[PATCH nf] Revert "netfilter: flowtable: Remove redundant hw refresh bit"

[Aleksander Jan Bajkowski]

This reverts commit c07531c01d8284aedaf95708ea90e76d11af0e21.

The previously mentioned commit significantly reduces NAT performance
in OpenWRT. Another user reports a high ping issue. The results of
IPv4 NAT benchmark on BT Home Hub 5A (with software flow offloading):
* 5.4.124             515 Mb/s
* 5.10.41             570 Mb/s
* 5.10.42             250 Mb/s
* 5.10.42 + revert    580 Mb/s

Reverting this commit fixes this issue.

Fixes: c07531c01d8284aedaf95708ea90e76d11af0e21 ("netfilter: flowtable: Remove redundant hw refresh bit")
Signed-off-by: Aleksander Jan Bajkowski <olek2@xxxxx>
---
 include/net/netfilter/nf_flow_table.h | 1 +
 net/netfilter/nf_flow_table_core.c    | 3 ++-
 net/netfilter/nf_flow_table_offload.c | 7 +++----
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 48ef7460ff30..51d8eb99764d 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -157,6 +157,7 @@ enum nf_flow_flags {
 	NF_FLOW_HW,
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
+	NF_FLOW_HW_REFRESH,
 	NF_FLOW_HW_PENDING,
 };
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 1d02650dd715..39c02d1aeedf 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -306,7 +306,8 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 {
 	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
 
-	if (likely(!nf_flowtable_hw_offload(flow_table)))
+	if (likely(!nf_flowtable_hw_offload(flow_table) ||
+		   !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags)))
 		return;
 
 	nf_flow_offload_add(flow_table, flow);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 528b2f172684..2af7bdb38407 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -902,11 +902,10 @@ static void flow_offload_work_add(struct flow_offload_work *offload)
 
 	err = flow_offload_rule_add(offload, flow_rule);
 	if (err < 0)
-		goto out;
-
-	set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
+		set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags);
+	else
+		set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
 
-out:
 	nf_flow_offload_destroy(flow_rule);
 }
 
-- 
2.30.2