@@ -626,6 +626,7 @@ struct netdev_queue {
struct Qdisc __rcu *qdisc_sleeping;
#ifdef CONFIG_SYSFS
struct kobject kobj;
+ const struct attribute_group **groups;
#endif
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
int numa_node;
@@ -15,6 +15,7 @@ struct netdev_rx_queue {
struct rps_dev_flow_table __rcu *rps_flow_table;
#endif
struct kobject kobj;
+ const struct attribute_group **groups;
struct net_device *dev;
netdevice_tracker dev_tracker;
@@ -1138,7 +1138,6 @@ static void rx_queue_get_ownership(const struct kobject *kobj,
static const struct kobj_type rx_queue_ktype = {
.sysfs_ops = &rx_queue_sysfs_ops,
.release = rx_queue_release,
- .default_groups = rx_queue_default_groups,
.namespace = rx_queue_namespace,
.get_ownership = rx_queue_get_ownership,
};
@@ -1172,10 +1171,15 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
if (error)
goto err;
+ queue->groups = rx_queue_default_groups;
+ error = sysfs_create_groups(kobj, queue->groups);
+ if (error)
+ goto err;
+
if (dev->sysfs_rx_queue_group) {
error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
if (error)
- goto err;
+ goto err_default_groups;
}
error = rx_queue_default_mask(dev, queue);
@@ -1186,6 +1190,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
return error;
+err_default_groups:
+ sysfs_remove_groups(kobj, queue->groups);
err:
kobject_put(kobj);
return error;
@@ -1230,12 +1236,14 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
}
while (--i >= new_num) {
- struct kobject *kobj = &dev->_rx[i].kobj;
+ struct netdev_rx_queue *queue = &dev->_rx[i];
+ struct kobject *kobj = &queue->kobj;
if (!refcount_read(&dev_net(dev)->ns.count))
kobj->uevent_suppress = 1;
if (dev->sysfs_rx_queue_group)
sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
+ sysfs_remove_groups(kobj, queue->groups);
kobject_put(kobj);
}
@@ -1757,7 +1765,6 @@ static void netdev_queue_get_ownership(const struct kobject *kobj,
static const struct kobj_type netdev_queue_ktype = {
.sysfs_ops = &netdev_queue_sysfs_ops,
.release = netdev_queue_release,
- .default_groups = netdev_queue_default_groups,
.namespace = netdev_queue_namespace,
.get_ownership = netdev_queue_get_ownership,
};
@@ -1779,15 +1786,24 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
if (error)
goto err;
+ queue->groups = netdev_queue_default_groups;
+ error = sysfs_create_groups(kobj, queue->groups);
+ if (error)
+ goto err;
+
#ifdef CONFIG_BQL
error = sysfs_create_group(kobj, &dql_group);
if (error)
- goto err;
+ goto err_default_groups;
#endif
kobject_uevent(kobj, KOBJ_ADD);
return 0;
+#ifdef CONFIG_BQL
+err_default_groups:
+ sysfs_remove_groups(kobj, queue->groups);
+#endif
err:
kobject_put(kobj);
return error;
@@ -1841,6 +1857,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
#ifdef CONFIG_BQL
sysfs_remove_group(&queue->kobj, &dql_group);
#endif
+ sysfs_remove_groups(&queue->kobj, queue->groups);
kobject_put(&queue->kobj);
}
Rx/tx queues embed their own kobject for registering their per-queue sysfs files. The issue is they're using the kobject default groups for this and entirely rely on the kobject refcounting for releasing their sysfs paths. In order to remove rtnl_trylock calls we need sysfs files not to rely on their associated kobject refcounting for their release. Thus we here move queues sysfs files from the kobject default groups to their own groups which can be removed separately. Signed-off-by: Antoine Tenart <atenart@kernel.org> --- include/linux/netdevice.h | 1 + include/net/netdev_rx_queue.h | 1 + net/core/net-sysfs.c | 27 ++++++++++++++++++++++----- 3 files changed, 24 insertions(+), 5 deletions(-)