c - 通过 C 中的 Netlink 从内核到用户空间的多播

Question

我正在尝试使用 Netlink 编写一个在内核空间和用户空间之间进行通信的简单程序。基本上这就是我想要实现的目标:

1. 用户空间程序开始绑定(bind)到用户定义的多播组。
2. 插入内核模块
3. 内核模块向这个多播组发送消息
4. 用户空间程序收到消息

这是我的代码:

======用户空间程序======

#include<stdio.h>
#include<string.h>
#include<stdlib.h>
#include<sys/socket.h>
#include<linux/netlink.h>
#include<sys/types.h>
#include<unistd.h>

#define MYPROTO NETLINK_USERSOCK
#define MYMGRP 0x21 //User defined group, consistent in both kernel prog and user prog

int open_netlink()
{
        int sock = socket(AF_NETLINK,SOCK_RAW,MYPROTO);
        struct sockaddr_nl addr;

        memset((void *)&addr, 0, sizeof(addr));

        if (sock<0)
                return sock;
        addr.nl_family = AF_NETLINK;
        addr.nl_pid = getpid();
        addr.nl_groups = MYMGRP;
        if (bind(sock,(struct sockaddr *)&addr,sizeof(addr))<0)
                return -1;
        return sock;
}

int read_event(int sock)
{
        struct sockaddr_nl nladdr;
        struct msghdr msg;
        struct iovec iov[2];
        struct nlmsghdr nlh;
        char buffer[65536];
        int ret;
        iov[0].iov_base = (void *)&nlh;
        iov[0].iov_len = sizeof(nlh);
        iov[1].iov_base = (void *)buffer;
        iov[1].iov_len = sizeof(buffer);
        msg.msg_name = (void *)&(nladdr);
        msg.msg_namelen = sizeof(nladdr);
        msg.msg_iov = iov;
        msg.msg_iovlen = sizeof(iov)/sizeof(iov[0]);
        ret=recvmsg(sock, &msg, 0);
        if (ret<0) {
                return ret;
        }
        printf("Received message payload: %s\n", NLMSG_DATA(&nlh));
}

int main(int argc, char *argv[])
{
        int nls = open_netlink();
        if (nls<0) {
                err(1,"netlink");
        }

        while (1)
                read_event(nls);
        return 0;
}

======内核模块======

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <net/sock.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <asm/types.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <linux/delay.h>

#define NETLINK_USER 31
#define MYGRP 0x21 //User defined group, consistent in both kernel prog and user prog

struct sock *nl_sk = NULL;

static void send_to_user() {
    struct sk_buff *skb_out;
    struct nlmsghdr *nlh;
    int msg_size;
    char *msg = "Hello from kernel";
    int res;

    printk(KERN_INFO "Entering: %s\n", __FUNCTION__);
    msg_size = strlen(msg);
    skb_out = nlmsg_new(msg_size, 0);

    if (!skb_out) {
        printk(KERN_ERR "Failed to allocate new skb\n");
        return;
    }
    nlh = nlmsg_put(skb_out, 0, 1, NLMSG_DONE, msg_size, 0);
    //NETLINK_CB(skb_out).dst_group = 1; /* Multicast to group 1, 1<<0 */
    strncpy(nlmsg_data(nlh), msg, msg_size);

    res = nlmsg_multicast(nl_sk, skb_out, 0, MYGRP, 0);
    if (res < 0) {
        printk(KERN_INFO "Error while sending bak to user, err id: %d\n", res);
    }
}

static int __init
hello_init(void) {

    struct netlink_kernel_cfg cfg = {
            .groups = MYGRP,
    };
    printk("Entering: %s\n", __FUNCTION__);
    nl_sk = netlink_kernel_create(&init_net, NETLINK_USER, &cfg);
    if (!nl_sk) {
        printk(KERN_ALERT "Error creating socket.\n");
        return -10;
    }

    send_to_user();

    return 0;
}

static void __exit
hello_exit(void) {

    printk(KERN_INFO "exiting hello module\n");
    netlink_kernel_release(nl_sk);
}

module_init(hello_init);
module_exit(hello_exit);

由于内核模块在初始化时只会发送一次消息，所以我先运行监听程序，然后再插入模块，虽然我总是得到这个错误:

Error while sending bak to user, err id: -3

当追踪到err id时，它反射(reflect)在netlink/af_netlink.c中的这段代码中:

if (info.delivery_failure) {
    kfree_skb(info.skb2);
    return -ENOBUFS;
}
consume_skb(info.skb2);

if (info.delivered) {
    if (info.congested && (allocation & __GFP_WAIT))
    yield();
    return 0;
}
return -ESRCH;

我认为这不是 delivery_failure 但由于某些原因仍未交付。

我指的是这个 example其中作者的程序不断监听路由变化。尽管我想使用用户定义的多播组。

有什么想法吗？提前致谢!

