[Devel] [PATCH RHEL9 COMMIT] neighbour: make proxy_queue.qlen limit per-device

[Konstantin Khorenko]

The commit is pushed to "branch-rh9-5.14.0-70.13.1.vz9.16.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh9-5.14.0-70.13.1.vz9.16.7
------>
commit e721e0d21cdd0c5b9b47dde78770a5c5710ca5c3
Author: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
Date:   Thu Aug 11 14:59:27 2022 +0300

    neighbour: make proxy_queue.qlen limit per-device
    
    Right now we have a neigh_param PROXY_QLEN which specifies maximum length
    of neigh_table->proxy_queue. But in fact, this limitation doesn't work well
    because check condition looks like:
    tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)
    
    The problem is that p (struct neigh_parms) is a per-device thing,
    but tbl (struct neigh_table) is a system-wide global thing.
    
    It seems reasonable to make proxy_queue limit per-device based.
    
    https://jira.sw.ru/browse/PSBM-140896
    
    Cc: "David S. Miller" <davem at davemloft.net>
    Cc: Eric Dumazet <edumazet at google.com>
    Cc: Jakub Kicinski <kuba at kernel.org>
    Cc: Paolo Abeni <pabeni at redhat.com>
    Cc: Daniel Borkmann <daniel at iogearbox.net>
    Cc: David Ahern <dsahern at kernel.org>
    Cc: Yajun Deng <yajun.deng at linux.dev>
    Cc: Roopa Prabhu <roopa at nvidia.com>
    Cc: Christian Brauner <brauner at kernel.org>
    Cc: netdev at vger.kernel.org
    Cc: linux-kernel at vger.kernel.org
    Cc: Alexey Kuznetsov <kuznet at ms2.inr.ac.ru>
    Cc: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
    Cc: Konstantin Khorenko <khorenko at virtuozzo.com>
    Cc: kernel at openvz.org
    Cc: devel at openvz.org
    Suggested-by: Denis V. Lunev <den at openvz.org>
    Signed-off-by: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
    
    Reviewed-by: Denis V. Lunev <den at openvz.org>
---
 include/net/neighbour.h |  1 +
 net/core/neighbour.c    | 25 ++++++++++++++++++++++---
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 22ced1381ede..8c8b8605bf98 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -81,6 +81,7 @@ struct neigh_parms {
 	struct rcu_head rcu_head;
 
 	int	reachable_time;
+	int	qlen;
 	int	data[NEIGH_VAR_DATA_MAX];
 	DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX);
 };
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f33e01a0ed5e..4f7edf22c2fd 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -292,9 +292,18 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 	skb = skb_peek(list);
 	while (skb != NULL) {
 		struct sk_buff *skb_next = skb_peek_next(skb, list);
-		if (net == NULL || net_eq(dev_net(skb->dev), net)) {
+		struct net_device *dev = skb->dev;
+		if (net == NULL || net_eq(dev_net(dev), net)) {
+			struct in_device *in_dev;
+
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
 			__skb_unlink(skb, list);
-			dev_put(skb->dev);
+
+			dev_put(dev);
 			kfree_skb(skb);
 		}
 		skb = skb_next;
@@ -1589,8 +1598,15 @@ static void neigh_proxy_process(struct timer_list *t)
 
 		if (tdif <= 0) {
 			struct net_device *dev = skb->dev;
+			struct in_device *in_dev;
 
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
 			__skb_unlink(skb, &tbl->proxy_queue);
+
 			if (tbl->proxy_redo && netif_running(dev)) {
 				rcu_read_lock();
 				tbl->proxy_redo(skb);
@@ -1615,7 +1631,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	unsigned long sched_next = jiffies +
 			prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
-	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
+	if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) {
 		kfree_skb(skb);
 		return;
 	}
@@ -1631,6 +1647,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	skb_dst_drop(skb);
 	dev_hold(skb->dev);
 	__skb_queue_tail(&tbl->proxy_queue, skb);
+	p->qlen++;
 	mod_timer(&tbl->proxy_timer, sched_next);
 	spin_unlock(&tbl->proxy_queue.lock);
 }
@@ -1663,6 +1680,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		refcount_set(&p->refcnt, 1);
 		p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
+		p->qlen = 0;
 		dev_hold(dev);
 		p->dev = dev;
 		write_pnet(&p->net, net);
@@ -1726,6 +1744,7 @@ void neigh_table_init(int index, struct neigh_table *tbl)
 	refcount_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
 			  neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));
+	tbl->parms.qlen = 0;
 
 	tbl->stats = alloc_percpu(struct neigh_statistics);
 	if (!tbl->stats)