Skip to content

L
linux
Commit 0ac5b42d authored by David S. Miller's avatar David S. Miller
Browse files
Options

Merge http://kernel-acme.bkbits.net:8080/net-cleanups-2.5-icmp 

into nuts.ninka.net:/home/davem/src/BK/net-2.5
parents eb2e01d8 61903c26
Show whitespace changes
Inline Side-by-side
Showing with 454 additions and 295 deletions
net/ipv4/icmp.c
View file @ 0ac5b42d
......@@ -52,9 +52,10 @@
* the rates sysctl configurable.
* Yu Tianli : Fixed two ugly bugs in icmp_send
* - IP option length was accounted wrongly
* - ICMP header length was not accounted at all.
* Tristan Greaves : Added sysctl option to ignore bogus broadcast
* responses from broken routers.
* - ICMP header length was not accounted
* at all.
* Tristan Greaves : Added sysctl option to ignore bogus
* broadcast responses from broken routers.
*
* To Fix:
*
......@@ -95,8 +96,7 @@
* Build xmit assembly blocks
*/
struct icmp_bxm
{
struct icmp_bxm {
struct sk_buff *skb;
int offset;
int data_len;
......@@ -114,29 +114,76 @@ struct icmp_bxm
/*
* Statistics
*/
struct icmp_mib icmp_statistics[NR_CPUS*2];
struct icmp_mib icmp_statistics[NR_CPUS * 2];
/* An array of errno for error messages from dest unreach. */
/* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOS_UNREACH and SR_FAIELD MUST be considered 'transient errs'. */
struct icmp_err icmp_err_convert[] = {
{ ENETUNREACH, 0 }, /* ICMP_NET_UNREACH */
{ EHOSTUNREACH, 0 }, /* ICMP_HOST_UNREACH */
{ ENOPROTOOPT, 1 }, /* ICMP_PROT_UNREACH */
{ ECONNREFUSED, 1 }, /* ICMP_PORT_UNREACH */
{ EMSGSIZE, 0 }, /* ICMP_FRAG_NEEDED */
{ EOPNOTSUPP, 0 }, /* ICMP_SR_FAILED */
{ ENETUNREACH, 1 }, /* ICMP_NET_UNKNOWN */
{ EHOSTDOWN, 1 }, /* ICMP_HOST_UNKNOWN */
{ ENONET, 1 }, /* ICMP_HOST_ISOLATED */
{ ENETUNREACH, 1 }, /* ICMP_NET_ANO */
{ EHOSTUNREACH, 1 }, /* ICMP_HOST_ANO */
{ ENETUNREACH, 0 }, /* ICMP_NET_UNR_TOS */
{ EHOSTUNREACH, 0 }, /* ICMP_HOST_UNR_TOS */
{ EHOSTUNREACH, 1 }, /* ICMP_PKT_FILTERED */
{ EHOSTUNREACH, 1 }, /* ICMP_PREC_VIOLATION */
{ EHOSTUNREACH, 1 } /* ICMP_PREC_CUTOFF */
{
errno: ENETUNREACH, /* ICMP_NET_UNREACH */
fatal: 0,
},
{
errno: EHOSTUNREACH, /* ICMP_HOST_UNREACH */
fatal: 0,
},
{
errno: ENOPROTOOPT /* ICMP_PROT_UNREACH */,
fatal: 1,
},
{
errno: ECONNREFUSED, /* ICMP_PORT_UNREACH */
fatal: 1,
},
{
errno: EMSGSIZE, /* ICMP_FRAG_NEEDED */
fatal: 0,
},
{
errno: EOPNOTSUPP, /* ICMP_SR_FAILED */
fatal: 0,
},
{
errno: ENETUNREACH, /* ICMP_NET_UNKNOWN */
fatal: 1,
},
{
errno: EHOSTDOWN, /* ICMP_HOST_UNKNOWN */
fatal: 1,
},
{
errno: ENONET, /* ICMP_HOST_ISOLATED */
fatal: 1,
},
{
errno: ENETUNREACH, /* ICMP_NET_ANO */
fatal: 1,
},
{
errno: EHOSTUNREACH, /* ICMP_HOST_ANO */
fatal: 1,
},
{
errno: ENETUNREACH, /* ICMP_NET_UNR_TOS */
fatal: 0,
},
{
errno: EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */
fatal: 0,
},
{
errno: EHOSTUNREACH, /* ICMP_PKT_FILTERED */
fatal: 1,
},
{
errno: EHOSTUNREACH, /* ICMP_PREC_VIOLATION */
fatal: 1,
},
{
errno: EHOSTUNREACH, /* ICMP_PREC_CUTOFF */
fatal: 1,
},
};
extern int sysctl_ip_default_ttl;
......@@ -160,7 +207,7 @@ int sysctl_icmp_ignore_bogus_error_responses;
* time exceeded (11), parameter problem (12)
*/
int sysctl_icmp_ratelimit = 1*HZ;
int sysctl_icmp_ratelimit = 1 * HZ;
int sysctl_icmp_ratemask = 0x1818;
/*
......@@ -182,7 +229,6 @@ static struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
* our ICMP output as well as maintain a clean interface throughout
* all layers. All Socketless IP sends will soon be gone.
*/
struct socket *icmp_socket;
/* ICMPv4 socket is only a bit non-reenterable (unlike ICMPv6,
......@@ -194,13 +240,17 @@ static int icmp_xmit_holder = -1;
static int icmp_xmit_lock_bh(void)
{
int rc;
if (!spin_trylock(&icmp_socket->sk->lock.slock)) {
rc = -EAGAIN;
if (icmp_xmit_holder == smp_processor_id())
return -EAGAIN;
goto out;
spin_lock(&icmp_socket->sk->lock.slock);
}
rc = 0;
icmp_xmit_holder = smp_processor_id();
return 0;
out:
return rc;
}
static __inline__ int icmp_xmit_lock(void)
......@@ -251,68 +301,75 @@ static __inline__ void icmp_xmit_unlock(void)
int xrlim_allow(struct dst_entry *dst, int timeout)
{
unsigned long now;
int rc = 0;
now = jiffies;
dst->rate_tokens += now - dst->rate_last;
dst->rate_last = now;
if (dst->rate_tokens > XRLIM_BURST_FACTOR*timeout)
dst->rate_tokens = XRLIM_BURST_FACTOR*timeout;
if (dst->rate_tokens > XRLIM_BURST_FACTOR * timeout)
dst->rate_tokens = XRLIM_BURST_FACTOR * timeout;
if (dst->rate_tokens >= timeout) {
dst->rate_tokens -= timeout;
return 1;
rc = 1;
}
return 0;
return rc;
}
static inline int icmpv4_xrlim_allow(struct rtable *rt, int type, int code)
{
struct dst_entry *dst = &rt->u.dst;
int rc = 1;
if (type > NR_ICMP_TYPES)
return 1;
goto out;
/* Don't limit PMTU discovery. */
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
return 1;
goto out;
/* No rate limit on loopback */
if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
return 1;
goto out;
/* Limit if icmp type is enabled in ratemask. */
if((1 << type) & sysctl_icmp_ratemask)
return xrlim_allow(dst, sysctl_icmp_ratelimit);
else
return 1;
if ((1 << type) & sysctl_icmp_ratemask)
rc = xrlim_allow(dst, sysctl_icmp_ratelimit);
out:
return rc;
}
/*
* Maintain the counters used in the SNMP statistics for outgoing ICMP
*/
static void icmp_out_count(int type)
{
if (type>NR_ICMP_TYPES)
return;
(icmp_pointers[type].output)[(smp_processor_id()*2+!in_softirq())*sizeof(struct icmp_mib)/sizeof(unsigned long)]++;
if (type <= NR_ICMP_TYPES) {
(icmp_pointers[type].output)[(smp_processor_id() * 2 +
!in_softirq()) *
sizeof(struct icmp_mib) /
sizeof(unsigned long)]++;
ICMP_INC_STATS(IcmpOutMsgs);
}
}
/*
* Checksum each fragment, and on the first include the headers and final checksum.
* Checksum each fragment, and on the first include the headers and final
* checksum.
*/
static int icmp_glue_bits(const void *p, char *to, unsigned int offset, unsigned int fraglen)
static int icmp_glue_bits(const void *p, char *to, unsigned int offset,
unsigned int fraglen)
{
struct icmp_bxm *icmp_param = (struct icmp_bxm *)p;
struct icmphdr *icmph;
unsigned int csum;
if (offset) {
icmp_param->csum=skb_copy_and_csum_bits(icmp_param->skb,
icmp_param->offset+(offset-icmp_param->head_len),
to, fraglen,icmp_param->csum);
return 0;
icmp_param->csum =
skb_copy_and_csum_bits(icmp_param->skb,
icmp_param->offset +
(offset - icmp_param->head_len),
to, fraglen, icmp_param->csum);
goto out;
}
/*
......@@ -323,13 +380,12 @@ static int icmp_glue_bits(const void *p, char *to, unsigned int offset, unsigned
csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
to, icmp_param->head_len,
icmp_param->csum);
csum=skb_copy_and_csum_bits(icmp_param->skb,
icmp_param->offset,
to+icmp_param->head_len,
fraglen-icmp_param->head_len,
csum);
icmph=(struct icmphdr *)to;
csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset,
to + icmp_param->head_len,
fraglen - icmp_param->head_len, csum);
icmph = (struct icmphdr *)to;
icmph->checksum = csum_fold(csum);
out:
return 0;
}
......@@ -339,20 +395,18 @@ static int icmp_glue_bits(const void *p, char *to, unsigned int offset, unsigned
static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
struct sock *sk=icmp_socket->sk;
struct sock *sk = icmp_socket->sk;
struct inet_opt *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = (struct rtable*)skb->dst;
struct rtable *rt = (struct rtable *)skb->dst;
u32 daddr;
if (ip_options_echo(&icmp_param->replyopts, skb))
return;
if (icmp_xmit_lock_bh())
return;
if (ip_options_echo(&icmp_param->replyopts, skb) ||
icmp_xmit_lock_bh())
goto out;
icmp_param->data.icmph.checksum=0;
icmp_param->csum=0;
icmp_param->data.icmph.checksum = 0;
icmp_param->csum = 0;
icmp_out_count(icmp_param->data.icmph.type);
inet->tos = skb->nh.iph->tos;
......@@ -364,8 +418,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
if (ipc.opt->srr)
daddr = icmp_param->replyopts.faddr;
}
if (ip_route_output(&rt, daddr, rt->rt_spec_dst, RT_TOS(skb->nh.iph->tos), 0))
goto out;
if (ip_route_output(&rt, daddr, rt->rt_spec_dst,
RT_TOS(skb->nh.iph->tos), 0))
goto out_unlock;
if (icmpv4_xrlim_allow(rt, icmp_param->data.icmph.type,
icmp_param->data.icmph.code)) {
ip_build_xmit(sk, icmp_glue_bits, icmp_param,
......@@ -373,15 +428,17 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
&ipc, rt, MSG_DONTWAIT);
}
ip_rt_put(rt);
out:
out_unlock:
icmp_xmit_unlock_bh();
out:;
}
/*
* 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).
* 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.
......@@ -393,13 +450,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
struct iphdr *iph;
int room;
struct icmp_bxm icmp_param;
struct rtable *rt = (struct rtable*)skb_in->dst;
struct rtable *rt = (struct rtable *)skb_in->dst;
struct ipcm_cookie ipc;
u32 saddr;
u8 tos;
if (!rt)
return;
goto out;
/*
* Find the original header. It is expected to be valid, of course.
......@@ -408,56 +465,57 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
*/
iph = skb_in->nh.iph;
if ((u8*)iph < skb_in->head || (u8*)(iph+1) > skb_in->tail)
return;
if ((u8 *)iph < skb_in->head || (u8 *)(iph + 1) > skb_in->tail)
goto out;
/*
* No replies to physical multicast/broadcast
*/
if (skb_in->pkt_type!=PACKET_HOST)
return;
if (skb_in->pkt_type != PACKET_HOST)
goto out;
/*
* Now check at the protocol level
*/
if (rt->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST))
return;
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))
return;
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
* We are an error, check if we are replying to an
* ICMP error
*/
if (iph->protocol==IPPROTO_ICMP) {
if (iph->protocol == IPPROTO_ICMP) {
u8 inner_type;
if (skb_copy_bits(skb_in,
skb_in->nh.raw + (iph->ihl<<2)
+ offsetof(struct icmphdr, type)
- skb_in->data,
&inner_type, 1))
return;
skb_in->nh.raw + (iph->ihl << 2) +
offsetof(struct icmphdr, type) -
skb_in->data, &inner_type, 1))
goto out;
/*
* Assume any unknown ICMP type is an error. This isn't
* specified by the RFC, but think about it..
* Assume any unknown ICMP type is an error. This
* isn't specified by the RFC, but think about it..
