pull request (net-next): ipsec-next 2013-02-14
Subsystems (3)
Steffen Klassert
maintainer1) Remove a duplicated call to skb_orphan() in pf_key, from Cong Wang.
2) Prepare xfrm and pf_key for algorithms without pf_key support, from Jussi Kivilinna.
3) Fix an unbalanced lock in xfrm_output_one(), from Li RongQing.
4) Add an IPsec state resolution packet queue to handle packets that are send before the states are resolved.
5) xfrm4_policy_fini() is unused since 2.6.11, time to remove it. From Michal Kubecek.
6) The xfrm gc threshold was configurable just in the initial namespace, make it configurable in all namespaces. From Michal Kubecek.
7) We currently can not insert policies with mark and mask such that some flows would be matched from both policies. Allow this if the priorities of these policies are different, the one with the higher priority is used in this case.
Please pull or let me know if there are problems.
Thanks!
The following changes since commit cef401de7be8c4e155c6746bfccf721a4fa5fab9:
net: fix possible wrong checksum generation (2013-01-28 00:27:15 -0500)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git master
for you to fetch changes up to 7cb8a93968e395e40a72a50da0b6114e752304b4:
xfrm: Allow inserting policies with matching mark and different priorities (2013-02-11 14:07:01 +0100)
----------------------------------------------------------------
Cong Wang (1):
af_key: remove a duplicated skb_orphan()
Jussi Kivilinna (1):
pf_key/xfrm_algo: prepare pf_key and xfrm_algo for new algorithms without pfkey support
Li RongQing (1):
xfrm: fix a unbalanced lock
Michal Kubecek (2):
xfrm: remove unused xfrm4_policy_fini()
xfrm: make gc_thresh configurable in all namespaces
Steffen Klassert (2):
xfrm: Add a state resolution packet queue
xfrm: Allow inserting policies with matching mark and different priorities
include/net/dst.h | 1 + include/net/netns/ipv4.h | 1 + include/net/netns/ipv6.h | 1 + include/net/xfrm.h | 12 ++- net/ipv4/xfrm4_policy.c | 58 ++++++++--- net/ipv6/xfrm6_policy.c | 52 +++++++++- net/key/af_key.c | 40 ++++++-- net/xfrm/xfrm_algo.c | 65 ++++++++++-- net/xfrm/xfrm_output.c | 2 +- net/xfrm/xfrm_policy.c | 247 ++++++++++++++++++++++++++++++++++++++++++++-- 10 files changed, 438 insertions(+), 41 deletions(-)
Steffen Klassert
maintainerPATCH 1/7 af_key: remove a duplicated skb_orphan()
From: Cong Wang <[email protected]>
skb_set_owner_r() will call skb_orphan(), I don't see any reason to call it twice.
--- net/key/af_key.c | 1 - 1 file changed, 1 deletion(-)
net/key/af_key.c +0 -1
@@ -203,7 +203,6 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, }if (*skb2 !=NULL ) {if (atomic_read (&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { -skb_orphan (*skb2);skb_set_owner_r (*skb2, sk);skb_queue_tail (&sk->sk_receive_queue, *skb2); sk->sk_data_ready (sk, (*skb2)->len);
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 2/7 pf_key/xfrm_algo: prepare pf_key and xfrm_algo for new algorithms without pfkey support
In reply to Steffen KlassertFrom: Jussi Kivilinna <[email protected]>
Mark existing algorithms as pfkey supported and make pfkey only use algorithms that have pfkey_supported set.
