path: root/target/linux/generic/backport-5.10/613-v5.15-02-netfilter-conntrack-remove-offload_pickup-sysctl-aga.patch

From 4592ee7f525c4683ec9e290381601fdee50ae110 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 4 Aug 2021 15:02:15 +0200
Subject: [PATCH] netfilter: conntrack: remove offload_pickup sysctl again

These two sysctls were added because the hardcoded defaults (2 minutes,
tcp, 30 seconds, udp) turned out to be too low for some setups.

They appeared in 5.14-rc1 so it should be fine to remove it again.

Marcelo convinced me that there should be no difference between a flow
that was offloaded vs. a flow that was not wrt. timeout handling.
Thus the default is changed to those for TCP established and UDP stream,
5 days and 120 seconds, respectively.

Marcelo also suggested to account for the timeout value used for the
offloading, this avoids increase beyond the value in the conntrack-sysctl
and will also instantly expire the conntrack entry with altered sysctls.

Example:
   nf_conntrack_udp_timeout_stream=60
   nf_flowtable_udp_timeout=60

This will remove offloaded udp flows after one minute, rather than two.

An earlier version of this patch also cleared the ASSURED bit to
allow nf_conntrack to evict the entry via early_drop (i.e., table full).
However, it looks like we can safely assume that connection timed out
via HW is still in established state, so this isn't needed.

Quoting Oz:
 [..] the hardware sends all packets with a set FIN flags to sw.
 [..] Connections that are aged in hardware are expected to be in the
 established state.

In case it turns out that back-to-sw-path transition can occur for
'dodgy' connections too (e.g., one side disappeared while software-path
would have been in RETRANS timeout), we can adjust this later.

Cc: Oz Shlomo <ozsh@nvidia.com>
Cc: Paul Blakey <paulb@nvidia.com>
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 Documentation/networking/nf_conntrack-sysctl.rst | 10 ----------
 include/net/netns/conntrack.h                    |  2 --
 net/netfilter/nf_conntrack_proto_tcp.c           |  1 -
 net/netfilter/nf_conntrack_proto_udp.c           |  1 -
 net/netfilter/nf_conntrack_standalone.c          | 16 ----------------
 net/netfilter/nf_flow_table_core.c               | 11 ++++++++---
 6 files changed, 8 insertions(+), 33 deletions(-)

--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -29,7 +29,6 @@ struct nf_tcp_net {
 	int tcp_max_retrans;
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	unsigned int offload_timeout;
-	unsigned int offload_pickup;
 #endif
 };
 
@@ -43,7 +42,6 @@ struct nf_udp_net {
 	unsigned int timeouts[UDP_CT_MAX];
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	unsigned int offload_timeout;
-	unsigned int offload_pickup;
 #endif
 };
 
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1460,7 +1460,6 @@ void nf_conntrack_tcp_init_net(struct ne
 
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	tn->offload_timeout = 30 * HZ;
-	tn->offload_pickup = 120 * HZ;
 #endif
 }
 
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -276,7 +276,6 @@ void nf_conntrack_udp_init_net(struct ne
 
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	un->offload_timeout = 30 * HZ;
-	un->offload_pickup = 30 * HZ;
 #endif
 }
 
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -569,7 +569,6 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK,
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP,
 #endif
 	NF_SYSCTL_CT_PROTO_TCP_LOOSE,
 	NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
@@ -578,7 +577,6 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP,
 #endif
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6,
@@ -772,12 +770,6 @@ static struct ctl_table nf_ct_sysctl_tab
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = {
-		.procname	= "nf_flowtable_tcp_pickup",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
 #endif
 	[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
 		.procname	= "nf_conntrack_tcp_loose",
@@ -820,12 +812,6 @@ static struct ctl_table nf_ct_sysctl_tab
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = {
-		.procname	= "nf_flowtable_udp_pickup",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
 #endif
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = {
 		.procname	= "nf_conntrack_icmp_timeout",
@@ -999,7 +985,6 @@ static void nf_conntrack_standalone_init
 
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout;
-	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup;
 #endif
 
 }
@@ -1090,7 +1075,6 @@ static int nf_conntrack_standalone_init_
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED];
 #if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout;
-	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup;
 #endif
 
 	nf_conntrack_standalone_init_tcp_sysctl(net, table);
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -182,20 +182,25 @@ static void flow_offload_fixup_ct_timeou
 {
 	struct net *net = nf_ct_net(ct);
 	int l4num = nf_ct_protonum(ct);
-	unsigned int timeout;
+	s32 timeout;
 
 	if (l4num == IPPROTO_TCP) {
 		struct nf_tcp_net *tn = nf_tcp_pernet(net);
 
-		timeout = tn->offload_pickup;
+		timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED];
+		timeout -= tn->offload_timeout;
 	} else if (l4num == IPPROTO_UDP) {
 		struct nf_udp_net *tn = nf_udp_pernet(net);
 
-		timeout = tn->offload_pickup;
+		timeout = tn->timeouts[UDP_CT_REPLIED];
+		timeout -= tn->offload_timeout;
 	} else {
 		return;
 	}
 
+	if (timeout < 0)
+		timeout = 0;
+
 	if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout)
 		WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
 }