* [RFC 1/3] [IPSEC] xfrm: Undo afinfo lock proliferation
2006-05-06 11:20 ` [RFC 0/3] [IPSEC]: Add xfrm_mode support Herbert Xu
@ 2006-05-06 11:21 ` Herbert Xu
[not found] ` <200605081522.14524.netdev@axxeo.de>
2006-05-06 11:21 ` [RFC 2/3] [IPSEC] xfrm: Abstract out encapsulation modes Herbert Xu
` (2 subsequent siblings)
3 siblings, 1 reply; 7+ messages in thread
From: Herbert Xu @ 2006-05-06 11:21 UTC (permalink / raw)
To: Miika Komu; +Cc: Diego Beltrami, David S. Miller, netdev
[-- Attachment #1: Type: text/plain, Size: 1029 bytes --]
Hi:
The number of locks used to manage afinfo structures can easily be reduced
down to one each for policy and state respectively. This is based on the
observation that the write locks are only held by module insertion/removal
which are very rare events so there is no need to further differentiate
between the insertion of modules like ipv6 versus esp6.
The removal of the read locks in xfrm4_policy.c/xfrm6_policy.c might look
suspicious at first. However, after you realise that nobody ever takes
the corresponding write lock you'll feel better :)
As far as I can gather it's an attempt to guard against the removal of
the corresponding modules. Since neither module can be unloaded at all
we can leave it to whoever fixes up IPv6 unloading :)
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
[-- Attachment #2: p1.patch --]
[-- Type: text/plain, Size: 8506 bytes --]
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -204,8 +204,7 @@ struct xfrm_type;
struct xfrm_dst;
struct xfrm_policy_afinfo {
unsigned short family;
- rwlock_t lock;
- struct xfrm_type_map *type_map;
+ struct xfrm_type *type_map[256];
struct dst_ops *dst_ops;
void (*garbage_collect)(void);
int (*dst_lookup)(struct xfrm_dst **dst, struct flowi *fl);
@@ -232,7 +231,6 @@ extern int __xfrm_state_delete(struct xf
struct xfrm_state_afinfo {
unsigned short family;
- rwlock_t lock;
struct list_head *state_bydst;
struct list_head *state_byspi;
int (*init_flags)(struct xfrm_state *x);
@@ -264,11 +262,6 @@ struct xfrm_type
u32 (*get_max_size)(struct xfrm_state *, int size);
};
-struct xfrm_type_map {
- rwlock_t lock;
- struct xfrm_type *map[256];
-};
-
extern int xfrm_register_type(struct xfrm_type *type, unsigned short family);
extern int xfrm_unregister_type(struct xfrm_type *type, unsigned short family);
extern struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -17,8 +17,6 @@
static struct dst_ops xfrm4_dst_ops;
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
-static struct xfrm_type_map xfrm4_type_map = { .lock = RW_LOCK_UNLOCKED };
-
static int xfrm4_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
{
return __ip_route_output_key((struct rtable**)dst, fl);
@@ -237,9 +235,7 @@ _decode_session4(struct sk_buff *skb, st
static inline int xfrm4_garbage_collect(void)
{
- read_lock(&xfrm4_policy_afinfo.lock);
xfrm4_policy_afinfo.garbage_collect();
- read_unlock(&xfrm4_policy_afinfo.lock);
return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
}
@@ -299,8 +295,6 @@ static struct dst_ops xfrm4_dst_ops = {
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
- .lock = RW_LOCK_UNLOCKED,
- .type_map = &xfrm4_type_map,
.dst_ops = &xfrm4_dst_ops,
.dst_lookup = xfrm4_dst_lookup,
.find_bundle = __xfrm4_find_bundle,
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -131,7 +131,6 @@ __xfrm4_find_acq(u8 mode, u32 reqid, u8
static struct xfrm_state_afinfo xfrm4_state_afinfo = {
.family = AF_INET,
- .lock = RW_LOCK_UNLOCKED,
.init_flags = xfrm4_init_flags,
.init_tempsel = __xfrm4_init_tempsel,
.state_lookup = __xfrm4_state_lookup,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -23,8 +23,6 @@
static struct dst_ops xfrm6_dst_ops;
static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
-static struct xfrm_type_map xfrm6_type_map = { .lock = RW_LOCK_UNLOCKED };
-
static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
{
int err = 0;
@@ -249,9 +247,7 @@ _decode_session6(struct sk_buff *skb, st
static inline int xfrm6_garbage_collect(void)
{
- read_lock(&xfrm6_policy_afinfo.lock);
xfrm6_policy_afinfo.garbage_collect();
- read_unlock(&xfrm6_policy_afinfo.lock);
return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2);
}
@@ -311,8 +307,6 @@ static struct dst_ops xfrm6_dst_ops = {
static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
- .lock = RW_LOCK_UNLOCKED,
- .type_map = &xfrm6_type_map,
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
.find_bundle = __xfrm6_find_bundle,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -135,7 +135,6 @@ __xfrm6_find_acq(u8 mode, u32 reqid, u8
static struct xfrm_state_afinfo xfrm6_state_afinfo = {
.family = AF_INET6,
- .lock = RW_LOCK_UNLOCKED,
.init_tempsel = __xfrm6_init_tempsel,
.state_lookup = __xfrm6_state_lookup,
.find_acq = __xfrm6_find_acq,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -46,45 +46,43 @@ static DEFINE_SPINLOCK(xfrm_policy_gc_lo
