Merge tag 'nf-next-24-09-06' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/netfilter/nf-next

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for net-next:

Patch #1 adds ctnetlink support for kernel side filtering for
	 deletions, from Changliang Wu.

Patch #2 updates nft_counter support to Use u64_stats_t,
	 from Sebastian Andrzej Siewior.

Patch #3 uses kmemdup_array() in all xtables frontends,
	 from Yan Zhen.

Patch #4 is a oneliner to use ERR_CAST() in nf_conntrack instead
	 opencoded casting, from Shen Lichuan.

Patch #5 removes unused argument in nftables .validate interface,
	 from Florian Westphal.

Patch #6 is a oneliner to correct a typo in nftables kdoc,
	 from Simon Horman.

Patch #7 fixes missing kdoc in nftables, also from Simon.

Patch #8 updates nftables to handle timeout less than CONFIG_HZ.

Patch #9 rejects element expiration if timeout is zero,
	 otherwise it is silently ignored.

Patch #10 disallows element expiration larger than timeout.

Patch #11 removes unnecessary READ_ONCE annotation while mutex is held.

Patch #12 adds missing READ_ONCE/WRITE_ONCE annotation in dynset.

Patch #13 annotates data-races around element expiration.

Patch #14 allocates timeout and expiration in one single set element
	  extension, they are tighly couple, no reason to keep them
	  separated anymore.

Patch #15 updates nftables to interpret zero timeout element as never
	  times out. Note that it is already possible to declare sets
	  with elements that never time out but this generalizes to all
	  kind of set with timeouts.

Patch #16 supports for element timeout and expiration updates.

* tag 'nf-next-24-09-06' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: nf_tables: set element timeout update support
  netfilter: nf_tables: zero timeout means element never times out
  netfilter: nf_tables: consolidate timeout extension for elements
  netfilter: nf_tables: annotate data-races around element expiration
  netfilter: nft_dynset: annotate data-races around set timeout
  netfilter: nf_tables: remove annotation to access set timeout while holding lock
  netfilter: nf_tables: reject expiration higher than timeout
  netfilter: nf_tables: reject element expiration with no timeout
  netfilter: nf_tables: elements with timeout below CONFIG_HZ never expire
  netfilter: nf_tables: Add missing Kernel doc
  netfilter: nf_tables: Correct spelling in nf_tables.h
  netfilter: nf_tables: drop unused 3rd argument from validate callback ops
  netfilter: conntrack: Convert to use ERR_CAST()
  netfilter: Use kmemdup_array instead of kmemdup for multiple allocation
  netfilter: nft_counter: Use u64_stats_t for statistic.
  netfilter: ctnetlink: support CTA_FILTER for flush
====================

Link: https://patch.msgid.link/20240905232920.5481-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/netfilter/nf_tables.h

@@ -209,6 +209,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
  *	@family: protocol family
  *	@level: depth of the chains
  *	@report: notify via unicast netlink message
+ *	@reg_inited: bitmap of initialised registers
  */
 struct nft_ctx {
 	struct net			*net;
@@ -313,6 +314,7 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
 /**
  * enum nft_iter_type - nftables set iterator type
  *
+ * @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
  */
@@ -685,9 +687,8 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
  *	@NFT_SET_EXT_DATA: mapping data
  *	@NFT_SET_EXT_FLAGS: element flags
  *	@NFT_SET_EXT_TIMEOUT: element timeout
- *	@NFT_SET_EXT_EXPIRATION: element expiration time
  *	@NFT_SET_EXT_USERDATA: user data associated with the element
- *	@NFT_SET_EXT_EXPRESSIONS: expressions assiciated with the element
+ *	@NFT_SET_EXT_EXPRESSIONS: expressions associated with the element
  *	@NFT_SET_EXT_OBJREF: stateful object reference associated with element
  *	@NFT_SET_EXT_NUM: number of extension types
  */
@@ -697,7 +698,6 @@ enum nft_set_extensions {
 	NFT_SET_EXT_DATA,
 	NFT_SET_EXT_FLAGS,
 	NFT_SET_EXT_TIMEOUT,
-	NFT_SET_EXT_EXPIRATION,
 	NFT_SET_EXT_USERDATA,
 	NFT_SET_EXT_EXPRESSIONS,
 	NFT_SET_EXT_OBJREF,
@@ -809,14 +809,14 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
 	return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
 }
 
