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 v3 bpf-next 1/9] tcp: Use a struct to represent a saved_syn
Date: Thu, 30 Jul 2020 13:57:04 -0700 [thread overview]
Message-ID: <20200730205704.3352619-1-kafai@fb.com> (raw)
In-Reply-To: <20200730205657.3351905-1-kafai@fb.com>
The TCP_SAVE_SYN has both the network header and tcp header.
The total length of the saved syn packet is currently stored in
the first 4 bytes (u32) of an array and the actual packet data is
stored after that.
A latter patch will add a bpf helper that allows to get the tcp header
alone from the saved syn without the network header. It will be more
convenient to have a direct offset to a specific header instead of
re-parsing it. This requires to separately store the network hdrlen.
The total header length (i.e. network + tcp) is still needed for the
current usage in getsockopt. Although this total length can be obtained
by looking into the tcphdr and then get the (th->doff << 2), this patch
chooses to directly store the tcp hdrlen in the second four bytes of
this newly created "struct saved_syn". By using a new struct, it can
give a readable name to each individual header length.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
include/linux/tcp.h | 7 ++++++-
include/net/request_sock.h | 8 +++++++-
net/core/filter.c | 4 ++--
net/ipv4/tcp.c | 9 +++++----
net/ipv4/tcp_input.c | 15 ++++++++-------
5 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 527d668a5275..5528912dc468 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -406,7 +406,7 @@ struct tcp_sock {
* socket. Used to retransmit SYNACKs etc.
*/
struct request_sock __rcu *fastopen_rsk;
- u32 *saved_syn;
+ struct saved_syn *saved_syn;
};
enum tsq_enum {
@@ -484,6 +484,11 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
tp->saved_syn = NULL;
}
+static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn)
+{
+ return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen;
+}
+
struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk);
static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index cf8b33213bbc..b1b101814ecb 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -41,6 +41,12 @@ struct request_sock_ops {
int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
+struct saved_syn {
+ u32 network_hdrlen;
+ u32 tcp_hdrlen;
+ u8 data[];
+};
+
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
@@ -60,7 +66,7 @@ struct request_sock {
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
- u32 *saved_syn;
+ struct saved_syn *saved_syn;
u32 secid;
u32 peer_secid;
};
diff --git a/net/core/filter.c b/net/core/filter.c
index 7124f0fe6974..250b5552a148 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4550,9 +4550,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
tp = tcp_sk(sk);
if (optlen <= 0 || !tp->saved_syn ||
- optlen > tp->saved_syn[0])
+ optlen > tcp_saved_syn_len(tp->saved_syn))
goto err_clear;
- memcpy(optval, tp->saved_syn + 1, optlen);
+ memcpy(optval, tp->saved_syn->data, optlen);
break;
default:
goto err_clear;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27de9380ed14..8a774b5094e9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3791,20 +3791,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
lock_sock(sk);
if (tp->saved_syn) {
- if (len < tp->saved_syn[0]) {
- if (put_user(tp->saved_syn[0], optlen)) {
+ if (len < tcp_saved_syn_len(tp->saved_syn)) {
+ if (put_user(tcp_saved_syn_len(tp->saved_syn),
+ optlen)) {
release_sock(sk);
return -EFAULT;
}
release_sock(sk);
return -EINVAL;
}
- len = tp->saved_syn[0];
+ len = tcp_saved_syn_len(tp->saved_syn);
if (put_user(len, optlen)) {
release_sock(sk);
return -EFAULT;
}
- if (copy_to_user(optval, tp->saved_syn + 1, len)) {
+ if (copy_to_user(optval, tp->saved_syn->data, len)) {
release_sock(sk);
return -EFAULT;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a018bafd7bdf..6c38ca9de17e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6598,13 +6598,14 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
{
if (tcp_sk(sk)->save_syn) {
u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
- u32 *copy;
-
- copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
- if (copy) {
- copy[0] = len;
- memcpy(©[1], skb_network_header(skb), len);
- req->saved_syn = copy;
+ struct saved_syn *saved_syn;
+
+ saved_syn = kmalloc(len + sizeof(*saved_syn), GFP_ATOMIC);
+ if (saved_syn) {
+ saved_syn->network_hdrlen = skb_network_header_len(skb);
+ saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
+ memcpy(saved_syn->data, skb_network_header(skb), len);
+ req->saved_syn = saved_syn;
}
}
}
--
2.24.1
next prev parent reply other threads:[~2020-07-30 20:57 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-30 20:56 [PATCH v3 bpf-next 0/9] BPF TCP header options Martin KaFai Lau
2020-07-30 20:57 ` Martin KaFai Lau [this message]
2020-07-31 15:57 ` [PATCH v3 bpf-next 1/9] tcp: Use a struct to represent a saved_syn Eric Dumazet
2020-07-31 17:31 ` Eric Dumazet
2020-07-30 20:57 ` [PATCH v3 bpf-next 2/9] tcp: bpf: Add TCP_BPF_DELACK_MAX setsockopt Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 3/9] tcp: bpf: Add TCP_BPF_RTO_MIN for bpf_setsockopt Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 4/9] tcp: Add unknown_opt arg to tcp_parse_options Martin KaFai Lau
2020-07-31 16:12 ` Eric Dumazet
2020-07-31 17:37 ` Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 5/9] bpf: sock_ops: Change some members of sock_ops_kern from u32 to u8 Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 6/9] bpf: tcp: Allow bpf prog to write and parse TCP header option Martin KaFai Lau
2020-07-31 16:06 ` Eric Dumazet
2020-07-31 17:59 ` Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 7/9] bpf: selftests: Add fastopen_connect to network_helpers Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 8/9] bpf: selftests: tcp header options Martin KaFai Lau
2020-07-30 20:57 ` [PATCH v3 bpf-next 9/9] tcp: bpf: Optionally store mac header in TCP_SAVE_SYN Martin KaFai Lau
2020-07-31 15:51 ` Eric Dumazet
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=20200730205704.3352619-1-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).