From b59f45d0b2878ab76f8053b0973654e6621828ee Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 27 May 2006 23:05:54 -0700 Subject: [PATCH] [IPSEC] xfrm: Abstract out encapsulation modes This patch adds the structure xfrm_mode. It is meant to represent the operations carried out by transport/tunnel modes. By doing this we allow additional encapsulation modes to be added without clogging up the xfrm_input/xfrm_output paths. Candidate modes include 4-to-6 tunnel mode, 6-to-4 tunnel mode, and BEET modes. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 4 + include/net/xfrm.h | 17 +++++ net/ipv4/Kconfig | 18 +++++ net/ipv4/Makefile | 2 + net/ipv4/xfrm4_input.c | 28 +------ net/ipv4/xfrm4_mode_transport.c | 69 ++++++++++++++++++ net/ipv4/xfrm4_mode_tunnel.c | 125 ++++++++++++++++++++++++++++++++ net/ipv4/xfrm4_output.c | 61 +--------------- net/ipv6/Kconfig | 20 +++++ net/ipv6/Makefile | 2 + net/ipv6/ip6_output.c | 2 + net/ipv6/xfrm6_input.c | 29 +------- net/ipv6/xfrm6_mode_transport.c | 73 +++++++++++++++++++ net/ipv6/xfrm6_mode_tunnel.c | 121 +++++++++++++++++++++++++++++++ net/ipv6/xfrm6_output.c | 63 +--------------- net/xfrm/xfrm_policy.c | 83 +++++++++++++++++++++ net/xfrm/xfrm_state.c | 6 ++ 17 files changed, 553 insertions(+), 170 deletions(-) create mode 100644 net/ipv4/xfrm4_mode_transport.c create mode 100644 net/ipv4/xfrm4_mode_tunnel.c create mode 100644 net/ipv6/xfrm6_mode_transport.c create mode 100644 net/ipv6/xfrm6_mode_tunnel.c diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 6b42cc474c01..46a15c7a1a13 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -118,6 +118,10 @@ enum XFRM_SHARE_UNIQUE /* Use once */ }; +#define XFRM_MODE_TRANSPORT 0 +#define XFRM_MODE_TUNNEL 1 +#define XFRM_MODE_MAX 2 + /* Netlink configuration messages. */ enum { XFRM_MSG_BASE = 0x10, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ed7c9747059d..ed5bb34f817f 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -20,6 +20,8 @@ #include #define XFRM_ALIGN8(len) (((len) + 7) & ~7) +#define MODULE_ALIAS_XFRM_MODE(family, encap) \ + MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) extern struct sock *xfrm_nl; extern u32 sysctl_xfrm_aevent_etime; @@ -164,6 +166,7 @@ struct xfrm_state /* Reference to data common to all the instances of this * transformer. */ struct xfrm_type *type; + struct xfrm_mode *mode; /* Security context */ struct xfrm_sec_ctx *security; @@ -205,6 +208,7 @@ struct xfrm_dst; struct xfrm_policy_afinfo { unsigned short family; struct xfrm_type *type_map[256]; + struct xfrm_mode *mode_map[XFRM_MODE_MAX]; struct dst_ops *dst_ops; void (*garbage_collect)(void); int (*dst_lookup)(struct xfrm_dst **dst, struct flowi *fl); @@ -267,6 +271,19 @@ extern int xfrm_unregister_type(struct xfrm_type *type, unsigned short family); extern struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family); extern void xfrm_put_type(struct xfrm_type *type); +struct xfrm_mode { + int (*input)(struct xfrm_state *x, struct sk_buff *skb); + int (*output)(struct sk_buff *skb); + + struct module *owner; + unsigned int encap; +}; + +extern int xfrm_register_mode(struct xfrm_mode *mode, int family); +extern int xfrm_unregister_mode(struct xfrm_mode *mode, int family); +extern struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family); +extern void xfrm_put_mode(struct xfrm_mode *mode); + struct xfrm_tmpl { /* id in template is interpreted as: diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index e40f75322377..35eb70b1448d 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -414,6 +414,24 @@ config INET_TUNNEL tristate default n +config INET_XFRM_MODE_TRANSPORT + tristate "IP: IPsec transport mode" + default y + select XFRM + ---help--- + Support for IPsec transport mode. + + If unsure, say Y. + +config INET_XFRM_MODE_TUNNEL + tristate "IP: IPsec tunnel mode" + default y + select XFRM + ---help--- + Support for IPsec tunnel mode. + + If unsure, say Y. + config INET_DIAG tristate "INET: socket monitoring interface" default y diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 9ef50a0b9d2c..4cc94482eacc 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -24,6 +24,8 @@ obj-$(CONFIG_INET_ESP) += esp4.o obj-$(CONFIG_INET_IPCOMP) += ipcomp.o obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o obj-$(CONFIG_INET_TUNNEL) += tunnel4.o +obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o +obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o obj-$(CONFIG_IP_PNP) += ipconfig.