ICMP:Internet控制报文协议实现学习笔记
ICMP是网络层的一个协议，可以看作IP协议的附属协议，因为它主要被IP用来与其他主机或路由器交换错误报文及其他需要注意的信息。当然，更高层协议(tcp/udp)甚至有些用户进程也可能用到ICMP报文
注册ICMP协议和ICMP协议的处理涉及以下文件：
net/ipv4/icmp.c ICMP协议处理入口
net/ipv4/af_inet.c 网络层和传输层接口
ICMP报文结构
参见tcp/ip协议学习笔记(5)Internet Control Message Protocol(ICMP)
注册ICMP报文类型
ICMP的net_protocol结构为icmp_protocol，定义了接收ICMP报文例程为icmp_rcv。
static const struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
.no_policy = 1,
.netns_ok = 1,
};
ICMP的初始化
static int __net_init icmp_sk_init(struct net *net)
{
int i, err;
net->ipv4.icmp_sk =
kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
if (net->ipv4.icmp_sk == NULL)
return -ENOMEM;
for_each_possible_cpu(i) {
struct sock *sk;
err = inet_ctl_sock_create(&sk, PF_INET,
SOCK_RAW, IPPROTO_ICMP, net);
if (err < 0)
goto fail;
net->ipv4.icmp_sk[i] = sk;
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
sk->sk_sndbuf =
(2 * ((64 * 1024) + sizeof(struct sk_buff)));
inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
}
/* Control parameters for ECHO replies. */
net->ipv4.sysctl_icmp_echo_ignore_all = 0;
net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1;
/* Control parameter - ignore bogus broadcast responses? */
net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1;
/*
* Configurable global rate limit.
*
* ratelimit defines tokens/packet consumed for dst->rate_token
* bucket ratemask defines which icmp types are ratelimited by
* setting it's bit position.
*
* default:
* dest unreachable (3), source quench (4),
* time exceeded (11), parameter problem (12)
*/
net->ipv4.sysctl_icmp_ratelimit = 1 * HZ;
net->ipv4.sysctl_icmp_ratemask = 0x1818;
net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
return 0;
fail:
for_each_possible_cpu(i)
inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
kfree(net->ipv4.icmp_sk);
return err;
}
static struct pernet_operations __net_initdata icmp_sk_ops = {
.init = icmp_sk_init,
.exit = icmp_sk_exit,
};
int __init icmp_init(void)
{
return register_pernet_subsys(&icmp_sk_ops);
}输入处理
ICMP输入处理函数是icmp_rcv()。ICMP报文到达时，IP层通过inet_protos[IPPROTO_ICMP]找到该函数进行输入处理。进入icmp_rcv()后，首先对ICMP报文中的参数作适当的校验，然后就会根据ICMP报文类型进行不同处理。
一个类型的ICMP报文对应一个icmp_control结构，在内核中定义了一个该结构类型的数组icmp_pointers[NR_ICMP_TYPES + 1]用来管理ICMP报文，icmp_control结构如下所示：
struct icmp_control {
void (*handler)(struct sk_buff *skb);
short error; /* This ICMP is classed as an error message */
};error值为1时表示是一个差错报文；为0则是一个查询ICMP报文。
#define ICMP_ECHOREPLY 0 /* Echo Reply */
#define ICMP_DEST_UNREACH 3 /* Destination Unreachable */
#define ICMP_SOURCE_QUENCH 4 /* Source Quench */
#define ICMP_REDIRECT 5 /* Redirect (change route) */
#define ICMP_ECHO 8 /* Echo Request */
#define ICMP_TIME_EXCEEDED 11 /* Time Exceeded */
#define ICMP_PARAMETERPROB 12 /* Parameter Problem */
#define ICMP_TIMESTAMP 13 /* Timestamp Request */
#define ICMP_TIMESTAMPREPLY 14 /* Timestamp Reply */
#define ICMP_INFO_REQUEST 15 /* Information Request */
#define ICMP_INFO_REPLY 16 /* Information Reply */
#define ICMP_ADDRESS 17 /* Address Mask Request */
#define ICMP_ADDRESSREPLY 18 /* Address Mask Reply */
#define NR_ICMP_TYPES 18
/*
* This table is the definition of how we handle ICMP.
*/
static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
[ICMP_ECHOREPLY] = {
.handler = icmp_discard,
},
[1] = {
.handler = icmp_discard,
.error = 1,
},
[2] = {
.handler = icmp_discard,
.error = 1,
},
[ICMP_DEST_UNREACH] = {
.handler = icmp_unreach,
.error = 1,
},
[ICMP_SOURCE_QUENCH] = {
.handler = icmp_unreach,
.error = 1,
},
[ICMP_REDIRECT] = {
.handler = icmp_redirect,
.error = 1,
},
[6] = {
.handler = icmp_discard,
.error = 1,
},
[7] = {
.handler = icmp_discard,
.error = 1,
},
[ICMP_ECHO] = {
.handler = icmp_echo,
},
[9] = {
.handler = icmp_discard,
.error = 1,
},
[10] = {
.handler = icmp_discard,
.error = 1,
},
[ICMP_TIME_EXCEEDED] = {
.handler = icmp_unreach,
.error = 1,
},
[ICMP_PARAMETERPROB] = {
.handler = icmp_unreach,
.error = 1,
},
[ICMP_TIMESTAMP] = {
.handler = icmp_timestamp,
},
[ICMP_TIMESTAMPREPLY] = {
.handler = icmp_discard,
},
[ICMP_INFO_REQUEST] = {
.handler = icmp_discard,
},
[ICMP_INFO_REPLY] = {
.handler = icmp_discard,
},
[ICMP_ADDRESS] = {
.handler = icmp_address,
},
[ICMP_ADDRESSREPLY] = {
.handler = icmp_address_reply,
},
};
/*
* Deal with incoming ICMP packets.
*/
int icmp_rcv(struct sk_buff *skb)
{
struct icmphdr *icmph;
struct rtable *rt = skb_rtable(skb);
struct net *net = dev_net(rt->u.dst.dev);
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
struct sec_path *sp = skb_sec_path(skb);
int nh;
if (!(sp && sp->xvec[sp->len - 1]->props.flags &
XFRM_STATE_ICMP))
goto drop;
if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr)))
goto drop;
nh = skb_network_offset(skb);
skb_set_network_header(skb, sizeof(*icmph));
if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
goto drop;
skb_set_network_header(skb, nh);
}
ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS);
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (!csum_fold(skb->csum))
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
if (__skb_checksum_complete(skb))
goto error;
}
if (!pskb_pull(skb, sizeof(*icmph)))
goto error;
icmph = icmp_hdr(skb);
ICMPMSGIN_INC_STATS_BH(net, icmph->type);
/*
* 18 is the highest 'known' ICMP type. Anything else is a mystery
*
* RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
* discarded.
*/
if (icmph->type > NR_ICMP_TYPES)
goto error;
/*
* Parse the ICMP message
*/
if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
/*
* RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be
* silently ignored (we let user decide with a sysctl).
* RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently
* discarded if to broadcast/multicast.
*/
if ((icmph->type == ICMP_ECHO ||
icmph->type == ICMP_TIMESTAMP) &&
net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
goto error;
}
if (icmph->type != ICMP_ECHO &&
icmph->type != ICMP_TIMESTAMP &&
icmph->type != ICMP_ADDRESS &&
icmph->type != ICMP_ADDRESSREPLY) {
goto error;
}
}
icmp_pointers[icmph->type].handler(skb);
drop:
kfree_skb(skb);
return 0;
error:
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
goto drop;
}
输出处理
发送ICMP报文
icmp_send()用于输出各种指定类型和编码的ICMP报文，但用该函数不能应答目的地址为组播或广播类型的硬件地址或IP地址的报文
/*
* Send an ICMP message in response to a situation
*
* RFC 1122: 3.2.2 MUST send at least the IP header and 8 bytes of header.
* MAY send more (we do).
* MUST NOT change this header information.
* MUST NOT reply to a multicast/broadcast IP address.
* MUST NOT reply to a multicast/broadcast MAC address.
* MUST reply to only the first fragment.
*/
void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
struct iphdr *iph;
int room;
struct icmp_bxm icmp_param;
struct rtable *rt = skb_rtable(skb_in);
struct ipcm_cookie ipc;
__be32 saddr;
u8 tos;
struct net *net;
struct sock *sk;
if (!rt)
goto out;
net = dev_net(rt->u.dst.dev);
/*
* Find the original header. It is expected to be valid, of course.
* Check this, icmp_send is called from the most obscure devices
* sometimes.
*/
iph = ip_hdr(skb_in);
if ((u8 *)iph < skb_in->head ||
(skb_in->network_header + sizeof(*iph)) > skb_in->tail)
goto out;
/*
* No replies to physical multicast/broadcast
*/
if (skb_in->pkt_type != PACKET_HOST)
goto out;
/*
* Now check at the protocol level
*/
if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
goto out;
/*
* Only reply to fragment 0. We byte re-order the constant
* mask for efficiency.
*/
if (iph->frag_off & htons(IP_OFFSET))
goto out;
/*
* If we send an ICMP error to an ICMP error a mess would result..
*/
if (icmp_pointers[type].error) {
/*
* We are an error, check if we are replying to an
* ICMP error
*/
if (iph->protocol == IPPROTO_ICMP) {
u8 _inner_type, *itp;
itp = skb_header_pointer(skb_in,
skb_network_header(skb_in) +
(iph->ihl << 2) +
offsetof(struct icmphdr,
type) -
skb_in->data,
sizeof(_inner_type),
&_inner_type);
if (itp == NULL)
goto out;
/*
* Assume any unknown ICMP type is an error. This
* isn't specified by the RFC, but think about it..
*/
if (*itp > NR_ICMP_TYPES ||
icmp_pointers[*itp].error)
goto out;
}
}
sk = icmp_xmit_lock(net);
if (sk == NULL)
return;
/*
* Construct source address and options.
*/
saddr = iph->daddr;
if (!(rt->rt_flags & RTCF_LOCAL)) {
struct net_device *dev = NULL;
if (rt->fl.iif &&
net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
dev = dev_get_by_index(net, rt->fl.iif);
if (dev) {
saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
dev_put(dev);
} else
saddr = 0;
}
tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
if (ip_options_echo(&icmp_param.replyopts, skb_in))
goto out_unlock;
/*
* Prepare data for ICMP header.
*/
icmp_param.data.icmph.type = type;
icmp_param.data.icmph.code = code;
icmp_param.data.icmph.un.gateway = info;
icmp_param.data.icmph.checksum = 0;
icmp_param.skb = skb_in;
icmp_param.offset = skb_network_offset(skb_in);
inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts;
ipc.shtx.flags = 0;
{
struct flowi fl = {
.nl_u = {
.ip4_u = {
.daddr = icmp_param.replyopts.srr ?
icmp_param.replyopts.faddr :
iph->saddr,
.saddr = saddr,
.tos = RT_TOS(tos)
}
},
.proto = IPPROTO_ICMP,
.uli_u = {
.icmpt = {
.type = type,
.code = code
}
}
};
int err;
struct rtable *rt2;
security_skb_classify_flow(skb_in, &fl);
if (__ip_route_output_key(net, &rt, &fl))
goto out_unlock;
/* No need to clone since we're just using its address. */
rt2 = rt;
err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0);
switch (err) {
case 0:
if (rt != rt2)
goto route_done;
break;
case -EPERM:
rt = NULL;
break;
default:
goto out_unlock;
}
if (xfrm_decode_session_reverse(skb_in, &fl, AF_INET))
goto relookup_failed;
if (inet_addr_type(net, fl.fl4_src) == RTN_LOCAL)
err = __ip_route_output_key(net, &rt2, &fl);
else {
struct flowi fl2 = {};
struct dst_entry *odst;
fl2.fl4_dst = fl.fl4_src;
if (ip_route_output_key(net, &rt2, &fl2))
goto relookup_failed;
/* Ugh! */
odst = skb_dst(skb_in);
err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src,
RT_TOS(tos), rt2->u.dst.dev);
dst_release(&rt2->u.dst);
rt2 = skb_rtable(skb_in);
skb_dst_set(skb_in, odst);
}
if (err)
goto relookup_failed;
err = xfrm_lookup(net, (struct dst_entry **)&rt2, &fl, NULL,
XFRM_LOOKUP_ICMP);
switch (err) {
case 0:
dst_release(&rt->u.dst);
rt = rt2;
break;
case -EPERM:
goto ende;
default:
relookup_failed:
if (!rt)
goto out_unlock;
break;
}
}
route_done:
if (!icmpv4_xrlim_allow(net, rt, type, code))
goto ende;
/* RFC says return as much as we can without exceeding 576 bytes. */
room = dst_mtu(&rt->u.dst);
if (room > 576)
room = 576;
room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen;
room -= sizeof(struct icmphdr);
icmp_param.data_len = skb_in->len - icmp_param.offset;
if (icmp_param.data_len > room)
icmp_param.data_len = room;
icmp_param.head_len = sizeof(struct icmphdr);
icmp_push_reply(&icmp_param, &ipc, &rt);
ende:
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
out:;
}
/*
* Driving logic for building and sending ICMP messages.
*/
static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
struct ipcm_cookie ipc;
struct rtable *rt = skb_rtable(skb);
struct net *net = dev_net(rt->u.dst.dev);
struct sock *sk;
struct inet_sock *inet;
__be32 daddr;
if (ip_options_echo(&icmp_param->replyopts, skb))
return;
sk = icmp_xmit_lock(net);
if (sk == NULL)
return;
inet = inet_sk(sk);
icmp_param->data.icmph.checksum = 0;
inet->tos = ip_hdr(skb)->tos;
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
ipc.shtx.flags = 0;
if (icmp_param->replyopts.optlen) {
ipc.opt = &icmp_param->replyopts;
if (ipc.opt->srr)
daddr = icmp_param->replyopts.faddr;
}
{
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = daddr,
.saddr = rt->rt_spec_dst,
.tos = RT_TOS(ip_hdr(skb)->tos) } },
.proto = IPPROTO_ICMP };
security_skb_classify_flow(skb, &fl);
if (ip_route_output_key(net, &rt, &fl))
goto out_unlock;
}
if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type,
icmp_param->data.icmph.code))
icmp_push_reply(icmp_param, &ipc, &rt);
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
}