Merge branch 'bpf_iter-uapi-fix'

Yonghong Song says:

====================
Andrii raised a concern that current uapi for bpf iterator map
element is a little restrictive and not suitable for future potential
complex customization. This is a valid suggestion, considering people
may indeed add more complex custimization to the iterator, e.g.,
cgroup_id + user_id, etc. for task or task_file. Another example might
be map_id plus additional control so that the bpf iterator may bail
out a bucket earlier if a bucket has too many elements which may hold
lock too long and impact other parts of systems.

Patch #1 modified uapi with kernel changes. Patch #2
adjusted libbpf api accordingly.

Changelogs:
  v3 -> v4:
    . add a forward declaration of bpf_iter_link_info in
      tools/lib/bpf/bpf.h in case that libbpf is built against
      not-latest uapi bpf.h.
    . target the patch set to "bpf" instead of "bpf-next"
  v2 -> v3:
    . undo "not reject iter_info.map.map_fd == 0" from v1.
      In the future map_fd may become optional, so let us use map_fd == 0
      indicating the map_fd is not set by user space.
    . add link_info_len to bpf_iter_attach_opts to ensure always correct
      link_info_len from user. Otherwise, libbpf may deduce incorrect
      link_info_len if it uses different uapi header than the user app.
  v1 -> v2:
    . ensure link_create target_fd/flags == 0 since they are not used. (Andrii)
    . if either of iter_info ptr == 0 or iter_info_len == 0, but not both,
      return error to user space. (Andrii)
    . do not reject iter_info.map.map_fd == 0, go ahead to use it trying to
      get a map reference since the map_fd is required for map_elem iterator.
    . use bpf_iter_link_info in bpf_iter_attach_opts instead of map_fd.
      this way, user space is responsible to set up bpf_iter_link_info and
      libbpf just passes the data to the kernel, simplifying libbpf design.
      (Andrii)
====================

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

1 files changed, 32 insertions, 8 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 4ffefdc1130f..7375d9a6d242 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -468,6 +468,7 @@ static void test_bpf_hash_map(void)
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_bpf_hash_map *skel;
 	int err, i, len, map_fd, iter_fd;
+	union bpf_iter_link_info linfo;
 	__u64 val, expected_val = 0;
 	struct bpf_link *link;
 	struct key_t {
@@ -490,13 +491,16 @@ static void test_bpf_hash_map(void)
 		goto out;
 
 	/* iterator with hashmap2 and hashmap3 should fail */
-	opts.map_fd = bpf_map__fd(skel->maps.hashmap2);
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap2);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
 	if (CHECK(!IS_ERR(link), "attach_iter",
 		  "attach_iter for hashmap2 unexpected succeeded\n"))
 		goto out;
 
-	opts.map_fd = bpf_map__fd(skel->maps.hashmap3);
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap3);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
 	if (CHECK(!IS_ERR(link), "attach_iter",
 		  "attach_iter for hashmap3 unexpected succeeded\n"))
@@ -519,7 +523,7 @@ static void test_bpf_hash_map(void)
 			goto out;
 	}
 
-	opts.map_fd = map_fd;
+	linfo.map.map_fd = map_fd;
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
@@ -562,6 +566,7 @@ static void test_bpf_percpu_hash_map(void)
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_bpf_percpu_hash_map *skel;
 	int err, i, j, len, map_fd, iter_fd;
+	union bpf_iter_link_info linfo;
 	__u32 expected_val = 0;
 	struct bpf_link *link;
 	struct key_t {
@@ -606,7 +611,10 @@ static void test_bpf_percpu_hash_map(void)
 			goto out;
 	}
 
-	opts.map_fd = map_fd;
+	memset(&linfo, 0, sizeof(linfo));
+	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_percpu_hash_map, &opts);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
@@ -649,6 +657,7 @@ static void test_bpf_array_map(void)
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	__u32 expected_key = 0, res_first_key;
 	struct bpf_iter_bpf_array_map *skel;
+	union bpf_iter_link_info linfo;
 	int err, i, map_fd, iter_fd;
 	struct bpf_link *link;
 	char buf[64] = {};
@@ -673,7 +682,10 @@ static void test_bpf_array_map(void)
 			goto out;
 	}
 
-	opts.map_fd = map_fd;
+	memset(&linfo, 0, sizeof(linfo));
+	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_array_map, &opts);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
@@ -730,6 +742,7 @@ static void test_bpf_percpu_array_map(void)
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_bpf_percpu_array_map *skel;
 	__u32 expected_key = 0, expected_val = 0;
+	union bpf_iter_link_info linfo;
 	int err, i, j, map_fd, iter_fd;
 	struct bpf_link *link;
 	char buf[64];
@@ -765,7 +778,10 @@ static void test_bpf_percpu_array_map(void)
 			goto out;
 	}
 
-	opts.map_fd = map_fd;
+	memset(&linfo, 0, sizeof(linfo));
+	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_percpu_array_map, &opts);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
@@ -803,6 +819,7 @@ static void test_bpf_sk_storage_map(void)
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	int err, i, len, map_fd, iter_fd, num_sockets;
 	struct bpf_iter_bpf_sk_storage_map *skel;
+	union bpf_iter_link_info linfo;
 	int sock_fd[3] = {-1, -1, -1};
 	__u32 val, expected_val = 0;
 	struct bpf_link *link;
@@ -829,7 +846,10 @@ static void test_bpf_sk_storage_map(void)
 			goto out;
 	}
 
-	opts.map_fd = map_fd;
+	memset(&linfo, 0, sizeof(linfo));
+	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);
 	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
 		goto out;
@@ -871,6 +891,7 @@ static void test_rdonly_buf_out_of_bound(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_test_kern5 *skel;
+	union bpf_iter_link_info linfo;
 	struct bpf_link *link;
 
 	skel = bpf_iter_test_kern5__open_and_load();
@@ -878,7 +899,10 @@ static void test_rdonly_buf_out_of_bound(void)
 		  "skeleton open_and_load failed\n"))
 		return;
 
-	opts.map_fd = bpf_map__fd(skel->maps.hashmap1);
+	memset(&linfo, 0, sizeof(linfo));
+	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap1);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
 	if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n"))
 		bpf_link__destroy(link);