| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 19 May 2015 16:24:53 -0700
From: Baptiste Covolato <baptiste@...sta.com>
To: "David S. Miller" <davem@...emloft.net>, netdev@...r.kernel.org
Cc: Francesco Ruggeri <fruggeri@...sta.com>,
Eric Mowat <mowat@...sta.com>,
Adrien Schildknecht <adrien+dev@...ischi.me>
Subject: [PATCH net-next 3/3] net: Make netdev_run_todo call notifiers in parallel.
In the case of unregister_netdevice_many, a queue of devices is
deleted but the final notifications are processed serially, with the next
one waiting until the previous device has been completely destroyed. This
patch allows netdev_run_todo to send all notifications at once, reducing
the total processing time for a large list.
Signed-off-by: Baptiste Covolato <baptiste@...sta.com>
Signed-off-by: Francesco Ruggeri <fruggeri@...sta.com>
---
net/core/dev.c | 146 ++++++++++++++++++++++++++++++++-------------------------
1 file changed, 83 insertions(+), 63 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 9b0814b..00c512e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6698,105 +6698,125 @@ EXPORT_SYMBOL(netdev_refcnt_read);
void netdev_run_todo(void)
{
struct list_head list;
+ struct net_device *dev, *n;
unsigned long rebroadcast_time, warning_time;
+ LIST_HEAD(cleanup_list);
/* Snapshot list, allow later requests */
list_replace_init(&net_todo_list, &list);
__rtnl_unlock();
-
/* Wait for rcu callbacks to finish before next phase */
- if (!list_empty(&list))
- rcu_barrier();
+ if (list_empty(&list))
+ return;
- while (!list_empty(&list)) {
- int refcnt;
- struct net_device *dev
- = list_first_entry(&list, struct net_device, todo_list);
- list_del(&dev->todo_list);
+ rcu_barrier();
- rtnl_lock();
+ rtnl_lock();
+ list_for_each_entry(dev, &list, todo_list)
call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
- __rtnl_unlock();
+ __rtnl_unlock();
+ list_for_each_entry_safe(dev, n, &list, todo_list) {
if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
pr_err("network todo '%s' but state %d\n",
dev->name, dev->reg_state);
dump_stack();
+ list_del(&dev->todo_list);
continue;
}
dev->reg_state = NETREG_UNREGISTERED;
+ }
- on_each_cpu(flush_backlog, NULL, 1);
+ on_each_cpu(flush_backlog, NULL, 1);
+ list_for_each_entry(dev, &list, todo_list)
linkwatch_forget_dev(dev);
- rebroadcast_time = warning_time = jiffies;
- refcnt = netdev_refcnt_read(dev);
-
- while (refcnt != 0) {
- if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
- rtnl_lock();
-
- /* Rebroadcast unregister notification */
- call_netdevice_notifiers(NETDEV_UNREGISTER,
- dev);
-
- __rtnl_unlock();
- rcu_barrier();
- rtnl_lock();
-
- call_netdevice_notifiers(
- NETDEV_UNREGISTER_FINAL, dev);
- if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
- &dev->state)) {
- /* We must not have linkwatch events
- * pending on unregister. If this
- * happens, we simply run the queue
- * unscheduled, resulting in a noop
- * for this device.
- */
- linkwatch_run_queue();
- }
+ rebroadcast_time = warning_time = jiffies;
+again:
+ list_for_each_entry_safe(dev, n, &list, todo_list) {
+ if (netdev_refcnt_read(dev) == 0)
+ list_move(&dev->todo_list, &cleanup_list);
+ }
+
+ if (!list_empty(&cleanup_list)) {
+ list_for_each_entry(dev, &cleanup_list, todo_list) {
+ /* paranoia */
+ BUG_ON(netdev_refcnt_read(dev));
+ BUG_ON(!list_empty(&dev->ptype_all));
+ BUG_ON(!list_empty(&dev->ptype_specific));
+ WARN_ON(rcu_access_pointer(dev->ip_ptr));
+ WARN_ON(rcu_access_pointer(dev->ip6_ptr));
+ WARN_ON(dev->dn_ptr);
+
+ if (dev->destructor)
+ dev->destructor(dev);
+ }
+
+ /* Report some network devices have been unregistered */
+ rtnl_lock();
+ list_for_each_entry(dev, &cleanup_list, todo_list)
+ dev_net(dev)->dev_unreg_count--;
+ __rtnl_unlock();
+ wake_up(&netdev_unregistering_wq);
- __rtnl_unlock();
+ list_for_each_entry_safe(dev, n, &cleanup_list, todo_list) {
+ list_del(&dev->todo_list);
- rebroadcast_time = jiffies;
- }
+ /* Free network devices */
+ kobject_put(&dev->dev.kobj);
+ }
+ }
- msleep(250);
+ /* No more interface to delete */
+ if (list_empty(&list))
+ return;
- refcnt = netdev_refcnt_read(dev);
+ if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
+ rtnl_lock();
- if (time_after(jiffies, warning_time + 10 * HZ)) {
- pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
- dev->name, refcnt);
- warning_time = jiffies;
- }
+ list_for_each_entry(dev, &list, todo_list) {
+ /* Rebroadcast unregister notification */
+ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
}
- /* paranoia */
- BUG_ON(netdev_refcnt_read(dev));
- BUG_ON(!list_empty(&dev->ptype_all));
- BUG_ON(!list_empty(&dev->ptype_specific));
- WARN_ON(rcu_access_pointer(dev->ip_ptr));
- WARN_ON(rcu_access_pointer(dev->ip6_ptr));
- WARN_ON(dev->dn_ptr);
+ __rtnl_unlock();
+ rcu_barrier();
+ rtnl_lock();
- if (dev->destructor)
- dev->destructor(dev);
+ list_for_each_entry(dev, &list, todo_list) {
+ call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
+ if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
+ &dev->state)) {
+ /* We must not have linkwatch events
+ * pending on unregister. If this
+ * happens, we simply run the queue
+ * unscheduled, resulting in a noop
+ * for this device.
+ */
+ linkwatch_run_queue();
+ }
+ }
- /* Report a network device has been unregistered */
- rtnl_lock();
- dev_net(dev)->dev_unreg_count--;
__rtnl_unlock();
- wake_up(&netdev_unregistering_wq);
- /* Free network device */
- kobject_put(&dev->dev.kobj);
+ rebroadcast_time = jiffies;
+ }
+
+ msleep(250);
+
+ if (time_after(jiffies, warning_time + 10 * HZ)) {
+ list_for_each_entry(dev, &list, todo_list) {
+ pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
+ dev->name, netdev_refcnt_read(dev));
+ }
+ warning_time = jiffies;
}
+
+ goto again;
}
/* Convert net_device_stats to rtnl_link_stats64. They have the same
--
2.4.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists