Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Alexei Starovoitov:

 - Fix sk_local_storage diag dump via netlink (Amery Hung)

 - Fix off-by-one in arena direct-value access (Junyoung Jang)

 - Reject TCP_NODELAY in bpf-tcp congestion control (KaFai Wan)

 - Fix type confusion in bpf_*_sock() (Kuniyuki Iwashima)

 - Reject TX-only AF_XDP sockets (Linpu Yu)

 - Don't run arg-tracking analysis twice on main subprog (Paul Chaignon)

 - Fix NULL pointer dereference in bpf_sk_storage_clone and fib lookup
   (Weiming Shi)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Fix off-by-one boundary validation in arena direct-value access
  xskmap: reject TX-only AF_XDP sockets
  bpf: Don't run arg-tracking analysis twice on main subprog
  bpf: Free reuseport cBPF prog after RCU grace period.
  bpf: tcp: Fix type confusion in sol_tcp_sockopt().
  bpf: tcp: Fix type confusion in bpf_skc_to_tcp6_sock().
  bpf: tcp: Fix type confusion in bpf_skc_to_tcp_sock().
  mptcp: bpf: Fix type confusion in bpf_mptcp_sock_from_subflow()
  selftest: bpf: Add test for bpf_tcp_sock() and RAW socket.
  bpf: tcp: Fix type confusion in bpf_tcp_sock().
  tools/headers: Regenerate stddef.h to fix BPF selftests
  bpf: Fix sk_local_storage diag dumping uninitialized special fields
  bpf: Fix NULL pointer dereference in bpf_skb_fib_lookup()
  sockmap: Fix sk_psock_drop() race vs sock_map_{unhash,close,destroy}().
  bpf: Fix NULL pointer dereference in bpf_sk_storage_clone and diag paths
  selftests/bpf: Verify bpf-tcp-cc rejects TCP_NODELAY
  selftests/bpf: Test TCP_NODELAY in TCP hdr opt callbacks
  bpf: Reject TCP_NODELAY in bpf-tcp-cc
  bpf: Reject TCP_NODELAY in TCP header option callbacks

7 files changed, 93 insertions, 3 deletions

diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
index c53cde425406..457498259494 100644
--- a/tools/include/uapi/linux/stddef.h
+++ b/tools/include/uapi/linux/stddef.h
@@ -3,7 +3,6 @@
 #define _LINUX_STDDEF_H
 
 
-
 #ifndef __always_inline
 #define __always_inline __inline__
 #endif
@@ -36,6 +35,11 @@
 		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
 	} ATTRS
 
+#ifdef __cplusplus
+/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
+#define __DECLARE_FLEX_ARRAY(T, member)	\
+	T member[0]
+#else
 /**
  * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
  *
@@ -52,3 +56,23 @@
 		TYPE NAME[]; \
 	}
 #endif
+
+#ifndef __counted_by
+#define __counted_by(m)
+#endif
+
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
+#ifndef __counted_by_ptr
+#define __counted_by_ptr(m)
+#endif
+
+#define __kernel_nonstring
+
+#endif /* _LINUX_STDDEF_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index f829b6f09bc9..fe30181e6336 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -112,6 +112,10 @@ static void test_cubic(void)
 
 	ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called");
 
+	ASSERT_TRUE(cubic_skel->bss->nodelay_init_reject, "init reject nodelay option");
+	ASSERT_TRUE(cubic_skel->bss->nodelay_cwnd_event_tx_start_reject,
+		    "cwnd_event_tx_start reject nodelay option");
+
 	bpf_link__destroy(link);
 	bpf_cubic__destroy(cubic_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 53637431ec5d..3a41c517b918 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -190,7 +190,7 @@ static int getsetsockopt(void)
 	fd = socket(AF_NETLINK, SOCK_RAW, 0);
 	if (fd < 0) {
 		log_err("Failed to create AF_NETLINK socket");
-		return -1;
+		goto err;
 	}
 
 	buf.u32 = 1;
@@ -211,6 +211,21 @@ static int getsetsockopt(void)
 	}
 	ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value");
 
+	/* Trick bpf_tcp_sock() with IPPROTO_TCP */
+	close(fd);
+	fd = socket(AF_INET, SOCK_RAW, IPPROTO_TCP);
+	if (!ASSERT_OK_FD(fd, "socket"))
+		goto err;
+
+	/* The BPF prog intercepts this before the kernel sees it, any
+	 * optlen works. Go with 4 bytes for simplicity.
+	 */
+	buf.u32 = 1;
+	optlen = sizeof(buf.u32);
+	err = setsockopt(fd, SOL_TCP, TCP_SAVED_SYN, &buf, optlen);
+	if (!ASSERT_ERR(err, "setsockopt(TCP_SAVED_SYN)"))
+		goto err;
+
 	free(big_buf);
 	close(fd);
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 56685fc03c7e..80e6315da2a5 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -507,6 +507,10 @@ static void misc(void)
 
 	ASSERT_EQ(misc_skel->bss->nr_hwtstamp, 0, "nr_hwtstamp");
 
+	ASSERT_TRUE(misc_skel->bss->nodelay_est_ok, "nodelay_est_ok");
+	ASSERT_TRUE(misc_skel->bss->nodelay_hdr_len_reject, "nodelay_hdr_len_reject");
+	ASSERT_TRUE(misc_skel->bss->nodelay_write_hdr_reject, "nodelay_write_hdr_reject");
+
 check_linum:
 	ASSERT_FALSE(check_error_linum(&sk_fds), "check_error_linum");
 	sk_fds_close(&sk_fds);
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index ce18a4db813f..ebd5a1e69f56 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -16,6 +16,7 @@
 
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_tracing.h>
+#include <errno.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -170,10 +171,18 @@ static void bictcp_hystart_reset(struct sock *sk)
 	ca->sample_cnt = 0;
 }
 
+bool nodelay_init_reject = false;
+bool nodelay_cwnd_event_tx_start_reject = false;
+
 SEC("struct_ops")
 void BPF_PROG(bpf_cubic_init, struct sock *sk)
 {
 	struct bpf_bictcp *ca = inet_csk_ca(sk);
+	int true_val = 1, ret;
+
+	ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+	if (ret == -EOPNOTSUPP)
+		nodelay_init_reject = true;
 
 	bictcp_reset(ca);
 
@@ -189,8 +198,13 @@ void BPF_PROG(bpf_cubic_cwnd_event_tx_start, struct sock *sk)
 {
 	struct bpf_bictcp *ca = inet_csk_ca(sk);
 	__u32 now = tcp_jiffies32;
+	int true_val = 1, ret;
 	__s32 delta;
 
+	ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+	if (ret == -EOPNOTSUPP)
+		nodelay_cwnd_event_tx_start_reject = true;
+
 	delta = now - tcp_sk(sk)->lsndtime;
 
 	/* We were application limited (idle) for a while.
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index cb990a7d3d45..5e0b27e7855c 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -149,6 +149,20 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	if (sk && sk->family == AF_NETLINK)
 		goto out;
 
+	if (sk && sk->family == AF_INET && sk->type == SOCK_RAW) {
+		struct bpf_tcp_sock *tp = bpf_tcp_sock(sk);
+
+		if (tp) {
+			char saved_syn[60];
+
+			bpf_getsockopt(sk, SOL_TCP, TCP_SAVED_SYN,
+				       &saved_syn, sizeof(saved_syn));
+			goto consumed;
+		}
+
+		goto out;
+	}
+
 	/* Make sure bpf_get_netns_cookie is callable.
 	 */
 	if (bpf_get_netns_cookie(NULL) == 0)
@@ -224,6 +238,8 @@ int _setsockopt(struct bpf_sockopt *ctx)
 		return 0; /* couldn't get sk storage */
 
 	storage->val = optval[0];
+
+consumed:
 	ctx->optlen = -1; /* BPF has consumed this option, don't call kernel
 			   * setsockopt handler.
 			   */
diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
index d487153a839d..ed5a0011b863 100644
--- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
@@ -29,6 +29,10 @@ unsigned int nr_syn = 0;
 unsigned int nr_fin = 0;
 unsigned int nr_hwtstamp = 0;
 
+bool nodelay_est_ok = false;
+bool nodelay_hdr_len_reject = false;
+bool nodelay_write_hdr_reject = false;
+
 /* Check the header received from the active side */
 static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn)
 {
@@ -300,7 +304,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops)
 SEC("sockops")
 int misc_estab(struct bpf_sock_ops *skops)
 {
-	int true_val = 1;
+	int true_val = 1, false_val = 0, ret;
 
 	switch (skops->op) {
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
@@ -316,10 +320,19 @@ int misc_estab(struct bpf_sock_ops *skops)
 	case BPF_SOCK_OPS_PARSE_HDR_OPT_CB:
 		return handle_parse_hdr(skops);
 	case BPF_SOCK_OPS_HDR_OPT_LEN_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+		if (ret == -EOPNOTSUPP)
+			nodelay_hdr_len_reject = true;
 		return handle_hdr_opt_len(skops);
 	case BPF_SOCK_OPS_WRITE_HDR_OPT_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+		if (ret == -EOPNOTSUPP)
+			nodelay_write_hdr_reject = true;
 		return handle_write_hdr_opt(skops);
 	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &false_val, sizeof(false_val));
+		if (!ret)
+			nodelay_est_ok = true;
 		return handle_passive_estab(skops);
 	}