netdev - [PATCH net-next v4 06/11] net-timestamp: support SCM_TSTAMP

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-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20241207173803.90744-7-kerneljasonxing@gmail.com>
Date: Sun,  8 Dec 2024 01:37:58 +0800
From: Jason Xing <kerneljasonxing@...il.com>
To: davem@...emloft.net,
	edumazet@...gle.com,
	kuba@...nel.org,
	pabeni@...hat.com,
	dsahern@...nel.org,
	willemdebruijn.kernel@...il.com,
	willemb@...gle.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@...ichev.me,
	haoluo@...gle.com,
	jolsa@...nel.org
Cc: bpf@...r.kernel.org,
	netdev@...r.kernel.org,
	Jason Xing <kernelxing@...cent.com>
Subject: [PATCH net-next v4 06/11] net-timestamp: support SCM_TSTAMP_ACK for bpf extension

From: Jason Xing <kernelxing@...cent.com>

Handle the ACK timestamp case. Actually testing SKBTX_BPF flag
can work, but we need to Introduce a new txstamp_ack_bpf to avoid
cache line misses in tcp_ack_tstamp().

Signed-off-by: Jason Xing <kernelxing@...cent.com>
---
 include/net/tcp.h              | 3 ++-
 include/uapi/linux/bpf.h       | 5 +++++
 net/core/skbuff.c              | 9 ++++++---
 net/ipv4/tcp_input.c           | 3 ++-
 net/ipv4/tcp_output.c          | 5 +++++
 tools/include/uapi/linux/bpf.h | 5 +++++
 6 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e9b37b76e894..8e5103d3c6b9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -959,9 +959,10 @@ struct tcp_skb_cb {
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+			txstamp_ack_bpf:1,	/* ack timestamp for bpf use */
 			eor:1,		/* Is skb MSG_EOR marked? */
 			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
-			unused:5;
+			unused:4;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a6d761f07f67..a0aff1b4eb61 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7032,6 +7032,11 @@ enum {
 					 * feature is on. It indicates the
 					 * recorded timestamp.
 					 */
+	BPF_SOCK_OPS_TS_ACK_OPT_CB,	/* Called when all the skbs are
+					 * acknowledged when SO_TIMESTAMPING
+					 * feature is on. It indicates the
+					 * recorded timestamp.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 73b15d6277f7..48b0c71e9522 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5553,6 +5553,9 @@ static void __skb_tstamp_tx_bpf(struct sock *sk, struct sk_buff *skb, int tstype
 	case SCM_TSTAMP_SND:
 		op = BPF_SOCK_OPS_TS_SW_OPT_CB;
 		break;
+	case SCM_TSTAMP_ACK:
+		op = BPF_SOCK_OPS_TS_ACK_OPT_CB;
+		break;
 	default:
 		return;
 	}
@@ -5632,9 +5635,9 @@ static bool skb_tstamp_is_set(const struct sk_buff *skb, int tstype, bool bpf_mo
 			return true;
 		return false;
 	case SCM_TSTAMP_ACK:
-		if (TCP_SKB_CB(skb)->txstamp_ack)
-			return true;
-		return false;
+		flag = bpf_mode ? TCP_SKB_CB(skb)->txstamp_ack_bpf :
+				  TCP_SKB_CB(skb)->txstamp_ack;
+		return !!flag;
 	}
 
 	return false;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5bdf13ac26ef..82bb26f5b214 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3321,7 +3321,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 	const struct skb_shared_info *shinfo;
 
 	/* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
-	if (likely(!TCP_SKB_CB(skb)->txstamp_ack))
+	if (likely(!TCP_SKB_CB(skb)->txstamp_ack &&
+		   !TCP_SKB_CB(skb)->txstamp_ack_bpf))
 		return;
 
 	shinfo = skb_shinfo(skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5485a70b5fe5..c8927143d3e1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1552,6 +1552,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
 static bool tcp_has_tx_tstamp(const struct sk_buff *skb)
 {
 	return TCP_SKB_CB(skb)->txstamp_ack ||
+	       TCP_SKB_CB(skb)->txstamp_ack_bpf ||
 		(skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP);
 }
 
@@ -1568,7 +1569,9 @@ static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2)
 		shinfo2->tx_flags |= tsflags;
 		swap(shinfo->tskey, shinfo2->tskey);
 		TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack;
+		TCP_SKB_CB(skb2)->txstamp_ack_bpf = TCP_SKB_CB(skb)->txstamp_ack_bpf;
 		TCP_SKB_CB(skb)->txstamp_ack = 0;
+		TCP_SKB_CB(skb)->txstamp_ack_bpf = 0;
 	}
 }
 
@@ -3209,6 +3212,8 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 		shinfo->tskey = next_shinfo->tskey;
 		TCP_SKB_CB(skb)->txstamp_ack |=
 			TCP_SKB_CB(next_skb)->txstamp_ack;
+		TCP_SKB_CB(skb)->txstamp_ack_bpf |=
+			TCP_SKB_CB(next_skb)->txstamp_ack_bpf;
 	}
 }
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 73fc0a95c9ca..0fe7d663a244 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7025,6 +7025,11 @@ enum {
 					 * feature is on. It indicates the
 					 * recorded timestamp.
 					 */
+	BPF_SOCK_OPS_TS_ACK_OPT_CB,	/* Called when all the skbs are
+					 * acknowledged when SO_TIMESTAMPING
+					 * feature is on. It indicates the
+					 * recorded timestamp.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
-- 
2.37.3