From fa86d322d89995fef1bfb5cc768b89d8c22ea0d9 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 24 Mar 2008 14:48:59 -0700 Subject: [NEIGH]: Fix race between pneigh deletion and ipv6's ndisc_recv_ns (v3). Proxy neighbors do not have any reference counting, so any caller of pneigh_lookup (unless it's a netlink triggered add/del routine) should _not_ perform any actions on the found proxy entry. There's one exception from this rule - the ipv6's ndisc_recv_ns() uses found entry to check the flags for NTF_ROUTER. This creates a race between the ndisc and pneigh_delete - after the pneigh is returned to the caller, the nd_tbl.lock is dropped and the deleting procedure may proceed. One of the fixes would be to add a reference counting, but this problem exists for ndisc only. Besides such a patch would be too big for -rc4. So I propose to introduce a __pneigh_lookup() which is supposed to be called with the lock held and use it in ndisc code to check the flags on alive pneigh entry. Changes from v2: As David noticed, Exported the __pneigh_lookup() to ipv6 module. The checkpatch generates a warning on it, since the EXPORT_SYMBOL does not follow the symbol itself, but in this file all the exports come at the end, so I decided no to break this harmony. Changes from v1: Fixed comments from YOSHIFUJI - indentation of prototype in header and the pndisc_check_router() name - and a compilation fix, pointed by Daniel - the is_routed was (falsely) considered as uninitialized by gcc. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/net/neighbour.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index ebbfb509822..64a5f0120b5 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -218,6 +218,10 @@ extern unsigned long neigh_rand_reach_time(unsigned long base); extern void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); extern struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, int creat); +extern struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, + struct net *net, + const void *key, + struct net_device *dev); extern int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); extern void neigh_app_ns(struct neighbour *n); -- cgit v1.2.3-70-g09d2 From df9dcb4588aca9cc243cf1f3f454361a84e1cbdb Mon Sep 17 00:00:00 2001 From: Kazunori MIYAZAWA Date: Mon, 24 Mar 2008 14:51:51 -0700 Subject: [IPSEC]: Fix inter address family IPsec tunnel handling. Signed-off-by: Kazunori MIYAZAWA Signed-off-by: David S. Miller --- include/net/xfrm.h | 23 +++++++++++++++++++ net/ipv4/xfrm4_mode_tunnel.c | 2 +- net/ipv4/xfrm4_output.c | 2 +- net/ipv6/xfrm6_mode_tunnel.c | 2 +- net/ipv6/xfrm6_output.c | 2 +- net/key/af_key.c | 2 +- net/xfrm/xfrm_input.c | 22 +++++++++++++++--- net/xfrm/xfrm_output.c | 18 ++++++++++++++- net/xfrm/xfrm_state.c | 54 ++++++++++++++++++++++++++++++++++++++------ net/xfrm/xfrm_user.c | 7 ++---- 10 files changed, 113 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 619c53bc3cd..4e6f9568cbe 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -204,6 +204,7 @@ struct xfrm_state * transformer. */ const struct xfrm_type *type; struct xfrm_mode *inner_mode; + struct xfrm_mode *inner_mode_iaf; struct xfrm_mode *outer_mode; /* Security context */ @@ -387,6 +388,27 @@ enum { extern int xfrm_register_mode(struct xfrm_mode *mode, int family); extern int xfrm_unregister_mode(struct xfrm_mode *mode, int family); +static inline int xfrm_af2proto(unsigned int family) +{ + switch(family) { + case AF_INET: + return IPPROTO_IPIP; + case AF_INET6: + return IPPROTO_IPV6; + default: + return 0; + } +} + +static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) +{ + if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || + (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) + return x->inner_mode; + else + return x->inner_mode_iaf; +} + struct xfrm_tmpl { /* id in template is interpreted as: @@ -1253,6 +1275,7 @@ extern int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, extern int xfrm_input_resume(struct sk_buff *skb, int nexthdr); extern int xfrm_output_resume(struct sk_buff *skb, int err); extern int xfrm_output(struct sk_buff *skb); +extern int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_extract_header(struct sk_buff *skb); extern int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 8dee617ee90..584e6d74e3a 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -41,7 +41,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; - top_iph->protocol = x->inner_mode->afinfo->proto; + top_iph->protocol = xfrm_af2proto(skb->dst->ops->family); /* DS disclosed */ top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d5a58a81802..8c3180adddb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -56,7 +56,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - err = x->inner_mode->afinfo->extract_output(x, skb); + err = xfrm_inner_extract_output(x, skb); if (err) return err; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 0c742faaa30..e20529b4c82 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -45,7 +45,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) 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; + top_iph->nexthdr = xfrm_af2proto(skb->dst->ops->family); dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, dsfield); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 79ccfb08073..0af823cf7f1 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -62,7 +62,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - err = x->inner_mode->afinfo->extract_output(x, skb); + err = xfrm_inner_extract_output(x, skb); if (err) return err; diff --git a/net/key/af_key.c b/net/key/af_key.c index 8b5f486ac80..e9ef9af4a53 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1219,7 +1219,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr, x->sel.prefixlen_s = addr->sadb_address_prefixlen; } - if (!x->sel.family) + if (x->props.mode == XFRM_MODE_TRANSPORT) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 62188c6a06d..75279402ccf 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -84,14 +84,21 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_mode *inner_mode = x->inner_mode; int err; err = x->outer_mode->afinfo->extract_input(x, skb); if (err) return err; - skb->protocol = x->inner_mode->afinfo->eth_proto; - return x->inner_mode->input2(x, skb); + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) + return -EAFNOSUPPORT; + } + + skb->protocol = inner_mode->afinfo->eth_proto; + return inner_mode->input2(x, skb); } EXPORT_SYMBOL(xfrm_prepare_input); @@ -101,6 +108,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) __be32 seq; struct xfrm_state *x; xfrm_address_t *daddr; + struct xfrm_mode *inner_mode; unsigned int family; int decaps = 0; int async = 0; @@ -207,7 +215,15 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - if (x->inner_mode->input(x, skb)) { + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) + goto drop; + } + + if (inner_mode->input(x, skb)) { XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 569d377932c..2519129c6d2 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -124,7 +124,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) if (!x) return dst_output(skb); - err = nf_hook(x->inner_mode->afinfo->family, + err = nf_hook(skb->dst->ops->family, NF_INET_POST_ROUTING, skb, NULL, skb->dst->dev, xfrm_output2); if (unlikely(err != 1)) @@ -193,4 +193,20 @@ int xfrm_output(struct sk_buff *skb) return xfrm_output2(skb); } + +int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct xfrm_mode *inner_mode; + if (x->sel.family == AF_UNSPEC) + inner_mode = xfrm_ip2inner_mode(x, + xfrm_af2proto(skb->dst->ops->family)); + else + inner_mode = x->inner_mode; + + if (inner_mode == NULL) + return -EAFNOSUPPORT; + return inner_mode->afinfo->extract_output(x, skb); +} + EXPORT_SYMBOL_GPL(xfrm_output); +EXPORT_SYMBOL_GPL(xfrm_inner_extract_output); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 7ba65e82941..58f1f9347b5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -388,6 +388,8 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->coaddr); if (x->inner_mode) xfrm_put_mode(x->inner_mode); + if (x->inner_mode_iaf) + xfrm_put_mode(x->inner_mode_iaf); if (x->outer_mode) xfrm_put_mode(x->outer_mode); if (x->type) { @@ -523,6 +525,8 @@ struct xfrm_state *xfrm_state_alloc(void) x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; + x->inner_mode = NULL; + x->inner_mode_iaf = NULL; spin_lock_init(&x->lock); } return x; @@ -796,7 +800,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, selector. */ if (x->km.state == XFRM_STATE_VALID) { - if (!xfrm_selector_match(&x->sel, fl, x->sel.family) || + if ((x->sel.family && !xfrm_selector_match(&x->sel, fl, x->sel.family)) || !security_xfrm_state_pol_flow_match(x, pol, fl)) continue; if (!best || @@ -1944,6 +1948,7 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu) int xfrm_init_state(struct xfrm_state *x) { struct xfrm_state_afinfo *afinfo; + struct xfrm_mode *inner_mode; int family = x->props.family; int err; @@ -1962,13 +1967,48 @@ int xfrm_init_state(struct xfrm_state *x) goto error; err = -EPROTONOSUPPORT; - x->inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); - if (x->inner_mode == NULL) - goto error; - if (!