| 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
| ||
|
Message-Id: <20241021215910.59767-3-chia-yu.chang@nokia-bell-labs.com>
Date: Mon, 21 Oct 2024 23:58:58 +0200
From: chia-yu.chang@...ia-bell-labs.com
To: netdev@...r.kernel.org, davem@...emloft.net, edumazet@...gle.com,
kuba@...nel.org, pabeni@...hat.com, dsahern@...nel.org,
netfilter-devel@...r.kernel.org, kadlec@...filter.org,
coreteam@...filter.org, pablo@...filter.org, bpf@...r.kernel.org,
joel.granados@...nel.org, linux-fsdevel@...r.kernel.org,
kees@...nel.org, mcgrof@...nel.org, ij@...nel.org,
ncardwell@...gle.com, koen.de_schepper@...ia-bell-labs.com,
g.white@...leLabs.com, ingemar.s.johansson@...csson.com,
mirja.kuehlewind@...csson.com, cheshire@...le.com, rs.ietf@....at,
Jason_Livingood@...cast.com, vidhi_goel@...le.com
Cc: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
Subject: [PATCH v4 net-next 02/14] tcp: create FLAG_TS_PROGRESS
From: Ilpo Järvinen <ij@...nel.org>
Whenever timestamp advances, it declares progress which
can be used by the other parts of the stack to decide that
the ACK is the most recent one seen so far.
AccECN will use this flag when deciding whether to use the
ACK to update AccECN state or not.
Signed-off-by: Ilpo Järvinen <ij@...nel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
---
net/ipv4/tcp_input.c | 37 ++++++++++++++++++++++++++++---------
1 file changed, 28 insertions(+), 9 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5a6f93148814..3295ad329aef 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -102,6 +102,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
#define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */
#define FLAG_ACK_MAYBE_DELAYED 0x10000 /* Likely a delayed ACK */
#define FLAG_DSACK_TLP 0x20000 /* DSACK for tail loss probe */
+#define FLAG_TS_PROGRESS 0x40000 /* Positive timestamp delta */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -3813,8 +3814,16 @@ static void tcp_store_ts_recent(struct tcp_sock *tp)
tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
}
-static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+static int __tcp_replace_ts_recent(struct tcp_sock *tp, s32 tstamp_delta)
{
+ tcp_store_ts_recent(tp);
+ return tstamp_delta > 0 ? FLAG_TS_PROGRESS : 0;
+}
+
+static int tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+{
+ s32 delta;
+
if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
/* PAWS bug workaround wrt. ACK frames, the PAWS discard
* extra check below makes sure this can only happen
@@ -3823,9 +3832,13 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
* Not only, also it occurs for expired timestamps.
*/
- if (tcp_paws_check(&tp->rx_opt, 0))
- tcp_store_ts_recent(tp);
+ if (tcp_paws_check(&tp->rx_opt, 0)) {
+ delta = tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent;
+ return __tcp_replace_ts_recent(tp, delta);
+ }
}
+
+ return 0;
}
/* This routine deals with acks during a TLP episode and ends an episode by
@@ -3982,7 +3995,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
* is in window.
*/
if (flag & FLAG_UPDATE_TS_RECENT)
- tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+ flag |= tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
FLAG_SND_UNA_ADVANCED) {
@@ -6140,6 +6153,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
int tcp_header_len = tp->tcp_header_len;
+ s32 tstamp_delta = 0;
+ int flag = 0;
/* Timestamp header prediction: tcp_header_len
* is automatically equal to th->doff*4 due to pred_flags
@@ -6152,8 +6167,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
if (!tcp_parse_aligned_timestamp(tp, th))
goto slow_path;
+ tstamp_delta = tp->rx_opt.rcv_tsval -
+ tp->rx_opt.ts_recent;
/* If PAWS failed, check it more carefully in slow path */
- if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
+ if (tstamp_delta < 0)
goto slow_path;
/* DO NOT update ts_recent here, if checksum fails
@@ -6173,12 +6190,13 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
if (tcp_header_len ==
(sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
tp->rcv_nxt == tp->rcv_wup)
- tcp_store_ts_recent(tp);
+ flag |= __tcp_replace_ts_recent(tp,
+ tstamp_delta);
/* We know that such packets are checksummed
* on entry.
*/
- tcp_ack(sk, skb, 0);
+ tcp_ack(sk, skb, flag);
__kfree_skb(skb);
tcp_data_snd_check(sk);
/* When receiving pure ack in fast path, update
@@ -6209,7 +6227,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
if (tcp_header_len ==
(sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
tp->rcv_nxt == tp->rcv_wup)
- tcp_store_ts_recent(tp);
+ flag |= __tcp_replace_ts_recent(tp,
+ tstamp_delta);
tcp_rcv_rtt_measure_ts(sk, skb);
@@ -6224,7 +6243,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
/* Well, only one small jumplet in fast path... */
- tcp_ack(sk, skb, FLAG_DATA);
+ tcp_ack(sk, skb, flag | FLAG_DATA);
tcp_data_snd_check(sk);
if (!inet_csk_ack_scheduled(sk))
goto no_ack;
--
2.34.1
Powered by blists - more mailing lists