Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.17-rc6).

Conflicts:

net/netfilter/nft_set_pipapo.c
net/netfilter/nft_set_pipapo_avx2.c
  c4eaca2e1052 ("netfilter: nft_set_pipapo: don't check genbit from packetpath lookups")
  84c1da7b38d9 ("netfilter: nft_set_pipapo: use avx2 algorithm for insertions too")

Only trivial adjacent changes (in a doc and a Makefile).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 99 insertions, 45 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 68e273d8821a..eed434e0a970 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1123,11 +1123,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 	return ERR_PTR(-ENOENT);
 }
 
-static __be16 nft_base_seq(const struct net *net)
+static unsigned int nft_base_seq(const struct net *net)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
+	return READ_ONCE(net->nft.base_seq);
+}
 
-	return htons(nft_net->base_seq & 0xffff);
+static __be16 nft_base_seq_be16(const struct net *net)
+{
+	return htons(nft_base_seq(net) & 0xffff);
 }
 
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
@@ -1147,7 +1150,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -1240,7 +1243,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -2022,7 +2025,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -2125,7 +2128,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -3663,7 +3666,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 
 	nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0,
-			   nft_base_seq(net));
+			   nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -3831,7 +3834,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -4042,7 +4045,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb,
 	buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
 			nla_len(nla[NFTA_RULE_TABLE]),
 			(char *)nla_data(nla[NFTA_RULE_TABLE]),
-			nft_net->base_seq);
+			nft_base_seq(net));
 	audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
 			AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC);
 	kfree(buf);
@@ -4879,7 +4882,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
 			   flags, ctx->family, NFNETLINK_V0,
-			   nft_base_seq(ctx->net));
+			   nft_base_seq_be16(ctx->net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -5024,7 +5027,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (ctx->family != NFPROTO_UNSPEC &&
@@ -6201,7 +6204,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
@@ -6230,7 +6233,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	seq    = cb->nlh->nlmsg_seq;
 
 	nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI,
-			   table->family, NFNETLINK_V0, nft_base_seq(net));
+			   table->family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -6323,7 +6326,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 
 	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
-			   NFNETLINK_V0, nft_base_seq(ctx->net));
+			   NFNETLINK_V0, nft_base_seq_be16(ctx->net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -6622,7 +6625,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb,
 		}
 		nelems++;
 	}
-	audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems);
+	audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems);
 
 out_unlock:
 	rcu_read_unlock();
@@ -8372,7 +8375,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -8437,7 +8440,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -8471,7 +8474,7 @@ cont:
 			idx++;
 		}
 		if (ctx->reset && entries)
-			audit_log_obj_reset(table, nft_net->base_seq, entries);
+			audit_log_obj_reset(table, nft_base_seq(net), entries);
 		if (rc < 0)
 			break;
 	}
@@ -8640,7 +8643,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb,
 	buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
 			nla_len(nla[NFTA_OBJ_TABLE]),
 			(char *)nla_data(nla[NFTA_OBJ_TABLE]),
-			nft_net->base_seq);
+			nft_base_seq(net));
 	audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
 			AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
 	kfree(buf);
@@ -8745,9 +8748,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 		    struct nft_object *obj, u32 portid, u32 seq, int event,
 		    u16 flags, int family, int report, gfp_t gfp)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
 	char *buf = kasprintf(gfp, "%s:%u",
-			      table->name, nft_net->base_seq);
+			      table->name, nft_base_seq(net));
 
 	audit_log_nfcfg(buf,
 			family,
@@ -9433,7 +9435,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -9502,7 +9504,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -9687,17 +9689,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 				   u32 portid, u32 seq)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
 	struct nlmsghdr *nlh;
 	char buf[TASK_COMM_LEN];
 	int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN);
 
 	nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC,
-			   NFNETLINK_V0, nft_base_seq(net));
+			   NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
-	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) ||
+	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) ||
 	    nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) ||
 	    nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current)))
 		goto nla_put_failure;
@@ -10959,11 +10960,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	 * Bump generation counter, invalidate any dump in progress.
 	 * Cannot fail after this point.
 	 */
-	base_seq = READ_ONCE(nft_net->base_seq);
+	base_seq = nft_base_seq(net);
 	while (++base_seq == 0)
 		;
 
-	WRITE_ONCE(nft_net->base_seq, base_seq);
+	/* pairs with smp_load_acquire in nft_lookup_eval */
+	smp_store_release(&net->nft.base_seq, base_seq);
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
@@ -11172,7 +11174,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	nft_commit_notify(net, NETLINK_CB(skb).portid);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
-	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
+	nf_tables_commit_audit_log(&adl, nft_base_seq(net));
 
 	nft_gc_seq_end(nft_net, gc_seq);
 	nft_net->validate_state = NFT_VALIDATE_SKIP;
@@ -11497,7 +11499,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
 	mutex_lock(&nft_net->commit_mutex);
 	nft_net->tstamp = get_jiffies_64();
 
