diff mbox

[RFC] Add netdev all_adj_list refcnt propagation to fix panic

Message ID 1459272303-8851-1-git-send-email-acollins@cradlepoint.com
State RFC, archived
Delegated to: David Miller
Headers show

Commit Message

Andrew Collins March 29, 2016, 5:25 p.m. UTC
This is an RFC patch to fix a relatively easily reproducible kernel
panic related to the all_adj_list handling for netdevs in recent kernels.

This is more to generate discussion than anything else.  I don't
particularly like this approach, I'm hoping someone has a better idea.

The following sequence of commands will reproduce the issue:

ip link add link eth0 name eth0.100 type vlan id 100
ip link add link eth0 name eth0.200 type vlan id 200
ip link add name testbr type bridge
ip link set eth0.100 master testbr
ip link set eth0.200 master testbr
ip link add link testbr mac0 type macvlan
ip link delete dev testbr

This creates an upper/lower tree of (excuse the poor ASCII art):

            /---eth0.100-eth0
mac0-testbr-
            \---eth0.200-eth0

When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
reference to eth0 is added, so this results in a panic.

This change adds reference count propagation so things are handled properly.

Matthias Schiffer reported a similar crash in batman-adv:

https://github.com/freifunk-gluon/gluon/issues/680
https://www.open-mesh.org/issues/247

which this patch also seems to resolve.
---
 net/core/dev.c | 68 ++++++++++++++++++++++++++++++++--------------------------
 1 file changed, 37 insertions(+), 31 deletions(-)

Comments

David Miller March 30, 2016, 8:01 p.m. UTC | #1
From: Andrew Collins <acollins@cradlepoint.com>
Date: Tue, 29 Mar 2016 11:25:03 -0600

> This is an RFC patch to fix a relatively easily reproducible kernel
> panic related to the all_adj_list handling for netdevs in recent kernels.
> 
> This is more to generate discussion than anything else.  I don't
> particularly like this approach, I'm hoping someone has a better idea.
> 
> The following sequence of commands will reproduce the issue:
> 
> ip link add link eth0 name eth0.100 type vlan id 100
> ip link add link eth0 name eth0.200 type vlan id 200
> ip link add name testbr type bridge
> ip link set eth0.100 master testbr
> ip link set eth0.200 master testbr
> ip link add link testbr mac0 type macvlan
> ip link delete dev testbr
> 
> This creates an upper/lower tree of (excuse the poor ASCII art):
> 
>             /---eth0.100-eth0
> mac0-testbr-
>             \---eth0.200-eth0
> 
> When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
> the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
> reference to eth0 is added, so this results in a panic.
> 
> This change adds reference count propagation so things are handled properly.
> 
> Matthias Schiffer reported a similar crash in batman-adv:
> 
> https://github.com/freifunk-gluon/gluon/issues/680
> https://www.open-mesh.org/issues/247
> 
> which this patch also seems to resolve.

Veaceslav, please look into this.

Thanks.
David Miller March 30, 2016, 8:15 p.m. UTC | #2
From: David Miller <davem@davemloft.net>
Date: Wed, 30 Mar 2016 16:01:50 -0400 (EDT)

> Veaceslav, please look into this.

Of course, his email now bounces.... :-/
Andrew Collins March 30, 2016, 8:32 p.m. UTC | #3
> From: Andrew Collins <acollins@cradlepoint.com>
> Date: Tue, 29 Mar 2016 11:25:03 -0600
>
>> This is an RFC patch to fix a relatively easily reproducible kernel
>> panic related to the all_adj_list handling for netdevs in recent kernels.
>>
>> This is more to generate discussion than anything else.  I don't
>> particularly like this approach, I'm hoping someone has a better idea.
>>
>> The following sequence of commands will reproduce the issue:
>>
>> ip link add link eth0 name eth0.100 type vlan id 100
>> ip link add link eth0 name eth0.200 type vlan id 200
>> ip link add name testbr type bridge
>> ip link set eth0.100 master testbr
>> ip link set eth0.200 master testbr
>> ip link add link testbr mac0 type macvlan
>> ip link delete dev testbr
>>
>> This creates an upper/lower tree of (excuse the poor ASCII art):
>>
>>              /---eth0.100-eth0
>> mac0-testbr-
>>              \---eth0.200-eth0
>>
>> When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
>> the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
>> reference to eth0 is added, so this results in a panic.
>>
>> This change adds reference count propagation so things are handled properly.
>>
>> Matthias Schiffer reported a similar crash in batman-adv:
>>
>> https://github.com/freifunk-gluon/gluon/issues/680
>> https://www.open-mesh.org/issues/247
>>
>> which this patch also seems to resolve.
>
> Veaceslav, please look into this.
>
> Thanks.
>
> !SIG:56fc30b5184771297483788!
>

+vfalico's new address picked up from git logs
diff mbox

Patch

diff --git a/net/core/dev.c b/net/core/dev.c
index b9bcbe7..4b4ef6b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5471,6 +5471,7 @@  static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
 
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
+					u16 ref_nr,
 					struct list_head *dev_list,
 					void *private, bool master)
 {
@@ -5480,7 +5481,7 @@  static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj = __netdev_find_adj(adj_dev, dev_list);
 
 	if (adj) {
-		adj->ref_nr++;
+		adj->ref_nr += ref_nr;
 		return 0;
 	}
 
@@ -5490,7 +5491,7 @@  static int __netdev_adjacent_dev_insert(struct net_device *dev,
 
 	adj->dev = adj_dev;
 	adj->master = master;
-	adj->ref_nr = 1;
+	adj->ref_nr = ref_nr;
 	adj->private = private;
 	dev_hold(adj_dev);
 
@@ -5529,6 +5530,7 @@  free_adj:
 
 static void __netdev_adjacent_dev_remove(struct net_device *dev,
 					 struct net_device *adj_dev,
+					 u16 ref_nr,
 					 struct list_head *dev_list)
 {
 	struct netdev_adjacent *adj;
@@ -5541,10 +5543,10 @@  static void __netdev_adjacent_dev_remove(struct net_device *dev,
 		BUG();
 	}
 
-	if (adj->ref_nr > 1) {
-		pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
-			 adj->ref_nr-1);
-		adj->ref_nr--;
+	if (adj->ref_nr > ref_nr) {
+		pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name,
+			 ref_nr, adj->ref_nr-ref_nr);
+		adj->ref_nr -= ref_nr;
 		return;
 	}
 
@@ -5563,21 +5565,22 @@  static void __netdev_adjacent_dev_remove(struct net_device *dev,
 
 static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 					    struct net_device *upper_dev,
+					    u16 ref_nr,
 					    struct list_head *up_list,
 					    struct list_head *down_list,
 					    void *private, bool master)
 {
 	int ret;
 
-	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
-					   master);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+					   private, master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
-					   false);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+					   private, false);
 	if (ret) {
-		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+		__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
 		return ret;
 	}
 
@@ -5585,9 +5588,10 @@  static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 }
 
 static int __netdev_adjacent_dev_link(struct net_device *dev,
-				      struct net_device *upper_dev)
+				      struct net_device *upper_dev,
+				      u16 ref_nr)
 {
-	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
 						&dev->all_adj_list.upper,
 						&upper_dev->all_adj_list.lower,
 						NULL, false);
@@ -5595,17 +5599,19 @@  static int __netdev_adjacent_dev_link(struct net_device *dev,
 
 static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
 					       struct net_device *upper_dev,
+					       u16 ref_nr,
 					       struct list_head *up_list,
 					       struct list_head *down_list)
 {
-	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
-	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
+	__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+	__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
 }
 
 static void __netdev_adjacent_dev_unlink(struct net_device *dev,
-					 struct net_device *upper_dev)
+					 struct net_device *upper_dev,
+					 u16 ref_nr)
 {
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
 					   &dev->all_adj_list.upper,
 					   &upper_dev->all_adj_list.lower);
 }
@@ -5614,17 +5620,17 @@  static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 						struct net_device *upper_dev,
 						void *private, bool master)
 {
-	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+	int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
 
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
 					       &dev->adj_list.upper,
 					       &upper_dev->adj_list.lower,
 					       private, master);
 	if (ret) {
-		__netdev_adjacent_dev_unlink(dev, upper_dev);
+		__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
 		return ret;
 	}
 
@@ -5634,8 +5640,8 @@  static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 						   struct net_device *upper_dev)
 {
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
 					   &dev->adj_list.upper,
 					   &upper_dev->adj_list.lower);
 }
@@ -5688,7 +5694,7 @@  static int __netdev_upper_dev_link(struct net_device *dev,
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			pr_debug("Interlinking %s with %s, non-neighbour\n",
 				 i->dev->name, j->dev->name);
-			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
+			ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
 			if (ret)
 				goto rollback_mesh;
 		}
@@ -5698,7 +5704,7 @@  static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		pr_debug("linking %s's upper device %s with %s\n",
 			 upper_dev->name, i->dev->name, dev->name);
-		ret = __netdev_adjacent_dev_link(dev, i->dev);
+		ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
 		if (ret)
 			goto rollback_upper_mesh;
 	}
@@ -5707,7 +5713,7 @@  static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		pr_debug("linking %s's lower device %s with %s\n", dev->name,
 			 i->dev->name, upper_dev->name);
-		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
+		ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
 		if (ret)
 			goto rollback_lower_mesh;
 	}
@@ -5725,7 +5731,7 @@  rollback_lower_mesh:
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 	}
 
 	i = NULL;
@@ -5735,7 +5741,7 @@  rollback_upper_mesh:
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 	}
 
 	i = j = NULL;
@@ -5747,7 +5753,7 @@  rollback_mesh:
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			if (i == to_i && j == to_j)
 				break;
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 		}
 		if (i == to_i)
 			break;
@@ -5827,16 +5833,16 @@  void netdev_upper_dev_unlink(struct net_device *dev,
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 
 	/* remove also the devices itself from lower/upper device
 	 * list
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
 				      &changeupper_info.info);