Merge tag 'nf-23-08-16' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Florisn Westphal says:

====================
These are netfilter fixes for the *net* tree.

First patch resolves a false-positive lockdep splat:
rcu_dereference is used outside of rcu read lock. Let lockdep
validate that the transaction mutex is locked.

Second patch fixes a kdoc warning added in previous PR.

Third patch fixes a memory leak:
The catchall element isn't disabled correctly, this allows
userspace to deactivate the element again. This results in refcount
underflow which in turn prevents memory release. This was always
broken since the feature was added in 5.13.

Patch 4 fixes an incorrect change in the previous pull request:
Adding a duplicate key to a set should work if the duplicate key
has expired, restore this behaviour. All from myself.

Patch #5 resolves an old historic artifact in sctp conntrack:
a 300ms timeout for shutdown_ack. Increase this to 3s. From Xin Long.

Patch #6 fixes a sysctl data race in ipvs, two threads can clobber the
sysctl value, from Sishuai Gong. This is a day-0 bug that predates git
history.

Patches 7, 8 and 9, from Pablo Neira Ayuso, are also followups
for the previous GC rework in nf_tables: The netlink notifier and the
netns exit path must both increment the gc worker seqcount, else worker
may encounter stale (free'd) pointers.
================

Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/nf_conntrack-sysctl.rst

···
 	Default is set to (hb_interval * path_max_retrans + rto_max)
 
 nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds)
-	default 0.3
+	default 3
 
 nf_conntrack_sctp_timeout_shutdown_recd - INTEGER (seconds)
-	default 0.3
+	default 3
 
 nf_conntrack_sctp_timeout_shutdown_ack_sent - INTEGER (seconds)
 	default 3

include/net/netfilter/nf_tables.h

···
  *	@expr: stateful expression
  * 	@ops: set ops
  * 	@flags: set flags
+ *	@dead: set will be freed, never cleared
  *	@genmask: generation mask
  * 	@klen: key length
  * 	@dlen: data length

net/netfilter/ipvs/ip_vs_ctl.c

···
 proc_do_sync_threshold(struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct netns_ipvs *ipvs = table->extra2;
 	int *valp = table->data;
 	int val[2];
 	int rc;
···
 		.mode = table->mode,
 	};
 
+	mutex_lock(&ipvs->sync_mutex);
 	memcpy(val, valp, sizeof(val));
 	rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
 	if (write) {
···
 		else
 			memcpy(valp, val, sizeof(val));
 	}
+	mutex_unlock(&ipvs->sync_mutex);
 	return rc;
 }
 
···
 	ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
 	ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
 	tbl[idx].data = &ipvs->sysctl_sync_threshold;
+	tbl[idx].extra2 = ipvs;
 	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
 	ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
 	tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;

net/netfilter/nf_conntrack_proto_sctp.c

···
 	[SCTP_CONNTRACK_COOKIE_WAIT]		= 3 SECS,
 	[SCTP_CONNTRACK_COOKIE_ECHOED]		= 3 SECS,
 	[SCTP_CONNTRACK_ESTABLISHED]		= 210 SECS,
-	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 300 SECS / 1000,
-	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 300 SECS / 1000,
+	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 3 SECS,
+	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 3 SECS,
 	[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]	= 3 SECS,
 	[SCTP_CONNTRACK_HEARTBEAT_SENT]		= 30 SECS,
 };
···
 	{
 /*	ORIGINAL	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
-/* init         */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init         */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW},
 /* init_ack     */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
 /* abort        */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
 /* shutdown     */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},

net/netfilter/nf_tables_api.c

···
 		ret = __nft_set_catchall_flush(ctx, set, &elem);
 		if (ret < 0)
 			break;
+		nft_set_elem_change_active(ctx->net, set, ext);
 	}
 
 	return ret;
···
 	if (!trans)
 		return NULL;
 
+	trans->net = maybe_get_net(net);
+	if (!trans->net) {
+		kfree(trans);
+		return NULL;
+	}
+
 	refcount_inc(&set->refs);
 	trans->set = set;
-	trans->net = get_net(net);
 	trans->seq = gc_seq;
 
 	return trans;
···
 	}
 }
 
+static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net)
+{
+	unsigned int gc_seq;
+
+	/* Bump gc counter, it becomes odd, this is the busy mark. */
+	gc_seq = READ_ONCE(nft_net->gc_seq);
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+
+	return gc_seq;
+}
+
+static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq)
+{
+	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+}
+
 static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
···
 
 	WRITE_ONCE(nft_net->base_seq, base_seq);
 
-	/* Bump gc counter, it becomes odd, this is the busy mark. */
-	gc_seq = READ_ONCE(nft_net->gc_seq);
-	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+	gc_seq = nft_gc_seq_begin(nft_net);
 
 	/* step 3. Start new generation, rules_gen_X now in use. */
 	net->nft.gencursor = nft_gencursor_next(net);
···
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
 	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
 
-	WRITE_ONCE(nft_net->gc_seq, ++gc_seq);
+	nft_gc_seq_end(nft_net, gc_seq);
 	nf_tables_commit_release(net);
 
 	return 0;
···
 	struct net *net = n->net;
 	unsigned int deleted;
 	bool restart = false;
+	unsigned int gc_seq;
 
 	if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER)
 		return NOTIFY_DONE;
···
 	nft_net = nft_pernet(net);
 	deleted = 0;
 	mutex_lock(&nft_net->commit_mutex);
+
+	gc_seq = nft_gc_seq_begin(nft_net);
+
 	if (!list_empty(&nf_tables_destroy_list))
 		rcu_barrier();
 again:
···
 		if (restart)
 			goto again;
 	}
+	nft_gc_seq_end(nft_net, gc_seq);
+
 	mutex_unlock(&nft_net->commit_mutex);
 
 	return NOTIFY_DONE;
···
 static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
+	unsigned int gc_seq;
 
 	mutex_lock(&nft_net->commit_mutex);
+
+	gc_seq = nft_gc_seq_begin(nft_net);
+
 	if (!list_empty(&nft_net->commit_list) ||
 	    !list_empty(&nft_net->module_list))
 		__nf_tables_abort(net, NFNL_ABORT_NONE);
+
 	__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));

net/netfilter/nft_dynset.c

···
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
+	if (set->flags & NFT_SET_OBJECT)
+		return -EOPNOTSUPP;
+
 	if (set->ops->update == NULL)
 		return -EOPNOTSUPP;
 

net/netfilter/nft_set_pipapo.c

···
 			goto out;
 
 		if (last) {
+			if (nft_set_elem_expired(&f->mt[b].e->ext))
+				goto next_match;
 			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
 				goto next_match;
···
 static void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
 			    const struct nft_set_elem *elem, unsigned int flags)
 {
-	struct nft_pipapo_elem *ret;
-
-	ret = pipapo_get(net, set, (const u8 *)elem->key.val.data,
+	return pipapo_get(net, set, (const u8 *)elem->key.val.data,
 			 nft_genmask_cur(net));
-	if (IS_ERR(ret))
-		return ret;
-
-	if (nft_set_elem_expired(&ret->ext))
-		return ERR_PTR(-ENOENT);
-
-	return ret;
 }
 
 /**
···
 
 /**
  * pipapo_gc() - Drop expired entries from set, destroy start and end elements
- * @set:	nftables API set representation
+ * @_set:	nftables API set representation
  * @m:		Matching data
  */
 static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m)
···
 	priv->clone = new_clone;
 }
 
+static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	const struct net *net = read_pnet(&set->net);
+
+	return lockdep_is_held(&nft_pernet(net)->commit_mutex);
+#else
+	return true;
+#endif
+}
+
 static void nft_pipapo_abort(const struct nft_set *set)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
···
 	if (!priv->dirty)
 		return;
 
-	m = rcu_dereference(priv->match);
+	m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set));
 
 	new_clone = pipapo_clone(m);
 	if (IS_ERR(new_clone))
···
 				const struct nft_set *set,
 				const struct nft_set_elem *elem)
 {
-	struct nft_pipapo_elem *e;
-
-	e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0);
-	if (IS_ERR(e))
-		return;
+	struct nft_pipapo_elem *e = elem->priv;
 
 	nft_set_elem_change_active(net, set, &e->ext);
 }
···
 	const u8 *data;
 
 	data = (const u8 *)nft_set_ext_key(&e->ext);
-
-	e = pipapo_get(net, set, data, 0);
-	if (IS_ERR(e))
-		return;
 
 	while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
 		union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];