From: Eric Dumazet <edumazet@xxxxxxxxxx>
[ Upstream commit 9669fffc1415bb0c30e5d2ec98a8e1c3a418cb9c ]
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@xxxxxxxxxx>
Reported-by: Thomas Bartschies <Thomas.Bartschies@xxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/bridge/netfilter/nf_conntrack_bridge.c | 3 +++
net/ipv4/ip_output.c | 3 +++
net/ipv6/ip6_output.c | 3 +++
net/ipv6/netfilter.c | 3 +++
4 files changed, 12 insertions(+)
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -34,6 +34,7 @@ static int nf_br_ip_fragment(struct net
{
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;
@@ -81,6 +82,7 @@ static int nf_br_ip_fragment(struct net
if (iter.frag)
ip_fraglist_prepare(skb, &iter);
+ skb->tstamp = tstamp;
err = output(net, sk, data, skb);
if (err || !iter.frag)
break;
@@ -105,6 +107,7 @@ slow_path:
goto blackhole;
}
+ skb2->tstamp = tstamp;
err = output(net, sk, data, skb2);
if (err)
goto blackhole;
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, stru
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, stru
ip_fraglist_prepare(skb, &iter);
}
+ skb->tstamp = tstamp;
err = output(net, sk, skb);
if (!err)
@@ -901,6 +903,7 @@ slow_path:
/*
* Put this fragment into the sending queue.
*/
+ skb2->tstamp = tstamp;
err = output(net, sk, skb2);
if (err)
goto fail;
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct
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
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;
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, str
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, str
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;
