Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2017-08-21

1) Support RX checksum with IPsec crypto offload for esp4/esp6.
   From Ilan Tayari.

2) Fixup IPv6 checksums when doing IPsec crypto offload.
   From Yossi Kuperman.

3) Auto load the xfrom offload modules if a user installs
   a SA that requests IPsec offload. From Ilan Tayari.

4) Clear RX offload informations in xfrm_input to not
   confuse the TX path with stale offload informations.
   From Ilan Tayari.

5) Allow IPsec GSO for local sockets if the crypto operation
   will be offloaded.

6) Support setting of an output mark to the xfrm_state.
   This mark can be used to to do the tunnel route lookup.
   From Lorenzo Colitti.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

16 files changed, 121 insertions, 37 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index afb4929d7232..9c7b70cce6d6 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -43,6 +43,8 @@
 	MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap))
 #define MODULE_ALIAS_XFRM_TYPE(family, proto) \
 	MODULE_ALIAS("xfrm-type-" __stringify(family) "-" __stringify(proto))
+#define MODULE_ALIAS_XFRM_OFFLOAD_TYPE(family, proto) \
+	MODULE_ALIAS("xfrm-offload-" __stringify(family) "-" __stringify(proto))
 
 #ifdef CONFIG_XFRM_STATISTICS
 #define XFRM_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.xfrm_statistics, field)
@@ -163,6 +165,7 @@ struct xfrm_state {
 		int		header_len;
 		int		trailer_len;
 		u32		extra_flags;
+		u32		output_mark;
 	} props;
 
 	struct xfrm_lifetime_cfg lft;
@@ -296,10 +299,12 @@ struct xfrm_policy_afinfo {
 	struct dst_entry	*(*dst_lookup)(struct net *net,
 					       int tos, int oif,
 					       const xfrm_address_t *saddr,
-					       const xfrm_address_t *daddr);
+					       const xfrm_address_t *daddr,
+					       u32 mark);
 	int			(*get_saddr)(struct net *net, int oif,
 					     xfrm_address_t *saddr,
-					     xfrm_address_t *daddr);
+					     xfrm_address_t *daddr,
+					     u32 mark);
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
@@ -1558,7 +1563,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 int xfrm_init_replay(struct xfrm_state *x);
 int xfrm_state_mtu(struct xfrm_state *x, int mtu);
-int __xfrm_init_state(struct xfrm_state *x, bool init_replay);
+int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
 int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
@@ -1638,7 +1643,7 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
 				    const xfrm_address_t *saddr,
 				    const xfrm_address_t *daddr,
-				    int family);
+				    int family, u32 mark);
 
 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
 
@@ -1856,6 +1861,20 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		       struct xfrm_user_offload *xuo);
 bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
 
+static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
+{
+	struct xfrm_state *x = dst->xfrm;
+
+	if (!x || !x->type_offload)
+		return false;
+
+	if (x->xso.offload_handle && (x->xso.dev == dst->path->dev) &&
+	    !dst->child->xfrm)
+		return true;
+
+	return false;
+}
+
 static inline void xfrm_dev_state_delete(struct xfrm_state *x)
 {
 	struct xfrm_state_offload *xso = &x->xso;
@@ -1898,6 +1917,11 @@ static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x
 {
 	return false;
 }
+
+static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
+{
+	return false;
+}
 #endif
 
 static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m)
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 2b384ff09fa0..5fe7370a2bef 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,6 +304,7 @@ enum xfrm_attr_type_t {
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
 	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
+	XFRMA_OUTPUT_MARK,	/* __u32 */
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)
diff --git a/net/core/sock.c b/net/core/sock.c
index 9ea988d25b0a..0f04d8bff607 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1776,7 +1776,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
 	sk->sk_route_caps &= ~sk->sk_route_nocaps;
 	if (sk_can_gso(sk)) {
-		if (dst->header_len) {
+		if (dst->header_len && !xfrm_dst_offload_ok(dst)) {
 			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
 		} else {
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0cbee0a666ff..741acd7b9646 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -510,7 +510,8 @@ int esp_input_done2(struct sk_buff *skb, int err)
 	int elen = skb->len - hlen;
 	int ihl;
 	u8 nexthdr[2];
-	int padlen;
+	int padlen, trimlen;
+	__wsum csumdiff;
 
 	if (!xo || (xo && !(xo->flags & CRYPTO_DONE)))
 		kfree(ESP_SKB_CB(skb)->tmp);
@@ -568,8 +569,15 @@ int esp_input_done2(struct sk_buff *skb, int err)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
-	pskb_trim(skb, skb->len - alen - padlen - 2);
-	__skb_pull(skb, hlen);
+	trimlen = alen + padlen + 2;
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0);
+		skb->csum = csum_block_sub(skb->csum, csumdiff,
+					   skb->len - trimlen);
+	}
+	pskb_trim(skb, skb->len - trimlen);
+
+	skb_pull_rcsum(skb, hlen);
 	if (x->props.mode == XFRM_MODE_TUNNEL)
 		skb_reset_transport_header(skb);
 	else
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index e0666016a764..aca1c85f0795 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -182,11 +182,13 @@ out:
 static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
+	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
 		return -EINVAL;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	if (!(xo->flags & CRYPTO_DONE))
+		skb->ip_summed = CHECKSUM_NONE;
 
 	return esp_input_done2(skb, 0);
 }
@@ -303,3 +305,4 @@ module_init(esp4_offload_init);
 module_exit(esp4_offload_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
+MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 4aefb149fe0a..d7bf0b041885 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -20,7 +20,8 @@
 static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 					    int tos, int oif,
 					    const xfrm_address_t *saddr,
-					    const xfrm_address_t *daddr)
+					    const xfrm_address_t *daddr,
+					    u32 mark)
 {
 	struct rtable *rt;
 
@@ -28,6 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 	fl4->daddr = daddr->a4;
 	fl4->flowi4_tos = tos;
 	fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
+	fl4->flowi4_mark = mark;
 	if (saddr)
 		fl4->saddr = saddr->a4;
 
@@ -42,20 +44,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
 
 static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
 					  const xfrm_address_t *saddr,
-					  const xfrm_address_t *daddr)
+					  const xfrm_address_t *daddr,
+					  u32 mark)
 {
 	struct flowi4 fl4;
 
-	return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr);
+	return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark);
 }
 
 static int xfrm4_get_saddr(struct net *net, int oif,
-			   xfrm_address_t *saddr, xfrm_address_t *daddr)
+			   xfrm_address_t *saddr, xfrm_address_t *daddr,
+			   u32 mark)
 {
 	struct dst_entry *dst;
 	struct flowi4 fl4;
 
-	dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr);
+	dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark);
 	if (IS_ERR(dst))
 		return -EHOSTUNREACH;
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9ed35473dcb5..74bde202eb9a 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -470,7 +470,8 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
 	int elen = skb->len - hlen;
 	int hdr_len = skb_network_header_len(skb);
-	int padlen;
+	int padlen, trimlen;
+	__wsum csumdiff;
 	u8 nexthdr[2];
 
 	if (!xo || (xo && !(xo->flags & CRYPTO_DONE)))
@@ -492,8 +493,17 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 
 	/* ... check padding bits here. Silly. :-) */
 
-	pskb_trim(skb, skb->len - alen - padlen - 2);
-	__skb_pull(skb, hlen);
+	trimlen = alen + padlen + 2;
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		skb_postpull_rcsum(skb, skb_network_header(skb),
+				   skb_network_header_len(skb));
+		csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0);
+		skb->csum = csum_block_sub(skb->csum, csumdiff,
+					   skb->len - trimlen);
+	}
+	pskb_trim(skb, skb->len - trimlen);
+
+	skb_pull_rcsum(skb, hlen);
 	if (x->props.mode == XFRM_MODE_TUNNEL)
 		skb_reset_transport_header(skb);
 	else
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index f02f131f6435..8d4e2ba9163d 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -209,11 +209,13 @@ out:
 static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
+	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead)))
 		return -EINVAL;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	if (!(xo->flags & CRYPTO_DONE))
+		skb->ip_summed = CHECKSUM_NONE;
 
 	return esp6_input_done2(skb, 0);
 }
@@ -332,3 +334,4 @@ module_init(esp6_offload_init);
 module_exit(esp6_offload_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
+MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET6, XFRM_PROTO_ESP);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 3ef5d913e7a3..f95943a13abc 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -34,6 +34,7 @@ EXPORT_SYMBOL(xfrm6_rcv_spi);
 int xfrm6_transport_finish(struct sk_buff *skb, int async)
 {
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	int nhlen = skb->data - skb_network_header(skb);
 
 	skb_network_header(skb)[IP6CB(skb)->nhoff] =
 		XFRM_MODE_SKB_CB(skb)->protocol;
@@ -43,8 +44,9 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 		return 1;
 #endif
 
-	__skb_push(skb, skb->data - skb_network_header(skb));
+	__skb_push(skb, nhlen);
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+	skb_postpush_rcsum(skb, skb_network_header(skb), nhlen);
 
 	if (xo && (xo->flags & XFRM_GRO)) {
 		skb_mac_header_rebuild(skb);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f44b25a48478..11d1314ab6c5 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -27,7 +27,8 @@
 
 static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
 					  const xfrm_address_t *saddr,
-					  const xfrm_address_t *daddr)
+					  const xfrm_address_t *daddr,
+					  u32 mark)
 {
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -36,6 +37,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+	fl6.flowi6_mark = mark;
 	memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
 	if (saddr)
 		memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
@@ -52,12 +54,13 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
 }
 
 static int xfrm6_get_saddr(struct net *net, int oif,
-			   xfrm_address_t *saddr, xfrm_address_t *daddr)
+			   xfrm_address_t *saddr, xfrm_address_t *daddr,
+			   u32 mark)
 {
 	struct dst_entry *dst;
 	struct net_device *dev;
 
-	dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr);
+	dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark);
 	if (IS_ERR(dst))
 		return -EHOSTUNREACH;
 
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 5cd7a244e88d..acf00104ef31 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -63,7 +63,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	xfrm_address_t *daddr;
 
 	if (!x->type_offload)
-		return 0;
+		return -EINVAL;
 
 	/* We don't yet support UDP encapsulation, TFC padding and ESN. */
 	if (x->encap || x->tfcpad || (x->props.flags & XFRM_STATE_ESN))
@@ -79,7 +79,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 			daddr = &x->props.saddr;
 		}
 
-		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, x->props.family);
+		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr,
+					x->props.family, x->props.output_mark);
 		if (IS_ERR(dst))
 			return 0;
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 923205e279f7..f07eec59dcae 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -424,6 +424,7 @@ resume:
 	nf_reset(skb);
 
 	if (decaps) {
+		skb->sp->olen = 0;
 		skb_dst_drop(skb);
 		gro_cells_receive(&gro_cells, skb);
 		return 0;
@@ -434,6 +435,7 @@ resume:
 
 		err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
 		if (xfrm_gro) {
+			skb->sp->olen = 0;
 			skb_dst_drop(skb);
 			gro_cells_receive(&gro_cells, skb);
 			return err;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 8c0b6722aaa8..31a2e6d34dba 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,6 +66,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 			goto error_nolock;
 		}
 
+		if (x->props.output_mark)
+			skb->mark = x->props.output_mark;
+
 		err = x->outer_mode->output(x, skb);
 		if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8da428f56aec..cc0d783ccbad 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -122,7 +122,7 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa
 struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
 				    const xfrm_address_t *saddr,
 				    const xfrm_address_t *daddr,
-				    int family)
+				    int family, u32 mark)
 {
 	const struct xfrm_policy_afinfo *afinfo;
 	struct dst_entry *dst;
@@ -131,7 +131,7 @@ struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
 	if (unlikely(afinfo == NULL))
 		return ERR_PTR(-EAFNOSUPPORT);
 
-	dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr);
+	dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark);
 
 	rcu_read_unlock();
 
@@ -143,7 +143,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
 						int tos, int oif,
 						xfrm_address_t *prev_saddr,
 						xfrm_address_t *prev_daddr,
-						int family)
+						int family, u32 mark)
 {
 	struct net *net = xs_net(x);
 	xfrm_address_t *saddr = &x->props.saddr;
@@ -159,7 +159,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
 		daddr = x->coaddr;
 	}
 
-	dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family);
+	dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark);
 
 	if (!IS_ERR(dst)) {
 		if (prev_saddr != saddr)
@@ -1340,14 +1340,14 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
 
 static int
 xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
-	       xfrm_address_t *remote, unsigned short family)
+	       xfrm_address_t *remote, unsigned short family, u32 mark)
 {
 	int err;
 	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
 
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
-	err = afinfo->get_saddr(net, oif, local, remote);
+	err = afinfo->get_saddr(net, oif, local, remote, mark);
 	rcu_read_unlock();
 	return err;
 }
@@ -1378,7 +1378,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 			if (xfrm_addr_any(local, tmpl->encap_family)) {
 				error = xfrm_get_saddr(net, fl->flowi_oif,
 						       &tmp, remote,
-						       tmpl->encap_family);
+						       tmpl->encap_family, 0);
 				if (error)
 					goto fail;
 				local = &tmp;
@@ -1598,7 +1598,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
 			family = xfrm[i]->props.family;
 			dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
-					      &saddr, &daddr, family);
+					      &saddr, &daddr, family,
+					      xfrm[i]->props.output_mark);
 			err = PTR_ERR(dst);
 			if (IS_ERR(dst))
 				goto put_states;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 82cbbce69b79..a41e2ef789c0 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -296,12 +296,14 @@ int xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
 }
 EXPORT_SYMBOL(xfrm_unregister_type_offload);
 
-static const struct xfrm_type_offload *xfrm_get_type_offload(u8 proto, unsigned short family)
+static const struct xfrm_type_offload *
+xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load)
 {
 	struct xfrm_state_afinfo *afinfo;
 	const struct xfrm_type_offload **typemap;
 	const struct xfrm_type_offload *type;
 
+retry:
 	afinfo = xfrm_state_get_afinfo(family);
 	if (unlikely(afinfo == NULL))
 		return NULL;
@@ -311,6 +313,12 @@ static const struct xfrm_type_offload *xfrm_get_type_offload(u8 proto, unsigned
 	if ((type && !try_module_get(type->owner)))
 		type = NULL;
 
+	if (!type && try_load) {
+		request_module("xfrm-offload-%d-%d", family, proto);
+		try_load = 0;
+		goto retry;
+	}
+
 	rcu_read_unlock();
 	return type;
 }
@@ -2165,7 +2173,7 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	return mtu - x->props.header_len;
 }
 
-int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
+int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {
 	struct xfrm_state_afinfo *afinfo;
 	struct xfrm_mode *inner_mode;
@@ -2230,7 +2238,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
 	if (x->type == NULL)
 		goto error;
 
-	x->type_offload = xfrm_get_type_offload(x->id.proto, family);
+	x->type_offload = xfrm_get_type_offload(x->id.proto, family, offload);
 
 	err = x->type->init_state(x);
 	if (err)
@@ -2258,7 +2266,7 @@ EXPORT_SYMBOL(__xfrm_init_state);
 
 int xfrm_init_state(struct xfrm_state *x)
 {
-	return __xfrm_init_state(x, true);
+	return __xfrm_init_state(x, true, false);
 }
 
 EXPORT_SYMBOL(xfrm_init_state);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1b539b7dcfab..cc3268d814b4 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -584,7 +584,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	xfrm_mark_get(attrs, &x->mark);
 
-	err = __xfrm_init_state(x, false);
+	if (attrs[XFRMA_OUTPUT_MARK])
+		x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]);
+
+	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
 	if (err)
 		goto error;
 
@@ -899,6 +902,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 		goto out;
 	if (x->security)
 		ret = copy_sec_ctx(x->security, skb);
+	if (x->props.output_mark) {
+		ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark);
+		if (ret)
+			goto out;
+	}
 out:
 	return ret;
 }
@@ -2454,6 +2462,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_PROTO]		= { .type = NLA_U8 },
 	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
 	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_OUTPUT_MARK]	= { .len = NLA_U32 },
 };
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2673,6 +2682,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
 		l += nla_total_size(sizeof(x->props.extra_flags));
 	if (x->xso.dev)
 		 l += nla_total_size(sizeof(x->xso));
+	if (x->props.output_mark)
+		l += nla_total_size(sizeof(x->props.output_mark));
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
 	l += nla_total_size_64bit(sizeof(u64));