* [v8 PATCH 1/3] NETFILTER added flags to ipv6_find_hdr()
2012-01-27 14:41 [v8 PATCH 0/3] NETFILTER new target module, HMARK Hans Schillstrom
@ 2012-01-27 14:41 ` Hans Schillstrom
2012-01-27 14:41 ` [v8 PATCH 2/3] NETFILTER module xt_hmark, new target for HASH based fwmark Hans Schillstrom
2012-01-27 14:41 ` [v8 PATCH 3/3] NETFILTER userspace part for target HMARK Hans Schillstrom
2 siblings, 0 replies; 10+ messages in thread
From: Hans Schillstrom @ 2012-01-27 14:41 UTC (permalink / raw)
To: kaber, pablo, jengelh, netfilter-devel, netdev; +Cc: hans, Hans Schillstrom
Two new flags to ipv6_find_hdr,
One that tells us that this is a fragment.
One that stops at AH if any i.e. treat it like a transport header.
i.e. make handling of ESP and AH the same.
Param offset can now point to an inner icmp ipv5 header.
Version 3:
offset param into ipv6_find_hdr set to zero.
Version 2:
wrapper removed and changes made at every call.
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
---
include/linux/netfilter_ipv6/ip6_tables.h | 8 +++++-
net/ipv6/netfilter/ip6_tables.c | 35 ++++++++++++++++++++++++----
net/ipv6/netfilter/ip6t_ah.c | 4 +-
net/ipv6/netfilter/ip6t_frag.c | 4 +-
net/ipv6/netfilter/ip6t_hbh.c | 4 +-
net/ipv6/netfilter/ip6t_rt.c | 4 +-
net/netfilter/xt_TPROXY.c | 4 +-
net/netfilter/xt_socket.c | 4 +-
8 files changed, 49 insertions(+), 18 deletions(-)
diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index f549adc..e1ad013 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -288,9 +288,15 @@ extern unsigned int ip6t_do_table(struct sk_buff *skb,
/* Check for an extension */
extern int ip6t_ext_hdr(u8 nexthdr);
+enum {
+ IP6T_FH_FRAG,
+ IP6T_FH_AUTH,
+ IP6T_FH_F_FRAG = 1 << IP6T_FH_FRAG,
+ IP6T_FH_F_AUTH = 1 << IP6T_FH_AUTH,
+};
/* find specified header and get offset to it */
extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
- int target, unsigned short *fragoff);
+ int target, unsigned short *fragoff, int *fragflg);
#ifdef CONFIG_COMPAT
#include <net/compat.h>
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 94874b0..9dab6a8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -146,7 +146,7 @@ ip6_packet_match(const struct sk_buff *skb,
int protohdr;
unsigned short _frag_off;
- protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off);
+ protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL);
if (protohdr < 0) {
if (_frag_off == 0)
*hotdrop = true;
@@ -375,6 +375,7 @@ ip6t_do_table(struct sk_buff *skb,
const struct xt_entry_match *ematch;
IP_NF_ASSERT(e);
+ acpar.thoff = 0;
if (!ip6_packet_match(skb, indev, outdev, &e->ipv6,
&acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) {
no_match:
@@ -2290,6 +2291,8 @@ static void __exit ip6_tables_fini(void)
* find the offset to specified header or the protocol number of last header
* if target < 0. "last header" is transport protocol header, ESP, or
* "No next header".
+ * Note, *offset is used as input param. an if != 0
+ * it must be an offset to an inner ipv6 header ex. icmp error
*
* If target header is found, its offset is set in *offset and return protocol
* number. Otherwise, return -1.
@@ -2302,17 +2305,34 @@ static void __exit ip6_tables_fini(void)
* *offset is meaningless and fragment offset is stored in *fragoff if fragoff
* isn't NULL.
*
+ * if flags != NULL AND
+ * it's a fragment the frag flag "IP6T_FH_F_FRAG" will be set
+ * it's an AH header and IP6T_FH_F_AUTH is set and target < 0
+ * stop at AH (i.e. treat is as a transport header)
*/
int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
- int target, unsigned short *fragoff)
+ int target, unsigned short *fragoff, int *flags)
{
unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
u8 nexthdr = ipv6_hdr(skb)->nexthdr;
- unsigned int len = skb->len - start;
+ unsigned int len;
if (fragoff)
*fragoff = 0;
+ if (*offset) {
+ struct ipv6hdr _ip6, *ip6;
+
+ ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6);
+ if (!ip6 || (ip6->version != 6)) {
+ printk(KERN_ERR "IPv6 header not found\n");
+ return -EBADMSG;
+ }
+ start = *offset + sizeof(struct ipv6hdr);
+ nexthdr = ip6->nexthdr;
+ }
+ len = skb->len - start;
+
while (nexthdr != target) {
struct ipv6_opt_hdr _hdr, *hp;
unsigned int hdrlen;
@@ -2329,6 +2349,9 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
if (nexthdr == NEXTHDR_FRAGMENT) {
unsigned short _frag_off;
__be16 *fp;
+
+ if (flags) /* Indicate that this is a fragment */
+ *flags |= IP6T_FH_F_FRAG;
fp = skb_header_pointer(skb,
start+offsetof(struct frag_hdr,
frag_off),
@@ -2349,9 +2372,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
return -ENOENT;
}
hdrlen = 8;
- } else if (nexthdr == NEXTHDR_AUTH)
+ } else if (nexthdr == NEXTHDR_AUTH) {
+ if (flags && (*flags & IP6T_FH_F_AUTH) && (target < 0))
+ break;
hdrlen = (hp->hdrlen + 2) << 2;
- else
+ } else
hdrlen = ipv6_optlen(hp);
nexthdr = hp->nexthdr;
diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c
index 89cccc5..04099ab 100644
--- a/net/ipv6/netfilter/ip6t_ah.c
+++ b/net/ipv6/netfilter/ip6t_ah.c
@@ -41,11 +41,11 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par)
struct ip_auth_hdr _ah;
const struct ip_auth_hdr *ah;
const struct ip6t_ah *ahinfo = par->matchinfo;
- unsigned int ptr;
+ unsigned int ptr = 0;
unsigned int hdrlen = 0;
int err;
- err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL);
+ err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL);
if (err < 0) {
if (err != -ENOENT)
par->hotdrop = true;
diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c
index eda898f..3b5735e 100644
--- a/net/ipv6/netfilter/ip6t_frag.c
+++ b/net/ipv6/netfilter/ip6t_frag.c
@@ -40,10 +40,10 @@ frag_mt6(const struct sk_buff *skb, struct xt_action_param *par)
struct frag_hdr _frag;
const struct frag_hdr *fh;
const struct ip6t_frag *fraginfo = par->matchinfo;
- unsigned int ptr;
+ unsigned int ptr = 0;
int err;
- err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL);
+ err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL);
if (err < 0) {
if (err != -ENOENT)
par->hotdrop = true;
diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c
index 59df051..01df142 100644
--- a/net/ipv6/netfilter/ip6t_hbh.c
+++ b/net/ipv6/netfilter/ip6t_hbh.c
@@ -50,7 +50,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
const struct ipv6_opt_hdr *oh;
const struct ip6t_opts *optinfo = par->matchinfo;
unsigned int temp;
- unsigned int ptr;
+ unsigned int ptr = 0;
unsigned int hdrlen = 0;
bool ret = false;
u8 _opttype;
@@ -62,7 +62,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
err = ipv6_find_hdr(skb, &ptr,
(par->match == &hbh_mt6_reg[0]) ?
- NEXTHDR_HOP : NEXTHDR_DEST, NULL);
+ NEXTHDR_HOP : NEXTHDR_DEST, NULL, NULL);
if (err < 0) {
if (err != -ENOENT)
par->hotdrop = true;
diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index d8488c5..2c99b94 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -42,14 +42,14 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
const struct ipv6_rt_hdr *rh;
const struct ip6t_rt *rtinfo = par->matchinfo;
unsigned int temp;
- unsigned int ptr;
+ unsigned int ptr = 0;
unsigned int hdrlen = 0;
bool ret = false;
struct in6_addr _addr;
const struct in6_addr *ap;
int err;
- err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL);
+ err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL, NULL);
if (err < 0) {
if (err != -ENOENT)
par->hotdrop = true;
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 35a959a..146033a 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -282,10 +282,10 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
struct sock *sk;
const struct in6_addr *laddr;
__be16 lport;
- int thoff;
+ int thoff = 0;
int tproto;
- tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
pr_debug("unable to find transport header in IPv6 packet, dropping\n");
return NF_DROP;
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 72bb07f..9ea482d 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -263,10 +263,10 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
struct sock *sk;
struct in6_addr *daddr, *saddr;
__be16 dport, sport;
- int thoff, tproto;
+ int thoff = 0, tproto;
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
- tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
pr_debug("unable to find transport header in IPv6 packet, dropping\n");
return NF_DROP;
--
1.7.2.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [v8 PATCH 2/3] NETFILTER module xt_hmark, new target for HASH based fwmark
2012-01-27 14:41 [v8 PATCH 0/3] NETFILTER new target module, HMARK Hans Schillstrom
2012-01-27 14:41 ` [v8 PATCH 1/3] NETFILTER added flags to ipv6_find_hdr() Hans Schillstrom
@ 2012-01-27 14:41 ` Hans Schillstrom
2012-02-08 0:27 ` Pablo Neira Ayuso
2012-01-27 14:41 ` [v8 PATCH 3/3] NETFILTER userspace part for target HMARK Hans Schillstrom
2 siblings, 1 reply; 10+ messages in thread
From: Hans Schillstrom @ 2012-01-27 14:41 UTC (permalink / raw)
To: kaber, pablo, jengelh, netfilter-devel, netdev; +Cc: hans, Hans Schillstrom
The target allows you to create rules in the "raw" and "mangle" tables
which alter the netfilter mark (nfmark) field within a given range.
First a 32 bit hash value is generated then modulus by <limit> and
finally an offset is added before it's written to nfmark.
Prior to routing, the nfmark can influence the routing method (see
"Use netfilter MARK value as routing key") and can also be used by
other subsystems to change their behavior.
man page
HMARK
This module does the same as MARK, i.e. set an fwmark, but the mark
is based on a hash value. The hash is based on saddr, daddr, sport,
dport and proto. The same mark will be produced independent of direction
if no masks is set or the same masks is used for src and dest.
The hash mark could be adjusted by modulus and finally an offset could
be added, i.e the final mark will be within a range. ICMP error will use
the the original message for hash calculation not the icmp it self.
Note: IPv4 packets with nf_defrag_ipv4 loaded will be defragmented before they reach hmark,
IPv6 nf_defrag is not implemented this way, hence fragmented ipv6 packets will reach hmark.
Default behavior is to completely ignore any fragment if it reach hmark.
--hmark-method L3 is fragment safe since neither ports or L4 protocol field is used.
None of the parameters effect the packet it self only the calculated hash value.
Parameters: Short hand methods
--hmark-method L3
Do not use L4 protocol field, ports or spi, only Layer 3 addresses,
mask length of L3 addresses can still be used. Fragment or not
does not matter in this case since only L3 address can be used in
calc. of hash value.
--hmark-method L3-4 (Default)
Include L4 in calculation. of hash value i.e. all masks below are valid.
Fragments will be ignored. (i.e no hash value produced)
For all masks default is all "1:s", to disable a field use mask 0
--hmark-src-mask length
The length of the mask to AND the source address with (saddr & value).
--hmark-dst-mask length
The length of the mask to AND the dest. address with (daddr & value).
--hmark-sport-mask value
A 16 bit value to AND the src port with (sport & value).
--hmark-dport-mask value
A 16 bit value to AND the dest port with (dport & value).
--hmark-sport-set value
A 16 bit value to OR the src port with (sport | value).
--hmark-dport-set value
A 16 bit value to OR the dest port with (dport | value).
--hmark-spi-mask value
Value to AND the spi field with (spi & value) valid for proto esp or ah.
--hmark-spi-set value
Value to OR the spi field with (spi | value) valid for proto esp or ah.
--hmark-proto-mask value
An 8 bit value to AND the L4 proto field with (proto & value).
--hmark-rnd value
A 32 bit initial value for hash calc, default is 0xc175a3b8.
Final processing of the mark in order of execution.
--hmark-mod value (must be > 0)
The easiest way to describe this is: hash = hash mod <value>
--hmark-offset value
The easiest way to describe this is: hash = hash + <value>
Examples:
Default rule handles all TCP, UDP, SCTP, ESP & AH
iptables -t mangle -A PREROUTING -m state --state NEW,ESTABLISHED,RELATED
-j HMARK --hmark-offset 10000 --hmark-mod 10
Handle SCTP and hash dest port only and produce a nfmark between 100-119.
iptables -t mangle -A PREROUTING -p SCTP -j HMARK --src-mask 0 --dst-mask 0
--sp-mask 0 --offset 100 --mod 20
No defragment by conntrack, None Fragments will have fwmark 100-119 and Fragments will have fwmark 120-139 (based on saddr and daddr
only)
iptables -t mangle -A PREROUTING -j HMARK --method L3-4 --mod 20 --offset 100
iptables -t mangle -A PREROUTING -m mark --mark 0 -j HMARK --method L3 --mod 20 --offset 120
Fragment safe Layer 3 only that keep a class C netw flow together
iptables -t mangle -A PREROUTING -j HMARK --method L3 --src-mask 24 --mod 20 --offset 100
Rev 8
method L3 / L3-4 added i.e. Fragment handling changed to
don't handle in "method L3-4"
Syntax change in user mode more NF compatible.
Most changes are base on Pablos review.
Rev 7
IPv6 descending into icmp error hdr didn't work as expected
with ipv6_find_hdr() Now it works as expected.
Rev 6
Compile options with or without conntrack fixed.
__ipv6_find_hdr() replaced by ipv6_find_hdr()
Rev 5
IPv6 rewritten uses __ipv6_find_hdr() (P. Mc Hardy)
Full mask and address used for IPv6 smask and dmask (J.Engelhart)
Changes due to comments by Pablo Neira Ayuso and Eric Dumazet
i.e uses of skb_header_pointer() and Null check of info->hmod
Man page changes
Rev 4
different targets for IPv4 and IPv6
Changes based on review by Pablo.
Rev 3
Support added to SCTP for IPv6
Rev 2
IPv6 header scan changed to follow RFC 2640
IPv4 icmp echo fragmented does now use proto as ipv6
IPv6 pskb_may_pull() check is done in every time in header loop.
IPv4 nat support added.
default added in IPv6 loop and null check of hp
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
---
include/linux/netfilter/xt_hmark.h | 71 ++++++++
net/netfilter/Kconfig | 17 ++
net/netfilter/Makefile | 1 +
net/netfilter/xt_hmark.c | 334 ++++++++++++++++++++++++++++++++++++
4 files changed, 423 insertions(+), 0 deletions(-)
create mode 100644 include/linux/netfilter/xt_hmark.h
create mode 100644 net/netfilter/xt_hmark.c
diff --git a/include/linux/netfilter/xt_hmark.h b/include/linux/netfilter/xt_hmark.h
new file mode 100644
index 0000000..f2ac47b
--- /dev/null
+++ b/include/linux/netfilter/xt_hmark.h
@@ -0,0 +1,71 @@
+#ifndef XT_HMARK_H_
+#define XT_HMARK_H_
+
+#include <linux/types.h>
+
+/*
+ * Flags must not start at 0, since it's used as none.
+ */
+enum {
+ XT_HMARK_SADR_AND = 1, /* SNAT & DNAT are used by the kernel module */
+ XT_HMARK_DADR_AND,
+ XT_HMARK_SPI_AND,
+ XT_HMARK_SPI_OR,
+ XT_HMARK_SPORT_AND,
+ XT_HMARK_DPORT_AND,
+ XT_HMARK_SPORT_OR,
+ XT_HMARK_DPORT_OR,
+ XT_HMARK_PROTO_AND,
+ XT_HMARK_RND,
+ XT_HMARK_MODULUS,
+ XT_HMARK_OFFSET,
+ XT_HMARK_USE_SNAT,
+ XT_HMARK_USE_DNAT,
+ XT_HMARK_METHOD_L3,
+ XT_HMARK_METHOD_L3_4,
+ XT_F_HMARK_USE_SNAT = 1 << XT_HMARK_USE_SNAT,
+ XT_F_HMARK_USE_DNAT = 1 << XT_HMARK_USE_DNAT,
+ XT_F_HMARK_SADR_AND = 1 << XT_HMARK_SADR_AND,
+ XT_F_HMARK_DADR_AND = 1 << XT_HMARK_DADR_AND,
+ XT_F_HMARK_SPI_AND = 1 << XT_HMARK_SPI_AND,
+ XT_F_HMARK_SPI_OR = 1 << XT_HMARK_SPI_OR,
+ XT_F_HMARK_SPORT_AND = 1 << XT_HMARK_SPORT_AND,
+ XT_F_HMARK_DPORT_AND = 1 << XT_HMARK_DPORT_AND,
+ XT_F_HMARK_SPORT_OR = 1 << XT_HMARK_SPORT_OR,
+ XT_F_HMARK_DPORT_OR = 1 << XT_HMARK_DPORT_OR,
+ XT_F_HMARK_PROTO_AND = 1 << XT_HMARK_PROTO_AND,
+ XT_F_HMARK_RND = 1 << XT_HMARK_RND,
+ XT_F_HMARK_MODULUS = 1 << XT_HMARK_MODULUS,
+ XT_F_HMARK_OFFSET = 1 << XT_HMARK_OFFSET,
+ XT_F_HMARK_METHOD_L3 = 1 << XT_HMARK_METHOD_L3,
+ XT_F_HMARK_METHOD_L3_4 = 1 << XT_HMARK_METHOD_L3_4,
+};
+
+#define XT_F_HMARK_L4_OPTS (XT_F_HMARK_SPI_AND | XT_F_HMARK_SPI_OR\
+ | XT_F_HMARK_SPORT_AND | XT_F_HMARK_SPORT_OR\
+ | XT_F_HMARK_DPORT_AND | XT_F_HMARK_DPORT_OR\
+ | XT_F_HMARK_PROTO_AND)
+
+union hports {
+ struct {
+ __u16 src;
+ __u16 dst;
+ } p16;
+ __u32 v32;
+};
+
+struct xt_hmark_info {
+ union nf_inet_addr smask; /* Source address mask */
+ union nf_inet_addr dmask; /* Dest address mask */
+ union hports pmask;
+ union hports pset;
+ __u32 spimask;
+ __u32 spiset;
+ __u16 flags; /* Print out only */
+ __u16 prmask; /* L4 Proto mask */
+ __u32 hashrnd;
+ __u32 hmod; /* Modulus */
+ __u32 hoffs; /* Offset */
+};
+
+#endif /* XT_HMARK_H_ */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index f8ac4ef..dfe84e1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -488,6 +488,23 @@ config NETFILTER_XT_TARGET_HL
since you can easily create immortal packets that loop
forever on the network.
+config NETFILTER_XT_TARGET_HMARK
+ tristate '"HMARK" target support'
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option adds the "HMARK" target.
+
+ The target allows you to create rules in the "raw" and "mangle" tables
+ which alter the netfilter mark (nfmark) field within a given range.
+ First a 32 bit hash value is generated then modulus by <limit> and
+ finally an offset is added before it's written to nfmark.
+
+ Prior to routing, the nfmark can influence the routing method (see
+ "Use netfilter MARK value as routing key") and can also be used by
+ other subsystems to change their behavior.
+
+ The mark match can also be used to match nfmark produced by this module.
+
config NETFILTER_XT_TARGET_IDLETIMER
tristate "IDLETIMER target support"
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 40f4c3d..21bc5e8 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -57,6 +57,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o
obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o
obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_hmark.o
obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
diff --git a/net/netfilter/xt_hmark.c b/net/netfilter/xt_hmark.c
new file mode 100644
index 0000000..c9d6654
--- /dev/null
+++ b/net/netfilter/xt_hmark.c
@@ -0,0 +1,334 @@
+/*
+ * xt_hmark - Netfilter module to set mark as hash value
+ *
+ * (C) 2011 Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *
+ *Description:
+ * This module calculates a hash value that can be modified by modulus
+ * and an offset, i.e. it is possible to produce a skb->mark within a range.
+ * The hash value is based on a direction independent five tuple:
+ * src & dst addr src & dst ports and protocol.
+ * There is two distinct modes for hash calculation:
+ *
+ * MODE_L3:
+ * In this mode ONLY src & dst addresses can be used in hash calc.
+ * src-mask & dst-mask is the only valid masks.
+ * In this mode no special care for fragments is necessary.
+ *
+ * MODE_L3_4:
+ * All five fields L4-proto, ports and addresses can be used in calc.
+ * ESP and AH don't have ports so SPI will be used instead.
+ * AH will not use ports even if it might be possible.
+ * Tunnels - only the outer saddr and daddr will be used,
+ *
+ * For ICMP error messages the hash mark values will be calculated on
+ * the source packet i.e. the packet caused the error (If sufficient
+ * amount of data exists).
+ *
+ * Fragments is not handled in this mode, (if they reach us)
+ * i.e. fw-mark will be updated.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <linux/icmp.h>
+
+#include <linux/netfilter/xt_hmark.h>
+#include <linux/netfilter/x_tables.h>
+#if defined(CONFIG_NF_NAT)
+#include <net/netfilter/nf_nat.h>
+#endif
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+# define WITH_IPV6 1
+#include <net/ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Hans Schillstrom <hans.schillstrom@ericsson.com>");
+MODULE_DESCRIPTION("Xtables: Packet range mark operations by Hash value");
+MODULE_ALIAS("ipt_HMARK");
+MODULE_ALIAS("ip6t_HMARK");
+
+/*
+ * ICMP, get header offset if icmp error
+ */
+static int get_inner_hdr(struct sk_buff *skb, int iphsz, int nhoff)
+{
+ const struct icmphdr *icmph;
+ struct icmphdr _ih;
+
+ /* Not enough header? */
+ icmph = skb_header_pointer(skb, nhoff + iphsz, sizeof(_ih), &_ih);
+ if (icmph == NULL)
+ return nhoff;
+
+ if (icmph->type > NR_ICMP_TYPES)
+ return nhoff;
+
+ /* Error message? */
+ if (icmph->type != ICMP_DEST_UNREACH &&
+ icmph->type != ICMP_SOURCE_QUENCH &&
+ icmph->type != ICMP_TIME_EXCEEDED &&
+ icmph->type != ICMP_PARAMETERPROB &&
+ icmph->type != ICMP_REDIRECT)
+ return nhoff;
+
+ return nhoff + iphsz + sizeof(_ih);
+}
+
+#ifdef WITH_IPV6
+/*
+ * Get ipv6 header offset if icmp error
+ */
+static int get_inner6_hdr(struct sk_buff *skb, int *offset)
+{
+ struct icmp6hdr *icmp6h, _ih6;
+
+ icmp6h = skb_header_pointer(skb, *offset, sizeof(_ih6), &_ih6);
+ if (icmp6h == NULL)
+ return 0;
+
+ if (icmp6h->icmp6_type && icmp6h->icmp6_type < 128) {
+ *offset += sizeof(struct icmp6hdr);
+ return 1;
+ }
+ return 0;
+}
+/*
+ * Calculate hash based fw-mark, on the five tuple if possible.
