bpf: Change uapi for bpf iterator map elements

Commit a5cbe05a6673 ("bpf: Implement bpf iterator for
map elements") added bpf iterator support for
map elements. The map element bpf iterator requires
info to identify a particular map. In the above
commit, the attr->link_create.target_fd is used
to carry map_fd and an enum bpf_iter_link_info
is added to uapi to specify the target_fd actually
representing a map_fd:
    enum bpf_iter_link_info {
	BPF_ITER_LINK_UNSPEC = 0,
	BPF_ITER_LINK_MAP_FD = 1,

	MAX_BPF_ITER_LINK_INFO,
    };

This is an extensible approach as we can grow
enumerator for pid, cgroup_id, etc. and we can
unionize target_fd for pid, cgroup_id, etc.
But in the future, there are chances that
more complex customization may happen, e.g.,
for tasks, it could be filtered based on
both cgroup_id and user_id.

This patch changed the uapi to have fields
	__aligned_u64	iter_info;
	__u32		iter_info_len;
for additional iter_info for link_create.
The iter_info is defined as
	union bpf_iter_link_info {
		struct {
			__u32   map_fd;
		} map;
	};

So future extension for additional customization
will be easier. The bpf_iter_link_info will be
passed to target callback to validate and generic
bpf_iter framework does not need to deal it any
more.

Note that map_fd = 0 will be considered invalid
and -EBADF will be returned to user space.

Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com

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),