xfrm: include mark in MIGRATE_STATE SA collision check

The SA lookup tuple is (daddr, spi, proto, family, mark), but the
EEXIST pre-check and the xfrm_state_insert() vs xfrm_state_add()
decision only considered daddr and family, ignoring mark.
A migration that only changes the mark inserts a duplicate SA tuple
into the hash tables.

The collision check is implemented as xfrm_state_mark_collides(),
which walks the SPI hash bucket for the target tuple and excludes the
state being migrated by pointer, rather than doing a separate
exact-match lookup followed by a wildcard lookup and comparing the
result against self.

Before:
root@west:~# ip xfrm state add src 10.1.1.1 dst 10.1.1.2 proto esp \
        spi 0x1000  reqid 100 mode tunnel aead "rfc4106(gcm(aes))" \
        0x1111111111111111111111111111111111111111 96 \
        mark 0x1 mask 0xff

root@west:~# ip xfrm state add src 10.1.1.1 dst 10.1.1.2 proto esp \
        spi 0x1000  reqid 100 mode tunnel aead "rfc4106(gcm(aes))" \
        0x1111111111111111111111111111111111111111 96 \
        mark 0x2 mask 0xff
root@west:~# ip xfrm state migrate dst 10.1.1.2 proto esp spi 0x1000 \
        mark 0x1 mask 0xff \
        new-dst 10.1.1.2 new-src 10.1.1.1 new-reqid 100 \
        new-mark 0x2 mask 0xff
ip x s
src 10.1.1.1 dst 10.1.1.2
    proto esp spi 0x00001000 reqid 100 mode tunnel
    replay-window 0
    mark 0x2/0xff
    aead rfc4106(gcm(aes)) 0x1111111111111111111111111111111111111111 96
    anti-replay context: seq 0x0, oseq 0x0, bitmap 0x00000000
src 10.1.1.1 dst 10.1.1.2
    proto esp spi 0x00001000 reqid 100 mode tunnel
    replay-window 0
    mark 0x2/0xff
    aead rfc4106(gcm(aes)) 0x1111111111111111111111111111111111111111 96
    anti-replay context: seq 0x0, oseq 0x0, bitmap 0x00000000
    sel src 0.0.0.0/0 dst 0.0.0.0/0

Notice two states with same mark 0x2/0xff.
After:

Error: New SA tuple already occupied.

Fixes: a9d155ea9b44 ("xfrm: add XFRM_MSG_MIGRATE_STATE for single SA migration")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Signed-off-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

3 files changed, 49 insertions, 12 deletions

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9e053388aa4b..26dd4b570588 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1751,6 +1751,10 @@ struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 struct xfrm_state *xfrm_state_lookup_exact(struct net *net, const struct xfrm_mark *mark,
 					   const xfrm_address_t *daddr, __be32 spi,
 					   u8 proto, unsigned short family);
+bool xfrm_state_mark_collides(struct net *net, u32 mark,
+			      const xfrm_address_t *daddr, __be32 spi,
+			      u8 proto, unsigned short family,
+			      const struct xfrm_state *self);
 #ifdef CONFIG_XFRM_SUB_POLICY
 void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
 		    unsigned short family);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f1e04df8d501..65663c7ba836 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2202,10 +2202,12 @@ int xfrm_state_migrate_install(const struct xfrm_state *x,
 			       struct netlink_ext_ack *extack)
 {
 	if (m->new_family == m->old_family &&
-	    xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
+	    xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family) &&
+	    xc->mark.v == x->mark.v && xc->mark.m == x->mark.m) {
 		/*
-		 * Care is needed when the destination address of the state is
-		 * to be updated as it is a part of triplet.
+		 * Care is needed when the destination address or mark of the
+		 * state is to be updated, as they are part of the lookup
+		 * triplet.
 		 */
 		xfrm_state_insert(xc);
 	} else {
@@ -2440,6 +2442,38 @@ xfrm_state_lookup_exact(struct net *net, const struct xfrm_mark *mark,
 }
 EXPORT_SYMBOL(xfrm_state_lookup_exact);
 
+/* True if some OTHER state at this tuple would wildcard-match "mark".
+ * Used by MIGRATE_STATE, which must exclude the state being migrated.
+ */
+bool xfrm_state_mark_collides(struct net *net, u32 mark,
+			      const xfrm_address_t *daddr, __be32 spi,
+			      u8 proto, unsigned short family,
+			      const struct xfrm_state *self)
+{
+	struct xfrm_hash_state_ptrs state_ptrs;
+	unsigned int h;
+	struct xfrm_state *x;
+	bool collides = false;
+
+	rcu_read_lock();
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+	h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs.hmask);
+
+	hlist_for_each_entry_rcu(x, state_ptrs.byspi + h, byspi) {
+		if (x != self && x->props.family == family &&
+		    x->id.spi == spi && x->id.proto == proto &&
+		    xfrm_addr_equal(&x->id.daddr, daddr, family) &&
+		    (mark & x->mark.m) == x->mark.v) {
+			collides = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return collides;
+}
+EXPORT_SYMBOL(xfrm_state_mark_collides);
+
 struct xfrm_state *
 xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
 	      u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr,
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 4de8c401eb44..a5fbe38839c4 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3476,15 +3476,14 @@ static int xfrm_do_migrate_state(struct sk_buff *skb, struct nlmsghdr *nlh,
 						       x->nat_keepalive_interval);
 
 	if (m.new_family != um->id.family ||
-	    !xfrm_addr_equal(&m.new_daddr, &um->id.daddr, um->id.family)) {
-		u32 new_mark_key = m.new_mark ? m.new_mark->v & m.new_mark->m :
-						m.old_mark.v & m.old_mark.m;
-		struct xfrm_state *x_new;
-
-		x_new = xfrm_state_lookup(net, new_mark_key, &m.new_daddr,
-					  um->id.spi, um->id.proto, m.new_family);
-		if (x_new) {
-			xfrm_state_put(x_new);
+	    !xfrm_addr_equal(&m.new_daddr, &um->id.daddr, um->id.family) ||
+	    (m.new_mark && (m.new_mark->v != x->mark.v ||
+			   m.new_mark->m != x->mark.m))) {
+		const struct xfrm_mark *new_mark = m.new_mark ? m.new_mark : &x->mark;
+
+		if (xfrm_state_mark_collides(net, new_mark->v & new_mark->m,
+					     &m.new_daddr, um->id.spi,
+					     um->id.proto, m.new_family, x)) {
 			NL_SET_ERR_MSG(extack, "New SA tuple already occupied");
 			err = -EEXIST;
 			goto out;