--- include/net/xfrm.h | 5 ++-- net/key/af_key.c | 39 +++++++++++++++++++++++------- net/xfrm/xfrm_algo.c | 65 +++++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 93 insertions(+), 16 deletions(-)
include/net/xfrm.h +3 -2
@@ -1320,6 +1320,7 @@ struct xfrm_algo_desc {char *name;char *compat; u8 available:1; + u8 pfkey_supported:1;union {struct xfrm_algo_aead_info aead;struct xfrm_algo_auth_info auth;
@@ -1561,8 +1562,8 @@ extern void xfrm_input_init(void);extern int xfrm_parse_spi (struct sk_buff *skb,u8 nexthdr,__be32 *spi,__be32 *seq);extern void xfrm_probe_algs (void ); -extern int xfrm_count_auth_supported (void ); -extern int xfrm_count_enc_supported (void ); +extern int xfrm_count_pfkey_auth_supported (void ); +extern int xfrm_count_pfkey_enc_supported (void );extern struct xfrm_algo_desc *xfrm_aalg_get_byidx (unsigned int idx);extern struct xfrm_algo_desc *xfrm_ealg_get_byidx (unsigned int idx);extern struct xfrm_algo_desc *xfrm_aalg_get_byid (int alg_id);
net/key/af_key.c +31 -8
@@ -815,18 +815,21 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, sa->sadb_sa_auth =0 ;if (x->aalg) {struct xfrm_algo_desc *a =xfrm_aalg_get_byname (x->aalg->alg_name,0 ); - sa->sadb_sa_auth = a ? a->desc.sadb_alg_id :0 ; + sa->sadb_sa_auth = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id :0 ; } sa->sadb_sa_encrypt =0 ;BUG_ON (x->ealg && x->calg);if (x->ealg) {struct xfrm_algo_desc *a =xfrm_ealg_get_byname (x->ealg->alg_name,0 ); - sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id :0 ; + sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id :0 ; }/* KAME compatible: sadb_sa_encrypt is overloaded with calg id */ if (x->calg) {struct xfrm_algo_desc *a =xfrm_calg_get_byname (x->calg->alg_name,0 ); - sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id :0 ; + sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id :0 ; } sa->sadb_sa_flags =0 ;
@@ -1137,7 +1140,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,if (sa->sadb_sa_auth) {int keysize =0 ;struct xfrm_algo_desc *a =xfrm_aalg_get_byid (sa->sadb_sa_auth); -if (!a) { +if (!a || !a->pfkey_supported) { err = -ENOSYS ; goto out; }
@@ -1159,7 +1162,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,if (sa->sadb_sa_encrypt) {if (hdr->sadb_msg_satype ==SADB_X_SATYPE_IPCOMP ) {struct xfrm_algo_desc *a =xfrm_calg_get_byid (sa->sadb_sa_encrypt); -if (!a) { +if (!a || !a->pfkey_supported) { err = -ENOSYS ; goto out; }
@@ -1171,7 +1174,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, }else {int keysize =0 ;struct xfrm_algo_desc *a =xfrm_ealg_get_byid (sa->sadb_sa_encrypt); -if (!a) { +if (!a || !a->pfkey_supported) { err = -ENOSYS ; goto out; }
@@ -1577,13 +1580,13 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,struct sadb_msg *hdr;int len, auth_len, enc_len, i; - auth_len =xfrm_count_auth_supported (); + auth_len =xfrm_count_pfkey_auth_supported ();if (auth_len) { auth_len *=sizeof (struct sadb_alg ); auth_len +=sizeof (struct sadb_supported ); } - enc_len =xfrm_count_enc_supported (); + enc_len =xfrm_count_pfkey_enc_supported ();if (enc_len) { enc_len *=sizeof (struct sadb_alg ); enc_len +=sizeof (struct sadb_supported );
@@ -1614,6 +1617,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,struct xfrm_algo_desc *aalg =xfrm_aalg_get_byidx (i);if (!aalg)break ; +if (!aalg->pfkey_supported) +continue ;if (aalg->available) *ap++ = aalg->desc; }
@@ -1633,6 +1638,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig,struct xfrm_algo_desc *ealg =xfrm_ealg_get_byidx (i);if (!ealg)break ; +if (!ealg->pfkey_supported) +continue ;if (ealg->available) *ap++ = ealg->desc; }
@@ -2824,6 +2831,8 @@ static int count_ah_combs(const struct xfrm_tmpl *t)const struct xfrm_algo_desc *aalg =xfrm_aalg_get_byidx (i);if (!aalg)break ; +if (!aalg->pfkey_supported) +continue ;if (aalg_tmpl_set (t, aalg) && aalg->available) sz +=sizeof (struct sadb_comb ); }
@@ -2839,6 +2848,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t)if (!ealg)break ; +if (!ealg->pfkey_supported) +continue ; +if (!(ealg_tmpl_set (t, ealg) && ealg->available))continue ;
@@ -2847,6 +2859,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t)if (!aalg)break ; +if (!aalg->pfkey_supported) +continue ; +if (aalg_tmpl_set (t, aalg) && aalg->available) sz +=sizeof (struct sadb_comb ); }