*/
if (inner_type>NR_ICMP_TYPES || icmp_pointers[inner_type].error)
return;
if (inner_type > NR_ICMP_TYPES ||
icmp_pointers[inner_type].error)
goto out;
}
}
if (icmp_xmit_lock())
return;
goto out;
/*
* Construct source address and options.
......@@ -467,7 +525,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
/*
* Restore original addresses if packet has been translated.
*/
if (rt->rt_flags&RTCF_NAT && IPCB(skb_in)->flags&IPSKB_TRANSLATED) {
if (rt->rt_flags & RTCF_NAT && IPCB(skb_in)->flags & IPSKB_TRANSLATED) {
iph->daddr = rt->key.dst;
iph->saddr = rt->key.src;
}
......@@ -477,12 +535,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
if (!(rt->rt_flags & RTCF_LOCAL))
saddr = 0;
tos = icmp_pointers[type].error ?
((iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL) :
tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
if (ip_route_output(&rt, iph->saddr, saddr, RT_TOS(tos), 0))
goto out;
goto out_unlock;
if (ip_options_echo(&icmp_param.replyopts, skb_in))
goto ende;
......@@ -492,13 +550,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
* Prepare data for ICMP header.
*/
icmp_param.data.icmph.type=type;
icmp_param.data.icmph.code=code;
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.csum=0;
icmp_param.skb=skb_in;
icmp_param.offset=skb_in->nh.raw - skb_in->data;
icmp_param.data.icmph.checksum = 0;
icmp_param.csum = 0;
icmp_param.skb = skb_in;
icmp_param.offset = skb_in->nh.raw - skb_in->data;
icmp_out_count(icmp_param.data.icmph.type);
inet_sk(icmp_socket->sk)->tos = tos;
inet_sk(icmp_socket->sk)->ttl = sysctl_ip_default_ttl;
......@@ -506,8 +564,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
ipc.opt = &icmp_param.replyopts;
if (icmp_param.replyopts.srr) {
ip_rt_put(rt);
if (ip_route_output(&rt, icmp_param.replyopts.faddr, saddr, RT_TOS(tos), 0))
goto out;
if (ip_route_output(&rt, icmp_param.replyopts.faddr,
saddr, RT_TOS(tos), 0))
goto out_unlock;
}
if (!icmpv4_xrlim_allow(rt, type, code))
......@@ -521,19 +580,19 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen;
room -= sizeof(struct icmphdr);
icmp_param.data_len=skb_in->len-icmp_param.offset;
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);
ip_build_xmit(icmp_socket->sk, icmp_glue_bits, &icmp_param,
icmp_param.data_len+sizeof(struct icmphdr),
icmp_param.data_len + sizeof(struct icmphdr),
&ipc, rt, MSG_DONTWAIT);
ende:
ip_rt_put(rt);
out:
out_unlock:
icmp_xmit_unlock();
out:;
}
......@@ -556,60 +615,59 @@ static void icmp_unreach(struct sk_buff *skb)
* additional check for longer headers in upper levels.
*/
if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
ICMP_INC_STATS_BH(IcmpInErrors);
return;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out_err;
icmph = skb->h.icmph;
iph = (struct iphdr *) skb->data;
iph = (struct iphdr *)skb->data;
if (iph->ihl<5) {
/* Mangled header, drop. */
ICMP_INC_STATS_BH(IcmpInErrors);
return;
}
if (iph->ihl < 5) /* Mangled header, drop. */
goto out_err;
if(icmph->type==ICMP_DEST_UNREACH) {
switch(icmph->code & 15) {
if (icmph->type == ICMP_DEST_UNREACH) {
switch (icmph->code & 15) {
case ICMP_NET_UNREACH:
break;
case ICMP_HOST_UNREACH:
break;
case ICMP_PROT_UNREACH:
break;
case ICMP_PORT_UNREACH:
break;
case ICMP_FRAG_NEEDED:
if (ipv4_config.no_pmtu_disc) {
if (net_ratelimit())
printk(KERN_INFO "ICMP: %u.%u.%u.%u: fragmentation needed and DF set.\n",
printk(KERN_INFO "ICMP: %u.%u.%u.%u: "
"fragmentation needed "
"and DF set.\n",
NIPQUAD(iph->daddr));
} else {
info = ip_rt_frag_needed(iph, ntohs(icmph->un.frag.mtu));
info = ip_rt_frag_needed(iph,
ntohs(icmph->un.frag.mtu));
if (!info)
goto out;
}
break;
case ICMP_SR_FAILED:
if (net_ratelimit())
printk(KERN_INFO "ICMP: %u.%u.%u.%u: Source Route Failed.\n", NIPQUAD(iph->daddr));
printk(KERN_INFO "ICMP: %u.%u.%u.%u: Source "
"Route Failed.\n",
NIPQUAD(iph->daddr));
break;
default:
break;
}
if (icmph->code>NR_ICMP_UNREACH)
if (icmph->code > NR_ICMP_UNREACH)
goto out;
} else if (icmph->type == ICMP_PARAMETERPROB) {
info = ntohl(icmph->un.gateway)>>24;
}
} else if (icmph->type == ICMP_PARAMETERPROB)
info = ntohl(icmph->un.gateway) >> 24;
/*
* Throw it at our lower layers
*
* RFC 1122: 3.2.2 MUST extract the protocol ID from the passed header.
* RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the transport layer.
* RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to transport layer.
* RFC 1122: 3.2.2 MUST extract the protocol ID from the passed
* header.
* RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the
* transport layer.
* RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to
* transport layer.
*/
/*
......@@ -619,25 +677,22 @@ static void icmp_unreach(struct sk_buff *skb)
* get the other vendor to fix their kit.
*/
if (!sysctl_icmp_ignore_bogus_error_responses)
{
if (inet_addr_type(iph->daddr) == RTN_BROADCAST)
{
if (!sysctl_icmp_ignore_bogus_error_responses &&
inet_addr_type(iph->daddr) == RTN_BROADCAST) {
if (net_ratelimit())
printk(KERN_WARNING "%u.%u.%u.%u sent an invalid ICMP error to a broadcast.\n",
printk(KERN_WARNING "%u.%u.%u.%u sent an invalid ICMP "
"error to a broadcast.\n",
NIPQUAD(skb->nh.iph->saddr));
goto out;
}
}
/* Checkin full IP header plus 8 bytes of protocol to
* avoid additional coding at protocol handlers.
*/
if (!pskb_may_pull(skb, iph->ihl*4+8))
if (!pskb_may_pull(skb, iph->ihl * 4 + 8))
goto out;
iph = (struct iphdr *) skb->data;
iph = (struct iphdr *)skb->data;
protocol = iph->protocol;
/*
......@@ -647,10 +702,10 @@ static void icmp_unreach(struct sk_buff *skb)
/* Note: See raw.c and net/raw.h, RAWV4_HTABLE_SIZE==MAX_INET_PROTOS */
hash = protocol & (MAX_INET_PROTOS - 1);
read_lock(&raw_v4_lock);
if ((raw_sk = raw_v4_htable[hash]) != NULL)
{
if ((raw_sk = raw_v4_htable[hash]) != NULL) {
while ((raw_sk = __raw_v4_lookup(raw_sk, protocol, iph->daddr,
iph->saddr, skb->dev->ifindex)) != NULL) {
iph->saddr,
skb->dev->ifindex)) != NULL) {
raw_err(raw_sk, skb, info);
raw_sk = raw_sk->next;
iph = (struct iphdr *)skb->data;
......@@ -664,12 +719,11 @@ static void icmp_unreach(struct sk_buff *skb)
* we are OK.
*/
ipprot = (struct inet_protocol *) inet_protos[hash];
ipprot = (struct inet_protocol *)inet_protos[hash];
while (ipprot) {
struct inet_protocol *nextip;
nextip = (struct inet_protocol *) ipprot->next;
nextip = (struct inet_protocol *)ipprot->next;
/*
* Pass it off to everyone who wants it.
*/
......@@ -682,7 +736,11 @@ static void icmp_unreach(struct sk_buff *skb)
ipprot = nextip;
}
out:;
out:
return;
out_err:
ICMP_INC_STATS_BH(IcmpInErrors);
goto out;
}
......@@ -695,18 +753,16 @@ static void icmp_redirect(struct sk_buff *skb)
struct iphdr *iph;
unsigned long ip;
if (skb->len < sizeof(struct iphdr)) {
ICMP_INC_STATS_BH(IcmpInErrors);
return;
}
if (skb->len < sizeof(struct iphdr))
goto out_err;
/*
* Get the copied header of the packet that caused the redirect
*/
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
return;
goto out;
iph = (struct iphdr *) skb->data;
iph = (struct iphdr *)skb->data;
ip = iph->daddr;
switch (skb->h.icmph->code & 7) {
......@@ -716,22 +772,31 @@ static void icmp_redirect(struct sk_buff *skb)
* As per RFC recommendations now handle it as
* a host redirect.
