM_ZC_NOTIFICATION
> handler.

Not in patch 2/3 In this patchset msg_control_copy_to_user is set in
this patch, in __sock_cmsg_send.

> 
> As for the initialization,
> 
> msg_sys is allocated from the kernel stack, if we don't initialize
> it to false, it might be randomly true, even though there is no
> cmsg wants to be copied back.
> 
> Why is there only one initialization here? The existing bit 
> msg_control_is_user only get initialized where the following code
> path will use it. msg_control_is_user is initialized in multiple
> locations in net/socket.c. However, In function hidp_send_frame,
> msg_control_is_user is not initialized, because the following path will
> not use this bit.
> 
> We only initialize msg_control_copy_to_user in function
> ____sys_sendmsg, because only in this function will we check this bit.
> 
> If the initialization here makes people confused, I will add some docs.
>

Mina Almasry July 26, 2024, 5 p.m. UTC | #12

On Thu, Jul 25, 2024 at 4:51 PM Zijian Zhang <[e-mail]> wrote:
...
> >> -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));
> >
> > put_cmsg() can fail as far as I can tell. Any reason we don't have to check for
> > failure here?
> >
> > What happens when these failures happen. Do we end up putting the ZC
> > notification later, or is the zc notification lost forever because we did not
> > detect the failure to put_cmsg() it?
> >
>
> That's a good question,
>
> The reason why I don't have check here is that I refered to net/socket.c
> and sock.c. It turns out there is no failure check for put_cmsgs in
> these files.
>
> For example, in sock_recv_errqueue, it invokes put_cmsg without check,
> and kfree_skb anyway. In this case, if put_cmsg fails, we will lose the
> information forever. I find cases where sock_recv_errqueue is used for
> TX_TIMESTAMP. Maybe loss for timestamp is okay?
>
> However, I find that sock_recv_errqueue is also used in rds_recvmsg to
> receive the zc notifications for rds socket. The zc notification could
> also be lost forever in this case?
>
> Not sure if anyone knows the reason why there is no failure check for
> put_cmsg in net/socket.c and sock.c?
>

I don't know to be honest. I think it's fine for the put_cmsg() to
fail and the notification to be delivered later. However I'm not sure
it's OK for the notification to be lost permanently because of an
error?

For timestamp I can see it not being a big deal if the notification is
lost. For ZC notifications, I think the normal flow is that the
application holds onto the TX buffer until it receives the
notification. If the notification is lost because of an error,
wouldn't that cause a permanent memory leak in the application?

My humble opinion is try as much as possible to either fully deliver
the notification or to save the notification for a future syscall, but
not to lose it. But, I see that no other reviewers are calling this
out, so maybe it's not a big deal and you shouldn't change anything.

> > This may be a lack of knowledge on my part, but i'm very confused that
> > msg_control_copy_to_user is set to false here, and then checked below, and it's
> > not touched in between. How could it evaluate to true below? Is it because something
> > overwrites the value in msg_sys between this set and the check?
> >
> > If something is overwriting it, is the initialization to false necessary?
> > I don't see other fields of msg_sys initialized this way.
> >
>
> ```
> msg_sys->msg_control_copy_to_user = false;
> ...
> err = __sock_sendmsg(sock, msg_sys); -> __sock_cmsg_send
> ...
> if (msg && msg_sys->msg_control_copy_to_user && err >= 0)
> ```
>
> The msg_control_copy_to_user maybe updated by the cmsg handler in
> the function __sock_cmsg_send. In patch 2/3, we have
> msg_control_copy_to_user updated to true in SCM_ZC_NOTIFICATION
> handler.
>
> As for the initialization,
>
> msg_sys is allocated from the kernel stack, if we don't initialize
> it to false, it might be randomly true, even though there is no
> cmsg wants to be copied back.
>
> Why is there only one initialization here? The existing bit
> msg_control_is_user only get initialized where the following code
> path will use it. msg_control_is_user is initialized in multiple
> locations in net/socket.c. However, In function hidp_send_frame,
> msg_control_is_user is not initialized, because the following path will
> not use this bit.
>
> We only initialize msg_control_copy_to_user in function
> ____sys_sendmsg, because only in this function will we check this bit.
>
> If the initialization here makes people confused, I will add some docs.
>

Thanks for the explanation. This looks correct to me now, no need to
add docs. I just missed the intention.

> >>
> >>      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;
> >
> > I'm a bit surprised there isn't any cleanup here if copying the cmsg to user
> > fails. It seems that that __sock_sendmsg() is executed, then if we fail here,
> > we just return an error without unrolling what __sock_sendmsg() did. Why is
> > this ok?
> >
> > Should sendmsg_copy_cmsg_to_user() be done before __sock_sendms() with a goto
> > out if it fails?
> >
>
> I did this refering to ____sys_recvmsg, in this function, if __put_user
> fails, we do not unroll what sock_recvmsg did, and return the error code
> of __put_user.
>
> Before __sock_sendmsg, the content of msg_control is not updated by the
> function __sock_cmsg_send, so sendmsg_copy_cmsg_to_user at this time
> might be not expected.
>

I see. I don't think sendmsg_copy_cmsg_to_user() should unroll
__sock_sendmsg(), but if possible for the notification not to be lost,
I think that would be an improvement.

Zijian Zhang July 26, 2024, 8 p.m. UTC | #13

On 7/26/24 10:00 AM, Mina Almasry wrote:
> On Thu, Jul 25, 2024 at 4:51 PM Zijian Zhang <[e-mail]> wrote:
> ...
>>>> -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));
>>>
>>> put_cmsg() can fail as far as I can tell. Any reason we don't have to check for
>>> failure here?
>>>
>>> What happens when these failures happen. Do we end up putting the ZC
>>> notification later, or is the zc notification lost forever because we did not
>>> detect the failure to put_cmsg() it?
>>>
>>
>> That's a good question,
>>
>> The reason why I don't have check here is that I refered to net/socket.c
>> and sock.c. It turns out there is no failure check for put_cmsgs in
>> these files.
>>
>> For example, in sock_recv_errqueue, it invokes put_cmsg without check,
>> and kfree_skb anyway. In this case, if put_cmsg fails, we will lose the
>> information forever. I find cases where sock_recv_errqueue is used for
>> TX_TIMESTAMP. Maybe loss for timestamp is okay?
>>
>> However, I find that sock_recv_errqueue is also used in rds_recvmsg to
>> receive the zc notifications for rds socket. The zc notification could
>> also be lost forever in this case?
>>
>> Not sure if anyone knows the reason why there is no failure check for
>> put_cmsg in net/socket.c and sock.c?
>>
> 
> I don't know to be honest. I think it's fine for the put_cmsg() to
> fail and the notification to be delivered later. However I'm not sure
> it's OK for the notification to be lost permanently because of an
> error?
> 
> For timestamp I can see it not being a big deal if the notification is
> lost. For ZC notifications, I think the normal flow is that the
> application holds onto the TX buffer until it receives the
> notification. If the notification is lost because of an error,
> wouldn't that cause a permanent memory leak in the application?
> 
> My humble opinion is try as much as possible to either fully deliver
> the notification or to save the notification for a future syscall, but
> not to lose it. But, I see that no other reviewers are calling this
> out, so maybe it's not a big deal and you shouldn't change anything.
> 

Agree, in ZC notification case, saving the notification for a future 
syscall is better than losing it forever. The difficulties I am aware of
are as follows,

If we find put_cmsg fails in
sendmsg_copy_cmsg_to_user, we have reached the end of ____sys_sendmsg,

1. Since the skb which carries the zc information has been freed from 
the errqueue. To roll back the effect, we need to sock_omalloc an skb
and insert it back. Or, we can store the information somewhere, but I
assume we need to allocate some memory, if the allocation fails, we may
still lose the info? Shall we make sure the allocation succeeds?

2. Currently, we free the skb in the hanlder of SCM_ZC_NOTIF, can we
free it after we are sure that put_cmsg succeed? One blocking I can
think of is that because of notification coalescing, the
information in the skb might be updated, since we snapshot the 
information earlier, so the information we copy to user might be
outdated. And, we also need a post handler for this cmsg_type, in
sendmsg_copy_cmsg_to_user.

3. The above is the specific unrolling/post handling logic for 
SCM_ZC_NOTIF. Each cmsg_type, which needs to be copied back could have
their own logic, we may add a function to handle it according to
cmsg_type. And call this function in sendmsg_copy_cmsg_to_user, to make
the code generic.

So besides ABI change, this is another problem we have for this
mechanism. These two concerns make our alternative usr_addr method(v4)
shine. In v4, users pass in a user address which points to a
zc_info_elem array. In the handler of SCM_ZC_NOTIF, we do copy to user
to that usr_addr. If it fails, in the context of the handler, the
unrolling is very clean and easy. The problem with this method is that
it makes the API of msg_control hacky.

Thanks for pointing this out, more comments are welcome!

>>> This may be a lack of knowledge on my part, but i'm very confused that
>>> msg_control_copy_to_user is set to false here, and then checked below, and it's
>>> not touched in between. How could it evaluate to true below? Is it because something
>>> overwrites the value in msg_sys between this set and the check?
>>>
>>> If something is overwriting it, is the initialization to false necessary?
>>> I don't see other fields of msg_sys initialized this way.
>>>
>>
>> ```
>> msg_sys->msg_control_copy_to_user = false;
>> ...
>> err = __sock_sendmsg(sock, msg_sys); -> __sock_cmsg_send
>> ...
>> if (msg && msg_sys->msg_control_copy_to_user && err >= 0)
>> ```
>>
>> The msg_control_copy_to_user maybe updated by the cmsg handler in
>> the function __sock_cmsg_send. In patch 2/3, we have
>> msg_control_copy_to_user updated to true in SCM_ZC_NOTIFICATION
>> handler.
>>
>> As for the initialization,
>>
>> msg_sys is allocated from the kernel stack, if we don't initialize
>> it to false, it might be randomly true, even though there is no
>> cmsg wants to be copied back.
>>
>> Why is there only one initialization here? The existing bit
>> msg_control_is_user only get initialized where the following code
>> path will use it. msg_control_is_user is initialized in multiple
>> locations in net/socket.c. However, In function hidp_send_frame,
>> msg_control_is_user is not initialized, because the following path will
>> not use this bit.
>>
>> We only initialize msg_control_copy_to_user in function
>> ____sys_sendmsg, because only in this function will we check this bit.
>>
>> If the initialization here makes people confused, I will add some docs.
>>
> 
> Thanks for the explanation. This looks correct to me now, no need to
> add docs. I just missed the intention.
> 

No problem, my pleasure.

>>>>
>>>>       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;
>>>
>>> I'm a bit surprised there isn't any cleanup here if copying the cmsg to user
>>> fails. It seems that that __sock_sendmsg() is executed, then if we fail here,
>>> we just return an error without unrolling what __sock_sendmsg() did. Why is
>>> this ok?
>>>
>>> Should sendmsg_copy_cmsg_to_user() be done before __sock_sendms() with a goto
>>> out if it fails?
>>>
>>
>> I did this refering to ____sys_recvmsg, in this function, if __put_user
>> fails, we do not unroll what sock_recvmsg did, and return the error code
>> of __put_user.
>>
>> Before __sock_sendmsg, the content of msg_control is not updated by the
>> function __sock_cmsg_send, so sendmsg_copy_cmsg_to_user at this time
>> might be not expected.
>>
> 
> I see. I don't think sendmsg_copy_cmsg_to_user() should unroll
> __sock_sendmsg(), but if possible for the notification not to be lost,
> I think that would be an improvement.
>

Patch

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;
 	return 0;
 }
 EXPORT_SYMBOL(__sock_cmsg_send);
@@ -2881,7 +2883,7 @@  int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 			return -EINVAL;
 		if (cmsg->cmsg_level != SOL_SOCKET)
 			continue;
-		ret = __sock_cmsg_send(sk, cmsg, sockc);
+		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
 		if (ret)
 			return ret;
 	}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cf377377b52d..6360b8ba9c84 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -267,7 +267,7 @@  int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 		}
 #endif
 		if (cmsg->cmsg_level == SOL_SOCKET) {
-			err = __sock_cmsg_send(sk, cmsg, &ipc->sockc);
+			err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
 			if (err)
 				return err;
 			continue;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fff78496803d..c9ae30acf895 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -777,7 +777,7 @@  int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 		}
 
 		if (cmsg->cmsg_level == SOL_SOCKET) {
-			err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
+			err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
 			if (err)
 				return err;
 			continue;
diff --git a/net/socket.c b/net/socket.c
index e416920e9399..6a9c9e24d781 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2525,8 +2525,43 @@  static int copy_msghdr_from_user(struct msghdr *kmsg,
 	return err < 0 ? err : 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;
+	}
+
 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);
 	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,