[v4,net-next,4/8] net: Postpone skb_clear_delivery_time() until knowing the skb is delivered locally

Commit Message

Martin KaFai Lau Feb. 11, 2022, 7:12 a.m. UTC

This patch postpones the delivery_time clearing until the stack knows
the skb is being delivered locally.  That will allow other kernel
forwarding path (e.g. ip[6]_forward) to keep the delivery_time also.

An earlier attempt was to do skb_clear_delivery_time() in
ip_local_deliver() and ip6_input().  The discussion [0] requested to
move it one step later into ip_local_deliver_finish()
and ip6_input_finish() so that the delivery_time can be kept
for the ip_vs forwarding path also.  To do that, this patch also
needs to take care of the (rcv) timestamp usecase in ip_is_fragment().
It needs to expect delivery_time in the skb->tstamp, so it needs to
save the mono_delivery_time bit in inet_frag_queue such that the
delivery_time (if any) can be restored in the final defragmented skb.

The ipv6 defrag is done in ip6_protocol_deliver_rcu() when figuring
out how to handle nexthdr and IPPROTO_FRAGMENT (44) is one of the
ipv6 extension header.  ip6_protocol_deliver_rcu() is after
ip6_input_finish() where the skb_clear_delivery_time() has
already been done, so change is not needed.

[0]: https://lore.kernel.org/netdev/[e-mail]/

Signed-off-by: Martin KaFai Lau <[e-mail]>
---
 include/net/inet_frag.h  | 1 +
 net/core/dev.c           | 1 -
 net/ipv4/inet_fragment.c | 1 +
 net/ipv4/ip_fragment.c   | 1 +
 net/ipv4/ip_input.c      | 1 +
 net/ipv6/ip6_input.c     | 1 +
 6 files changed, 5 insertions(+), 1 deletion(-)

Patch

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 63540be0fc34..c0e517f31d82 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -90,6 +90,7 @@  struct inet_frag_queue {
 	ktime_t			stamp;
 	int			len;
 	int			meat;
+	bool			mono_delivery_time;
 	__u8			flags;
 	u16			max_size;
 	struct fqdir		*fqdir;
diff --git a/net/core/dev.c b/net/core/dev.c
index f41707ab2fb9..041cef7473fd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5222,7 +5222,6 @@  static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 			goto out;
 	}
 #endif
-	skb_clear_delivery_time(skb);
 	skb_reset_redirect(skb);
 skip_classify:
 	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 341096807100..63948f6aeca0 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -572,6 +572,7 @@  void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 	skb_mark_not_on_list(head);
 	head->prev = NULL;
 	head->tstamp = q->stamp;
+	head->mono_delivery_time = q->mono_delivery_time;
 }
 EXPORT_SYMBOL(inet_frag_reasm_finish);
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index fad803d2d711..fb153569889e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -349,6 +349,7 @@  static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		qp->iif = dev->ifindex;
 
 	qp->q.stamp = skb->tstamp;
+	qp->q.mono_delivery_time = skb->mono_delivery_time;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
 	add_frag_mem_limit(qp->q.fqdir, skb->truesize);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d94f9f7e60c3..95f7bb052784 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -226,6 +226,7 @@  void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
 
 static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb_clear_delivery_time(skb);
 	__skb_pull(skb, skb_network_header_len(skb));
 
 	rcu_read_lock();
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index d4b1e2c5aa76..5b5ea35635f9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -459,6 +459,7 @@  void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
 
 static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb_clear_delivery_time(skb);
 	rcu_read_lock();
 	ip6_protocol_deliver_rcu(net, skb, 0, false);
 	rcu_read_unlock();