bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP

The xskmap is yet another BPF map, very much inspired by
dev/cpu/sockmap, and is a holder of AF_XDP sockets. A user application
adds AF_XDP sockets into the map, and by using the bpf_redirect_map
helper, an XDP program can redirect XDP frames to an AF_XDP socket.

Note that a socket that is bound to certain ifindex/queue index will
*only* accept XDP frames from that netdev/queue index. If an XDP
program tries to redirect from a netdev/queue index other than what
the socket is bound to, the frame will not be received on the socket.

A socket can reside in multiple maps.

v3: Fixed race and simplified code.
v2: Removed one indirection in map lookup.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 36 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c553f6f9c6b0..68ecdb4eea09 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -676,6 +676,31 @@ static inline int sock_map_prog(struct bpf_map *map,
 }
 #endif
 
+#if defined(CONFIG_XDP_SOCKETS)
+struct xdp_sock;
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+		       struct xdp_sock *xs);
+void __xsk_map_flush(struct bpf_map *map);
+#else
+struct xdp_sock;
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+						     u32 key)
+{
+	return NULL;
+}
+
+static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+				     struct xdp_sock *xs)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void __xsk_map_flush(struct bpf_map *map)
+{
+}
+#endif
+
 /* verifier prototypes for helper functions called from eBPF programs */
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 2b28fcf6f6ae..d7df1b323082 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -49,4 +49,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
+#if defined(CONFIG_XDP_SOCKETS)
+BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
+#endif
 #endif
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index a0342dff6a4d..ce3a2ab16b8f 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -28,6 +28,7 @@ struct xdp_sock {
 	struct xsk_queue *rx;
 	struct net_device *dev;
 	struct xdp_umem *umem;
+	struct list_head flush_node;
 	u16 queue_id;
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
@@ -39,6 +40,7 @@ struct xdp_buff;
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 void xsk_flush(struct xdp_sock *xs);
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -53,6 +55,11 @@ static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 static inline void xsk_flush(struct xdp_sock *xs)
 {
 }
+
+static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+	return false;
+}
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8daef7326bb7..a3a495052511 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
 	BPF_MAP_TYPE_CPUMAP,
+	BPF_MAP_TYPE_XSKMAP,
 };
 
 enum bpf_prog_type {