static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family);
static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo);
+static struct xfrm_policy_afinfo *xfrm_policy_lock_afinfo(unsigned int family);
+static void xfrm_policy_unlock_afinfo(struct xfrm_policy_afinfo *afinfo);
int xfrm_register_type(struct xfrm_type *type, unsigned short family)
{
- struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
- struct xfrm_type_map *typemap;
+ struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family);
+ struct xfrm_type **typemap;
int err = 0;
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
typemap = afinfo->type_map;
- write_lock_bh(&typemap->lock);
- if (likely(typemap->map[type->proto] == NULL))
- typemap->map[type->proto] = type;
+ if (likely(typemap[type->proto] == NULL))
+ typemap[type->proto] = type;
else
err = -EEXIST;
- write_unlock_bh(&typemap->lock);
- xfrm_policy_put_afinfo(afinfo);
+ xfrm_policy_unlock_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_register_type);
int xfrm_unregister_type(struct xfrm_type *type, unsigned short family)
{
- struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
- struct xfrm_type_map *typemap;
+ struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family);
+ struct xfrm_type **typemap;
int err = 0;
if (unlikely(afinfo == NULL))
return -EAFNOSUPPORT;
typemap = afinfo->type_map;
- write_lock_bh(&typemap->lock);
- if (unlikely(typemap->map[type->proto] != type))
+ if (unlikely(typemap[type->proto] != type))
err = -ENOENT;
else
- typemap->map[type->proto] = NULL;
- write_unlock_bh(&typemap->lock);
- xfrm_policy_put_afinfo(afinfo);
+ typemap[type->proto] = NULL;
+ xfrm_policy_unlock_afinfo(afinfo);
return err;
}
EXPORT_SYMBOL(xfrm_unregister_type);
@@ -92,7 +90,7 @@ EXPORT_SYMBOL(xfrm_unregister_type);
struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
{
struct xfrm_policy_afinfo *afinfo;
- struct xfrm_type_map *typemap;
+ struct xfrm_type **typemap;
struct xfrm_type *type;
int modload_attempted = 0;
@@ -102,11 +100,9 @@ retry:
return NULL;
typemap = afinfo->type_map;
- read_lock(&typemap->lock);
- type = typemap->map[proto];
+ type = typemap[proto];
if (unlikely(type && !try_module_get(type->owner)))
type = NULL;
- read_unlock(&typemap->lock);
if (!type && !modload_attempted) {
xfrm_policy_put_afinfo(afinfo);
request_module("xfrm-type-%d-%d",
@@ -1306,17 +1302,31 @@ static struct xfrm_policy_afinfo *xfrm_p
return NULL;
read_lock(&xfrm_policy_afinfo_lock);
afinfo = xfrm_policy_afinfo[family];
- if (likely(afinfo != NULL))
- read_lock(&afinfo->lock);
- read_unlock(&xfrm_policy_afinfo_lock);
+ if (unlikely(!afinfo))
+ read_unlock(&xfrm_policy_afinfo_lock);
return afinfo;
}
static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo)
{
- if (unlikely(afinfo == NULL))
- return;
- read_unlock(&afinfo->lock);
+ read_unlock(&xfrm_policy_afinfo_lock);
+}
+
+static struct xfrm_policy_afinfo *xfrm_policy_lock_afinfo(unsigned int family)
+{
+ struct xfrm_policy_afinfo *afinfo;
+ if (unlikely(family >= NPROTO))
+ return NULL;
+ write_lock_bh(&xfrm_policy_afinfo_lock);
+ afinfo = xfrm_policy_afinfo[family];
+ if (unlikely(!afinfo))
+ write_unlock_bh(&xfrm_policy_afinfo_lock);
+ return afinfo;
+}
+
+static void xfrm_policy_unlock_afinfo(struct xfrm_policy_afinfo *afinfo)
+{
+ write_unlock_bh(&xfrm_policy_afinfo_lock);
}
static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1103,17 +1103,14 @@ static struct xfrm_state_afinfo *xfrm_st
return NULL;
read_lock(&xfrm_state_afinfo_lock);
afinfo = xfrm_state_afinfo[family];
- if (likely(afinfo != NULL))
- read_lock(&afinfo->lock);
- read_unlock(&xfrm_state_afinfo_lock);
+ if (unlikely(!afinfo))
+ read_unlock(&xfrm_state_afinfo_lock);
return afinfo;
}
static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
{
- if (unlikely(afinfo == NULL))
- return;
- read_unlock(&afinfo->lock);
+ read_unlock(&xfrm_state_afinfo_lock);
}
/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
^ permalink raw reply [flat|nested] 7+ messages in thread* [RFC 2/3] [IPSEC] xfrm: Abstract out encapsulation modes
2006-05-06 11:20 ` [RFC 0/3] [IPSEC]: Add xfrm_mode support Herbert Xu
2006-05-06 11:21 ` [RFC 1/3] [IPSEC] xfrm: Undo afinfo lock proliferation Herbert Xu
@ 2006-05-06 11:21 ` Herbert Xu
2006-05-06 11:24 ` [RFC 3/3] [IPSEC]: Abstract out transport mode input code Herbert Xu
2006-05-10 20:54 ` [RFC 0/3] [IPSEC]: Add xfrm_mode support David S. Miller
3 siblings, 0 replies; 7+ messages in thread
From: Herbert Xu @ 2006-05-06 11:21 UTC (permalink / raw)
To: Miika Komu; +Cc: Diego Beltrami, David S. Miller, netdev
[-- Attachment #1: Type: text/plain, Size: 604 bytes --]
Hi:
This patch adds the structure xfrm_mode. It is meant to represent
the operations carried out by transport/tunnel modes.
By doing this we allow additional encapsulation modes to be added
without clogging up the xfrm_input/xfrm_output paths.
Candidate modes include 4-to-6 tunnel mode, 6-to-4 tunnel mode, and
BEET modes.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
[-- Attachment #2: p2.patch --]
[-- Type: text/plain, Size: 25668 bytes --]
diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -118,6 +118,10 @@ enum
XFRM_SHARE_UNIQUE /* Use once */
};
+#define XFRM_MODE_TRANSPORT 0
+#define XFRM_MODE_TUNNEL 1
+#define XFRM_MODE_MAX 2
+
/* Netlink configuration messages. */
enum {
XFRM_MSG_BASE = 0x10,
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -20,6 +20,8 @@
#include <net/ip6_fib.h>
#define XFRM_ALIGN8(len) (((len) + 7) & ~7)
+#define MODULE_ALIAS_XFRM_MODE(family, encap) \
+ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap))
extern struct sock *xfrm_nl;
extern u32 sysctl_xfrm_aevent_etime;
@@ -164,6 +166,7 @@ struct xfrm_state
/* Reference to data common to all the instances of this
* transformer. */
struct xfrm_type *type;
+ struct xfrm_mode *mode;
/* Security context */
struct xfrm_sec_ctx *security;
@@ -205,6 +208,7 @@ struct xfrm_dst;
struct xfrm_policy_afinfo {
unsigned short family;
struct xfrm_type *type_map[256];
+ struct xfrm_mode *mode_map[XFRM_MODE_MAX];
struct dst_ops *dst_ops;
void (*garbage_collect)(void);
int (*dst_lookup)(struct xfrm_dst **dst, struct flowi *fl);
@@ -267,6 +271,19 @@ extern int xfrm_unregister_type(struct x
extern struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family);
extern void xfrm_put_type(struct xfrm_type *type);
+struct xfrm_mode {
+ int (*input)(struct xfrm_state *x, struct sk_buff *skb);
+ int (*output)(struct sk_buff *skb);
+
+ struct module *owner;
+ int encap;
+};
+
+extern int xfrm_register_mode(struct xfrm_mode *mode, int family);
+extern int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
+extern struct xfrm_mode *xfrm_get_mode(int encap, int family);
+extern void xfrm_put_mode(struct xfrm_mode *mode);
+
struct xfrm_tmpl
{
/* id in template is interpreted as:
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -414,6 +414,24 @@ config INET_TUNNEL
tristate
default n
+config INET_XFRM_MODE_TRANSPORT
+ tristate "IP: IPsec transport mode"
+ default y
+ select XFRM
+ ---help---
+ Support for IPsec transport mode.
+
+ If unsure, say Y.
+
+config INET_XFRM_MODE_TUNNEL
+ tristate "IP: IPsec tunnel mode"
+ default y
+ select XFRM
+ ---help---
+ Support for IPsec tunnel mode.
+
+ If unsure, say Y.
+
config INET_DIAG
tristate "INET: socket monitoring interface"
default y
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -24,6 +24,8 @@ obj-$(CONFIG_INET_ESP) += esp4.o
obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
+obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
+obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
obj-$(CONFIG_IP_PNP) += ipconfig.o
obj-$(CONFIG_IP_ROUTE_MULTIPATH_RR) += multipath_rr.o
obj-$(CONFIG_IP_ROUTE_MULTIPATH_RANDOM) += multipath_random.o
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -13,7 +13,6 @@
#include <linux/string.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
-#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/xfrm.h>
@@ -24,15 +23,6 @@ int xfrm4_rcv(struct sk_buff *skb)
EXPORT_SYMBOL(xfrm4_rcv);
-static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
-{
- struct iphdr *outer_iph = skb->nh.iph;
- struct iphdr *inner_iph = skb->h.ipiph;
-
- if (INET_ECN_is_ce(outer_iph->tos))
- IP_ECN_set_ce(inner_iph);
-}
-
static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq)
{
switch (nexthdr) {
@@ -113,24 +103,10 @@ int xfrm4_rcv_encap(struct sk_buff *skb,
xfrm_vec[xfrm_nr++] = x;
- iph = skb->nh.iph;
+ if (x->mode->input(x, skb))
+ goto drop;
if (x->props.mode) {
- if (iph->protocol != IPPROTO_IPIP)
- goto drop;
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- goto drop;
- if (skb_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
- goto drop;
- if (x->props.flags & XFRM_STATE_DECAP_DSCP)
- ipv4_copy_dscp(iph, skb->h.ipiph);
- if (!(x->props.flags & XFRM_STATE_NOECN))
- ipip_ecn_decapsulate(skb);
- skb->mac.raw = memmove(skb->data - skb->mac_len,
- skb->mac.raw, skb->mac_len);
- skb->nh.raw = skb->data;
- memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
decaps = 1;
break;
}
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
new file mode 100644
--- /dev/null
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -0,0 +1,69 @@
+/*
+ * xfrm4_mode_transport.c - Transport mode encapsulation for IPv4.
+ *
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+
+/* Add encapsulation header.
+ *
+ * The IP header will be moved forward to make space for the encapsulation
+ * header.
+ *
+ * On exit, skb->h will be set to the start of the payload to be processed
+ * by x->type->output and skb->nh will be set to the top IP header.
+ */
+static int xfrm4_transport_output(struct sk_buff *skb)
+{
+ struct xfrm_state *x;
+ struct iphdr *iph;
+ int ihl;
+
+ iph = skb->nh.iph;
+ skb->h.ipiph = iph;
+
+ ihl = iph->ihl * 4;
+ skb->h.raw += ihl;
+
+ x = skb->dst->xfrm;
+ skb->nh.raw = memmove(skb_push(skb, x->props.header_len), iph, ihl);
+ return 0;
+}
+
+static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ return 0;
+}
+
+static struct xfrm_mode xfrm4_transport_mode = {
+ .input = xfrm4_transport_input,
+ .output = xfrm4_transport_output,
+ .owner = THIS_MODULE,
+ .encap = XFRM_MODE_TRANSPORT,
+};
+
+static int __init xfrm4_transport_init(void)
+{
+ return xfrm_register_mode(&xfrm4_transport_mode, AF_INET);
+}
+
+static void __exit xfrm4_transport_exit(void)
+{
+ int err;
+
+ err = xfrm_unregister_mode(&xfrm4_transport_mode, AF_INET);
+ BUG_ON(err);
+}
+
+module_init(xfrm4_transport_init);
+module_exit(xfrm4_transport_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TRANSPORT);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
new file mode 100644
--- /dev/null
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -0,0 +1,125 @@
+/*
+ * xfrm4_mode_tunnel.c - Tunnel mode encapsulation for IPv4.
+ *
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/dst.h>
+#include <net/inet_ecn.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+
+static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
+{
+ struct iphdr *outer_iph = skb->nh.iph;
+ struct iphdr *inner_iph = skb->h.ipiph;
+
+ if (INET_ECN_is_ce(outer_iph->tos))
+ IP_ECN_set_ce(inner_iph);
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401. The following fields
+ * in it shall be filled in by x->type->output:
+ * tot_len
+ * check
+ *
+ * On exit, skb->h will be set to the start of the payload to be processed
+ * by x->type->output and skb->nh will be set to the top IP header.
+ */
+static int xfrm4_tunnel_output(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb->dst;
+ struct xfrm_state *x = dst->xfrm;
+ struct iphdr *iph, *top_iph;
+ int flags;
+
+ iph = skb->nh.iph;
+ skb->h.ipiph = iph;
+
+ skb->nh.raw = skb_push(skb, x->props.header_len);
+ top_iph = skb->nh.iph;
+
+ top_iph->ihl = 5;
+ top_iph->version = 4;
+
+ /* DS disclosed */
+ top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos);
+
+ flags = x->props.flags;
+ if (flags & XFRM_STATE_NOECN)
+ IP_ECN_clear(top_iph);
+
+ top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
+ 0 : (iph->frag_off & htons(IP_DF));
+ if (!top_iph->frag_off)
+ __ip_select_ident(top_iph, dst->child, 0);
+
+ top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
+
+ top_iph->saddr = x->props.saddr.a4;
+ top_iph->daddr = x->id.daddr.a4;
+ top_iph->protocol = IPPROTO_IPIP;
+
+ memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
+ return 0;
+}
+
+static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct iphdr *iph = skb->nh.iph;
+ int err = -EINVAL;
+
+ if (iph->protocol != IPPROTO_IPIP)
+ goto out;
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ goto out;
+
+ if (skb_cloned(skb) &&
+ (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ goto out;
+
+ if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+ ipv4_copy_dscp(iph, skb->h.ipiph);
+ if (!(x->props.flags & XFRM_STATE_NOECN))
+ ipip_ecn_decapsulate(skb);
+ skb->mac.raw = memmove(skb->data - skb->mac_len,
+ skb->mac.raw, skb->mac_len);
+ skb->nh.raw = skb->data;
+ memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
+ err = 0;
+
+out:
+ return err;
+}
+
+static struct xfrm_mode xfrm4_tunnel_mode = {
+ .input = xfrm4_tunnel_input,
+ .output = xfrm4_tunnel_output,
+ .owner = THIS_MODULE,
+ .encap = XFRM_MODE_TUNNEL,
+};
+
+static int __init xfrm4_tunnel_init(void)
+{
+ return xfrm_register_mode(&xfrm4_tunnel_mode, AF_INET);
+}
+
+static void __exit xfrm4_tunnel_exit(void)
+{
+ int err;
+
+ err = xfrm_unregister_mode(&xfrm4_tunnel_mode, AF_INET);
+ BUG_ON(err);
+}
+
+module_init(xfrm4_tunnel_init);
+module_exit(xfrm4_tunnel_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TUNNEL);
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -12,67 +12,10 @@
#include <linux/skbuff.h>
#include <linux/spinlock.h>
#include <linux/netfilter_ipv4.h>
-#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/icmp.h>
-/* Add encapsulation header.
- *
- * In transport mode, the IP header will be moved forward to make space
- * for the encapsulation header.
- *
- * In tunnel mode, the top IP header will be constructed per RFC 2401.
- * The following fields in it shall be filled in by x->type->output:
- * tot_len
- * check
- *
- * On exit, skb->h will be set to the start of the payload to be processed
- * by x->type->output and skb->nh will be set to the top IP header.
- */
-static void xfrm4_encap(struct sk_buff *skb)
-{
- struct dst_entry *dst = skb->dst;
- struct xfrm_state *x = dst->xfrm;
- struct iphdr *iph, *top_iph;
- int flags;
-
- iph = skb->nh.iph;
- skb->h.ipiph = iph;
-
- skb->nh.raw = skb_push(skb, x->props.header_len);
- top_iph = skb->nh.iph;
-
- if (!x->props.mode) {
- skb->h.raw += iph->ihl*4;
- memmove(top_iph, iph, iph->ihl*4);
- return;
- }
-
- top_iph->ihl = 5;
- top_iph->version = 4;
-
- /* DS disclosed */
- top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos);
-
- flags = x->props.flags;
- if (flags & XFRM_STATE_NOECN)
- IP_ECN_clear(top_iph);
-
- top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
- 0 : (iph->frag_off & htons(IP_DF));
- if (!top_iph->frag_off)
- __ip_select_ident(top_iph, dst->child, 0);
-
- top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
-
- top_iph->saddr = x->props.saddr.a4;
- top_iph->daddr = x->id.daddr.a4;
- top_iph->protocol = IPPROTO_IPIP;
-
- memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
-}
-
static int xfrm4_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
@@ -121,7 +64,9 @@ static int xfrm4_output_one(struct sk_bu
if (err)
goto error;
- xfrm4_encap(skb);
+ err = x->mode->output(skb);
+ if (err)
+ goto error;
err = x->type->output(x, skb);
if (err)
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -106,6 +106,26 @@ config INET6_TUNNEL
tristate
default n
+config INET6_XFRM_MODE_TRANSPORT
+ tristate "IPv6: IPsec transport mode"
+ depends on IPV6
+ default IPV6
+ select XFRM
+ ---help---
+ Support for IPsec transport mode.
+
+ If unsure, say Y.
+
+config INET6_XFRM_MODE_TUNNEL
+ tristate "IPv6: IPsec tunnel mode"
+ depends on IPV6
+ default IPV6
+ select XFRM
+ ---help---
+ Support for IPsec tunnel mode.
+
+ If unsure, say Y.
+
config IPV6_TUNNEL
tristate "IPv6: IPv6-in-IPv6 tunnel"
select INET6_TUNNEL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -20,6 +20,8 @@ obj-$(CONFIG_INET6_ESP) += esp6.o
obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o
obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o
obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o
+obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o
+obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o
obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -39,6 +39,7 @@
#include <linux/in6.h>
#include <linux/tcp.h>
#include <linux/route.h>
+#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -488,6 +489,7 @@ int ip6_find_1stfragopt(struct sk_buff *
return offset;
}
+EXPORT_SYMBOL_GPL(ip6_find_1stfragopt);
static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -13,21 +13,9 @@
#include <linux/string.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
-#include <net/ip.h>
#include <net/ipv6.h>
#include <net/xfrm.h>
-static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
-{
- struct ipv6hdr *outer_iph = skb->nh.ipv6h;
- struct ipv6hdr *inner_iph = skb->h.ipv6h;
-
- if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
- IP6_ECN_set_ce(inner_iph);
-}
-
int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi)
{
int err;
@@ -81,21 +69,10 @@ int xfrm6_rcv_spi(struct sk_buff *skb, u
xfrm_vec[xfrm_nr++] = x;
+ if (x->mode->input(x, skb))
+ goto drop;
+
if (x->props.mode) { /* XXX */
- if (nexthdr != IPPROTO_IPV6)
- goto drop;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- goto drop;
- if (skb_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
- goto drop;
- if (x->props.flags & XFRM_STATE_DECAP_DSCP)
- ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h);
- if (!(x->props.flags & XFRM_STATE_NOECN))
- ipip6_ecn_decapsulate(skb);
- skb->mac.raw = memmove(skb->data - skb->mac_len,
- skb->mac.raw, skb->mac_len);
- skb->nh.raw = skb->data;
decaps = 1;
break;
}
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
new file mode 100644
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -0,0 +1,73 @@
+/*
+ * xfrm6_mode_transport.c - Transport mode encapsulation for IPv6.
+ *
+ * Copyright (C) 2002 USAGI/WIDE Project
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/dst.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+
+/* Add encapsulation header.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the encapsulation header.
+ *
+ * On exit, skb->h will be set to the start of the encapsulation header to be
+ * filled in by x->type->output and skb->nh will be set to the nextheader field
+ * of the extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header. The value of skb->data will always
+ * point to the top IP header.
+ */
+static int xfrm6_transport_output(struct sk_buff *skb)
+{
+ struct xfrm_state *x = skb->dst->xfrm;
+ struct ipv6hdr *iph;
+ u8 *prevhdr;
+ int hdr_len;
+
+ skb_push(skb, x->props.header_len);
+ iph = skb->nh.ipv6h;
+
+ hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
+ skb->nh.raw = prevhdr - x->props.header_len;
+ skb->h.raw = skb->data + hdr_len;
+ memmove(skb->data, iph, hdr_len);
+ return 0;
+}
+
+static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ return 0;
+}
+
+static struct xfrm_mode xfrm6_transport_mode = {
+ .input = xfrm6_transport_input,
+ .output = xfrm6_transport_output,
+ .owner = THIS_MODULE,
+ .encap = XFRM_MODE_TRANSPORT,
+};
+
+static int __init xfrm6_transport_init(void)
+{
+ return xfrm_register_mode(&xfrm6_transport_mode, AF_INET6);
+}
+
+static void __exit xfrm6_transport_exit(void)
+{
+ int err;
+
+ err = xfrm_unregister_mode(&xfrm6_transport_mode, AF_INET6);
+ BUG_ON(err);
+}
+
+module_init(xfrm6_transport_init);
+module_exit(xfrm6_transport_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TRANSPORT);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
new file mode 100644
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -0,0 +1,121 @@
+/*
+ * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6.
+ *
+ * Copyright (C) 2002 USAGI/WIDE Project
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/dsfield.h>
+#include <net/dst.h>
+#include <net/inet_ecn.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+
+static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
+{
+ struct ipv6hdr *outer_iph = skb->nh.ipv6h;
+ struct ipv6hdr *inner_iph = skb->h.ipv6h;
+
+ if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
+ IP6_ECN_set_ce(inner_iph);
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401. The following fields
+ * in it shall be filled in by x->type->output:
+ * payload_len
+ *
+ * On exit, skb->h will be set to the start of the encapsulation header to be
+ * filled in by x->type->output and skb->nh will be set to the nextheader field
+ * of the extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header. The value of skb->data will always
+ * point to the top IP header.
+ */
+static int xfrm6_tunnel_output(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb->dst;
+ struct xfrm_state *x = dst->xfrm;
+ struct ipv6hdr *iph, *top_iph;
+ int dsfield;
+
+ skb_push(skb, x->props.header_len);
+ iph = skb->nh.ipv6h;
+
+ skb->nh.raw = skb->data;
+ top_iph = skb->nh.ipv6h;
+ skb->nh.raw = &top_iph->nexthdr;
+ skb->h.ipv6h = top_iph + 1;
+
+ top_iph->version = 6;
+ top_iph->priority = iph->priority;
+ top_iph->flow_lbl[0] = iph->flow_lbl[0];
+ top_iph->flow_lbl[1] = iph->flow_lbl[1];
+ top_iph->flow_lbl[2] = iph->flow_lbl[2];
+ dsfield = ipv6_get_dsfield(top_iph);
+ dsfield = INET_ECN_encapsulate(dsfield, dsfield);
+ if (x->props.flags & XFRM_STATE_NOECN)
+ dsfield &= ~INET_ECN_MASK;
+ ipv6_change_dsfield(top_iph, 0, dsfield);
+ top_iph->nexthdr = IPPROTO_IPV6;
+ top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
+ ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
+ ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+ return 0;
+}
+
+static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ int err = -EINVAL;
+
+ if (skb->nh.raw[IP6CB(skb)->nhoff] != IPPROTO_IPV6)
+ goto out;
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ goto out;
+
+ if (skb_cloned(skb) &&
+ (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ goto out;
+
+ if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+ ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h);
+ if (!(x->props.flags & XFRM_STATE_NOECN))
+ ipip6_ecn_decapsulate(skb);
+ skb->mac.raw = memmove(skb->data - skb->mac_len,
+ skb->mac.raw, skb->mac_len);
+ skb->nh.raw = skb->data;
+ err = 0;
+
+out:
+ return err;
+}
+
+static struct xfrm_mode xfrm6_tunnel_mode = {
+ .input = xfrm6_tunnel_input,
+ .output = xfrm6_tunnel_output,
+ .owner = THIS_MODULE,
+ .encap = XFRM_MODE_TUNNEL,
+};
+
+static int __init xfrm6_tunnel_init(void)
+{
+ return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6);
+}
+
+static void __exit xfrm6_tunnel_exit(void)
+{
+ int err;
+
+ err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6);
+ BUG_ON(err);
+}
+
+module_init(xfrm6_tunnel_init);
+module_exit(xfrm6_tunnel_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -14,68 +14,9 @@
#include <linux/spinlock.h>
#include <linux/icmpv6.h>
#include <linux/netfilter_ipv6.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
#include <net/ipv6.h>
#include <net/xfrm.h>
-/* Add encapsulation header.
- *
- * In transport mode, the IP header and mutable extension headers will be moved
- * forward to make space for the encapsulation header.
- *
- * In tunnel mode, the top IP header will be constructed per RFC 2401.
- * The following fields in it shall be filled in by x->type->output:
- * payload_len
- *
- * On exit, skb->h will be set to the start of the encapsulation header to be
- * filled in by x->type->output and skb->nh will be set to the nextheader field
- * of the extension header directly preceding the encapsulation header, or in
- * its absence, that of the top IP header. The value of skb->data will always
- * point to the top IP header.
- */
-static void xfrm6_encap(struct sk_buff *skb)
-{
- struct dst_entry *dst = skb->dst;
- struct xfrm_state *x = dst->xfrm;
- struct ipv6hdr *iph, *top_iph;
- int dsfield;
-
- skb_push(skb, x->props.header_len);
- iph = skb->nh.ipv6h;
-
- if (!x->props.mode) {
- u8 *prevhdr;
- int hdr_len;
-
- hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
- skb->nh.raw = prevhdr - x->props.header_len;
- skb->h.raw = skb->data + hdr_len;
- memmove(skb->data, iph, hdr_len);
- return;
- }
-
- skb->nh.raw = skb->data;
- top_iph = skb->nh.ipv6h;
- skb->nh.raw = &top_iph->nexthdr;
- skb->h.ipv6h = top_iph + 1;
-
- top_iph->version = 6;
- top_iph->priority = iph->priority;
- top_iph->flow_lbl[0] = iph->flow_lbl[0];
- top_iph->flow_lbl[1] = iph->flow_lbl[1];
- top_iph->flow_lbl[2] = iph->flow_lbl[2];
- dsfield = ipv6_get_dsfield(top_iph);
- dsfield = INET_ECN_encapsulate(dsfield, dsfield);
- if (x->props.flags & XFRM_STATE_NOECN)
- dsfield &= ~INET_ECN_MASK;
- ipv6_change_dsfield(top_iph, 0, dsfield);
- top_iph->nexthdr = IPPROTO_IPV6;
- top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
- ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
- ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
-}
-
static int xfrm6_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
@@ -118,7 +59,9 @@ static int xfrm6_output_one(struct sk_bu
if (err)
goto error;
- xfrm6_encap(skb);
+ err = x->mode->output(skb);
+ if (err)
+ goto error;
err = x->type->output(x, skb);
if (err)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -138,6 +138,76 @@ void xfrm_put_type(struct xfrm_type *typ
module_put(type->owner);
}
+int xfrm_register_mode(struct xfrm_mode *mode, int family)
+{
+ struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family);
+ struct xfrm_mode **modemap;
+ int err = 0;
+
+ if (unlikely(afinfo == NULL))
+ return -EAFNOSUPPORT;
+ modemap = afinfo->mode_map;
+
+ if (likely(modemap[mode->encap] == NULL))
+ modemap[mode->encap] = mode;
+ else
+ err = -EEXIST;
+ xfrm_policy_unlock_afinfo(afinfo);
+ return err;
+}
+EXPORT_SYMBOL(xfrm_register_mode);
+
+int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
+{
+ struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family);
+ struct xfrm_mode **modemap;
+ int err = 0;
+
+ if (unlikely(afinfo == NULL))
+ return -EAFNOSUPPORT;
+ modemap = afinfo->mode_map;
+
+ if (unlikely(modemap[mode->encap] != mode))
+ err = -ENOENT;
+ else
+ modemap[mode->encap] = NULL;
+ xfrm_policy_unlock_afinfo(afinfo);
+ return err;
+}
+EXPORT_SYMBOL(xfrm_unregister_mode);
+
+struct xfrm_mode *xfrm_get_mode(int encap, int family)
+{
+ struct xfrm_policy_afinfo *afinfo;
+ struct xfrm_mode **modemap;
+ struct xfrm_mode *mode;
+ int modload_attempted = 0;
+
+retry:
+ afinfo = xfrm_policy_get_afinfo(family);
+ if (unlikely(afinfo == NULL))
+ return NULL;
+ modemap = afinfo->mode_map;
+
+ mode = modemap[encap];
+ if (unlikely(mode && !try_module_get(mode->owner)))
+ mode = NULL;
+ if (!mode && !modload_attempted) {
+ xfrm_policy_put_afinfo(afinfo);
+ request_module("xfrm-mode-%d-%d", family, encap);
+ modload_attempted = 1;
+ goto retry;
+ }
+
+ xfrm_policy_put_afinfo(afinfo);
+ return mode;
+}
+
+void xfrm_put_mode(struct xfrm_mode *mode)
+{
+ module_put(mode->owner);
+}
+
static inline unsigned long make_jiffies(long secs)
{
if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -77,6 +77,8 @@ static void xfrm_state_gc_destroy(struct
kfree(x->ealg);
kfree(x->calg);
kfree(x->encap);
+ if (x->mode)
+ xfrm_put_mode(x->mode);
if (x->type) {
x->type->destructor(x);
xfrm_put_type(x->type);
@@ -1193,6 +1195,10 @@ int xfrm_init_state(struct xfrm_state *x
if (err)
goto error;
+ x->mode = xfrm_get_mode(x->props.mode, family);
+ if (x->mode == NULL)
+ goto error;
+
x->km.state = XFRM_STATE_VALID;
error:
^ permalink raw reply [flat|nested] 7+ messages in thread* [RFC 3/3] [IPSEC]: Abstract out transport mode input code
2006-05-06 11:20 ` [RFC 0/3] [IPSEC]: Add xfrm_mode support Herbert Xu
2006-05-06 11:21 ` [RFC 1/3] [IPSEC] xfrm: Undo afinfo lock proliferation Herbert Xu
2006-05-06 11:21 ` [RFC 2/3] [IPSEC] xfrm: Abstract out encapsulation modes Herbert Xu
@ 2006-05-06 11:24 ` Herbert Xu
2006-05-10 20:54 ` [RFC 0/3] [IPSEC]: Add xfrm_mode support David S. Miller
3 siblings, 0 replies; 7+ messages in thread
From: Herbert Xu @ 2006-05-06 11:24 UTC (permalink / raw)
To: Miika Komu; +Cc: Diego Beltrami, David S. Miller, netdev
[-- Attachment #1: Type: text/plain, Size: 561 bytes --]
Hi:
This patch is totally untested but shows how we can use xfrm_mode to
remove unnecessary code sharing between modes that in fact end up
slowing things down. In particular, notice how we've eliminated a
double IP header copying for tunnel mode which is in fact the common
case.
I need to finish it for IPv6 and actually test this one :)
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
[-- Attachment #2: p3.patch --]
[-- Type: text/plain, Size: 3551 bytes --]
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index e2e4771..30524b9 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -172,11 +172,8 @@
}
}
((struct iphdr*)work_buf)->protocol = ah->nexthdr;
- skb->nh.raw = skb_pull(skb, ah_hlen);
- memcpy(skb->nh.raw, work_buf, iph->ihl*4);
- skb->nh.iph->tot_len = htons(skb->len);
- skb_pull(skb, skb->nh.iph->ihl*4);
- skb->h.raw = skb->data;
+ skb->h.raw = memcpy(skb->nh.raw, work_buf, iph->ihl * 4) + ah_hlen;
+ __skb_pull(skb, ah_hlen + iph->ihl * 4);
return 0;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 9d1881c..451803e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -143,10 +143,8 @@
int alen = esp->auth.icv_trunc_len;
int elen = skb->len - sizeof(struct ip_esp_hdr) - esp->conf.ivlen - alen;
int nfrags;
- int encap_len = 0;
u8 nexthdr[2];
struct scatterlist *sg;
- u8 workbuf[60];
int padlen;
if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr)))
@@ -209,7 +207,6 @@
struct udphdr *uh;
uh = (struct udphdr *)(iph + 1);
- encap_len = (void*)esph - (void*)uh;
/*
* 1) if the NAT-T peer's IP or port changed then
@@ -246,11 +243,9 @@
iph->protocol = nexthdr[1];
pskb_trim(skb, skb->len - alen - padlen - 2);
- memcpy(workbuf, skb->nh.raw, iph->ihl*4);
- skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
- skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
- memcpy(skb->nh.raw, workbuf, iph->ihl*4);
- skb->nh.iph->tot_len = htons(skb->len);
+ skb->h.raw = __skb_pull(skb,
+ sizeof(struct ip_esp_hdr) + esp->conf.ivlen) -
+ iph->ihl * 4;
return 0;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index cd810f4..704937b 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -45,7 +45,6 @@
static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
{
int err, plen, dlen;
- struct iphdr *iph;
struct ipcomp_data *ipcd = x->data;
u8 *start, *scratch;
struct crypto_tfm *tfm;
@@ -74,8 +73,6 @@
skb_put(skb, dlen - plen);
memcpy(skb->data, scratch, dlen);
- iph = skb->nh.iph;
- iph->tot_len = htons(dlen + iph->ihl * 4);
out:
put_cpu();
return err;
@@ -108,9 +105,8 @@
skb->nh.raw += sizeof(struct ip_comp_hdr);
memcpy(skb->nh.raw, &tmp_iph, tmp_iph.iph.ihl * 4);
iph = skb->nh.iph;
- iph->tot_len = htons(ntohs(iph->tot_len) - sizeof(struct ip_comp_hdr));
iph->protocol = nexthdr;
- skb->h.raw = skb->data;
+ skb->h.raw = skb->nh.raw;
err = ipcomp_decompress(x, skb);
out:
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index e46d9a4..c2e507e 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -40,6 +40,11 @@
static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
+ if (skb->h.raw != skb->nh.raw)
+ skb->nh.raw = memmove(skb->h.raw, skb->nh.raw,
+ skb->nh.iph->ihl * 4);
+ skb->nh.iph->tot_len = htons(skb->len);
+ skb->h.raw = skb->data;
return 0;
}
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index f8d880b..a304d1d 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -73,9 +73,11 @@
static int xfrm4_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct iphdr *iph = skb->nh.iph;
+ struct iphdr *iph;
int err = -EINVAL;
+ skb->nh.raw = skb->data;
+ iph = skb->nh.iph;
if (iph->protocol != IPPROTO_IPIP)
goto out;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
^ permalink raw reply related [flat|nested] 7+ messages in thread