inet: Run SK_LOOKUP BPF program on socket lookup

Run a BPF program before looking up a listening socket on the receive path.
Program selects a listening socket to yield as result of socket lookup by
calling bpf_sk_assign() helper and returning SK_PASS code. Program can
revert its decision by assigning a NULL socket with bpf_sk_assign().

Alternatively, BPF program can also fail the lookup by returning with
SK_DROP, or let the lookup continue as usual with SK_PASS on return, when
no socket has been selected with bpf_sk_assign().

This lets the user match packets with listening sockets freely at the last
possible point on the receive path, where we know that packets are destined
for local delivery after undergoing policing, filtering, and routing.

With BPF code selecting the socket, directing packets destined to an IP
range or to a port range to a single socket becomes possible.

In case multiple programs are attached, they are run in series in the order
in which they were attached. The end result is determined from return codes
of all the programs according to following rules:

 1. If any program returned SK_PASS and selected a valid socket, the socket
    is used as result of socket lookup.
 2. If more than one program returned SK_PASS and selected a socket,
    last selection takes effect.
 3. If any program returned SK_DROP, and no program returned SK_PASS and
    selected a socket, socket lookup fails with -ECONNREFUSED.
 4. If all programs returned SK_PASS and none of them selected a socket,
    socket lookup continues to htable-based lookup.
Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com

include/linux/filter.h

@@ -1295,4 +1295,95 @@ struct bpf_sk_lookup_kern {
 	bool		no_reuseport;
 };
 
+extern struct static_key_false bpf_sk_lookup_enabled;
+
+/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup.
+ *
+ * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and
+ * SK_DROP. Their meaning is as follows:
+ *
+ *  SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result
+ *  SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup
+ *  SK_DROP                           : terminate lookup with -ECONNREFUSED
+ *
+ * This macro aggregates return values and selected sockets from
+ * multiple BPF programs according to following rules in order:
+ *
+ *  1. If any program returned SK_PASS and a non-NULL ctx.selected_sk,
+ *     macro result is SK_PASS and last ctx.selected_sk is used.
+ *  2. If any program returned SK_DROP return value,
+ *     macro result is SK_DROP.
+ *  3. Otherwise result is SK_PASS and ctx.selected_sk is NULL.
+ *
+ * Caller must ensure that the prog array is non-NULL, and that the
+ * array as well as the programs it contains remain valid.
+ */
+#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func)			\
+	({								\
+		struct bpf_sk_lookup_kern *_ctx = &(ctx);		\
+		struct bpf_prog_array_item *_item;			\
+		struct sock *_selected_sk = NULL;			\
+		bool _no_reuseport = false;				\
+		struct bpf_prog *_prog;					\
+		bool _all_pass = true;					\
+		u32 _ret;						\
+									\
+		migrate_disable();					\
+		_item = &(array)->items[0];				\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			/* restore most recent selection */		\
+			_ctx->selected_sk = _selected_sk;		\
+			_ctx->no_reuseport = _no_reuseport;		\
+									\
+			_ret = func(_prog, _ctx);			\
+			if (_ret == SK_PASS && _ctx->selected_sk) {	\
+				/* remember last non-NULL socket */	\
+				_selected_sk = _ctx->selected_sk;	\
+				_no_reuseport = _ctx->no_reuseport;	\
+			} else if (_ret == SK_DROP && _all_pass) {	\
+				_all_pass = false;			\
+			}						\
+			_item++;					\
+		}							\
+		_ctx->selected_sk = _selected_sk;			\
+		_ctx->no_reuseport = _no_reuseport;			\
+		migrate_enable();					\
+		_all_pass || _selected_sk ? SK_PASS : SK_DROP;		\
+	 })
+
+static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
+					const __be32 saddr, const __be16 sport,
+					const __be32 daddr, const u16 dport,
+					struct sock **psk)
+{
+	struct bpf_prog_array *run_array;
+	struct sock *selected_sk = NULL;
+	bool no_reuseport = false;
+
+	rcu_read_lock();
+	run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]);
+	if (run_array) {
+		struct bpf_sk_lookup_kern ctx = {
+			.family		= AF_INET,
+			.protocol	= protocol,
+			.v4.saddr	= saddr,
+			.v4.daddr	= daddr,
+			.sport		= sport,
+			.dport		= dport,
+		};
+		u32 act;
+
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		if (act == SK_PASS) {
+			selected_sk = ctx.selected_sk;
+			no_reuseport = ctx.no_reuseport;
+		} else {
+			selected_sk = ERR_PTR(-ECONNREFUSED);
+		}
+	}
+	rcu_read_unlock();
+	*psk = selected_sk;
+	return no_reuseport;
+}
+
 #endif /* __LINUX_FILTER_H__ */