@@ -2870,6 +2885,9 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)if (!aalg)break ; +if (!aalg->pfkey_supported) +continue ; +if (aalg_tmpl_set (t, aalg) && aalg->available) {struct sadb_comb *c; c = (struct sadb_comb *)skb_put (skb,sizeof (struct sadb_comb ));
@@ -2902,6 +2920,9 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)if (!ealg)break ; +if (!ealg->pfkey_supported) +continue ; +if (!(ealg_tmpl_set (t, ealg) && ealg->available))continue ;
@@ -2910,6 +2931,8 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)const struct xfrm_algo_desc *aalg =xfrm_aalg_get_byidx (k);if (!aalg)break ; +if (!aalg->pfkey_supported) +continue ;if (!(aalg_tmpl_set (t, aalg) && aalg->available))continue ; c = (struct sadb_comb *)skb_put (skb,sizeof (struct sadb_comb ));
net/xfrm/xfrm_algo.c +59 -6
254 lines not on this page · raw message
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 3/7 xfrm: fix a unbalanced lock
In reply to Steffen KlassertFrom: Li RongQing <[email protected]>
--- net/xfrm/xfrm_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/xfrm/xfrm_output.c +1 -1
@@ -64,7 +64,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)if (unlikely (x->km.state !=XFRM_STATE_VALID )) {XFRM_INC_STATS (net,LINUX_MIB_XFRMOUTSTATEINVALID ); - goto error_nolock; + goto error; } err =xfrm_state_check_expire (x);
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 4/7 xfrm: Add a state resolution packet queue
In reply to Steffen KlassertAs the default, we blackhole packets until the key manager resolves the states. This patch implements a packet queue where IPsec packets are queued until the states are resolved. We generate a dummy xfrm bundle, the output routine of the returned route enqueues the packet to a per policy queue and arms a timer that checks for state resolution when dst_output() is called. Once the states are resolved, the packets are sent out of the queue. If the states are not resolved after some time, the queue is flushed.
This patch keeps the defaut behaviour to blackhole packets as long as we have no states. To enable the packet queue the sysctl xfrm_larval_drop must be switched off.
--- include/net/dst.h | 1 + include/net/xfrm.h | 7 ++ net/xfrm/xfrm_policy.c | 229 +++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 233 insertions(+), 4 deletions(-)
include/net/dst.h +1 -0
@@ -61,6 +61,7 @@ struct dst_entry {#define DST_NOPEER 0x0040#define DST_FAKE_RTABLE 0x0080#define DST_XFRM_TUNNEL 0x0100 +#define DST_XFRM_QUEUE 0x0200unsigned short pending_confirm;
include/net/xfrm.h +7 -0
@@ -501,6 +501,12 @@ struct xfrm_policy_walk {u32 seq; }; +struct xfrm_policy_queue { +struct sk_buff_head hold_queue; +struct timer_list hold_timer; +unsigned long timeout; +}; +struct xfrm_policy {#ifdef CONFIG_NET_NS struct net *xp_net;
@@ -522,6 +528,7 @@ struct xfrm_policy {struct xfrm_lifetime_cfg lft;struct xfrm_lifetime_cur curlft;struct xfrm_policy_walk_entry walk; +struct xfrm_policy_queue polq;u8 type;u8 action;u8 flags;
net/xfrm/xfrm_policy.c +225 -4
308 lines not on this page · raw message
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 5/7 xfrm: remove unused xfrm4_policy_fini()
In reply to Steffen KlassertFrom: Michal Kubecek <[email protected]>
Function xfrm4_policy_fini() is unused since xfrm4_fini() was removed in 2.6.11.
--- net/ipv4/xfrm4_policy.c | 9 --------- 1 file changed, 9 deletions(-)
net/ipv4/xfrm4_policy.c +0 -9
@@ -270,15 +270,6 @@ static void __init xfrm4_policy_init(void)xfrm_policy_register_afinfo (&xfrm4_policy_afinfo); } -static void __exit xfrm4_policy_fini(void) -{ -#ifdef CONFIG_SYSCTL -if (sysctl_hdr) -unregister_net_sysctl_table (sysctl_hdr); -#endif -xfrm_policy_unregister_afinfo (&xfrm4_policy_afinfo); -} -void __init xfrm4_init (void ) {dst_entries_init (&xfrm4_dst_ops);
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 6/7 xfrm: make gc_thresh configurable in all namespaces
In reply to Steffen KlassertFrom: Michal Kubecek <[email protected]>
The xfrm gc threshold can be configured via xfrm{4,6}_gc_thresh sysctl but currently only in init_net, other namespaces always use the default value. This can substantially limit the number of IPsec tunnels that can be effectively used.
--- include/net/netns/ipv4.h | 1 + include/net/netns/ipv6.h | 1 + net/ipv4/xfrm4_policy.c | 49 ++++++++++++++++++++++++++++++++++++++++--- net/ipv6/xfrm6_policy.c | 52 +++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 95 insertions(+), 8 deletions(-)
include/net/netns/ipv4.h +1 -0
@@ -22,6 +22,7 @@ struct netns_ipv4 {struct ctl_table_header *frags_hdr;struct ctl_table_header *ipv4_hdr;struct ctl_table_header *route_hdr; +struct ctl_table_header *xfrm4_hdr;#endif struct ipv4_devconf *devconf_all;struct ipv4_devconf *devconf_dflt;
include/net/netns/ipv6.h +1 -0
@@ -16,6 +16,7 @@ struct netns_sysctl_ipv6 {struct ctl_table_header *route_hdr;struct ctl_table_header *icmp_hdr;struct ctl_table_header *frags_hdr; +struct ctl_table_header *xfrm6_hdr;#endif int bindv6only;int flush_delay;
net/ipv4/xfrm4_policy.c +46 -3
61 lines not on this page · raw message
net/ipv6/xfrm6_policy.c +47 -5
70 lines not on this page · raw message
Signature · 1 line
1.7.9.5
Steffen Klassert
maintainerPATCH 7/7 xfrm: Allow inserting policies with matching mark and different priorities
In reply to Steffen KlassertWe currently can not insert policies with mark and mask such that some flows would be matched from both policies. We make this possible when the priority of these policies are different. If both policies match a flow, the one with the higher priority is used.
--- net/xfrm/xfrm_policy.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)
net/xfrm/xfrm_policy.c +16 -2
@@ -607,6 +607,21 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,spin_unlock_bh (&pq->hold_queue.lock); } +static bool xfrm_policy_mark_match (struct xfrm_policy *policy, +struct xfrm_policy *pol) +{ +u32 mark = policy->mark.v & policy->mark.m; + +if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m) +return true; + +if ((mark & pol->mark.m) == pol->mark.v && + policy->priority == pol->priority) +return true; + +return false; +} +int xfrm_policy_insert (int dir,struct xfrm_policy *policy,int excl) {struct net *net =xp_net (policy);
@@ -614,7 +629,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)struct xfrm_policy *delpol;struct hlist_head *chain;struct hlist_node *entry, *newpos; -u32 mark = policy->mark.v & policy->mark.m;write_lock_bh (&xfrm_policy_lock); chain =policy_hash_bysel (net, &policy->selector, policy->family, dir);
@@ -623,7 +637,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)hlist_for_each_entry (pol, entry, chain, bydst) {if (pol->type == policy->type && !selector_cmp (&pol->selector, &policy->selector) && - (mark & pol->mark.m) == pol->mark.v && +xfrm_policy_mark_match (policy, pol) &&xfrm_sec_ctx_match (pol->security, policy->security) && !WARN_ON (delpol)) {if (excl) {
Signature · 1 line
1.7.9.5
David Miller
maintainerFrom: Steffen Klassert <[email protected]>
Date: Thu, 14 Feb 2013 12:47:20 +0100
Quoted 17 lines
1) Remove a duplicated call to
skb_orphan()inpf_key, from Cong Wang.2) Prepare xfrm and
pf_keyfor algorithms withoutpf_keysupport, from Jussi Kivilinna.3) Fix an unbalanced lock in
xfrm_output_one(), from Li RongQing.4) Add an IPsec state resolution packet queue to handle packets that are send before the states are resolved.
5)
xfrm4_policy_fini()is unused since 2.6.11, time to remove it. From Michal Kubecek.6) The xfrm gc threshold was configurable just in the initial namespace, make it configurable in all namespaces. From Michal Kubecek.
Quoted 6 lines
7) We currently can not insert policies with mark and mask such that some flows would be matched from both policies. Allow this if the priorities of these policies are different, the one with the higher priority is used in this case.
Please pull or let me know if there are problems.
Pulled, thanks Steffen.