| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <3CAFA460-F722-4771-B64A-1E8FDDAFE2A3@fb.com>
Date: Wed, 24 Jan 2018 22:07:59 +0000
From: Lawrence Brakmo <brakmo@...com>
To: Yuchung Cheng <ycheng@...gle.com>
CC: netdev <netdev@...r.kernel.org>, Kernel Team <Kernel-team@...com>,
"Blake Matheny" <bmatheny@...com>, Alexei Starovoitov <ast@...com>,
Daniel Borkmann <daniel@...earbox.net>,
Eric Dumazet <eric.dumazet@...il.com>,
Neal Cardwell <ncardwell@...gle.com>
Subject: Re: [PATCH bpf-next v8 08/12] bpf: Add support for reading sk_state
and more
On 1/24/18, 12:07 PM, "netdev-owner@...r.kernel.org on behalf of Yuchung Cheng" <netdev-owner@...r.kernel.org on behalf of ycheng@...gle.com> wrote:
On Tue, Jan 23, 2018 at 11:57 PM, Lawrence Brakmo <brakmo@...com> wrote:
> 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
Might as well get ca_state, sacked_out and lost_out to estimate CA
states and the packets in flight?
Will try to add in updated patchset. If not, I will add as a new patch.
> total_retrans
> segs_in
> data_segs_in
> segs_out
> data_segs_out
> sk_txhash
> bytes_received (__u64)
> bytes_acked (__u64)
>
> Signed-off-by: Lawrence Brakmo <brakmo@...com>
> ---
> include/uapi/linux/bpf.h | 20 +++++++
> net/core/filter.c | 135 +++++++++++++++++++++++++++++++++++++++++++----
> 2 files changed, 144 insertions(+), 11 deletions(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 2a8c40a..6998032 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -979,6 +979,26 @@ struct bpf_sock_ops {
> __u32 snd_cwnd;
> __u32 srtt_us; /* Averaged RTT << 3 in usecs */
> __u32 bpf_sock_ops_cb_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;
> + __u32 sk_txhash;
> + __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 6936d19..ffe9b60 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3855,33 +3855,43 @@ void bpf_warn_invalid_xdp_action(u32 act)
> }
> EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
>
> -static bool __is_valid_sock_ops_access(int off, int size)
> +static bool sock_ops_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_ops))
> return false;
> +
> /* The verifier guarantees that size > 0. */
> if (off % size != 0)
> return false;
> - if (size != sizeof(__u32))
> - return false;
> -
> - return true;
> -}
>
> -static bool sock_ops_is_valid_access(int off, int size,
> - enum bpf_access_type type,
> - struct bpf_insn_access_aux *info)
> -{
> if (type == BPF_WRITE) {
> switch (off) {
> case offsetof(struct bpf_sock_ops, reply):
> + if (size != size_default)
> + return false;
> break;
> default:
> return false;
> }
> + } else {
> + switch (off) {
> + case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received,
> + bytes_acked):
> + if (size != sizeof(__u64))
> + return false;
> + break;
> + default:
> + if (size != size_default)
> + return false;
> + break;
> + }
> }
>
> - return __is_valid_sock_ops_access(off, size);
> + return true;
> }
>
> static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write,
> @@ -4498,6 +4508,32 @@ 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(BPF_FIELD, OBJ_FIELD, OBJ) \
> do { \
> @@ -4580,6 +4616,83 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
> 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, sk_txhash):
> + SOCK_OPS_GET_FIELD(sk_txhash, sk_txhash, struct sock);
> + 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;
> }
> --
> 2.9.5
>
Powered by blists - more mailing lists