Merge tag 'nf-23-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

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

The following patchset contains Netfilter fixes for net:

1) Remove unused variable causing compilation warning in nft_set_rbtree,
   from Yang Li. This unused variable is a left over from previous
   merge window.

2) Possible return of uninitialized in nf_conntrack_bridge, from
   Linkui Xiao. This is there since nf_conntrack_bridge is available.

3) Fix incorrect pointer math in nft_byteorder, from Dan Carpenter.
   Problem has been there since 2016.

4) Fix bogus error in destroy set element command. Problem is there
   since this new destroy command was added.

5) Fix race condition in ipset between swap and destroy commands and
   add/del/test control plane. This problem is there since ipset was
   merged.

6) Split async and sync catchall GC in two function to fix unsafe
   iteration over RCU. This is a fix-for-fix that was included in
   the previous pull request.

* tag 'nf-23-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nf_tables: split async and sync catchall in two functions
  netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test
  netfilter: nf_tables: bogus ENOENT when destroying element which does not exist
  netfilter: nf_tables: fix pointer math issue in nft_byteorder_eval()
  netfilter: nf_conntrack_bridge: initialize err to 0
  netfilter: nft_set_rbtree: Remove unused variable nft_net
====================

Link: https://lore.kernel.org/r/20231115184514.8965-1-pablo@netfilter.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

7 files changed, 47 insertions, 42 deletions

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3bbd13ab1ecf59..b157c5cafd14cf 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -178,9 +178,9 @@ static inline __be32 nft_reg_load_be32(const u32 *sreg)
 	return *(__force __be32 *)sreg;
 }
 
-static inline void nft_reg_store64(u32 *dreg, u64 val)
+static inline void nft_reg_store64(u64 *dreg, u64 val)
 {
-	put_unaligned(val, (u64 *)dreg);
+	put_unaligned(val, dreg);
 }
 
 static inline u64 nft_reg_load64(const u32 *sreg)
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index b5c406a6e7654f..abb090f94ed260 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
-	int err;
+	int err = 0;
 
 	/* for offloaded checksums cleanup checksum before fragmentation */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 35d2f9c9ada025..4c133e06be1de2 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 	ip_set_dereference((inst)->ip_set_list)[id]
 #define ip_set_ref_netlink(inst,id)	\
 	rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p)	\
+	rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set)
 static struct ip_set *
 ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
-	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	rcu_read_lock();
-	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(inst->ip_set_list)[index];
-	rcu_read_unlock();
-
-	return set;
+	/* ip_set_list and the set pointer need to be protected */
+	return ip_set_dereference_nfnl(inst->ip_set_list)[index];
 }
 
 static inline void
@@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
+	/* Make sure all readers of the old set pointers are completed. */
+	synchronize_rcu();
+
 	return 0;
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a761ee6796f6fa..c0a42989b98226 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7263,10 +7263,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
-			break;
+			return err;
 		}
 	}
-	return err;
+
+	return 0;
 }
 
 /*
@@ -9679,16 +9680,14 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans)
 	call_rcu(&trans->rcu, nft_trans_gc_trans_free);
 }
 
-static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
-						  unsigned int gc_seq,
-						  bool sync)
+struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
+						 unsigned int gc_seq)
 {
-	struct nft_set_elem_catchall *catchall, *next;
+	struct nft_set_elem_catchall *catchall;
 	const struct nft_set *set = gc->set;
-	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
 
-	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
 		if (!nft_set_elem_expired(ext))
@@ -9698,35 +9697,42 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
 
 		nft_set_elem_dead(ext);
 dead_elem:
-		if (sync)
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
-		else
-			gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
-
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
 		if (!gc)
 			return NULL;
 
-		elem_priv = catchall->elem;
-		if (sync) {
-			nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
-			nft_setelem_catchall_destroy(catchall);
-		}
-
-		nft_trans_gc_elem_add(gc, elem_priv);
+		nft_trans_gc_elem_add(gc, catchall->elem);
 	}
 
 	return gc;
 }
 
-struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
-						 unsigned int gc_seq)
-{
-	return nft_trans_gc_catchall(gc, gc_seq, false);
-}
-
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
-	return nft_trans_gc_catchall(gc, 0, true);
+	struct nft_set_elem_catchall *catchall, *next;
+	const struct nft_set *set = gc->set;
+	struct nft_elem_priv *elem_priv;
+	struct nft_set_ext *ext;
+
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net));
+
+	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+
+		if (!nft_set_elem_expired(ext))
+			continue;
+
+		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
+		if (!gc)
+			return NULL;
+
+		elem_priv = catchall->elem;
+		nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
+		nft_setelem_catchall_destroy(catchall);
+		nft_trans_gc_elem_add(gc, elem_priv);
+	}
+
+	return gc;
 }
 
 static void nf_tables_module_autoload_cleanup(struct net *net)
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index e596d1a842f702..f6e791a6810151 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 
 	switch (priv->size) {
 	case 8: {
+		u64 *dst64 = (void *)dst;
 		u64 src64;
 
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = nft_reg_load64(&src[i]);
-				nft_reg_store64(&dst[i],
+				nft_reg_store64(&dst64[i],
 						be64_to_cpu((__force __be64)src64));
 			}
 			break;
@@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = (__force __u64)
 					cpu_to_be64(nft_reg_load64(&src[i]));
-				nft_reg_store64(&dst[i], src64);
+				nft_reg_store64(&dst64[i], src64);
 			}
 			break;
 		}
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index f7da7c43333b5a..ba0d3683a45d32 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key,
 {
 	switch (key) {
 	case NFT_META_TIME_NS:
-		nft_reg_store64(dest, ktime_get_real_ns());
+		nft_reg_store64((u64 *)dest, ktime_get_real_ns());
 		break;
 	case NFT_META_TIME_DAY:
 		nft_reg_store8(dest, nft_meta_weekday());
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 6f1186abd47b43..baa3fea4fe65c8 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -624,14 +624,12 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
-	struct nftables_pernet *nft_net;
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
 	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	nft_net = nft_pernet(net);
 
 	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (!gc)