bpf-for-netdev

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCZIDxUwAKCRDbK58LschI
 g5hDAQD7ukrniCvMRNIm2yUZIGSxE4RvGiXptO4a0NfLck5R/wEAsfN2KUsPcPhW
 HS37lVfx7VVXfj42+REf7lWLu4TXpwk=
 =6mS/
 -----END PGP SIGNATURE-----

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

Daniel Borkmann says:

====================
pull-request: bpf 2023-06-07

We've added 7 non-merge commits during the last 7 day(s) which contain
a total of 12 files changed, 112 insertions(+), 7 deletions(-).

The main changes are:

1) Fix a use-after-free in BPF's task local storage, from KP Singh.

2) Make struct path handling more robust in bpf_d_path, from Jiri Olsa.

3) Fix a syzbot NULL-pointer dereference in sockmap, from Eric Dumazet.

4) UAPI fix for BPF_NETFILTER before final kernel ships,
   from Florian Westphal.

5) Fix map-in-map array_map_gen_lookup code generation where elem_size was
   not being set for inner maps, from Rhys Rustad-Elliott.

6) Fix sockopt_sk selftest's NETLINK_LIST_MEMBERSHIPS assertion,
   from Yonghong Song.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Add extra path pointer check to d_path helper
  selftests/bpf: Fix sockopt_sk selftest
  bpf: netfilter: Add BPF_NETFILTER bpf_attach_type
  selftests/bpf: Add access_inner_map selftest
  bpf: Fix elem_size not being set for inner maps
  bpf: Fix UAF in task local storage
  bpf, sockmap: Avoid potential NULL dereference in sk_psock_verdict_data_ready()
====================

Link: https://lore.kernel.org/r/20230607220514.29698-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/uapi/linux/bpf.h

@@ -1035,6 +1035,7 @@ enum bpf_attach_type {
 	BPF_TRACE_KPROBE_MULTI,
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
+	BPF_NETFILTER,
 	__MAX_BPF_ATTACH_TYPE
 };
 

kernel/bpf/map_in_map.c

@@ -69,9 +69,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	/* Misc members not needed in bpf_map_meta_equal() check. */
 	inner_map_meta->ops = inner_map->ops;
 	if (inner_map->ops == &array_map_ops) {
+		struct bpf_array *inner_array_meta =
+			container_of(inner_map_meta, struct bpf_array, map);
+		struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map);
+
+		inner_array_meta->index_mask = inner_array->index_mask;
+		inner_array_meta->elem_size = inner_array->elem_size;
 		inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
-		container_of(inner_map_meta, struct bpf_array, map)->index_mask =
-		     container_of(inner_map, struct bpf_array, map)->index_mask;
 	}
 
 	fdput(f);

kernel/bpf/syscall.c

@@ -2433,6 +2433,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_NETFILTER:
+		if (expected_attach_type == BPF_NETFILTER)
+			return 0;
+		return -EINVAL;
 	case BPF_PROG_TYPE_SYSCALL:
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
@@ -4590,7 +4594,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 
 	switch (prog->type) {
 	case BPF_PROG_TYPE_EXT:
+		break;
 	case BPF_PROG_TYPE_NETFILTER:
+		if (attr->link_create.attach_type != BPF_NETFILTER) {
+			ret = -EINVAL;
+			goto out;
+		}
 		break;
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_TRACEPOINT:

kernel/fork.c

@@ -627,6 +627,7 @@ void free_task(struct task_struct *tsk)
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
+	bpf_task_storage_free(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -979,7 +980,6 @@ void __put_task_struct(struct task_struct *tsk)
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
-	bpf_task_storage_free(tsk);
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
 	put_signal_struct(tsk->signal);

kernel/trace/bpf_trace.c

@@ -900,13 +900,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
 
 BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
 {
+	struct path copy;
 	long len;
 	char *p;
 
 	if (!sz)
 		return 0;
 
-	p = d_path(path, buf, sz);
+	/*
+	 * The path pointer is verified as trusted and safe to use,
+	 * but let's double check it's valid anyway to workaround
+	 * potentially broken verifier.
+	 */
+	len = copy_from_kernel_nofault(&copy, path, sizeof(*path));
+	if (len < 0)
+		return len;
+
+	p = d_path(&copy, buf, sz);
 	if (IS_ERR(p)) {
 		len = PTR_ERR(p);
 	} else {

net/core/skmsg.c

@@ -1210,7 +1210,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
 
 		rcu_read_lock();
 		psock = sk_psock(sk);
-		psock->saved_data_ready(sk);
+		if (psock)
+			psock->saved_data_ready(sk);
 		rcu_read_unlock();
 	}
 }

tools/include/uapi/linux/bpf.h

@@ -1035,6 +1035,7 @@ enum bpf_attach_type {
 	BPF_TRACE_KPROBE_MULTI,
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
+	BPF_NETFILTER,
 	__MAX_BPF_ATTACH_TYPE
 };
 

tools/lib/bpf/libbpf.c

@@ -117,6 +117,7 @@ static const char * const attach_type_name[] = {
 	[BPF_PERF_EVENT]		= "perf_event",
 	[BPF_TRACE_KPROBE_MULTI]	= "trace_kprobe_multi",
 	[BPF_STRUCT_OPS]		= "struct_ops",
+	[BPF_NETFILTER]			= "netfilter",
 };
 
 static const char * const link_type_name[] = {
@@ -8712,7 +8713,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
 	SEC_DEF("struct_ops.s+",	STRUCT_OPS, 0, SEC_SLEEPABLE),
 	SEC_DEF("sk_lookup",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
-	SEC_DEF("netfilter",		NETFILTER, 0, SEC_NONE),
+	SEC_DEF("netfilter",		NETFILTER, BPF_NETFILTER, SEC_NONE),
 };
 
 static size_t custom_sec_def_cnt;

tools/lib/bpf/libbpf_probes.c

@@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+		break;
 	case BPF_PROG_TYPE_NETFILTER:
+		opts.expected_attach_type = BPF_NETFILTER;
 		break;
 	default:
 		return -EOPNOTSUPP;

tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c

@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+
+#include "inner_array_lookup.skel.h"
+
+void test_inner_array_lookup(void)
+{
+	int map1_fd, err;
+	int key = 3;
+	int val = 1;
+	struct inner_array_lookup *skel;
+
+	skel = inner_array_lookup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load_skeleton"))
+		return;
+
+	err = inner_array_lookup__attach(skel);
+	if (!ASSERT_OK(err, "skeleton_attach"))
+		goto cleanup;
+
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(map1_fd, &key, &val, 0);
+
+	/* Probe should have set the element at index 3 to 2 */
+	bpf_map_lookup_elem(map1_fd, &key, &val);
+	ASSERT_EQ(val, 2, "value_is_2");
+
+cleanup:
+	inner_array_lookup__destroy(skel);
+}

tools/testing/selftests/bpf/prog_tests/sockopt_sk.c

@@ -209,7 +209,7 @@ static int getsetsockopt(void)
 			err, errno);
 		goto err;
 	}
-	ASSERT_EQ(optlen, 4, "Unexpected NETLINK_LIST_MEMBERSHIPS value");
+	ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value");
 
 	free(big_buf);
 	close(fd);

tools/testing/selftests/bpf/progs/inner_array_lookup.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct inner_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 5);
+	__type(key, int);
+	__type(value, int);
+} inner_map1 SEC(".maps");
+
+struct outer_map {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 3);
+	__type(key, int);
+	__array(values, struct inner_map);
+} outer_map1 SEC(".maps") = {
+	.values = {
+		[2] = &inner_map1,
+	},
+};
+
+SEC("raw_tp/sys_enter")
+int handle__sys_enter(void *ctx)
+{
+	int outer_key = 2, inner_key = 3;
+	int *val;
+	void *map;
+
+	map = bpf_map_lookup_elem(&outer_map1, &outer_key);
+	if (!map)
+		return 1;
+
+	val = bpf_map_lookup_elem(map, &inner_key);
+	if (!val)
+		return 1;
+
+	if (*val == 1)
+		*val = 2;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";