[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231013220433.70792-7-kuniyu@amazon.com>
Date: Fri, 13 Oct 2023 15:04:28 -0700
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: "David S. Miller" <davem@...emloft.net>, Eric Dumazet
<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
<pabeni@...hat.com>, David Ahern <dsahern@...nel.org>, Alexei Starovoitov
<ast@...nel.org>, Daniel Borkmann <daniel@...earbox.net>, Andrii Nakryiko
<andrii@...nel.org>, Martin KaFai Lau <martin.lau@...ux.dev>, Song Liu
<song@...nel.org>, Yonghong Song <yonghong.song@...ux.dev>, John Fastabend
<john.fastabend@...il.com>, KP Singh <kpsingh@...nel.org>, Stanislav Fomichev
<sdf@...gle.com>, Hao Luo <haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>,
Mykola Lysenko <mykolal@...com>
CC: Kuniyuki Iwashima <kuniyu@...zon.com>, Kuniyuki Iwashima
<kuni1840@...il.com>, <bpf@...r.kernel.org>, <netdev@...r.kernel.org>
Subject: [PATCH v1 bpf-next 06/11] bpf: tcp: Add SYN Cookie validation SOCK_OPS hook.
This patch adds a new SOCK_OPS hook to validate arbitrary SYN Cookie.
When the kernel receives ACK for SYN Cookie, the hook is invoked with
bpf_sock_ops.op == BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB if the listener has
BPF_SOCK_OPS_SYNCOOKIE_CB_FLAG set by bpf_sock_ops_cb_flags_set().
The BPF program can access the following information to validate ISN:
bpf_sock_ops.sk : 4-tuple
bpf_sock_ops.skb : TCP header
bpf_sock_ops.args[0] : ISN
The program must decode MSS and set it to bpf_sock_ops.replylong[0].
By default, the kernel validates SYN Cookie before allocating reqsk, but
the hook is invoked after allocating reqsk to keep the user interface
consistent with BPF_SOCK_OPS_GEN_SYNCOOKIE_CB.
Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.com>
---
include/net/tcp.h | 12 ++++++
include/uapi/linux/bpf.h | 20 +++++++---
net/ipv4/syncookies.c | 73 +++++++++++++++++++++++++++-------
net/ipv6/syncookies.c | 44 +++++++++++++-------
tools/include/uapi/linux/bpf.h | 20 +++++++---
5 files changed, 130 insertions(+), 39 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 676618c89bb7..90d95acdc34a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2158,6 +2158,18 @@ static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
return ops->cookie_init_seq(skb, mss);
}
+
+#ifdef CONFIG_CGROUP_BPF
+int bpf_skops_cookie_check(struct sock *sk, struct request_sock *req,
+ struct sk_buff *skb);
+#else
+static inline int bpf_skops_cookie_check(struct sock *sk, struct request_sock *req,
+ struct sk_buff *skb)
+{
+ return 0;
+}
+#endif
+
#else
static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
const struct sock *sk, struct sk_buff *skb,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d3cc530613c0..e6f1507d7895 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6738,13 +6738,16 @@ enum {
* options first before the BPF program does.
*/
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
- /* Call bpf when the kernel generates SYN Cookie (ISN) for SYN+ACK.
+ /* Call bpf when the kernel generates SYN Cookie (ISN) for SYN+ACK
+ * and validates ACK for SYN Cookie.
*
- * The bpf prog will be called to encode MSS into SYN Cookie with
- * sock_ops->op == BPF_SOCK_OPS_GEN_SYNCOOKIE_CB.
+ * The bpf prog will be first called to encode MSS into SYN Cookie
+ * with sock_ops->op == BPF_SOCK_OPS_GEN_SYNCOOKIE_CB. Then, the
+ * bpf prog will be called to decode MSS from SYN Cookie with
+ * sock_ops->op == BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB.
*
- * Please refer to the comment in BPF_SOCK_OPS_GEN_SYNCOOKIE_CB for
- * input and output.
+ * Please refer to the comment in BPF_SOCK_OPS_GEN_SYNCOOKIE_CB and
+ * BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB for input and output.
*/
BPF_SOCK_OPS_SYNCOOKIE_CB_FLAG = (1<<7),
/* Mask of all currently supported cb flags */
@@ -6868,6 +6871,13 @@ enum {
*
* replylong[0]: ISN
*/
+ BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB,/* Validate SYN Cookie and set
+ * MSS.
+ *
+ * args[0]: ISN
+ *
+ * replylong[0]: MSS
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 514f1a4abdee..b1dd415863ff 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -317,6 +317,37 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
}
EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);
+#if IS_ENABLED(CONFIG_CGROUP_BPF) && IS_ENABLED(CONFIG_SYN_COOKIES)
+int bpf_skops_cookie_check(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
+{
+ struct bpf_sock_ops_kern sock_ops;
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+ sock_ops.op = BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB;
+ sock_ops.sk = req_to_sk(req);
+ sock_ops.args[0] = tcp_rsk(req)->snt_isn;
+
+ bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+ if (BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk))
+ goto err;
+
+ if (!sock_ops.replylong[0])
+ goto err;
+
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+
+ return sock_ops.replylong[0];
+
+err:
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(bpf_skops_cookie_check);
+#endif
+
/* On input, sk is a listener.
* Output is listener if incoming packet would not create a child
* NULL if memory could not be allocated.
@@ -336,6 +367,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
int full_space, mss;
struct flowi4 fl4;
struct rtable *rt;
+ bool bpf_cookie;
__u8 rcv_wscale;
u32 tsoff = 0;
@@ -343,16 +375,19 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
!th->ack || th->rst)
goto out;
- if (tcp_synq_no_recent_overflow(sk))
- goto out;
+ bpf_cookie = BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_SYNCOOKIE_CB_FLAG);
+ if (!bpf_cookie) {
+ if (tcp_synq_no_recent_overflow(sk))
+ goto out;
- mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
- if (mss == 0) {
- __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
- goto out;
- }
+ mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
+ if (mss == 0) {
+ __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
+ goto out;
+ }
- __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
+ __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
+ }
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
@@ -365,7 +400,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
tcp_opt.rcv_tsecr -= tsoff;
}
- if (!cookie_timestamp_decode(net, &tcp_opt))
+ if (!bpf_cookie && !cookie_timestamp_decode(net, &tcp_opt))
goto out;
req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops,
@@ -375,21 +410,31 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
ireq = inet_rsk(req);
treq = tcp_rsk(req);
- treq->rcv_isn = ntohl(th->seq) - 1;
- treq->snt_isn = cookie;
- treq->ts_off = tsoff;
- treq->txhash = net_tx_rndhash();
- req->mss = mss;
ireq->ir_num = ntohs(th->dest);
ireq->ir_rmt_port = th->source;
+ treq->snt_isn = cookie;
+
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
+
+ if (bpf_cookie) {
+ mss = bpf_skops_cookie_check(sk, req, skb);
+ if (!mss) {
+ reqsk_free(req);
+ goto out;
+ }
+ }
+
+ req->mss = mss;
ireq->ir_mark = inet_request_mark(sk, skb);
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
ireq->wscale_ok = tcp_opt.wscale_ok;
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
+ treq->rcv_isn = ntohl(th->seq) - 1;
+ treq->ts_off = tsoff;
+ treq->txhash = net_tx_rndhash();
treq->snt_synack = 0;
treq->tfo_listener = false;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 60bdc4d9150b..3e920e7eb5d3 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -139,6 +139,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst;
struct sock *ret = sk;
int full_space, mss;
+ bool bpf_cookie;
__u8 rcv_wscale;
u32 tsoff = 0;
@@ -146,16 +147,19 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
!th->ack || th->rst)
goto out;
- if (tcp_synq_no_recent_overflow(sk))
- goto out;
+ bpf_cookie = BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_SYNCOOKIE_CB_FLAG);
+ if (!bpf_cookie) {
+ if (tcp_synq_no_recent_overflow(sk))
+ goto out;
- mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie);
- if (mss == 0) {
- __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
- goto out;
- }
+ mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie);
+ if (mss == 0) {
+ __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
+ goto out;
+ }
- __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
+ __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
+ }
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
@@ -168,7 +172,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
tcp_opt.rcv_tsecr -= tsoff;
}
- if (!cookie_timestamp_decode(net, &tcp_opt))
+ if (!bpf_cookie && !cookie_timestamp_decode(net, &tcp_opt))
goto out;
req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops,
@@ -177,17 +181,25 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out_drop;
ireq = inet_rsk(req);
+ ireq->ir_rmt_port = th->source;
+ ireq->ir_num = ntohs(th->dest);
+ ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
treq = tcp_rsk(req);
- treq->tfo_listener = false;
+ treq->snt_isn = cookie;
+
+ if (bpf_cookie) {
+ mss = bpf_skops_cookie_check(sk, req, skb);
+ if (!mss) {
+ reqsk_free(req);
+ goto out;
+ }
+ }
if (security_inet_conn_request(sk, skb, req))
goto out_free;
- req->mss = mss;
- ireq->ir_rmt_port = th->source;
- ireq->ir_num = ntohs(th->dest);
- ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
- ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
@@ -203,6 +215,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ireq->ir_mark = inet_request_mark(sk, skb);
+ req->mss = mss;
req->num_retrans = 0;
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
@@ -210,6 +223,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->snt_synack = 0;
+ treq->tfo_listener = false;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
treq->ts_off = tsoff;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d3cc530613c0..e6f1507d7895 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6738,13 +6738,16 @@ enum {
* options first before the BPF program does.
*/
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
- /* Call bpf when the kernel generates SYN Cookie (ISN) for SYN+ACK.
+ /* Call bpf when the kernel generates SYN Cookie (ISN) for SYN+ACK
+ * and validates ACK for SYN Cookie.
*
- * The bpf prog will be called to encode MSS into SYN Cookie with
- * sock_ops->op == BPF_SOCK_OPS_GEN_SYNCOOKIE_CB.
+ * The bpf prog will be first called to encode MSS into SYN Cookie
+ * with sock_ops->op == BPF_SOCK_OPS_GEN_SYNCOOKIE_CB. Then, the
+ * bpf prog will be called to decode MSS from SYN Cookie with
+ * sock_ops->op == BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB.
*
- * Please refer to the comment in BPF_SOCK_OPS_GEN_SYNCOOKIE_CB for
- * input and output.
+ * Please refer to the comment in BPF_SOCK_OPS_GEN_SYNCOOKIE_CB and
+ * BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB for input and output.
*/
BPF_SOCK_OPS_SYNCOOKIE_CB_FLAG = (1<<7),
/* Mask of all currently supported cb flags */
@@ -6868,6 +6871,13 @@ enum {
*
* replylong[0]: ISN
*/
+ BPF_SOCK_OPS_CHECK_SYNCOOKIE_CB,/* Validate SYN Cookie and set
+ * MSS.
+ *
+ * args[0]: ISN
+ *
+ * replylong[0]: MSS
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
--
2.30.2
Powered by blists - more mailing lists