From 9abefcb1aaa58b9d5aa40a8bb12c87d02415e4c8 Mon Sep 17 00:00:00 2001 From: Sergei Miroshnichenko Date: Wed, 7 Sep 2016 16:51:12 +0300 Subject: can: dev: fix deadlock reported after bus-off A timer was used to restart after the bus-off state, leading to a relatively large can_restart() executed in an interrupt context, which in turn sets up pinctrl. When this happens during system boot, there is a high probability of grabbing the pinctrl_list_mutex, which is locked already by the probe() of other device, making the kernel suspect a deadlock condition [1]. To resolve this issue, the restart_timer is replaced by a delayed work. [1] https://github.com/victronenergy/venus/issues/24 Signed-off-by: Sergei Miroshnichenko Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5261751f6bd4..5f5270941ba0 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -32,6 +32,7 @@ enum can_mode { * CAN common private data */ struct can_priv { + struct net_device *dev; struct can_device_stats can_stats; struct can_bittiming bittiming, data_bittiming; @@ -47,7 +48,7 @@ struct can_priv { u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; - struct timer_list restart_timer; + struct delayed_work restart_work; int (*do_set_bittiming)(struct net_device *dev); int (*do_set_data_bittiming)(struct net_device *dev); -- cgit v1.2.3 From 2cf750704bb6d7ed8c7d732e071dd1bc890ea5e8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 25 Sep 2016 23:08:31 +0200 Subject: ipmr, ip6mr: fix scheduling while atomic and a deadlock with ipmr_get_route Since the commit below the ipmr/ip6mr rtnl_unicast() code uses the portid instead of the previous dst_pid which was copied from in_skb's portid. Since the skb is new the portid is 0 at that point so the packets are sent to the kernel and we get scheduling while atomic or a deadlock (depending on where it happens) by trying to acquire rtnl two times. Also since this is RTM_GETROUTE, it can be triggered by a normal user. Here's the sleeping while atomic trace: [ 7858.212557] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620 [ 7858.212748] in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/0 [ 7858.212881] 2 locks held by swapper/0/0: [ 7858.213013] #0: (((&mrt->ipmr_expire_timer))){+.-...}, at: [] call_timer_fn+0x5/0x350 [ 7858.213422] #1: (mfc_unres_lock){+.....}, at: [] ipmr_expire_process+0x25/0x130 [ 7858.213807] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.8.0-rc7+ #179 [ 7858.213934] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 7858.214108] 0000000000000000 ffff88005b403c50 ffffffff813a7804 0000000000000000 [ 7858.214412] ffffffff81a1338e ffff88005b403c78 ffffffff810a4a72 ffffffff81a1338e [ 7858.214716] 000000000000026c 0000000000000000 ffff88005b403ca8 ffffffff810a4b9f [ 7858.215251] Call Trace: [ 7858.215412] [] dump_stack+0x85/0xc1 [ 7858.215662] [] ___might_sleep+0x192/0x250 [ 7858.215868] [] __might_sleep+0x6f/0x100 [ 7858.216072] [] mutex_lock_nested+0x33/0x4d0 [ 7858.216279] [] ? netlink_lookup+0x25f/0x460 [ 7858.216487] [] rtnetlink_rcv+0x1b/0x40 [ 7858.216687] [] netlink_unicast+0x19c/0x260 [ 7858.216900] [] rtnl_unicast+0x20/0x30 [ 7858.217128] [] ipmr_destroy_unres+0xa9/0xf0 [ 7858.217351] [] ipmr_expire_process+0x8f/0x130 [ 7858.217581] [] ? ipmr_net_init+0x180/0x180 [ 7858.217785] [] ? ipmr_net_init+0x180/0x180 [ 7858.217990] [] call_timer_fn+0xa5/0x350 [ 7858.218192] [] ? call_timer_fn+0x5/0x350 [ 7858.218415] [] ? ipmr_net_init+0x180/0x180 [ 7858.218656] [] run_timer_softirq+0x260/0x640 [ 7858.218865] [] ? __do_softirq+0xbb/0x54f [ 7858.219068] [] __do_softirq+0xe8/0x54f [ 7858.219269] [] irq_exit+0xb8/0xc0 [ 7858.219463] [] smp_apic_timer_interrupt+0x42/0x50 [ 7858.219678] [] apic_timer_interrupt+0x8c/0xa0 [ 7858.219897] [] ? native_safe_halt+0x6/0x10 [ 7858.220165] [] ? trace_hardirqs_on+0xd/0x10 [ 7858.220373] [] default_idle+0x23/0x190 [ 7858.220574] [] arch_cpu_idle+0xf/0x20 [ 7858.220790] [] default_idle_call+0x4c/0x60 [ 7858.221016] [] cpu_startup_entry+0x39b/0x4d0 [ 7858.221257] [] rest_init+0x135/0x140 [ 7858.221469] [] start_kernel+0x50e/0x51b [ 7858.221670] [] ? early_idt_handler_array+0x120/0x120 [ 7858.221894] [] x86_64_start_reservations+0x2a/0x2c [ 7858.222113] [] x86_64_start_kernel+0x13b/0x14a Fixes: 2942e9005056 ("[RTNETLINK]: Use rtnl_unicast() for rtnetlink unicasts") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 2 +- include/linux/mroute6.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index d351fd3e1049..e5fb81376e92 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -120,5 +120,5 @@ struct mfc_cache { struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, - struct rtmsg *rtm, int nowait); + struct rtmsg *rtm, int nowait, u32 portid); #endif diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 3987b64040c5..19a1c0c2993b 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -116,7 +116,7 @@ struct mfc6_cache { struct rtmsg; extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, - struct rtmsg *rtm, int nowait); + struct rtmsg *rtm, int nowait, u32 portid); #ifdef CONFIG_IPV6_MROUTE extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb); -- cgit v1.2.3