Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-01-26

We've added 107 non-merge commits during the last 4 day(s) which contain
a total of 101 files changed, 6009 insertions(+), 1260 deletions(-).

The main changes are:

1) Add BPF token support to delegate a subset of BPF subsystem
   functionality from privileged system-wide daemons such as systemd
   through special mount options for userns-bound BPF fs to a trusted
   & unprivileged application. With addressed changes from Christian
   and Linus' reviews, from Andrii Nakryiko.

2) Support registration of struct_ops types from modules which helps
   projects like fuse-bpf that seeks to implement a new struct_ops type,
   from Kui-Feng Lee.

3) Add support for retrieval of cookies for perf/kprobe multi links,
   from Jiri Olsa.

4) Bigger batch of prep-work for the BPF verifier to eventually support
   preserving boundaries and tracking scalars on narrowing fills,
   from Maxim Mikityanskiy.

5) Extend the tc BPF flavor to support arbitrary TCP SYN cookies to help
   with the scenario of SYN floods, from Kuniyuki Iwashima.

6) Add code generation to inline the bpf_kptr_xchg() helper which
   improves performance when stashing/popping the allocated BPF objects,
   from Hou Tao.

7) Extend BPF verifier to track aligned ST stores as imprecise spilled
   registers, from Yonghong Song.

8) Several fixes to BPF selftests around inline asm constraints and
   unsupported VLA code generation, from Jose E. Marchesi.

9) Various updates to the BPF IETF instruction set draft document such
   as the introduction of conformance groups for instructions,
   from Dave Thaler.

10) Fix BPF verifier to make infinite loop detection in is_state_visited()
    exact to catch some too lax spill/fill corner cases,
    from Eduard Zingerman.

11) Refactor the BPF verifier pointer ALU check to allow ALU explicitly
    instead of implicitly for various register types, from Hao Sun.

12) Fix the flaky tc_redirect_dtime BPF selftest due to slowness
    in neighbor advertisement at setup time, from Martin KaFai Lau.

13) Change BPF selftests to skip callback tests for the case when the
    JIT is disabled, from Tiezhu Yang.

14) Add a small extension to libbpf which allows to auto create
    a map-in-map's inner map, from Andrey Grafin.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (107 commits)
  selftests/bpf: Add missing line break in test_verifier
  bpf, docs: Clarify definitions of various instructions
  bpf: Fix error checks against bpf_get_btf_vmlinux().
  bpf: One more maintainer for libbpf and BPF selftests
  selftests/bpf: Incorporate LSM policy to token-based tests
  selftests/bpf: Add tests for LIBBPF_BPF_TOKEN_PATH envvar
  libbpf: Support BPF token path setting through LIBBPF_BPF_TOKEN_PATH envvar
  selftests/bpf: Add tests for BPF object load with implicit token
  selftests/bpf: Add BPF object loading tests with explicit token passing
  libbpf: Wire up BPF token support at BPF object level
  libbpf: Wire up token_fd into feature probing logic
  libbpf: Move feature detection code into its own file
  libbpf: Further decouple feature checking logic from bpf_object
  libbpf: Split feature detectors definitions from cached results
  selftests/bpf: Utilize string values for delegate_xxx mount options
  bpf: Support symbolic BPF FS delegation mount options
  bpf: Fail BPF_TOKEN_CREATE if no delegation option was set on BPF FS
  bpf,selinux: Allocate bpf_security_struct per BPF token
  selftests/bpf: Add BPF token-enabled tests
  libbpf: Add BPF token support to bpf_prog_load() API
  ...
====================

Link: https://lore.kernel.org/r/20240126215710.19855-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 44 insertions, 18 deletions

diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index ae8b15e6896fd..834edc18463ac 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -12,7 +12,7 @@
 #include <net/bpf_sk_storage.h>
 
 /* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
-extern struct bpf_struct_ops bpf_tcp_congestion_ops;
+static struct bpf_struct_ops bpf_tcp_congestion_ops;
 
 static u32 unsupported_ops[] = {
 	offsetof(struct tcp_congestion_ops, get_info),
@@ -20,6 +20,7 @@ static u32 unsupported_ops[] = {
 
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
+static const struct btf_type *tcp_congestion_ops_type;
 
 static int bpf_tcp_ca_init(struct btf *btf)
 {
@@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
+	type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return -EINVAL;
+	tcp_congestion_ops_type = btf_type_by_id(btf, type_id);
+
 	return 0;
 }
 
@@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog)
 	u32 midx;
 
 	midx = prog->expected_attach_type;
-	t = bpf_tcp_congestion_ops.type;
+	t = tcp_congestion_ops_type;
 	m = &btf_type_member(t)[midx];
 
 	return __btf_member_bit_offset(t, m) / 8;
@@ -191,7 +197,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -339,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
 	.release = __bpf_tcp_ca_release,
 };
 
-struct bpf_struct_ops bpf_tcp_congestion_ops = {
+static struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
 	.unreg = bpf_tcp_ca_unreg,
@@ -350,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
 	.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
+	.owner = THIS_MODULE,
 };
 
 static int __init bpf_tcp_ca_kfunc_init(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set);
+	int ret;
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set);
+	ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops);
+
+	return ret;
 }
 late_initcall(bpf_tcp_ca_kfunc_init);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 61f1c96cfe63e..be88bf586ff9f 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -51,15 +51,6 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 			    count, &syncookie_secret[c]);
 }
 
-/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */
-static u64 tcp_ns_to_ts(bool usec_ts, u64 val)
-{
-	if (usec_ts)
-		return div_u64(val, NSEC_PER_USEC);
-
-	return div_u64(val, NSEC_PER_MSEC);
-}
-
 /*
  * when syncookies are in effect and tcp timestamps are enabled we encode
  * tcp options in the lower bits of the timestamp value that will be
@@ -304,6 +295,24 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_BPF)
+struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb)
+{
+	struct request_sock *req = inet_reqsk(skb->sk);
+
+	skb->sk = NULL;
+	skb->destructor = NULL;
+
+	if (cookie_tcp_reqsk_init(sk, skb, req)) {
+		reqsk_free(req);
+		req = NULL;
+	}
+
+	return req;
+}
+EXPORT_SYMBOL_GPL(cookie_bpf_check);
+#endif
+
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk, struct sk_buff *skb,
 					    struct tcp_options_received *tcp_opt,
@@ -404,9 +413,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	    !th->ack || th->rst)
 		goto out;
 
-	req = cookie_tcp_check(net, sk, skb);
-	if (IS_ERR(req))
-		goto out;
+	if (cookie_bpf_ok(skb)) {
+		req = cookie_bpf_check(sk, skb);
+	} else {
+		req = cookie_tcp_check(net, sk, skb);
+		if (IS_ERR(req))
+			goto out;
+	}
 	if (!req)
 		goto out_drop;
 
@@ -454,7 +467,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
-	ireq->rcv_wscale  = rcv_wscale;
+	if (!req->syncookie)
+		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);