* ipvs: Use frag walker helper in SCTP proto support.
From: David Miller @ 2010-10-04 6:46 UTC (permalink / raw)
To: horms; +Cc: netdev, netfilter-devel
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/netfilter/ipvs/ip_vs_proto_sctp.c | 19 ++++++++++---------
1 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 4c0855c..2f982a4 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -61,6 +61,7 @@ sctp_snat_handler(struct sk_buff *skb,
{
sctp_sctphdr_t *sctph;
unsigned int sctphoff;
+ struct sk_buff *iter;
__be32 crc32;
#ifdef CONFIG_IP_VS_IPV6
@@ -89,8 +90,8 @@ sctp_snat_handler(struct sk_buff *skb,
/* Calculate the checksum */
crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next)
- crc32 = sctp_update_cksum((u8 *) skb->data, skb_headlen(skb),
+ skb_walk_frags(skb, iter)
+ crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
crc32);
crc32 = sctp_end_cksum(crc32);
sctph->checksum = crc32;
@@ -102,9 +103,9 @@ static int
sctp_dnat_handler(struct sk_buff *skb,
struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
{
-
sctp_sctphdr_t *sctph;
unsigned int sctphoff;
+ struct sk_buff *iter;
__be32 crc32;
#ifdef CONFIG_IP_VS_IPV6
@@ -133,8 +134,8 @@ sctp_dnat_handler(struct sk_buff *skb,
/* Calculate the checksum */
crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next)
- crc32 = sctp_update_cksum((u8 *) skb->data, skb_headlen(skb),
+ skb_walk_frags(skb, iter)
+ crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
crc32);
crc32 = sctp_end_cksum(crc32);
sctph->checksum = crc32;
@@ -145,9 +146,9 @@ sctp_dnat_handler(struct sk_buff *skb,
static int
sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
{
- struct sk_buff *list = skb_shinfo(skb)->frag_list;
unsigned int sctphoff;
struct sctphdr *sh, _sctph;
+ struct sk_buff *iter;
__le32 cmp;
__le32 val;
__u32 tmp;
@@ -166,9 +167,9 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
cmp = sh->checksum;
tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb));
- for (; list; list = list->next)
- tmp = sctp_update_cksum((__u8 *) list->data,
- skb_headlen(list), tmp);
+ skb_walk_frags(skb, iter)
+ tmp = sctp_update_cksum((__u8 *) iter->data,
+ skb_headlen(iter), tmp);
val = sctp_end_cksum(tmp);
--
1.7.3.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 5/5] XFRM,IPv6: Add IRO remapping capability via socket ancillary data path
From: Arnaud Ebalard @ 2010-10-04 6:25 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
In-Reply-To: <cover.1286139128.git.arno@natisbad.org>
This provides the ability to remap src/dst address using IRO
via ancillary data passed to sockets. This is the IRO equivalent
of what is done for RH2/HAO (i.e. IPV6_RTHDR/IPV6_DSTOPTS).
This is used by UMIP during BA emission when acting as a Home
Agent.
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
---
include/net/ipv6.h | 4 ++++
net/ipv6/datagram.c | 20 ++++++++++++++++++++
net/ipv6/exthdrs.c | 19 +++++++++++++------
net/ipv6/ip6_flowlabel.c | 7 +++++++
net/ipv6/ip6_output.c | 22 ++++++++++++++++++++++
net/ipv6/raw.c | 3 ++-
6 files changed, 68 insertions(+), 7 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4a3cd2c..2ba96d8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -188,6 +188,10 @@ struct ipv6_txoptions {
struct ipv6_rt_hdr *srcrt; /* Routing Header */
struct ipv6_opt_hdr *dst1opt;
+ /* XXX protect those via some ifdef e.g. CONFIG_XFRM_SUB_POLICY ? */
+ struct in6_addr *iro_src;
+ struct in6_addr *iro_dst;
+
/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
};
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2952c9e..0ac7adf 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -757,6 +757,26 @@ int datagram_send_ctl(struct net *net,
}
break;
+#ifdef CONFIG_XFRM_SUB_POLICY
+ case IPV6_IROSRC:
+ case IPV6_IRODST:
+ if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_addr))) {
+ err = -EINVAL;
+ goto exit_f;
+ }
+
+ if (!capable(CAP_NET_RAW)) {
+ err = -EPERM;
+ goto exit_f;
+ }
+
+ if (cmsg->cmsg_type == IPV6_IROSRC)
+ opt->iro_src = (struct in6_addr *)CMSG_DATA(cmsg);
+ else
+ opt->iro_dst = (struct in6_addr *)CMSG_DATA(cmsg);
+ break;
+#endif
+
case IPV6_2292RTHDR:
case IPV6_RTHDR:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 262f105..e480b06 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -750,6 +750,10 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
*((char**)&opt2->dst1opt) += dif;
if (opt2->srcrt)
*((char**)&opt2->srcrt) += dif;
+ if (opt2->iro_src)
+ *((char**)&opt2->iro_src) += dif;
+ if (opt2->iro_dst)
+ *((char**)&opt2->iro_dst) += dif;
}
return opt2;
}
@@ -874,24 +878,27 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
/**
* fl6_update_dst - update flowi destination address with info given
- * by srcrt option, if any.
+ * by srcrt/iro_dst option, if any.
