bpf: implement syscall command BPF_MAP_GET_NEXT_KEY for stacktrace map

Currently, bpf syscall command BPF_MAP_GET_NEXT_KEY is not
supported for stacktrace map. However, there are use cases where
user space wants to enumerate all stacktrace map entries where
BPF_MAP_GET_NEXT_KEY command will be really helpful.
In addition, if user space wants to delete all map entries
in order to save memory and does not want to close the
map file descriptor, BPF_MAP_GET_NEXT_KEY may help improve
performance if map entries are sparsely populated.

The implementation has similar behavior for
BPF_MAP_GET_NEXT_KEY implementation in hashtab. If user provides
a NULL key pointer or an invalid key, the first key is returned.
Otherwise, the first valid key after the input parameter "key"
is returned, or -ENOENT if no valid key can be found.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 26 insertions, 2 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a15bc636cc98..6c63c2222ea8 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -226,9 +226,33 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 	return 0;
 }
 
-static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+static int stack_map_get_next_key(struct bpf_map *map, void *key,
+				  void *next_key)
 {
-	return -EINVAL;
+	struct bpf_stack_map *smap = container_of(map,
+						  struct bpf_stack_map, map);
+	u32 id;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!key) {
+		id = 0;
+	} else {
+		id = *(u32 *)key;
+		if (id >= smap->n_buckets || !smap->buckets[id])
+			id = 0;
+		else
+			id++;
+	}
+
+	while (id < smap->n_buckets && !smap->buckets[id])
+		id++;
+
+	if (id >= smap->n_buckets)
+		return -ENOENT;
+
+	*(u32 *)next_key = id;
+	return 0;
 }
 
 static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,