Merge pull request #1258 from shodoco/tcpbpf

Update bpf.h and virtual_bpf.h to 4.13-rc1

src/cc/compat/linux/bpf.h

@@ -82,6 +82,11 @@ enum bpf_cmd {
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
 	BPF_PROG_TEST_RUN,
+	BPF_PROG_GET_NEXT_ID,
+	BPF_MAP_GET_NEXT_ID,
+	BPF_PROG_GET_FD_BY_ID,
+	BPF_MAP_GET_FD_BY_ID,
+	BPF_OBJ_GET_INFO_BY_FD,
 };
 
 enum bpf_map_type {
@@ -115,12 +120,14 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
+	BPF_PROG_TYPE_SOCK_OPS,
 };
 
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_SOCK_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -132,6 +139,13 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -177,6 +191,7 @@ union bpf_attr {
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		prog_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -201,6 +216,21 @@ union bpf_attr {
 		__u32		repeat;
 		__u32		duration;
 	} test;
+
+	struct { /* anonymous struct used by BPF_*_GET_*_ID */
+		union {
+			__u32		start_id;
+			__u32		prog_id;
+			__u32		map_id;
+		};
+		__u32		next_id;
+	};
+
+	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+		__u32		bpf_fd;
+		__u32		info_len;
+		__aligned_u64	info;
+	} info;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -305,8 +335,11 @@ union bpf_attr {
  *     @flags: room for future extensions
  *     Return: 0 on success or negative error
  *
- * u64 bpf_perf_event_read(&map, index)
- *     Return: Number events read or error code
+ * u64 bpf_perf_event_read(map, flags)
+ *     read perf event counter value
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     Return: value of perf event counter read or error code
  *
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
@@ -320,11 +353,11 @@ union bpf_attr {
  *     @skb: pointer to skb
  *     Return: realm if != 0
  *
- * int bpf_perf_event_output(ctx, map, index, data, size)
+ * int bpf_perf_event_output(ctx, map, flags, data, size)
  *     output perf raw sample
  *     @ctx: struct pt_regs*
  *     @map: pointer to perf_event_array map
- *     @index: index of event in the map
+ *     @flags: index of event in the map or bitmask flags
  *     @data: data on stack to be output as raw data
  *     @size: size of data
  *     Return: 0 on success or negative error
@@ -482,6 +515,30 @@ union bpf_attr {
  *     Get the owner uid of the socket stored inside sk_buff.
  *     @skb: pointer to skb
  *     Return: uid of the socket owner on success or overflowuid if failed.
+ *
+ * u32 bpf_set_hash(skb, hash)
+ *     Set full skb->hash.
+ *     @skb: pointer to skb
+ *     @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls setsockopt. Not all opts are available, only those with
+ *     integer optvals plus TCP_CONGESTION.
+ *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in byes
+ *     Return: 0 or negative error
+ *
+ * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
+ *     Grow or shrink room in sk_buff.
+ *     @skb: pointer to skb
+ *     @len_diff: (signed) amount of room to grow/shrink
+ *     @mode: operation mode (enum bpf_adj_room_mode)
+ *     @flags: reserved for future use
+ *     Return: 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -531,7 +588,10 @@ union bpf_attr {
 	FN(xdp_adjust_head),		\
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
-	FN(get_socket_uid),
+	FN(get_socket_uid),		\
+	FN(set_hash),			\
+	FN(setsockopt),			\
+	FN(skb_adjust_room),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -581,6 +641,11 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+	BPF_ADJ_ROOM_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -662,4 +727,77 @@ struct xdp_md {
 	__u32 data_end;
 };
 
+#define BPF_TAG_SIZE	8
+
+struct bpf_prog_info {
+	__u32 type;
+	__u32 id;
+	__u8  tag[BPF_TAG_SIZE];
+	__u32 jited_prog_len;
+	__u32 xlated_prog_len;
+	__aligned_u64 jited_prog_insns;
+	__aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+	__u32 type;
+	__u32 id;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 map_flags;
+} __attribute__((aligned(8)));
+
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+	__u32 op;
+	union {
+		__u32 reply;
+		__u32 replylong[4];
+	};
+	__u32 family;
+	__u32 remote_ip4;	/* Stored in network byte order */
+	__u32 local_ip4;	/* Stored in network byte order */
+	__u32 remote_ip6[4];	/* Stored in network byte order */
+	__u32 local_ip6[4];	/* Stored in network byte order */
+	__u32 remote_port;	/* Stored in network byte order */
+	__u32 local_port;	/* stored in host byte order */
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+	BPF_SOCK_OPS_VOID,
+	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
+					 * -1 if default value should be used
+					 */
+	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
+					 * window (in packets) or -1 if default
+					 * value should be used
+					 */
+	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
+					 * active connection is initialized
+					 */
+	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
+						 * active connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
+						 * passive connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
+					 * needs ECN
+					 */
+};
+
+#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+
 #endif /* _UAPI__LINUX_BPF_H__ */

src/cc/compat/linux/virtual_bpf.h

@@ -83,6 +83,11 @@ enum bpf_cmd {
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
 	BPF_PROG_TEST_RUN,
+	BPF_PROG_GET_NEXT_ID,
+	BPF_MAP_GET_NEXT_ID,
+	BPF_PROG_GET_FD_BY_ID,
+	BPF_MAP_GET_FD_BY_ID,
+	BPF_OBJ_GET_INFO_BY_FD,
 };
 
 enum bpf_map_type {
@@ -116,12 +121,14 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
+	BPF_PROG_TYPE_SOCK_OPS,
 };
 
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_SOCK_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -133,6 +140,13 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -178,6 +192,7 @@ union bpf_attr {
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		prog_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -202,6 +217,21 @@ union bpf_attr {
 		__u32		repeat;
 		__u32		duration;
 	} test;
+
+	struct { /* anonymous struct used by BPF_*_GET_*_ID */
+		union {
+			__u32		start_id;
+			__u32		prog_id;
+			__u32		map_id;
+		};
+		__u32		next_id;
+	};
+
+	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+		__u32		bpf_fd;
+		__u32		info_len;
+		__aligned_u64	info;
+	} info;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -306,8 +336,11 @@ union bpf_attr {
  *     @flags: room for future extensions
  *     Return: 0 on success or negative error
  *
- * u64 bpf_perf_event_read(&map, index)
- *     Return: Number events read or error code
+ * u64 bpf_perf_event_read(map, flags)
+ *     read perf event counter value
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     Return: value of perf event counter read or error code
  *
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
@@ -321,11 +354,11 @@ union bpf_attr {
  *     @skb: pointer to skb
  *     Return: realm if != 0
  *
- * int bpf_perf_event_output(ctx, map, index, data, size)
+ * int bpf_perf_event_output(ctx, map, flags, data, size)
  *     output perf raw sample
  *     @ctx: struct pt_regs*
  *     @map: pointer to perf_event_array map
- *     @index: index of event in the map
+ *     @flags: index of event in the map or bitmask flags
  *     @data: data on stack to be output as raw data
  *     @size: size of data
  *     Return: 0 on success or negative error
@@ -483,6 +516,30 @@ union bpf_attr {
  *     Get the owner uid of the socket stored inside sk_buff.
  *     @skb: pointer to skb
  *     Return: uid of the socket owner on success or overflowuid if failed.
+ *
+ * u32 bpf_set_hash(skb, hash)
+ *     Set full skb->hash.
+ *     @skb: pointer to skb
+ *     @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls setsockopt. Not all opts are available, only those with
+ *     integer optvals plus TCP_CONGESTION.
+ *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in byes
+ *     Return: 0 or negative error
+ *
+ * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
+ *     Grow or shrink room in sk_buff.
+ *     @skb: pointer to skb
+ *     @len_diff: (signed) amount of room to grow/shrink
+ *     @mode: operation mode (enum bpf_adj_room_mode)
+ *     @flags: reserved for future use
+ *     Return: 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -532,7 +589,10 @@ union bpf_attr {
 	FN(xdp_adjust_head),		\
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
-	FN(get_socket_uid),
+	FN(get_socket_uid),		\
+	FN(set_hash),			\
+	FN(setsockopt),			\
+	FN(skb_adjust_room),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -582,6 +642,11 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+	BPF_ADJ_ROOM_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -663,5 +728,78 @@ struct xdp_md {
 	__u32 data_end;
 };
 
+#define BPF_TAG_SIZE	8
+
+struct bpf_prog_info {
+	__u32 type;
+	__u32 id;
+	__u8  tag[BPF_TAG_SIZE];
+	__u32 jited_prog_len;
+	__u32 xlated_prog_len;
+	__aligned_u64 jited_prog_insns;
+	__aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+	__u32 type;
+	__u32 id;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 map_flags;
+} __attribute__((aligned(8)));
+
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+	__u32 op;
+	union {
+		__u32 reply;
+		__u32 replylong[4];
+	};
+	__u32 family;
+	__u32 remote_ip4;	/* Stored in network byte order */
+	__u32 local_ip4;	/* Stored in network byte order */
+	__u32 remote_ip6[4];	/* Stored in network byte order */
+	__u32 local_ip6[4];	/* Stored in network byte order */
+	__u32 remote_port;	/* Stored in network byte order */
+	__u32 local_port;	/* stored in host byte order */
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+	BPF_SOCK_OPS_VOID,
+	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
+					 * -1 if default value should be used
+					 */
+	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
+					 * window (in packets) or -1 if default
+					 * value should be used
+					 */
+	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
+					 * active connection is initialized
+					 */
+	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
+						 * active connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
+						 * passive connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
+					 * needs ECN
+					 */
+};
+
+#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+
 #endif /* _UAPI__LINUX_BPF_H__ */
 )********"