From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>, <netdev@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
David Miller <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, <kernel-team@fb.com>,
Willem de Bruijn <willemb@google.com>
Subject: [PATCH v4 net-next 2/8] net: Add skb_clear_tstamp() to keep the mono delivery_time
Date: Thu, 10 Feb 2022 23:12:44 -0800 [thread overview]
Message-ID: <20220211071244.886294-1-kafai@fb.com> (raw)
In-Reply-To: <20220211071232.885225-1-kafai@fb.com>
Right now, skb->tstamp is reset to 0 whenever the skb is forwarded.
If skb->tstamp has the mono delivery_time, clearing it can hurt
the performance when it finally transmits out to fq@phy-dev.
The earlier patch added a skb->mono_delivery_time bit to
flag the skb->tstamp carrying the mono delivery_time.
This patch adds skb_clear_tstamp() helper which keeps
the mono delivery_time and clear everything else.
The delivery_time clearing is postponed until the stack knows the
skb will be delivered locally. It will be done in a later patch.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
drivers/net/loopback.c | 2 +-
include/linux/skbuff.h | 10 +++++++++-
net/bridge/br_forward.c | 2 +-
net/core/filter.c | 6 +++---
net/core/skbuff.c | 2 +-
net/ipv4/ip_forward.c | 2 +-
net/ipv6/ip6_output.c | 2 +-
net/netfilter/ipvs/ip_vs_xmit.c | 6 +++---
net/netfilter/nf_dup_netdev.c | 2 +-
net/netfilter/nf_flow_table_ip.c | 4 ++--
net/netfilter/nft_fwd_netdev.c | 2 +-
net/openvswitch/vport.c | 2 +-
net/xfrm/xfrm_interface.c | 2 +-
13 files changed, 26 insertions(+), 18 deletions(-)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index ed0edf5884ef..70a38fa09299 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -74,7 +74,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
skb_tx_timestamp(skb);
/* do not fool net_timestamp_check() with various clock bases */
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
skb_orphan(skb);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 32c793de3801..07e618f8b41a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3938,6 +3938,14 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
skb->mono_delivery_time = 0;
}
+static inline void skb_clear_tstamp(struct sk_buff *skb)
+{
+ if (skb->mono_delivery_time)
+ return;
+
+ skb->tstamp = 0;
+}
+
static inline u8 skb_metadata_len(const struct sk_buff *skb)
{
return skb_shinfo(skb)->meta_len;
@@ -4794,7 +4802,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress)
#ifdef CONFIG_NET_REDIRECT
skb->from_ingress = from_ingress;
if (skb->from_ingress)
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
#endif
}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index ec646656dbf1..02bb620d3b8d 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -62,7 +62,7 @@ EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
net, sk, skb, NULL, skb->dev,
br_dev_queue_push_xmit);
diff --git a/net/core/filter.c b/net/core/filter.c
index f497ca7a16d2..a2d712be4985 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2107,7 +2107,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
}
skb->dev = dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
dev_xmit_recursion_inc();
ret = dev_queue_xmit(skb);
@@ -2176,7 +2176,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
}
skb->dev = dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
skb = skb_expand_head(skb, hh_len);
@@ -2274,7 +2274,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
}
skb->dev = dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
skb = skb_expand_head(skb, hh_len);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0118f0afaa4f..3e3da8fdf8f5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5350,7 +5350,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
ipvs_reset(skb);
skb->mark = 0;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 00ec819f949b..92ba3350274b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -79,7 +79,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
if (unlikely(opt->optlen))
ip_forward_options(skb);
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
return dst_output(net, sk, skb);
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 55665f3f7a77..9fc1b08cf622 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -440,7 +440,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
}
#endif
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
return dst_output(net, sk, skb);
}
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index d2e5a8f644b8..029171379884 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -610,7 +610,7 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
nf_reset_ct(skb);
skb_forward_csum(skb);
if (skb->dev)
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
}
return ret;
}
@@ -652,7 +652,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
if (!local) {
skb_forward_csum(skb);
if (skb->dev)
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output);
} else
@@ -674,7 +674,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
ip_vs_drop_early_demux_sk(skb);
skb_forward_csum(skb);
if (skb->dev)
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output);
} else
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index a579e59ee5c5..7873bd1389c3 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -19,7 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev)
skb_push(skb, skb->mac_len);
skb->dev = dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
dev_queue_xmit(skb);
}
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 889cf88d3dba..f1d387129f02 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -376,7 +376,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
nf_flow_nat_ip(flow, skb, thoff, dir, iph);
ip_decrease_ttl(iph);
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
if (flow_table->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
@@ -611,7 +611,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
nf_flow_nat_ipv6(flow, skb, dir, ip6h);
ip6h->hop_limit--;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
if (flow_table->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index fa9301ca6033..4b2b0946c0b6 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -140,7 +140,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
return;
skb->dev = dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
neigh_xmit(neigh_table, dev, addr, skb);
out:
regs->verdict.code = verdict;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index cf2ce5812489..82a74f998966 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -507,7 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
}
skb->dev = vport->dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
vport->ops->send(skb);
return;
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 57448fc519fc..4991e99ced9a 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -190,7 +190,7 @@ static void xfrmi_dev_uninit(struct net_device *dev)
static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
{
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
skb->pkt_type = PACKET_HOST;
skb->skb_iif = 0;
skb->ignore_df = 0;
--
2.30.2
next prev parent reply other threads:[~2022-02-11 7:12 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-11 7:12 [PATCH v4 net-next 0/8] Preserve mono delivery time (EDT) in skb->tstamp Martin KaFai Lau
2022-02-11 7:12 ` [PATCH v4 net-next 1/8] net: Add skb->mono_delivery_time to distinguish mono delivery_time from (rcv) timestamp Martin KaFai Lau
2022-02-12 19:13 ` Cong Wang
2022-02-12 23:27 ` Martin KaFai Lau
2022-02-15 20:49 ` Daniel Borkmann
2022-02-16 6:11 ` Martin KaFai Lau
2022-02-11 7:12 ` Martin KaFai Lau [this message]
2022-02-11 7:12 ` [PATCH v4 net-next 3/8] net: Set skb->mono_delivery_time and clear it after sch_handle_ingress() Martin KaFai Lau
2022-02-15 21:04 ` Daniel Borkmann
2022-02-11 7:12 ` [PATCH v4 net-next 4/8] net: Postpone skb_clear_delivery_time() until knowing the skb is delivered locally Martin KaFai Lau
2022-02-11 7:13 ` [PATCH v4 net-next 5/8] bpf: Keep the (rcv) timestamp behavior for the existing tc-bpf@ingress Martin KaFai Lau
2022-02-15 23:30 ` Daniel Borkmann
2022-02-16 5:51 ` Martin KaFai Lau
2022-02-17 0:03 ` Daniel Borkmann
2022-02-17 1:50 ` Martin KaFai Lau
2022-02-17 6:52 ` Martin KaFai Lau
2022-02-11 7:13 ` [PATCH v4 net-next 6/8] bpf: Clear skb->mono_delivery_time bit if needed after running tc-bpf@egress Martin KaFai Lau
2022-02-11 7:13 ` [PATCH v4 net-next 7/8] bpf: Add __sk_buff->delivery_time_type and bpf_skb_set_delivery_time() Martin KaFai Lau
2022-02-11 7:13 ` [PATCH v4 net-next 8/8] bpf: selftests: test skb->tstamp in redirect_neigh Martin KaFai Lau
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220211071244.886294-1-kafai@fb.com \
--to=kafai@fb.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kernel-team@fb.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=willemb@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox