Patchwork [v5,2/3] NETFILTER module xt_hmark, new target for HASH based fwmark

login
register
mail settings
Submitter Hans Schillstrom
Date Jan. 2, 2012, 3:06 p.m.
Message ID <1325516801-25488-3-git-send-email-hans.schillstrom@ericsson.com>
Download mbox | patch
Permalink /patch/133853/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Hans Schillstrom - Jan. 2, 2012, 3:06 p.m.
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
       independet 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 finaly an
       offset could be added, i.e the final mark will be within a range.
       ICMP errors will have hash calc based on the original message.
       Note:
        - None of the parameters effect the packet it self
          only the calculated hash value.
       Fragmentation:
        - If a packet is fragmented NONE of the Fragments will include
          ports in the hash calculation.
          When fragments arrives on different machines HMARK will produce
          same fwmark for all frags inpendent of machine so they can be routed
          to the same destination.
        - If nf_defrag_ipv{4,6} is loaded the packets will be defragmented
          before reaching HMARK, i.e. in that case ports (if any) will be used.
          (ICMP Time exceeded will be sent if fragments are lost)

       Parameters: For all masks default is all "1:s", to disable a field
                   use mask 0. For IPv6 it's just the last 32 bits that
                   is included in the hash.

       --hmark-smask length (0-32 or 0-128)
              The value to AND the source address with (saddr & value).

       --hmark-dmask length (0-32 or 0-128)
              The value to AND the dest. address with (daddr & value).

       --hmark-sp-mask value
              A 16 bit value to AND the src port with (sport & value).

       --hmark-dp-mask value
              A 16 bit value to AND the dest port with (dport & value).

       --hmark-sp-set value
              A 16 bit value to OR the src port with (sport | value).

       --hmark-dp-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
              A 16 bit value to AND the L4 proto field with (proto & value).

       --hmark-rnd value
              A 32 bit intitial value for hash calc, default is 0xc175a3b8.

       --hmark-dnat (only IPv4)
              Replace src addr/port with original dst addr/port before calc, hash

       --hmark-snat (only IPv4)
              Replace dst addr/port with original src addr/port before calc, hash

       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-offs alue (must be > 0)
              The easiest way to describe this is:  hash = hash + <value>

       Examples:

       Default rule handles all TCP, UDP, SCTP, ESP & AH
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 |   62 +++++++
 net/netfilter/Kconfig              |   17 ++
 net/netfilter/Makefile             |    1 +
 net/netfilter/xt_hmark.c           |  332 ++++++++++++++++++++++++++++++++++++
 4 files changed, 412 insertions(+), 0 deletions(-)
 create mode 100644 include/linux/netfilter/xt_hmark.h
 create mode 100644 net/netfilter/xt_hmark.c

Patch

diff --git a/include/linux/netfilter/xt_hmark.h b/include/linux/netfilter/xt_hmark.h
new file mode 100644
index 0000000..366ecce
--- /dev/null
+++ b/include/linux/netfilter/xt_hmark.h
@@ -0,0 +1,62 @@ 
+#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_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,
+};
+
+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 d5597b7..6e85d7d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -470,6 +470,23 @@  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 1a02853..359eeb6 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -56,6 +56,7 @@  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..1a854a9
--- /dev/null
+++ b/net/netfilter/xt_hmark.c
@@ -0,0 +1,332 @@ 
+/*
+ * 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.
+ *	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.
+ *	AH will not use ports even if it might be possible.
+ *	Tunnels - only the outer saddr and daddr will beused,
+ *
+ *	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).
+ *
+ *Note:	None of the fragments will include ports/spi in the calculation of
+ *	the hash value. (i.e. all frags must the same hash value.)
+ *
+ *	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>
+#include <net/netfilter/nf_nat.h>
+
+#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 inner header so calc can be made on the source message
+ *
+ * iphsz: ip header size in bytes
+ * nhoff: network header offset
+ * return; updated nhoff if an 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
+/* Dummy header used for size calculation of an error header */
+struct _icmpv6_errh {
+	__u8		icmp6_type;
+	__u8		icmp6_code;
+	__u16		icmp6_cksum;
+	__u32		icmp6_nu;
+};
+/*
+ * Get ipv6 header offset if icmp type < 128 i.e. an error.
+ * @param: offset  input: where ICMPv6 header starts
+ *                output: where ipv6 header starts / unchanged.
+ *
+ * Returns true if it's an icmp error
+ *              and updates *offset to where ipv6 header starts
+ */
+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 _icmpv6_errh);
+		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
+ */
+__u32 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;
+	u8 nexthdr;
+	union hports uports = { .v32 = 0 };
+	unsigned short fragoff = 0;
+
+	if (!info->hmod)
+		return XT_CONTINUE;
+
+	nhoffs = skb_network_offset(skb);
+	ip6 = (struct ipv6hdr *) (skb->data + nhoffs);
+
+	/* Try to get transport header */
+	nexthdr = __ipv6_find_hdr(skb, &nhoffs, -1, &fragoff, &flag);
+	if (nexthdr < 0)
+		return XT_CONTINUE;
+	/* dont 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)) {
+		ip6 = skb_header_pointer(skb, nhoffs, sizeof(_ip6), &_ip6);
+		if (!ip6)
+			return XT_CONTINUE;
+		nhoffs += sizeof(_ip6);
+		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]);
+
+	/* Is next header valid for port or SPI calculation ? */
+	poff = proto_ports_offset(nexthdr);
+	if ((flag & IP6T_FH_F_FRAG) || poff < 0)
+		goto no6ports;
+	nhoffs += poff;
+	/* Since uports is modified, skb_header_pointer() can't be used */
+	 if (!pskb_may_pull(skb, nhoffs + 4))
+		goto no6ports;
+	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
+ */
+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;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+	union hports uports;
+
+	if (!info->hmod)
+		return XT_CONTINUE;
+
+	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 (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;
+		}
+	}
+	/* Check if ports can be used in hash calculation. */
+	poff = proto_ports_offset(ip_proto);
+	if (frag || poff < 0)
+		goto noports;
+
+	nhoff += (ip->ihl * 4) + poff;
+	if (!pskb_may_pull(skb, nhoff + 4))
+		goto noports;
+
+	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);