+ * special cases :
+ * - Fragments do not use ports not even on the first fragment,
+ * nf_defrag_ipv6.ko don't defrag for us like it do in ipv4.
+ * This might be changed in the future.
+ * - On ICMP errors the inner header will be used.
+ * - Tunnels no ports
+ * - ESP & AH uses SPI
+ * @returns XT_CONTINUE
+ */
+static unsigned int
+hmark_v6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ struct xt_hmark_info *info = (struct xt_hmark_info *)par->targinfo;
+ struct ipv6hdr *ip6, _ip6;
+ int poff, flag = IP6T_FH_F_AUTH; /* Ports offset, find_hdr flags */
+ u32 addr1, addr2, hash, nhoffs = 0;
+ u8 nexthdr;
+ union hports uports = { .v32 = 0 };
+ unsigned short fragoff = 0;
+
+ ip6 = (struct ipv6hdr *) (skb->data + skb_network_offset(skb));
+
+ /* Try to get transport header */
+ nexthdr = ipv6_find_hdr(skb, &nhoffs, -1, &fragoff, &flag);
+ if (nexthdr < 0)
+ return XT_CONTINUE;
+ /* don't check for icmp on fragments */
+ if ((flag & IP6T_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6))
+ goto noicmp;
+ /* ICMP: if an error then move ptr to inner header */
+ if (get_inner6_hdr(skb, &nhoffs)) {
+ /* Get IPv6 header ptr just to get the saddr & daddr later */
+ ip6 = skb_header_pointer(skb, nhoffs, sizeof(_ip6), &_ip6);
+ if (!ip6)
+ return XT_CONTINUE;
+ /* Treat AH as ESP */
+ flag = IP6T_FH_F_AUTH;
+ nexthdr = ipv6_find_hdr(skb, &nhoffs, -1, &fragoff, &flag);
+ if (nexthdr < 0)
+ return XT_CONTINUE;
+ }
+noicmp:
+ /* Mask of the address and xor it into a u32 */
+ addr1 = (__force u32)
+ (ip6->saddr.s6_addr32[0] & info->smask.in6.s6_addr32[0]) ^
+ (ip6->saddr.s6_addr32[1] & info->smask.in6.s6_addr32[1]) ^
+ (ip6->saddr.s6_addr32[2] & info->smask.in6.s6_addr32[2]) ^
+ (ip6->saddr.s6_addr32[3] & info->smask.in6.s6_addr32[3]);
+ addr2 = (__force u32)
+ (ip6->daddr.s6_addr32[0] & info->dmask.in6.s6_addr32[0]) ^
+ (ip6->daddr.s6_addr32[1] & info->dmask.in6.s6_addr32[1]) ^
+ (ip6->daddr.s6_addr32[2] & info->dmask.in6.s6_addr32[2]) ^
+ (ip6->daddr.s6_addr32[3] & info->dmask.in6.s6_addr32[3]);
+
+ /* user space tool ensures that prmask is zero when method is L3*/
+ if ((info->flags & XT_F_HMARK_METHOD_L3) ||
+ (nexthdr == IPPROTO_ICMPV6))
+ goto no6ports;
+
+ /* Is next header valid for port or SPI calculation ? */
+ poff = proto_ports_offset(nexthdr);
+ if ((flag & IP6T_FH_F_FRAG) || poff < 0)
+ return XT_CONTINUE;
+
+ nhoffs += poff;
+ /* Since uports is modified, skb_header_pointer() can't be used */
+ if (!pskb_may_pull(skb, nhoffs + 4))
+ return XT_CONTINUE;
+ uports.v32 = * (__force u32 *) (skb->data + nhoffs);
+
+ if ((nexthdr == IPPROTO_ESP) || (nexthdr == IPPROTO_AH))
+ uports.v32 = (uports.v32 & info->spimask) | info->spiset;
+ else {
+ uports.v32 = (uports.v32 & info->pmask.v32) | info->pset.v32;
+ /* get a consistent hash (same value on both flow directions) */
+ if (uports.p16.dst < uports.p16.src)
+ swap(uports.p16.dst, uports.p16.src);
+ }
+
+no6ports:
+ nexthdr &= info->prmask;
+ /* get a consistent hash (same value on both flow directions) */
+ if (addr2 < addr1)
+ swap(addr1, addr2);
+
+ hash = jhash_3words(addr1, addr2, uports.v32, info->hashrnd) ^ nexthdr;
+ skb->mark = (hash % info->hmod) + info->hoffs;
+ return XT_CONTINUE;
+}
+#endif
+/*
+ * Calculate hash based fw-mark, on the five tuple if possible.
+ * special cases :
+ * - Fragments do not use ports not even on the first fragment,
+ * unless nf_defrag_xx.ko is used.
+ * - On ICMP errors the inner header will be used.
+ * - Tunnels no ports
+ * - ESP & AH uses SPI
+ * @returns XT_CONTINUE
+ */
+static unsigned int
+hmark_v4(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ struct xt_hmark_info *info = (struct xt_hmark_info *)par->targinfo;
+ int nhoff, poff, frag = 0;
+ struct iphdr *ip, _ip;
+ u8 ip_proto;
+ u32 addr1, addr2, hash;
+ u16 snatport = 0, dnatport = 0;
+ union hports uports;
+#if defined(CONFIG_NF_NAT)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+#endif
+
+ nhoff = skb_network_offset(skb);
+ uports.v32 = 0;
+
+ ip = (struct iphdr *) (skb->data + nhoff);
+ if (ip->protocol == IPPROTO_ICMP) {
+ /* calc hash on inner header if an icmp error */
+ nhoff = get_inner_hdr(skb, ip->ihl * 4, nhoff);
+ ip = skb_header_pointer(skb, nhoff, sizeof(_ip), &_ip);
+ if (!ip)
+ return XT_CONTINUE;
+ }
+
+ ip_proto = ip->protocol;
+ if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+ frag = 1;
+
+ addr1 = (__force u32) ip->saddr & info->smask.ip;
+ addr2 = (__force u32) ip->daddr & info->dmask.ip;
+
+#if defined(CONFIG_NF_NAT)
+ if (ct && test_bit(IP_CT_IS_REPLY, &ct->status)) {
+ struct nf_conntrack_tuple *otuple;
+
+ otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+ /*
+ * On the "return flow", to get the original address
+ */
+ if ((ct->status & IPS_DST_NAT) &&
+ (info->flags & XT_HMARK_USE_DNAT)) {
+ addr1 = (__force u32) otuple->dst.u3.in.s_addr;
+ dnatport = otuple->dst.u.udp.port;
+ }
+ if ((ct->status & IPS_SRC_NAT) &&
+ (info->flags & XT_HMARK_USE_SNAT)) {
+ addr2 = (__force u32) otuple->src.u3.in.s_addr;
+ snatport = otuple->src.u.udp.port;
+ }
+ }
+#endif
+ /* user space tool ensures that prmask is zero when method is L3*/
+ if ((info->flags & XT_F_HMARK_METHOD_L3) || (ip_proto == IPPROTO_ICMP))
+ goto noports;
+ /* Check if ports can be used in hash calculation. */
+ poff = proto_ports_offset(ip_proto);
+ if (frag || poff < 0)
+ return XT_CONTINUE;
+
+ nhoff += (ip->ihl * 4) + poff;
+ if (!pskb_may_pull(skb, nhoff + 4))
+ return XT_CONTINUE;
+
+ uports.v32 = * (__force u32 *) (skb->data + nhoff);
+ if (ip_proto == IPPROTO_ESP || ip_proto == IPPROTO_AH)
+ uports.v32 = (uports.v32 & info->spimask) | info->spiset;
+ else {
+ if (snatport) /* Replace nat'ed port(s) */
+ uports.p16.dst = snatport;
+ if (dnatport)
+ uports.p16.src = dnatport;
+ uports.v32 = (uports.v32 & info->pmask.v32) |
+ info->pset.v32;
+ /* get a consistent hash (same value on both flow directions) */
+ if (uports.p16.dst < uports.p16.src)
