[SRU][F:linux-bluefield][PATCH 1/2] netfilter: flowtable: separate replace, destroy and stats to different workqueues

[Roi Dayan]

From: Oz Shlomo <ozsh at nvidia.com>

BugLink: https://bugs.launchpad.net/bugs/1922678

Currently the flow table offload replace, destroy and stats work items are
executed on a single workqueue. As such, DESTROY and STATS commands may
be backloged after a burst of REPLACE work items. This scenario can bloat
up memory and may cause active connections to age.

Instatiate add, del and stats workqueues to avoid backlogs of non-dependent
actions. Provide sysfs control over the workqueue attributes, allowing
userspace applications to control the workqueue cpumask.

Signed-off-by: Oz Shlomo <ozsh at nvidia.com>
Reviewed-by: Paul Blakey <paulb at nvidia.com>
Signed-off-by: Pablo Neira Ayuso <pablo at netfilter.org>
(backported from commit 2ed37183abb70233146dc82f19cb1cbceed2b505)
Signed-off-by: Roi Dayan <roid at nvidia.com>
---
 net/netfilter/nf_flow_table_offload.c | 44 ++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index db1797e398ae..685ff5b906e4 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -12,7 +12,9 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 
-static struct workqueue_struct *nf_flow_offload_wq;
+static struct workqueue_struct *nf_flow_offload_add_wq;
+static struct workqueue_struct *nf_flow_offload_del_wq;
+static struct workqueue_struct *nf_flow_offload_stats_wq;
 
 struct flow_offload_work {
 	struct list_head	list;
@@ -818,7 +820,12 @@ static void flow_offload_work_handler(struct work_struct *work)
 
 static void flow_offload_queue_work(struct flow_offload_work *offload)
 {
-	queue_work(nf_flow_offload_wq, &offload->work);
+	if (offload->cmd == FLOW_CLS_REPLACE)
+		queue_work(nf_flow_offload_add_wq, &offload->work);
+	else if (offload->cmd == FLOW_CLS_DESTROY)
+		queue_work(nf_flow_offload_del_wq, &offload->work);
+	else
+		queue_work(nf_flow_offload_stats_wq, &offload->work);
 }
 
 static struct flow_offload_work *
@@ -890,8 +897,11 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
 {
-	if (nf_flowtable_hw_offload(flowtable))
-		flush_workqueue(nf_flow_offload_wq);
+	if (nf_flowtable_hw_offload(flowtable)) {
+		flush_workqueue(nf_flow_offload_add_wq);
+		flush_workqueue(nf_flow_offload_del_wq);
+		flush_workqueue(nf_flow_offload_stats_wq);
+	}
 }
 
 static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
@@ -1059,18 +1069,36 @@ static struct flow_indr_block_entry block_ing_entry = {
 
 int nf_flow_table_offload_init(void)
 {
-	nf_flow_offload_wq  = alloc_workqueue("nf_flow_table_offload",
-					      WQ_UNBOUND, 0);
-	if (!nf_flow_offload_wq)
+	nf_flow_offload_add_wq  = alloc_workqueue("nf_ft_offload_add",
+						  WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_add_wq)
 		return -ENOMEM;
 
+	nf_flow_offload_del_wq  = alloc_workqueue("nf_ft_offload_del",
+						  WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_del_wq)
+		goto err_del_wq;
+
+	nf_flow_offload_stats_wq  = alloc_workqueue("nf_ft_offload_stats",
+						    WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!nf_flow_offload_stats_wq)
+		goto err_stats_wq;
+
 	flow_indr_add_block_cb(&block_ing_entry);
 
 	return 0;
+
+err_stats_wq:
+	destroy_workqueue(nf_flow_offload_del_wq);
+err_del_wq:
+	destroy_workqueue(nf_flow_offload_add_wq);
+	return -ENOMEM;
 }
 
 void nf_flow_table_offload_exit(void)
 {
 	flow_indr_del_block_cb(&block_ing_entry);
-	destroy_workqueue(nf_flow_offload_wq);
+	destroy_workqueue(nf_flow_offload_add_wq);
+	destroy_workqueue(nf_flow_offload_del_wq);
+	destroy_workqueue(nf_flow_offload_stats_wq);
 }
-- 
2.26.2