netdev - [PATCH bpf-next] bpf: add sacked flag in BPF_SOCK_OPS_RETRANS

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240417124622.35333-1-lulie@linux.alibaba.com>
Date: Wed, 17 Apr 2024 20:46:22 +0800
From: Philo Lu <lulie@...ux.alibaba.com>
To: bpf@...r.kernel.org
Cc: netdev@...r.kernel.org,
	edumazet@...gle.com,
	davem@...emloft.net,
	kuba@...nel.org,
	pabeni@...hat.com,
	ast@...nel.org,
	daniel@...earbox.net,
	andrii@...nel.org,
	martin.lau@...ux.dev,
	eddyz87@...il.com,
	song@...nel.org,
	yonghong.song@...ux.dev,
	john.fastabend@...il.com,
	kpsingh@...nel.org,
	sdf@...gle.com,
	haoluo@...gle.com,
	jolsa@...nel.org,
	dsahern@...nel.org,
	laoar.shao@...il.com,
	xuanzhuo@...ux.alibaba.com,
	fred.cc@...baba-inc.com
Subject: [PATCH bpf-next] bpf: add sacked flag in BPF_SOCK_OPS_RETRANS_CB

Add TCP_SKB_CB(skb)->sacked as the 4th arg of sockops passed to bpf
program. Then we can get the retransmission efficiency by counting skbs
w/ and w/o TCPCB_EVER_RETRANS mark. And for this purpose, sacked
updating is moved after the BPF_SOCK_OPS_RETRANS_CB hook.

Signed-off-by: Philo Lu <lulie@...ux.alibaba.com>
---
 include/net/tcp.h              | 14 ++++++++++++++
 include/uapi/linux/bpf.h       |  2 ++
 net/ipv4/tcp_output.c          |  9 +++++----
 tools/include/uapi/linux/bpf.h |  2 ++
 4 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ae35199d3b3..7defe67183c9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2660,6 +2660,14 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
 	return tcp_call_bpf(sk, op, 3, args);
 }
 
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3, u32 arg4)
+{
+	u32 args[4] = {arg1, arg2, arg3, arg4};
+
+	return tcp_call_bpf(sk, op, 4, args);
+}
+
 #else
 static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 {
@@ -2677,6 +2685,12 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
 	return -EPERM;
 }
 
+static inline int tcp_call_bpf_4arg(struct sock *sk, int op, u32 arg1, u32 arg2,
+				    u32 arg3, u32 arg4)
+{
+	return -EPERM;
+}
+
 #endif
 
 static inline u32 tcp_timeout_init(struct sock *sk)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cee0a7915c08..df6bb9a62e0b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6938,6 +6938,8 @@ enum {
 					 * Arg2: # segments
 					 * Arg3: return value of
 					 *       tcp_transmit_skb (0 => success)
+					 * Arg4: TCP_SKB_CB(skb)->sacked before
+					 *       TCPCB_EVER_RETRANS marking
 					 */
 	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
 					 * Arg1: old_state
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e3167ad96567..370e6cee6794 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3387,15 +3387,16 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
 
+	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+		tcp_call_bpf_4arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+				  TCP_SKB_CB(skb)->seq, segs, err,
+				  TCP_SKB_CB(skb)->sacked);
+
 	/* To avoid taking spuriously low RTT samples based on a timestamp
 	 * for a transmit that never happened, always mark EVER_RETRANS
 	 */
 	TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
 
-	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
-		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
-				  TCP_SKB_CB(skb)->seq, segs, err);
-
 	if (likely(!err)) {
 		trace_tcp_retransmit_skb(sk, skb);
 	} else if (err != -EBUSY) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cee0a7915c08..df6bb9a62e0b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6938,6 +6938,8 @@ enum {
 					 * Arg2: # segments
 					 * Arg3: return value of
 					 *       tcp_transmit_skb (0 => success)
+					 * Arg4: TCP_SKB_CB(skb)->sacked before
+					 *       TCPCB_EVER_RETRANS marking
 					 */
 	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
 					 * Arg1: old_state
-- 
2.32.0.3.g01195cf9f