Merge branch 'bpf-sk-lookup'

Joe Stringer says:

====================
This series proposes a new helper for the BPF API which allows BPF programs to
perform lookups for sockets in a network namespace. This would allow programs
to determine early on in processing whether the stack is expecting to receive
the packet, and perform some action (eg drop, forward somewhere) based on this
information.

The series is structured roughly into:
* Misc refactor
* Add the socket pointer type
* Add reference tracking to ensure that socket references are freed
* Extend the BPF API to add sk_lookup_xxx() / sk_release() functions
* Add tests/documentation

The helper proposed in this series includes a parameter for a tuple which must
be filled in by the caller to determine the socket to look up. The simplest
case would be filling with the contents of the packet, ie mapping the packet's
5-tuple into the parameter. In common cases, it may alternatively be useful to
reverse the direction of the tuple and perform a lookup, to find the socket
that initiates this connection; and if the BPF program ever performs a form of
IP address translation, it may further be useful to be able to look up
arbitrary tuples that are not based upon the packet, but instead based on state
held in BPF maps or hardcoded in the BPF program.

Currently, access into the socket's fields are limited to those which are
otherwise already accessible, and are restricted to read-only access.

Changes since v3:
* New patch: "bpf: Reuse canonical string formatter for ctx errs"
* Add PTR_TO_SOCKET to is_ctx_reg().
* Add a few new checks to prevent mixing of socket/non-socket pointers.
* Swap order of checks in sock_filter_is_valid_access().
* Prefix register spill macros with "bpf_".
* Add acks from previous round
* Rebase

Changes since v2:
* New patch: "selftests/bpf: Generalize dummy program types".
  This enables adding verifier tests for socket lookup with tail calls.
* Define the semantics of the new helpers more clearly in uAPI header.
* Fix release of caller_net when netns is not specified.
* Use skb->sk to find caller net when skb->dev is unavailable.
* Fix build with !CONFIG_NET.
* Replace ptr_id defensive coding when releasing reference state with an
  internal error (-EFAULT).
* Remove flags argument to sk_release().
* Add several new assembly tests suggested by Daniel.
* Add a few new C tests.
* Fix typo in verifier error message.

Changes since v1:
* Limit netns_id field to 32 bits
* Reuse reg_type_mismatch() in more places
* Reduce the number of passes at convert_ctx_access()
* Replace ptr_id defensive coding when releasing reference state with an
  internal error (-EFAULT)
* Rework 'struct bpf_sock_tuple' to allow passing a packet pointer
* Allow direct packet access from helper
* Fix compile error with CONFIG_IPV6 enabled
* Improve commit messages

