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>

2 files changed, 626 insertions, 183 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index b5a002d7b263..b584cb42a803 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -73,6 +73,7 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
+#include <net/lwtunnel.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1793,6 +1794,20 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk)
+{
+	sk = sk_to_full_sk(sk);
+
+	return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_sk_fullsock_proto = {
+	.func		= bpf_sk_fullsock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+};
+
 static inline int sk_skb_try_make_writable(struct sk_buff *skb,
 					   unsigned int write_len)
 {
@@ -4803,7 +4818,15 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
 }
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
-BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len,
+			     bool ingress)
+{
+	return bpf_lwt_push_ip_encap(skb, hdr, len, ingress);
+}
+#endif
+
+BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
 	   u32, len)
 {
 	switch (type) {
@@ -4812,13 +4835,40 @@ BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
 	case BPF_LWT_ENCAP_SEG6_INLINE:
 		return bpf_push_seg6_encap(skb, type, hdr, len);
 #endif
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+	case BPF_LWT_ENCAP_IP:
+		return bpf_push_ip_encap(skb, hdr, len, true /* ingress */);
+#endif
 	default:
 		return -EINVAL;
 	}
 }
 
-static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
-	.func		= bpf_lwt_push_encap,
+BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type,
+	   void *, hdr, u32, len)
+{
+	switch (type) {
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+	case BPF_LWT_ENCAP_IP:
+		return bpf_push_ip_encap(skb, hdr, len, false /* egress */);
+#endif
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = {
+	.func		= bpf_lwt_in_push_encap,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE
+};
+
+static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = {
+	.func		= bpf_lwt_xmit_push_encap,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
@@ -5018,6 +5068,54 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 };
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
+#define CONVERT_COMMON_TCP_SOCK_FIELDS(md_type, CONVERT)		\
+do {									\
+	switch (si->off) {						\
+	case offsetof(md_type, snd_cwnd):				\
+		CONVERT(snd_cwnd); break;				\
+	case offsetof(md_type, srtt_us):				\
+		CONVERT(srtt_us); break;				\
+	case offsetof(md_type, snd_ssthresh):				\
+		CONVERT(snd_ssthresh); break;				\
+	case offsetof(md_type, rcv_nxt):				\
+		CONVERT(rcv_nxt); break;				\
+	case offsetof(md_type, snd_nxt):				\
+		CONVERT(snd_nxt); break;				\
+	case offsetof(md_type, snd_una):				\
+		CONVERT(snd_una); break;				\
+	case offsetof(md_type, mss_cache):				\
+		CONVERT(mss_cache); break;				\
+	case offsetof(md_type, ecn_flags):				\
+		CONVERT(ecn_flags); break;				\
+	case offsetof(md_type, rate_delivered):				\
+		CONVERT(rate_delivered); break;				\
+	case offsetof(md_type, rate_interval_us):			\
+		CONVERT(rate_interval_us); break;			\
+	case offsetof(md_type, packets_out):				\
+		CONVERT(packets_out); break;				\
+	case offsetof(md_type, retrans_out):				\
+		CONVERT(retrans_out); break;				\
+	case offsetof(md_type, total_retrans):				\
+		CONVERT(total_retrans); break;				\
+	case offsetof(md_type, segs_in):				\
+		CONVERT(segs_in); break;				\
+	case offsetof(md_type, data_segs_in):				\
+		CONVERT(data_segs_in); break;				\
+	case offsetof(md_type, segs_out):				\
+		CONVERT(segs_out); break;				\
+	case offsetof(md_type, data_segs_out):				\
+		CONVERT(data_segs_out); break;				\
+	case offsetof(md_type, lost_out):				\
+		CONVERT(lost_out); break;				\
+	case offsetof(md_type, sacked_out):				\
+		CONVERT(sacked_out); break;				\
+	case offsetof(md_type, bytes_received):				\
+		CONVERT(bytes_received); break;				\
+	case offsetof(md_type, bytes_acked):				\
+		CONVERT(bytes_acked); break;				\
+	}								\
+} while (0)
+
 #ifdef CONFIG_INET
 static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 			      int dif, int sdif, u8 family, u8 proto)
@@ -5255,6 +5353,79 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+				  struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, bytes_acked))
+		return false;
+
+	if (off % size != 0)
+		return false;
+
+	switch (off) {
+	case offsetof(struct bpf_tcp_sock, bytes_received):
+	case offsetof(struct bpf_tcp_sock, bytes_acked):
+		return size == sizeof(__u64);
+	default:
+		return size == sizeof(__u32);
+	}
+}
+
+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)
+{
+	struct bpf_insn *insn = insn_buf;
+
+#define BPF_TCP_SOCK_GET_COMMON(FIELD)					\
+	do {								\
+		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) >	\
+			     FIELD_SIZEOF(struct bpf_tcp_sock, FIELD));	\
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\
+				      si->dst_reg, si->src_reg,		\
+				      offsetof(struct tcp_sock, FIELD)); \
+	} while (0)
+
+	CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_tcp_sock,
+				       BPF_TCP_SOCK_GET_COMMON);
+
+	if (insn > insn_buf)
+		return insn - insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct bpf_tcp_sock, rtt_min):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) !=
+			     sizeof(struct minmax));
+		BUILD_BUG_ON(sizeof(struct minmax) <
+			     sizeof(struct minmax_sample));
+
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
+				      offsetof(struct tcp_sock, rtt_min) +
+				      offsetof(struct minmax_sample, v));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
+{
+	sk = sk_to_full_sk(sk);
+
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_tcp_sock_proto = {
+	.func		= bpf_tcp_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_TCP_SOCK_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5284,7 +5455,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_lwt_seg6_adjust_srh ||
 	    func == bpf_lwt_seg6_action ||
 #endif
-	    func == bpf_lwt_push_encap)
+	    func == bpf_lwt_in_push_encap ||
+	    func == bpf_lwt_xmit_push_encap)
 		return true;
 
 	return false;
@@ -5408,6 +5580,12 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_sk_fullsock:
+		return &bpf_sk_fullsock_proto;
+#ifdef CONFIG_INET
+	case BPF_FUNC_tcp_sock:
+		return &bpf_tcp_sock_proto;
+#endif
 	default:
 		return sk_filter_func_proto(func_id, prog);
 	}
@@ -5479,6 +5657,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_uid_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_skb_fib_lookup_proto;
+	case BPF_FUNC_sk_fullsock:
+		return &bpf_sk_fullsock_proto;
 #ifdef CONFIG_XFRM
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
@@ -5496,6 +5676,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_tcp_sock:
+		return &bpf_tcp_sock_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5672,7 +5854,7 @@ lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_lwt_push_encap:
-		return &bpf_lwt_push_encap_proto;
+		return &bpf_lwt_in_push_encap_proto;
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
@@ -5708,6 +5890,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_l4_csum_replace_proto;
 	case BPF_FUNC_set_hash_invalid:
 		return &bpf_set_hash_invalid_proto;
+	case BPF_FUNC_lwt_push_encap:
+		return &bpf_lwt_xmit_push_encap_proto;
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
@@ -5766,6 +5950,11 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 		if (size != sizeof(__u64))
 			return false;
 		break;
+	case offsetof(struct __sk_buff, sk):
+		if (type == BPF_WRITE || size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL;
+		break;
 	default:
 		/* Only narrow read access allowed for now. */
 		if (type == BPF_WRITE) {
@@ -5937,31 +6126,44 @@ full_access:
 	return true;
 }
 
-static bool __sock_filter_check_size(int off, int size,
+bool bpf_sock_common_is_valid_access(int off, int size,
+				     enum bpf_access_type type,
 				     struct bpf_insn_access_aux *info)
 {
-	const int size_default = sizeof(__u32);
-
 	switch (off) {
-	case bpf_ctx_range(struct bpf_sock, src_ip4):
-	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
-		bpf_ctx_record_field_size(info, size_default);
-		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	case bpf_ctx_range_till(struct bpf_sock, type, priority):
+		return false;
+	default:
+		return bpf_sock_is_valid_access(off, size, type, info);
 	}
-
-	return size == size_default;
 }
 
 bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 			      struct bpf_insn_access_aux *info)
 {
+	const int size_default = sizeof(__u32);
+
 	if (off < 0 || off >= sizeof(struct bpf_sock))
 		return false;
 	if (off % size != 0)
 		return false;
-	if (!__sock_filter_check_size(off, size, info))
-		return false;
-	return true;
+
+	switch (off) {
+	case offsetof(struct bpf_sock, state):
+	case offsetof(struct bpf_sock, family):
+	case offsetof(struct bpf_sock, type):
+	case offsetof(struct bpf_sock, protocol):
+	case offsetof(struct bpf_sock, dst_port):
+	case offsetof(struct bpf_sock, src_port):
+	case bpf_ctx_range(struct bpf_sock, src_ip4):
+	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
+	case bpf_ctx_range(struct bpf_sock, dst_ip4):
+	case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
+		bpf_ctx_record_field_size(info, size_default);
+		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	}
+
+	return size == size_default;
 }
 
 static bool sock_filter_is_valid_access(int off, int size,
@@ -6750,6 +6952,13 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		off += offsetof(struct qdisc_skb_cb, pkt_len);
 		*target_size = 4;
 		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off);
+		break;
+
+	case offsetof(struct __sk_buff, sk):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_buff, sk));
+		break;
 	}
 
 	return insn - insn_buf;
@@ -6798,24 +7007,32 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct bpf_sock, family):
-		BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2);
-
-		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
-				      offsetof(struct sock, sk_family));
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock_common, skc_family),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common,
+				       skc_family,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_family),
+				       target_size));
 		break;
 
 	case offsetof(struct bpf_sock, type):
+		BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2);
 		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
 				      offsetof(struct sock, __sk_flags_offset));
 		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
 		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
+		*target_size = 2;
 		break;
 
 	case offsetof(struct bpf_sock, protocol):
+		BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
 		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
 				      offsetof(struct sock, __sk_flags_offset));
 		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
 		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT);
+		*target_size = 1;
 		break;
 
 	case offsetof(struct bpf_sock, src_ip4):
@@ -6827,6 +7044,15 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				       target_size));
 		break;
 
+	case offsetof(struct bpf_sock, dst_ip4):
+		*insn++ = BPF_LDX_MEM(
+			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common, skc_daddr,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_daddr),
+				       target_size));
+		break;
+
 	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
 #if IS_ENABLED(CONFIG_IPV6)
 		off = si->off;
@@ -6845,6 +7071,23 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 #endif
 		break;
 
+	case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+		off = si->off;
+		off -= offsetof(struct bpf_sock, dst_ip6[0]);
+		*insn++ = BPF_LDX_MEM(
+			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common,
+				       skc_v6_daddr.s6_addr32[0],
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_v6_daddr.s6_addr32[0]),
+				       target_size) + off);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+		*target_size = 4;
+#endif
+		break;
+
 	case offsetof(struct bpf_sock, src_port):
 		*insn++ = BPF_LDX_MEM(
 			BPF_FIELD_SIZEOF(struct sock_common, skc_num),
@@ -6854,6 +7097,26 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 						    skc_num),
 				       target_size));
 		break;
+
+	case offsetof(struct bpf_sock, dst_port):
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock_common, skc_dport),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common, skc_dport,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_dport),
+				       target_size));
+		break;
+
+	case offsetof(struct bpf_sock, state):
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock_common, skc_state),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common, skc_state,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_state),
+				       target_size));
+		break;
 	}
 
 	return insn - insn_buf;
@@ -7101,6 +7364,85 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	struct bpf_insn *insn = insn_buf;
 	int off;
 
+/* Helper macro for adding read access to tcp_sock or sock fields. */
+#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
+	do {								      \
+		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
+			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern,     \
+						is_fullsock),		      \
+				      si->dst_reg, si->src_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       is_fullsock));		      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2);	      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern, sk),\
+				      si->dst_reg, si->src_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern, sk));\
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ,		      \
+						       OBJ_FIELD),	      \
+				      si->dst_reg, si->dst_reg,		      \
+				      offsetof(OBJ, OBJ_FIELD));	      \
+	} while (0)
+
+#define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \
+		SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock)
+
+/* Helper macro for adding write access to tcp_sock or sock fields.
+ * The macro is called with two registers, dst_reg which contains a pointer
+ * to ctx (context) and src_reg which contains the value that should be
+ * stored. However, we need an additional register since we cannot overwrite
+ * dst_reg because it may be used later in the program.
+ * Instead we "borrow" one of the other register. We first save its value
+ * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore
+ * it at the end of the macro.
+ */
+#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
+	do {								      \
+		int reg = BPF_REG_9;					      \
+		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
+			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		*insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg,		      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       temp));			      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern,     \
+						is_fullsock),		      \
+				      reg, si->dst_reg,			      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       is_fullsock));		      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2);		      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern, sk),\
+				      reg, si->dst_reg,			      \
+				      offsetof(struct bpf_sock_ops_kern, sk));\
+		*insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD),	      \
+				      reg, si->src_reg,			      \
+				      offsetof(OBJ, OBJ_FIELD));	      \
+		*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       temp));			      \
+	} while (0)
+
+#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE)	      \
+	do {								      \
+		if (TYPE == BPF_WRITE)					      \
+			SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
+		else							      \
+			SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
+	} while (0)
+
+	CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_sock_ops,
+				       SOCK_OPS_GET_TCP_SOCK_FIELD);
+
+	if (insn > insn_buf)
+		return insn - insn_buf;
+
 	switch (si->off) {
 	case offsetof(struct bpf_sock_ops, op) ...
 	     offsetof(struct bpf_sock_ops, replylong[3]):
@@ -7258,175 +7600,15 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 				      FIELD_SIZEOF(struct minmax_sample, t));
 		break;
 
-/* Helper macro for adding read access to tcp_sock or sock fields. */
-#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
-	do {								      \
-		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
-			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
-						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
-				      si->dst_reg, si->src_reg,		      \
-				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2);	      \
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
-						struct bpf_sock_ops_kern, sk),\
-				      si->dst_reg, si->src_reg,		      \
-				      offsetof(struct bpf_sock_ops_kern, sk));\
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ,		      \
-						       OBJ_FIELD),	      \
-				      si->dst_reg, si->dst_reg,		      \
-				      offsetof(OBJ, OBJ_FIELD));	      \
-	} while (0)
-
-/* Helper macro for adding write access to tcp_sock or sock fields.
- * The macro is called with two registers, dst_reg which contains a pointer
- * to ctx (context) and src_reg which contains the value that should be
- * stored. However, we need an additional register since we cannot overwrite
- * dst_reg because it may be used later in the program.
- * Instead we "borrow" one of the other register. We first save its value
- * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore
- * it at the end of the macro.
- */
-#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
-	do {								      \
-		int reg = BPF_REG_9;					      \
-		BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) >		      \
-			     FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD));   \
-		if (si->dst_reg == reg || si->src_reg == reg)		      \
-			reg--;						      \
-		if (si->dst_reg == reg || si->src_reg == reg)		      \
-			reg--;						      \
-		*insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg,		      \
-				      offsetof(struct bpf_sock_ops_kern,      \
-					       temp));			      \
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
-						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
-				      reg, si->dst_reg,			      \
-				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2);		      \
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
-						struct bpf_sock_ops_kern, sk),\
-				      reg, si->dst_reg,			      \
-				      offsetof(struct bpf_sock_ops_kern, sk));\
-		*insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD),	      \
-				      reg, si->src_reg,			      \
-				      offsetof(OBJ, OBJ_FIELD));	      \
-		*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg,		      \
-				      offsetof(struct bpf_sock_ops_kern,      \
-					       temp));			      \
-	} while (0)
-
-#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE)	      \
-	do {								      \
-		if (TYPE == BPF_WRITE)					      \
-			SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
-		else							      \
-			SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
-	} while (0)
-
-	case offsetof(struct bpf_sock_ops, snd_cwnd):
-		SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, srtt_us):
-		SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
-		break;
-
 	case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags):
 		SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags,
 				   struct tcp_sock);
 		break;
 
-	case offsetof(struct bpf_sock_ops, snd_ssthresh):
-		SOCK_OPS_GET_FIELD(snd_ssthresh, snd_ssthresh, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, rcv_nxt):
-		SOCK_OPS_GET_FIELD(rcv_nxt, rcv_nxt, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, snd_nxt):
-		SOCK_OPS_GET_FIELD(snd_nxt, snd_nxt, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, snd_una):
-		SOCK_OPS_GET_FIELD(snd_una, snd_una, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, mss_cache):
-		SOCK_OPS_GET_FIELD(mss_cache, mss_cache, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, ecn_flags):
-		SOCK_OPS_GET_FIELD(ecn_flags, ecn_flags, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, rate_delivered):
-		SOCK_OPS_GET_FIELD(rate_delivered, rate_delivered,
-				   struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, rate_interval_us):
-		SOCK_OPS_GET_FIELD(rate_interval_us, rate_interval_us,
-				   struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, packets_out):
-		SOCK_OPS_GET_FIELD(packets_out, packets_out, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, retrans_out):
-		SOCK_OPS_GET_FIELD(retrans_out, retrans_out, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, total_retrans):
-		SOCK_OPS_GET_FIELD(total_retrans, total_retrans,
-				   struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, segs_in):
-		SOCK_OPS_GET_FIELD(segs_in, segs_in, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, data_segs_in):
-		SOCK_OPS_GET_FIELD(data_segs_in, data_segs_in, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, segs_out):
-		SOCK_OPS_GET_FIELD(segs_out, segs_out, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, data_segs_out):
-		SOCK_OPS_GET_FIELD(data_segs_out, data_segs_out,
-				   struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, lost_out):
-		SOCK_OPS_GET_FIELD(lost_out, lost_out, struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, sacked_out):
-		SOCK_OPS_GET_FIELD(sacked_out, sacked_out, struct tcp_sock);
-		break;
-
 	case offsetof(struct bpf_sock_ops, sk_txhash):
 		SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
 					  struct sock, type);
 		break;
-
-	case offsetof(struct bpf_sock_ops, bytes_received):
-		SOCK_OPS_GET_FIELD(bytes_received, bytes_received,
-				   struct tcp_sock);
-		break;
-
-	case offsetof(struct bpf_sock_ops, bytes_acked):
-		SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock);
-		break;
-
 	}
 	return insn - insn_buf;
 }
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index a648568c5e8f..a5c8c79d468a 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/bpf.h>
 #include <net/lwtunnel.h>
+#include <net/gre.h>
+#include <net/ip6_route.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
@@ -55,6 +57,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 
 	switch (ret) {
 	case BPF_OK:
+	case BPF_LWT_REROUTE:
 		break;
 
 	case BPF_REDIRECT:
@@ -87,6 +90,30 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 	return ret;
 }
 
+static int bpf_lwt_input_reroute(struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *iph = ip_hdr(skb);
+
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, skb_dst(skb)->dev);
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		err = ipv6_stub->ipv6_route_input(skb);
+	} else {
+		err = -EAFNOSUPPORT;
+	}
+
+	if (err)
+		goto err;
+	return dst_input(skb);
+
+err:
+	kfree_skb(skb);
+	return err;
+}
+
 static int bpf_input(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -98,11 +125,11 @@ static int bpf_input(struct sk_buff *skb)
 		ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT);
 		if (ret < 0)
 			return ret;
+		if (ret == BPF_LWT_REROUTE)
+			return bpf_lwt_input_reroute(skb);
 	}
 
 	if (unlikely(!dst->lwtstate->orig_input)) {
-		pr_warn_once("orig_input not set on dst for prog %s\n",
-			     bpf->out.name);
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -147,6 +174,102 @@ static int xmit_check_hhlen(struct sk_buff *skb)
 	return 0;
 }
 
