Merge tag 'nf-24-09-12' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following batch contains two fixes from Florian Westphal:

Patch #1 fixes a sk refcount leak in nft_socket on mismatch.

Patch #2 fixes cgroupsv2 matching from containers due to incorrect
	 level in subtree.

netfilter pull request 24-09-12

* tag 'nf-24-09-12' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_socket: make cgroupsv2 matching work with namespaces
  netfilter: nft_socket: fix sk refcount leaks
====================

Link: https://patch.msgid.link/20240911222520.3606-1-pablo@netfilter.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

net/netfilter/nft_socket.c

@@ -9,7 +9,8 @@
 
 struct nft_socket {
 	enum nft_socket_keys		key:8;
-	u8				level;
+	u8				level;		/* cgroupv2 level to extract */
+	u8				level_user;	/* cgroupv2 level provided by userspace */
 	u8				len;
 	union {
 		u8			dreg;
@@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo
 	memcpy(dest, &cgid, sizeof(u64));
 	return true;
 }
+
+/* process context only, uses current->nsproxy. */
+static noinline int nft_socket_cgroup_subtree_level(void)
+{
+	struct cgroup *cgrp = cgroup_get_from_path("/");
+	int level;
+
+	if (!cgrp)
+		return -ENOENT;
+
+	level = cgrp->level;
+
+	cgroup_put(cgrp);
+
+	if (WARN_ON_ONCE(level > 255))
+		return -ERANGE;
+
+	if (WARN_ON_ONCE(level < 0))
+		return -EINVAL;
+
+	return level;
+}
 #endif
 
 static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt)
@@ -110,21 +133,21 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			*dest = READ_ONCE(sk->sk_mark);
 		} else {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 	case NFT_SOCKET_WILDCARD:
 		if (!sk_fullsock(sk)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		nft_socket_wildcard(pkt, regs, sk, dest);
 		break;
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case NFT_SOCKET_CGROUPV2:
 		if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 #endif
@@ -133,6 +156,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		regs->verdict.code = NFT_BREAK;
 	}
 
+out_put_sk:
 	if (sk != skb->sk)
 		sock_gen_put(sk);
 }
@@ -173,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	case NFT_SOCKET_MARK:
 		len = sizeof(u32);
 		break;
-#ifdef CONFIG_CGROUPS
+#ifdef CONFIG_SOCK_CGROUP_DATA
 	case NFT_SOCKET_CGROUPV2: {
 		unsigned int level;
+		int err;
 
 		if (!tb[NFTA_SOCKET_LEVEL])
 			return -EINVAL;
@@ -184,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 		if (level > 255)
 			return -EOPNOTSUPP;
 
+		err = nft_socket_cgroup_subtree_level();
+		if (err < 0)
+			return err;
+
+		priv->level_user = level;
+
+		level += err;
+		/* Implies a giant cgroup tree */
+		if (WARN_ON_ONCE(level > 255))
+			return -EOPNOTSUPP;
+
 		priv->level = level;
 		len = sizeof(u64);
 		break;
@@ -208,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb,
 	if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg))
 		return -1;
 	if (priv->key == NFT_SOCKET_CGROUPV2 &&
-	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level)))
+	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user)))
 		return -1;
 	return 0;
 }