-static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext)
-{
-	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
-}
+struct nft_timeout {
+	u64	timeout;
+	u64	expiration;
+};
 
-static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext)
+static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext)
 {
-	return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
+	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
 }
 
 static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext)
@@ -832,8 +832,11 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
 					  u64 tstamp)
 {
-	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+	if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) ||
+	    READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0)
+		return false;
+
+	return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration));
 }
 
 static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
@@ -961,8 +964,7 @@ struct nft_expr_ops {
 						const struct nft_expr *expr,
 						bool reset);
 	int				(*validate)(const struct nft_ctx *ctx,
-						    const struct nft_expr *expr,
-						    const struct nft_data **data);
+						    const struct nft_expr *expr);
 	bool				(*reduce)(struct nft_regs_track *track,
 						  const struct nft_expr *expr);
 	bool				(*gc)(struct net *net,
@@ -1747,10 +1749,18 @@ struct nft_trans_table {
 #define nft_trans_table_update(trans)			\
 	nft_trans_container_table(trans)->update
 
+enum nft_trans_elem_flags {
+	NFT_TRANS_UPD_TIMEOUT		= (1 << 0),
+	NFT_TRANS_UPD_EXPIRATION	= (1 << 1),
+};
+
 struct nft_trans_elem {
 	struct nft_trans		nft_trans;
 	struct nft_set			*set;
 	struct nft_elem_priv		*elem_priv;
+	u64				timeout;
+	u64				expiration;
+	u8				update_flags;
 	bool				bound;
 };
 
@@ -1760,6 +1770,12 @@ struct nft_trans_elem {
 	nft_trans_container_elem(trans)->set
 #define nft_trans_elem_priv(trans)			\
 	nft_trans_container_elem(trans)->elem_priv
+#define nft_trans_elem_update_flags(trans)		\
+	nft_trans_container_elem(trans)->update_flags
+#define nft_trans_elem_timeout(trans)			\
+	nft_trans_container_elem(trans)->timeout
+#define nft_trans_elem_expiration(trans)		\
+	nft_trans_container_elem(trans)->expiration
 #define nft_trans_elem_set_bound(trans)			\
 	nft_trans_container_elem(trans)->bound
 

include/net/netfilter/nf_tproxy.h

@@ -36,6 +36,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
 
 /**
  * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
+ * @net:	The network namespace.
  * @skb:	The skb being processed.
  * @laddr:	IPv4 address to redirect to or zero.
  * @lport:	TCP port to redirect to or zero.

include/net/netfilter/nft_fib.h

@@ -21,9 +21,7 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in)
 int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset);
 int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		 const struct nlattr * const tb[]);
-int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		     const struct nft_data **data);
-
+int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr);
 
 void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 			const struct nft_pktinfo *pkt);

include/net/netfilter/nft_meta.h

@@ -41,8 +41,7 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx,
 			  const struct nft_expr *expr);
 
 int nft_meta_set_validate(const struct nft_ctx *ctx,
-			  const struct nft_expr *expr,
-			  const struct nft_data **data);
+			  const struct nft_expr *expr);
 
 bool nft_meta_get_reduce(struct nft_regs_track *track,
 			 const struct nft_expr *expr);

include/net/netfilter/nft_reject.h

@@ -15,8 +15,7 @@ struct nft_reject {
 extern const struct nla_policy nft_reject_policy[];
 
 int nft_reject_validate(const struct nft_ctx *ctx,
-			const struct nft_expr *expr,
-			const struct nft_data **data);
+			const struct nft_expr *expr);
 
 int nft_reject_init(const struct nft_ctx *ctx,
 		    const struct nft_expr *expr,

include/uapi/linux/netfilter/nf_tables.h

@@ -436,7 +436,7 @@ enum nft_set_elem_flags {
  * @NFTA_SET_ELEM_KEY: key value (NLA_NESTED: nft_data)
  * @NFTA_SET_ELEM_DATA: data value of mapping (NLA_NESTED: nft_data_attributes)
  * @NFTA_SET_ELEM_FLAGS: bitmask of nft_set_elem_flags (NLA_U32)
- * @NFTA_SET_ELEM_TIMEOUT: timeout value (NLA_U64)
+ * @NFTA_SET_ELEM_TIMEOUT: timeout value, zero means never times out (NLA_U64)
  * @NFTA_SET_ELEM_EXPIRATION: expiration time (NLA_U64)
  * @NFTA_SET_ELEM_USERDATA: user data (NLA_BINARY)
  * @NFTA_SET_ELEM_EXPR: expression (NLA_NESTED: nft_expr_attributes)

net/bridge/netfilter/ebtables.c

@@ -1256,7 +1256,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 		goto free_unlock;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		if (newinfo->nentries)

net/bridge/netfilter/nft_meta_bridge.c

@@ -168,8 +168,7 @@ static bool nft_meta_bridge_set_reduce(struct nft_regs_track *track,
 }
 
 static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,
-					const struct nft_expr *expr,
-					const struct nft_data **data)
+					const struct nft_expr *expr)
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
 	unsigned int hooks;
@@ -179,7 +178,7 @@ static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,
 		hooks = 1 << NF_BR_PRE_ROUTING;
 		break;
 	default:
-		return nft_meta_set_validate(ctx, expr, data);
+		return nft_meta_set_validate(ctx, expr);
 	}
 
 	return nft_chain_validate_hooks(ctx->chain, hooks);

net/bridge/netfilter/nft_reject_bridge.c

@@ -170,8 +170,7 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 }
 
 static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
+				      const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
 						    (1 << NF_BR_LOCAL_IN));

net/ipv4/netfilter/arp_tables.c

@@ -1547,7 +1547,7 @@ int arpt_register_table(struct net *net,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;

net/ipv4/netfilter/ip_tables.c

@@ -1767,7 +1767,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;

net/ipv6/netfilter/ip6_tables.c

@@ -1773,7 +1773,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;

net/netfilter/nf_conntrack_core.c

@@ -1722,7 +1722,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
 				  hash);
 	if (IS_ERR(ct))
-		return (struct nf_conntrack_tuple_hash *)ct;
+		return ERR_CAST(ct);
 
 	if (!nf_ct_add_synproxy(ct, tmpl)) {
 		nf_conntrack_free(ct);

net/netfilter/nf_conntrack_netlink.c

@@ -1579,9 +1579,6 @@ static int ctnetlink_flush_conntrack(struct net *net,
 	};
 
 	if (ctnetlink_needs_filter(family, cda)) {
-		if (cda[CTA_FILTER])
-			return -EOPNOTSUPP;
-
 		filter = ctnetlink_alloc_filter(cda, family);
 		if (IS_ERR(filter))
 			return PTR_ERR(filter);
@@ -1610,14 +1607,14 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (cda[CTA_TUPLE_ORIG])
+	if (cda[CTA_TUPLE_ORIG] && !cda[CTA_FILTER])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
 					    family, &zone);
-	else if (cda[CTA_TUPLE_REPLY])
+	else if (cda[CTA_TUPLE_REPLY] && !cda[CTA_FILTER])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
 					    family, &zone);
 	else {
-		u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC;
+		u8 u3 = info->nfmsg->version || cda[CTA_FILTER] ? family : AF_UNSPEC;
 
 		return ctnetlink_flush_conntrack(info->net, cda,
 						 NETLINK_CB(skb).portid,

net/netfilter/nf_nat_core.c

@@ -1104,7 +1104,7 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 	if (!nat_proto_net->nat_hook_ops) {
 		WARN_ON(nat_proto_net->users != 0);
 
-		nat_ops = kmemdup(orig_nat_ops, sizeof(*orig_nat_ops) * ops_count, GFP_KERNEL);
+		nat_ops = kmemdup_array(orig_nat_ops, ops_count, sizeof(*orig_nat_ops), GFP_KERNEL);
 		if (!nat_ops) {
 			mutex_unlock(&nf_nat_proto_mutex);
 			return -ENOMEM;