netdev - [PATCH net-next 2/3] tcp: call tcp_set_skb_tso_segs() from tcp_write

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: <20240418214600.1291486-3-edumazet@google.com>
Date: Thu, 18 Apr 2024 21:45:59 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, 
	Paolo Abeni <pabeni@...hat.com>
Cc: netdev@...r.kernel.org, Neal Cardwell <ncardwell@...gle.com>, 
	Kevin Yang <yyd@...gle.com>, eric.dumazet@...il.com, Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 2/3] tcp: call tcp_set_skb_tso_segs() from tcp_write_xmit()

tcp_write_xmit() calls tcp_init_tso_segs()
to set gso_size and gso_segs on the packet.

tcp_init_tso_segs() requires the stack to maintain
an up to date tcp_skb_pcount(), and this makes sense
for packets in rtx queue. Not so much for packets
still in the write queue.

In the following patch, we don't want to deal with
tcp_skb_pcount() when moving payload from 2nd
skb to 1st skb in the write queue.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
 net/ipv4/tcp_output.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index acbc76ca3e640354880c62c2423cfe4ba99f0be3..5e8665241f9345f38ce56afffe473948aef66786 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1502,18 +1502,22 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 }
 
 /* Initialize TSO segments for a packet. */
-static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
+static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now)
 {
+	int tso_segs;
+
 	if (skb->len <= mss_now) {
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
-		tcp_skb_pcount_set(skb, 1);
 		TCP_SKB_CB(skb)->tcp_gso_size = 0;
-	} else {
-		tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
-		TCP_SKB_CB(skb)->tcp_gso_size = mss_now;
+		tcp_skb_pcount_set(skb, 1);
+		return 1;
 	}
+	TCP_SKB_CB(skb)->tcp_gso_size = mss_now;
+	tso_segs = DIV_ROUND_UP(skb->len, mss_now);
+	tcp_skb_pcount_set(skb, tso_segs);
+	return tso_segs;
 }
 
 /* Pcount in the middle of the write queue got changed, we need to do various
@@ -2097,10 +2101,9 @@ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now)
 {
 	int tso_segs = tcp_skb_pcount(skb);
 
-	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
-		tcp_set_skb_tso_segs(skb, mss_now);
-		tso_segs = tcp_skb_pcount(skb);
-	}
+	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now))
+		return tcp_set_skb_tso_segs(skb, mss_now);
+
 	return tso_segs;
 }
 
@@ -2733,9 +2736,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (tcp_pacing_check(sk))
 			break;
 
-		tso_segs = tcp_init_tso_segs(skb, mss_now);
-		BUG_ON(!tso_segs);
-
 		cwnd_quota = tcp_cwnd_test(tp);
 		if (!cwnd_quota) {
 			if (push_one == 2)
@@ -2745,6 +2745,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
+		tso_segs = tcp_set_skb_tso_segs(skb, mss_now);
+
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) {
 			is_rwnd_limited = true;
 			break;
-- 
2.44.0.769.g3c40516874-goog