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, 29 insertions, 8 deletions

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index fbe1f557cb88..af86048e5afd 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -98,12 +98,21 @@ static struct bpf_iter_reg bpf_map_reg_info = {
 	.seq_info		= &bpf_map_seq_info,
 };
 
-static int bpf_iter_check_map(struct bpf_prog *prog,
-			      struct bpf_iter_aux_info *aux)
+static int bpf_iter_attach_map(struct bpf_prog *prog,
+			       union bpf_iter_link_info *linfo,
+			       struct bpf_iter_aux_info *aux)
 {
 	u32 key_acc_size, value_acc_size, key_size, value_size;
-	struct bpf_map *map = aux->map;
+	struct bpf_map *map;
 	bool is_percpu = false;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -112,7 +121,7 @@ static int bpf_iter_check_map(struct bpf_prog *prog,
 	else if (map->map_type != BPF_MAP_TYPE_HASH &&
 		 map->map_type != BPF_MAP_TYPE_LRU_HASH &&
 		 map->map_type != BPF_MAP_TYPE_ARRAY)
-		return -EINVAL;
+		goto put_map;
 
 	key_acc_size = prog->aux->max_rdonly_access;
 	value_acc_size = prog->aux->max_rdwr_access;
@@ -122,10 +131,22 @@ static int bpf_iter_check_map(struct bpf_prog *prog,
 	else
 		value_size = round_up(map->value_size, 8) * num_possible_cpus();
 
-	if (key_acc_size > key_size || value_acc_size > value_size)
-		return -EACCES;
+	if (key_acc_size > key_size || value_acc_size > value_size) {
+		err = -EACCES;
+		goto put_map;
+	}
 
+	aux->map = map;
 	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
 }
 
 DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
@@ -133,8 +154,8 @@ DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
 
 static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.target			= "bpf_map_elem",
-	.check_target		= bpf_iter_check_map,
-	.req_linfo		= BPF_ITER_LINK_MAP_FD,
+	.attach_target		= bpf_iter_attach_map,
+	.detach_target		= bpf_iter_detach_map,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),