Hi David,
here are some bugfix patches which we would like to have integrated into net.
Please pull or let me know of any problem!
Thank you, Simon
The following changes since commit 29fbff8698fc0ac1a1d74584b258e0bf18b469f9:
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net (2016-10-13 21:40:23 -0700)
are available in the git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-net-for-davem-20161026
for you to fetch changes up to 9799c50372b23ed774791bdb87d700f1286ee8a9:
batman-adv: fix splat on disabling an interface (2016-10-21 14:47:02 +0200)
---------------------------------------------------------------- Here are three batman-adv bugfix patches:
- Fix RCU usage for neighbor list, by Sven Eckelmann
- Fix BATADV_DBG_ALL loglevel to include TP Meter messages, by Sven Eckelmann
- Fix possible splat when disabling an interface, by Linus Luessing
---------------------------------------------------------------- Linus Lüssing (1): batman-adv: fix splat on disabling an interface
Sven Eckelmann (2): batman-adv: Modify neigh_list only with rcu-list functions batman-adv: Add BATADV_DBG_TP_METER to BATADV_DBG_ALL
net/batman-adv/hard-interface.c | 1 - net/batman-adv/log.h | 2 +- net/batman-adv/originator.c | 2 +- 3 files changed, 2 insertions(+), 3 deletions(-)
From: Sven Eckelmann sven.eckelmann@open-mesh.com
The batadv_hard_iface::neigh_list is accessed via rcu based primitives. Thus all operations done on it have to fulfill the requirements by RCU. So using non-RCU mechanisms like hlist_add_head is not allowed because it misses the barriers required to protect concurrent readers when accessing the data behind the pointer.
Fixes: cef63419f7db ("batman-adv: add list of unique single hop neighbors per hard-interface") Signed-off-by: Sven Eckelmann sven.eckelmann@open-mesh.com Acked-by: Linus Lüssing linus.luessing@c0d3.blue Signed-off-by: Simon Wunderlich sw@simonwunderlich.de --- net/batman-adv/originator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 5f3bfc4..7c8d160 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -544,7 +544,7 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface, if (bat_priv->algo_ops->neigh.hardif_init) bat_priv->algo_ops->neigh.hardif_init(hardif_neigh);
- hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list); + hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list);
out: spin_unlock_bh(&hard_iface->neigh_list_lock);
From: Sven Eckelmann sven@narfation.org
The BATADV_DBG_ALL has to contain the bit of BATADV_DBG_TP_METER to really support all available debug messages.
Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de --- net/batman-adv/log.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index e0e1a88..d2905a8 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -63,7 +63,7 @@ enum batadv_dbg_level { BATADV_DBG_NC = BIT(5), BATADV_DBG_MCAST = BIT(6), BATADV_DBG_TP_METER = BIT(7), - BATADV_DBG_ALL = 127, + BATADV_DBG_ALL = 255, };
#ifdef CONFIG_BATMAN_ADV_DEBUG
From: Linus Lüssing linus.luessing@c0d3.blue
As long as there is still a reference for a hard interface held, there might still be a forwarding packet relying on its attributes.
Therefore avoid setting hard_iface->soft_iface to NULL when disabling a hard interface.
This fixes the following, potential splat:
batman_adv: bat0: Interface deactivated: eth1 batman_adv: bat0: Removing interface: eth1 cgroup: new mount options do not match the existing superblock, will be ignored batman_adv: bat0: Interface deactivated: eth3 batman_adv: bat0: Removing interface: eth3 ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1986 at ./net/batman-adv/bat_iv_ogm.c:549 batadv_iv_send_outstanding_bat_ogm_packet+0x145/0x643 [batman_adv] Modules linked in: batman_adv(O-) <...> CPU: 3 PID: 1986 Comm: kworker/u8:2 Tainted: G W O 4.6.0-rc6+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 Workqueue: bat_events batadv_iv_send_outstanding_bat_ogm_packet [batman_adv] 0000000000000000 ffff88001d93bca0 ffffffff8126c26b 0000000000000000 0000000000000000 ffff88001d93bcf0 ffffffff81051615 ffff88001f19f818 000002251d93bd68 0000000000000046 ffff88001dc04a00 ffff88001becbe48 Call Trace: [<ffffffff8126c26b>] dump_stack+0x67/0x90 [<ffffffff81051615>] __warn+0xc7/0xe5 [<ffffffff8105164b>] warn_slowpath_null+0x18/0x1a [<ffffffffa0356f24>] batadv_iv_send_outstanding_bat_ogm_packet+0x145/0x643 [batman_adv] [<ffffffff8108b01f>] ? __lock_is_held+0x32/0x54 [<ffffffff810689a2>] process_one_work+0x2a8/0x4f5 [<ffffffff81068856>] ? process_one_work+0x15c/0x4f5 [<ffffffff81068df2>] worker_thread+0x1d5/0x2c0 [<ffffffff81068c1d>] ? process_scheduled_works+0x2e/0x2e [<ffffffff81068c1d>] ? process_scheduled_works+0x2e/0x2e [<ffffffff8106dd90>] kthread+0xc0/0xc8 [<ffffffff8144de82>] ret_from_fork+0x22/0x40 [<ffffffff8106dcd0>] ? __init_kthread_worker+0x55/0x55 ---[ end trace 647f9f325123dc05 ]---
What happened here is, that there was still a forw_packet (here: a BATMAN IV OGM) in the queue of eth3 with the forw_packet->if_incoming set to eth1 and the forw_packet->if_outgoing set to eth3.
When eth3 is to be deactivated and removed, then this thread waits for the forw_packet queued on eth3 to finish. Because eth1 was deactivated and removed earlier and by that had forw_packet->if_incoming->soft_iface, set to NULL, the splat when trying to send/flush the OGM on eth3 occures.
Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Linus Lüssing linus.luessing@c0d3.blue [sven@narfation.org: Reduced size of Oops message] Signed-off-by: Sven Eckelmann sven@narfation.org Signed-off-by: Simon Wunderlich sw@simonwunderlich.de --- net/batman-adv/hard-interface.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 08ce361..e034afb 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -652,7 +652,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_softif_destroy_sysfs(hard_iface->soft_iface); }
- hard_iface->soft_iface = NULL; batadv_hardif_put(hard_iface);
out:
From: Simon Wunderlich sw@simonwunderlich.de Date: Wed, 26 Oct 2016 17:55:12 +0200
here are some bugfix patches which we would like to have integrated into net.
Please pull or let me know of any problem!
Pulled, thanks Simon.
b.a.t.m.a.n@lists.open-mesh.org
-
David Miller -
Simon Wunderlich