5 files changed, 26 insertions, 6 deletions

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 426534a711b0..ea6f29ad7888 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
  * @NFT_ITER_UNSPEC: unspecified, to catch errors
  * @NFT_ITER_READ: read-only iteration over set elements
  * @NFT_ITER_UPDATE: iteration under mutex to update set element state
+ * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element
  */
 enum nft_iter_type {
 	NFT_ITER_UNSPEC,
 	NFT_ITER_READ,
 	NFT_ITER_UPDATE,
+	NFT_ITER_UPDATE_CLONE,
 };
 
 struct nft_set;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index df67932d3e09..058f7004cb2b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 	}
 }
 
+/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation
+ * phase, the set clone might already exist from a previous command, or it might
+ * be a set that is going away and does not require a clone. The netns and
+ * netlink release paths also need to work on the live set.
+ */
 static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	struct nft_set_iter iter = {
@@ -7903,9 +7908,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx,
 
 static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask)
 {
+	/* The set backend might need to clone the set, do it now from the
+	 * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type.
+	 */
 	struct nft_set_iter iter = {
 		.genmask	= genmask,
-		.type		= NFT_ITER_UPDATE,
+		.type		= NFT_ITER_UPDATE_CLONE,
 		.fn		= nft_setelem_flush,
 	};
 
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 739b992bde59..b0e571c8e3f3 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 {
 	switch (iter->type) {
 	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		/* only relevant for netlink dumps which use READ type */
 		WARN_ON_ONCE(iter->skip != 0);
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 7ef4b44471d3..c091898df710 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2144,13 +2144,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 	const struct nft_pipapo_match *m;
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		m = pipapo_maybe_clone(set);
 		if (!m) {
 			iter->err = -ENOMEM;
 			return;
 		}
-
+		nft_pipapo_do_walk(ctx, set, m, iter);
+		break;
+	case NFT_ITER_UPDATE:
+		if (priv->clone)
+			m = priv->clone;
+		else
+			m = rcu_dereference_protected(priv->match,
+						      nft_pipapo_transaction_mutex_held(set));
 		nft_pipapo_do_walk(ctx, set, m, iter);
 		break;
 	case NFT_ITER_READ:
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 3f02e4478216..ee3d4f5b9ff7 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_rbtree *priv = nft_set_priv(set);
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
-		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
-
+	case NFT_ITER_UPDATE_CLONE:
 		if (nft_array_may_resize(set) < 0) {
 			iter->err = -ENOMEM;
 			break;
 		}
+		fallthrough;
+	case NFT_ITER_UPDATE:
+		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
+
 		nft_rbtree_do_walk(ctx, set, iter);
 		break;
 	case NFT_ITER_READ: