icmp: fix icmp_ndo_send address translation for reply direction

The icmp_ndo_send function was originally introduced to ensure proper
rate limiting when icmp_send is called by a network device driver,
where the packet's source address may have already been transformed
by SNAT.

However, the original implementation only considers the
IP_CT_DIR_ORIGINAL direction for SNAT and always replaced the packet's
source address with that of the original-direction tuple. This causes
two problems:

1. For SNAT:
   Reply-direction packets were incorrectly translated using the source
   address of the CT original direction, even though no translation is
   required.

2. For DNAT:
   Reply-direction packets were not handled at all. In DNAT, the original
   direction's destination is translated. Therefore, in the reply
   direction the source address must be set to the reply-direction
   source, so rate limiting works as intended.

Fix this by using the connection direction to select the correct tuple
for source address translation, and adjust the pre-checks to handle
reply-direction packets in case of DNAT.

Additionally, wrap the `ct->status` access in READ_ONCE(). This avoids
possible KCSAN reports about concurrent updates to `ct->status`.

Fixes: 0b41713b6066 ("icmp: introduce helper for nat'd source address in network device context")
Signed-off-by: Fabian Bläse <fabian@blaese.de>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 8 insertions, 4 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2ffe73ea644f..c48c572f024d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -799,11 +799,12 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	struct sk_buff *cloned_skb = NULL;
 	struct ip_options opts = { 0 };
 	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_dir dir;
 	struct nf_conn *ct;
 	__be32 orig_ip;
 
 	ct = nf_ct_get(skb_in, &ctinfo);
-	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+	if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) {
 		__icmp_send(skb_in, type, code, info, &opts);
 		return;
 	}
@@ -818,7 +819,8 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		goto out;
 
 	orig_ip = ip_hdr(skb_in)->saddr;
-	ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
+	dir = CTINFO2DIR(ctinfo);
+	ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip;
 	__icmp_send(skb_in, type, code, info, &opts);
 	ip_hdr(skb_in)->saddr = orig_ip;
 out:
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 9e3574880cb0..233914b63bdb 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -54,11 +54,12 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
 	struct inet6_skb_parm parm = { 0 };
 	struct sk_buff *cloned_skb = NULL;
 	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_dir dir;
 	struct in6_addr orig_ip;
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(skb_in, &ctinfo);
-	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+	if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) {
 		__icmpv6_send(skb_in, type, code, info, &parm);
 		return;
 	}
@@ -73,7 +74,8 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
 		goto out;
 
 	orig_ip = ipv6_hdr(skb_in)->saddr;
-	ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
+	dir = CTINFO2DIR(ctinfo);
+	ipv6_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.in6;
 	__icmpv6_send(skb_in, type, code, info, &parm);
 	ipv6_hdr(skb_in)->saddr = orig_ip;
 out: