1 files changed, 155 insertions, 22 deletions

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 67ca7ac955a3..ad2202fa82f3 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -34,6 +34,8 @@
 
 #define xfrm_state_deref_prot(table, net) \
 	rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+#define xfrm_state_deref_check(table, net) \
+	rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
 
 static void xfrm_state_gc_task(struct work_struct *work);
 
@@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net,
 					 u32 reqid,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
 }
 
@@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net,
 					 const xfrm_address_t *saddr,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
 }
 
@@ -77,11 +83,15 @@ static inline unsigned int
 xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
 	      __be32 spi, u8 proto, unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
 }
 
 static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
 }
 
@@ -467,6 +477,11 @@ static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
 		.flags = XFRM_MODE_FLAG_TUNNEL,
 		.family = AF_INET,
 	},
+	[XFRM_MODE_IPTFS] = {
+		.encap = XFRM_MODE_IPTFS,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
 };
 
 static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
@@ -488,6 +503,11 @@ static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
 		.flags = XFRM_MODE_FLAG_TUNNEL,
 		.family = AF_INET6,
 	},
+	[XFRM_MODE_IPTFS] = {
+		.encap = XFRM_MODE_IPTFS,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
 };
 
 static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
@@ -515,6 +535,60 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 	return NULL;
 }
 
+static const struct xfrm_mode_cbs  __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX];
+static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock);
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs)
+{
+	if (mode >= XFRM_MODE_MAX)
+		return -EINVAL;
+
+	spin_lock_bh(&xfrm_mode_cbs_map_lock);
+	rcu_assign_pointer(xfrm_mode_cbs_map[mode], mode_cbs);
+	spin_unlock_bh(&xfrm_mode_cbs_map_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_register_mode_cbs);
+
+void xfrm_unregister_mode_cbs(u8 mode)
+{
+	if (mode >= XFRM_MODE_MAX)
+		return;
+
+	spin_lock_bh(&xfrm_mode_cbs_map_lock);
+	RCU_INIT_POINTER(xfrm_mode_cbs_map[mode], NULL);
+	spin_unlock_bh(&xfrm_mode_cbs_map_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_unregister_mode_cbs);
+
+static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode)
+{
+	const struct xfrm_mode_cbs *cbs;
+	bool try_load = true;
+
+	if (mode >= XFRM_MODE_MAX)
+		return NULL;
+
+retry:
+	rcu_read_lock();
+
+	cbs = rcu_dereference(xfrm_mode_cbs_map[mode]);
+	if (cbs && !try_module_get(cbs->owner))
+		cbs = NULL;
+
+	rcu_read_unlock();
+
+	if (mode == XFRM_MODE_IPTFS && !cbs && try_load) {
+		request_module("xfrm-iptfs");
+		try_load = false;
+		goto retry;
+	}
+
+	return cbs;
+}
+
 void xfrm_state_free(struct xfrm_state *x)
 {
 	kmem_cache_free(xfrm_state_cache, x);
@@ -523,6 +597,8 @@ EXPORT_SYMBOL(xfrm_state_free);
 
 static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
+	if (x->mode_cbs && x->mode_cbs->destroy_state)
+		x->mode_cbs->destroy_state(x);
 	hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
 	kfree(x->aead);
@@ -682,6 +758,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		x->replay_maxdiff = 0;
 		x->pcpu_num = UINT_MAX;
 		spin_lock_init(&x->lock);
+		x->mode_data = NULL;
 	}
 	return x;
 }
@@ -1041,16 +1118,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 	x->props.family = tmpl->encap_family;
 }
 
-static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+struct xfrm_hash_state_ptrs {
+	const struct hlist_head *bydst;
+	const struct hlist_head *bysrc;
+	const struct hlist_head *byspi;
+	unsigned int hmask;
+};
+
+static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs)
+{
+	unsigned int sequence;
+
+	do {
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+		ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net);
+		ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net);
+		ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net);
+		ptrs->hmask = net->xfrm.state_hmask;
+	} while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence));
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs,
+						  u32 mark,
 						  const xfrm_address_t *daddr,
 						  __be32 spi, u8 proto,
 						  unsigned short family,
 						  struct xfrm_dev_offload *xdo)
 {
-	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1084,15 +1183,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
 	return NULL;
 }
 
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs,
+					      u32 mark,
 					      const 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(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
 		    x->id.proto     != proto ||
@@ -1114,11 +1214,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 					   __be32 spi, u8 proto,
 					   unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct hlist_head *state_cache_input;
 	struct xfrm_state *x = NULL;
-	int cpu = get_cpu();
 
-	state_cache_input =  per_cpu_ptr(net->xfrm.state_cache_input, cpu);
+	state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
@@ -1135,7 +1235,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 		goto out;
 	}
 
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 
 	if (x && x->km.state == XFRM_STATE_VALID) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -1150,20 +1252,20 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 
 out:
 	rcu_read_unlock();
-	put_cpu();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_input_state_lookup);
 
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs,
+						     u32 mark,
 						     const xfrm_address_t *daddr,
 						     const xfrm_address_t *saddr,
 						     u8 proto, unsigned short family)
 {
-	unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+	unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+	hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) {
 		if (x->props.family != family ||
 		    x->id.proto     != proto ||
 		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -1183,14 +1285,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 static inline struct xfrm_state *
 __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xs_net(x);
 	u32 mark = x->mark.v & x->mark.m;
 
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
 	if (use_spi)
-		return __xfrm_state_lookup(net, mark, &x->id.daddr,
+		return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr,
 					   x->id.spi, x->id.proto, family);
 	else
-		return __xfrm_state_lookup_byaddr(net, mark,
+		return __xfrm_state_lookup_byaddr(&state_ptrs, mark,
 						  &x->id.daddr,
 						  &x->props.saddr,
 						  x->id.proto, family);
@@ -1264,6 +1369,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		unsigned short family, u32 if_id)
 {
 	static xfrm_address_t saddr_wildcard = { };
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xp_net(pol);
 	unsigned int h, h_wildcard;
 	struct xfrm_state *x, *x0, *to_put;
@@ -1328,8 +1434,10 @@ cached:
 	else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
 		WARN_ON(1);
 
-	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1362,8 +1470,9 @@ cached:
 	if (best || acquire_in_progress)
 		goto found;
 
-	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+	h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid,
+				     encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1401,7 +1510,7 @@ found:
 
 	if (!x && !error && !acquire_in_progress) {
 		if (tmpl->id.spi &&
-		    (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+		    (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
 						  tmpl->id.spi, tmpl->id.proto,
 						  encap_family,
 						  &pol->xdo)) != NULL) {
@@ -1945,6 +2054,12 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->new_mapping_sport = 0;
 	x->dir = orig->dir;
 
+	x->mode_cbs = orig->mode_cbs;
+	if (x->mode_cbs && x->mode_cbs->clone_state) {
+		if (x->mode_cbs->clone_state(x, orig))
+			goto error;
+	}
+
 	return x;
 
  error:
@@ -2180,10 +2295,13 @@ struct xfrm_state *
 xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
 		  u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	rcu_read_lock();
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 	rcu_read_unlock();
 	return x;
 }
@@ -2194,10 +2312,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 			 const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			 u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
@@ -2271,6 +2393,7 @@ static int __xfrm6_state_sort_cmp(const void *p)
 #endif
 	case XFRM_MODE_TUNNEL:
 	case XFRM_MODE_BEET:
+	case XFRM_MODE_IPTFS:
 		return 4;
 	}
 	return 5;
@@ -2297,6 +2420,7 @@ static int __xfrm6_tmpl_sort_cmp(const void *p)
 #endif
 	case XFRM_MODE_TUNNEL:
 	case XFRM_MODE_BEET:
+	case XFRM_MODE_IPTFS:
 		return 3;
 	}
 	return 4;
@@ -2986,6 +3110,9 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	case XFRM_MODE_TUNNEL:
 		break;
 	default:
+		if (x->mode_cbs && x->mode_cbs->get_inner_mtu)
+			return x->mode_cbs->get_inner_mtu(x, mtu);
+
 		WARN_ON_ONCE(1);
 		break;
 	}
@@ -3086,6 +3213,12 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload,
 		}
 	}
 
+	x->mode_cbs = xfrm_get_mode_cbs(x->props.mode);
+	if (x->mode_cbs) {
+		if (x->mode_cbs->init_state)
+			err = x->mode_cbs->init_state(x);
+		module_put(x->mode_cbs->owner);
+	}
 error:
 	return err;
 }