Merge branch 'bpf: add bpf_for_each_map_elem() helper'

Yonghong Song says:

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

This patch set introduced bpf_for_each_map_elem() helper.
The helper permits bpf program iterates through all elements
for a particular map.

The work originally inspired by an internal discussion where
firewall rules are kept in a map and bpf prog wants to
check packet 5 tuples against all rules in the map.
A bounded loop can be used but it has a few drawbacks.
As the loop iteration goes up, verification time goes up too.
For really large maps, verification may fail.
A helper which abstracts out the loop itself will not have
verification time issue.

A recent discussion in [1] involves to iterate all hash map
elements in bpf program. Currently iterating all hashmap elements
in bpf program is not easy if key space is really big.
Having a helper to abstract out the loop itself is even more
meaningful.

The proposed helper signature looks like:
  long bpf_for_each_map_elem(map, callback_fn, callback_ctx, flags)
where callback_fn is a static function and callback_ctx is
a piece of data allocated on the caller stack which can be
accessed by the callback_fn. The callback_fn signature might be
different for different maps. For example, for hash/array maps,
the signature is
  long callback_fn(map, key, val, callback_ctx)

In the rest of series, Patches 1/2/3/4 did some refactoring. Patch 5
implemented core kernel support for the helper. Patches 6 and 7
added hashmap and arraymap support. Patches 8/9 added libbpf
support. Patch 10 added bpftool support. Patches 11 and 12 added
selftests for hashmap and arraymap.

[1]: https://lore.kernel.org/bpf/20210122205415.113822-1-xiyou.wangcong@gmail.com/

Changelogs:
  v4 -> v5:
    - rebase on top of bpf-next.
  v3 -> v4:
    - better refactoring of check_func_call(), calculate subprogno outside
      of __check_func_call() helper. (Andrii)
    - better documentation (like the list of supported maps and their
      callback signatures) in uapi header. (Andrii)
    - implement and use ASSERT_LT in selftests. (Andrii)
    - a few other minor changes.
  v2 -> v3:
    - add comments in retrieve_ptr_limit(), which is in sanitize_ptr_alu(),
      to clarify the code is not executed for PTR_TO_MAP_KEY handling,
      but code is manually tested. (Alexei)
    - require BTF for callback function. (Alexei)
    - simplify hashmap/arraymap callback return handling as return value
      [0, 1] has been enforced by the verifier. (Alexei)
    - also mark global subprog (if used in ld_imm64) as RELO_SUBPROG_ADDR. (Andrii)
    - handle the condition to mark RELO_SUBPROG_ADDR properly. (Andrii)
    - make bpftool subprog insn offset dumping consist with pcrel calls. (Andrii)
  v1 -> v2:
    - setup callee frame in check_helper_call() and then proceed to verify
      helper return value as normal (Alexei)
    - use meta data to keep track of map/func pointer to avoid hard coding
      the register number (Alexei)
    - verify callback_fn return value range [0, 1]. (Alexei)
    - add migrate_{disable, enable} to ensure percpu value is the one
      bpf program expects to see. (Alexei)
    - change bpf_for_each_map_elem() return value to the number of iterated
      elements. (Andrii)
    - Change libbpf pseudo_func relo name to RELO_SUBPROG_ADDR and use
      more rigid checking for the relocation. (Andrii)
    - Better format to print out subprog address with bpftool. (Andrii)
    - Use bpf_prog_test_run to trigger bpf run, instead of bpf_iter. (Andrii)
    - Other misc changes.
====================