+static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
+{
+	struct net_device *l3mdev = l3mdev_master_dev_rcu(skb_dst(skb)->dev);
+	int oif = l3mdev ? l3mdev->ifindex : 0;
+	struct dst_entry *dst = NULL;
+	int err = -EAFNOSUPPORT;
+	struct sock *sk;
+	struct net *net;
+	bool ipv4;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		ipv4 = true;
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		ipv4 = false;
+	else
+		goto err;
+
+	sk = sk_to_full_sk(skb->sk);
+	if (sk) {
+		if (sk->sk_bound_dev_if)
+			oif = sk->sk_bound_dev_if;
+		net = sock_net(sk);
+	} else {
+		net = dev_net(skb_dst(skb)->dev);
+	}
+
+	if (ipv4) {
+		struct iphdr *iph = ip_hdr(skb);
+		struct flowi4 fl4 = {};
+		struct rtable *rt;
+
+		fl4.flowi4_oif = oif;
+		fl4.flowi4_mark = skb->mark;
+		fl4.flowi4_uid = sock_net_uid(net, sk);
+		fl4.flowi4_tos = RT_TOS(iph->tos);
+		fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
+		fl4.flowi4_proto = iph->protocol;
+		fl4.daddr = iph->daddr;
+		fl4.saddr = iph->saddr;
+
+		rt = ip_route_output_key(net, &fl4);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
+			goto err;
+		}
+		dst = &rt->dst;
+	} else {
+		struct ipv6hdr *iph6 = ipv6_hdr(skb);
+		struct flowi6 fl6 = {};
+
+		fl6.flowi6_oif = oif;
+		fl6.flowi6_mark = skb->mark;
+		fl6.flowi6_uid = sock_net_uid(net, sk);
+		fl6.flowlabel = ip6_flowinfo(iph6);
+		fl6.flowi6_proto = iph6->nexthdr;
+		fl6.daddr = iph6->daddr;
+		fl6.saddr = iph6->saddr;
+
+		err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6);
+		if (unlikely(err))
+			goto err;
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			goto err;
+		}
+	}
+	if (unlikely(dst->error)) {
+		err = dst->error;
+		dst_release(dst);
+		goto err;
+	}
+
+	/* Although skb header was reserved in bpf_lwt_push_ip_encap(), it
+	 * was done for the previous dst, so we are doing it here again, in
+	 * case the new dst needs much more space. The call below is a noop
+	 * if there is enough header space in skb.
+	 */
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+	if (unlikely(err))
+		goto err;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	err = dst_output(dev_net(skb_dst(skb)->dev), skb->sk, skb);
+	if (unlikely(err))
+		goto err;
+
+	/* ip[6]_finish_output2 understand LWTUNNEL_XMIT_DONE */
+	return LWTUNNEL_XMIT_DONE;
+
+err:
+	kfree_skb(skb);
+	return err;
+}
+
 static int bpf_xmit(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -154,11 +277,20 @@ static int bpf_xmit(struct sk_buff *skb)
 
 	bpf = bpf_lwt_lwtunnel(dst->lwtstate);
 	if (bpf->xmit.prog) {
+		__be16 proto = skb->protocol;
 		int ret;
 
 		ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT);
 		switch (ret) {
 		case BPF_OK:
+			/* If the header changed, e.g. via bpf_lwt_push_encap,
+			 * BPF_LWT_REROUTE below should have been used if the
+			 * protocol was also changed.
+			 */
+			if (skb->protocol != proto) {
+				kfree_skb(skb);
+				return -EINVAL;
+			}
 			/* If the header was expanded, headroom might be too
 			 * small for L2 header to come, expand as needed.
 			 */
@@ -169,6 +301,8 @@ static int bpf_xmit(struct sk_buff *skb)
 			return LWTUNNEL_XMIT_CONTINUE;
 		case BPF_REDIRECT:
 			return LWTUNNEL_XMIT_DONE;
+		case BPF_LWT_REROUTE:
+			return bpf_lwt_xmit_reroute(skb);
 		default:
 			return ret;
 		}
@@ -390,6 +524,133 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = {
 	.owner		= THIS_MODULE,
 };
 
