Merge branch 'netdev-adjacency'

David Ahern says:

====================
net: Fix netdev adjacency tracking

The netdev adjacency tracking is failing to create proper dependencies
for some topologies. For example this topology

        +--------+
        |  myvrf |
        +--------+
          |    |
          |  +---------+
          |  | macvlan |
          |  +---------+
          |    |
      +----------+
      |  bridge  |
      +----------+
          |
      +--------+
      | bond1  |
      +--------+
          |
      +--------+
      |  eth3  |
      +--------+

hits 1 of 2 problems depending on the order of enslavement. The base set of
commands for both cases:

    ip link add bond1 type bond
    ip link set bond1 up
    ip link set eth3 down
    ip link set eth3 master bond1
    ip link set eth3 up

    ip link add bridge type bridge
    ip link set bridge up
    ip link add macvlan link bridge type macvlan
    ip link set macvlan up

    ip link add myvrf type vrf table 1234
    ip link set myvrf up

    ip link set bridge master myvrf

Case 1 enslave macvlan to the vrf before enslaving the bond to the bridge:

    ip link set macvlan master myvrf
    ip link set bond1 master bridge

Attempts to delete the VRF:
    ip link delete myvrf

trigger the BUG in __netdev_adjacent_dev_remove:

[  587.405260] tried to remove device eth3 from myvrf
[  587.407269] ------------[ cut here ]------------
[  587.408918] kernel BUG at /home/dsa/kernel.git/net/core/dev.c:5661!
[  587.411113] invalid opcode: 0000 [#1] SMP
[  587.412454] Modules linked in: macvlan bridge stp llc bonding vrf
[  587.414765] CPU: 0 PID: 726 Comm: ip Not tainted 4.8.0+ #109
[  587.416766] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[  587.420241] task: ffff88013ab6eec0 task.stack: ffffc90000628000
[  587.422163] RIP: 0010:[<ffffffff813cef03>]  [<ffffffff813cef03>] __netdev_adjacent_dev_remove+0x40/0x12c
...
[  587.446053] Call Trace:
[  587.446424]  [<ffffffff813d1542>] __netdev_adjacent_dev_unlink+0x20/0x3c
[  587.447390]  [<ffffffff813d16a3>] netdev_upper_dev_unlink+0xfa/0x15e
[  587.448297]  [<ffffffffa00003a3>] vrf_del_slave+0x13/0x2a [vrf]
[  587.449153]  [<ffffffffa00004a4>] vrf_dev_uninit+0xea/0x114 [vrf]
[  587.450036]  [<ffffffff813d19b0>] rollback_registered_many+0x22b/0x2da
[  587.450974]  [<ffffffff813d1aac>] unregister_netdevice_many+0x17/0x48
[  587.451903]  [<ffffffff813de444>] rtnl_delete_link+0x3c/0x43
[  587.452719]  [<ffffffff813dedcd>] rtnl_dellink+0x180/0x194

When the BUG is converted to a WARN_ON it shows 4 missing adjacencies:
  eth3 - myvrf, mvrf - eth3, bond1 - myvrf and myvrf - bond1

All of those are because the __netdev_upper_dev_link function does not
properly link macvlan lower devices to myvrf when it is enslaved.

The second case just flips the ordering of the enslavements:
    ip link set bond1 master bridge
    ip link set macvlan master myvrf

Then run:
    ip link delete bond1
    ip link delete myvrf

The vrf delete command hangs because myvrf has a reference that has not
been released. In this case the removal code does not account for 2 paths
between eth3 and myvrf - one from bridge to vrf and the other through the
macvlan.

Rather than try to maintain a linked list of all upper and lower devices
per netdevice, only track the direct neighbors. The remaining stack can
be determined by recursively walking the neighbors.

The existing netdev_for_each_all_upper_dev_rcu,
netdev_for_each_all_lower_dev and netdev_for_each_all_lower_dev_rcu macros
are replaced with APIs that walk the upper and lower device lists. The
new APIs take a callback function and a data arg that is passed to the
callback for each device in the list. Drivers using the old macros are
converted in separate patches to make it easier on reviewers. It is an
API conversion only; no functional change is intended.

v3
- address Stephen's comment to simplify logic and remove typecasts

v2
- fixed bond0 references in cover-letter
- fixed definition of netdev_next_lower_dev_rcu to mirror the upper_dev
  version.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 15 insertions, 23 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bf341b65ca5e..458c87631e7f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1456,7 +1456,6 @@ enum netdev_priv_flags {
  *	@ptype_specific: Device-specific, protocol-specific packet handlers
  *
  *	@adj_list:	Directly linked devices, like slaves for bonding
- *	@all_adj_list:	All linked devices, *including* neighbours
  *	@features:	Currently active device features
  *	@hw_features:	User-changeable features
  *
@@ -1675,11 +1674,6 @@ struct net_device {
 		struct list_head lower;
 	} adj_list;
 
-	struct {
-		struct list_head upper;
-		struct list_head lower;
-	} all_adj_list;
-
 	netdev_features_t	features;
 	netdev_features_t	hw_features;
 	netdev_features_t	wanted_features;
@@ -3771,12 +3765,13 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 	     updev; \
 	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
 
-/* iterate through upper list, must be called under RCU read lock */
-#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
-	for (iter = &(dev)->all_adj_list.upper, \
-	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
-	     updev; \
-	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
+int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
+				  int (*fn)(struct net_device *upper_dev,
+					    void *data),
+				  void *data);
+
+bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
+				  struct net_device *upper_dev);
 
 void *netdev_lower_get_next_private(struct net_device *dev,
 				    struct list_head **iter);
@@ -3809,17 +3804,14 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev,
 struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
 						 struct list_head **iter);
 
-#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
-	for (iter = (dev)->all_adj_list.lower.next, \
-	     ldev = netdev_all_lower_get_next(dev, &(iter)); \
-	     ldev; \
-	     ldev = netdev_all_lower_get_next(dev, &(iter)))
-
-#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
-	for (iter = (dev)->all_adj_list.lower.next, \
-	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
-	     ldev; \
-	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
+int netdev_walk_all_lower_dev(struct net_device *dev,
+			      int (*fn)(struct net_device *lower_dev,
+					void *data),
+			      void *data);
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+				  int (*fn)(struct net_device *lower_dev,
+					    void *data),
+				  void *data);
 
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);