Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-06-17

We've added 72 non-merge commits during the last 15 day(s) which contain
a total of 92 files changed, 4582 insertions(+), 834 deletions(-).

The main changes are:

1) Add 64 bit enum value support to BTF, from Yonghong Song.

2) Implement support for sleepable BPF uprobe programs, from Delyan Kratunov.

3) Add new BPF helpers to issue and check TCP SYN cookies without binding to a
   socket especially useful in synproxy scenarios, from Maxim Mikityanskiy.

4) Fix libbpf's internal USDT address translation logic for shared libraries as
   well as uprobe's symbol file offset calculation, from Andrii Nakryiko.

5) Extend libbpf to provide an API for textual representation of the various
   map/prog/attach/link types and use it in bpftool, from Daniel Müller.

6) Provide BTF line info for RV64 and RV32 JITs, and fix a put_user bug in the
   core seen in 32 bit when storing BPF function addresses, from Pu Lehui.

7) Fix libbpf's BTF pointer size guessing by adding a list of various aliases
   for 'long' types, from Douglas Raillard.

8) Fix bpftool to readd setting rlimit since probing for memcg-based accounting
   has been unreliable and caused a regression on COS, from Quentin Monnet.

9) Fix UAF in BPF cgroup's effective program computation triggered upon BPF link
   detachment, from Tadeusz Struk.

10) Fix bpftool build bootstrapping during cross compilation which was pointing
    to the wrong AR process, from Shahab Vahedi.

11) Fix logic bug in libbpf's is_pow_of_2 implementation, from Yuze Chi.

12) BPF hash map optimization to avoid grabbing spinlocks of all CPUs when there
    is no free element. Also add a benchmark as reproducer, from Feng Zhou.

13) Fix bpftool's codegen to bail out when there's no BTF, from Michael Mullin.

14) Various minor cleanup and improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (72 commits)
  bpf: Fix bpf_skc_lookup comment wrt. return type
  bpf: Fix non-static bpf_func_proto struct definitions
  selftests/bpf: Don't force lld on non-x86 architectures
  selftests/bpf: Add selftests for raw syncookie helpers in TC mode
  bpf: Allow the new syncookie helpers to work with SKBs
  selftests/bpf: Add selftests for raw syncookie helpers
  bpf: Add helpers to issue and check SYN cookies in XDP
  bpf: Allow helpers to accept pointers with a fixed size
  bpf: Fix documentation of th_len in bpf_tcp_{gen,check}_syncookie
  selftests/bpf: add tests for sleepable (uk)probes
  libbpf: add support for sleepable uprobe programs
  bpf: allow sleepable uprobe programs to attach
  bpf: implement sleepable uprobes by chaining gps
  bpf: move bpf_prog to bpf.h
  libbpf: Fix internal USDT address translation logic for shared libraries
  samples/bpf: Check detach prog exist or not in xdp_fwd
  selftests/bpf: Avoid skipping certain subtests
  selftests/bpf: Fix test_varlen verification failure with latest llvm
  bpftool: Do not check return value from libbpf_set_strict_mode()
  Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK"
  ...
====================

Link: https://lore.kernel.org/r/20220617220836.7373-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 152 insertions, 2 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 5af58eb48587..151aa4756bd6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6463,8 +6463,6 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 
 /* bpf_skc_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 struct sock *
 __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
@@ -7444,6 +7442,114 @@ static const struct bpf_func_proto bpf_skb_set_tstamp_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
+#ifdef CONFIG_SYN_COOKIES
+BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph,
+	   struct tcphdr *, th, u32, th_len)
+{
+	u32 cookie;
+	u16 mss;
+
+	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+		return -EINVAL;
+
+	mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT;
+	cookie = __cookie_v4_init_sequence(iph, th, &mss);
+
+	return cookie | ((u64)mss << 32);
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = {
+	.func		= bpf_tcp_raw_gen_syncookie_ipv4,
+	.gpl_only	= true, /* __cookie_v4_init_sequence() is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg1_size	= sizeof(struct iphdr),
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph,
+	   struct tcphdr *, th, u32, th_len)
+{
+#if IS_BUILTIN(CONFIG_IPV6)
+	const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
+		sizeof(struct ipv6hdr);
+	u32 cookie;
+	u16 mss;
+
+	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+		return -EINVAL;
+
+	mss = tcp_parse_mss_option(th, 0) ?: mss_clamp;
+	cookie = __cookie_v6_init_sequence(iph, th, &mss);
+
+	return cookie | ((u64)mss << 32);
+#else
+	return -EPROTONOSUPPORT;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = {
+	.func		= bpf_tcp_raw_gen_syncookie_ipv6,
+	.gpl_only	= true, /* __cookie_v6_init_sequence() is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg1_size	= sizeof(struct ipv6hdr),
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph,
+	   struct tcphdr *, th)
+{
+	u32 cookie = ntohl(th->ack_seq) - 1;
+
+	if (__cookie_v4_check(iph, th, cookie) > 0)
+		return 0;
+
+	return -EACCES;
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = {
+	.func		= bpf_tcp_raw_check_syncookie_ipv4,
+	.gpl_only	= true, /* __cookie_v4_check is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg1_size	= sizeof(struct iphdr),
+	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg2_size	= sizeof(struct tcphdr),
+};
+
+BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph,
+	   struct tcphdr *, th)
+{
+#if IS_BUILTIN(CONFIG_IPV6)
+	u32 cookie = ntohl(th->ack_seq) - 1;
+
+	if (__cookie_v6_check(iph, th, cookie) > 0)
+		return 0;
+
+	return -EACCES;
+#else
+	return -EPROTONOSUPPORT;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = {
+	.func		= bpf_tcp_raw_check_syncookie_ipv6,
+	.gpl_only	= true, /* __cookie_v6_check is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg1_size	= sizeof(struct ipv6hdr),
+	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
+	.arg2_size	= sizeof(struct tcphdr),
+};
+#endif /* CONFIG_SYN_COOKIES */
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -7807,6 +7913,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_assign_proto;
 	case BPF_FUNC_skb_set_tstamp:
 		return &bpf_skb_set_tstamp_proto;
+#ifdef CONFIG_SYN_COOKIES
+	case BPF_FUNC_tcp_raw_gen_syncookie_ipv4:
+		return &bpf_tcp_raw_gen_syncookie_ipv4_proto;
+	case BPF_FUNC_tcp_raw_gen_syncookie_ipv6:
+		return &bpf_tcp_raw_gen_syncookie_ipv6_proto;
+	case BPF_FUNC_tcp_raw_check_syncookie_ipv4:
+		return &bpf_tcp_raw_check_syncookie_ipv4_proto;
+	case BPF_FUNC_tcp_raw_check_syncookie_ipv6:
+		return &bpf_tcp_raw_check_syncookie_ipv6_proto;
+#endif
 #endif
 	default:
 		return bpf_sk_base_func_proto(func_id);
@@ -7856,6 +7972,16 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_check_syncookie_proto;
 	case BPF_FUNC_tcp_gen_syncookie:
 		return &bpf_tcp_gen_syncookie_proto;
+#ifdef CONFIG_SYN_COOKIES
+	case BPF_FUNC_tcp_raw_gen_syncookie_ipv4:
+		return &bpf_tcp_raw_gen_syncookie_ipv4_proto;
+	case BPF_FUNC_tcp_raw_gen_syncookie_ipv6:
+		return &bpf_tcp_raw_gen_syncookie_ipv6_proto;
+	case BPF_FUNC_tcp_raw_check_syncookie_ipv4:
+		return &bpf_tcp_raw_check_syncookie_ipv4_proto;
+	case BPF_FUNC_tcp_raw_check_syncookie_ipv6:
+		return &bpf_tcp_raw_check_syncookie_ipv6_proto;
+#endif
 #endif
 	default:
 		return bpf_sk_base_func_proto(func_id);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 22b983ade0e7..7e03f96e441b 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -715,6 +715,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	psock->eval = __SK_NONE;
 	psock->sk_proto = prot;
 	psock->saved_unhash = prot->unhash;
+	psock->saved_destroy = prot->destroy;
 	psock->saved_close = prot->close;
 	psock->saved_write_space = sk->sk_write_space;
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 81d4b4756a02..9f08ccfaf6da 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1561,6 +1561,29 @@ void sock_map_unhash(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sock_map_unhash);
 
+void sock_map_destroy(struct sock *sk)
+{
+	void (*saved_destroy)(struct sock *sk);
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		if (sk->sk_prot->destroy)
+			sk->sk_prot->destroy(sk);
+		return;
+	}
+
+	saved_destroy = psock->saved_destroy;
+	sock_map_remove_links(sk, psock);
+	rcu_read_unlock();
+	sk_psock_stop(psock, true);
+	sk_psock_put(sk, psock);
+	saved_destroy(sk);
+}
+EXPORT_SYMBOL_GPL(sock_map_destroy);
+
 void sock_map_close(struct sock *sk, long timeout)
 {
 	void (*saved_close)(struct sock *sk, long timeout);