[PATCH net-next v10 3/6] net: add a generation counter for dev->mc changes

[Yuyang Huang]

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 mc_dev pointer, set for dev->mc only, and bump
the counter of dev_net(mc_dev) from the count helpers. 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@xxxxxxxxx>
---
 include/linux/netdevice.h   |  3 +++
 include/net/net_namespace.h |  1 +
 net/core/dev_addr_lists.c   | 15 +++++++++++++++
 3 files changed, 19 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3d9e3a70ca5c9..6c837ea34748e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -259,6 +259,9 @@ struct netdev_hw_addr_list {
 
 	/* Auxiliary tree for faster lookup on addition and deletion */
 	struct rb_root		tree;
+
+	/* Set for dev->mc only, the device the list belongs to */
+	struct net_device	*mc_dev;
 };
 
 #define netdev_hw_addr_list_count(l) ((l)->_count)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 46b4c67e2966f..c29a22ca178fa 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;	/* dev->mc membership changes */
 	u32			ifindex;
 
 	spinlock_t		nsid_lock;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index d615192d1c3b1..3ab053cbf8b99 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -16,9 +16,19 @@
 
 #include "dev.h"
 
+/* RTM_GETMULTICAST dumps use the netns generation counter to detect
+ * changes of dev->mc between dump rounds.
+ */
+static void __hw_addr_changed(struct netdev_hw_addr_list *list)
+{
+	if (list->mc_dev)
+		atomic_inc(&dev_net(list->mc_dev)->dev_mc_genid);
+}
+
 static void __hw_addr_count_add(struct netdev_hw_addr_list *list, int value)
 {
 	list->_count += value;
+	__hw_addr_changed(list);
 }
 
 static void __hw_addr_count_inc(struct netdev_hw_addr_list *list)
@@ -33,7 +43,10 @@ static void __hw_addr_count_dec(struct netdev_hw_addr_list *list)
 
 static void __hw_addr_count_reset(struct netdev_hw_addr_list *list)
 {
+	if (!list->_count)
+		return;
 	list->_count = 0;
+	__hw_addr_changed(list);
 }
 
 /*
@@ -521,6 +534,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list)
 	INIT_LIST_HEAD(&list->list);
 	list->_count = 0;
 	list->tree = RB_ROOT;
+	list->mc_dev = NULL;
 }
 EXPORT_SYMBOL(__hw_addr_init);
 
@@ -1197,6 +1211,7 @@ EXPORT_SYMBOL(dev_mc_flush);
 void dev_mc_init(struct net_device *dev)
 {
 	__hw_addr_init(&dev->mc);
+	dev->mc.mc_dev = dev;
 }
 EXPORT_SYMBOL(dev_mc_init);
 
-- 
2.43.0