Merge branch 'fixes for bpf map iterator'

Hou Tao says:

====================

From: Hou Tao <houtao1@huawei.com>

Hi,

The patchset constitues three fixes for bpf map iterator:

(1) patch 1~4: fix user-after-free during reading map iterator fd
It is possible when both the corresponding link fd and map fd are
closed bfore reading the iterator fd. I had squashed these four patches
into one, but it was not friendly for stable backport, so I break these
fixes into four single patches in the end. Patch 7 is its testing patch.

(2) patch 5: fix invalidity check for values in sk local storage map
Patch 8 adds two tests for it.

(3) patch 6: reject sleepable program for non-resched map iterator
Patch 9 add a test for it.

Please check the individual patches for more details. And comments are
always welcome.

Regards,
Tao

Changes since v2:
* patch 1~6: update commit messages (from Yonghong & Martin)
* patch 7: add more detailed comments (from Yonghong)
* patch 8: use NULL directly instead of (void *)0

v1: https://lore.kernel.org/bpf/20220806074019.2756957-1-houtao@huaweicloud.com
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 144 insertions, 3 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index a33874b081b6..e89685bd587c 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -28,6 +28,7 @@
 #include "bpf_iter_test_kern6.skel.h"
 #include "bpf_iter_bpf_link.skel.h"
 #include "bpf_iter_ksym.skel.h"
+#include "bpf_iter_sockmap.skel.h"
 
 static int duration;
 
@@ -67,6 +68,50 @@ free_link:
 	bpf_link__destroy(link);
 }
 
+static void do_read_map_iter_fd(struct bpf_object_skeleton **skel, struct bpf_program *prog,
+				struct bpf_map *map)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	union bpf_iter_link_info linfo;
+	struct bpf_link *link;
+	char buf[16] = {};
+	int iter_fd, len;
+
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = bpf_map__fd(map);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(prog, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_map_iter"))
+		return;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "create_map_iter")) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	/* Close link and map fd prematurely */
+	bpf_link__destroy(link);
+	bpf_object__destroy_skeleton(*skel);
+	*skel = NULL;
+
+	/* Try to let map free work to run first if map is freed */
+	usleep(100);
+	/* Memory used by both sock map and sock local storage map are
+	 * freed after two synchronize_rcu() calls, so wait for it
+	 */
+	kern_sync_rcu();
+	kern_sync_rcu();
+
+	/* Read after both map fd and link fd are closed */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	ASSERT_GE(len, 0, "read_iterator");
+
+	close(iter_fd);
+}
+
 static int read_fd_into_buffer(int fd, char *buf, int size)
 {
 	int bufleft = size;
@@ -634,6 +679,12 @@ static void test_bpf_hash_map(void)
 			goto out;
 	}
 
+	/* Sleepable program is prohibited for hash map iterator */
+	linfo.map.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.sleepable_dummy_dump, &opts);
+	if (!ASSERT_ERR_PTR(link, "attach_sleepable_prog_to_iter"))
+		goto out;
+
 	linfo.map.map_fd = map_fd;
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
 	if (!ASSERT_OK_PTR(link, "attach_iter"))
@@ -827,6 +878,20 @@ out:
 	bpf_iter_bpf_array_map__destroy(skel);
 }
 
+static void test_bpf_array_map_iter_fd(void)
+{
+	struct bpf_iter_bpf_array_map *skel;
+
+	skel = bpf_iter_bpf_array_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_array_map__open_and_load"))
+		return;
+
+	do_read_map_iter_fd(&skel->skeleton, skel->progs.dump_bpf_array_map,
+			    skel->maps.arraymap1);
+
+	bpf_iter_bpf_array_map__destroy(skel);
+}
+
 static void test_bpf_percpu_array_map(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
@@ -1009,6 +1074,20 @@ out:
 	bpf_iter_bpf_sk_storage_helpers__destroy(skel);
 }
 
