diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c9345fe3f8d214c6c58db5107ab42512222c6833..138c1868be1d3ff09de5aee2c1774c3250b9cb1e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -257,6 +257,7 @@ extern int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { unsigned int family; + unsigned int proto; struct module *owner; struct xfrm_type *type_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; @@ -267,6 +268,8 @@ struct xfrm_state_afinfo { int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); + int (*extract_output)(struct xfrm_state *x, + struct sk_buff *skb); }; extern int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo); @@ -312,7 +315,18 @@ struct xfrm_mode { * header. The value of the network header will always point * to the top IP header while skb->data will point to the payload. */ - int (*output)(struct xfrm_state *x,struct sk_buff *skb); + int (*output2)(struct xfrm_state *x,struct sk_buff *skb); + + /* + * This is the actual output entry point. + * + * For transport mode and equivalent this would be identical to + * output2 (which does not need to be set). While tunnel mode + * and equivalent would set this to a tunnel encapsulation function + * (xfrm4_prepare_output or xfrm6_prepare_output) that would in turn + * call output2. + */ + int (*output)(struct xfrm_state *x, struct sk_buff *skb); struct xfrm_state_afinfo *afinfo; struct module *owner; @@ -454,6 +468,35 @@ struct xfrm_skb_cb { #define XFRM_SKB_CB(__skb) ((struct xfrm_skb_cb *)&((__skb)->cb[0])) +/* + * This structure is used by the afinfo prepare_input/prepare_output functions + * to transmit header information to the mode input/output functions. + */ +struct xfrm_mode_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + } header; + + /* Copied from header for IPv4, always set to zero and DF for IPv6. */ + __be16 id; + __be16 frag_off; + + /* TOS for IPv4, class for IPv6. */ + u8 tos; + + /* TTL for IPv4, hop limitfor IPv6. */ + u8 ttl; + + /* Protocol for IPv4, NH for IPv6. */ + u8 protocol; + + /* Used by IPv6 only, zero for IPv4. */ + u8 flow_lbl[3]; +}; + +#define XFRM_MODE_SKB_CB(__skb) ((struct xfrm_mode_skb_cb *)&((__skb)->cb[0])) + /* Audit Information */ struct xfrm_audit { @@ -1051,6 +1094,7 @@ extern void xfrm_replay_notify(struct xfrm_state *x, int event); extern int xfrm_state_mtu(struct xfrm_state *x, int mtu); extern int xfrm_init_state(struct xfrm_state *x); extern int xfrm_output(struct sk_buff *skb); +extern int xfrm4_extract_header(struct sk_buff *skb); extern int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); extern int xfrm4_rcv(struct sk_buff *skb); @@ -1060,9 +1104,12 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) return xfrm4_rcv_encap(skb, nexthdr, spi, 0); } +extern int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); +extern int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_output(struct sk_buff *skb); extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); +extern int xfrm6_extract_header(struct sk_buff *skb); extern int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi); extern int xfrm6_rcv(struct sk_buff *skb); extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, @@ -1072,6 +1119,8 @@ extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short extern __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr); extern void xfrm6_tunnel_free_spi(xfrm_address_t *saddr); extern __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr); +extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); +extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_output(struct sk_buff *skb); extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index e42e122414be1e461c01898aff091f405b48dfa2..94842adce144111d9cf14096329d2760e41ce06e 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -43,7 +43,17 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) ph = (struct ip_beet_phdr *)__skb_pull(skb, sizeof(*iph) - hdrlen); top_iph = ip_hdr(skb); - memmove(top_iph, iph, sizeof(*iph)); + + top_iph->ihl = 5; + top_iph->version = 4; + + top_iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol; + top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos; + + top_iph->id = XFRM_MODE_SKB_CB(skb)->id; + top_iph->frag_off = XFRM_MODE_SKB_CB(skb)->frag_off; + top_iph->ttl = XFRM_MODE_SKB_CB(skb)->ttl; + if (unlikely(optlen)) { BUG_ON(optlen < 0); @@ -111,7 +121,8 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) static struct xfrm_mode xfrm4_beet_mode = { .input = xfrm4_beet_input, - .output = xfrm4_beet_output, + .output2 = xfrm4_beet_output, + .output = xfrm4_prepare_output, .owner = THIS_MODULE, .