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_RR) += multipath_rr.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_RANDOM) += multipath_random.o diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 3e174c83bfe7..817ed84511a6 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include @@ -24,15 +23,6 @@ int xfrm4_rcv(struct sk_buff *skb) EXPORT_SYMBOL(xfrm4_rcv); -static inline void ipip_ecn_decapsulate(struct sk_buff *skb) -{ - struct iphdr *outer_iph = skb->nh.iph; - struct iphdr *inner_iph = skb->h.ipiph; - - if (INET_ECN_is_ce(outer_iph->tos)) - IP_ECN_set_ce(inner_iph); -} - static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) { switch (nexthdr) { @@ -113,24 +103,10 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) xfrm_vec[xfrm_nr++] = x; - iph = skb->nh.iph; + if (x->mode->input(x, skb)) + goto drop; if (x->props.mode) { - if (iph->protocol != IPPROTO_IPIP) - goto drop; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto drop; - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - goto drop; - if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv4_copy_dscp(iph, skb->h.ipiph); - if (!(x->props.flags & XFRM_STATE_NOECN)) - ipip_ecn_decapsulate(skb); - skb->mac.raw = memmove(skb->data - skb->mac_len, - skb->mac.raw, skb->mac_len); - skb->nh.raw = skb->data; - memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); decaps = 1; break; } diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c new file mode 100644 index 000000000000..e46d9a4ccc55 --- /dev/null +++ b/net/ipv4/xfrm4_mode_transport.c @@ -0,0 +1,69 @@ +/* + * xfrm4_mode_transport.c - Transport mode encapsulation for IPv4. + * + * Copyright (c) 2004-2006 Herbert Xu + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Add encapsulation header. + * + * The IP header will be moved forward to make space for the encapsulation + * header. + * + * On exit, skb->h will be set to the start of the payload to be processed + * by x->type->output and skb->nh will be set to the top IP header. + */ +static int xfrm4_transport_output(struct sk_buff *skb) +{ + struct xfrm_state *x; + struct iphdr *iph; + int ihl; + + iph = skb->nh.iph; + skb->h.ipiph = iph; + + ihl = iph->ihl * 4; + skb->h.raw += ihl; + + x = skb->dst->xfrm; + skb->nh.raw = memmove(skb_push(skb, x->props.header_len), iph, ihl); + return 0; +} + +static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) +{ + return 0; +} + +static struct xfrm_mode xfrm4_transport_mode = { + .input = xfrm4_transport_input, + .output = xfrm4_transport_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TRANSPORT, +}; + +static int __init xfrm4_transport_init(void) +{ + return xfrm_register_mode(&xfrm4_transport_mode, AF_INET); +} + +static void __exit xfrm4_transport_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm4_transport_mode, AF_INET); + BUG_ON(err); +} + +module_init(xfrm4_transport_init); +module_exit(xfrm4_transport_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TRANSPORT); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c new file mode 100644 index 000000000000..f8d880beb12f --- /dev/null +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -0,0 +1,125 @@ +/* + * xfrm4_mode_tunnel.c - Tunnel mode encapsulation for IPv4. + * + * Copyright (c) 2004-2006 Herbert Xu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static inline void ipip_ecn_decapsulate(struct sk_buff *skb) +{ + struct iphdr *outer_iph = skb->nh.iph; + struct iphdr *inner_iph = skb->h.ipiph; + + if (INET_ECN_is_ce(outer_iph->tos)) + IP_ECN_set_ce(inner_iph); +} + +/* Add encapsulation header. + * + * The top IP header will be constructed per RFC 2401. The following fields + * in it shall be filled in by x->type->output: + * tot_len + * check + * + * On exit, skb->h