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, 29 deletions

diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 363b9cafc2d8..b6715964b685 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -338,8 +338,8 @@ static void bpf_iter_link_release(struct bpf_link *link)
 	struct bpf_iter_link *iter_link =
 		container_of(link, struct bpf_iter_link, link);
 
-	if (iter_link->aux.map)
-		bpf_map_put_with_uref(iter_link->aux.map);
+	if (iter_link->tinfo->reg_info->detach_target)
+		iter_link->tinfo->reg_info->detach_target(&iter_link->aux);
 }
 
 static void bpf_iter_link_dealloc(struct bpf_link *link)
@@ -390,15 +390,35 @@ bool bpf_link_is_iter(struct bpf_link *link)
 
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
+	union bpf_iter_link_info __user *ulinfo;
 	struct bpf_link_primer link_primer;
 	struct bpf_iter_target_info *tinfo;
-	struct bpf_iter_aux_info aux = {};
+	union bpf_iter_link_info linfo;
 	struct bpf_iter_link *link;
-	u32 prog_btf_id, target_fd;
+	u32 prog_btf_id, linfo_len;
 	bool existed = false;
-	struct bpf_map *map;
 	int err;
 
+	if (attr->link_create.target_fd || attr->link_create.flags)
+		return -EINVAL;
+
+	memset(&linfo, 0, sizeof(union bpf_iter_link_info));
+
+	ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
+	linfo_len = attr->link_create.iter_info_len;
+	if (!ulinfo ^ !linfo_len)
+		return -EINVAL;
+
+	if (ulinfo) {
+		err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
+					       linfo_len);
+		if (err)
+			return err;
+		linfo_len = min_t(u32, linfo_len, sizeof(linfo));
+		if (copy_from_user(&linfo, ulinfo, linfo_len))
+			return -EFAULT;
+	}
+
 	prog_btf_id = prog->aux->attach_btf_id;
 	mutex_lock(&targets_mutex);
 	list_for_each_entry(tinfo, &targets, list) {
@@ -411,13 +431,6 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (!existed)
 		return -ENOENT;
 
-	/* Make sure user supplied flags are target expected. */
-	target_fd = attr->link_create.target_fd;
-	if (attr->link_create.flags != tinfo->reg_info->req_linfo)
-		return -EINVAL;
-	if (!attr->link_create.flags && target_fd)
-		return -EINVAL;
-
 	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
 	if (!link)
 		return -ENOMEM;
@@ -431,28 +444,15 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		return err;
 	}
 
-	if (tinfo->reg_info->req_linfo == BPF_ITER_LINK_MAP_FD) {
-		map = bpf_map_get_with_uref(target_fd);
-		if (IS_ERR(map)) {
-			err = PTR_ERR(map);
-			goto cleanup_link;
-		}
-
-		aux.map = map;
-		err = tinfo->reg_info->check_target(prog, &aux);
+	if (tinfo->reg_info->attach_target) {
+		err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux);
 		if (err) {
-			bpf_map_put_with_uref(map);
-			goto cleanup_link;
+			bpf_link_cleanup(&link_primer);
+			return err;
 		}
-
-		link->aux.map = map;
 	}
 
 	return bpf_link_settle(&link_primer);
-
-cleanup_link:
-	bpf_link_cleanup(&link_primer);
-	return err;
 }
 
 static void init_seq_meta(struct bpf_iter_priv_data *priv_data,