*
* @fl: flowi for which fl6_dst is to be updated
- * @opt: struct ipv6_txoptions in which to look for srcrt opt
+ * @opt: struct ipv6_txoptions in which to look for srcrt/iro_dst opt
* @orig: copy of original fl6_dst address if modified
*
- * Returns NULL if no txoptions or no srcrt, otherwise returns orig
- * and initial value of fl->fl6_dst set in orig
+ * Returns NULL if no txoptions or no options to change flowi destination
+ * (srcrt or IRO destination remapping rule), otherwise returns orig and
+ * initial value of fl->fl6_dst set in orig
*/
struct in6_addr *fl6_update_dst(struct flowi *fl,
const struct ipv6_txoptions *opt,
struct in6_addr *orig)
{
- if (!opt || !opt->srcrt)
+ if (!opt || (!opt->srcrt && !opt->iro_dst))
return NULL;
ipv6_addr_copy(orig, &fl->fl6_dst);
- ipv6_addr_copy(&fl->fl6_dst, ((struct rt0_hdr *)opt->srcrt)->addr);
+ ipv6_addr_copy(&fl->fl6_dst,
+ opt->iro_dst ?: ((struct rt0_hdr *)opt->srcrt)->addr);
+
return orig;
}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1365468..dbf9c29 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -280,6 +280,9 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
opt_space->hopopt = fl_opt->hopopt;
opt_space->dst0opt = fl_opt->dst0opt;
opt_space->srcrt = fl_opt->srcrt;
+ /* XXX protect those via some ifdef - see net/ipv6.h */
+ opt_space->iro_src = fl_opt->iro_src;
+ opt_space->iro_dst = fl_opt->iro_dst;
opt_space->opt_nflen = fl_opt->opt_nflen;
} else {
if (fopt->opt_nflen == 0)
@@ -287,6 +290,9 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
opt_space->hopopt = NULL;
opt_space->dst0opt = NULL;
opt_space->srcrt = NULL;
+ /* XXX protect those via some ifdef - see net/ipv6.h */
+ opt_space->iro_src = NULL;
+ opt_space->iro_dst = NULL;
opt_space->opt_nflen = 0;
}
opt_space->dst1opt = fopt->dst1opt;
@@ -456,6 +462,7 @@ static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2)
return 1;
if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt))
return 1;
+
return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 99157b4..210f269 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -222,6 +222,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
+ if (opt->iro_dst)
+ first_hop = opt->iro_dst;
}
skb_push(skb, sizeof(struct ipv6hdr));
@@ -1106,6 +1108,12 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}
+static inline struct in6_addr *ip6_iro_addr_dup(struct in6_addr *addr,
+ gfp_t gfp)
+{
+ return addr ? kmemdup(addr, sizeof(struct in6_addr), gfp) : NULL;
+}
+
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
@@ -1162,6 +1170,16 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
+ np->cork.opt->iro_src = ip6_iro_addr_dup(opt->iro_src,
+ sk->sk_allocation);
+ if (opt->iro_src && !np->cork.opt->iro_src)
+ return -ENOBUFS;
+
+ np->cork.opt->iro_dst = ip6_iro_addr_dup(opt->iro_dst,
+ sk->sk_allocation);
+ if (opt->iro_dst && !np->cork.opt->iro_dst)
+ return -ENOBUFS;
+
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
@@ -1440,6 +1458,8 @@ static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
kfree(np->cork.opt->dst1opt);
kfree(np->cork.opt->hopopt);
kfree(np->cork.opt->srcrt);
+ kfree(np->cork.opt->iro_src);
+ kfree(np->cork.opt->iro_dst);
kfree(np->cork.opt);
np->cork.opt = NULL;
}
@@ -1495,6 +1515,8 @@ int ip6_push_pending_frames(struct sock *sk)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
+ if (opt && opt->iro_dst)
+ final_dst = opt->iro_dst;
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 45e6efb..1a11bd5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -828,7 +828,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (flowlabel == NULL)
return -EINVAL;
}
- if (!(opt->opt_nflen|opt->opt_flen))
+ if (!(opt->opt_nflen|opt->opt_flen) &&
+ (!opt->iro_src && !opt->iro_dst))
opt = NULL;
}
if (opt == NULL)
--
1.7.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 4/5] XFRM,IPv6: Add IRO remapping hook in xfrm_input()
From: Arnaud Ebalard @ 2010-10-04 6:25 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
In-Reply-To: <cover.1286139128.git.arno@natisbad.org>
Add a hook in xfrm_input() to allow IRO remapping to occur when
an incoming packet matching an existing SA (based on SPI) with
an unexpected destination or source address is received.
Because IRO does not consume additional bits in a packet (that's
the point), there is no way to demultiplex based on something
like nh or spi. Instead, IRO input handlers (for source and
destination address remapping) are called upon address mismatch
during IPsec processing.
For that to work, we rely on the fact that SPI values generated
locally are no more linked to destination address (first patch
of the set) and we postpone a bit the expected address check in
xfrm_input() (inside xfrm_state_lookup() against daddr param) by
introducing a call to the input_addr_check() handler from the
struct xfrm_state_afinfo associated with the address family.
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
---
include/net/xfrm.h | 5 +++
net/ipv4/xfrm4_input.c | 11 +++++++
net/ipv4/xfrm4_state.c | 1 +
net/ipv6/xfrm6_input.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++-
net/ipv6/xfrm6_state.c | 1 +
net/xfrm/xfrm_input.c | 5 ++-
net/xfrm/xfrm_state.c | 2 +-
7 files changed, 90 insertions(+), 4 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 05b2b1f..5b84c19 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -312,6 +312,8 @@ struct xfrm_state_afinfo {
struct sk_buff *skb);
int (*transport_finish)(struct sk_buff *skb,
int async);
+ int (*input_addr_check)(struct sk_buff *skb,
+ struct xfrm_state *x);
};
extern int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
@@ -623,6 +625,7 @@ struct xfrm_spi_skb_cb {
struct inet6_skb_parm h6;
} header;
+ unsigned int saddroff;
unsigned int daddroff;
unsigned int family;
};
@@ -1405,6 +1408,7 @@ extern int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type);
extern int xfrm4_transport_finish(struct sk_buff *skb, int async);
extern int xfrm4_rcv(struct sk_buff *skb);
+extern int xfrm4_input_addr_check(struct sk_buff *skb, struct xfrm_state *x);
static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
{
@@ -1423,6 +1427,7 @@ extern int xfrm6_transport_finish(struct sk_buff *skb, int async);
extern int xfrm6_rcv(struct sk_buff *skb);
extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto);
+extern int xfrm6_input_addr_check(struct sk_buff *skb, struct xfrm_state *x);
extern int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
extern __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 06814b6..8d414ca 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -41,6 +41,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->saddroff = offsetof(struct iphdr, saddr);
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
@@ -164,3 +165,13 @@ int xfrm4_rcv(struct sk_buff *skb)
return xfrm4_rcv_spi(skb, ip_hdr(skb)->protocol, 0);
}
EXPORT_SYMBOL(xfrm4_rcv);
+
+int xfrm4_input_addr_check(struct sk_buff *skb, struct xfrm_state *x)
+{
+ xfrm_address_t *daddr;
+
+ daddr = (xfrm_address_t *)(skb_network_header(skb) +
+ XFRM_SPI_SKB_CB(skb)->daddroff);
+
+ return xfrm_addr_cmp(&x->id.daddr, daddr, AF_INET);
+}
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 4794762..c6b038a 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -79,6 +79,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
.extract_input = xfrm4_extract_input,
.extract_output = xfrm4_extract_output,
.transport_finish = xfrm4_transport_finish,
+ .input_addr_check = xfrm4_input_addr_check,
};
void __init xfrm4_state_init(void)
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index f8c3cf8..aeb7fc6 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -15,6 +15,7 @@
#include <linux/netfilter_ipv6.h>
#include <net/ipv6.h>
#include <net/xfrm.h>
+#include <net/ip6_route.h> /* XXX for ip6_route_input() */
int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb)
{
@@ -24,6 +25,7 @@ int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb)
int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
+ XFRM_SPI_SKB_CB(skb)->saddroff = offsetof(struct ipv6hdr, saddr);
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
return xfrm_input(skb, nexthdr, spi, 0);
}
@@ -142,5 +144,70 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
drop:
return -1;
}
-
EXPORT_SYMBOL(xfrm6_input_addr);
+
+#if defined(CONFIG_XFRM_SUB_POLICY)
+/* Perform check on source and destination addresses and possibly IRO
+ * address remapping upon mismatch and if matching IRO state exists. */
+int xfrm6_input_addr_check(struct sk_buff *skb, struct xfrm_state *x)
+{
+ xfrm_address_t *saddr, *exp_saddr, *daddr, *exp_daddr;
+
+ saddr = (xfrm_address_t *)(skb_network_header(skb) +
+ XFRM_SPI_SKB_CB(skb)->saddroff);
+ daddr = (xfrm_address_t *)(skb_network_header(skb) +
+ XFRM_SPI_SKB_CB(skb)->daddroff);
+
+ exp_daddr = &x->id.daddr;
+ if (xfrm_addr_cmp(exp_daddr, daddr, AF_INET6)) {
+ /* Destination address mismatch: check if we have an IRO
+ * destination remapping state to explain that.