kernel/bpf/net_namespace.c

@@ -25,6 +25,28 @@ struct bpf_netns_link {
 /* Protects updates to netns_bpf */
 DEFINE_MUTEX(netns_bpf_mutex);
 
+static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_dec(&bpf_sk_lookup_enabled);
+		break;
+	default:
+		break;
+	}
+}
+
+static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_inc(&bpf_sk_lookup_enabled);
+		break;
+	default:
+		break;
+	}
+}
+
 /* Must be called with netns_bpf_mutex held. */
 static void netns_bpf_run_array_detach(struct net *net,
 				       enum netns_bpf_attach_type type)
@@ -91,6 +113,9 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	if (!net)
 		goto out_unlock;
 
+	/* Mark attach point as unused */
+	netns_bpf_attach_type_unneed(type);
+
 	/* Remember link position in case of safe delete */
 	idx = link_index(net, type, net_link);
 	list_del(&net_link->node);
@@ -428,6 +453,9 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 					lockdep_is_held(&netns_bpf_mutex));
 	bpf_prog_array_free(run_array);
 
+	/* Mark attach point as used */
+	netns_bpf_attach_type_need(type);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 	return err;
@@ -503,8 +531,10 @@ static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
 	mutex_lock(&netns_bpf_mutex);
 	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
 		netns_bpf_run_array_detach(net, type);
-		list_for_each_entry(net_link, &net->bpf.links[type], node)
+		list_for_each_entry(net_link, &net->bpf.links[type], node) {
 			net_link->net = NULL; /* auto-detach link */
+			netns_bpf_attach_type_unneed(type);
+		}
 		if (net->bpf.progs[type])
 			bpf_prog_put(net->bpf.progs[type]);
 	}

net/core/filter.c

@@ -9230,6 +9230,9 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
 const struct bpf_prog_ops sk_reuseport_prog_ops = {
 };
 
+DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled);
+EXPORT_SYMBOL(bpf_sk_lookup_enabled);
+
 BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
 	   struct sock *, sk, u64, flags)
 {

net/ipv4/inet_hashtables.c

@@ -299,6 +299,29 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 	return result;
 }
 
+static inline struct sock *inet_lookup_run_bpf(struct net *net,
+					       struct inet_hashinfo *hashinfo,
+					       struct sk_buff *skb, int doff,
+					       __be32 saddr, __be16 sport,
+					       __be32 daddr, u16 hnum)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	if (hashinfo != &tcp_hashinfo)
+		return NULL; /* only TCP is supported */
+
+	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP,
+					    saddr, sport, daddr, hnum, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+
 struct sock *__inet_lookup_listener(struct net *net,
 				    struct inet_hashinfo *hashinfo,
 				    struct sk_buff *skb, int doff,
@@ -310,6 +333,14 @@ struct sock *__inet_lookup_listener(struct net *net,
 	struct sock *result = NULL;
 	unsigned int hash2;
 
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
+					     saddr, sport, daddr, hnum);
+		if (result)
+			goto done;
+	}
+
 	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);