will be set to the start of the payload to be processed + * by x->type->output and skb->nh will be set to the top IP header. + */ +static int xfrm4_tunnel_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb->dst; + struct xfrm_state *x = dst->xfrm; + struct iphdr *iph, *top_iph; + int flags; + + iph = skb->nh.iph; + skb->h.ipiph = iph; + + skb->nh.raw = skb_push(skb, x->props.header_len); + top_iph = skb->nh.iph; + + top_iph->ihl = 5; + top_iph->version = 4; + + /* DS disclosed */ + top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos); + + flags = x->props.flags; + if (flags & XFRM_STATE_NOECN) + IP_ECN_clear(top_iph); + + top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? + 0 : (iph->frag_off & htons(IP_DF)); + if (!top_iph->frag_off) + __ip_select_ident(top_iph, dst->child, 0); + + top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); + + top_iph->saddr = x->props.saddr.a4; + top_iph->daddr = x->id.daddr.a4; + top_iph->protocol = IPPROTO_IPIP; + + memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); + return 0; +} + +static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct iphdr *iph = skb->nh.iph; + int err = -EINVAL; + + if (iph->protocol != IPPROTO_IPIP) + goto out; + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto out; + + if (skb_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + goto out; + + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv4_copy_dscp(iph, skb->h.ipiph); + if (!(x->props.flags & XFRM_STATE_NOECN)) + ipip_ecn_decapsulate(skb); + skb->mac.raw = memmove(skb->data - skb->mac_len, + skb->mac.raw, skb->mac_len); + skb->nh.raw = skb->data; + memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); + err = 0; + +out: + return err; +} + +static struct xfrm_mode xfrm4_tunnel_mode = { + .input = xfrm4_tunnel_input, + .output = xfrm4_tunnel_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TUNNEL, +}; + +static int __init xfrm4_tunnel_init(void) +{ + return xfrm_register_mode(&xfrm4_tunnel_mode, AF_INET); +} + +static void __exit xfrm4_tunnel_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm4_tunnel_mode, AF_INET); + BUG_ON(err); +} + +module_init(xfrm4_tunnel_init); +module_exit(xfrm4_tunnel_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TUNNEL); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 4ef8efaf6a67..ac9d91d4bb05 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -12,67 +12,10 @@ #include #include #include -#include #include #include #include -/* Add encapsulation header. - * - * In transport mode, the IP header will be moved forward to make space - * for the encapsulation header. - * - * In tunnel mode, the top IP header will be constructed per RFC 2401. - * The following fields in it shall be filled in by x->type->output: - * tot_len - * check - * - * On exit, skb->h will be set to the start of the payload to be processed - * by x->type->output and skb->nh will be set to the top IP header. - */ -static void xfrm4_encap(struct sk_buff *skb) -{ - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; - struct iphdr *iph, *top_iph; - int flags; - - iph = skb->nh.iph; - skb->h.ipiph = iph; - - skb->nh.raw = skb_push(skb, x->props.header_len); - top_iph = skb->nh.iph; - - if (!x->props.mode) { - skb->h.raw += iph->ihl*4; - memmove(top_iph, iph, iph->ihl*4); - return; - } - - top_iph->ihl = 5; - top_iph->version = 4; - - /* DS disclosed */ - top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos); - - flags = x->props.flags; - if (flags & XFRM_STATE_NOECN) - IP_ECN_clear(top_iph); - - top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? - 0 : (iph->frag_off & htons(IP_DF)); - if (!top_iph->frag_off) - __ip_select_ident(top_iph, dst->child, 0); - - top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); - - top_iph->saddr = x->props.saddr.a4; - top_iph->daddr = x->id.daddr.a4; - top_iph->protocol = IPPROTO_IPIP; - - memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); -} - static int xfrm4_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; @@ -121,7 +64,9 @@ static int xfrm4_output_one(struct sk_buff *skb) if (err) goto error; - xfrm4_encap(skb); + err = x->mode->output(skb); + if (err) + goto error; err = x->type->output(x, skb); if (err) diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index f8a107ab5592..e923d4dea418 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -106,6 +106,26 @@ config INET6_TUNNEL tristate default n +config INET6_XFRM_MODE_TRANSPORT + tristate "IPv6: IPsec transport mode" + depends on IPV6 + default IPV6 + select XFRM + ---help--- + Support for IPsec transport mode. + + If unsure, say Y. + +config INET6_XFRM_MODE_TUNNEL + tristate "IPv6: IPsec tunnel mode" + depends on IPV6 + default IPV6 + select XFRM + ---help--- + Support for IPsec tunnel mode. + + If unsure, say Y. + config IPV6_TUNNEL tristate "IPv6: IPv6-in-IPv6 tunnel" select INET6_TUNNEL diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index a760b0988fbb..386e0a626948 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -20,6 +20,8 @@ obj-$(CONFIG_INET6_ESP) += esp6.o obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o +obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o +obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e46048974f37..416f6e428a0a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -488,6 +489,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } +EXPORT_SYMBOL_GPL(ip6_find_1stfragopt); static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 00cfdee18dca..0405d74ff910 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -13,21 +13,9 @@ #include #include #include -#include -#include -#include #include #include -static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) -{ - struct ipv6hdr *outer_iph = skb->nh.ipv6h; - struct ipv6hdr *inner_iph = skb->h.ipv6h; - - if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) - IP6_ECN_set_ce(inner_iph); -} - int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi) { int err; @@ -81,21 +69,10 @@ int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi) xfrm_vec[xfrm_nr++] = x; + if (x->mode->input(x, skb)) + goto drop; + if (x->props.mode) { /* XXX */ - if (nexthdr != IPPROTO_IPV6) - goto drop; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto drop; - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - goto drop; - if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h); - if (!(x->props.flags & XFRM_STATE_NOECN)) - ipip6_ecn_decapsulate(skb); - skb->mac.raw = memmove(skb->data - skb->mac_len, - skb->mac.raw, skb->mac_len); - skb->nh.raw = skb->data; decaps = 1; break; } diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c new file mode 100644 index 000000000000..5efbbae08ef0 --- /dev/null +++ b/net/ipv6/xfrm6_mode_transport.c @@ -0,0 +1,73 @@ +/* + * xfrm6_mode_transport.c - Transport mode encapsulation for IPv6. + * + * Copyright (C) 2002 USAGI/WIDE Project + * Copyright (c) 2004-2006 Herbert Xu + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Add encapsulation header. + * + * The IP header and mutable extension headers will be moved forward to make + * space for the encapsulation header. + * + * On exit, skb->h will be set to the start of the encapsulation header to be + * filled in by x->type->output and skb->nh will be set to the nextheader field + * of the extension header directly preceding the encapsulation header, or in + * its absence, that of the top IP header. The value of skb->data will always + * point to the top IP header. + */ +static int xfrm6_transport_output(struct sk_buff *skb) +{ + struct xfrm_state *x = skb->dst->xfrm; + struct ipv6hdr *iph; + u8 *prevhdr; + int hdr_len; + + skb_push(skb, x->props.header_len); + iph = skb->nh.ipv6h; + + hdr_len = ip6_find_1stfragopt(skb, &prevhdr); + skb->nh.raw = prevhdr - x->props.header_len; + skb->h.raw = skb->data + hdr_len; + memmove(skb->data, iph, hdr_len); + return 0; +} + +static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) +{ + return 0; +} + +static struct xfrm_mode xfrm6_transport_mode = { + .input = xfrm6_transport_input, + .output = xfrm6_transport_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TRANSPORT, +}; + +static int __init xfrm6_transport_init(void) +{ + return xfrm_register_mode(&xfrm6_transport_mode, AF_INET6); +} + +static void __exit xfrm6_transport_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_transport_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_transport_init); +module_exit(xfrm6_transport_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TRANSPORT); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c new file mode 100644 index 000000000000..8af79be2edca --- /dev/null +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -0,0 +1,121 @@ +/* + * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6. + * + * Copyright (C) 2002 USAGI/WIDE Project + * Copyright (c) 2004-2006 Herbert Xu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) +{ + struct ipv6hdr *outer_iph = skb->nh.ipv6h; + struct ipv6hdr *inner_iph = skb->h.ipv6h; + + if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) + IP6_ECN_set_ce(inner_iph); +} + +/* Add encapsulation header. + * + * The top IP header will be constructed per RFC 2401. The following fields + * in it shall be filled in by x->type->output: + * payload_len + * + * On exit, skb->h will be set to the start of the encapsulation header to be + * filled in by x->type->output and skb->nh will be set to the nextheader field + * of the extension header directly preceding the encapsulation header, or in + * its absence, that of the top IP header. The value of skb->data will always + * point to the top IP header. + */ +static int xfrm6_tunnel_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb->dst; + struct xfrm_state *x = dst->xfrm; + struct ipv6hdr *iph, *top_iph; + int dsfield; + + skb_push(skb, x->props.header_len); + iph = skb->nh.ipv6h; + + skb->nh.raw = skb->data; + top_iph = skb->nh.ipv6h; + skb->nh.raw = &top_iph->nexthdr; + skb->h.ipv6h = top_iph + 1; + + top_iph->version = 6; + top_iph->priority = iph->priority; + top_iph->flow_lbl[0] = iph->flow_lbl[0]; + top_iph->flow_lbl[1] = iph->flow_lbl[1]; + top_iph->flow_lbl[2] = iph->flow_lbl[2]; + dsfield = ipv6_get_dsfield(top_iph); + dsfield = INET_ECN_encapsulate(dsfield, dsfield); + if (x->props.flags & XFRM_STATE_NOECN) + dsfield &= ~INET_ECN_MASK; + ipv6_change_dsfield(top_iph, 0, dsfield); + top_iph->nexthdr = IPPROTO_IPV6; + top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT); + ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); + ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + return 0; +} + +static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) +{ + int err = -EINVAL; + + if (skb->nh.raw[IP6CB(skb)->nhoff] != IPPROTO_IPV6) + goto out; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + + if (skb_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + goto out; + + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h); + if (!(x->props.flags & XFRM_STATE_NOECN)) + ipip6_ecn_decapsulate(skb); + skb->mac.raw = memmove(skb->data - skb->mac_len, + skb->mac.raw, skb->mac_len); + skb->nh.raw = skb->data; + err = 0; + +out: + return err; +} + +static struct xfrm_mode xfrm6_tunnel_mode = { + .input = xfrm6_tunnel_input, + .output = xfrm6_tunnel_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TUNNEL, +}; + +static int __init xfrm6_tunnel_init(void) +{ + return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6); +} + +static void __exit xfrm6_tunnel_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_tunnel_init); +module_exit(xfrm6_tunnel_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 80242172a5df..16e84254a252 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -14,68 +14,9 @@ #include #include #include -#include -#include #include #include -/* Add encapsulation header. - * - * In transport mode, the IP header and mutable extension headers will be moved - * forward to make space for the encapsulation header. - * - * In tunnel mode, the top IP header will be constructed per RFC 2401. - * The following fields in it shall be filled in by x->type->output: - * payload_len - * - * On exit, skb->h will be set to the start of the encapsulation header to be - * filled in by x->type->output and skb->nh will be set to the nextheader field - * of the extension header directly