+ *
+ * Note: saddr is provided as a hint. If source address
+ * is also a remapped one, xfrm6_input_addr() will manage
+ * to find IRO destination remapping state */
+ if (xfrm6_input_addr(skb, exp_daddr, saddr,
+ XFRM_PROTO_IRO_DST) < 0)
+ return -1;
+
+ /* Copy destination address to sec_path for sock opts and
+ * replace packet destination address with expected HoA */
+ ipv6_addr_copy(&skb->sp->irodst, (struct in6_addr *)daddr);
+ ipv6_addr_copy((struct in6_addr *)daddr,
+ (struct in6_addr *)exp_daddr);
+
+ skb_dst_drop(skb);
+ ip6_route_input(skb);
+ if (skb_dst(skb)->error)
+ return -1;
+ }
+
+ exp_saddr = &x->props.saddr;
+ if (xfrm_addr_cmp(exp_saddr, saddr, AF_INET6)) {
+ /* Source address mismatch: check if we have an IRO
+ * source remapping state to explain that.
+ *
+ * Note: unlike for destination addresses above, a
+ * source mismatch is not considered fatal */
+ if (xfrm6_input_addr(skb, daddr, exp_saddr,
+ XFRM_PROTO_IRO_SRC) < 0)
+ return 0;
+
+ /* Copy destination address to sec_path for sock opts and
+ * then replace source address with expected peer's HoA */
+ ipv6_addr_copy(&skb->sp->irosrc, (struct in6_addr *)saddr);
+ ipv6_addr_copy((struct in6_addr *)saddr,
+ (struct in6_addr *)exp_saddr);
+ }
+
+ return 0;
+}
+#else
+int xfrm6_input_addr_check(struct sk_buff *skb, struct xfrm_state *x)
+{
+ xfrm_address_t *daddr;
+ daddr = (xfrm_address_t *)(skb_network_header(skb) +
+ XFRM_SPI_SKB_CB(skb)->daddroff);
+ return xfrm_addr_cmp(&x->id.daddr, daddr, AF_INET6);
+}
+#endif
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index a67575d..aeb4688 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -179,6 +179,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
.extract_input = xfrm6_extract_input,
.extract_output = xfrm6_extract_output,
.transport_finish = xfrm6_transport_finish,
+ .input_addr_check = xfrm6_input_addr_check,
};
int __init xfrm6_state_init(void)
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 45f1c98..9ff65f6 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -152,8 +152,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
goto drop;
}
- x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
- if (x == NULL) {
+ x = xfrm_state_lookup(net, skb->mark, NULL, spi, nexthdr, family);
+ if (x == NULL ||
+ x->outer_mode->afinfo->input_addr_check(skb, x)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
goto drop;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b6a4d8d..b8f7c08 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -685,7 +685,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_ad
if (x->props.family != family ||
x->id.spi != spi ||
x->id.proto != proto ||
- xfrm_addr_cmp(&x->id.daddr, daddr, family))
+ (daddr && xfrm_addr_cmp(&x->id.daddr, daddr, family)))
continue;
if ((mark & x->mark.m) != x->mark.v)
--
1.7.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 3/5] XFRM,IPv6: Add IRO src/dst address remapping XFRM types and i/o handlers
From: Arnaud Ebalard @ 2010-10-04 6:25 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
In-Reply-To: <cover.1286139128.git.arno@natisbad.org>
Add IRO source and destination remapping XFRM types and associated
input/output handlers. This allows userland to install such states
in order to support remapping of source or destination address
of packet. They basically work like existing RH2 and HAO ones; the
main difference is that output handlers do not expand the packet by
adding an extension header: they simply change the source or
destination in place. Input handlers are almost the same as RH2/HAO
version in their behavior, but they are triggered differently. RH2
and HAO handlers are triggered based on structures found in the
packet. On input, IRO states (and associated handlers) are looked
up when processing an IPsec-protected packet, when there is an
address mismatch.
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
---
include/net/xfrm.h | 2 +
net/ipv6/mip6.c | 181 ++++++++++++++++++++++++++++++++++++++++------
net/ipv6/xfrm6_mode_ro.c | 11 +++-
net/xfrm/xfrm_user.c | 4 +
4 files changed, 176 insertions(+), 22 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index e6a753c..05b2b1f 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -35,6 +35,8 @@
#define XFRM_PROTO_IPV6 41
#define XFRM_PROTO_ROUTING IPPROTO_ROUTING
#define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS
+#define XFRM_PROTO_IRO_SRC 127
+#define XFRM_PROTO_IRO_DST 128
#define XFRM_ALIGN8(len) (((len) + 7) & ~7)
#define MODULE_ALIAS_XFRM_MODE(family, encap) \
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index d6e9599..9685599 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -302,18 +302,26 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
return offset;
}
-static int mip6_destopt_init_state(struct xfrm_state *x)
+/* Helper performing basic sanity checks on given mip6 state
+ * during state's initialization process */
+static int mip6_state_init_sanity_check(struct xfrm_state *x)
{
if (x->id.spi) {
- printk(KERN_INFO "%s: spi is not 0: %u\n", __func__,
- x->id.spi);
+ pr_info("%s: SPI is not 0 but %u\n", __func__, x->id.spi);
return -EINVAL;
}
if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) {
- printk(KERN_INFO "%s: state's mode is not %u: %u\n",
- __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode);
+ pr_info("%s: state's mode is not RO (%u) but %u\n", __func__,
+ XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode);
return -EINVAL;
}
+ return 0;
+}
+
+static int mip6_destopt_init_state(struct xfrm_state *x)
+{
+ if (mip6_state_init_sanity_check(x))
+ return -EINVAL;
x->props.header_len = sizeof(struct ipv6_destopt_hdr) +
calc_padlen(sizeof(struct ipv6_destopt_hdr), 6) +
@@ -440,16 +448,8 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb,
static int mip6_rthdr_init_state(struct xfrm_state *x)
{
- if (x->id.spi) {
- printk(KERN_INFO "%s: spi is not 0: %u\n", __func__,
- x->id.spi);
- return -EINVAL;
- }
- if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) {
- printk(KERN_INFO "%s: state's mode is not %u: %u\n",
- __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode);
+ if (mip6_state_init_sanity_check(x))
return -EINVAL;
- }
x->props.header_len = sizeof(struct rt2_hdr);
@@ -477,20 +477,145 @@ static const struct xfrm_type mip6_rthdr_type =
.hdr_offset = mip6_rthdr_offset,
};
+#ifdef CONFIG_XFRM_SUB_POLICY
+/* IRO equivalent of mip6_destopt_input(): handles incoming packet with a
+ * source address different from the one expected in the SA: check that
+ * received source address is indeed the CoA we expected (or any address
+ * if the state references the unspecified address '::') */
+static int mip6_iro_src_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ int err = 1;
+
+ spin_lock(&x->lock);
+ if (!ipv6_addr_equal(&iph->saddr, (struct in6_addr *)x->coaddr) &&
+ !ipv6_addr_any((struct in6_addr *)x->coaddr))
+ err = -ENOENT;
+ spin_unlock(&x->lock);
+
+ return err;
+}
+
+/* IRO equivalent of mip6_destopt_output(): replaces current source address
+ * of outgoing packet by state's CoA. */
+static int mip6_iro_src_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ spin_lock_bh(&x->lock);
+ memcpy(&iph->saddr, x->coaddr, sizeof(iph->saddr));
+ spin_unlock_bh(&x->lock);
+
+ return 0;
+}
+
+static int mip6_iro_src_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl)
+{
+ /* XXX We may need some reject handler at some point but it is not
+ * critical yet: see xfrm_secpath_reject() in net/xfrm/xfrm_policy.c
+ * and aslo what mip6_destopt_reject() implements */
+
+ pr_debug("%s: not implemented yet.\n", __func__);
+
+ return 0;
+}
+
+/* This is the IRO equivalent of mip6_rthdr_input(): handles incoming packet
+ * with a destination address different from the one expected in the SA:
+ * check that received destination address is indeed the CoA we expected
+ * (or any address if the state references the unspecified address '::') */
+static int mip6_iro_dst_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ int err = 1;
+
+ spin_lock(&x->lock);
+ if (!ipv6_addr_equal(&iph->daddr, (struct in6_addr *)x->coaddr) &&
+ !ipv6_addr_any((struct in6_addr *)x->coaddr))
+ err = -ENOENT;
+ spin_unlock(&x->lock);
+
+ return err;
+}
+
+/* IRO equivalent of mip6_rthdr_output(): replaces current destination
+ * address of outgoing packet with state's CoA */
+static int mip6_iro_dst_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ spin_lock_bh(&x->lock);
+ memcpy(&iph->daddr, x->coaddr, sizeof(iph->daddr));
+ spin_unlock_bh(&x->lock);
+
+ return 0;
+}
+
+/* Common to iro src and dst remapping states. */
+static int mip6_iro_init_state(struct xfrm_state *x)
+{
+ return mip6_state_init_sanity_check(x);
+}
+
+/* Unlike common IPsec protocols, nothing to do when destroying */
+static void mip6_iro_destroy(struct xfrm_state *x)
+{
+}
+
+static const struct xfrm_type mip6_iro_src_type =
+{
+ .description = "MIP6_IRO_SRC",
+ .owner = THIS_MODULE,
+ .proto = XFRM_PROTO_IRO_SRC,
+ .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR,
+ .init_state = mip6_iro_init_state,
+ .destructor = mip6_iro_destroy,
+ .input = mip6_iro_src_input,
+ .output = mip6_iro_src_output,
+ .reject = mip6_iro_src_reject,
+};
+
+static const struct xfrm_type mip6_iro_dst_type =
+{
+ .description = "MIP6_IRO_DST",
+ .owner = THIS_MODULE,
+ .proto = XFRM_PROTO_IRO_DST,
+ .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR,
+ .init_state = mip6_iro_init_state,
+ .destructor = mip6_iro_destroy,
+ .input = mip6_iro_dst_input,
+ .output = mip6_iro_dst_output,
+};
+#endif /* CONFIG_XFRM_SUB_POLICY */
+
static int __init mip6_init(void)
{
- printk(KERN_INFO "Mobile IPv6\n");
+ pr_info("Mobile IPv6\n");
if (xfrm_register_type(&mip6_destopt_type, AF_INET6) < 0) {
- printk(KERN_INFO "%s: can't add xfrm type(destopt)\n", __func__);
+ pr_info("%s: can't add xfrm type(destopt)\n", __func__);
goto mip6_destopt_xfrm_fail;
}
if (xfrm_register_type(&mip6_rthdr_type, AF_INET6) < 0) {
- printk(KERN_INFO "%s: can't add xfrm type(rthdr)\n", __func__);
+ pr_info("%s: can't add xfrm type(rthdr)\n", __func__);
goto mip6_rthdr_xfrm_fail;
}
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+ if (xfrm_register_type(&mip6_iro_src_type, AF_INET6) < 0) {
+ pr_info("%s: can't add xfrm type(IRO src remap)\n",
+ __func__);
+ goto mip6_iro_src_remap_xfrm_fail;
+ }
+ if (xfrm_register_type(&mip6_iro_dst_type, AF_INET6) < 0) {
+ pr_info("%s: can't add xfrm type(IRO dst remap)\n",
+ __func__);
+ goto mip6_iro_dst_remap_xfrm_fail;
+ }
+#endif
+
if (rawv6_mh_filter_register(mip6_mh_filter) < 0) {
- printk(KERN_INFO "%s: can't add rawv6 mh filter\n", __func__);
+ pr_info("%s: can't add rawv6 mh filter\n", __func__);
goto mip6_rawv6_mh_fail;
}
@@ -498,6 +623,12 @@ static int __init mip6_init(void)
return 0;
mip6_rawv6_mh_fail:
+#ifdef CONFIG_XFRM_SUB_POLICY
+ xfrm_unregister_type(&mip6_iro_dst_type, AF_INET6);
+ mip6_iro_dst_remap_xfrm_fail:
+ xfrm_unregister_type(&mip6_iro_src_type, AF_INET6);
+ mip6_iro_src_remap_xfrm_fail:
+#endif
xfrm_unregister_type(&mip6_rthdr_type, AF_INET6);
mip6_rthdr_xfrm_fail:
xfrm_unregister_type(&mip6_destopt_type, AF_INET6);
@@ -508,11 +639,19 @@ static int __init mip6_init(void)
static void __exit mip6_fini(void)
{
if (rawv6_mh_filter_unregister(mip6_mh_filter) < 0)
- printk(KERN_INFO "%s: can't remove rawv6 mh filter\n", __func__);
+ pr_info("%s: can't remove rawv6 mh filter\n", __func__);
+#ifdef CONFIG_XFRM_SUB_POLICY
+ if (xfrm_unregister_type(&mip6_iro_dst_type, AF_INET6) < 0)
+ pr_info("%s: can't remove xfrm type(IRO dst remap)\n",
+ __func__);
+ if (xfrm_unregister_type(&mip6_iro_src_type, AF_INET6) < 0)
+ pr_info("%s: can't remove xfrm type(IRO src remap)\n",
+ __func__);
+#endif
if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0)
- printk(KERN_INFO "%s: can't remove xfrm type(rthdr)\n", __func__);
+ pr_info("%s: can't remove xfrm type(rthdr)\n", __func__);
if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0)
- printk(KERN_INFO "%s: can't remove xfrm type(destopt)\n", __func__);
+ pr_info("%s: can't remove xfrm type(destopt)\n", __func__);
}
module_init(mip6_init);
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index 63d5d49..ea33178 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -45,6 +45,15 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