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 68a9f56ff09f2ba7afba24999631659bfeb0810d..cc8bbb274e37e8b07bb1a5419feef21ef457c5f6 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -36,53 +36,37 @@ static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb->dst; - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; - struct iphdr *iph, *top_iph; + struct iphdr *top_iph; int flags; - iph = ip_hdr(skb); - skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); - skb->transport_header = skb->network_header + sizeof(*iph); + skb->transport_header = skb->network_header + sizeof(*top_iph); top_iph = ip_hdr(skb); top_iph->ihl = 5; top_iph->version = 4; - flags = x->props.flags; + top_iph->protocol = x->inner_mode->afinfo->proto; /* DS disclosed */ - if (xdst->route->ops->family == AF_INET) { - top_iph->protocol = IPPROTO_IPIP; - top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos); - top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? - 0 : (iph->frag_off & htons(IP_DF)); - } -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - else { - struct ipv6hdr *ipv6h = (struct ipv6hdr*)iph; - top_iph->protocol = IPPROTO_IPV6; - top_iph->tos = INET_ECN_encapsulate(iph->tos, ipv6_get_dsfield(ipv6h)); - top_iph->frag_off = 0; - } -#endif + top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, + XFRM_MODE_SKB_CB(skb)->tos); + flags = x->props.flags; if (flags & XFRM_STATE_NOECN) IP_ECN_clear(top_iph); - if (!top_iph->frag_off) - __ip_select_ident(top_iph, dst->child, 0); + top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? + 0 : XFRM_MODE_SKB_CB(skb)->frag_off; + ip_select_ident(top_iph, dst->child, NULL); top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; - skb->protocol = htons(ETH_P_IP); - - memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); return 0; } @@ -136,7 +120,8 @@ static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) static struct xfrm_mode xfrm4_tunnel_mode = { .input = xfrm4_tunnel_input, - .output = xfrm4_tunnel_output, + .output2 = xfrm4_tunnel_output, + .output = xfrm4_prepare_output, .owner = THIS_MODULE, .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index c4a7156962bd58797d93b7c21051bcc797c98de9..13fd11335e28ecbb303b8725fa93294a221733b8 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -8,11 +8,12 @@ * 2 of the License, or (at your option) any later version. */ -#include #include #include +#include #include #include +#include #include #include #include @@ -25,8 +26,6 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE) goto out; - IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; - if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) goto out; @@ -40,19 +39,39 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) return ret; } +int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + err = xfrm4_tunnel_check_size(skb); + if (err) + return err; + + return xfrm4_extract_header(skb); +} + +int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + err = x->inner_mode->afinfo->extract_output(x, skb); + if (err) + return err; + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; + + skb->protocol = htons(ETH_P_IP); + + return x->outer_mode->output2(x, skb); +} +EXPORT_SYMBOL(xfrm4_prepare_output); + static inline int xfrm4_output_one(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; struct iphdr *iph; int err; - if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { - err = xfrm4_tunnel_check_size(skb); - if (err) - goto error_nolock; - } - err = xfrm_output(skb); if (err) goto error_nolock; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 13d54a1c3337bd311c7245f331367296f07b0558..e6030e74ff65de644154532084ee4e8418b26265 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -47,12 +47,29 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->props.family = AF_INET; } +int xfrm4_extract_header(struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + + XFRM_MODE_SKB_CB(skb)->id = iph->id; + XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off; + XFRM_MODE_SKB_CB(skb)->tos = iph->tos; + XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl; + XFRM_MODE_SKB_CB(skb)->protocol = iph->protocol; + memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0, + sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); + + return 0; +} + static struct xfrm_state_afinfo xfrm4_state_afinfo = { .family = AF_INET, + .proto = IPPROTO_IPIP, .