+static int handle_gso_type(struct sk_buff *skb, unsigned int gso_type,
+			   int encap_len)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	gso_type |= SKB_GSO_DODGY;
+	shinfo->gso_type |= gso_type;
+	skb_decrease_gso_size(shinfo, encap_len);
+	shinfo->gso_segs = 0;
+	return 0;
+}
+
+static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len)
+{
+	int next_hdr_offset;
+	void *next_hdr;
+	__u8 protocol;
+
+	/* SCTP and UDP_L4 gso need more nuanced handling than what
+	 * handle_gso_type() does above: skb_decrease_gso_size() is not enough.
+	 * So at the moment only TCP GSO packets are let through.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		return -ENOTSUPP;
+
+	if (ipv4) {
+		protocol = ip_hdr(skb)->protocol;
+		next_hdr_offset = sizeof(struct iphdr);
+		next_hdr = skb_network_header(skb) + next_hdr_offset;
+	} else {
+		protocol = ipv6_hdr(skb)->nexthdr;
+		next_hdr_offset = sizeof(struct ipv6hdr);
+		next_hdr = skb_network_header(skb) + next_hdr_offset;
+	}
+
+	switch (protocol) {
+	case IPPROTO_GRE:
+		next_hdr_offset += sizeof(struct gre_base_hdr);
+		if (next_hdr_offset > encap_len)
+			return -EINVAL;
+
+		if (((struct gre_base_hdr *)next_hdr)->flags & GRE_CSUM)
+			return handle_gso_type(skb, SKB_GSO_GRE_CSUM,
+					       encap_len);
+		return handle_gso_type(skb, SKB_GSO_GRE, encap_len);
+
+	case IPPROTO_UDP:
+		next_hdr_offset += sizeof(struct udphdr);
+		if (next_hdr_offset > encap_len)
+			return -EINVAL;
+
+		if (((struct udphdr *)next_hdr)->check)
+			return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL_CSUM,
+					       encap_len);
+		return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL, encap_len);
+
+	case IPPROTO_IP:
+	case IPPROTO_IPV6:
+		if (ipv4)
+			return handle_gso_type(skb, SKB_GSO_IPXIP4, encap_len);
+		else
+			return handle_gso_type(skb, SKB_GSO_IPXIP6, encap_len);
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+}
+
+int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
+{
+	struct iphdr *iph;
+	bool ipv4;
+	int err;
+
+	if (unlikely(len < sizeof(struct iphdr) || len > LWT_BPF_MAX_HEADROOM))
+		return -EINVAL;
+
+	/* validate protocol and length */
+	iph = (struct iphdr *)hdr;
+	if (iph->version == 4) {
+		ipv4 = true;
+		if (unlikely(len < iph->ihl * 4))
+			return -EINVAL;
+	} else if (iph->version == 6) {
+		ipv4 = false;
+		if (unlikely(len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	if (ingress)
+		err = skb_cow_head(skb, len + skb->mac_len);
+	else
+		err = skb_cow_head(skb,
+				   len + LL_RESERVED_SPACE(skb_dst(skb)->dev));
+	if (unlikely(err))
+		return err;
+
+	/* push the encap headers and fix pointers */
+	skb_reset_inner_headers(skb);
+	skb->encapsulation = 1;
+	skb_push(skb, len);
+	if (ingress)
+		skb_postpush_rcsum(skb, iph, len);
+	skb_reset_network_header(skb);
+	memcpy(skb_network_header(skb), hdr, len);
+	bpf_compute_data_pointers(skb);
+	skb_clear_hash(skb);
+
+	if (ipv4) {
+		skb->protocol = htons(ETH_P_IP);
+		iph = ip_hdr(skb);
+
+		if (!iph->check)
+			iph->check = ip_fast_csum((unsigned char *)iph,
+						  iph->ihl);
+	} else {
+		skb->protocol = htons(ETH_P_IPV6);
+	}
+
+	if (skb_is_gso(skb))
+		return handle_gso_encap(skb, ipv4, len);
+
+	return 0;
+}
+
 static int __init bpf_lwt_init(void)
 {
 	return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF);