Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-02-16

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) numerous libbpf API improvements, from Andrii, Andrey, Yonghong.

2) test all bpf progs in alu32 mode, from Jiong.

3) skb->sk access and bpf_sk_fullsock(), bpf_tcp_sock() helpers, from Martin.

4) support for IP encap in lwt bpf progs, from Peter.

5) remove XDP_QUERY_XSK_UMEM dead code, from Jan.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 139 insertions, 14 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bd169a7bcc93..de18227b3d95 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -194,6 +194,7 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
+	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 };
 
 /* type of values returned from helper functions */
@@ -203,6 +204,7 @@ enum bpf_return_type {
 	RET_PTR_TO_MAP_VALUE,		/* returns a pointer to map elem value */
 	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
 	RET_PTR_TO_SOCKET_OR_NULL,	/* returns a pointer to a socket or NULL */
+	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -256,6 +258,10 @@ enum bpf_reg_type {
 	PTR_TO_FLOW_KEYS,	 /* reg points to bpf_flow_keys */
 	PTR_TO_SOCKET,		 /* reg points to struct bpf_sock */
 	PTR_TO_SOCKET_OR_NULL,	 /* reg points to struct bpf_sock or NULL */
+	PTR_TO_SOCK_COMMON,	 /* reg points to sock_common */
+	PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
+	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
+	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -767,8 +773,9 @@ int bpf_map_offload_get_next_key(struct bpf_map *map,
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
 
 struct bpf_offload_dev *
-bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops);
+bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv);
 void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
+void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev);
 int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
 				    struct net_device *netdev);
 void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
@@ -920,6 +927,9 @@ void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
 #if defined(CONFIG_NET)
+bool bpf_sock_common_is_valid_access(int off, int size,
+				     enum bpf_access_type type,
+				     struct bpf_insn_access_aux *info);
 bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 			      struct bpf_insn_access_aux *info);
 u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
@@ -928,6 +938,12 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				struct bpf_prog *prog,
 				u32 *target_size);
 #else
+static inline bool bpf_sock_common_is_valid_access(int off, int size,
+						   enum bpf_access_type type,
+						   struct bpf_insn_access_aux *info)
+{
+	return false;
+}
 static inline bool bpf_sock_is_valid_access(int off, int size,
 					    enum bpf_access_type type,
 					    struct bpf_insn_access_aux *info)
@@ -944,4 +960,31 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 }
 #endif
 
+#ifdef CONFIG_INET
+bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+				  struct bpf_insn_access_aux *info);
+
+u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
+				    const struct bpf_insn *si,
+				    struct bpf_insn *insn_buf,
+				    struct bpf_prog *prog,
+				    u32 *target_size);
+#else
+static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
+						enum bpf_access_type type,
+						struct bpf_insn_access_aux *info)
+{
+	return false;
+}
+
+static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
+						  const struct bpf_insn *si,
+						  struct bpf_insn *insn_buf,
+						  struct bpf_prog *prog,
+						  u32 *target_size)
+{
+	return 0;
+}
+#endif /* CONFIG_INET */
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1fb733f38a47..aab4d9f6613d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -868,7 +868,6 @@ enum bpf_netdev_command {
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
-	XDP_QUERY_XSK_UMEM,
 	XDP_SETUP_XSK_UMEM,
 };
 
@@ -895,10 +894,10 @@ struct netdev_bpf {
 		struct {
 			struct bpf_offloaded_map *offmap;
 		};
-		/* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */
+		/* XDP_SETUP_XSK_UMEM */
 		struct {
-			struct xdp_umem *umem; /* out for query*/
-			u16 queue_id; /* in for query */
+			struct xdp_umem *umem;
+			u16 queue_id;
 		} xsk;
 	};
 };
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 20d523ee2fec..269ec27385e9 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -248,6 +248,7 @@ struct ipv6_stub {
 				 const struct in6_addr *addr);
 	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
 			       struct dst_entry **dst, struct flowi6 *fl6);
+	int (*ipv6_route_input)(struct sk_buff *skb);
 
 	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
 	struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 33fd9ba7e0e5..671113bcb2cc 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -126,6 +126,8 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int lwtunnel_input(struct sk_buff *skb);
 int lwtunnel_xmit(struct sk_buff *skb);
+int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len,
+			  bool ingress);
 
 static inline void lwtunnel_set_redirect(struct dst_entry *dst)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1777fa0c61e4..bcdd2474eee7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2016,6 +2016,19 @@ union bpf_attr {
  *			Only works if *skb* contains an IPv6 packet. Insert a
  *			Segment Routing Header (**struct ipv6_sr_hdr**) inside
  *			the IPv6 header.
+ *		**BPF_LWT_ENCAP_IP**
+ *			IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ *			must be IPv4 or IPv6, followed by zero or more
+ *			additional headers, up to LWT_BPF_MAX_HEADROOM total
+ *			bytes in all prepended headers. Please note that
+ *			if skb_is_gso(skb) is true, no more than two headers
+ *			can be prepended, and the inner header, if present,
+ *			should be either GRE or UDP/GUE.
+ *
+ *		BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of
+ *		type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called
+ *		by bpf programs of types BPF_PROG_TYPE_LWT_IN and
+ *		BPF_PROG_TYPE_LWT_XMIT.
  *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2329,6 +2342,23 @@ union bpf_attr {
  *		"**y**".
  *	Return
  *		0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_sock** pointer such
+ *		that all the fields in bpf_sock can be accessed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or NULL in
+ *		case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_tcp_sock** pointer from a
+ *		**struct bpf_sock** pointer.
+ *
+ *	Return
+ *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2425,7 +2455,9 @@ union bpf_attr {
 	FN(msg_pop_data),		\
 	FN(rc_pointer_rel),		\
 	FN(spin_lock),			\
-	FN(spin_unlock),
+	FN(spin_unlock),		\
+	FN(sk_fullsock),		\
+	FN(tcp_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2498,7 +2530,8 @@ enum bpf_hdr_start_off {
 /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
 enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6,
-	BPF_LWT_ENCAP_SEG6_INLINE
+	BPF_LWT_ENCAP_SEG6_INLINE,
+	BPF_LWT_ENCAP_IP,
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -2545,6 +2578,7 @@ struct __sk_buff {
 	__u64 tstamp;
 	__u32 wire_len;
 	__u32 gso_segs;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 struct bpf_tunnel_key {
@@ -2586,7 +2620,15 @@ enum bpf_ret_code {
 	BPF_DROP = 2,
 	/* 3-6 reserved */
 	BPF_REDIRECT = 7,
-	/* >127 are reserved for prog type specific return codes */
+	/* >127 are reserved for prog type specific return codes.
+	 *
+	 * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+	 *    BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+	 *    changed and should be routed based on its new L3 header.
+	 *    (This is an L3 redirect, as opposed to L2 redirect
+	 *    represented by BPF_REDIRECT above).
+	 */
+	BPF_LWT_REROUTE = 128,
 };
 
 struct bpf_sock {
@@ -2596,14 +2638,52 @@ struct bpf_sock {
 	__u32 protocol;
 	__u32 mark;
 	__u32 priority;
-	__u32 src_ip4;		/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	/* IP address also allows 1 and 2 bytes access */
+	__u32 src_ip4;
+	__u32 src_ip6[4];
+	__u32 src_port;		/* host byte order */
+	__u32 dst_port;		/* network byte order */
+	__u32 dst_ip4;
+	__u32 dst_ip6[4];
+	__u32 state;
+};
+
+struct bpf_tcp_sock {
+	__u32 snd_cwnd;		/* Sending congestion window		*/
+	__u32 srtt_us;		/* smoothed round trip time << 3 in usecs */
+	__u32 rtt_min;
+	__u32 snd_ssthresh;	/* Slow start size threshold		*/
+	__u32 rcv_nxt;		/* What we want to receive next		*/
+	__u32 snd_nxt;		/* Next sequence we send		*/
+	__u32 snd_una;		/* First byte we want an ack for	*/
+	__u32 mss_cache;	/* Cached effective mss, not including SACKS */
+	__u32 ecn_flags;	/* ECN status bits.			*/
+	__u32 rate_delivered;	/* saved rate sample: packets delivered */
+	__u32 rate_interval_us;	/* saved rate sample: time elapsed */
+	__u32 packets_out;	/* Packets which are "in flight"	*/
+	__u32 retrans_out;	/* Retransmitted packets out		*/
+	__u32 total_retrans;	/* Total retransmits for entire connection */
+	__u32 segs_in;		/* RFC4898 tcpEStatsPerfSegsIn
+				 * total number of segments in.
 				 */
-	__u32 src_ip6[4];	/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	__u32 data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
+				 * total number of data segments in.
+				 */
+	__u32 segs_out;		/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	__u32 data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	__u32 lost_out;		/* Lost packets			*/
+	__u32 sacked_out;	/* SACK'd packets			*/
+	__u64 bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+				 * sum(delta(rcv_nxt)), or how many bytes
+				 * were acked.
 				 */
-	__u32 src_port;		/* Allows 4-byte read.
-				 * Stored in host byte order
+	__u64 bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
+				 * sum(delta(snd_una)), or how many bytes
+				 * were acked.
 				 */
 };