+ swap(uports.p16.src, uports.p16.dst);
+ }
+
+noports:
+ ip_proto &= info->prmask;
+ /* get a consistent hash (same value on both flow directions) */
+ if (addr2 < addr1)
+ swap(addr1, addr2);
+
+ hash = jhash_3words(addr1, addr2, uports.v32, info->hashrnd) ^ ip_proto;
+ skb->mark = (hash % info->hmod) + info->hoffs;
+ return XT_CONTINUE;
+}
+
+static struct xt_target hmark_tg_reg[] __read_mostly = {
+ {
+ .name = "HMARK",
+ .revision = 0,
+ .family = NFPROTO_IPV4,
+ .target = hmark_v4,
+ .targetsize = sizeof(struct xt_hmark_info),
+ .me = THIS_MODULE,
+ },
+#ifdef WITH_IPV6
+ {
+ .name = "HMARK",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .target = hmark_v6,
+ .targetsize = sizeof(struct xt_hmark_info),
+ .me = THIS_MODULE,
+ },
+#endif
+};
+
+static int __init hmark_mt_init(void)
+{
+ int ret;
+
+ ret = xt_register_targets(hmark_tg_reg, ARRAY_SIZE(hmark_tg_reg));
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+static void __exit hmark_mt_exit(void)
+{
+ xt_unregister_targets(hmark_tg_reg, ARRAY_SIZE(hmark_tg_reg));
+}
+
+module_init(hmark_mt_init);
+module_exit(hmark_mt_exit);
--
1.7.2.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [v8 PATCH 3/3] NETFILTER userspace part for target HMARK
2012-01-27 14:41 [v8 PATCH 0/3] NETFILTER new target module, HMARK Hans Schillstrom
2012-01-27 14:41 ` [v8 PATCH 1/3] NETFILTER added flags to ipv6_find_hdr() Hans Schillstrom
2012-01-27 14:41 ` [v8 PATCH 2/3] NETFILTER module xt_hmark, new target for HASH based fwmark Hans Schillstrom
@ 2012-01-27 14:41 ` Hans Schillstrom
2012-02-08 0:32 ` Pablo Neira Ayuso
2 siblings, 1 reply; 10+ messages in thread
From: Hans Schillstrom @ 2012-01-27 14:41 UTC (permalink / raw)
To: kaber, pablo, jengelh, netfilter-devel, netdev; +Cc: hans, Hans Schillstrom
The target allows you to create rules in the "raw" and "mangle" tables
which alter the netfilter mark (nfmark) field within a given range.
First a 32 bit hash value is generated then modulus by <limit> and
finally an offset is added before it's written to nfmark.
Prior to routing, the nfmark can influence the routing method (see
"Use netfilter MARK value as routing key") and can also be used by
other subsystems to change their behaviour.
The mark match can also be used to match nfmark produced by this module.
Ver 8
Syntax changes more descriptive options
--hmark-method added.
Ver 6-7 -
Ver 5
smask and dmask changed to length
Ver 4
xtoptions used for parsing.
Ver 3
-
Ver 2
IPv4 NAT added
iptables ver 1.4.12.1 adaptions.
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
---
extensions/libxt_HMARK.c | 372 ++++++++++++++++++++++++++++++++++++
extensions/libxt_HMARK.man | 88 +++++++++
include/linux/netfilter/xt_hmark.h | 71 +++++++
3 files changed, 531 insertions(+), 0 deletions(-)
create mode 100644 extensions/libxt_HMARK.c
create mode 100644 extensions/libxt_HMARK.man
create mode 100644 include/linux/netfilter/xt_hmark.h
diff --git a/extensions/libxt_HMARK.c b/extensions/libxt_HMARK.c
new file mode 100644
index 0000000..09d9c75
--- /dev/null
+++ b/extensions/libxt_HMARK.c
@@ -0,0 +1,372 @@
+/*
+ * Shared library add-on to iptables to add HMARK target support.
+ *
+ * The kernel module calculates a hash value that can be modified by modulus
+ * and an offset. The hash value is based on a direction independent
+ * five tuple: src & dst addr src & dst ports and protocol.
+ * However src & dst port can be masked and are not used for fragmented
+ * packets, ESP and AH don't have ports so SPI will be used instead.
+ * For ICMP error messages the hash mark values will be calculated on
+ * the source packet i.e. the packet caused the error (If sufficient
+ * amount of data exists).
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <xtables.h>
+#include <linux/netfilter/xt_hmark.h>
+
+
+#define DEF_HRAND 0xc175a3b8 /* Default "random" value to jhash */
+
+static void HMARK_help(void)
+{
+ printf(
+"HMARK target options, i.e. modify hash calculation by:\n"
+" --hmark-method <method> Overall L3/L4 and fragment behavior\n"
+" L3 Fragment safe, do not use ports or proto\n"
+" i.e. Fragments don't need special care.\n"
+" L3-4 (Default) Fragment unsafe, use ports and proto\n"
+" if defrag off in conntrack\n"
+" no hmark on any part of a fragment\n"
+" Limit/modify the calculated hash mark by:\n"
+" --hmark-mod value nfmark modulus value\n"
+" --hmark-offset value Last action add value to nfmark\n\n"
+" Fine tuning of what will be included in hash calculation\n"
+" --hmark-src-mask length Source address mask length\n"
+" --hmark-dst-mask length Dest address mask length\n"
+" --hmark-sport-mask value Mask src port with value\n"
+" --hmark-dport-mask value Mask dst port with value\n"
+" --hmark-spi-mask value For esp and ah AND spi with value\n"
+" --hmark-sport-set value OR src port with value\n"
+" --hmark-dport-set value OR dst port with value\n"
+" --hmark-spi-set value For esp and ah OR spi with value\n"
+" --hmark-proto-mask value Mask Protocol with value\n"
+" --hmark-rnd Initial Random value to hash cacl.\n"
+" For NAT in IPv4 the original address can be used in the return path.\n"
+" Make sure to qualify the statement in a proper way when using nat flags\n"
+" --hmark-ct-orig-src Replace src addr with original dst addr\n"
+" --hmark-ct-orig-dst Replace dst addr with original src addr\n"
+" In many cases hmark can be omitted i.e. --src-mask can be used\n");
+}
+
+#define hi struct xt_hmark_info
+
+static const struct xt_option_entry HMARK_opts[] = {
+ { .name = "hmark-method", .type = XTTYPE_STRING, .id = XT_HMARK_METHOD_L3
+ },
+ { .name = "hmark-src-mask", .type = XTTYPE_PLENMASK, .id = XT_HMARK_SADR_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, smask)
+ },
+ { .name = "hmark-dst-mask", .type = XTTYPE_PLENMASK, .id = XT_HMARK_DADR_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, dmask)
+ },
+ { .name = "hmark-sport-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_SPORT_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pmask.p16.src)
