Merge branch 'bpf-sk-storage-clone'

Stanislav Fomichev says:

====================
Currently there is no way to propagate sk storage from the listener
socket to a newly accepted one. Consider the following use case:

        fd = socket();
        setsockopt(fd, SOL_IP, IP_TOS,...);
        /* ^^^ setsockopt BPF program triggers here and saves something
         * into sk storage of the listener.
         */
        listen(fd, ...);
        while (client = accept(fd)) {
                /* At this point all association between listener
                 * socket and newly accepted one is gone. New
                 * socket will not have any sk storage attached.
                 */
        }

Let's add new BPF_F_CLONE flag that can be specified when creating
a socket storage map. This new flag indicates that map contents
should be cloned when the socket is cloned.

v4:
* drop 'goto err' in bpf_sk_storage_clone (Yonghong Song)
* add comment about race with bpf_sk_storage_map_free to the
  bpf_sk_storage_clone side as well (Daniel Borkmann)

v3:
* make sure BPF_F_NO_PREALLOC is always present when creating
  a map (Martin KaFai Lau)
* don't call bpf_sk_storage_free explicitly, rely on
  sk_free_unlock_clone to do the cleanup (Martin KaFai Lau)

v2:
* remove spinlocks around selem_link_map/sk (Martin KaFai Lau)
* BPF_F_CLONE on a map, not selem (Martin KaFai Lau)
* hold a map while cloning (Martin KaFai Lau)
* use BTF maps in selftests (Yonghong Song)
* do proper cleanup selftests; don't call close(-1) (Yonghong Song)
* export bpf_map_inc_not_zero
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

3 files changed, 15 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f9a506147c8a..15ae49862b82 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -647,6 +647,8 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
 struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map,
+						   bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index b9dcb02e756b..8e4f831d2e52 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -10,4 +10,14 @@ void bpf_sk_storage_free(struct sock *sk);
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
 
+#ifdef CONFIG_BPF_SYSCALL
+int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
+#else
+static inline int bpf_sk_storage_clone(const struct sock *sk,
+				       struct sock *newsk)
+{
+	return 0;
+}
+#endif
+
 #endif /* _BPF_SK_STORAGE_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4393bd4b2419..0ef594ac3899 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -337,6 +337,9 @@ enum bpf_attach_type {
 #define BPF_F_RDONLY_PROG	(1U << 7)
 #define BPF_F_WRONLY_PROG	(1U << 8)
 
+/* Clone map from listener for newly accepted socket */
+#define BPF_F_CLONE		(1U << 9)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)