+static void test_bpf_sk_stoarge_map_iter_fd(void)
+{
+	struct bpf_iter_bpf_sk_storage_map *skel;
+
+	skel = bpf_iter_bpf_sk_storage_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_sk_storage_map__open_and_load"))
+		return;
+
+	do_read_map_iter_fd(&skel->skeleton, skel->progs.rw_bpf_sk_storage_map,
+			    skel->maps.sk_stg_map);
+
+	bpf_iter_bpf_sk_storage_map__destroy(skel);
+}
+
 static void test_bpf_sk_storage_map(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
@@ -1044,7 +1123,15 @@ static void test_bpf_sk_storage_map(void)
 	linfo.map.map_fd = map_fd;
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
-	link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts);
+	link = bpf_program__attach_iter(skel->progs.oob_write_bpf_sk_storage_map, &opts);
+	err = libbpf_get_error(link);
+	if (!ASSERT_EQ(err, -EACCES, "attach_oob_write_iter")) {
+		if (!err)
+			bpf_link__destroy(link);
+		goto out;
+	}
+
+	link = bpf_program__attach_iter(skel->progs.rw_bpf_sk_storage_map, &opts);
 	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
@@ -1052,6 +1139,7 @@ static void test_bpf_sk_storage_map(void)
 	if (!ASSERT_GE(iter_fd, 0, "create_iter"))
 		goto free_link;
 
+	skel->bss->to_add_val = time(NULL);
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
@@ -1065,6 +1153,13 @@ static void test_bpf_sk_storage_map(void)
 	if (!ASSERT_EQ(skel->bss->val_sum, expected_val, "val_sum"))
 		goto close_iter;
 
+	for (i = 0; i < num_sockets; i++) {
+		err = bpf_map_lookup_elem(map_fd, &sock_fd[i], &val);
+		if (!ASSERT_OK(err, "map_lookup") ||
+		    !ASSERT_EQ(val, i + 1 + skel->bss->to_add_val, "check_map_value"))
+			break;
+	}
+
 close_iter:
 	close(iter_fd);
 free_link:
@@ -1217,6 +1312,19 @@ out:
 	bpf_iter_task_vma__destroy(skel);
 }
 
+void test_bpf_sockmap_map_iter_fd(void)
+{
+	struct bpf_iter_sockmap *skel;
+
+	skel = bpf_iter_sockmap__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_sockmap__open_and_load"))
+		return;
+
+	do_read_map_iter_fd(&skel->skeleton, skel->progs.copy, skel->maps.sockmap);
+
+	bpf_iter_sockmap__destroy(skel);
+}
+
 void test_bpf_iter(void)
 {
 	if (test__start_subtest("btf_id_or_null"))
@@ -1267,10 +1375,14 @@ void test_bpf_iter(void)
 		test_bpf_percpu_hash_map();
 	if (test__start_subtest("bpf_array_map"))
 		test_bpf_array_map();
+	if (test__start_subtest("bpf_array_map_iter_fd"))
+		test_bpf_array_map_iter_fd();
 	if (test__start_subtest("bpf_percpu_array_map"))
 		test_bpf_percpu_array_map();
 	if (test__start_subtest("bpf_sk_storage_map"))
 		test_bpf_sk_storage_map();
+	if (test__start_subtest("bpf_sk_storage_map_iter_fd"))
+		test_bpf_sk_stoarge_map_iter_fd();
 	if (test__start_subtest("bpf_sk_storage_delete"))
 		test_bpf_sk_storage_delete();
 	if (test__start_subtest("bpf_sk_storage_get"))
@@ -1283,4 +1395,6 @@ void test_bpf_iter(void)
 		test_link_iter();
 	if (test__start_subtest("ksym"))
 		test_ksym_iter();
+	if (test__start_subtest("bpf_sockmap_map_iter_fd"))
+		test_bpf_sockmap_map_iter_fd();
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
index 0aa3cd34cbe3..d7a69217fb68 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -112,3 +112,12 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
 
 	return 0;
 }
+
+SEC("iter.s/bpf_map_elem")
+int sleepable_dummy_dump(struct bpf_iter__bpf_map_elem *ctx)
+{
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(ctx->meta->seq, "map dump starts\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
index 6b70ccaba301..c7b8e006b171 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
@@ -16,19 +16,37 @@ struct {
 
 __u32 val_sum = 0;
 __u32 ipv6_sk_count = 0;
+__u32 to_add_val = 0;
 
 SEC("iter/bpf_sk_storage_map")
-int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+int rw_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
 {
 	struct sock *sk = ctx->sk;
 	__u32 *val = ctx->value;
 
-	if (sk == (void *)0 || val == (void *)0)
+	if (sk == NULL || val == NULL)
 		return 0;
 
 	if (sk->sk_family == AF_INET6)
 		ipv6_sk_count++;
 
 	val_sum += *val;
+
+	*val += to_add_val;
+
+	return 0;
+}
+
+SEC("iter/bpf_sk_storage_map")
+int oob_write_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+{
+	struct sock *sk = ctx->sk;
+	__u32 *val = ctx->value;
+
+	if (sk == NULL || val == NULL)
+		return 0;
+
+	*(val + 1) = 0xdeadbeef;
+
 	return 0;
 }