All of lore.kernel.org
 help / color / mirror / Atom feed
From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Eric Dumazet <edumazet@google.com>, <kernel-team@fb.com>,
	Lawrence Brakmo <brakmo@fb.com>,
	Neal Cardwell <ncardwell@google.com>, <netdev@vger.kernel.org>,
	Yuchung Cheng <ycheng@google.com>
Subject: [PATCH bpf-next 02/10] tcp: bpf: Parse BPF experimental header option
Date: Fri, 26 Jun 2020 10:55:14 -0700	[thread overview]
Message-ID: <20200626175514.1460570-1-kafai@fb.com> (raw)
In-Reply-To: <20200626175501.1459961-1-kafai@fb.com>

This patch adds logic to parse experimental kind 254 with 16 bit magic
0xeB9F.  The latter patch will allow bpf prog to write and parse data
under this experimental kind and magic.

A one byte bpf_hdr_opt_off is added to tcp_skb_cb by using an existing
4 byte hole.  It is only used in rx.  It stores the offset to the
bpf experimental option and will be made available to BPF prog
in a latter patch.  This offset is also stored in the saved_syn.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/net/request_sock.h | 1 +
 include/net/tcp.h          | 3 +++
 net/ipv4/tcp_input.c       | 6 ++++++
 net/ipv4/tcp_ipv4.c        | 1 +
 net/ipv6/tcp_ipv6.c        | 1 +
 5 files changed, 12 insertions(+)

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index d77237ec9fb4..55297286c066 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -43,6 +43,7 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
 
 struct saved_syn {
 	u32 network_hdrlen;
+	u32 bpf_hdr_opt_off;
 	u8 data[];
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eab1c7d0facb..07a9dfe35242 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -191,6 +191,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
  */
 #define TCPOPT_FASTOPEN_MAGIC	0xF989
 #define TCPOPT_SMC_MAGIC	0xE2D4C3D9
+#define TCPOPT_BPF_MAGIC	0xEB9F
 
 /*
  *     TCP option lengths
@@ -204,6 +205,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_FASTOPEN_BASE  2
 #define TCPOLEN_EXP_FASTOPEN_BASE  4
 #define TCPOLEN_EXP_SMC_BASE   6
+#define TCPOLEN_EXP_BPF_BASE   4
 
 /* But this is what stacks really send out. */
 #define TCPOLEN_TSTAMP_ALIGNED		12
@@ -857,6 +859,7 @@ struct tcp_skb_cb {
 			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
 			unused:5;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
+	__u8            bpf_hdr_opt_off;/* offset to bpf hdr option. rx only. */
 	union {
 		struct {
 			/* There is space for up to 24 bytes */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb0e32b2def9..640408a80b3d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3924,6 +3924,10 @@ void tcp_parse_options(const struct net *net,
 					tcp_parse_fastopen_option(opsize -
 						TCPOLEN_EXP_FASTOPEN_BASE,
 						ptr + 2, th->syn, foc, true);
+				else if (opsize >= TCPOLEN_EXP_BPF_BASE &&
+					 get_unaligned_be16(ptr) ==
+					 TCPOPT_BPF_MAGIC)
+					TCP_SKB_CB(skb)->bpf_hdr_opt_off = (ptr - 2) - (unsigned char *)th;
 				else
 					smc_parse_options(th, opt_rx, ptr,
 							  opsize);
@@ -6562,6 +6566,8 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 		saved_syn = kmalloc(len + sizeof(*saved_syn), GFP_ATOMIC);
 		if (saved_syn) {
 			saved_syn->network_hdrlen = skb_network_header_len(skb);
+			saved_syn->bpf_hdr_opt_off =
+				TCP_SKB_CB(skb)->bpf_hdr_opt_off;
 			memcpy(saved_syn->data, skb_network_header(skb), len);
 			req->saved_syn = saved_syn;
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ea0df9fd7618..a3535b7fe002 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1864,6 +1864,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 	TCP_SKB_CB(skb)->sacked	 = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
 			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+	TCP_SKB_CB(skb)->bpf_hdr_opt_off = 0;
 }
 
 /*
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f67d45ff00b4..8356d0562279 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1545,6 +1545,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->sacked = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
 			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+	TCP_SKB_CB(skb)->bpf_hdr_opt_off = 0;
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
-- 
2.24.1


  parent reply	other threads:[~2020-06-26 17:55 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-26 17:55 [PATCH bpf-next 00/10] BPF TCP header options Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 01/10] tcp: Use a struct to represent a saved_syn Martin KaFai Lau
2020-06-27 17:41   ` Eric Dumazet
2020-06-30 23:24     ` Martin KaFai Lau
2020-06-30 23:35       ` Eric Dumazet
2020-06-26 17:55 ` Martin KaFai Lau [this message]
2020-06-27 16:44   ` [PATCH bpf-next 02/10] tcp: bpf: Parse BPF experimental header option Eric Dumazet
2020-06-27 17:17   ` Eric Dumazet
2020-06-28 23:44     ` Martin KaFai Lau
2020-06-29  0:45     ` Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 03/10] bpf: sock_ops: Change some members of sock_ops_kern from u32 to u8 Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 04/10] bpf: tcp: Allow bpf prog to write and parse BPF TCP header option Martin KaFai Lau
2020-06-28 18:24   ` Alexei Starovoitov
2020-06-29  0:34     ` Martin KaFai Lau
2020-07-02  5:31       ` Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 05/10] bpf: selftests: A few improvements to network_helpers.c Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 06/10] bpf: selftests: Add fastopen_connect to network_helpers Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 07/10] bpf: selftests: Restore netns after each test Martin KaFai Lau
2020-06-26 22:45   ` Andrii Nakryiko
2020-06-27  0:23     ` Martin KaFai Lau
2020-06-27 20:31       ` Andrii Nakryiko
2020-06-29 18:00         ` Martin KaFai Lau
2020-06-29 18:13           ` Andrii Nakryiko
2020-06-29 18:24             ` Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 08/10] bpf: selftests: tcp header options Martin KaFai Lau
2020-06-26 17:55 ` [PATCH bpf-next 09/10] tcp: bpf: Add TCP_BPF_DELACK_MAX and TCP_BPF_RTO_MIN to bpf_setsockopt Martin KaFai Lau
2020-06-27 17:30   ` Eric Dumazet
2020-06-26 17:56 ` [PATCH bpf-next 10/10] bpf: selftest: Add test for TCP_BPF_DELACK_MAX and TCP_BPF_RTO_MIN Martin KaFai Lau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200626175514.1460570-1-kafai@fb.com \
    --to=kafai@fb.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brakmo@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=edumazet@google.com \
    --cc=kernel-team@fb.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=ycheng@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.