*/
case ICMP_REDIR_HOST:
case ICMP_REDIR_HOSTTOS:
ip_rt_redirect(skb->nh.iph->saddr, ip, skb->h.icmph->un.gateway, iph->saddr, iph->tos, skb->dev);
ip_rt_redirect(skb->nh.iph->saddr,
ip, skb->h.icmph->un.gateway,
iph->saddr, iph->tos, skb->dev);
break;
default:
break;
}
out:
return;
out_err:
ICMP_INC_STATS_BH(IcmpInErrors);
goto out;
}
/*
* Handle ICMP_ECHO ("ping") requests.
*
* RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo requests.
* RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be included in the reply.
* RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring echo requests, MUST have default=NOT.
* RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
* requests.
* RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be
* included in the reply.
* RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring
* echo requests, MUST have default=NOT.
* See also WRT handling of options once they are done and working.
*/
......@@ -740,12 +805,12 @@ static void icmp_echo(struct sk_buff *skb)
if (!sysctl_icmp_echo_ignore_all) {
struct icmp_bxm icmp_param;
icmp_param.data.icmph=*skb->h.icmph;
icmp_param.data.icmph.type=ICMP_ECHOREPLY;
icmp_param.skb=skb;
icmp_param.offset=0;
icmp_param.data_len=skb->len;
icmp_param.head_len=sizeof(struct icmphdr);
icmp_param.data.icmph = *skb->h.icmph;
icmp_param.data.icmph.type = ICMP_ECHOREPLY;
icmp_param.skb = skb;
icmp_param.offset = 0;
icmp_param.data_len = skb->len;
icmp_param.head_len = sizeof(struct icmphdr);
icmp_reply(&icmp_param, skb);
}
}
......@@ -757,37 +822,38 @@ static void icmp_echo(struct sk_buff *skb)
* MUST be accurate to a few minutes.
* MUST be updated at least at 15Hz.
*/
static void icmp_timestamp(struct sk_buff *skb)
{
struct timeval tv;
struct icmp_bxm icmp_param;
/*
* Too short.
*/
if (skb->len < 4) {
ICMP_INC_STATS_BH(IcmpInErrors);
return;
}
if (skb->len < 4)
goto out_err;
/*
* Fill in the current time as ms since midnight UT:
*/
do_gettimeofday(&tv);
icmp_param.data.times[1] = htonl((tv.tv_sec % 86400) * 1000 + tv.tv_usec / 1000);
icmp_param.data.times[1] = htonl((tv.tv_sec % 86400) * 1000 +
tv.tv_usec / 1000);
icmp_param.data.times[2] = icmp_param.data.times[1];
if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4))
BUG();
icmp_param.data.icmph=*skb->h.icmph;
icmp_param.data.icmph.type=ICMP_TIMESTAMPREPLY;
icmp_param.data.icmph.code=0;
icmp_param.skb=skb;
icmp_param.offset=0;
icmp_param.data_len=0;
icmp_param.head_len=sizeof(struct icmphdr)+12;
icmp_param.data.icmph = *skb->h.icmph;
icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
icmp_param.data.icmph.code = 0;
icmp_param.skb = skb;
icmp_param.offset = 0;
icmp_param.data_len = 0;
icmp_param.head_len = sizeof(struct icmphdr) + 12;
icmp_reply(&icmp_param, skb);
out:
return;
out_err:
ICMP_INC_STATS_BH(IcmpInErrors);
goto out;
}
......@@ -839,35 +905,38 @@ static void icmp_address(struct sk_buff *skb)
static void icmp_address_reply(struct sk_buff *skb)
{
struct rtable *rt = (struct rtable*)skb->dst;
struct rtable *rt = (struct rtable *)skb->dst;
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct in_ifaddr *ifa;
u32 mask;
if (skb->len < 4 || !(rt->rt_flags&RTCF_DIRECTSRC))
return;
goto out;
in_dev = in_dev_get(dev);
if (!in_dev)
return;
goto out;
read_lock(&in_dev->lock);
if (in_dev->ifa_list &&
IN_DEV_LOG_MARTIANS(in_dev) &&
IN_DEV_FORWARD(in_dev)) {
if (skb_copy_bits(skb, 0, &mask, 4))
BUG();
for (ifa=in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
if (mask == ifa->ifa_mask && inet_ifa_match(rt->rt_src, ifa))
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
if (mask == ifa->ifa_mask &&
inet_ifa_match(rt->rt_src, ifa))
break;
}
if (!ifa && net_ratelimit()) {
printk(KERN_INFO "Wrong address mask %u.%u.%u.%u from %s/%u.%u.%u.%u\n",
printk(KERN_INFO "Wrong address mask %u.%u.%u.%u from "
"%s/%u.%u.%u.%u\n",
NIPQUAD(mask), dev->name, NIPQUAD(rt->rt_src));
}
}
read_unlock(&in_dev->lock);
in_dev_put(in_dev);
out:;
}
static void icmp_discard(struct sk_buff *skb)
......@@ -877,19 +946,19 @@ static void icmp_discard(struct sk_buff *skb)
/*
* Deal with incoming ICMP packets.
