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

Daniel Borkmann says:

====================
bpf 2022-08-10

We've added 23 non-merge commits during the last 7 day(s) which contain
a total of 19 files changed, 424 insertions(+), 35 deletions(-).

The main changes are:

1) Several fixes for BPF map iterator such as UAFs along with selftests, from Hou Tao.

2) Fix BPF syscall program's {copy,strncpy}_from_bpfptr() to not fault, from Jinghao Jia.

3) Reject BPF syscall programs calling BPF_PROG_RUN, from Alexei Starovoitov and YiFei Zhu.

4) Fix attach_btf_obj_id info to pick proper target BTF, from Stanislav Fomichev.

5) BPF design Q/A doc update to clarify what is not stable ABI, from Paul E. McKenney.

6) Fix BPF map's prealloc_lru_pop to not reinitialize, from Kumar Kartikeya Dwivedi.

7) Fix bpf_trampoline_put to avoid leaking ftrace hash, from Jiri Olsa.

8) Fix arm64 JIT to address sparse errors around BPF trampoline, from Xu Kuohai.

9) Fix arm64 JIT to use kvcalloc instead of kcalloc for internal program address
   offset buffer, from Aijun Sun.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: (23 commits)
  selftests/bpf: Ensure sleepable program is rejected by hash map iter
  selftests/bpf: Add write tests for sk local storage map iterator
  selftests/bpf: Add tests for reading a dangling map iter fd
  bpf: Only allow sleepable program for resched-able iterator
  bpf: Check the validity of max_rdwr_access for sock local storage map iterator
  bpf: Acquire map uref in .init_seq_private for sock{map,hash} iterator
  bpf: Acquire map uref in .init_seq_private for sock local storage map iterator
  bpf: Acquire map uref in .init_seq_private for hash map iterator
  bpf: Acquire map uref in .init_seq_private for array map iterator
  bpf: Disallow bpf programs call prog_run command.
  bpf, arm64: Fix bpf trampoline instruction endianness
  selftests/bpf: Add test for prealloc_lru_pop bug
  bpf: Don't reinit map value in prealloc_lru_pop
  bpf: Allow calling bpf_prog_test kfuncs in tracing programs
  bpf, arm64: Allocate program buffer using kvcalloc instead of kcalloc
  selftests/bpf: Excercise bpf_obj_get_info_by_fd for bpf2bpf
  bpf: Use proper target btf when exporting attach_btf_obj_id
  mptcp, btf: Add struct mptcp_sock definition when CONFIG_MPTCP is disabled
  bpf: Cleanup ftrace hash in bpf_trampoline_put
  BPF: Fix potential bad pointer dereference in bpf_sys_bpf()
  ...
====================

Link: https://lore.kernel.org/r/20220810190624.10748-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 311 insertions, 5 deletions

diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index bd6f4505e7b1..70adf7b119b9 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -66,13 +66,13 @@ struct bpf_load_and_run_opts {
 	const char *errstr;
 };
 
-long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
 
 static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 			  unsigned int size)
 {
 #ifdef __KERNEL__
-	return bpf_sys_bpf(cmd, attr, size);
+	return kern_sys_bpf(cmd, attr, size);
 #else
 	return syscall(__NR_bpf, cmd, attr, size);
 #endif
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/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 02bb8cbf9194..da860b07abb5 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -3,6 +3,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include <bpf/btf.h>
+#include "bind4_prog.skel.h"
 
 typedef int (*test_cb)(struct bpf_object *obj);
 
@@ -407,6 +408,98 @@ static void test_func_replace_global_func(void)
 				  prog_name, false, NULL);
 }
 
+static int find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	struct btf *btf;
+	int ret;
+
+	ret = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
+	if (ret)
+		return ret;
+
+	if (!info.btf_id)
+		return -EINVAL;
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	ret = libbpf_get_error(btf);
+	if (ret)
+		return ret;
+
+	ret = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+	btf__free(btf);
+	return ret;
+}
+
+static int load_fentry(int attach_prog_fd, int attach_btf_id)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		    .expected_attach_type = BPF_TRACE_FENTRY,
+		    .attach_prog_fd = attach_prog_fd,
+		    .attach_btf_id = attach_btf_id,
+	);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	return bpf_prog_load(BPF_PROG_TYPE_TRACING,
+			     "bind4_fentry",
+			     "GPL",
+			     insns,
+			     ARRAY_SIZE(insns),
+			     &opts);
+}
+
+static void test_fentry_to_cgroup_bpf(void)
+{
+	struct bind4_prog *skel = NULL;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	int cgroup_fd = -1;
+	int fentry_fd = -1;
+	int btf_id;
+
+	cgroup_fd = test__join_cgroup("/fentry_to_cgroup_bpf");
+	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+		return;
+
+	skel = bind4_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto cleanup;
+
+	skel->links.bind_v4_prog = bpf_program__attach_cgroup(skel->progs.bind_v4_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.bind_v4_prog, "bpf_program__attach_cgroup"))
+		goto cleanup;
+
+	btf_id = find_prog_btf_id("bind_v4_prog", bpf_program__fd(skel->progs.bind_v4_prog));
+	if (!ASSERT_GE(btf_id, 0, "find_prog_btf_id"))
+		goto cleanup;
+
+	fentry_fd = load_fentry(bpf_program__fd(skel->progs.bind_v4_prog), btf_id);
+	if (!ASSERT_GE(fentry_fd, 0, "load_fentry"))
+		goto cleanup;
+
+	/* Make sure bpf_obj_get_info_by_fd works correctly when attaching
+	 * to another BPF program.
+	 */
+
+	ASSERT_OK(bpf_obj_get_info_by_fd(fentry_fd, &info, &info_len),
+		  "bpf_obj_get_info_by_fd");
+
+	ASSERT_EQ(info.btf_id, 0, "info.btf_id");
+	ASSERT_EQ(info.attach_btf_id, btf_id, "info.attach_btf_id");
+	ASSERT_GT(info.attach_btf_obj_id, 0, "info.attach_btf_obj_id");
+
+cleanup:
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	if (fentry_fd >= 0)
+		close(fentry_fd);
+	bind4_prog__destroy(skel);
+}
+
 /* NOTE: affect other tests, must run in serial mode */
 void serial_test_fexit_bpf2bpf(void)
 {
@@ -430,4 +523,6 @@ void serial_test_fexit_bpf2bpf(void)
 		test_fmod_ret_freplace();
 	if (test__start_subtest("func_replace_global_func"))
 		test_func_replace_global_func();
+	if (test__start_subtest("fentry_to_cgroup_bpf"))
+		test_fentry_to_cgroup_bpf();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/lru_bug.c b/tools/testing/selftests/bpf/prog_tests/lru_bug.c
new file mode 100644
index 000000000000..3c7822390827
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lru_bug.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#include "lru_bug.skel.h"
+
+void test_lru_bug(void)
+{
+	struct lru_bug *skel;
+	int ret;
+
+	skel = lru_bug__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "lru_bug__open_and_load"))
+		return;
+	ret = lru_bug__attach(skel);
+	if (!ASSERT_OK(ret, "lru_bug__attach"))
+		goto end;
+	usleep(1);
+	ASSERT_OK(skel->data->result, "prealloc_lru_pop doesn't call check_and_init_map_value");
+end:
+	lru_bug__destroy(skel);
+}
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;
 }
diff --git a/tools/testing/selftests/bpf/progs/lru_bug.c b/tools/testing/selftests/bpf/progs/lru_bug.c
new file mode 100644
index 000000000000..687081a724b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lru_bug.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct map_value {
+	struct task_struct __kptr *ptr;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct map_value);
+} lru_map SEC(".maps");
+
+int pid = 0;
+int result = 1;
+
+SEC("fentry/bpf_ktime_get_ns")
+int printk(void *ctx)
+{
+	struct map_value v = {};
+
+	if (pid == bpf_get_current_task_btf()->pid)
+		bpf_map_update_elem(&lru_map, &(int){0}, &v, 0);
+	return 0;
+}
+
+SEC("fentry/do_nanosleep")
+int nanosleep(void *ctx)
+{
+	struct map_value val = {}, *v;
+	struct task_struct *current;
+
+	bpf_map_update_elem(&lru_map, &(int){0}, &val, 0);
+	v = bpf_map_lookup_elem(&lru_map, &(int){0});
+	if (!v)
+		return 0;
+	bpf_map_delete_elem(&lru_map, &(int){0});
+	current = bpf_get_current_task_btf();
+	v->ptr = current;
+	pid = current->pid;
+	bpf_ktime_get_ns();
+	result = !v->ptr;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";