preceding the encapsulation header, or in - * its absence, that of the top IP header. The value of skb->data will always - * point to the top IP header. - */ -static void xfrm6_encap(struct sk_buff *skb) -{ - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; - struct ipv6hdr *iph, *top_iph; - int dsfield; - - skb_push(skb, x->props.header_len); - iph = skb->nh.ipv6h; - - if (!x->props.mode) { - u8 *prevhdr; - int hdr_len; - - hdr_len = ip6_find_1stfragopt(skb, &prevhdr); - skb->nh.raw = prevhdr - x->props.header_len; - skb->h.raw = skb->data + hdr_len; - memmove(skb->data, iph, hdr_len); - return; - } - - skb->nh.raw = skb->data; - top_iph = skb->nh.ipv6h; - skb->nh.raw = &top_iph->nexthdr; - skb->h.ipv6h = top_iph + 1; - - top_iph->version = 6; - top_iph->priority = iph->priority; - top_iph->flow_lbl[0] = iph->flow_lbl[0]; - top_iph->flow_lbl[1] = iph->flow_lbl[1]; - top_iph->flow_lbl[2] = iph->flow_lbl[2]; - dsfield = ipv6_get_dsfield(top_iph); - dsfield = INET_ECN_encapsulate(dsfield, dsfield); - if (x->props.flags & XFRM_STATE_NOECN) - dsfield &= ~INET_ECN_MASK; - ipv6_change_dsfield(top_iph, 0, dsfield); - top_iph->nexthdr = IPPROTO_IPV6; - top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT); - ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); -} - static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; @@ -118,7 +59,9 @@ static int xfrm6_output_one(struct sk_buff *skb) if (err) goto error; - xfrm6_encap(skb); + err = x->mode->output(skb); + if (err) + goto error; err = x->type->output(x, skb); if (err) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 44b64a593c01..b8936926c24b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -138,6 +138,89 @@ void xfrm_put_type(struct xfrm_type *type) module_put(type->owner); } +int xfrm_register_mode(struct xfrm_mode *mode, int family) +{ + struct xfrm_policy_afinfo *afinfo; + struct xfrm_mode **modemap; + int err; + + if (unlikely(mode->encap >= XFRM_MODE_MAX)) + return -EINVAL; + + afinfo = xfrm_policy_lock_afinfo(family); + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + + err = -EEXIST; + modemap = afinfo->mode_map; + if (likely(modemap[mode->encap] == NULL)) { + modemap[mode->encap] = mode; + err = 0; + } + + xfrm_policy_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_register_mode); + +int xfrm_unregister_mode(struct xfrm_mode *mode, int family) +{ + struct xfrm_policy_afinfo *afinfo; + struct xfrm_mode **modemap; + int err; + + if (unlikely(mode->encap >= XFRM_MODE_MAX)) + return -EINVAL; + + afinfo = xfrm_policy_lock_afinfo(family); + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + + err = -ENOENT; + modemap = afinfo->mode_map; + if (likely(modemap[mode->encap] == mode)) { + modemap[mode->encap] = NULL; + err = 0; + } + + xfrm_policy_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_unregister_mode); + +struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) +{ + struct xfrm_policy_afinfo *afinfo; + struct xfrm_mode *mode; + int modload_attempted = 0; + + if (unlikely(encap >= XFRM_MODE_MAX)) + return NULL; + +retry: + afinfo = xfrm_policy_get_afinfo(family); + if (unlikely(afinfo == NULL)) + return NULL; + + mode = afinfo->mode_map[encap]; + if (unlikely(mode && !try_module_get(mode->owner))) + mode = NULL; + if (!mode && !modload_attempted) { + xfrm_policy_put_afinfo(afinfo); + request_module("xfrm-mode-%d-%d", family, encap); + modload_attempted = 1; + goto retry; + } + + xfrm_policy_put_afinfo(afinfo); + return mode; +} + +void xfrm_put_mode(struct xfrm_mode *mode) +{ + module_put(mode->owner); +} + static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ee62c239a7e3..17b29ec3c417 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -77,6 +77,8 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->ealg); kfree(x->calg); kfree(x->encap); + if (x->mode) + xfrm_put_mode(x->mode); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -1193,6 +1195,10 @@ int xfrm_init_state(struct xfrm_state *x) if (err) goto error; + x->mode = xfrm_get_mode(x->props.mode, family); + if (x->mode == NULL) + goto error; + x->km.state = XFRM_STATE_VALID; error: