Skip to contentSkip to conversation

FAILED: patch "[PATCH] tcp: clamp route advmss to TCP_MIN_MSS" failed to apply to 6.18-stable tree

PATCH New [email protected] 2 participants 7 messages Aug 31 – Sep 1

Subsystems (3)
Networking Stable branch TCP
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x 870a9e42ecc6fe1b8c25d87af043cb0d9c178fe1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026083104-huddle-balancing-d57b@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 870a9e42ecc6fe1b8c25d87af043cb0d9c178fe1 Mon Sep 17 00:00:00 2001
From: Yong Wang <[email protected]>
Date: Wed, 19 Aug 2026 23:22:04 +0800
Subject: [PATCH] tcp: clamp route advmss to TCP_MIN_MSS

tcp_select_initial_window() assumes that callers never pass an MSS smaller than 1, but route-derived advmss values can violate that assumption.

A too-small explicit RTAX_ADVMSS is one way to get there, but it is not the only one. The same divide-by-zero can also be reached through the "default advmss" path when RTAX_ADVMSS is left at 0 and the effective advmss is later driven down by route MTU and min_adv_mss.

Introduce a tcp_dst_advmss() helper that clamps route advmss to TCP_MIN_MSS before TCP consumes it, and use it in the TCP paths that derive advmss from dst metrics. This keeps the effective MSS from dropping to zero before tcp_select_initial_window() rounds the receive window.

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc [email protected]
Reported-by Vega <[email protected]>
Signed-off-by Yong Wang <[email protected]>
Signed-off-by Ren Wei <[email protected]>
Link https://patch.msgid.link/251eaf8277fa7c66364c9815c5da01662d269181.1787074852.git.edragain@163.com open here
Signed-off-by Jakub Kicinski <[email protected]>
include/net/tcp.h +5 -0
index 2c5b889530b5..670c20876f26 100644
@@ -1782,6 +1782,11 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+static inline u32 tcp_dst_advmss(const struct dst_entry *dst)
+{
+	return max_t(u32, dst_metric_advmss(dst), TCP_MIN_MSS);
+}
+
 static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);
net/ipv4/tcp_ipv4.c +1 -1
index 190c7af4cf92..9f053eb8b46e 100644
@@ -1736,7 +1736,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
net/ipv4/tcp_minisocks.c +1 -1
index 12254e6eb2f3..f3fa0b18eda0 100644
@@ -440,7 +440,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	u32 rcv_wnd;
 	int mss;
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
net/ipv4/tcp_output.c +3 -3
index fcaa04e65189..f2709d585edb 100644
@@ -143,7 +143,7 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 	int mss = tp->advmss;
 
 	if (dst) {
-		unsigned int metric = dst_metric_advmss(dst);
+		unsigned int metric = tcp_dst_advmss(dst);
 
 		if (metric < mss) {
 			mss = metric;

@@ -3972,7 +3972,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	}
 	skb_dst_set(skb, dst);
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 	now = tcp_clock_ns();

@@ -4128,7 +4128,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW));
-	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	tp->advmss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
net/ipv6/tcp_ipv6.c +1 -1
index 9e9155b1b3aa..df9c29eb5c1f 100644
@@ -1487,7 +1487,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst6_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
maintainer
#1 lore raw

PATCH 1/6 ipv6: pass proto by value to ipv6_push_nfrag_opts() and ipv6_push_frag_opts()

From: Eric Dumazet <[email protected]>

[ Upstream commit 1bc46dd209667346c5aa56c351995e7c260696d0 ]

With CONFIG_STACKPROTECTOR_STRONG=y, it is better to avoid passing a pointer to an automatic variable.

Change these exported functions to return 'u8 proto' instead of void.

- ipv6_push_nfrag_opts()
- ipv6_push_frag_opts()

For instance, replace

	ipv6_push_frag_opts(skb, opt, &proto);
with:
	proto = ipv6_push_frag_opts(skb, opt, proto);

Note that even after this change, ip6_xmit() has to use a stack canary because of @first_hop variable.

Signed-off-by Eric Dumazet <[email protected]>
Reviewed-by Kuniyuki Iwashima <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Jakub Kicinski <[email protected]>

Stable-dep-of: 870a9e42ecc6 ("tcp: clamp route advmss to TCP_MIN_MSS")

Signed-off-by Sasha Levin <[email protected]>
---
 include/net/ipv6.h    | 10 ++++----
 net/ipv6/exthdrs.c    | 55 +++++++++++++++++++++++--------------------
 net/ipv6/ip6_output.c | 19 ++++++++-------
 net/ipv6/ip6_tunnel.c |  2 +-
 4 files changed, 46 insertions(+), 40 deletions(-)
include/net/ipv6.h +5 -5
index 087aa7f502d56..aa8b525908ea0 100644
@@ -1147,11 +1147,11 @@ int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
  *	Extension header (options) processing
  */
 
-void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
-			  u8 *proto, struct in6_addr **daddr_p,
-			  struct in6_addr *saddr);
-void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
-			 u8 *proto);
+u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
+			u8 proto, struct in6_addr **daddr_p,
+			struct in6_addr *saddr);
+u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
+		       u8 proto);
 
 int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp,
 		     __be16 *frag_offp);
net/ipv6/exthdrs.c +29 -26

109 lines not on this page · raw message

net/ipv6/ip6_output.c +11 -8
index 5f2c96e052dff..351649874733e 100644
@@ -307,11 +307,12 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		seg_len += opt->opt_nflen + opt->opt_flen;
 
 		if (opt->opt_flen)
-			ipv6_push_frag_opts(skb, opt, &proto);
+			proto = ipv6_push_frag_opts(skb, opt, proto);
 
 		if (opt->opt_nflen)
-			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
-					     &fl6->saddr);
+			proto = ipv6_push_nfrag_opts(skb, opt, proto,
+						     &first_hop,
+						     &fl6->saddr);
 	}
 
 	if (unlikely(seg_len > IPV6_MAXPLEN)) {

@@ -1941,11 +1942,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	__skb_pull(skb, skb_network_header_len(skb));
 
 	final_dst = &fl6->daddr;
-	if (opt && opt->opt_flen)
-		ipv6_push_frag_opts(skb, opt, &proto);
-	if (opt && opt->opt_nflen)
-		ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr);
-
+	if (opt) {
+		if (opt->opt_flen)
+			proto = ipv6_push_frag_opts(skb, opt, proto);
+		if (opt->opt_nflen)
+			proto = ipv6_push_nfrag_opts(skb, opt, proto,
+						     &final_dst, &fl6->saddr);
+	}
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
net/ipv6/ip6_tunnel.c +1 -1
index 757c37092be7d..ba3084cecc979 100644
@@ -1273,7 +1273,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 	if (encap_limit >= 0) {
 		init_tel_txopt(&opt, encap_limit);
-		ipv6_push_frag_opts(skb, &opt.ops, &proto);
+		proto = ipv6_push_frag_opts(skb, &opt.ops, proto);
 	}
 
 	skb_push(skb, sizeof(struct ipv6hdr));
Signature · 1 line
2.53.0
maintainer
#2 lore raw

PATCH 2/6 ipv6: add some unlikely()/likely() clauses in ip6_output.c

From: Eric Dumazet <[email protected]>

[ Upstream commit 2855e4925416c5900a9c6cece11f4a2e56bf6e63 ]

1) daddr is unlikely a multicast in ip6_finish_output2().

2) ip6_finish_output_gso_slowpath_drop() should not be called often.

3) ip6_fragment() should not be called often.

4) opt is unlikely to be set.

5) ip6_xmit() and ip6_forward() mostly sends not too big packets.

6) Most __ip6_make_skb() calls are for UDP packets, not ICMPV6 ones.

