Re: Possible circular locking dependency (3.3-rc2)
From: NeilBrown
Date: Mon Feb 20 2012 - 04:09:14 EST
On Mon, 20 Feb 2012 09:07:42 +0100 Thomas Weber
<thomas.weber.linux@xxxxxxxxxxxxxx> wrote:
> Hello,
>
> I applied the patch from Ming, but got also an error.
> I am ccing Neil, because I also applied some patches from him.
That looks like it is the third of the three patches I sent.
I needed some locking and there was a mutex available that seemed to be
available so I used it. Apparently it causes problems.
I don't think I ever saw that myself ... I wonder why.
There is already a dependency between the mutex I used and s_active
in sysfs. I guess that means I'll have to create a new lock just for
the purpose of keeping two threads from using the w1 bus at the same time...
Apart from this - which is just a warning, though maybe it could become a
real deadlock - is the bq27000 now working for you?
NeilBrown
>
> Regards,
> Thomas
>
> > [ 6.229370] ======================================================
> > [ 6.235870] [ INFO: possible circular locking dependency detected ]
> > [ 6.242431] 3.3.0-rc4-00020-ga02b31a #10 Not tainted
> > [ 6.247650] -------------------------------------------------------
> > [ 6.254241] udevadm/596 is trying to acquire lock:
> > [ 6.259277] (&dev->mutex#2){+.+.+.}, at: [<c0308af0>] w1_bq27000_read+0x1c/0x48
> > [ 6.267120]
> > [ 6.267120] but task is already holding lock:
> > [ 6.273254] (s_active#11){++++.+}, at: [<c01463d4>] sysfs_write_file+0xdc/0x180
> > [ 6.281097]
> > [ 6.281127] which lock already depends on the new lock.
> > [ 6.281127]
> > [ 6.289703]
> > [ 6.289703] the existing dependency chain (in reverse order) is:
> > [ 6.297576]
> > [ 6.297576] -> #1 (s_active#11){++++.+}:
> > [ 6.303283] [<c007b3c8>] lock_acquire+0xa0/0x128
> > [ 6.308807] [<c0147b50>] sysfs_addrm_finish+0xf4/0x148
> > [ 6.314880] [<c0146184>] sysfs_hash_and_remove+0x4c/0x88
> > [ 6.321136] [<c0146cec>] sysfs_remove_file+0x30/0x38
> > [ 6.326995] [<c0275bec>] device_del+0xf0/0x17c
> > [ 6.332336] [<c0275c84>] device_unregister+0xc/0x18
> > [ 6.338104] [<c0306b28>] w1_slave_detach+0xac/0xcc
> > [ 6.343811] [<c0306e5c>] w1_reconnect_slaves+0xc0/0x10c
> > [ 6.349945] [<c0307924>] w1_register_family+0x90/0xa0
> > [ 6.355926] [<c0008760>] do_one_initcall+0x34/0x174
> > [ 6.361694] [<c054980c>] kernel_init+0x94/0x11c
> > [ 6.367126] [<c00148b0>] kernel_thread_exit+0x0/0x8
> > [ 6.372924]
> > [ 6.372924] -> #0 (&dev->mutex#2){+.+.+.}:
> > [ 6.378845] [<c007a980>] __lock_acquire+0x1678/0x1ad4
> > [ 6.384826] [<c007b3c8>] lock_acquire+0xa0/0x128
> > [ 6.390319] [<c03c7b24>] mutex_lock_nested+0x48/0x2bc
> > [ 6.396301] [<c0308af0>] w1_bq27000_read+0x1c/0x48
> > [ 6.401977] [<c03098d4>] bq27000_read_platform+0x2c/0x124
> > [ 6.408325] [<c030a004>] bq27x00_battery_get_property+0x1cc/0x3cc
> > [ 6.415374] [<c0309154>] power_supply_show_property+0x4c/0x224
> > [ 6.422180] [<c0309468>] power_supply_uevent+0xe4/0x224
> > [ 6.428314] [<c0276b60>] dev_uevent+0xb4/0x170
> > [ 6.433654] [<c01f4b84>] kobject_uevent_env+0x1d8/0x478
> > [ 6.439819] [<c027603c>] store_uevent+0x50/0x54
> > [ 6.445220] [<c0274f58>] dev_attr_store+0x18/0x24
> > [ 6.450805] [<c01463f8>] sysfs_write_file+0x100/0x180
> > [ 6.456787] [<c00e96a0>] vfs_write+0xa8/0x138
> > [ 6.462036] [<c00e9910>] sys_write+0x40/0x6c
> > [ 6.467163] [<c00138e0>] ret_fast_syscall+0x0/0x3c
> > [ 6.472869]
> > [ 6.472869] other info that might help us debug this:
> > [ 6.472900]
> > [ 6.481292] Possible unsafe locking scenario:
> > [ 6.481292]
> > [ 6.487518] CPU0 CPU1
> > [ 6.492248] ---- ----
> > [ 6.497009] lock(s_active#11);
> > [ 6.500427] lock(&dev->mutex#2);
> > [ 6.506683] lock(s_active#11);
> > [ 6.512756] lock(&dev->mutex#2);
> > [ 6.516357]
> > [ 6.516357] *** DEADLOCK ***
> > [ 6.516357]
> > [ 6.522583] 2 locks held by udevadm/596:
> > [ 6.526702] #0: (&buffer->mutex){+.+.+.}, at: [<c0146320>] sysfs_write_file+0x28/0x180
> > [ 6.535278] #1: (s_active#11){++++.+}, at: [<c01463d4>] sysfs_write_file+0xdc/0x180
> > [ 6.543579]
> > [ 6.543579]
> > [ 6.543579] stack backtrace:
> > [ 6.548217] [<c0019e9c>] (unwind_backtrace+0x0/0xf8) from [<c03c3544>] (print_circular_bug+0x2c8/0x2d4)
> > [ 6.558105] [<c03c3544>] (print_circular_bug+0x2c8/0x2d4) from [<c007a980>] (__lock_acquire+0x1678/0x1ad4)
> > [ 6.568267] [<c007a980>] (__lock_acquire+0x1678/0x1ad4) from [<c007b3c8>] (lock_acquire+0xa0/0x128)
> > [ 6.577789] [<c007b3c8>] (lock_acquire+0xa0/0x128) from [<c03c7b24>] (mutex_lock_nested+0x48/0x2bc)
> > [ 6.587310] [<c03c7b24>] (mutex_lock_nested+0x48/0x2bc) from [<c0308af0>] (w1_bq27000_read+0x1c/0x48)
> > [ 6.597015] [<c0308af0>] (w1_bq27000_read+0x1c/0x48) from [<c03098d4>] (bq27000_read_platform+0x2c/0x124)
> > [ 6.607086] [<c03098d4>] (bq27000_read_platform+0x2c/0x124) from [<c030a004>] (bq27x00_battery_get_property+0x1cc/0x3cc)
> > [ 6.618499] [<c030a004>] (bq27x00_battery_get_property+0x1cc/0x3cc) from [<c0309154>] (power_supply_show_property+0x4c/0x224)
> > [ 6.630401] [<c0309154>] (power_supply_show_property+0x4c/0x224) from [<c0309468>] (power_supply_uevent+0xe4/0x224)
> > [ 6.641357] [<c0309468>] (power_supply_uevent+0xe4/0x224) from [<c0276b60>] (dev_uevent+0xb4/0x170)
> > [ 6.650909] [<c0276b60>] (dev_uevent+0xb4/0x170) from [<c01f4b84>] (kobject_uevent_env+0x1d8/0x478)
> > [ 6.660430] [<c01f4b84>] (kobject_uevent_env+0x1d8/0x478) from [<c027603c>] (store_uevent+0x50/0x54)
> > [ 6.670013] [<c027603c>] (store_uevent+0x50/0x54) from [<c0274f58>] (dev_attr_store+0x18/0x24)
> > [ 6.679107] [<c0274f58>] (dev_attr_store+0x18/0x24) from [<c01463f8>] (sysfs_write_file+0x100/0x180)
> > [ 6.688720] [<c01463f8>] (sysfs_write_file+0x100/0x180) from [<c00e96a0>] (vfs_write+0xa8/0x138)
> > [ 6.697967] [<c00e96a0>] (vfs_write+0xa8/0x138) from [<c00e9910>] (sys_write+0x40/0x6c)
> > [ 6.706390] [<c00e9910>] (sys_write+0x40/0x6c) from [<c00138e0>] (ret_fast_syscall+0x0/0x3c)
Attachment:
signature.asc
Description: PGP signature