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>

4 files changed, 12 insertions, 7 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index eab14c97c15d..0750681057c2 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -599,6 +599,9 @@ int bpf_link_create(int prog_fd, int target_fd,
 	attr.link_create.target_fd = target_fd;
 	attr.link_create.attach_type = attach_type;
 	attr.link_create.flags = OPTS_GET(opts, flags, 0);
+	attr.link_create.iter_info =
+		ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
+	attr.link_create.iter_info_len = OPTS_GET(opts, iter_info_len, 0);
 
 	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 28855fd5b5f4..015d13f25fcc 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -168,11 +168,14 @@ LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
+union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */
 struct bpf_link_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 	__u32 flags;
+	union bpf_iter_link_info *iter_info;
+	__u32 iter_info_len;
 };
-#define bpf_link_create_opts__last_field flags
+#define bpf_link_create_opts__last_field iter_info_len
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7be04e45d29c..0a06124f7999 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8306,10 +8306,8 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	if (!OPTS_VALID(opts, bpf_iter_attach_opts))
 		return ERR_PTR(-EINVAL);
 
-	if (OPTS_HAS(opts, map_fd)) {
-		target_fd = opts->map_fd;
-		link_create_opts.flags = BPF_ITER_LINK_MAP_FD;
-	}
+	link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0);
+	link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0);
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3ed1399bfbbc..5ecb4069a9f0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -267,9 +267,10 @@ LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
 
 struct bpf_iter_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 map_fd;
+	union bpf_iter_link_info *link_info;
+	__u32 link_info_len;
 };
-#define bpf_iter_attach_opts__last_field map_fd
+#define bpf_iter_attach_opts__last_field link_info_len
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_iter(struct bpf_program *prog,