Signed-off-by Eric Dumazet <[email protected]>
Reviewed-by Kuniyuki Iwashima <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Jakub Kicinski <[email protected]>

Stable-dep-of: 870a9e42ecc6 ("tcp: clamp route advmss to TCP_MIN_MSS")

Signed-off-by Sasha Levin <[email protected]>
---
 net/ipv6/ip6_output.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)
net/ipv6/ip6_output.c +12 -12
index 351649874733e..d048321733b38 100644
@@ -80,7 +80,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 
 	hdr = ipv6_hdr(skb);
 	daddr = &hdr->daddr;
-	if (ipv6_addr_is_multicast(daddr)) {
+	if (unlikely(ipv6_addr_is_multicast(daddr))) {
 		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
 		    ((mroute6_is_socket(net, skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||

@@ -181,8 +181,8 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
 static int ip6_finish_output_gso(struct net *net, struct sock *sk,
 				 struct sk_buff *skb, unsigned int mtu)
 {
-	if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
-	    !skb_gso_validate_network_len(skb, mtu))
+	if (unlikely(!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu)))
 		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
 
 	return ip6_finish_output2(net, sk, skb);

@@ -204,8 +204,8 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 	if (skb_is_gso(skb))
 		return ip6_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu ||
-	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
+	if (unlikely(skb->len > mtu ||
+	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
 
 	return ip6_finish_output2(net, sk, skb);

@@ -303,7 +303,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		}
 	}
 
-	if (opt) {
+	if (unlikely(opt)) {
 		seg_len += opt->opt_nflen + opt->opt_flen;
 
 		if (opt->opt_flen)

@@ -356,7 +356,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	skb->mark = mark;
 
 	mtu = dst_mtu(dst);
-	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
+	if (likely((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb))) {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
 
 		/* if egress device is enslaved to an L3 master device pass the

@@ -656,7 +656,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (ip6_pkt_too_big(skb, mtu)) {
+	if (unlikely(ip6_pkt_too_big(skb, mtu))) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);

@@ -1370,7 +1370,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	/*
 	 * setup for corking
 	 */
-	if (opt) {
+	if (unlikely(opt)) {
 		if (WARN_ON(v6_cork->opt))
 			return -EINVAL;
 

@@ -1886,7 +1886,7 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
 static void ip6_cork_release(struct inet_cork_full *cork,
 			     struct inet6_cork *v6_cork)
 {
-	if (v6_cork->opt) {
+	if (unlikely(v6_cork->opt)) {
 		struct ipv6_txoptions *opt = v6_cork->opt;
 
 		kfree(opt->dst0opt);

@@ -1942,7 +1942,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	__skb_pull(skb, skb_network_header_len(skb));
 
 	final_dst = &fl6->daddr;
-	if (opt) {
+	if (unlikely(opt)) {
 		if (opt->opt_flen)
 			proto = ipv6_push_frag_opts(skb, opt, proto);
 		if (opt->opt_nflen)

@@ -1970,7 +1970,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
-	if (proto == IPPROTO_ICMPV6) {
+	if (unlikely(proto == IPPROTO_ICMPV6)) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 		u8 icmp6_type;
Signature · 1 line
2.53.0
maintainer
#3 lore raw

PATCH 3/6 inet: add dst4_mtu() and dst6_mtu() helpers

In reply to Sasha Levin

From: Eric Dumazet <[email protected]>

[ Upstream commit 8776c4ef3ab22b95f55713f00a7a576e6402507d ]

With CONFIG_MITIGATION_RETPOLINE=y dst_mtu() is a bit fat, because it is generic.

Indeed, clang does not always inline it.

Add dst4_mtu() and dst6_mtu() helpers for callers that expect either ipv4_mtu() or ip6_mtu() to be called.

These helpers are always inlined.

Signed-off-by Eric Dumazet <[email protected]>
Reviewed-by Kuniyuki Iwashima <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Jakub Kicinski <[email protected]>

Stable-dep-of: 870a9e42ecc6 ("tcp: clamp route advmss to TCP_MIN_MSS")

Signed-off-by Sasha Levin <[email protected]>
---
 include/net/dst.h       | 6 ++++++
 include/net/ip6_route.h | 6 ++++++
 2 files changed, 12 insertions(+)
include/net/dst.h +6 -0
index f8aa1239b4db6..307073eae7f83 100644
@@ -219,6 +219,12 @@ static inline u32 dst_mtu(const struct dst_entry *dst)
 	return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst);
 }
 
+/* Variant of dst_mtu() for IPv4 users. */
+static inline u32 dst4_mtu(const struct dst_entry *dst)
+{
+	return INDIRECT_CALL_1(dst->ops->mtu, ipv4_mtu, dst);
+}
+
 /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
 static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
 {
include/net/ip6_route.h +6 -0
index 7c5512baa4b2b..a55f9bf95fe39 100644
@@ -266,6 +266,12 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		 int (*output)(struct net *, struct sock *, struct sk_buff *));
 
+/* Variant of dst_mtu() for IPv6 users */
+static inline u32 dst6_mtu(const struct dst_entry *dst)
+{
+	return INDIRECT_CALL_1(dst->ops->mtu, ip6_mtu, dst);
+}
+
 static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb)
 {
 	const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
Signature · 1 line
2.53.0
maintainer
#4 lore raw

PATCH 4/6 ipv6: use dst6_mtu() instead of dst_mtu()

In reply to Sasha Levin

From: Eric Dumazet <[email protected]>

[ Upstream commit b40f0130a23b6bab8b359e158a40af81f11f14be ]

When we expect an IPv6 dst, use dst6_mtu() instead of dst_mtu() to save some code space.

Due to current dst6_mtu() implementation, only convert users in IPv6 stack.

Signed-off-by Eric Dumazet <[email protected]>
Reviewed-by Kuniyuki Iwashima <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Jakub Kicinski <[email protected]>

Stable-dep-of: 870a9e42ecc6 ("tcp: clamp route advmss to TCP_MIN_MSS")

Signed-off-by Sasha Levin <[email protected]>
---
 net/ipv6/ip6_gre.c       |  2 +-
 net/ipv6/ip6_output.c    |  6 +++---
 net/ipv6/ip6_tunnel.c    |  4 ++--
 net/ipv6/ipv6_sockglue.c |  4 ++--
 net/ipv6/route.c         | 10 ++++++----
 net/ipv6/tcp_ipv6.c      |  9 +++++----
 6 files changed, 19 insertions(+), 16 deletions(-)
net/ipv6/ip6_gre.c +1 -1
index 58b473c157c82..4fbda6d83c0dc 100644
@@ -1057,7 +1057,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst) {
 		mtu = READ_ONCE(dst_dev(dst)->mtu);
-		if (dst_mtu(dst) > mtu)
+		if (dst6_mtu(dst) > mtu)
 			dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 	}
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
net/ipv6/ip6_output.c +3 -3
index d048321733b38..7545fdbf07da2 100644
@@ -355,7 +355,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	skb->priority = priority;
 	skb->mark = mark;
 
-	mtu = dst_mtu(dst);
+	mtu = dst6_mtu(dst);
 	if (likely((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb))) {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
 

@@ -1405,10 +1405,10 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	v6_cork->dontfrag = ipc6->dontfrag;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
 		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
-		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
+		      READ_ONCE(rt->dst.dev->mtu) : dst6_mtu(&rt->dst);
 	else
 		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
-			READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
+			READ_ONCE(rt->dst.dev->mtu) : dst6_mtu(xfrm_dst_path(&rt->dst));
 
 	frag_size = READ_ONCE(np->frag_size);
 	if (frag_size && frag_size < mtu)
net/ipv6/ip6_tunnel.c +2 -2
index ba3084cecc979..e321feca8926d 100644
@@ -643,7 +643,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	/* change mtu on this route */
 	if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
-		if (rel_info > dst_mtu(skb_dst(skb2)))
+		if (rel_info > dst6_mtu(skb_dst(skb2)))
 			goto out;
 
 		skb_dst_update_pmtu_no_confirm(skb2, rel_info);

@@ -1195,7 +1195,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
+	mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
net/ipv6/ipv6_sockglue.c +2 -2
index a61e742794f9e..d784a8644ff20 100644
@@ -1184,7 +1184,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		rcu_read_lock();
 		dst = __sk_dst_get(sk);
 		if (dst)
-			val = dst_mtu(dst);
+			val = dst6_mtu(dst);
 		rcu_read_unlock();
 		if (!val)
 			return -ENOTCONN;

@@ -1283,7 +1283,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		rcu_read_lock();
 		dst = __sk_dst_get(sk);
 		if (dst)
-			mtuinfo.ip6m_mtu = dst_mtu(dst);
+			mtuinfo.ip6m_mtu = dst6_mtu(dst);
 		rcu_read_unlock();
 		if (!mtuinfo.ip6m_mtu)
 			return -ENOTCONN;
net/ipv6/route.c +6 -4
index 5894f7dd4d4d7..5ad2d92319562 100644
@@ -2053,6 +2053,8 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
 					 struct rt6_info *rt, int mtu)
 {
+	u32 dmtu = dst6_mtu(&rt->dst);
+
 	/* If the new MTU is lower than the route PMTU, this new MTU will be the
 	 * lowest MTU in the path: always allow updating the route PMTU to
 	 * reflect PMTU decreases.

@@ -2063,10 +2065,10 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
 	 * handle this.
 	 */
 
-	if (dst_mtu(&rt->dst) >= mtu)
+	if (dmtu >= mtu)
 		return true;
 
-	if (dst_mtu(&rt->dst) == idev->cnf.mtu6)
+	if (dmtu == idev->cnf.mtu6)
 		return true;
 
 	return false;

@@ -2936,7 +2938,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 	if (mtu < IPV6_MIN_MTU)
 		return;
-	if (mtu >= dst_mtu(dst))
+	if (mtu >= dst6_mtu(dst))
 		return;
 
 	if (!rt6_cache_allowed_for_pmtu(rt6)) {

@@ -3252,7 +3254,7 @@ EXPORT_SYMBOL_GPL(ip6_sk_redirect);
 
 static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 {
-	unsigned int mtu = dst_mtu(dst);
+	unsigned int mtu = dst6_mtu(dst);
 	struct net *net;
 
 	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
net/ipv6/tcp_ipv6.c +5 -4
index 952bf49efbc6a..cedfdf728cd41 100644
@@ -351,7 +351,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 static void tcp_v6_mtu_reduced(struct sock *sk)
 {
 	struct dst_entry *dst;
-	u32 mtu;
+	u32 mtu, dmtu;
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
 		return;

@@ -368,8 +368,9 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
 	if (!dst)
 		return;
 
-	if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
-		tcp_sync_mss(sk, dst_mtu(dst));
+	dmtu = dst6_mtu(dst);
+	if (inet_csk(sk)->icsk_pmtu_cookie > dmtu) {
+		tcp_sync_mss(sk, dmtu);
 		tcp_simple_retransmit(sk);
 	}
 }

@@ -1499,7 +1500,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	tcp_ca_openreq_child(newsk, dst);
 
-	tcp_sync_mss(newsk, dst_mtu(dst));
+	tcp_sync_mss(newsk, dst6_mtu(dst));
 	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
Signature · 1 line
2.53.0
maintainer
#5 lore raw

PATCH 5/6 ipv4: use dst4_mtu() instead of dst_mtu()

In reply to Sasha Levin

From: Eric Dumazet <[email protected]>

[ Upstream commit fe8570186f100b6cc499b2f7705946baf1388cde ]

When we expect an IPv4 dst, use dst4_mtu() instead of dst_mtu() to save some code space.

Signed-off-by Eric Dumazet <[email protected]>
Reviewed-by Kuniyuki Iwashima <[email protected]>
Link https://patch.msgid.link/[email protected] open here
Signed-off-by Jakub Kicinski <[email protected]>

Stable-dep-of: 870a9e42ecc6 ("tcp: clamp route advmss to TCP_MIN_MSS")

Signed-off-by Sasha Levin <[email protected]>
---
 net/ipv4/icmp.c                     |  2 +-
 net/ipv4/ip_output.c                |  4 ++--
 net/ipv4/ip_sockglue.c              |  2 +-
 net/ipv4/ipmr.c                     |  2 +-
 net/ipv4/netfilter/nf_reject_ipv4.c |  2 +-
 net/ipv4/tcp_ipv4.c                 | 13 ++++++-------
 net/ipv6/sit.c                      |  2 +-
 7 files changed, 13 insertions(+), 14 deletions(-)
net/ipv4/icmp.c +1 -1
index 691d7b076c620..a66e1a7175e90 100644
@@ -790,7 +790,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 	/* RFC says return as much as we can without exceeding 576 bytes. */
 
-	room = dst_mtu(&rt->dst);
+	room = dst4_mtu(&rt->dst);
 	if (room > 576)
 		room = 576;
 	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
net/ipv4/ip_output.c +2 -2
index 47d24f74ed1b6..267ac4730b590 100644
@@ -1303,7 +1303,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		return -EFAULT;
 
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+			 dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
 
 	if (!inetdev_valid_mtu(cork->fragsize))
 		return -ENETUNREACH;

@@ -1442,7 +1442,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	pmtudisc = READ_ONCE(inet->pmtudisc);
 	if (pmtudisc == IP_PMTUDISC_DO ||
 	    pmtudisc == IP_PMTUDISC_PROBE ||
-	    (skb->len <= dst_mtu(&rt->dst) &&
+	    (skb->len <= dst4_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
net/ipv4/ip_sockglue.c +1 -1
index 7d4f1face2e79..7af607f329ac3 100644
@@ -1634,7 +1634,7 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		val = 0;
 		dst = sk_dst_get(sk);
 		if (dst) {
-			val = dst_mtu(dst);
+			val = dst4_mtu(dst);
 			dst_release(dst);
 		}
 		if (!val)
net/ipv4/ipmr.c +1 -1
index ca9eaee4c2ef5..131382c388e95 100644
@@ -1895,7 +1895,7 @@ static int ipmr_prepare_xmit(struct net *net, struct mr_table *mrt,
 			return -1;
 	}
 
-	if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
+	if (skb->len+encap > dst4_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
 		/* Do not fragment multicasts. Alas, IPv4 does not
 		 * allow to send ICMP, so that packets will disappear
 		 * to blackhole.
net/ipv4/netfilter/nf_reject_ipv4.c +1 -1
index c47d56576720f..4626dc46808f3 100644
@@ -303,7 +303,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		goto free_nskb;
 
 	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
+	if (nskb->len > dst4_mtu(skb_dst(nskb)))
 		goto free_nskb;
 
 	nf_ct_attach(nskb, oldskb);
net/ipv4/tcp_ipv4.c +6 -7
index 708b69cc2f56c..6f8d27035b6fe 100644
@@ -373,7 +373,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct dst_entry *dst;
-	u32 mtu;
+	u32 mtu, dmtu;
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
 		return;

@@ -385,15 +385,14 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 	/* Something is about to be wrong... Remember soft error
 	 * for the case, if this connection will not able to recover.
 	 */
-	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
+	dmtu = dst4_mtu(dst);
+	if (mtu < dmtu && ip_dont_fragment(sk, dst))
 		WRITE_ONCE(sk->sk_err_soft, EMSGSIZE);
 
-	mtu = dst_mtu(dst);
-
 	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
 	    ip_sk_accept_pmtu(sk) &&
-	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
-		tcp_sync_mss(sk, mtu);
+	    inet_csk(sk)->icsk_pmtu_cookie > dmtu) {
+		tcp_sync_mss(sk, dmtu);
 
 		/* Resend the TCP packet because it's
 		 * clear that the old packet has been

@@ -1817,7 +1816,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 #endif
 	tcp_ca_openreq_child(newsk, dst);
 
-	tcp_sync_mss(newsk, dst_mtu(dst));
+	tcp_sync_mss(newsk, dst4_mtu(dst));
 	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
net/ipv6/sit.c +1 -1
index c03df1682a639..77918643d1754 100644
@@ -963,7 +963,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	iph6 = ipv6_hdr(skb);
 
 	if (df) {
-		mtu = dst_mtu(&rt->dst) - t_hlen;
+		mtu = dst4_mtu(&rt->dst) - t_hlen;
 
 		if (mtu < IPV4_MIN_MTU) {
 			DEV_STATS_INC(dev, collisions);
Signature · 1 line
2.53.0
maintainer
#6 lore raw

PATCH 6/6 tcp: clamp route advmss to TCP_MIN_MSS

In reply to Sasha Levin

From: Yong Wang <[email protected]>

[ Upstream commit 870a9e42ecc6fe1b8c25d87af043cb0d9c178fe1 ]

tcp_select_initial_window() assumes that callers never pass an MSS smaller than 1, but route-derived advmss values can violate that assumption.

A too-small explicit RTAX_ADVMSS is one way to get there, but it is not the only one. The same divide-by-zero can also be reached through the "default advmss" path when RTAX_ADVMSS is left at 0 and the effective advmss is later driven down by route MTU and min_adv_mss.

Introduce a tcp_dst_advmss() helper that clamps route advmss to TCP_MIN_MSS before TCP consumes it, and use it in the TCP paths that derive advmss from dst metrics. This keeps the effective MSS from dropping to zero before tcp_select_initial_window() rounds the receive window.

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc [email protected]
Reported-by Vega <[email protected]>
Signed-off-by Yong Wang <[email protected]>
Signed-off-by Ren Wei <[email protected]>
Link https://patch.msgid.link/251eaf8277fa7c66364c9815c5da01662d269181.1787074852.git.edragain@163.com open here
Signed-off-by Jakub Kicinski <[email protected]>
Signed-off-by Sasha Levin <[email protected]>
---
 include/net/tcp.h        | 5 +++++
 net/ipv4/tcp_ipv4.c      | 2 +-
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv4/tcp_output.c    | 6 +++---
 net/ipv6/tcp_ipv6.c      | 2 +-
 5 files changed, 11 insertions(+), 6 deletions(-)
include/net/tcp.h +5 -0
index c9439e7f3e7b8..25bb67e28ad47 100644
@@ -1686,6 +1686,11 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+static inline u32 tcp_dst_advmss(const struct dst_entry *dst)
+{
+	return max_t(u32, dst_metric_advmss(dst), TCP_MIN_MSS);
+}
+
 static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);
net/ipv4/tcp_ipv4.c +1 -1
index 6f8d27035b6fe..dcd7c9f12c253 100644
@@ -1817,7 +1817,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
net/ipv4/tcp_minisocks.c +1 -1
index 4ac30573f233f..a496c26737fde 100644
@@ -445,7 +445,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	u32 rcv_wnd;
 	int mss;
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
net/ipv4/tcp_output.c +3 -3
index 479be2f242627..efa533a362e37 100644
@@ -129,7 +129,7 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 	int mss = tp->advmss;
 
 	if (dst) {
-		unsigned int metric = dst_metric_advmss(dst);
+		unsigned int metric = tcp_dst_advmss(dst);
 
 		if (metric < mss) {
 			mss = metric;

@@ -3906,7 +3906,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	}
 	skb_dst_set(skb, dst);
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 	now = tcp_clock_ns();

@@ -4062,7 +4062,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW));
-	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	tp->advmss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
net/ipv6/tcp_ipv6.c +1 -1
index cedfdf728cd41..9e1db70c20943 100644
@@ -1501,7 +1501,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst6_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
Signature · 1 line
2.53.0