+ },
+ { .name = "hmark-dport-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_DPORT_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pmask.p16.dst)
+ },
+ { .name = "hmark-spi-mask", .type = XTTYPE_UINT32, .id = XT_HMARK_SPI_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, spimask)
+ },
+ { .name = "hmark-sport-set", .type = XTTYPE_UINT16, .id = XT_HMARK_SPORT_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pset.p16.src)
+ },
+ { .name = "hmark-dport-set", .type = XTTYPE_UINT16, .id = XT_HMARK_DPORT_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pset.p16.dst)
+ },
+ { .name = "hmark-spi-set", .type = XTTYPE_UINT32, .id = XT_HMARK_SPI_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, spiset)
+ },
+ { .name = "hmark-proto-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_PROTO_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, prmask)
+ },
+ { .name = "hmark-rnd", .type = XTTYPE_UINT32, .id = XT_HMARK_RND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, hashrnd)
+ },
+ { .name = "hmark-mod", .type = XTTYPE_UINT32, .id = XT_HMARK_MODULUS,
+ .min = 1, .flags = XTOPT_PUT | XTOPT_MAND, XTOPT_POINTER(hi, hmod)
+ },
+ { .name = "hmark-offset", .type = XTTYPE_UINT32, .id = XT_HMARK_OFFSET,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, hoffs)
+ },
+ { .name = "hmark-ct-orig-src", .type = XTTYPE_NONE, .id = XT_HMARK_USE_DNAT },
+ { .name = "hmark-ct-orig-dst", .type = XTTYPE_NONE, .id = XT_HMARK_USE_SNAT },
+
+ { .name = "method", .type = XTTYPE_STRING, .id = XT_HMARK_METHOD_L3
+ },
+ { .name = "src-mask", .type = XTTYPE_PLENMASK, .id = XT_HMARK_SADR_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, smask)
+ },
+ { .name = "dst-mask", .type = XTTYPE_PLENMASK, .id = XT_HMARK_DADR_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, dmask)
+ },
+ { .name = "sport-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_SPORT_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pmask.p16.src)
+ },
+ { .name = "dport-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_DPORT_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pmask.p16.dst)
+ },
+ { .name = "spi-mask", .type = XTTYPE_UINT32, .id = XT_HMARK_SPI_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, spimask)
+ },
+ { .name = "sport-set", .type = XTTYPE_UINT16, .id = XT_HMARK_SPORT_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pset.p16.src)
+ },
+ { .name = "dport-set", .type = XTTYPE_UINT16, .id = XT_HMARK_DPORT_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, pset.p16.dst)
+ },
+ { .name = "spi-set", .type = XTTYPE_UINT32, .id = XT_HMARK_SPI_OR,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, spiset)
+ },
+ { .name = "proto-mask", .type = XTTYPE_UINT16, .id = XT_HMARK_PROTO_AND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, prmask)
+ },
+ { .name = "rnd", .type = XTTYPE_UINT32, .id = XT_HMARK_RND,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, hashrnd)
+ },
+ { .name = "mod", .type = XTTYPE_UINT32, .id = XT_HMARK_MODULUS,
+ .min = 1, .flags = XTOPT_PUT | XTOPT_MAND, XTOPT_POINTER(hi, hmod)
+ },
+ { .name = "offset", .type = XTTYPE_UINT32, .id = XT_HMARK_OFFSET,
+ .flags = XTOPT_PUT, XTOPT_POINTER(hi, hoffs)
+ },
+ { .name = "ct-orig-src", .type = XTTYPE_NONE, .id = XT_HMARK_USE_DNAT },
+ { .name = "ct-orig-dst", .type = XTTYPE_NONE, .id = XT_HMARK_USE_SNAT },
+ XTOPT_TABLEEND,
+};
+
+static void HMARK_parse(struct xt_option_call *cb)
+{
+ struct xt_hmark_info *info = cb->data;
+
+ if (!cb->xflags) {
+ memset(info, 0xff, sizeof(struct xt_hmark_info));
+ info->pset.v32 = 0;
+ info->flags = 0;
+ info->spiset = 0;
+ info->hoffs = 0;
+ info->hashrnd = DEF_HRAND;
+ }
+ xtables_option_parse(cb);
+
+ switch (cb->entry->id) {
+ case XT_HMARK_SPI_AND:
+ info->spimask = htonl(cb->val.u32);
+ break;
+ case XT_HMARK_SPI_OR:
+ info->spiset = htonl(cb->val.u32);
+ break;
+ case XT_HMARK_SPORT_AND:
+ info->pmask.p16.src = htons(cb->val.u16);
+ break;
+ case XT_HMARK_DPORT_AND:
+ info->pmask.p16.dst = htons(cb->val.u16);
+ break;
+ case XT_HMARK_SPORT_OR:
+ info->pset.p16.src = htons(cb->val.u16);
+ break;
+ case XT_HMARK_DPORT_OR:
+ info->pset.p16.dst = htons(cb->val.u16);
+ break;
+ case XT_HMARK_MODULUS:
+ if (info->hmod == 0) {
+ xtables_error(PARAMETER_PROBLEM,
+ "xxx modulus 0 ? "
+ "thats a div by 0");
+ info->hmod = 0xffffffff;
+ }
+ break;
+ case XT_HMARK_METHOD_L3:
+ if (strcmp(cb->arg, "L3") == 0) {
+ info->prmask = 0;
+ cb->xflags &= ~XT_F_HMARK_METHOD_L3_4;
+ } else if (strcmp(cb->arg, "L3-4") == 0) {
+ cb->xflags &= ~XT_F_HMARK_METHOD_L3;
+ cb->xflags |= XT_F_HMARK_METHOD_L3_4;
+ }
+ }
+ info->flags = cb->xflags;
+}
+
+static void HMARK_check(struct xt_fcheck_call *cb)
+{
+ if (!(cb->xflags & XT_F_HMARK_MODULUS))
+ xtables_error(PARAMETER_PROBLEM, "HMARK: the --hmark-mod, "
+ "is not set, or zero wich is a div by zero");
+ /* Check for invalid options */
+ if (cb->xflags & XT_F_HMARK_METHOD_L3 &&
+ (cb->xflags & XT_F_HMARK_L4_OPTS))
+ xtables_error(PARAMETER_PROBLEM, "HMARK: --hmark-method L3, "
+ "can not be combined by an Layer 4 options: "
+ "port, spi or proto ");
+}
+/*
+ * Common print for IPv4 & IPv6
+ */
+static void HMARK_print(const struct xt_hmark_info *info)
+{
+ if (info->flags & XT_F_HMARK_METHOD_L3) {
+ printf("method L3 ");
+ } else {
+ if (info->flags & XT_F_HMARK_METHOD_L3_4)
+ printf("method L3-4 ");
+ if (info->flags & XT_F_HMARK_SPORT_AND)
+ printf("sport-mask 0x%x ", htons(info->pmask.p16.src));
+ if (info->flags & XT_F_HMARK_DPORT_AND)
+ printf("dport-mask 0x%x ", htons(info->pmask.p16.dst));
+ if (info->flags & XT_F_HMARK_SPI_AND)
+ printf("spi-mask 0x%x ", htonl(info->spimask));
+ if (info->flags & XT_F_HMARK_SPORT_OR)
+ printf("sport-set 0x%x ", htons(info->pset.p16.src));
+ if (info->flags & XT_F_HMARK_DPORT_OR)
+ printf("dport-set 0x%x ", htons(info->pset.p16.dst));
+ if (info->flags & XT_F_HMARK_SPI_OR)
+ printf("spi-set 0x%x ", htonl(info->spiset));
+ if (info->flags & XT_F_HMARK_PROTO_AND)
+ printf("proto-mask 0x%x ", info->prmask);
+ }
+ if (info->flags & XT_F_HMARK_RND)
+ printf("rnd 0x%x ", info->hashrnd);
+
+}
+
+static void HMARK_ip6_print(const void *ip, const struct xt_entry_target *target,
+ int numeric)
+{
+ const struct xt_hmark_info *info =
+ (const struct xt_hmark_info *)target->data;
+
+ printf(" HMARK ");
+ if (info->flags & XT_F_HMARK_MODULUS)
+ printf("%% 0x%x ", info->hmod);
+ if (info->flags & XT_F_HMARK_OFFSET)
+ printf("+ 0x%x ", info->hoffs);
+ if (info->flags & XT_F_HMARK_USE_SNAT)
+ printf("ct-orig-dst, ");
+ if (info->flags & XT_F_HMARK_SADR_AND)
+ printf("src-mask %s ", xtables_ip6mask_to_numeric(&info->smask.in6) + 1);
+ if (info->flags & XT_F_HMARK_USE_DNAT)
+ printf("ct-orig-src, ");
+ if (info->flags & XT_F_HMARK_DADR_AND)
+ printf("dst-mask %s ", xtables_ip6mask_to_numeric(&info->dmask.in6) + 1);
+ HMARK_print(info);
+}
+static void HMARK_ip4_print(const void *ip, const struct xt_entry_target *target, int numeric)
+{
+ const struct xt_hmark_info *info = (const struct xt_hmark_info *)target->data;
+
+ printf(" HMARK ");
+ if (info->flags & XT_F_HMARK_MODULUS)
+ printf("%% 0x%x ", info->hmod);
+ if (info->flags & XT_F_HMARK_OFFSET)
+ printf("+ 0x%x ", info->hoffs);
+ if (info->flags & XT_F_HMARK_USE_SNAT)
+ printf("ct-orig-dst, ");
+ if (info->flags & XT_F_HMARK_SADR_AND)
+ printf("src-mask %s ", xtables_ipmask_to_numeric(&info->smask.in) + 1);
+ if (info->flags & XT_F_HMARK_USE_DNAT)
+ printf("ct-orig-src, ");
+ if (info->flags & XT_F_HMARK_DADR_AND)
+ printf("dst-mask %s ", xtables_ipmask_to_numeric(&info->dmask.in) + 1);
+ HMARK_print(info);
+}
+static void HMARK_save(const struct xt_hmark_info *info)
+{
+ if (info->flags & XT_F_HMARK_METHOD_L3) {
+ printf(" --hmark-method L3");
+ } else {
+ if (info->flags & XT_F_HMARK_METHOD_L3_4)
+ printf(" --hmark-method L3-4");
+ if (info->flags & XT_F_HMARK_SPORT_AND)
+ printf(" --hmark-sport-mask 0x%x", htons(info->pmask.p16.src));
+ if (info->flags & XT_F_HMARK_DPORT_AND)
+ printf(" --hmark-dport-mask 0x%x", htons(info->pmask.p16.dst));
+ if (info->flags & XT_F_HMARK_SPI_AND)
+ printf(" --hmark-spi-mask 0x%x", htonl(info->spimask));
+ if (info->flags & XT_F_HMARK_SPORT_OR)
+ printf(" --hmark-sport-set 0x%x", htons(info->pset.p16.src));
+ if (info->flags & XT_F_HMARK_DPORT_OR)
+ printf(" --hmark-dport-set 0x%x", htons(info->pset.p16.dst));
+ if (info->flags & XT_F_HMARK_SPI_OR)
+ printf(" --hmark-spi-set 0x%x", htonl(info->spiset));
+ if (info->flags & XT_F_HMARK_PROTO_AND)
+ printf(" --hmark-proto-mask 0x%x", info->prmask);
+ }
+ if (info->flags & XT_F_HMARK_RND)
+ printf(" --hmark-rnd 0x%x", info->hashrnd);
+ if (info->flags & XT_F_HMARK_MODULUS)
+ printf(" --hmark-mod 0x%x", info->hmod);
+ if (info->flags & XT_F_HMARK_OFFSET)
+ printf(" --hmark-offs 0x%x", info->hoffs);
+ if (info->flags & XT_F_HMARK_USE_DNAT)
+ printf(" --hmark-ct-orig-src");
+ if (info->flags & XT_F_HMARK_USE_SNAT)
+ printf(" --hmark-ct-orig-dst");
+}
+
+static void HMARK_ip6_save(const void *ip, const struct xt_entry_target *target)
+{
+ const struct xt_hmark_info *info =
+ (const struct xt_hmark_info *)target->data;
+
+ if (info->flags & XT_F_HMARK_SADR_AND)
+ printf(" --hmark-src-mask %s", xtables_ip6mask_to_numeric(&info->smask.in6) + 1);
+ if (info->flags & XT_F_HMARK_DADR_AND)
+ printf(" --hmark-dst-mask %s", xtables_ip6mask_to_numeric(&info->dmask.in6) + 1);
+ HMARK_save(info);
+}
+
+static void HMARK_ip4_save(const void *ip, const struct xt_entry_target *target)
+{
+ const struct xt_hmark_info *info =
+ (const struct xt_hmark_info *)target->data;
+
+ if (info->flags & XT_F_HMARK_SADR_AND)
+ printf(" --hmark-src-mask %s", xtables_ipmask_to_numeric(&info->smask.in) + 1);
+ if (info->flags & XT_F_HMARK_DADR_AND)
+ printf(" --hmark-dst-mask %s", xtables_ipmask_to_numeric(&info->dmask.in) + 1);
+ HMARK_save(info);
+}
+
+static struct xtables_target mark_tg_reg[] = {
+ {
+ .family = NFPROTO_IPV4,
+ .name = "HMARK",
+ .version = XTABLES_VERSION,
+ .revision = 0,
+ .size = XT_ALIGN(sizeof(struct xt_hmark_info)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_hmark_info)),
+ .help = HMARK_help,
+ .print = HMARK_ip4_print,
+ .save = HMARK_ip4_save,
+ .x6_parse = HMARK_parse,
+ .x6_fcheck = HMARK_check,
+ .x6_options = HMARK_opts,
+ },
+ {
+ .family = NFPROTO_IPV6,
+ .name = "HMARK",
+ .version = XTABLES_VERSION,
+ .revision = 0,
+ .size = XT_ALIGN(sizeof(struct xt_hmark_info)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_hmark_info)),
+ .help = HMARK_help,
+ .print = HMARK_ip6_print,
+ .save = HMARK_ip6_save,
+ .x6_parse = HMARK_parse,
+ .x6_fcheck = HMARK_check,
+ .x6_options = HMARK_opts,
+ },
+};
+
+void _init(void)
+{
+ xtables_register_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg));
+}
+
diff --git a/extensions/libxt_HMARK.man b/extensions/libxt_HMARK.man
new file mode 100644
index 0000000..d514c8b
--- /dev/null
+++ b/extensions/libxt_HMARK.man
@@ -0,0 +1,88 @@
+This module does the same as MARK, i.e. set an fwmark, but the mark is based on a hash value.
+The hash is based on saddr, daddr, sport, dport and proto. The same mark will be produced independent of direction if no masks is set or the same masks is used for src and dest.
+The hash mark could be adjusted by modulus and finally an offset could be added, i.e the final mark will be within a range.
+ICMP error will use the the original message for hash calculation not the icmp it self.
+
+Note: IPv4 packets with nf_defrag_ipv4 loaded will be defragmented before they reach hmark,
+ IPv6 nf_defrag is not implemented this way, hence fragmented ipv6 packets will reach hmark.
+ Default behavior is to completely ignore any fragment if it reach hmark.
+ --hmark-method L3 is fragment safe since neither ports or L4 protocol field is used.
+ None of the parameters effect the packet it self only the calculated hash value.
