Re: [RFC PATCH 05/27] containers: Open a socket inside a container

[ebiederm@xmission.com (Eric W. Biederman)]

David Howells <dhowells@redhat.com> writes:

> Provide a system call to open a socket inside of a container, using that
> container's network namespace.  This allows netlink to be used to manage
> the container.
>
> 	fd = container_socket(int container_fd,
> 			      int domain, int type, int protocol);
>

Nacked-by: "Eric W. Biederman" <ebiederm@xmission.com>

Use a namespace file descriptor if you need this.  So far we have not
added this system call as it is just a performance optimization.  And it
has been too niche to matter.

If this that has changed we can add this separately from everything else
you are doing here.


> Signed-off-by: David Howells <dhowells@redhat.com>
> ---
>
>  arch/x86/entry/syscalls/syscall_32.tbl |    1 +
>  arch/x86/entry/syscalls/syscall_64.tbl |    1 +
>  include/linux/socket.h                 |    3 ++-
>  include/linux/syscalls.h               |    2 ++
>  kernel/sys_ni.c                        |    1 +
>  net/compat.c                           |    2 +-
>  net/socket.c                           |   34 +++++++++++++++++++++++++++-----
>  7 files changed, 37 insertions(+), 7 deletions(-)
>
> diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
> index 8666693510f9..f4c9beff77a6 100644
> --- a/arch/x86/entry/syscalls/syscall_32.tbl
> +++ b/arch/x86/entry/syscalls/syscall_32.tbl
> @@ -409,3 +409,4 @@
>  395	i386	sb_notify		sys_sb_notify			__ia32_sys_sb_notify
>  396	i386	container_create	sys_container_create		__ia32_sys_container_create
>  397	i386	fork_into_container	sys_fork_into_container		__ia32_sys_fork_into_container
> +398	i386	container_socket	sys_container_socket		__ia32_sys_container_socket
> diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
> index d40d4790fcb2..e20cdf7b5527 100644
> --- a/arch/x86/entry/syscalls/syscall_64.tbl
> +++ b/arch/x86/entry/syscalls/syscall_64.tbl
> @@ -354,6 +354,7 @@
>  343	common	sb_notify		__x64_sys_sb_notify
>  344	common	container_create	__x64_sys_container_create
>  345	common	fork_into_container	__x64_sys_fork_into_container
> +346	common	container_socket	__x64_sys_container_socket
>  
>  #
>  # x32-specific system call numbers start at 512 to avoid cache impact
> diff --git a/include/linux/socket.h b/include/linux/socket.h
> index ab2041a00e01..154ac900a8a5 100644
> --- a/include/linux/socket.h
> +++ b/include/linux/socket.h
> @@ -10,6 +10,7 @@
>  #include <linux/compiler.h>		/* __user			*/
>  #include <uapi/linux/socket.h>
>  
> +struct net;
>  struct pid;
>  struct cred;
>  
> @@ -376,7 +377,7 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
>  			int addr_len);
>  extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
>  			 int __user *upeer_addrlen, int flags);
> -extern int __sys_socket(int family, int type, int protocol);
> +extern int __sys_socket(struct net *net, int family, int type, int protocol);
>  extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
>  extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
>  			 int addrlen);
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index 15e5cc704df3..547334c6ffc2 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -947,6 +947,8 @@ asmlinkage long sys_container_create(const char __user *name, unsigned int flags
>  				     unsigned long spare3, unsigned long spare4,
>  				     unsigned long spare5);
>  asmlinkage long sys_fork_into_container(int containerfd);
> +asmlinkage long sys_container_socket(int containerfd,
> +				     int domain, int type, int protocol);
>  
>  /*
>   * Architecture-specific system calls
> diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
> index a23ad529d548..ce9c5bb30e7f 100644
> --- a/kernel/sys_ni.c
> +++ b/kernel/sys_ni.c
> @@ -236,6 +236,7 @@ COND_SYSCALL(shmdt);
>  /* net/socket.c */
>  COND_SYSCALL(socket);
>  COND_SYSCALL(socketpair);
> +COND_SYSCALL(container_socket);
>  COND_SYSCALL(bind);
>  COND_SYSCALL(listen);
>  COND_SYSCALL(accept);
> diff --git a/net/compat.c b/net/compat.c
> index 959d1c51826d..1b2db740fd33 100644
> --- a/net/compat.c
> +++ b/net/compat.c
> @@ -856,7 +856,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
>  
>  	switch (call) {
>  	case SYS_SOCKET:
> -		ret = __sys_socket(a0, a1, a[2]);
> +		ret = __sys_socket(current->nsproxy->net_ns, a0, a1, a[2]);
>  		break;
>  	case SYS_BIND:
>  		ret = __sys_bind(a0, compat_ptr(a1), a[2]);
> diff --git a/net/socket.c b/net/socket.c
> index 7d271a1d0c7e..7406580598b9 100644
> --- a/net/socket.c
> +++ b/net/socket.c
> @@ -80,6 +80,7 @@
>  #include <linux/highmem.h>
>  #include <linux/mount.h>
>  #include <linux/fs_context.h>
> +#include <linux/container.h>
>  #include <linux/security.h>
>  #include <linux/syscalls.h>
>  #include <linux/compat.h>
> @@ -1326,9 +1327,9 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
>  }
>  EXPORT_SYMBOL(sock_create_kern);
>  
> -int __sys_socket(int family, int type, int protocol)
> +int __sys_socket(struct net *net, int family, int type, int protocol)
>  {
> -	int retval;
> +	long retval;
>  	struct socket *sock;
>  	int flags;
>  
> @@ -1346,7 +1347,7 @@ int __sys_socket(int family, int type, int protocol)
>  	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
>  		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
>  
> -	retval = sock_create(family, type, protocol, &sock);
> +	retval = __sock_create(net, family, type, protocol, &sock, 0);
>  	if (retval < 0)
>  		return retval;
>  
> @@ -1355,9 +1356,32 @@ int __sys_socket(int family, int type, int protocol)
>  
>  SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
>  {
> -	return __sys_socket(family, type, protocol);
> +	return __sys_socket(current->nsproxy->net_ns, family, type, protocol);
>  }
>  
> +/*
> + * Create a socket inside a container.
> + */
> +#ifdef CONFIG_CONTAINERS
> +SYSCALL_DEFINE4(container_socket,
> +		int, containerfd, int, family, int, type, int, protocol)
> +{
> +	struct fd f = fdget(containerfd);
> +	long ret;
> +
> +	if (!f.file)
> +		return -EBADF;
> +	ret = -EINVAL;
> +	if (is_container_file(f.file)) {
> +		struct container *c = f.file->private_data;
> +
> +		ret = __sys_socket(c->ns->net_ns, family, type, protocol);
> +	}
> +	fdput(f);
> +	return ret;
> +}
> +#endif
> +
>  /*
>   *	Create a pair of connected sockets.
>   */
> @@ -2555,7 +2579,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
>  
>  	switch (call) {
>  	case SYS_SOCKET:
> -		err = __sys_socket(a0, a1, a[2]);
> +		err = __sys_socket(current->nsproxy->net_ns, a0, a1, a[2]);
>  		break;
>  	case SYS_BIND:
>  		err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);