Answer 1

这是我在您的代码中发现的两个关键问题:

1. 内核程序和用户程序中的协议(protocol)族和多播组都需要保持一致。您的协议(protocol)系列在用户空间中为 NETLINK_USERSOCK (2)，在内核空间中为 NETLINK_USER (31)。
2. addr.nl_groups = MYMGRP; 出于某种原因无法正常工作。不过，这样做是可行的:setsockopt(sock, 270, NETLINK_ADD_MEMBERSHIP, &group, sizeof(group))。

不致命:

1. 在这种情况下，模块不监听组消息，因此您不需要在 netlink_kernel_create() 参数中包含多播组。

此外，与 netlink 无关，但无论如何都很有用:

1. strlen() 不包括空字符。在消息分配期间，您可能应该添加一个字节来弥补这一点。
2. 在这种情况下，NLMSG_DATA(&nlh) 是未定义的行为。这是因为您的 header 和数据位于单独的内存块中，不能保证粘合在一起，并且宏所做的只是在 nlh 之后访问内存块:

#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))

这是我的代码版本:

用户空间程序:

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <sys/socket.h>
#include <linux/netlink.h>
#include <unistd.h>

/* Protocol family, consistent in both kernel prog and user prog. */
#define MYPROTO NETLINK_USERSOCK
/* Multicast group, consistent in both kernel prog and user prog. */
#define MYMGRP 21

int open_netlink(void)
{
    int sock;
    struct sockaddr_nl addr;
    int group = MYMGRP;

    sock = socket(AF_NETLINK, SOCK_RAW, MYPROTO);
    if (sock < 0) {
        printf("sock < 0.\n");
        return sock;
    }

    memset((void *) &addr, 0, sizeof(addr));
    addr.nl_family = AF_NETLINK;
    addr.nl_pid = getpid();
    /* This doesn't work for some reason. See the setsockopt() below. */
    /* addr.nl_groups = MYMGRP; */

    if (bind(sock, (struct sockaddr *) &addr, sizeof(addr)) < 0) {
        printf("bind < 0.\n");
        return -1;
    }

    /*
     * 270 is SOL_NETLINK. See
     * http://lxr.free-electrons.com/source/include/linux/socket.h?v=4.1#L314
     * and
     * http://stackoverflow.com/questions/17732044/
     */
    if (setsockopt(sock, 270, NETLINK_ADD_MEMBERSHIP, &group, sizeof(group)) < 0) {
        printf("setsockopt < 0\n");
        return -1;
    }

    return sock;
}

void read_event(int sock)
{
    struct sockaddr_nl nladdr;
    struct msghdr msg;
    struct iovec iov;
    char buffer[65536];
    int ret;

    iov.iov_base = (void *) buffer;
    iov.iov_len = sizeof(buffer);
    msg.msg_name = (void *) &(nladdr);
    msg.msg_namelen = sizeof(nladdr);
    msg.msg_iov = &iov;
    msg.msg_iovlen = 1;

    printf("Ok, listening.\n");
    ret = recvmsg(sock, &msg, 0);
    if (ret < 0)
        printf("ret < 0.\n");
    else
        printf("Received message payload: %s\n", NLMSG_DATA((struct nlmsghdr *) &buffer));
}

int main(int argc, char *argv[])
{
    int nls;

    nls = open_netlink();
    if (nls < 0)
        return nls;

    while (1)
        read_event(nls);

    return 0;
}

这是内核模块:

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <net/netlink.h>
#include <net/net_namespace.h>

/* Protocol family, consistent in both kernel prog and user prog. */
#define MYPROTO NETLINK_USERSOCK
/* Multicast group, consistent in both kernel prog and user prog. */
#define MYGRP 21

static struct sock *nl_sk = NULL;

static void send_to_user(void)
{
    struct sk_buff *skb;
    struct nlmsghdr *nlh;
    char *msg = "Hello from kernel";
    int msg_size = strlen(msg) + 1;
    int res;

    pr_info("Creating skb.\n");
    skb = nlmsg_new(NLMSG_ALIGN(msg_size + 1), GFP_KERNEL);
    if (!skb) {
        pr_err("Allocation failure.\n");
        return;
    }

    nlh = nlmsg_put(skb, 0, 1, NLMSG_DONE, msg_size + 1, 0);
    strcpy(nlmsg_data(nlh), msg);

    pr_info("Sending skb.\n");
    res = nlmsg_multicast(nl_sk, skb, 0, MYGRP, GFP_KERNEL);
    if (res < 0)
        pr_info("nlmsg_multicast() error: %d\n", res);
    else
        pr_info("Success.\n");
}

static int __init hello_init(void)
{
    pr_info("Inserting hello module.\n");

    nl_sk = netlink_kernel_create(&init_net, MYPROTO, NULL);
    if (!nl_sk) {
        pr_err("Error creating socket.\n");
        return -10;
    }

    send_to_user();

    netlink_kernel_release(nl_sk);
    return 0;
}

static void __exit hello_exit(void)
{
    pr_info("Exiting hello module.\n");
}

module_init(hello_init);
module_exit(hello_exit);

MODULE_LICENSE("GPL");

在内核 3.13 中测试。

(我可以建议人们使用 libnl-3 而不是用户空间程序的原始套接字。它的多播 Netlink 文档是 actually decent 。)