+
+.PP
+Parameters:
+Short hand methods
+.TP
+\fB\-\-hmark\-method\fP \fIL3\fP
+Do not use L4 protocol field, ports or spi, only Layer 3 addresses, mask length
+of L3 addresses can still be used. Fragment or not does not matter in
+this case since only L3 address can be used in calc. of hash value.
+.TP
+\fB\-\-hmark\-method\fP \fIL3-4\fP (Default)
+Include L4 in calculation. of hash value i.e. all masks below are valid.
+Fragments will be ignored. (i.e no hash value produced)
+.PP
+For all masks default is all "1:s", to disable a field use mask 0
+.TP
+\fB\-\-hmark\-src\-mask\fP \fIlength\fP
+The length of the mask to AND the source address with (saddr & value).
+.TP
+\fB\-\-hmark\-dst\-mask\fP \fIlength\fP
+The length of the mask to AND the dest. address with (daddr & value).
+.TP
+\fB\-\-hmark\-sport\-mask\fP \fIvalue\fP
+A 16 bit value to AND the src port with (sport & value).
+.TP
+\fB\-\-hmark\-dport\-mask\fP \fIvalue\fP
+A 16 bit value to AND the dest port with (dport & value).
+.TP
+\fB\-\-hmark\-sport\-set\fP \fIvalue\fP
+A 16 bit value to OR the src port with (sport | value).
+.TP
+\fB\-\-hmark\-dport\-set\fP \fIvalue\fP
+A 16 bit value to OR the dest port with (dport | value).
+.TP
+\fB\-\-hmark\-spi\-mask\fP \fIvalue\fP
+Value to AND the spi field with (spi & value) valid for proto esp or ah.
+.TP
+\fB\-\-hmark\-spi\-set\fP \fIvalue\fP
+Value to OR the spi field with (spi | value) valid for proto esp or ah.
+.TP
+\fB\-\-hmark\-proto\-mask\fP \fIvalue\fP
+An 8 bit value to AND the L4 proto field with (proto & value).
+.TP
+\fB\-\-hmark\-rnd\fP \fIvalue\fP
+A 32 bit initial value for hash calc, default is 0xc175a3b8.
+.PP
+Final processing of the mark in order of execution.
+.TP
+\fB\-\-hmark\-mod\fP \fIvalue (must be > 0)\fP
+The easiest way to describe this is: hash = hash mod <value>
+.TP
+\fB\-\-hmark\-offset\fP \fIvalue\fP
+The easiest way to describe this is: hash = hash + <value>
+.PP
+\fIExamples:\fP
+.PP
+Default rule handles all TCP, UDP, SCTP, ESP & AH
+.IP
+iptables \-t mangle \-A PREROUTING \-m state \-\-state NEW,ESTABLISHED,RELATED
+ \-j HMARK \-\-hmark-offs 10000 \-\-hmark-mod 10
+.PP
+Handle SCTP and hash dest port only and produce a nfmark between 100-119.
+.IP
+iptables \-t mangle \-A PREROUTING -p SCTP \-j HMARK \-\-src\-mask 0 \-\-dst\-mask 0
+ \-\-sp\-mask 0 \-\-offset 100 \-\-mod 20
+.PP
+No defragment by conntrack, None Fragments will have fwmark 100-119
+and Fragments will have fwmark 120-139 (based on saddr and daddr only)
+.IP
+iptables \-t mangle \-A PREROUTING \-j HMARK \-\-method L3\-4 \-\-mod 20 \-\-offset 100
+.IP
+iptables \-t mangle \-A PREROUTING \-m mark \-\-mark 0 \-j HMARK \-\-method L3 \-\-mod 20 \-\-offset 120
+
+.PP
+Fragment safe Layer 3 only that keep a class C netw flow together
+.IP
+iptables \-t mangle \-A PREROUTING \-j HMARK \-\-method L3 \-\-src\-mask 24 \-\-mod 20 \-\-offset 100
+
diff --git a/include/linux/netfilter/xt_hmark.h b/include/linux/netfilter/xt_hmark.h
new file mode 100644
index 0000000..f2ac47b
--- /dev/null
+++ b/include/linux/netfilter/xt_hmark.h
@@ -0,0 +1,71 @@
+#ifndef XT_HMARK_H_
+#define XT_HMARK_H_
+
+#include <linux/types.h>
+
+/*
+ * Flags must not start at 0, since it's used as none.
+ */
+enum {
+ XT_HMARK_SADR_AND = 1, /* SNAT & DNAT are used by the kernel module */
+ XT_HMARK_DADR_AND,
+ XT_HMARK_SPI_AND,
+ XT_HMARK_SPI_OR,
+ XT_HMARK_SPORT_AND,
+ XT_HMARK_DPORT_AND,
+ XT_HMARK_SPORT_OR,
+ XT_HMARK_DPORT_OR,
+ XT_HMARK_PROTO_AND,
+ XT_HMARK_RND,
+ XT_HMARK_MODULUS,
+ XT_HMARK_OFFSET,
+ XT_HMARK_USE_SNAT,
+ XT_HMARK_USE_DNAT,
+ XT_HMARK_METHOD_L3,
+ XT_HMARK_METHOD_L3_4,
+ XT_F_HMARK_USE_SNAT = 1 << XT_HMARK_USE_SNAT,
+ XT_F_HMARK_USE_DNAT = 1 << XT_HMARK_USE_DNAT,
+ XT_F_HMARK_SADR_AND = 1 << XT_HMARK_SADR_AND,
+ XT_F_HMARK_DADR_AND = 1 << XT_HMARK_DADR_AND,
+ XT_F_HMARK_SPI_AND = 1 << XT_HMARK_SPI_AND,
+ XT_F_HMARK_SPI_OR = 1 << XT_HMARK_SPI_OR,
+ XT_F_HMARK_SPORT_AND = 1 << XT_HMARK_SPORT_AND,
+ XT_F_HMARK_DPORT_AND = 1 << XT_HMARK_DPORT_AND,
+ XT_F_HMARK_SPORT_OR = 1 << XT_HMARK_SPORT_OR,
+ XT_F_HMARK_DPORT_OR = 1 << XT_HMARK_DPORT_OR,
+ XT_F_HMARK_PROTO_AND = 1 << XT_HMARK_PROTO_AND,
+ XT_F_HMARK_RND = 1 << XT_HMARK_RND,
+ XT_F_HMARK_MODULUS = 1 << XT_HMARK_MODULUS,
+ XT_F_HMARK_OFFSET = 1 << XT_HMARK_OFFSET,
+ XT_F_HMARK_METHOD_L3 = 1 << XT_HMARK_METHOD_L3,
+ XT_F_HMARK_METHOD_L3_4 = 1 << XT_HMARK_METHOD_L3_4,
+};
+
+#define XT_F_HMARK_L4_OPTS (XT_F_HMARK_SPI_AND | XT_F_HMARK_SPI_OR\
+ | XT_F_HMARK_SPORT_AND | XT_F_HMARK_SPORT_OR\
+ | XT_F_HMARK_DPORT_AND | XT_F_HMARK_DPORT_OR\
+ | XT_F_HMARK_PROTO_AND)
+
+union hports {
+ struct {
+ __u16 src;
+ __u16 dst;
+ } p16;
+ __u32 v32;
+};
+
+struct xt_hmark_info {
+ union nf_inet_addr smask; /* Source address mask */
+ union nf_inet_addr dmask; /* Dest address mask */
+ union hports pmask;
+ union hports pset;
+ __u32 spimask;
+ __u32 spiset;
+ __u16 flags; /* Print out only */
+ __u16 prmask; /* L4 Proto mask */
+ __u32 hashrnd;
+ __u32 hmod; /* Modulus */
+ __u32 hoffs; /* Offset */
+};
+
+#endif /* XT_HMARK_H_ */
--
1.7.2.3
^ permalink raw reply related [flat|nested] 10+ messages in thread