u8 *prevhdr;
int hdr_len;
+ /* Unlike RH2 (IPPROTO_ROUTING) and HAO in DstOpt
+ * (IPPROTO_DSTOPTS), IRO remapping states do not
+ * add extension header to the packet. Source
+ * and/or destination addresses are simply modified
+ * in place. */
+ if (x->id.proto == XFRM_PROTO_IRO_SRC ||
+ x->id.proto == XFRM_PROTO_IRO_DST)
+ goto out;
+
iph = ipv6_hdr(skb);
hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
@@ -54,8 +63,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
__skb_pull(skb, hdr_len);
memmove(ipv6_hdr(skb), iph, hdr_len);
+ out:
x->lastused = get_seconds();
-
return 0;
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 8bae6b2..2aecd40 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -179,6 +179,10 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
case IPPROTO_DSTOPTS:
case IPPROTO_ROUTING:
+#ifdef CONFIG_XFRM_SUB_POLICY
+ case XFRM_PROTO_IRO_SRC:
+ case XFRM_PROTO_IRO_DST:
+#endif
if (attrs[XFRMA_ALG_COMP] ||
attrs[XFRMA_ALG_AUTH] ||
attrs[XFRMA_ALG_AUTH_TRUNC] ||
--
1.7.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 2/5] XFRM,IPv6: Introduce receive sockopts to access IRO remapped src/dst addresses
From: Arnaud Ebalard @ 2010-10-04 6:25 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
In-Reply-To: <cover.1286139128.git.arno@natisbad.org>
This patch introduces IRO recv sockopts, in order for userland processes
(e.g. UMIP) to access on-wire source or destination addresses found in
incoming (IPsec-protected) packets as they were before remapping by IRO.
The socket options are respectively IPV6_RECVIROSRC and IPV6_RECVIRODST.
Basically, the two recv socket options are similar in their purpose to
their generic RH2/HAO counterparts defined in RFC 3542 (IPV6_RECVIROSRC
<-> IPV6_RECVDSTOPTS, IPV6_RECVIRODST <-> IPV6_RECVRTHDR). They differ
on the following aspects:
- IRO reporting sockopts only work on incoming IPsec-protected packets
Userspace will never get IRO remapped address report for common
(non protected) packets.
- The receiver gets the original source/desination address (IRO
remapping) from its IPsec stack.
- as IRO sockopts only deal with addresses, no specific structure is
defined, i.e. struct in6_addr is used to pass info.
As we only interact with IPsec protected packets, struct sec_path is
used to carry information (addresses) for incoming packets that have
undergone remapping process.
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
---
include/linux/in6.h | 7 +++++++
include/linux/ipv6.h | 4 +++-
include/net/xfrm.h | 5 +++++
net/ipv6/datagram.c | 18 ++++++++++++++++++
net/ipv6/ipv6_sockglue.c | 26 ++++++++++++++++++++++++++
5 files changed, 59 insertions(+), 1 deletions(-)
diff --git a/include/linux/in6.h b/include/linux/in6.h
index c4bf46f..52a98ab 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -283,4 +283,11 @@ struct in6_flowlabel_req {
* MRT6_PIM 208
* (reserved) 209
*/
+
+/* IRO (IPsec Route Optimization) sockopts */
+#define IPV6_RECVIROSRC 74
+#define IPV6_IROSRC 75
+#define IPV6_RECVIRODST 76
+#define IPV6_IRODST 77
+
#endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index e62683b..55289ee 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -341,7 +341,9 @@ struct ipv6_pinfo {
odstopts:1,
rxflow:1,
rxtclass:1,
- rxpmtu:1;
+ rxpmtu:1,
+ irosrc:1,
+ irodst:1;
} bits;
__u16 all;
} rxopt;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4f53532..e6a753c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -909,6 +909,11 @@ struct sec_path {
atomic_t refcnt;
int len;
struct xfrm_state *xvec[XFRM_MAX_DEPTH];
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+ struct in6_addr irosrc;
+ struct in6_addr irodst;
+#endif
};
static inline struct sec_path *
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index ef371aa..2952c9e 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -29,6 +29,7 @@
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/tcp_states.h>
+#include <net/xfrm.h>
#include <linux/errqueue.h>
#include <asm/uaccess.h>
@@ -504,6 +505,23 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
}
+#ifdef CONFIG_XFRM_SUB_POLICY
+ /* If access to IRO-remapped source or destination address has been
+ * requested and it has indeed been remapped, provide the on-wire
+ * address to userland */
+ if (skb_sec_path(skb)) {
+ struct sec_path *sp = skb_sec_path(skb);
+
+ if (np->rxopt.bits.irosrc && !ipv6_addr_any(&sp->irosrc))
+ put_cmsg(msg, SOL_IPV6, IPV6_IROSRC,
+ sizeof(sp->irosrc), &sp->irosrc);
+
+ if (np->rxopt.bits.irodst && !ipv6_addr_any(&sp->irodst))
+ put_cmsg(msg, SOL_IPV6, IPV6_IRODST,
+ sizeof(sp->irodst), &sp->irodst);
+ }
+#endif
+
if (opt->lastopt &&
(np->rxopt.bits.dstopts || np->rxopt.bits.srcrt)) {
/*
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a7f66bc..722a49f 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -302,6 +302,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = 0;
break;
+#ifdef CONFIG_XFRM_SUB_POLICY
+ case IPV6_RECVIROSRC:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ np->rxopt.bits.irosrc = valbool;
+ retv = 0;
+ break;
+
+ case IPV6_RECVIRODST:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ np->rxopt.bits.irodst = valbool;
+ retv = 0;
+ break;
+#endif
+
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
@@ -1056,6 +1072,16 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->rxopt.bits.dstopts;
break;
+#ifdef CONFIG_XFRM_SUB_POLICY
+ case IPV6_RECVIROSRC:
+ val = np->rxopt.bits.irosrc;
+ break;
+
+ case IPV6_RECVIRODST:
+ val = np->rxopt.bits.irodst;
+ break;
+#endif
+
case IPV6_2292DSTOPTS:
val = np->rxopt.bits.odstopts;
break;
--
1.7.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 1/5] XFRM,IPv6: Remove xfrm_spi_hash() dependency on destination address
From: Arnaud Ebalard @ 2010-10-04 6:25 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
In-Reply-To: <cover.1286139128.git.arno@natisbad.org>
In the new IPsec architecture [RFC4301], "for an SA used to carry
unicast traffic, the Security Parameters Index (SPI) by itself
suffices to specify an SA". Section 4.1 of [RFC4301] provides
additional guidance on the topic.
In the old IPsec architecture [RFC2401], a SA "is uniquely identified
by a triple consisting of a Security Parameter Index (SPI), an IP
Destination Address and a security protocol (AH or ESP) identifier".
If an IPsec stack only supports the behavior mandated by the old
IPsec architecture, SAD lookup on inbound packets require the use of
both the SPI and the destination address of the SA.
For inbound IPsec traffic, IRO remapping rules may exist on the MN to
remap the destination address (CoA) into the HoA. In that case, by
design, the address found in the destination address field of the
packet (CoA) does not match the one in the SA (HoA).
At the moment, Linux XFRM stack includes the address when computing
the hash to perform state lookup by SPI. This patch changes XFRM
state hash computation to prevent destination address to be
used. This will later allow finding states for packets w/ mangled
destination addresses.
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
---
net/xfrm/xfrm_hash.h | 21 +--------------------
net/xfrm/xfrm_state.c | 20 ++++++++------------
2 files changed, 9 insertions(+), 32 deletions(-)
diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h
index 8e69533..19eeee7 100644
--- a/net/xfrm/xfrm_hash.h
+++ b/net/xfrm/xfrm_hash.h
@@ -4,16 +4,6 @@
#include <linux/xfrm.h>
#include <linux/socket.h>
-static inline unsigned int __xfrm4_addr_hash(xfrm_address_t *addr)
-{
- return ntohl(addr->a4);
-}
-
-static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr)
-{
- return ntohl(addr->a6[2] ^ addr->a6[3]);
-}
-
static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr)
{
u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4;
@@ -60,18 +50,9 @@ static inline unsigned __xfrm_src_hash(xfrm_address_t *daddr,
}
static inline unsigned int
-__xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family,
- unsigned int hmask)
+__xfrm_spi_hash(__be32 spi, u8 proto, unsigned int hmask)
{
unsigned int h = (__force u32)spi ^ proto;
- switch (family) {
- case AF_INET:
- h ^= __xfrm4_addr_hash(daddr);
- break;
- case AF_INET6:
- h ^= __xfrm6_addr_hash(daddr);
- break;
- }
return (h ^ (h >> 10) ^ (h >> 20)) & hmask;
}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index eb96ce5..b6a4d8d 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -30,7 +30,7 @@
/* Each xfrm_state may be linked to two tables:
- 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
+ 1. Hash table by (spi,ah/esp) to find SA by SPI. (input,ctl)
2. Hash table by (daddr,family,reqid) to find what SAs exist for given
destination/tunnel endpoint. (output)
*/
@@ -67,9 +67,9 @@ static inline unsigned int xfrm_src_hash(struct net *net,
}
static inline unsigned int
-xfrm_spi_hash(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
+xfrm_spi_hash(struct net *net, __be32 spi, u8 proto)
{
- return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
+ return __xfrm_spi_hash(spi, proto, net->xfrm.state_hmask);
}
static void xfrm_hash_transfer(struct hlist_head *list,
@@ -95,9 +95,7 @@ static void xfrm_hash_transfer(struct hlist_head *list,
hlist_add_head(&x->bysrc, nsrctable+h);
if (x->id.spi) {
- h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
- x->id.proto, x->props.family,
- nhashmask);
+ h = __xfrm_spi_hash(x->id.spi, x->id.proto, nhashmask);
hlist_add_head(&x->byspi, nspitable+h);
}
}
@@ -679,7 +677,7 @@ xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl,
static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family)
{
- unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+ unsigned int h = xfrm_spi_hash(net, spi, proto);
struct xfrm_state *x;
struct hlist_node *entry;
@@ -868,7 +866,7 @@ found:
h = xfrm_src_hash(net, daddr, saddr, encap_family);
hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
if (x->id.spi) {
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
+ h = xfrm_spi_hash(net, x->id.spi, x->id.proto);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
}
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
@@ -942,9 +940,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
if (x->id.spi) {
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
- x->props.family);
-
+ h = xfrm_spi_hash(net, x->id.spi, x->id.proto);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
}
@@ -1535,7 +1531,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
}
if (x->id.spi) {
spin_lock_bh(&xfrm_state_lock);
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
+ h = xfrm_spi_hash(net, x->id.spi, x->id.proto);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
spin_unlock_bh(&xfrm_state_lock);
--
1.7.1
^ permalink raw reply related
* [PATCHv4 net-next-2.6 0/5] Removal of RH2/HAO from IPsec-protected MIPv6 traffic
From: Arnaud Ebalard @ 2010-10-04 6:24 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet, Herbert Xu, Hideaki YOSHIFUJI; +Cc: netdev
Hi,
This is version 4 of the patches. Compared to previous version:
- symbols which need not be exported are no more exported
- s/printk(KERNINFO, ...)/pr_info()/ in net/ipv6/mip6.c (my code
and existing one)
- I also refactored some initialization code for mip6 states
(by introduced mip6_state_init_sanity_check())
After the discussion with Herbert, I decided to leave input handlers
as they are at the moment until I have some additional time to dig on
it. At least, it's safe.
Regarding reject handler() (to warn user space so that a Binding Error
can be sent), it still does nothing yet.
Herbert, if you read this, can you take a quick look at patches 1/5 and
4/5 to tell if the changes are acceptable for IPsec users.
Cheers,
a+
^ permalink raw reply
* Re: [PATCH net-next] net: introduce DST_NOCACHE flag
From: David Miller @ 2010-10-04 5:18 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1285868687.2615.900.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 30 Sep 2010 19:44:47 +0200
...
> Introduce a new dst flag, DST_NOCACHE, that is set when dst was not
> inserted in route cache.
...
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cute, and applied, but it shows that we're RCU'd so much of the
surrounding infrastructure that the neighbour cache is now pretty
high on the list of things to RCU.
^ permalink raw reply
* Re: [PATCH net-next-2.6] be2net: add multiple RX queue support
From: David Miller @ 2010-10-04 5:12 UTC (permalink / raw)
To: sathya.perla; +Cc: netdev
In-Reply-To: <20101001104133.GA17206@emulex.com>
From: Sathya Perla <sathya.perla@emulex.com>
Date: Fri, 1 Oct 2010 16:11:33 +0530
> Dave, incorporated your comment to discover the num of supported MSIx vectors
> dynamically; thanks.
>
> This patch adds multiple RX queue support to be2net. There are
> upto 4 extra rx-queues per port into which TCP/UDP traffic can be hashed into.
> Some of the ethtool stats are now displayed on a per queue basis.
>
> Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Looks good, applied, thanks.
^ permalink raw reply
* Re: pull request: wireless-next-2.6 2010-10-01
From: David Miller @ 2010-10-04 5:11 UTC (permalink / raw)
To: linville-2XuSBdqkA4R54TAoqtyWWQ
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20101001161819.GD3049-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
From: "John W. Linville" <linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
Date: Fri, 1 Oct 2010 12:18:19 -0400
> Here is the latest round of wireless LAN updates intended for 2.6.37.
> Included are some ath5k bits from Bruno Randolf, some carl9170 updates
> from Christian Lamparter, some mac80211 updates from Johannes Berg,
> some work for supporting multiple VIFs on one device from Ben Greear,
> and a smattering of other bits.
>
> Please let me know if there are problems!
Pulled, thanks John.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [patch 1/1] [PATCH] qeth: tagging with VLAN-ID 0
From: David Miller @ 2010-10-04 5:08 UTC (permalink / raw)
To: frank.blaschka; +Cc: netdev, linux-s390, ursula.braun
In-Reply-To: <20101001125142.037089467@de.ibm.com>
From: frank.blaschka@de.ibm.com
Date: Fri, 01 Oct 2010 14:51:13 +0200
> From: Ursula Braun <ursula.braun@de.ibm.com>
>
> This patch adapts qeth to handle tagged frames with VLAN-ID 0 and
> with or without priority information in the tag. It enables qeth to
> receive priority-tagged frames on a base interface, for example from
> z/OS, without configuring an additional VLAN interface.
>
> Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
> Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
I'll apply this, thanks.
^ permalink raw reply
* Re: [PATCH net-next] cxgb4: remove a bogus PCI function number check
From: David Miller @ 2010-10-04 5:07 UTC (permalink / raw)
To: dm; +Cc: netdev
In-Reply-To: <1285874232-1554-1-git-send-email-dm@chelsio.com>
From: Dimitris Michailidis <dm@chelsio.com>
Date: Thu, 30 Sep 2010 12:17:12 -0700
> Remove a bogus PCI function number check from the driver's .remove
> method that causes pci_release_regions not to be called for function 0
> if additional functions are attached and one of them is used as primary.
>
> Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
Applied, thanks.
^ permalink raw reply
* Re: [PATCH 4/4] drivers/atm/idt77252.c: Remove unnecessary error check
From: David Miller @ 2010-10-04 5:06 UTC (permalink / raw)
To: julia
Cc: wharms, chas, kernel-janitors, linux-atm-general, netdev,
linux-kernel
In-Reply-To: <Pine.LNX.4.64.1010021636330.21879@ask.diku.dk>
From: Julia Lawall <julia@diku.dk>
Date: Sat, 2 Oct 2010 16:37:07 +0200 (CEST)
> This code does not call deinit_card(card); in an error case, as done in
> other error-handling code in the same function. But actually, the called
> function init_sram can only return 0, so there is no need for the error
> check at all.
>
> init_sram is also given a void return type, and its single return statement
> at the end of the function is dropped.
>
> A simplified version of the sematic match that finds this problem is as
> follows: (http://coccinelle.lip6.fr/)
...
> Signed-off-by: Julia Lawall <julia@diku.dk>
Applied, thank you.
^ permalink raw reply
* Re: [PATCH] Fix out-of-bounds reading in sctp_asoc_get_hmac()
From: David Miller @ 2010-10-04 5:00 UTC (permalink / raw)
To: vladislav.yasevich
Cc: drosenberg, sri, linux-sctp, linux-kernel, security, stable,
netdev
In-Reply-To: <4CA65D0E.6080604@hp.com>
From: Vlad Yasevich <vladislav.yasevich@hp.com>
Date: Fri, 01 Oct 2010 18:13:34 -0400
> On 10/01/2010 05:51 PM, Dan Rosenberg wrote:
>> The sctp_asoc_get_hmac() function iterates through a peer's hmac_ids
>> array and attempts to ensure that only a supported hmac entry is
>> returned. The current code fails to do this properly - if the last id
>> in the array is out of range (greater than SCTP_AUTH_HMAC_ID_MAX), the
>> id integer remains set after exiting the loop, and the address of an
>> out-of-bounds entry will be returned and subsequently used in the
>> parent
>> function, causing potentially ugly memory corruption. This patch
>> resets
>> the id integer to 0 on encountering an invalid id so that NULL will be
>> returned after finishing the loop if no valid ids are found.
>>
>> Signed-off-by: Dan Rosenberg<drosenberg@vsecurity.com>
>
> Good catch.
>
> Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Applied.
^ permalink raw reply
* Re: [PATCH] correct IGMP behavior on v3 query during v2-compatibility mode
From: David Miller @ 2010-10-04 5:01 UTC (permalink / raw)
To: dlstevens; +Cc: netdev
In-Reply-To: <1285892980.21804.7.camel@w-dls.beaverton.ibm.com>
From: David L Stevens <dlstevens@us.ibm.com>
Date: Thu, 30 Sep 2010 17:29:40 -0700
> A recent patch to allow IGMPv2 responses to IGMPv3 queries
> bypasses length checks for valid query lengths, incorrectly
> resets the v2_seen timer, and does not support IGMPv1.
>
> The following patch responds with a v2 report as required
> by IGMPv2 while correcting the other problems introduced
> by the patch.
>
> Signed-Off-By: David L Stevens <dlstevens@us.ibm.com>
Applied, thanks David.
^ permalink raw reply
* Re: [patch 1/2] drivers-net-tulip-de4x5c-fix-copy-length-in-de4x5_ioctl-checkpatch-fixes
From: David Miller @ 2010-10-04 5:00 UTC (permalink / raw)
To: akpm; +Cc: netdev, dan.j.rosenberg, grundler, jeffm
In-Reply-To: <201010012117.o91LHCJt021158@imap1.linux-foundation.org>
From: akpm@linux-foundation.org
Date: Fri, 01 Oct 2010 14:17:12 -0700
> From: Andrew Morton <akpm@linux-foundation.org>
>
> ERROR: trailing statements should be on next line
> #23: FILE: drivers/net/tulip/de4x5.c:5477:
> + if (copy_to_user(ioc->data, tmp.lval, ioc->len)) return -EFAULT;
>
> total: 1 errors, 0 warnings, 8 lines checked
>
> ./patches/drivers-net-tulip-de4x5c-fix-copy-length-in-de4x5_ioctl.patch has style problems, please review. If any of these errors
> are false positives report them to the maintainer, see
> CHECKPATCH in MAINTAINERS.
