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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-10-03

We've added 143 non-merge commits during the last 27 day(s) which contain
a total of 151 files changed, 8321 insertions(+), 1402 deletions(-).

The main changes are:

1) Add kfuncs for PKCS#7 signature verification from BPF programs, from Roberto Sassu.

2) Add support for struct-based arguments for trampoline based BPF programs,
   from Yonghong Song.

3) Fix entry IP for kprobe-multi and trampoline probes under IBT enabled, from Jiri Olsa.

4) Batch of improvements to veristat selftest tool in particular to add CSV output,
   a comparison mode for CSV outputs and filtering, from Andrii Nakryiko.

5) Add preparatory changes needed for the BPF core for upcoming BPF HID support,
   from Benjamin Tissoires.

6) Support for direct writes to nf_conn's mark field from tc and XDP BPF program
   types, from Daniel Xu.

7) Initial batch of documentation improvements for BPF insn set spec, from Dave Thaler.

8) Add a new BPF_MAP_TYPE_USER_RINGBUF map which provides single-user-space-producer /
   single-kernel-consumer semantics for BPF ring buffer, from David Vernet.

9) Follow-up fixes to BPF allocator under RT to always use raw spinlock for the BPF
   hashtab's bucket lock, from Hou Tao.

10) Allow creating an iterator that loops through only the resources of one
    task/thread instead of all, from Kui-Feng Lee.

11) Add support for kptrs in the per-CPU arraymap, from Kumar Kartikeya Dwivedi.

12) Add a new kfunc helper for nf to set src/dst NAT IP/port in a newly allocated CT
    entry which is not yet inserted, from Lorenzo Bianconi.

13) Remove invalid recursion check for struct_ops for TCP congestion control BPF
    programs, from Martin KaFai Lau.

14) Fix W^X issue with BPF trampoline and BPF dispatcher, from Song Liu.

15) Fix percpu_counter leakage in BPF hashtab allocation error path, from Tetsuo Handa.

16) Various cleanups in BPF selftests to use preferred ASSERT_* macros, from Wang Yufen.

17) Add invocation for cgroup/connect{4,6} BPF programs for ICMP pings, from YiFei Zhu.

18) Lift blinding decision under bpf_jit_harden = 1 to bpf_capable(), from Yauheni Kaliuta.

19) Various libbpf fixes and cleanups including a libbpf NULL pointer deref, from Xin Liu.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (143 commits)
  net: netfilter: move bpf_ct_set_nat_info kfunc in nf_nat_bpf.c
  Documentation: bpf: Add implementation notes documentations to table of contents
  bpf, docs: Delete misformatted table.
  selftests/xsk: Fix double free
  bpftool: Fix error message of strerror
  libbpf: Fix overrun in netlink attribute iteration
  selftests/bpf: Fix spelling mistake "unpriviledged" -> "unprivileged"
  samples/bpf: Fix typo in xdp_router_ipv4 sample
  bpftool: Remove unused struct event_ring_info
  bpftool: Remove unused struct btf_attach_point
  bpf, docs: Add TOC and fix formatting.
  bpf, docs: Add Clang note about BPF_ALU
  bpf, docs: Move Clang notes to a separate file
  bpf, docs: Linux byteswap note
  bpf, docs: Move legacy packet instructions to a separate file
  selftests/bpf: Check -EBUSY for the recurred bpf_setsockopt(TCP_CONGESTION)
  bpf: tcp: Stop bpf_setsockopt(TCP_CONGESTION) in init ops to recur itself
  bpf: Refactor bpf_setsockopt(TCP_CONGESTION) handling into another function
  bpf: Move the "cdg" tcp-cc check to the common sol_tcp_sockopt()
  bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline
  ...
====================

Link: https://lore.kernel.org/r/20221003194915.11847-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 178 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/connect_ping.c b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
new file mode 100644
index 000000000000..289218c2216c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2022 Google LLC.
+ */
+
+#define _GNU_SOURCE
+#include <sys/mount.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+#include "connect_ping.skel.h"
+
+/* 2001:db8::1 */
+#define BINDADDR_V6 { { { 0x20,0x01,0x0d,0xb8,0,0,0,0,0,0,0,0,0,0,0,1 } } }
+static const struct in6_addr bindaddr_v6 = BINDADDR_V6;
+
+static void subtest(int cgroup_fd, struct connect_ping *skel,
+		    int family, int do_bind)
+{
+	struct sockaddr_in sa4 = {
+		.sin_family = AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
+	};
+	struct sockaddr_in6 sa6 = {
+		.sin6_family = AF_INET6,
+		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
+	};
+	struct sockaddr *sa;
+	socklen_t sa_len;
+	int protocol;
+	int sock_fd;
+
+	switch (family) {
+	case AF_INET:
+		sa = (struct sockaddr *)&sa4;
+		sa_len = sizeof(sa4);
+		protocol = IPPROTO_ICMP;
+		break;
+	case AF_INET6:
+		sa = (struct sockaddr *)&sa6;
+		sa_len = sizeof(sa6);
+		protocol = IPPROTO_ICMPV6;
+		break;
+	}
+
+	memset(skel->bss, 0, sizeof(*skel->bss));
+	skel->bss->do_bind = do_bind;
+
+	sock_fd = socket(family, SOCK_DGRAM, protocol);
+	if (!ASSERT_GE(sock_fd, 0, "sock-create"))
+		return;
+
+	if (!ASSERT_OK(connect(sock_fd, sa, sa_len), "connect"))
+		goto close_sock;
+
+	if (!ASSERT_EQ(skel->bss->invocations_v4, family == AF_INET ? 1 : 0,
+		       "invocations_v4"))
+		goto close_sock;
+	if (!ASSERT_EQ(skel->bss->invocations_v6, family == AF_INET6 ? 1 : 0,
+		       "invocations_v6"))
+		goto close_sock;
+	if (!ASSERT_EQ(skel->bss->has_error, 0, "has_error"))
+		goto close_sock;
+
+	if (!ASSERT_OK(getsockname(sock_fd, sa, &sa_len),
+		       "getsockname"))
+		goto close_sock;
+
+	switch (family) {
+	case AF_INET:
+		if (!ASSERT_EQ(sa4.sin_family, family, "sin_family"))
+			goto close_sock;
+		if (!ASSERT_EQ(sa4.sin_addr.s_addr,
+			       htonl(do_bind ? 0x01010101 : INADDR_LOOPBACK),
+			       "sin_addr"))
+			goto close_sock;
+		break;
+	case AF_INET6:
+		if (!ASSERT_EQ(sa6.sin6_family, AF_INET6, "sin6_family"))
+			goto close_sock;
+		if (!ASSERT_EQ(memcmp(&sa6.sin6_addr,
+				      do_bind ? &bindaddr_v6 : &in6addr_loopback,
+				      sizeof(sa6.sin6_addr)),
+			       0, "sin6_addr"))
+			goto close_sock;
+		break;
+	}
+
+close_sock:
+	close(sock_fd);
+}
+
+void test_connect_ping(void)
+{
+	struct connect_ping *skel;
+	int cgroup_fd;
+
+	if (!ASSERT_OK(unshare(CLONE_NEWNET | CLONE_NEWNS), "unshare"))
+		return;
+
+	/* overmount sysfs, and making original sysfs private so overmount
+	 * does not propagate to other mntns.
+	 */
+	if (!ASSERT_OK(mount("none", "/sys", NULL, MS_PRIVATE, NULL),
+		       "remount-private-sys"))
+		return;
+	if (!ASSERT_OK(mount("sysfs", "/sys", "sysfs", 0, NULL),
+		       "mount-sys"))
+		return;
+	if (!ASSERT_OK(mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL),
+		       "mount-bpf"))
+		goto clean_mount;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "lo-up"))
+		goto clean_mount;
+	if (!ASSERT_OK(system("ip addr add 1.1.1.1 dev lo"), "lo-addr-v4"))
+		goto clean_mount;
+	if (!ASSERT_OK(system("ip -6 addr add 2001:db8::1 dev lo"), "lo-addr-v6"))
+		goto clean_mount;
+	if (write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0"))
+		goto clean_mount;
+
+	cgroup_fd = test__join_cgroup("/connect_ping");
+	if (!ASSERT_GE(cgroup_fd, 0, "cg-create"))
+		goto clean_mount;
+
+	skel = connect_ping__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel-load"))
+		goto close_cgroup;
+	skel->links.connect_v4_prog =
+		bpf_program__attach_cgroup(skel->progs.connect_v4_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.connect_v4_prog, "cg-attach-v4"))
+		goto skel_destroy;
+	skel->links.connect_v6_prog =
+		bpf_program__attach_cgroup(skel->progs.connect_v6_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.connect_v6_prog, "cg-attach-v6"))
+		goto skel_destroy;
+
+	/* Connect a v4 ping socket to localhost, assert that only v4 is called,
+	 * and called exactly once, and that the socket's bound address is
+	 * original loopback address.
+	 */
+	if (test__start_subtest("ipv4"))
+		subtest(cgroup_fd, skel, AF_INET, 0);
+
+	/* Connect a v4 ping socket to localhost, assert that only v4 is called,
+	 * and called exactly once, and that the socket's bound address is
+	 * address we explicitly bound.
+	 */
+	if (test__start_subtest("ipv4-bind"))
+		subtest(cgroup_fd, skel, AF_INET, 1);
+
+	/* Connect a v6 ping socket to localhost, assert that only v6 is called,
+	 * and called exactly once, and that the socket's bound address is
+	 * original loopback address.
+	 */
+	if (test__start_subtest("ipv6"))
+		subtest(cgroup_fd, skel, AF_INET6, 0);
+
+	/* Connect a v6 ping socket to localhost, assert that only v6 is called,
+	 * and called exactly once, and that the socket's bound address is
+	 * address we explicitly bound.
+	 */
+	if (test__start_subtest("ipv6-bind"))
+		subtest(cgroup_fd, skel, AF_INET6, 1);
+
+skel_destroy:
+	connect_ping__destroy(skel);
+
+close_cgroup:
+	close(cgroup_fd);
+
+clean_mount:
+	umount2("/sys", MNT_DETACH);
+}