套接字之sendmsg系统调用

sendmsg系统调用允许在用户空间构造消息头和控制信息，用此函数可以发送多个数据缓冲区的数据，并支持控制信息；当调用进入内核后，会将用户端的user_msghdr对应拷贝到内核的msghdr中，然后进行数据发送；

 SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags)
 {
     /* 不支持64位采用32位兼容标记 */
     if (flags & MSG_CMSG_COMPAT)
         return -EINVAL;

     /* 调用__sys_sendmsg */
     return __sys_sendmsg(fd, msg, flags);
 }

 /*
  *    BSD sendmsg interface
  */

 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
     int fput_needed, err;
     struct msghdr msg_sys;
     struct socket *sock;

     /* 查找socket */
     sock = sockfd_lookup_light(fd, &err, &fput_needed);
     if (!sock)
         goto out;

     /* 发送数据 */
     err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, );

     fput_light(sock->file, fput_needed);
 out:
     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)
 {
     struct compat_msghdr __user *msg_compat =
         (struct compat_msghdr __user *)msg;
     struct sockaddr_storage address;
     struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
     unsigned char ctl[sizeof(struct cmsghdr) + ]
                 __aligned(sizeof(__kernel_size_t));
     /* 20 is size of ipv6_pktinfo */
     unsigned char *ctl_buf = ctl;
     int ctl_len;
     ssize_t err;

     msg_sys->msg_name = &address;

     /* 需要做64位采用32位兼容 */
     if (MSG_CMSG_COMPAT & flags)
         /* 从64位消息头拷贝数据到32位消息头 */
         err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov);
     else
         /* 从用户空间拷贝消息数据到消息头 */
         err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
     if (err < )
         return err;

     err = -ENOBUFS;

     /* 控制信息长度错误 */
     if (msg_sys->msg_controllen > INT_MAX)
         goto out_freeiov;

     /* 拷贝控制信息 */
     flags |= (msg_sys->msg_flags & allowed_msghdr_flags);
     ctl_len = msg_sys->msg_controllen;
     if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
         err =
             cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl,
                              sizeof(ctl));
         if (err)
             goto out_freeiov;
         ctl_buf = msg_sys->msg_control;
         ctl_len = msg_sys->msg_controllen;
     } else if (ctl_len) {
         BUILD_BUG_ON(sizeof(struct cmsghdr) !=
                  CMSG_ALIGN(sizeof(struct cmsghdr)));
         if (ctl_len > sizeof(ctl)) {
             ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL);
             if (ctl_buf == NULL)
                 goto out_freeiov;
         }
         err = -EFAULT;
         /*
          * Careful! Before this, msg_sys->msg_control contains a user pointer.
          * Afterwards, it will be a kernel pointer. Thus the compiler-assisted
          * checking falls down on this.
          */
         if (copy_from_user(ctl_buf,
                    (void __user __force *)msg_sys->msg_control,
                    ctl_len))
             goto out_freectl;
         msg_sys->msg_control = ctl_buf;
     }

     /* 设置发送标记 */
     msg_sys->msg_flags = flags;

     /* 设置非阻塞标记 */
     if (sock->file->f_flags & O_NONBLOCK)
         msg_sys->msg_flags |= MSG_DONTWAIT;
     /*
      * If this is sendmmsg() and current destination address is same as
      * previously succeeded address, omit asking LSM's decision.
      * used_address->name_len is initialized to UINT_MAX so that the first
      * destination address never matches.
      */
     /* 如果这次发送的地址跟上次成功发送的一致 */
     if (used_address && msg_sys->msg_name &&
         used_address->name_len == msg_sys->msg_namelen &&
         !memcmp(&used_address->name, msg_sys->msg_name,
             used_address->name_len)) {
         /* 无需进行检查，直接发送 */
         err = sock_sendmsg_nosec(sock, msg_sys);
         goto out_freectl;
     }

     /* 进行安全模块检查后发送 */
     err = sock_sendmsg(sock, msg_sys);
     /*
      * If this is sendmmsg() and sending to current destination address was
      * successful, remember it.
      */

     /* 发送成功需要更新成功地址记录 */
     if (used_address && err >= ) {
         used_address->name_len = msg_sys->msg_namelen;
         if (msg_sys->msg_name)
             memcpy(&used_address->name, msg_sys->msg_name,
                    used_address->name_len);
     }

 out_freectl:
     if (ctl_buf != ctl)
         sock_kfree_s(sock->sk, ctl_buf, ctl_len);
 out_freeiov:
     kfree(iov);
     return err;
 }

TCP层的sendmsg实现为tcp_sendmsg，详情请移步<TCP层sendmsg系统调用的实现分析>；