>
> Please run checkpatch prior to sending patches
>
> Cc: Dan Rosenberg <dan.j.rosenberg@gmail.com>
> Cc: Grant Grundler <grundler@parisc-linux.org>
> Cc: Jeff Mahoney <jeffm@suse.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Applied to net-next-2.6
^ permalink raw reply
* Re: [patch 2/2] drivers/net/stmmac/: add HAS_IOMEM dependency
From: David Miller @ 2010-10-04 5:00 UTC (permalink / raw)
To: akpm; +Cc: netdev, schwidefsky, heiko.carstens, peppe.cavallaro
In-Reply-To: <201010012117.o91LHDCF021161@imap1.linux-foundation.org>
From: akpm@linux-foundation.org
Date: Fri, 01 Oct 2010 14:17:13 -0700
> From: Martin Schwidefsky <schwidefsky@de.ibm.com>
>
> The stmmac driver does not compile on s390:
>
> drivers/net/stmmac/stmmac_main.c: In function 'stmmac_adjust_link':
> drivers/net/stmmac/stmmac_main.c:210: error: implicit declaration of function 'readl'
> drivers/net/stmmac/stmmac_main.c:263: error: implicit declaration of function 'writel'
> drivers/net/stmmac/stmmac_main.c: In function 'stmmac_dvr_probe':
> drivers/net/stmmac/stmmac_main.c:1674: error: implicit declaration of function 'ioremap'
> drivers/net/stmmac/stmmac_main.c:1674: warning: assignment makes pointer from integer without a cast
> drivers/net/stmmac/stmmac_main.c:1761: error: implicit declaration of function 'iounmap'
> make[3]: *** [drivers/net/stmmac/stmmac_main.o] Error 1
>
> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
> Cc: Giuseppe CAVALLARO <peppe.cavallaro@st.com>
> Cc: David S. Miller <davem@davemloft.net>
> Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This got fixed by adding a dependency on CPU_SUBTYPE_ST40.
^ permalink raw reply
* Re: [patch 1/1] sctp: prevent reading out-of-bounds memory
From: David Miller @ 2010-10-04 4:59 UTC (permalink / raw)
To: akpm; +Cc: netdev, dan.j.rosenberg, vladislav.yasevich
In-Reply-To: <201010012116.o91LGwS5021150@imap1.linux-foundation.org>
From: akpm@linux-foundation.org
Date: Fri, 01 Oct 2010 14:16:58 -0700
> From: Dan Rosenberg <dan.j.rosenberg@gmail.com>
>
> Two user-controlled allocations in SCTP are subsequently dereferenced as
> sockaddr structs, without checking if the dereferenced struct members fall
> beyond the end of the allocated chunk. There doesn't appear to be any
> information leakage here based on how these members are used and
> additional checking, but it's still worth fixing.
>
> [akpm@linux-foundation.org: remove unfashionable newlines, fix gmail tab->space conversion]
> Signed-off-by: Dan Rosenberg <dan.j.rosenberg@gmail.com>
> Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
> Cc: David Miller <davem@davemloft.net>
> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Applied.
^ permalink raw reply
* Re: [PATCH net-next 4/4] ipmr: cleanups
From: David Miller @ 2010-10-04 4:51 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1285985729.2582.525.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 02 Oct 2010 04:15:29 +0200
> Various code style cleanups
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next 3/4] ipmr: RCU protection for mfc_cache_array
From: David Miller @ 2010-10-04 4:51 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1285985708.2582.523.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 02 Oct 2010 04:15:08 +0200
> Use RCU & RTNL protection for mfc_cache_array[]
>
> ipmr_cache_find() is called under rcu_read_lock();
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next 2/4] ipmr: RCU conversion of mroute_sk
From: David Miller @ 2010-10-04 4:51 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1285985701.2582.522.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 02 Oct 2010 04:15:01 +0200
> Use RCU and RTNL to protect (struct mr_table)->mroute_sk
>
> Readers use RCU, writers use RTNL.
>
> ip_ra_control() already use an RCU grace period before
> ip_ra_destroy_rcu(), so we dont need synchronize_rcu() in
> mrtsock_destruct()
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next 1/4] ipmr: __pim_rcv() is called under rcu_read_lock
From: David Miller @ 2010-10-04 4:51 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1285985695.2582.521.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 02 Oct 2010 04:14:55 +0200
> No need to get a reference on reg_dev and release it, we are in a
> rcu_read_lock() protected section.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next] gre: protocol table can be static
From: David Miller @ 2010-10-04 4:51 UTC (permalink / raw)
To: shemminger; +Cc: netdev, herbert
In-Reply-To: <20101002085800.4cd06561@s6510>
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Sat, 2 Oct 2010 08:58:00 +0900
> This table is only used in gre.c
>
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Applied.
^ permalink raw reply
* Re: [PATCH 1/2] Revert "ipv4: Make INET_LRO a bool instead of tristate."
From: David Miller @ 2010-10-04 4:01 UTC (permalink / raw)
To: ben; +Cc: netdev
In-Reply-To: <1286164495.3916.316.camel@localhost>
From: Ben Hutchings <ben@decadent.org.uk>
Date: Mon, 04 Oct 2010 04:54:55 +0100
> On Sun, 2010-10-03 at 19:56 -0700, David Miller wrote:
>> From: Ben Hutchings <ben@decadent.org.uk>
>> Date: Mon, 04 Oct 2010 02:37:42 +0100
>>
>> > You made the change I want to revert in response to
>> > <http://article.gmane.org/gmane.linux.kernel/825646>. The real problem
>> > with its configuration is actually that CONFIG_INET is not set but
>> > CONFIG_INET_LRO=m, and the fix is to make CONFIG_PASEMI_MAC depend on
>> > CONFIG_INET.
>>
>> Ben, you can't just revert this by itself.
>>
>> That knowingly breaks the build.
>>
>> If you want the tristate back, you must do it after or at the
>> same time as fixing the driver deps.
>
> The fact that the driver dependencies are broken has nothing to do with
> whether CONFIG_INET_LRO is boolean or tristate. You fixed a problem
> that didn't exist rather than the problem that did.
Oh, I see, ok I'll apply your patches thanks for explaining Ben.
^ permalink raw reply
* Re: [PATCH] ibmtr: fix tr%d in dmesg
From: David Miller @ 2010-10-04 3:56 UTC (permalink / raw)
To: mroos; +Cc: netdev
In-Reply-To: <alpine.SOC.1.00.1010022056000.27121@math.ut.ee>
From: Meelis Roos <mroos@linux.ee>
Date: Sat, 2 Oct 2010 21:35:15 +0300 (EEST)
> ibmtr and ibmtr_cs show tr%d in dmesg after alloc_netdev() but before
> register_netdev(). Fix it like e100 does - put a different name into
> dev->name until the device gets registered. I/O port seems to be unique
> enough and is available for the time of printk messages. With the fix,
> dmesg shows
>
> ibmtr@0a20: ISA P&P 16/4 Adapter/A (short) | 16/4 ISA-16 Adapter found
> ibmtr@0a20: using irq 3, PIOaddr a20, 64K shared RAM.
> ibmtr@0a20: Hardware address : 00:40:aa:a9:03:98
> ibmtr@0a20: Shared RAM paging disabled. ti->page_mask 0
> ibmtr@0a20: Maximum Receive Internet Protocol MTU 16Mbps: 16344, 4Mbps: 6104
> tr0: port 0xa20, irq 3, mmio 0xd4850000, sram 0xd0000, hwaddr=00:40:aa:a9:03:98
>
> Signed-off-by: Meelis Roos <mroos@linux.ee>
That may be how e100 does it, but this is a very ugly hack and
an abuse of netdev->name
Instead, the more correct way to fit this is to use dev_info(),
dev_err(), and friends. It will both print the correct stuff,
and also document the probing path messages that occur before
the net device is registered.
So please correct the prolem that way, thank you.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox