[LTS 9.2] netfilter: CVE-2024-0607, CVE-2024-0193, CVE-2024-42109, CVE-2024-54031 + non-CVE bugfixes

include/net/netfilter/nf_tables.h

@@ -147,9 +147,9 @@ static inline u16 nft_reg_load16(const u32 *sreg)
 	return *(u16 *)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)
@@ -665,15 +665,18 @@ struct nft_set_ext_tmpl {
 /**
  *	struct nft_set_ext - set extensions
  *
- *	@genmask: generation mask
+ *	@genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT)
  *	@offset: offsets of individual extension types
  *	@data: beginning of extension data
+ *
+ *	This structure must be aligned to word size, otherwise atomic bitops
+ *	on genmask field can cause alignment failure on some archs.
  */
 struct nft_set_ext {
 	u8	genmask;
 	u8	offset[NFT_SET_EXT_NUM];
 	char	data[];
-};
+} __aligned(BITS_PER_LONG / 8);
 
 static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
 {
@@ -1654,7 +1657,7 @@ void nft_chain_filter_fini(void);
 void __init nft_chain_route_init(void);
 void nft_chain_route_fini(void);
 
-void nf_tables_trans_destroy_flush_work(void);
+void nf_tables_trans_destroy_flush_work(struct net *net);
 
 int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result);
 __be64 nf_jiffies64_to_msecs(u64 input);
@@ -1668,6 +1671,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re
 struct nftables_pernet {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct list_head	destroy_list;
 	struct list_head	binding_list;
 	struct list_head	module_list;
 	struct list_head	notify_list;
@@ -1676,6 +1680,7 @@ struct nftables_pernet {
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
+	struct work_struct	destroy_work;
 };
 
 extern unsigned int nf_tables_net_id;

net/netfilter/nf_tables_api.c

@@ -30,7 +30,6 @@ unsigned int nf_tables_net_id __read_mostly;
 static LIST_HEAD(nf_tables_expressions);
 static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
-static LIST_HEAD(nf_tables_destroy_list);
 static LIST_HEAD(nf_tables_gc_list);
 static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
 static DEFINE_SPINLOCK(nf_tables_gc_list_lock);
@@ -122,7 +121,6 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state)
 	nft_net->validate_state = new_validate_state;
 }
 static void nf_tables_trans_destroy_work(struct work_struct *w);
-static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work);
 
 static void nft_trans_gc_work(struct work_struct *work);
 static DECLARE_WORK(trans_gc_work, nft_trans_gc_work);
@@ -5379,7 +5377,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_set_dump_args *args;
 
-	if (nft_set_elem_expired(ext))
+	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
 	args = container_of(iter, struct nft_set_dump_args, iter);
@@ -8824,11 +8822,12 @@ static void nft_commit_release(struct nft_trans *trans)
 
 static void nf_tables_trans_destroy_work(struct work_struct *w)
 {
+	struct nftables_pernet *nft_net = container_of(w, struct nftables_pernet, destroy_work);
 	struct nft_trans *trans, *next;
 	LIST_HEAD(head);
 
 	spin_lock(&nf_tables_destroy_list_lock);
-	list_splice_init(&nf_tables_destroy_list, &head);
+	list_splice_init(&nft_net->destroy_list, &head);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
 	if (list_empty(&head))
@@ -8842,9 +8841,11 @@ static void nf_tables_trans_destroy_work(struct work_struct *w)
 	}
 }
 
-void nf_tables_trans_destroy_flush_work(void)
+void nf_tables_trans_destroy_flush_work(struct net *net)
 {
-	flush_work(&trans_destroy_work);
+	struct nftables_pernet *nft_net = nft_pernet(net);
+
+	flush_work(&nft_net->destroy_work);
 }
 EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work);
 
@@ -9263,11 +9264,11 @@ static void nf_tables_commit_release(struct net *net)
 
 	trans->put_net = true;
 	spin_lock(&nf_tables_destroy_list_lock);
-	list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list);
+	list_splice_tail_init(&nft_net->commit_list, &nft_net->destroy_list);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
 	nf_tables_module_autoload_cleanup(net);
-	schedule_work(&trans_destroy_work);
+	schedule_work(&nft_net->destroy_work);
 
 	mutex_unlock(&nft_net->commit_mutex);
 }
@@ -9376,7 +9377,7 @@ static void nft_set_commit_update(struct list_head *set_update_list)
 	list_for_each_entry_safe(set, next, set_update_list, pending_update) {
 		list_del_init(&set->pending_update);
 
-		if (!set->ops->commit)
+		if (!set->ops->commit || set->dead)
 			continue;
 
 		set->ops->commit(set);
@@ -9834,6 +9835,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_trans_destroy(trans);
 				break;
 			}
+			nft_trans_set(trans)->dead = 1;
 			list_del_rcu(&nft_trans_set(trans)->list);
 			break;
 		case NFT_MSG_DELSET:
@@ -10676,8 +10678,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
-	if (!list_empty(&nf_tables_destroy_list))
-		nf_tables_trans_destroy_flush_work();
+	nf_tables_trans_destroy_flush_work(net);
 again:
 	list_for_each_entry(table, &nft_net->tables, list) {
 		if (nft_table_has_owner(table) &&
@@ -10715,13 +10716,15 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 	INIT_LIST_HEAD(&nft_net->tables);
 	INIT_LIST_HEAD(&nft_net->commit_list);
+	INIT_LIST_HEAD(&nft_net->destroy_list);
 	INIT_LIST_HEAD(&nft_net->binding_list);
 	INIT_LIST_HEAD(&nft_net->module_list);
 	INIT_LIST_HEAD(&nft_net->notify_list);
 	mutex_init(&nft_net->commit_mutex);
 	nft_net->base_seq = 1;
 	nft_net->gc_seq = 0;
 	nft_net->validate_state = NFT_VALIDATE_SKIP;
+	INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work);
 
 	return 0;
 }
@@ -10749,14 +10752,17 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	if (!list_empty(&nft_net->module_list))
 		nf_tables_module_autoload_cleanup(net);
 
+	cancel_work_sync(&nft_net->destroy_work);
 	__nft_release_tables(net);
 
 	nft_gc_seq_end(nft_net, gc_seq);
 
 	mutex_unlock(&nft_net->commit_mutex);
+
 	WARN_ON_ONCE(!list_empty(&nft_net->tables));
 	WARN_ON_ONCE(!list_empty(&nft_net->module_list));
 	WARN_ON_ONCE(!list_empty(&nft_net->notify_list));
+	WARN_ON_ONCE(!list_empty(&nft_net->destroy_list));
 }
 
 static void nf_tables_exit_batch(struct list_head *net_exit_list)
@@ -10841,7 +10847,6 @@ static void __exit nf_tables_module_exit(void)
 	nft_chain_route_fini();
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_gc_work);
-	cancel_work_sync(&trans_destroy_work);
 	rcu_barrier();
 	rhltable_destroy(&nft_objname_ht);
 	nf_tables_core_module_exit();

net/netfilter/nft_byteorder.c

@@ -38,20 +38,22 @@ 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], be64_to_cpu(src64));
+				nft_reg_store64(&dst64[i],
+						be64_to_cpu((__force __be64)src64));
 			}
 			break;
 		case NFT_BYTEORDER_HTON:
 			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;
 		}

net/netfilter/nft_compat.c

@@ -223,15 +223,15 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	return 0;
 }
 
-static void nft_compat_wait_for_destructors(void)
+static void nft_compat_wait_for_destructors(struct net *net)
 {
 	/* xtables matches or targets can have side effects, e.g.
 	 * creation/destruction of /proc files.
 	 * The xt ->destroy functions are run asynchronously from
 	 * work queue.  If we have pending invocations we thus
 	 * need to wait for those to finish.
 	 */
-	nf_tables_trans_destroy_flush_work();
+	nf_tables_trans_destroy_flush_work(net);
 }
 
 static int
@@ -257,7 +257,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
 
-	nft_compat_wait_for_destructors();
+	nft_compat_wait_for_destructors(ctx->net);
 
 	ret = xt_check_target(&par, size, proto, inv);
 	if (ret < 0) {
@@ -494,7 +494,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
 
-	nft_compat_wait_for_destructors();
+	nft_compat_wait_for_destructors(ctx->net);
 
 	return xt_check_match(&par, size, proto, inv);
 }

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());

net/netfilter/nft_set_hash.c

@@ -24,11 +24,13 @@
 struct nft_rhash {
 	struct rhashtable		ht;
 	struct delayed_work		gc_work;
+	u32				wq_gc_seq;
 };
 
 struct nft_rhash_elem {
 	struct nft_elem_priv		priv;
 	struct rhash_head		node;
+	u32				wq_gc_seq;
 	struct nft_set_ext		ext;
 };
 
@@ -337,6 +339,10 @@ static void nft_rhash_gc(struct work_struct *work)
 	if (!gc)
 		goto done;
 
+	/* Elements never collected use a zero gc worker sequence number. */
+	if (unlikely(++priv->wq_gc_seq == 0))
+		priv->wq_gc_seq++;
+
 	rhashtable_walk_enter(&priv->ht, &hti);
 	rhashtable_walk_start(&hti);
 
@@ -354,6 +360,14 @@ static void nft_rhash_gc(struct work_struct *work)
 			goto try_later;
 		}
 
+		/* rhashtable walk is unstable, already seen in this gc run?
+		 * Then, skip this element. In case of (unlikely) sequence
+		 * wraparound and stale element wq_gc_seq, next gc run will
+		 * just find this expired element.
+		 */
+		if (he->wq_gc_seq == priv->wq_gc_seq)
+			continue;
+
 		if (nft_set_elem_is_dead(&he->ext))
 			goto dead_elem;
 
@@ -370,6 +384,8 @@ static void nft_rhash_gc(struct work_struct *work)
 		if (!gc)
 			goto try_later;
 
+		/* annotate gc sequence for this attempt. */
+		he->wq_gc_seq = priv->wq_gc_seq;
 		nft_trans_gc_elem_add(gc, he);
 	}
 

net/netfilter/nft_set_pipapo.c

@@ -603,7 +603,7 @@ static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	       const struct nft_set_elem *elem, unsigned int flags)
 {
-	static struct nft_pipapo_elem *e;
+	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
 		       nft_genmask_cur(net));
@@ -1603,7 +1603,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m)
 		if (nft_set_elem_expired(&e->ext)) {
 			priv->dirty = true;
 
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
+			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
 			if (!gc)
 				return;