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, .output = xfrm4_output, + .extract_output = xfrm4_extract_output, }; void __init xfrm4_state_init(void) diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 2bfb4f05c14cdffec7f7c455e5ecf43f34acd4c9..4988ed9c76c62da8dffc1db86b29d8bc073253ac 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -25,25 +25,24 @@ */ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) { - struct ipv6hdr *iph, *top_iph; - u8 *prevhdr; - int hdr_len; + struct ipv6hdr *top_iph; - iph = ipv6_hdr(skb); - - hdr_len = ip6_find_1stfragopt(skb, &prevhdr); - - skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); - skb->transport_header = skb->network_header + hdr_len; - __skb_pull(skb, hdr_len); - + skb->mac_header = skb->network_header + + offsetof(struct ipv6hdr, nexthdr); + skb->transport_header = skb->network_header + sizeof(*top_iph); top_iph = ipv6_hdr(skb); - memmove(top_iph, iph, hdr_len); + top_iph->version = 6; + + memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, + sizeof(top_iph->flow_lbl)); + top_iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol; + + ipv6_change_dsfield(top_iph, 0, XFRM_MODE_SKB_CB(skb)->tos); + top_iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl; 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; } @@ -76,7 +75,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) static struct xfrm_mode xfrm6_beet_mode = { .input = xfrm6_beet_input, - .output = xfrm6_beet_output, + .output2 = xfrm6_beet_output, + .output = xfrm6_prepare_output, .owner = THIS_MODULE, .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 9a43ea722481865529eb5c1a1cd571703d09c86c..d45ce5d44197dc49cb67a3f68d69dee20cd0ad6a 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -38,33 +38,22 @@ static inline void ip6ip_ecn_decapsulate(struct sk_buff *skb) static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb->dst; - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; - struct ipv6hdr *iph, *top_iph; + struct ipv6hdr *top_iph; int dsfield; - iph = ipv6_hdr(skb); - skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); - skb->transport_header = skb->network_header + sizeof(*iph); + skb->transport_header = skb->network_header + sizeof(*top_iph); top_iph = ipv6_hdr(skb); top_iph->version = 6; - if (xdst->route->ops->family == AF_INET6) { - 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]; - top_iph->nexthdr = IPPROTO_IPV6; - } else { - top_iph->priority = 0; - top_iph->flow_lbl[0] = 0; - top_iph->flow_lbl[1] = 0; - top_iph->flow_lbl[2] = 0; - top_iph->nexthdr = IPPROTO_IPIP; - } - dsfield = ipv6_get_dsfield(top_iph); + + memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, + sizeof(top_iph->flow_lbl)); + top_iph->nexthdr = x->inner_mode->afinfo->proto; + + dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, dsfield); if (x->props.flags & XFRM_STATE_NOECN) dsfield &= ~INET_ECN_MASK; @@ -72,7 +61,6 @@ static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) 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); - skb->protocol = htons(ETH_P_IPV6); return 0; } @@ -116,7 +104,8 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) static struct xfrm_mode xfrm6_tunnel_mode = { .input = xfrm6_tunnel_input, - .output = xfrm6_tunnel_output, + .output2 = xfrm6_tunnel_output, + .output = xfrm6_prepare_output, .owner = THIS_MODULE, .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 656976760ad47175afa8bc6ac7d2152d5e7f95b4..bc2e80e3b0b1cde9bfb421cc7f5381304acbf37d 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -10,10 +10,12 @@ */ #include -#include +#include +#include #include #include #include +#include #include #include @@ -43,19 +45,38 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) return ret; } +int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + err = xfrm6_tunnel_check_size(skb); + if (err) + return err; + + return xfrm6_extract_header(skb); +} + +int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + err = x->inner_mode->afinfo->extract_output(x, skb); + if (err) + return err; + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + + skb->protocol = htons(ETH_P_IPV6); + + return x->outer_mode->output2(x, skb); +} +EXPORT_SYMBOL(xfrm6_prepare_output); + static inline int xfrm6_output_one(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; struct ipv6hdr *iph; int err; - if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { - err = xfrm6_tunnel_check_size(skb); - if (err) - goto error_nolock; - } - err = xfrm_output(skb); if (err) goto error_nolock; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index b392bee396f16341c2842aa20c3759c19afb0238..98b05f47232252a32b1b76eb9a96aa5a61999627 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -168,13 +169,30 @@ __xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n) return 0; } +int xfrm6_extract_header(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + + XFRM_MODE_SKB_CB(skb)->id = 0; + XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF); + XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph); + XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit; + XFRM_MODE_SKB_CB(skb)->protocol = iph->nexthdr; + memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl, + sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); + + return 0; +} + static struct xfrm_state_afinfo xfrm6_state_afinfo = { .family = AF_INET6, + .proto = IPPROTO_IPV6, .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, + .extract_output = xfrm6_extract_output, }; void __init xfrm6_state_init(void)