我试图通过linux socket发送一些文件描述符，但它不起作用。我究竟做错了什么？一个人应该如何调试这样的东西？我尝试将perror（）放在任何可能的地方，但他们声称一切正常。这是我写的：
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <sys/wait.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <fcntl.h>
void wyslij(int socket, int fd) // send fd by socket
{
struct msghdr msg = {0};
char buf[CMSG_SPACE(sizeof fd)];
msg.msg_control = buf;
msg.msg_controllen = sizeof buf;
struct cmsghdr * cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(sizeof fd);
*((int *) CMSG_DATA(cmsg)) = fd;
msg.msg_controllen = cmsg->cmsg_len; // why does example from man need it? isn't it redundant?
sendmsg(socket, &msg, 0);
}
int odbierz(int socket) // receive fd from socket
{
struct msghdr msg = {0};
recvmsg(socket, &msg, 0);
struct cmsghdr * cmsg = CMSG_FIRSTHDR(&msg);
unsigned char * data = CMSG_DATA(cmsg);
int fd = *((int*) data); // here program stops, probably with segfault
return fd;
}
int main()
{
int sv[2];
socketpair(AF_UNIX, SOCK_DGRAM, 0, sv);
int pid = fork();
if (pid > 0) // in parent
{
close(sv[1]);
int sock = sv[0];
int fd = open("./z7.c", O_RDONLY);
wyslij(sock, fd);
close(fd);
}
else // in child
{
close(sv[0]);
int sock = sv[1];
sleep(0.5);
int fd = odbierz(sock);
}
}
答案 0 :(得分：35)
Stevens（et al）UNIX® Network Programming, Vol 1: The Sockets Networking API描述了在第15章 Unix域协议，特别是§15.7传递描述符中的流程之间传输文件描述符的过程。完全描述它很繁琐，但它必须在Unix域套接字（AF_UNIX或AF_LOCAL）上完成，并且发送方进程使用sendmsg()，而接收方使用recvmsg()
我在Mac OS X 10.10.1 Yosemite上使用GCC 4.9.1获得了这个问题的温和修改（和仪表化）版本的代码，以便为我工作：
#include "stderr.h"
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
static
void wyslij(int socket, int fd) // send fd by socket
{
struct msghdr msg = { 0 };
char buf[CMSG_SPACE(sizeof(fd))];
memset(buf, '\0', sizeof(buf));
struct iovec io = { .iov_base = "ABC", .iov_len = 3 };
msg.msg_iov = &io;
msg.msg_iovlen = 1;
msg.msg_control = buf;
msg.msg_controllen = sizeof(buf);
struct cmsghdr * cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
*((int *) CMSG_DATA(cmsg)) = fd;
msg.msg_controllen = CMSG_SPACE(sizeof(fd));
if (sendmsg(socket, &msg, 0) < 0)
err_syserr("Failed to send message\n");
}
static
int odbierz(int socket) // receive fd from socket
{
struct msghdr msg = {0};
char m_buffer[256];
struct iovec io = { .iov_base = m_buffer, .iov_len = sizeof(m_buffer) };
msg.msg_iov = &io;
msg.msg_iovlen = 1;
char c_buffer[256];
msg.msg_control = c_buffer;
msg.msg_controllen = sizeof(c_buffer);
if (recvmsg(socket, &msg, 0) < 0)
err_syserr("Failed to receive message\n");
struct cmsghdr * cmsg = CMSG_FIRSTHDR(&msg);
unsigned char * data = CMSG_DATA(cmsg);
err_remark("About to extract fd\n");
int fd = *((int*) data);
err_remark("Extracted fd %d\n", fd);
return fd;
}
int main(int argc, char **argv)
{
const char *filename = "./z7.c";
err_setarg0(argv[0]);
err_setlogopts(ERR_PID);
if (argc > 1)
filename = argv[1];
int sv[2];
if (socketpair(AF_UNIX, SOCK_DGRAM, 0, sv) != 0)
err_syserr("Failed to create Unix-domain socket pair\n");
int pid = fork();
if (pid > 0) // in parent
{
err_remark("Parent at work\n");
close(sv[1]);
int sock = sv[0];
int fd = open(filename, O_RDONLY);
if (fd < 0)
err_syserr("Failed to open file %s for reading\n", filename);
wyslij(sock, fd);
close(fd);
nanosleep(&(struct timespec){ .tv_sec = 1, .tv_nsec = 500000000}, 0);
err_remark("Parent exits\n");
}
else // in child
{
err_remark("Child at play\n");
close(sv[0]);
int sock = sv[1];
nanosleep(&(struct timespec){ .tv_sec = 0, .tv_nsec = 500000000}, 0);
int fd = odbierz(sock);
printf("Read %d!\n", fd);
char buffer[256];
ssize_t nbytes;
while ((nbytes = read(fd, buffer, sizeof(buffer))) > 0)
write(1, buffer, nbytes);
printf("Done!\n");
close(fd);
}
return 0;
}
原始代码的已检测但未修复版本的输出为：
$ ./fd-passing
fd-passing: pid=1391: Parent at work
fd-passing: pid=1391: Failed to send message
error (40) Message too long
fd-passing: pid=1392: Child at play
$ fd-passing: pid=1392: Failed to receive message
error (40) Message too long
请注意，父级在子级之前完成，因此提示出现在输出的中间。
“固定”代码的输出是：
$ ./fd-passing
fd-passing: pid=1046: Parent at work
fd-passing: pid=1048: Child at play
fd-passing: pid=1048: About to extract fd
fd-passing: pid=1048: Extracted fd 3
Read 3!
This is the file z7.c.
It isn't very interesting.
It isn't even C code.
But it is used by the fd-passing program to demonstrate that file
descriptors can indeed be passed between sockets on occasion.
Done!
fd-passing: pid=1046: Parent exits
$
主要的重大变化是将struct iovec添加到两个函数中struct msghdr的数据中，并在接收函数（odbierz()）中为控制消息提供空间。我在调试中报告了一个中间步骤，我将struct iovec提供给父级，并删除了父级的“消息太长”错误。为了证明它正在工作（传递了文件描述符），我添加了代码来从传递的文件描述符中读取和打印文件。原始代码有sleep(0.5)，但由于sleep()采用无符号整数，这相当于不睡眠。我用C99复合文字让孩子睡了0.5秒。父节点休眠1.5秒，以便在父节点退出之前完成子节点的输出。我也可以使用wait()或waitpid()，但实在是太懒了。
我没有回去检查所有的添加都是必要的。
"stderr.h"标头声明了err_*()个函数。我写的代码（1987年以前的第一个版本）简洁地报告了错误。 err_setlogopts(ERR_PID)调用为具有PID的所有消息添加前缀。对于时间戳，err_setlogopts(ERR_PID|ERR_STAMP)也可以完成这项工作。
我建议您修改代码以使用
int复制描述符memcpy()，而不是直接访问数据吗？它不一定是正确对齐的 - 这就是为什么手册页示例也使用memcpy()- 并且有许多Linux架构，其中未对齐的int访问会导致问题（由SIGBUS信号杀死进程）。
不仅Linux体系结构：SPARC和Power都需要对齐数据，并且通常分别运行Solaris和AIX。曾几何时，DEC Alpha也需要这样，但是现在很少见到它们。
与此相关的手册页cmsg(3)中的代码是：
struct msghdr msg = {0};
struct cmsghdr *cmsg;
int myfds[NUM_FD]; /* Contains the file descriptors to pass. */
char buf[CMSG_SPACE(sizeof myfds)]; /* ancillary data buffer */
int *fdptr;
msg.msg_control = buf;
msg.msg_controllen = sizeof buf;
cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(sizeof(int) * NUM_FD);
/* Initialize the payload: */
fdptr = (int *) CMSG_DATA(cmsg);
memcpy(fdptr, myfds, NUM_FD * sizeof(int));
/* Sum of the length of all control messages in the buffer: */
msg.msg_controllen = CMSG_SPACE(sizeof(int) * NUM_FD);
对fdptr的分配似乎假设CMSG_DATA(cmsg)已完全对齐以转换为int *，而memcpy()的使用假设为{{1}不仅仅是1.据说，它应该指向数组NUM_FD，并且可能没有像Nominal Animal所说的那样完全对齐，所以在我看来{{1} }只是一个闯入者，如果使用的例子会更好：
buf然后接收端的反向过程是合适的。该程序仅传递单个文件描述符，因此代码可修改为：
fdptr我似乎也回忆起各种操作系统的历史问题w.r.t.没有正常有效载荷数据的辅助数据，通过发送至少一个虚拟字节也可以避免，但我找不到任何要验证的引用，所以我可能记错了。
鉴于Mac OS X（具有Darwin / BSD基础）至少需要一个memcpy(CMSG_DATA(cmsg), myfds, NUM_FD * sizeof(int));
，即使描述了一个零长度的消息，我也愿意相信上面显示的代码，包含一个3字节的消息，是正确方向的一个很好的步骤。该消息可能应该是一个空字节而不是3个字母。
我修改了代码，如下所示。它使用memmove(CMSG_DATA(cmsg), &fd, sizeof(fd)); // Send
memmove(&fd, CMSG_DATA(cmsg), sizeof(fd)); // Receive
将文件描述符复制到struct iovec缓冲区和从memmove()缓冲区复制。它传输单个消息字节，这是一个空字节。
在将文件描述符传递给子文件之前，它还使父进程读取（最多）32个字节的文件。孩子继续阅读父母离开的地方。这表明传输的文件描述符包括文件偏移量。
接收方应在cmsg上进行更多验证，然后再将其视为文件描述符传递消息。
cmsg示例运行：
#include "stderr.h"
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>
static
void wyslij(int socket, int fd) // send fd by socket
{
struct msghdr msg = { 0 };
char buf[CMSG_SPACE(sizeof(fd))];
memset(buf, '\0', sizeof(buf));
/* On Mac OS X, the struct iovec is needed, even if it points to minimal data */
struct iovec io = { .iov_base = "", .iov_len = 1 };
msg.msg_iov = &io;
msg.msg_iovlen = 1;
msg.msg_control = buf;
msg.msg_controllen = sizeof(buf);
struct cmsghdr * cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
memmove(CMSG_DATA(cmsg), &fd, sizeof(fd));
msg.msg_controllen = CMSG_SPACE(sizeof(fd));
if (sendmsg(socket, &msg, 0) < 0)
err_syserr("Failed to send message\n");
}
static
int odbierz(int socket) // receive fd from socket
{
struct msghdr msg = {0};
/* On Mac OS X, the struct iovec is needed, even if it points to minimal data */
char m_buffer[1];
struct iovec io = { .iov_base = m_buffer, .iov_len = sizeof(m_buffer) };
msg.msg_iov = &io;
msg.msg_iovlen = 1;
char c_buffer[256];
msg.msg_control = c_buffer;
msg.msg_controllen = sizeof(c_buffer);
if (recvmsg(socket, &msg, 0) < 0)
err_syserr("Failed to receive message\n");
struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
err_remark("About to extract fd\n");
int fd;
memmove(&fd, CMSG_DATA(cmsg), sizeof(fd));
err_remark("Extracted fd %d\n", fd);
return fd;
}
int main(int argc, char **argv)
{
const char *filename = "./z7.c";
err_setarg0(argv[0]);
err_setlogopts(ERR_PID);
if (argc > 1)
filename = argv[1];
int sv[2];
if (socketpair(AF_UNIX, SOCK_DGRAM, 0, sv) != 0)
err_syserr("Failed to create Unix-domain socket pair\n");
int pid = fork();
if (pid > 0) // in parent
{
err_remark("Parent at work\n");
close(sv[1]);
int sock = sv[0];
int fd = open(filename, O_RDONLY);
if (fd < 0)
err_syserr("Failed to open file %s for reading\n", filename);
/* Read some data to demonstrate that file offset is passed */
char buffer[32];
int nbytes = read(fd, buffer, sizeof(buffer));
if (nbytes > 0)
err_remark("Parent read: [[%.*s]]\n", nbytes, buffer);
wyslij(sock, fd);
close(fd);
nanosleep(&(struct timespec){ .tv_sec = 1, .tv_nsec = 500000000}, 0);
err_remark("Parent exits\n");
}
else // in child
{
err_remark("Child at play\n");
close(sv[0]);
int sock = sv[1];
nanosleep(&(struct timespec){ .tv_sec = 0, .tv_nsec = 500000000}, 0);
int fd = odbierz(sock);
printf("Read %d!\n", fd);
char buffer[256];
ssize_t nbytes;
while ((nbytes = read(fd, buffer, sizeof(buffer))) > 0)
write(1, buffer, nbytes);
printf("Done!\n");
close(fd);
}
return 0;
}