-	genid_ok = genid == 0 || nft_net->base_seq == genid;
+	genid_ok = genid == 0 || nft_base_seq(net) == genid;
 	if (!genid_ok)
 		mutex_unlock(&nft_net->commit_mutex);
 
@@ -12134,7 +12136,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 	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;
+	net->nft.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);
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 40c602ffbcba..58c5b14889c4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -24,11 +24,11 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
-#ifdef CONFIG_MITIGATION_RETPOLINE
-const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
+static const struct nft_set_ext *
+__nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		    const u32 *key)
 {
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (set->ops == &nft_set_hash_fast_type.ops)
 		return nft_hash_lookup_fast(net, set, key);
 	if (set->ops == &nft_set_hash_type.ops)
@@ -51,10 +51,46 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		return nft_rbtree_lookup(net, set, key);
 
 	WARN_ON_ONCE(1);
+#endif
 	return set->ops->lookup(net, set, key);
 }
+
+static unsigned int nft_base_seq(const struct net *net)
+{
+	/* pairs with smp_store_release() in nf_tables_commit() */
+	return smp_load_acquire(&net->nft.base_seq);
+}
+
+static bool nft_lookup_should_retry(const struct net *net, unsigned int seq)
+{
+	return unlikely(seq != nft_base_seq(net));
+}
+
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
+{
+	const struct nft_set_ext *ext;
+	unsigned int base_seq;
+
+	do {
+		base_seq = nft_base_seq(net);
+
+		ext = __nft_set_do_lookup(net, set, key);
+		if (ext)
+			break;
+		/* No match?  There is a small chance that lookup was
+		 * performed in the old generation, but nf_tables_commit()
+		 * already unlinked a (matching) element.
+		 *
+		 * We need to repeat the lookup to make sure that we didn't
+		 * miss a matching element in the new generation.
+		 */
+	} while (nft_lookup_should_retry(net, base_seq));
+
+	return ext;
+}
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
-#endif
 
 void nft_lookup_eval(const struct nft_expr *expr,
 		     struct nft_regs *regs,
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index c24c922f895d..8d3f040a904a 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
 	const struct nft_bitmap *priv = nft_set_priv(set);
 	struct nft_bitmap_elem *be;
 
-	list_for_each_entry_rcu(be, &priv->list, head) {
+	list_for_each_entry_rcu(be, &priv->list, head,
+				lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) {
 		if (iter->count < iter->skip)
 			goto cont;
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 4b64c3bd8e70..a7b8fa8cab7c 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -549,6 +549,23 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m,
  *
  * This function is called from the data path.  It will search for
  * an element matching the given key in the current active copy.
+ * Unlike other set types, this uses NFT_GENMASK_ANY instead of
+ * nft_genmask_cur().
+ *
+ * This is because new (future) elements are not reachable from
+ * priv->match, they get added to priv->clone instead.
+ * When the commit phase flips the generation bitmask, the
+ * 'now old' entries are skipped but without the 'now current'
+ * elements becoming visible. Using nft_genmask_cur() thus creates
+ * inconsistent state: matching old entries get skipped but thew
+ * newly matching entries are unreachable.
+ *
+ * GENMASK will still find the 'now old' entries which ensures consistent
+ * priv->match view.
+ *
+ * nft_pipapo_commit swaps ->clone and ->match shortly after the
+ * genbit flip.  As ->clone doesn't contain the old entries in the first
+ * place, lookup will only find the now-current ones.
  *
  * Return: ntables API extension pointer or NULL if no match.
  */
@@ -557,12 +574,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_elem *e;
 
 	m = rcu_dereference(priv->match);
-	e = pipapo_get_slow(m, (const u8 *)key, genmask, get_jiffies_64());
+	e = pipapo_get_slow(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64());
 
 	return e ? &e->ext : NULL;
 }
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 7559306d0aed..27dab3667548 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1275,7 +1275,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const u8 *rp = (const u8 *)key;
 	const struct nft_pipapo_elem *e;
@@ -1293,7 +1292,7 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 
 	m = rcu_dereference(priv->match);
 
-	e = pipapo_get_avx2(m, rp, genmask, get_jiffies_64());
+	e = pipapo_get_avx2(m, rp, NFT_GENMASK_ANY, get_jiffies_64());
 	local_bh_enable();
 
 	return e ? &e->ext : NULL;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index b311b66df3e9..ca594161b840 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			    nft_rbtree_interval_end(rbe) &&
 			    nft_rbtree_interval_start(interval))
 				continue;
-			interval = rbe;
+			if (nft_set_elem_active(&rbe->ext, genmask) &&
+			    !nft_rbtree_elem_expired(rbe))
+				interval = rbe;
 		} else if (d > 0)
 			parent = rcu_dereference_raw(parent->rb_right);
 		else {
@@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
-	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_rbtree_elem_expired(interval) &&
 	    nft_rbtree_interval_start(interval))
 		return &interval->ext;