aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/icmp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/icmp.c')
-rw-r--r--net/ipv4/icmp.c128
1 files changed, 93 insertions, 35 deletions
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 17ff9fd7cdd..42b7bcf8045 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -337,6 +337,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
struct sock *sk;
struct inet_sock *inet;
__be32 daddr, saddr;
+ u32 mark = IP4_REPLY_MARK(net, skb->mark);
if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
return;
@@ -349,10 +350,14 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
icmp_param->data.icmph.checksum = 0;
inet->tos = ip_hdr(skb)->tos;
+ sk->sk_mark = mark;
daddr = ipc.addr = ip_hdr(skb)->saddr;
saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
+
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
if (ipc.opt->opt.srr)
@@ -361,6 +366,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.saddr = saddr;
+ fl4.flowi4_mark = mark;
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
@@ -379,7 +385,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
const struct iphdr *iph,
- __be32 saddr, u8 tos,
+ __be32 saddr, u8 tos, u32 mark,
int type, int code,
struct icmp_bxm *param)
{
@@ -391,6 +397,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->daddr = (param->replyopts.opt.opt.srr ?
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
+ fl4->flowi4_mark = mark;
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
@@ -482,12 +489,13 @@ 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 icmp_bxm *icmp_param;
struct rtable *rt = skb_rtable(skb_in);
struct ipcm_cookie ipc;
struct flowi4 fl4;
__be32 saddr;
u8 tos;
+ u32 mark;
struct net *net;
struct sock *sk;
@@ -503,7 +511,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
iph = ip_hdr(skb_in);
if ((u8 *)iph < skb_in->head ||
- (skb_in->network_header + sizeof(*iph)) > skb_in->tail)
+ (skb_network_header(skb_in) + sizeof(*iph)) >
+ skb_tail_pointer(skb_in))
goto out;
/*
@@ -557,9 +566,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
}
}
+ icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC);
+ if (!icmp_param)
+ return;
+
sk = icmp_xmit_lock(net);
if (sk == NULL)
- return;
+ goto out_free;
/*
* Construct source address and options.
@@ -584,8 +597,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
+ mark = IP4_REPLY_MARK(net, skb_in->mark);
- if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
+ if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
goto out_unlock;
@@ -593,19 +607,22 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
* 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);
+ 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;
+ sk->sk_mark = mark;
ipc.addr = iph->saddr;
- ipc.opt = &icmp_param.replyopts.opt;
+ ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
- rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
- type, code, &icmp_param);
+ rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
+ type, code, icmp_param);
if (IS_ERR(rt))
goto out_unlock;
@@ -617,19 +634,21 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
room = dst_mtu(&rt->dst);
if (room > 576)
room = 576;
- room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
+ room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.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_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, &fl4, &ipc, &rt);
+ icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
+out_free:
+ kfree(icmp_param);
out:;
}
EXPORT_SYMBOL(icmp_send);
@@ -656,8 +675,19 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
rcu_read_unlock();
}
+static bool icmp_tag_validation(int proto)
+{
+ bool ok;
+
+ rcu_read_lock();
+ ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
+ rcu_read_unlock();
+ return ok;
+}
+
/*
- * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH.
+ * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ * ICMP_PARAMETERPROB.
*/
static void icmp_unreach(struct sk_buff *skb)
@@ -692,13 +722,23 @@ static void icmp_unreach(struct sk_buff *skb)
case ICMP_PORT_UNREACH:
break;
case ICMP_FRAG_NEEDED:
- if (ipv4_config.no_pmtu_disc) {
+ /* for documentation of the ip_no_pmtu_disc
+ * values please see
+ * Documentation/networking/ip-sysctl.txt
+ */
+ switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+ default:
LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"),
&iph->daddr);
- } else {
- info = ntohs(icmph->un.frag.mtu);
- if (!info)
+ break;
+ case 2:
+ goto out;
+ case 3:
+ if (!icmp_tag_validation(iph->protocol))
goto out;
+ /* fall through */
+ case 0:
+ info = ntohs(icmph->un.frag.mtu);
}
break;
case ICMP_SR_FAILED:
@@ -873,16 +913,8 @@ int icmp_rcv(struct sk_buff *skb)
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 (skb_checksum_simple_validate(skb))
+ goto csum_error;
if (!pskb_pull(skb, sizeof(*icmph)))
goto error;
@@ -929,11 +961,37 @@ int icmp_rcv(struct sk_buff *skb)
drop:
kfree_skb(skb);
return 0;
+csum_error:
+ ICMP_INC_STATS_BH(net, ICMP_MIB_CSUMERRORS);
error:
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
goto drop;
}
+void icmp_err(struct sk_buff *skb, u32 info)
+{
+ struct iphdr *iph = (struct iphdr *)skb->data;
+ int offset = iph->ihl<<2;
+ struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
+ int type = icmp_hdr(skb)->type;
+ int code = icmp_hdr(skb)->code;
+ struct net *net = dev_net(skb->dev);
+
+ /*
+ * Use ping_err to handle all icmp errors except those
+ * triggered by ICMP_ECHOREPLY which sent from kernel.
+ */
+ if (icmph->type != ICMP_ECHOREPLY) {
+ ping_err(skb, offset, info);
+ return;
+ }
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
+ else if (type == ICMP_REDIRECT)
+ ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
+}
+
/*
* This table is the definition of how we handle ICMP.
*/
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 02:33:38 +0000