xfrm: add mode_cbs module functionality

Add a set of callbacks xfrm_mode_cbs to xfrm_state. These callbacks
enable the addition of new xfrm modes, such as IP-TFS to be defined
in modules.

Signed-off-by: Christian Hopps <[email protected]>
Tested-by: Antony Antony <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>

Author: choppsv1

include/net/xfrm.h

@@ -213,6 +213,7 @@ struct xfrm_state {
 		u16		family;
 		xfrm_address_t	saddr;
 		int		header_len;
+		int		enc_hdr_len;
 		int		trailer_len;
 		u32		extra_flags;
 		struct xfrm_mark	smark;
@@ -303,6 +304,9 @@ struct xfrm_state {
 	 * interpreted by xfrm_type methods. */
 	void			*data;
 	u8			dir;
+
+	const struct xfrm_mode_cbs	*mode_cbs;
+	void				*mode_data;
 };
 
 static inline struct net *xs_net(struct xfrm_state *x)
@@ -460,6 +464,45 @@ struct xfrm_type_offload {
 int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
+/**
+ * struct xfrm_mode_cbs - XFRM mode callbacks
+ * @owner: module owner or NULL
+ * @init_state: Add/init mode specific state in `xfrm_state *x`
+ * @clone_state: Copy mode specific values from `orig` to new state `x`
+ * @destroy_state: Cleanup mode specific state from `xfrm_state *x`
+ * @user_init: Process mode specific netlink attributes from user
+ * @copy_to_user: Add netlink attributes to `attrs` based on state in `x`
+ * @sa_len: Return space required to store mode specific netlink attributes
+ * @get_inner_mtu: Return avail payload space after removing encap overhead
+ * @input: Process received packet from SA using mode
+ * @output: Output given packet using mode
+ * @prepare_output: Add mode specific encapsulation to packet in skb. On return
+ *	`transport_header` should point at ESP header, `network_header` should
+ *	point at outer IP header and `mac_header` should opint at the
+ *	protocol/nexthdr field of the outer IP.
+ *
+ * One should examine and understand the specific uses of these callbacks in
+ * xfrm for further detail on how and when these functions are called. RTSL.
+ */
+struct xfrm_mode_cbs {
+	struct module	*owner;
+	int	(*init_state)(struct xfrm_state *x);
+	int	(*clone_state)(struct xfrm_state *x, struct xfrm_state *orig);
+	void	(*destroy_state)(struct xfrm_state *x);
+	int	(*user_init)(struct net *net, struct xfrm_state *x,
+			     struct nlattr **attrs,
+			     struct netlink_ext_ack *extack);
+	int	(*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb);
+	unsigned int (*sa_len)(const struct xfrm_state *x);
+	u32	(*get_inner_mtu)(struct xfrm_state *x, int outer_mtu);
+	int	(*input)(struct xfrm_state *x, struct sk_buff *skb);
+	int	(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	int	(*prepare_output)(struct xfrm_state *x, struct sk_buff *skb);
+};
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs);
+void xfrm_unregister_mode_cbs(u8 mode);
+
 static inline int xfrm_af2proto(unsigned int family)
 {
 	switch(family) {

net/xfrm/xfrm_device.c

@@ -42,7 +42,8 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
 		skb->transport_header = skb->network_header + hsize;
 
 	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + x->props.header_len);
+	pskb_pull(skb,
+		  skb->mac_len + x->props.header_len - x->props.enc_hdr_len);
 }
 
 static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb,

net/xfrm/xfrm_input.c

@@ -446,13 +446,20 @@ static int xfrm_inner_mode_input(struct xfrm_state *x,
 		WARN_ON_ONCE(1);
 		break;
 	default:
+		if (x->mode_cbs && x->mode_cbs->input)
+			return x->mode_cbs->input(x, skb);
+
 		WARN_ON_ONCE(1);
 		break;
 	}
 
 	return -EOPNOTSUPP;
 }
 
+/* NOTE: encap_type - In addition to the normal (non-negative) values for
+ * encap_type, a negative value of -1 or -2 can be used to resume/restart this
+ * function after a previous invocation early terminated for async operation.
+ */
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
 	const struct xfrm_state_afinfo *afinfo;
@@ -489,6 +496,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		family = x->props.family;
 
+		/* An encap_type of -2 indicates reconstructed inner packet */
+		if (encap_type == -2)
+			goto resume_decapped;
+
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
 			async = 1;
@@ -679,11 +690,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
 
-		if (xfrm_inner_mode_input(x, skb)) {
+		err = xfrm_inner_mode_input(x, skb);
+		if (err == -EINPROGRESS)
+			return 0;
+		else if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
 			goto drop;
 		}
-
+resume_decapped:
 		if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) {
 			decaps = 1;
 			break;

net/xfrm/xfrm_output.c

@@ -472,6 +472,8 @@ static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
 		WARN_ON_ONCE(1);
 		break;
 	default:
+		if (x->mode_cbs && x->mode_cbs->prepare_output)
+			return x->mode_cbs->prepare_output(x, skb);
 		WARN_ON_ONCE(1);
 		break;
 	}

net/xfrm/xfrm_policy.c

@@ -2748,13 +2748,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 
 		dst1->input = dst_discard;
 
-		rcu_read_lock();
-		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
-		if (likely(afinfo))
-			dst1->output = afinfo->output;
-		else
-			dst1->output = dst_discard_out;
-		rcu_read_unlock();
+		if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) {
+			dst1->output = xfrm[i]->mode_cbs->output;
+		} else {
+			rcu_read_lock();
+			afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+			if (likely(afinfo))
+				dst1->output = afinfo->output;
+			else
+				dst1->output = dst_discard_out;
+			rcu_read_unlock();
+		}
 
 		xdst_prev = xdst;
 

net/xfrm/xfrm_state.c

@@ -515,6 +515,60 @@ 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 +577,8 @@ 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 +738,7 @@ 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;
 }
@@ -1945,6 +2002,12 @@ 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:
@@ -2986,6 +3049,9 @@ 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 +3152,12 @@ 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;
 }

net/xfrm/xfrm_user.c

@@ -932,6 +932,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 			goto error;
 	}
 
+	if (x->mode_cbs && x->mode_cbs->user_init) {
+		err = x->mode_cbs->user_init(net, x, attrs, extack);
+		if (err)
+			goto error;
+	}
+
 	return x;
 
 error:
@@ -1347,6 +1353,10 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 		if (ret)
 			goto out;
 	}
+	if (x->mode_cbs && x->mode_cbs->copy_to_user)
+		ret = x->mode_cbs->copy_to_user(x, skb);
+	if (ret)
+		goto out;
 	if (x->mapping_maxage) {
 		ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage);
 		if (ret)
@@ -3606,6 +3616,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
 	if (x->nat_keepalive_interval)
 		l += nla_total_size(sizeof(x->nat_keepalive_interval));
 
+	if (x->mode_cbs && x->mode_cbs->sa_len)
+		l += x->mode_cbs->sa_len(x);
+
 	return l;
 }