[PATCH net-next v8 2/5] net: add a generation counter for dev->mc changes

[Yuyang Huang <sigefriedhyy@gmail.com>]

A multi-part RTM_GETMULTICAST dump of dev->mc resumes by position, so
entries added or removed between two dump rounds can be skipped or
repeated. The IPv4 and IPv6 dumps report that with NLM_F_DUMP_INTR by
stamping cb->seq from a per netns generation counter combined with
dev_base_seq, see inet_base_seq().

Add the equivalent for the device multicast lists: a per netns counter
bumped whenever an entry is added to or removed from any dev->mc. The
list helpers do not know which device a list belongs to, so give
netdev_hw_addr_list an owner, set for the lists of a device and NULL
for snapshots and other standalone lists, and change list->count
through helpers that bump the counter of dev_net(owner) when the list
is dev->mc. That covers the dev_mc_* helpers, both lists of a sync,
the hardware sync helpers drivers call from their rx mode callbacks or
their own workers and the reconciliation after an asynchronous rx mode
update. It is atomic since the writers only hold the address lock of
their own device.

Used by the following patch for the AF_PACKET multicast dump.

Signed-off-by: Yuyang Huang <sigefriedhyy@gmail.com>
---
 include/linux/netdevice.h   |  5 ++++
 include/net/net_namespace.h |  1 +
 net/core/dev_addr_lists.c   | 52 +++++++++++++++++++++++++++++++------
 3 files changed, 50 insertions(+), 8 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d037faff7c44..69d1cde0a38a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -256,6 +256,11 @@ struct netdev_hw_addr_list {
 
 	/* Auxiliary tree for faster lookup on addition and deletion */
 	struct rb_root		tree;
+
+	/* The device a list belongs to, NULL for snapshots and other
+	 * standalone lists
+	 */
+	struct net_device	*owner;
 };
 
 #define netdev_hw_addr_list_count(l) ((l)->count)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 46b4c67e2966..d8c681ab5c74 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -71,6 +71,7 @@ struct net {
 	spinlock_t		rules_mod_lock;
 
 	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
+	atomic_t		dev_mc_genid;	/* bumped on dev->mc changes */
 	u32			ifindex;
 
 	spinlock_t		nsid_lock;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 08528ca0a8b3..c941c3ec1007 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -16,6 +16,37 @@
 
 #include "dev.h"
 
+/* Only dev->mc is tracked, RTM_GETMULTICAST dumps use the netns generation
+ * counter to detect changes between dump rounds.
+ */
+static void __hw_addr_changed(struct netdev_hw_addr_list *list)
+{
+	struct net_device *dev = list->owner;
+
+	if (dev && list == &dev->mc)
+		atomic_inc(&dev_net(dev)->dev_mc_genid);
+}
+
+static void __hw_addr_count_inc(struct netdev_hw_addr_list *list)
+{
+	list->count++;
+	__hw_addr_changed(list);
+}
+
+static void __hw_addr_count_dec(struct netdev_hw_addr_list *list)
+{
+	list->count--;
+	__hw_addr_changed(list);
+}
+
+static void __hw_addr_count_reset(struct netdev_hw_addr_list *list)
+{
+	if (!list->count)
+		return;
+	list->count = 0;
+	__hw_addr_changed(list);
+}
+
 /*
  * General list handling functions
  */
@@ -125,7 +156,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
 	rb_insert_color(&ha->node, &list->tree);
 
 	list_add_tail_rcu(&ha->list, &list->list);
-	list->count++;
+	__hw_addr_count_inc(list);
 
 	return 0;
 }
@@ -161,7 +192,7 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list,
 
 	list_del_rcu(&ha->list);
 	kfree_rcu(ha, rcu_head);
-	list->count--;
+	__hw_addr_count_dec(list);
 	return 0;
 }
 
@@ -492,7 +523,7 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list)
 		list_del_rcu(&ha->list);
 		kfree_rcu(ha, rcu_head);
 	}
-	list->count = 0;
+	__hw_addr_count_reset(list);
 }
 EXPORT_SYMBOL_IF_KUNIT(__hw_addr_flush);
 
@@ -501,6 +532,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list)
 	INIT_LIST_HEAD(&list->list);
 	list->count = 0;
 	list->tree = RB_ROOT;
+	list->owner = NULL;
 }
 EXPORT_SYMBOL(__hw_addr_init);
 
@@ -536,7 +568,7 @@ int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap,
 			entry = list_first_entry(&cache->list,
 						 struct netdev_hw_addr, list);
 			list_del(&entry->list);
-			cache->count--;
+			__hw_addr_count_dec(cache);
 			memcpy(entry->addr, ha->addr, addr_len);
 			entry->type = ha->type;
 			entry->global_use = false;
@@ -554,7 +586,7 @@ int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap,
 
 		list_add_tail(&entry->list, &snap->list);
 		__hw_addr_insert(snap, entry, addr_len);
-		snap->count++;
+		__hw_addr_count_inc(snap);
 	}
 
 	return 0;
@@ -604,14 +636,14 @@ void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list,
 			if (delta > 0) {
 				rb_erase(&ref_ha->node, &ref->tree);
 				list_del(&ref_ha->list);
-				ref->count--;
+				__hw_addr_count_dec(ref);
 				ref_ha->sync_cnt = delta;
 				ref_ha->refcount = delta;
 				list_add_tail_rcu(&ref_ha->list,
 						  &real_list->list);
 				__hw_addr_insert(real_list, ref_ha,
 						 addr_len);
-				real_list->count++;
+				__hw_addr_count_inc(real_list);
 			}
 			continue;
 		}
@@ -622,7 +654,7 @@ void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list,
 			rb_erase(&real_ha->node, &real_list->tree);
 			list_del_rcu(&real_ha->list);
 			kfree_rcu(real_ha, rcu_head);
-			real_list->count--;
+			__hw_addr_count_dec(real_list);
 		}
 	}
 
@@ -685,6 +717,7 @@ int dev_addr_init(struct net_device *dev)
 	/* rtnl_mutex must be held here */
 
 	__hw_addr_init(&dev->dev_addrs);
+	dev->dev_addrs.owner = dev;
 	memset(addr, 0, sizeof(addr));
 	err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr),
 			    NETDEV_HW_ADDR_T_LAN);
@@ -962,6 +995,7 @@ EXPORT_SYMBOL(dev_uc_flush);
 void dev_uc_init(struct net_device *dev)
 {
 	__hw_addr_init(&dev->uc);
+	dev->uc.owner = dev;
 }
 EXPORT_SYMBOL(dev_uc_init);
 
@@ -1177,6 +1211,7 @@ EXPORT_SYMBOL(dev_mc_flush);
 void dev_mc_init(struct net_device *dev)
 {
 	__hw_addr_init(&dev->mc);
+	dev->mc.owner = dev;
 }
 EXPORT_SYMBOL(dev_mc_init);
 
@@ -1348,6 +1383,7 @@ static void netif_rx_mode_retry(struct timer_list *t)
 void netif_rx_mode_init(struct net_device *dev)
 {
 	__hw_addr_init(&dev->rx_mode_addr_cache);
+	dev->rx_mode_addr_cache.owner = dev;
 	timer_setup(&dev->rx_mode_retry_timer, netif_rx_mode_retry, 0);
 }
 
-- 
2.43.0