Changes since RFC:
* Split up sk_lookup() into sk_lookup_tcp(), sk_lookup_udp().
* Only take references on the socket when necessary.
  * Make sk_release() only free the socket reference in this case.
* Fix some runtime reference leaks:
  * Disallow BPF_LD_[ABS|IND] instructions while holding a reference.
  * Disallow bpf_tail_call() while holding a reference.
* Prevent the same instruction being used for reference and other
  pointer type.
* Simplify locating copies of a reference during helper calls by caching
  the pointer id from the caller.
* Fix kbuild compilation warnings with particular configs.
* Improve code comments describing the new verifier pieces.
* Tested by Nitin
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 169 insertions, 12 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 72db8afb7cb6..591c698bc517 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -58,13 +58,17 @@
 #include <net/busy_poll.h>
 #include <net/tcp.h>
 #include <net/xfrm.h>
+#include <net/udp.h>
 #include <linux/bpf_trace.h>
 #include <net/xdp_sock.h>
 #include <linux/inetdevice.h>
+#include <net/inet_hashtables.h>
+#include <net/inet6_hashtables.h>
 #include <net/ip_fib.h>
 #include <net/flow.h>
 #include <net/arp.h>
 #include <net/ipv6.h>
+#include <net/net_namespace.h>
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
@@ -4813,6 +4817,141 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 };
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
+struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
+		       struct sk_buff *skb, u8 family, u8 proto)
+{
+	int dif = skb->dev->ifindex;
+	bool refcounted = false;
+	struct sock *sk = NULL;
+
+	if (family == AF_INET) {
+		__be32 src4 = tuple->ipv4.saddr;
+		__be32 dst4 = tuple->ipv4.daddr;
+		int sdif = inet_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+					   src4, tuple->ipv4.sport,
+					   dst4, tuple->ipv4.dport,
+					   dif, sdif, &refcounted);
+		else
+			sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
+					       dst4, tuple->ipv4.dport,
+					       dif, sdif, &udp_table, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
+		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
+		int sdif = inet6_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+					    src6, tuple->ipv6.sport,
+					    dst6, tuple->ipv6.dport,
+					    dif, sdif, &refcounted);
+		else
+			sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport,
+					       dst6, tuple->ipv6.dport,
+					       dif, sdif, &udp_table, skb);
+#endif
+	}
+
+	if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) {
+		WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+		sk = NULL;
+	}
+	return sk;
+}
+
+/* bpf_sk_lookup performs the core lookup for different types of sockets,
+ * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
+ * Returns the socket as an 'unsigned long' to simplify the casting in the
+ * callers to satisfy BPF_CALL declarations.
+ */
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct net *caller_net;
+	struct sock *sk = NULL;
+	u8 family = AF_UNSPEC;
+	struct net *net;
+
+	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
+	if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
+		goto out;
+
+	if (skb->dev)
+		caller_net = dev_net(skb->dev);
+	else
+		caller_net = sock_net(skb->sk);
+	if (netns_id) {
+		net = get_net_ns_by_id(caller_net, netns_id);
+		if (unlikely(!net))
+			goto out;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+		put_net(net);
+	} else {
+		net = caller_net;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+	}
+
+	if (sk)
+		sk = sk_to_full_sk(sk);
+out:
+	return (unsigned long) sk;
+}
+
+BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
+	.func		= bpf_sk_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
+	.func		= bpf_sk_lookup_udp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_1(bpf_sk_release, struct sock *, sk)
+{
+	if (!sock_flag(sk, SOCK_RCU_FREE))
+		sock_gen_put(sk);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_release_proto = {
+	.func		= bpf_sk_release,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCKET,
+};
+
 bool bpf_helper_changes_pkt_data(void *func)
 {
 	if (func == bpf_skb_vlan_push ||
@@ -5019,6 +5158,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_ancestor_cgroup_id:
 		return &bpf_skb_ancestor_cgroup_id_proto;
 #endif
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5119,6 +5264,12 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_hash_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5394,23 +5545,29 @@ static bool __sock_filter_check_size(int off, int size,
 	return size == size_default;
 }
 
-static bool sock_filter_is_valid_access(int off, int size,
-					enum bpf_access_type type,
-					const struct bpf_prog *prog,
-					struct bpf_insn_access_aux *info)
+bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+			      struct bpf_insn_access_aux *info)
 {
 	if (off < 0 || off >= sizeof(struct bpf_sock))
 		return false;
 	if (off % size != 0)
 		return false;
-	if (!__sock_filter_check_attach_type(off, type,
-					     prog->expected_attach_type))
-		return false;
 	if (!__sock_filter_check_size(off, size, info))
 		return false;
 	return true;
 }
 
+static bool sock_filter_is_valid_access(int off, int size,
+					enum bpf_access_type type,
+					const struct bpf_prog *prog,
+					struct bpf_insn_access_aux *info)
+{
+	if (!bpf_sock_is_valid_access(off, size, type, info))
+		return false;
+	return __sock_filter_check_attach_type(off, type,
+					       prog->expected_attach_type);
+}
+
 static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write,
 				const struct bpf_prog *prog, int drop_verdict)
 {
@@ -6122,10 +6279,10 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
-					  const struct bpf_insn *si,
-					  struct bpf_insn *insn_buf,
-					  struct bpf_prog *prog, u32 *target_size)
+u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
+				const struct bpf_insn *si,
+				struct bpf_insn *insn_buf,
+				struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
 	int off;
@@ -7037,7 +7194,7 @@ const struct bpf_prog_ops lwt_seg6local_prog_ops = {
 const struct bpf_verifier_ops cg_sock_verifier_ops = {
 	.get_func_proto		= sock_filter_func_proto,
 	.is_valid_access	= sock_filter_is_valid_access,
-	.convert_ctx_access	= sock_filter_convert_ctx_access,
+	.convert_ctx_access	= bpf_sock_convert_ctx_access,
 };
 
 const struct bpf_prog_ops cg_sock_prog_ops = {