(x->inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && - family != x->sel.family) - goto error; + if (x->sel.family != AF_UNSPEC) { + inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); + if (inner_mode == NULL) + goto error; + + if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && + family != x->sel.family) { + xfrm_put_mode(inner_mode); + goto error; + } + + x->inner_mode = inner_mode; + } else { + struct xfrm_mode *inner_mode_iaf; + + inner_mode = xfrm_get_mode(x->props.mode, AF_INET); + if (inner_mode == NULL) + goto error; + + if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) { + xfrm_put_mode(inner_mode); + goto error; + } + + inner_mode_iaf = xfrm_get_mode(x->props.mode, AF_INET6); + if (inner_mode_iaf == NULL) + goto error; + + if (!(inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)) { + xfrm_put_mode(inner_mode_iaf); + goto error; + } + + if (x->props.family == AF_INET) { + x->inner_mode = inner_mode; + x->inner_mode_iaf = inner_mode_iaf; + } else { + x->inner_mode = inner_mode_iaf; + x->inner_mode_iaf = inner_mode; + } + } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f971ca5645f..5d96f2728dc 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -288,12 +288,9 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); x->props.flags = p->flags; - /* - * Set inner address family if the KM left it as zero. - * See comment in validate_tmpl. - */ - if (!x->sel.family) + if (x->props.mode == XFRM_MODE_TRANSPORT) x->sel.family = p->family; + } /* -- cgit v1.2.3-70-g09d2 From 732c8bd590625e8bc0b88313b82930e336b2bec4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 26 Mar 2008 16:51:09 -0700 Subject: [IPSEC]: Fix BEET output The IPv6 BEET output function is incorrectly including the inner header in the payload to be protected. This causes a crash as the packet doesn't actually have that many bytes for a second header. The IPv4 BEET output on the other hand is broken when it comes to handling an inner IPv6 header since it always assumes an inner IPv4 header. This patch fixes both by making sure that neither BEET output function touches the inner header at all. All access is now done through the protocol-independent cb structure. Two new attributes are added to make this work, the IP header length and the IPv4 option length. They're filled in by the inner mode's output function. Thanks to Joakim Koskela for finding this problem. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/xfrm.h | 6 ++++++ net/ipv4/xfrm4_mode_beet.c | 11 +++++------ net/ipv4/xfrm4_state.c | 2 ++ net/ipv6/xfrm6_mode_beet.c | 1 + net/ipv6/xfrm6_state.c | 2 ++ 5 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4e6f9568cbe..0d255ae008b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -552,6 +552,9 @@ struct xfrm_mode_skb_cb { __be16 id; __be16 frag_off; + /* IP header length (excluding options or extension headers). */ + u8 ihl; + /* TOS for IPv4, class for IPv6. */ u8 tos; @@ -561,6 +564,9 @@ struct xfrm_mode_skb_cb { /* Protocol for IPv4, NH for IPv6. */ u8 protocol; + /* Option length for IPv4, zero for IPv6. */ + u8 optlen; + /* Used by IPv6 only, zero for IPv4. */ u8 flow_lbl[3]; }; diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index b47030ba162..9c798abce73 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -39,13 +39,11 @@ static void xfrm4_beet_make_header(struct sk_buff *skb) static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) { struct ip_beet_phdr *ph; - struct iphdr *iph, *top_iph; + struct iphdr *top_iph; int hdrlen, optlen; - iph = ip_hdr(skb); - hdrlen = 0; - optlen = iph->ihl * 4 - sizeof(*iph); + optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); @@ -53,11 +51,12 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) hdrlen); 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); xfrm4_beet_make_header(skb); - ph = (struct ip_beet_phdr *)__skb_pull(skb, sizeof(*iph) - hdrlen); + ph = (struct ip_beet_phdr *) + __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index fdeebe68a37..07735ed280d 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -52,10 +52,12 @@ int xfrm4_extract_header(struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); 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)->optlen = iph->ihl * 4 - sizeof(*iph); memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0, sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 0527d11c1ae..d6ce400f585 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -45,6 +45,7 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); + __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index dc817e035e2..ff1e1db8e23 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -174,10 +174,12 @@ int xfrm6_extract_header(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); 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)->optlen = 0; memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl, sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); -- cgit v1.2.3-70-g09d2