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

1 files changed, 130 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
new file mode 100644
index 000000000000..68eb12a287d4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "for_each_hash_map_elem.skel.h"
+#include "for_each_array_map_elem.skel.h"
+
+static unsigned int duration;
+
+static void test_hash_map(void)
+{
+	int i, err, hashmap_fd, max_entries, percpu_map_fd;
+	struct for_each_hash_map_elem *skel;
+	__u64 *percpu_valbuf = NULL;
+	__u32 key, num_cpus, retval;
+	__u64 val;
+
+	skel = for_each_hash_map_elem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_hash_map_elem__open_and_load"))
+		return;
+
+	hashmap_fd = bpf_map__fd(skel->maps.hashmap);
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i + 1;
+		err = bpf_map_update_elem(hashmap_fd, &key, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	num_cpus = bpf_num_possible_cpus();
+	percpu_map_fd = bpf_map__fd(skel->maps.percpu_map);
+	percpu_valbuf = malloc(sizeof(__u64) * num_cpus);
+	if (!ASSERT_OK_PTR(percpu_valbuf, "percpu_valbuf"))
+		goto out;
+
+	key = 1;
+	for (i = 0; i < num_cpus; i++)
+		percpu_valbuf[i] = i + 1;
+	err = bpf_map_update_elem(percpu_map_fd, &key, percpu_valbuf, BPF_ANY);
+	if (!ASSERT_OK(err, "percpu_map_update"))
+		goto out;
+
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access),
+				1, &pkt_v4, sizeof(pkt_v4), NULL, NULL,
+				&retval, &duration);
+	if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n",
+		  err, errno, retval))
+		goto out;
+
+	ASSERT_EQ(skel->bss->hashmap_output, 4, "hashmap_output");
+	ASSERT_EQ(skel->bss->hashmap_elems, max_entries, "hashmap_elems");
+
+	key = 1;
+	err = bpf_map_lookup_elem(hashmap_fd, &key, &val);
+	ASSERT_ERR(err, "hashmap_lookup");
+
+	ASSERT_EQ(skel->bss->percpu_called, 1, "percpu_called");
+	ASSERT_LT(skel->bss->cpu, num_cpus, "num_cpus");
+	ASSERT_EQ(skel->bss->percpu_map_elems, 1, "percpu_map_elems");
+	ASSERT_EQ(skel->bss->percpu_key, 1, "percpu_key");
+	ASSERT_EQ(skel->bss->percpu_val, skel->bss->cpu + 1, "percpu_val");
+	ASSERT_EQ(skel->bss->percpu_output, 100, "percpu_output");
+out:
+	free(percpu_valbuf);
+	for_each_hash_map_elem__destroy(skel);
+}
+
+static void test_array_map(void)
+{
+	__u32 key, num_cpus, max_entries, retval;
+	int i, arraymap_fd, percpu_map_fd, err;
+	struct for_each_array_map_elem *skel;
+	__u64 *percpu_valbuf = NULL;
+	__u64 val, expected_total;
+
+	skel = for_each_array_map_elem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_array_map_elem__open_and_load"))
+		return;
+
+	arraymap_fd = bpf_map__fd(skel->maps.arraymap);
+	expected_total = 0;
+	max_entries = bpf_map__max_entries(skel->maps.arraymap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i + 1;
+		/* skip the last iteration for expected total */
+		if (i != max_entries - 1)
+			expected_total += val;
+		err = bpf_map_update_elem(arraymap_fd, &key, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	num_cpus = bpf_num_possible_cpus();
+	percpu_map_fd = bpf_map__fd(skel->maps.percpu_map);
+	percpu_valbuf = malloc(sizeof(__u64) * num_cpus);
+	if (!ASSERT_OK_PTR(percpu_valbuf, "percpu_valbuf"))
+		goto out;
+
+	key = 0;
+	for (i = 0; i < num_cpus; i++)
+		percpu_valbuf[i] = i + 1;
+	err = bpf_map_update_elem(percpu_map_fd, &key, percpu_valbuf, BPF_ANY);
+	if (!ASSERT_OK(err, "percpu_map_update"))
+		goto out;
+
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access),
+				1, &pkt_v4, sizeof(pkt_v4), NULL, NULL,
+				&retval, &duration);
+	if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n",
+		  err, errno, retval))
+		goto out;
+
+	ASSERT_EQ(skel->bss->arraymap_output, expected_total, "array_output");
+	ASSERT_EQ(skel->bss->cpu + 1, skel->bss->percpu_val, "percpu_val");
+
+out:
+	free(percpu_valbuf);
+	for_each_array_map_elem__destroy(skel);
+}
+
+void test_for_each(void)
+{
+	if (test__start_subtest("hash_map"))
+		test_hash_map();
+	if (test__start_subtest("array_map"))
+		test_array_map();
+}