[PATCH bpf 07/11] bpf: Add support for reading sk_state and more
From: Lawrence Brakmo <hidden>
Date: 2017-12-19 06:23:07
Subsystem:
bpf [general] (safe dynamic programs and tools), bpf [networking] (tcx & tc bpf, sock_addr), networking [general], the rest · Maintainers:
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko, Eduard Zingerman, Kumar Kartikeya Dwivedi, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
Add support for reading many more tcp_sock fields state, same as sk->sk_state rtt_min same as sk->rtt_min.s[0].v (current rtt_min) snd_ssthresh rcv_nxt snd_nxt snd_una mss_cache ecn_flags rate_delivered rate_interval_us packets_out retrans_out total_retrans segs_in data_segs_in segs_out data_segs_out bytes_received (__u64) bytes_acked (__u64) Signed-off-by: Lawrence Brakmo <redacted> --- include/uapi/linux/bpf.h | 19 ++++++++++ net/core/filter.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 114 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1c36795..19a0b1b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h@@ -954,6 +954,25 @@ struct bpf_sock_ops { __u32 snd_cwnd; __u32 srtt_us; /* Averaged RTT << 3 in usecs */ __u32 bpf_sock_ops_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u64 bytes_received; + __u64 bytes_acked; }; /* List of known BPF sock_ops operators.
diff --git a/net/core/filter.c b/net/core/filter.c
index 2692514..2628077 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c@@ -3828,7 +3828,7 @@ static bool __is_valid_sock_ops_access(int off, int size) /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; - if (size != sizeof(__u32)) + if (size != sizeof(__u32) && size != sizeof(__u64)) return false; return true;
@@ -4448,6 +4448,32 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, is_fullsock)); break; + case offsetof(struct bpf_sock_ops, state): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + + *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_B, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_state)); + break; + + case offsetof(struct bpf_sock_ops, 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_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_W, si->dst_reg, si->dst_reg, + offsetof(struct tcp_sock, rtt_min) + + FIELD_SIZEOF(struct minmax_sample, t)); + break; + /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(FIELD_NAME, OBJ) \ do { \
@@ -4528,6 +4554,74 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_OR_SET_FIELD(bpf_sock_ops_flags, struct tcp_sock, type); break; + + case offsetof(struct bpf_sock_ops, snd_ssthresh): + SOCK_OPS_GET_FIELD(snd_ssthresh, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, rcv_nxt): + SOCK_OPS_GET_FIELD(rcv_nxt, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, snd_nxt): + SOCK_OPS_GET_FIELD(snd_nxt, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, snd_una): + SOCK_OPS_GET_FIELD(snd_una, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, mss_cache): + SOCK_OPS_GET_FIELD(mss_cache, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, ecn_flags): + SOCK_OPS_GET_FIELD(ecn_flags, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, rate_delivered): + SOCK_OPS_GET_FIELD(rate_delivered, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, rate_interval_us): + SOCK_OPS_GET_FIELD(rate_interval_us, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, packets_out): + SOCK_OPS_GET_FIELD(packets_out, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, retrans_out): + SOCK_OPS_GET_FIELD(retrans_out, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, total_retrans): + SOCK_OPS_GET_FIELD(total_retrans, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, segs_in): + SOCK_OPS_GET_FIELD(segs_in, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, data_segs_in): + SOCK_OPS_GET_FIELD(data_segs_in, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, segs_out): + SOCK_OPS_GET_FIELD(data_segs_out, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, data_segs_out): + SOCK_OPS_GET_FIELD(data_segs_out, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, bytes_received): + SOCK_OPS_GET_FIELD(bytes_received, struct tcp_sock); + break; + + case offsetof(struct bpf_sock_ops, bytes_acked): + SOCK_OPS_GET_FIELD(bytes_acked, struct tcp_sock); + break; } return insn - insn_buf; }
--
2.9.5