*/
int icmp_rcv(struct sk_buff *skb)
{
struct icmphdr *icmph;
struct rtable *rt = (struct rtable*)skb->dst;
struct rtable *rt = (struct rtable *)skb->dst;
ICMP_INC_STATS_BH(IcmpInMsgs);
switch (skb->ip_summed) {
case CHECKSUM_HW:
if ((u16)csum_fold(skb->csum) == 0)
if (!(u16)csum_fold(skb->csum))
break;
NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "icmp v4 hw csum failure\n"));
NETDEBUG(if (net_ratelimit())
printk(KERN_DEBUG "icmp v4 hw csum failure\n"));
case CHECKSUM_NONE:
if ((u16)csum_fold(skb_checksum(skb, 0, skb->len, 0)))
goto error;
......@@ -904,7 +973,8 @@ int icmp_rcv(struct sk_buff *skb)
/*
* 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.
* RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
* discarded.
*/
if (icmph->type > NR_ICMP_TYPES)
goto error;
......@@ -914,7 +984,7 @@ int icmp_rcv(struct sk_buff *skb)
* Parse the ICMP message
*/
if (rt->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST)) {
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).
......@@ -933,7 +1003,9 @@ int icmp_rcv(struct sk_buff *skb)
}
}
icmp_pointers[icmph->type].input[smp_processor_id()*2*sizeof(struct icmp_mib)/sizeof(unsigned long)]++;
icmp_pointers[icmph->type].input[smp_processor_id() * 2 *
sizeof(struct icmp_mib) /
sizeof(unsigned long)]++;
(icmp_pointers[icmph->type].handler)(skb);
drop:
......@@ -947,40 +1019,127 @@ int icmp_rcv(struct sk_buff *skb)
/*
* This table is the definition of how we handle ICMP.
*/
static struct icmp_control icmp_pointers[NR_ICMP_TYPES+1] = {
/* ECHO REPLY (0) */
{ &icmp_statistics[0].IcmpOutEchoReps, &icmp_statistics[0].IcmpInEchoReps, icmp_discard, 0 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
/* DEST UNREACH (3) */
{ &icmp_statistics[0].IcmpOutDestUnreachs, &icmp_statistics[0].IcmpInDestUnreachs, icmp_unreach, 1 },
/* SOURCE QUENCH (4) */
{ &icmp_statistics[0].IcmpOutSrcQuenchs, &icmp_statistics[0].IcmpInSrcQuenchs, icmp_unreach, 1 },
/* REDIRECT (5) */
{ &icmp_statistics[0].IcmpOutRedirects, &icmp_statistics[0].IcmpInRedirects, icmp_redirect, 1 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
/* ECHO (8) */
{ &icmp_statistics[0].IcmpOutEchos, &icmp_statistics[0].IcmpInEchos, icmp_echo, 0 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
{ &icmp_statistics[0].dummy, &icmp_statistics[0].IcmpInErrors, icmp_discard, 1 },
/* TIME EXCEEDED (11) */
{ &icmp_statistics[0].IcmpOutTimeExcds, &icmp_statistics[0].IcmpInTimeExcds, icmp_unreach, 1 },
/* PARAMETER PROBLEM (12) */
{ &icmp_statistics[0].IcmpOutParmProbs, &icmp_statistics[0].IcmpInParmProbs, icmp_unreach, 1 },
/* TIMESTAMP (13) */
{ &icmp_statistics[0].IcmpOutTimestamps, &icmp_statistics[0].IcmpInTimestamps, icmp_timestamp, 0 },
/* TIMESTAMP REPLY (14) */
{ &icmp_statistics[0].IcmpOutTimestampReps, &icmp_statistics[0].IcmpInTimestampReps, icmp_discard, 0 },
/* INFO (15) */
{ &icmp_statistics[0].dummy, &icmp_statistics[0].dummy, icmp_discard, 0 },
/* INFO REPLY (16) */
{ &icmp_statistics[0].dummy, &icmp_statistics[0].dummy, icmp_discard, 0 },
/* ADDR MASK (17) */
{ &icmp_statistics[0].IcmpOutAddrMasks, &icmp_statistics[0].IcmpInAddrMasks, icmp_address, 0 },
/* ADDR MASK REPLY (18) */
{ &icmp_statistics[0].IcmpOutAddrMaskReps, &icmp_statistics[0].IcmpInAddrMaskReps, icmp_address_reply, 0 }
static struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
/* ECHO REPLY (0) */
[0] = {
output: &icmp_statistics[0].IcmpOutEchoReps,
input: &icmp_statistics[0].IcmpInEchoReps,
handler: icmp_discard,
},
[1] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
[2] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
/* DEST UNREACH (3) */
[3] = {
output: &icmp_statistics[0].IcmpOutDestUnreachs,
input: &icmp_statistics[0].IcmpInDestUnreachs,
handler: icmp_unreach,
error: 1,
},
/* SOURCE QUENCH (4) */
[4] = {
output: &icmp_statistics[0].IcmpOutSrcQuenchs,
input: &icmp_statistics[0].IcmpInSrcQuenchs,
icmp_unreach,
error: 1,
},
/* REDIRECT (5) */
[5] = {
output: &icmp_statistics[0].IcmpOutRedirects,
input: &icmp_statistics[0].IcmpInRedirects,
handler: icmp_redirect,
error: 1,
},
[6] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
[7] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
/* ECHO (8) */
[8] = {
output: &icmp_statistics[0].IcmpOutEchos,
input: &icmp_statistics[0].IcmpInEchos,
handler: icmp_echo,
error: 0,
},
[9] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
[10] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].IcmpInErrors,
handler: icmp_discard,
error: 1,
},
/* TIME EXCEEDED (11) */
[11] = {
output: &icmp_statistics[0].IcmpOutTimeExcds,
input: &icmp_statistics[0].IcmpInTimeExcds,
handler: icmp_unreach,
error: 1,
},
/* PARAMETER PROBLEM (12) */
[12] = {
output: &icmp_statistics[0].IcmpOutParmProbs,
input: &icmp_statistics[0].IcmpInParmProbs,
handler: icmp_unreach,
error: 1,
},
/* TIMESTAMP (13) */
[13] = {
output: &icmp_statistics[0].IcmpOutTimestamps,
input: &icmp_statistics[0].IcmpInTimestamps,
handler: icmp_timestamp,
},
/* TIMESTAMP REPLY (14) */
[14] = {
output: &icmp_statistics[0].IcmpOutTimestampReps,
input: &icmp_statistics[0].IcmpInTimestampReps,
handler: icmp_discard,
},
/* INFO (15) */
[15] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].dummy,
handler: icmp_discard,
},
/* INFO REPLY (16) */
[16] = {
output: &icmp_statistics[0].dummy,
input: &icmp_statistics[0].dummy,
handler: icmp_discard,
},
/* ADDR MASK (17) */
[17] = {
output: &icmp_statistics[0].IcmpOutAddrMasks,
input: &icmp_statistics[0].IcmpInAddrMasks,
handler: icmp_address,
},
/* ADDR MASK REPLY (18) */
[18] = {
output: &icmp_statistics[0].IcmpOutAddrMaskReps,
input: &icmp_statistics[0].IcmpInAddrMaskReps,
handler: icmp_address_reply,
}
};
void __init icmp_init(struct net_proto_family *ops)
......@@ -990,8 +1149,8 @@ void __init icmp_init(struct net_proto_family *ops)
if (err < 0)
panic("Failed to create the ICMP control socket.\n");
icmp_socket->sk->allocation=GFP_ATOMIC;
icmp_socket->sk->sndbuf = SK_WMEM_MAX*2;
icmp_socket->sk->allocation = GFP_ATOMIC;
icmp_socket->sk->sndbuf = SK_WMEM_MAX * 2;
inet = inet_sk(icmp_socket->sk);
inet->ttl = MAXTTL;
inet->pmtudisc = IP_PMTUDISC_DONT;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7