net: ensure correct skb->tstamp in various fragmenters

Thomas found that some forwarded packets would be stuck
in FQ packet scheduler because their skb->tstamp contained
timestamps far in the future.

We thought we addressed this point in commit 8203e2d844d3
("net: clear skb->tstamp in forwarding paths") but there
is still an issue when/if a packet needs to be fragmented.

In order to meet EDT requirements, we have to make sure all
fragments get the original skb->tstamp.

Note that this original skb->tstamp should be zero in
forwarding path, but might have a non zero value in
output path if user decided so.

Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Thomas Bartschies <Thomas.Bartschies@cvk.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 12 insertions, 0 deletions

diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 8842798c29e6..506d6141e44e 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -33,6 +33,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 	unsigned int hlen, ll_rs, mtu;
+	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
 	int err;
@@ -80,6 +81,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 			if (iter.frag)
 				ip_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -104,6 +106,7 @@ slow_path:
 			goto blackhole;
 		}
 
+		skb2->tstamp = tstamp;
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 28fca408812c..814b9b8882a0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt = skb_rtable(skb);
 	unsigned int mtu, hlen, ll_rs;
 	struct ip_fraglist_iter iter;
+	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	int err = 0;
 
@@ -846,6 +847,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				ip_fraglist_prepare(skb, &iter);
 			}
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, skb);
 
 			if (!err)
@@ -900,6 +902,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
+		skb2->tstamp = tstamp;
 		err = output(net, sk, skb2);
 		if (err)
 			goto fail;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index edadee4a7e76..71827b56c006 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
+	ktime_t tstamp = skb->tstamp;
 	int hroom, err = 0;
 	__be32 frag_id;
 	u8 *prevhdr, nexthdr = 0;
@@ -855,6 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -913,6 +915,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
+		frag->tstamp = tstamp;
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index a9bff556d3b2..409e79b84a83 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				  struct sk_buff *))
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+	ktime_t tstamp = skb->tstamp;
 	struct ip6_frag_state state;
 	u8 *prevhdr, nexthdr = 0;
 	unsigned int mtu, hlen;
@@ -183,6 +184,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -215,6 +217,7 @@ slow_path:
 			goto blackhole;
 		}
 
+		skb2->tstamp = tstamp;
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;