[PATCH 3.2 115/152] Fix circular locking dependency (3.3-rc2)

2015-02-16 Thread Ben Hutchings
3.2.67-rc1 review patch.  If anyone has any objections, please let me know.

--

From: Ming Lei 

commit 864533ceb6db336dead389577c102a8b792a121a upstream.

Hi,

On Wed, Feb 8, 2012 at 8:41 PM, Felipe Balbi  wrote:
> Hi guys,
>
> I have just triggered the folllowing:
>
> [   84.860321] ==
> [   84.860321] [ INFO: possible circular locking dependency detected ]
> [   84.860321] 3.3.0-rc2-00026-ge4e8a39 #474 Not tainted
> [   84.860321] ---
> [   84.860321] bash/949 is trying to acquire lock:
> [   84.860321]  (sysfs_lock){+.+.+.}, at: [] 
> gpio_value_store+0x24/0xcc
> [   84.860321]
> [   84.860321] but task is already holding lock:
> [   84.860321]  (s_active#22){.+}, at: [] 
> sysfs_write_file+0xdc/0x184
> [   84.911468]
> [   84.911468] which lock already depends on the new lock.
> [   84.911468]
> [   84.920043]
> [   84.920043] the existing dependency chain (in reverse order) is:
> [   84.920043]
> [   84.927886] -> #1 (s_active#22){.+}:
> [   84.927886]        [] check_prevs_add+0xdc/0x150
> [   84.927886]        [] validate_chain.clone.24+0x564/0x694
> [   84.927886]        [] __lock_acquire+0x49c/0x980
> [   84.951660]        [] lock_acquire+0x98/0x100
> [   84.951660]        [] sysfs_deactivate+0xb0/0x100
> [   84.962982]        [] sysfs_addrm_finish+0x2c/0x6c
> [   84.962982]        [] sysfs_remove_dir+0x84/0x98
> [   84.962982]        [] kobject_del+0x10/0x78
> [   84.974670]        [] device_del+0x140/0x170
> [   84.974670]        [] device_unregister+0xc/0x18
> [   84.985382]        [] gpio_unexport+0xbc/0xdc
> [   84.985382]        [] gpio_free+0x14/0xfc
> [   85.001708]        [] unexport_store+0x78/0x8c
> [   85.001708]        [] class_attr_store+0x18/0x24
> [   85.007293]        [] sysfs_write_file+0x100/0x184
> [   85.018981]        [] vfs_write+0xb4/0x148
> [   85.018981]        [] sys_write+0x40/0x70
> [   85.018981]        [] ret_fast_syscall+0x0/0x3c
> [   85.035003]
> [   85.035003] -> #0 (sysfs_lock){+.+.+.}:
> [   85.035003]        [] check_prev_add+0x680/0x698
> [   85.035003]        [] check_prevs_add+0xdc/0x150
> [   85.052093]        [] validate_chain.clone.24+0x564/0x694
> [   85.052093]        [] __lock_acquire+0x49c/0x980
> [   85.052093]        [] lock_acquire+0x98/0x100
> [   85.069885]        [] mutex_lock_nested+0x3c/0x2f4
> [   85.069885]        [] gpio_value_store+0x24/0xcc
> [   85.069885]        [] dev_attr_store+0x18/0x24
> [   85.087158]        [] sysfs_write_file+0x100/0x184
> [   85.087158]        [] vfs_write+0xb4/0x148
> [   85.098297]        [] sys_write+0x40/0x70
> [   85.098297]        [] ret_fast_syscall+0x0/0x3c
> [   85.109069]
> [   85.109069] other info that might help us debug this:
> [   85.109069]
> [   85.117462]  Possible unsafe locking scenario:
> [   85.117462]
> [   85.117462]        CPU0                    CPU1
> [   85.128417]                            
> [   85.128417]   lock(s_active#22);
> [   85.128417]                                lock(sysfs_lock);
> [   85.128417]                                lock(s_active#22);
> [   85.142486]   lock(sysfs_lock);
> [   85.151794]
> [   85.151794]  *** DEADLOCK ***
> [   85.151794]
> [   85.151794] 2 locks held by bash/949:
> [   85.158020]  #0:  (>mutex){+.+.+.}, at: [] 
> sysfs_write_file+0x28/0x184
> [   85.170349]  #1:  (s_active#22){.+}, at: [] 
> sysfs_write_file+0xdc/0x184
> [   85.170349]
> [   85.178588] stack backtrace:
> [   85.178588] [] (unwind_backtrace+0x0/0xf0) from [] 
> (print_circular_bug+0x100/0x114)
> [   85.193023] [] (print_circular_bug+0x100/0x114) from 
> [] (check_prev_add+0x680/0x698)
> [   85.193023] [] (check_prev_add+0x680/0x698) from [] 
> (check_prevs_add+0xdc/0x150)
> [   85.212524] [] (check_prevs_add+0xdc/0x150) from [] 
> (validate_chain.clone.24+0x564/0x694)
> [   85.212524] [] (validate_chain.clone.24+0x564/0x694) from 
> [] (__lock_acquire+0x49c/0x980)
> [   85.233306] [] (__lock_acquire+0x49c/0x980) from [] 
> (lock_acquire+0x98/0x100)
> [   85.233306] [] (lock_acquire+0x98/0x100) from [] 
> (mutex_lock_nested+0x3c/0x2f4)
> [   85.242614] [] (mutex_lock_nested+0x3c/0x2f4) from [] 
> (gpio_value_store+0x24/0xcc)
> [   85.261840] [] (gpio_value_store+0x24/0xcc) from [] 
> (dev_attr_store+0x18/0x24)
> [   85.261840] [] (dev_attr_store+0x18/0x24) from [] 
> (sysfs_write_file+0x100/0x184)
> [   85.271240] [] (sysfs_write_file+0x100/0x184) from [] 
> (vfs_write+0xb4/0x148)
> [   85.290008] [] (vfs_write+0xb4/0x148) from [] 
> (sys_write+0x40/0x70)
> [   85.298400] [] (sys_write+0x40/0x70) from [] 
> (ret_fast_syscall+0x0/0x3c)
> -bash: echo: write error: Operation not permitted
>
> the way to trigger is:
>
> root@legolas:~# cd /sys/class/gpio/
> root@legolas:/sys/class/gpio# echo 2 > export
> root@legolas:/sys/class/gpio# echo 2 > unexport
> root@legolas:/sys/class/gpio# echo 2 > export
> root@legolas:/sys/class/gpio# cd gpio2/

[PATCH 3.2 115/152] Fix circular locking dependency (3.3-rc2)

2015-02-16 Thread Ben Hutchings
3.2.67-rc1 review patch.  If anyone has any objections, please let me know.

--

From: Ming Lei tom.leim...@gmail.com

commit 864533ceb6db336dead389577c102a8b792a121a upstream.

Hi,

On Wed, Feb 8, 2012 at 8:41 PM, Felipe Balbi ba...@ti.com wrote:
 Hi guys,

 I have just triggered the folllowing:

 [   84.860321] ==
 [   84.860321] [ INFO: possible circular locking dependency detected ]
 [   84.860321] 3.3.0-rc2-00026-ge4e8a39 #474 Not tainted
 [   84.860321] ---
 [   84.860321] bash/949 is trying to acquire lock:
 [   84.860321]  (sysfs_lock){+.+.+.}, at: [c0275358] 
 gpio_value_store+0x24/0xcc
 [   84.860321]
 [   84.860321] but task is already holding lock:
 [   84.860321]  (s_active#22){.+}, at: [c016996c] 
 sysfs_write_file+0xdc/0x184
 [   84.911468]
 [   84.911468] which lock already depends on the new lock.
 [   84.911468]
 [   84.920043]
 [   84.920043] the existing dependency chain (in reverse order) is:
 [   84.920043]
 [   84.927886] - #1 (s_active#22){.+}:
 [   84.927886]        [c008f640] check_prevs_add+0xdc/0x150
 [   84.927886]        [c008fc18] validate_chain.clone.24+0x564/0x694
 [   84.927886]        [c0090cdc] __lock_acquire+0x49c/0x980
 [   84.951660]        [c0091838] lock_acquire+0x98/0x100
 [   84.951660]        [c016a8e8] sysfs_deactivate+0xb0/0x100
 [   84.962982]        [c016b1b4] sysfs_addrm_finish+0x2c/0x6c
 [   84.962982]        [c016b8bc] sysfs_remove_dir+0x84/0x98
 [   84.962982]        [c02590d8] kobject_del+0x10/0x78
 [   84.974670]        [c02c29e8] device_del+0x140/0x170
 [   84.974670]        [c02c2a24] device_unregister+0xc/0x18
 [   84.985382]        [c0276894] gpio_unexport+0xbc/0xdc
 [   84.985382]        [c02768c8] gpio_free+0x14/0xfc
 [   85.001708]        [c0276a28] unexport_store+0x78/0x8c
 [   85.001708]        [c02c5af8] class_attr_store+0x18/0x24
 [   85.007293]        [c0169990] sysfs_write_file+0x100/0x184
 [   85.018981]        [c0109d48] vfs_write+0xb4/0x148
 [   85.018981]        [c0109fd0] sys_write+0x40/0x70
 [   85.018981]        [c0013cc0] ret_fast_syscall+0x0/0x3c
 [   85.035003]
 [   85.035003] - #0 (sysfs_lock){+.+.+.}:
 [   85.035003]        [c008f54c] check_prev_add+0x680/0x698
 [   85.035003]        [c008f640] check_prevs_add+0xdc/0x150
 [   85.052093]        [c008fc18] validate_chain.clone.24+0x564/0x694
 [   85.052093]        [c0090cdc] __lock_acquire+0x49c/0x980
 [   85.052093]        [c0091838] lock_acquire+0x98/0x100
 [   85.069885]        [c047e280] mutex_lock_nested+0x3c/0x2f4
 [   85.069885]        [c0275358] gpio_value_store+0x24/0xcc
 [   85.069885]        [c02c18dc] dev_attr_store+0x18/0x24
 [   85.087158]        [c0169990] sysfs_write_file+0x100/0x184
 [   85.087158]        [c0109d48] vfs_write+0xb4/0x148
 [   85.098297]        [c0109fd0] sys_write+0x40/0x70
 [   85.098297]        [c0013cc0] ret_fast_syscall+0x0/0x3c
 [   85.109069]
 [   85.109069] other info that might help us debug this:
 [   85.109069]
 [   85.117462]  Possible unsafe locking scenario:
 [   85.117462]
 [   85.117462]        CPU0                    CPU1
 [   85.128417]                            
 [   85.128417]   lock(s_active#22);
 [   85.128417]                                lock(sysfs_lock);
 [   85.128417]                                lock(s_active#22);
 [   85.142486]   lock(sysfs_lock);
 [   85.151794]
 [   85.151794]  *** DEADLOCK ***
 [   85.151794]
 [   85.151794] 2 locks held by bash/949:
 [   85.158020]  #0:  (buffer-mutex){+.+.+.}, at: [c01698b8] 
 sysfs_write_file+0x28/0x184
 [   85.170349]  #1:  (s_active#22){.+}, at: [c016996c] 
 sysfs_write_file+0xdc/0x184
 [   85.170349]
 [   85.178588] stack backtrace:
 [   85.178588] [c001b824] (unwind_backtrace+0x0/0xf0) from [c008de64] 
 (print_circular_bug+0x100/0x114)
 [   85.193023] [c008de64] (print_circular_bug+0x100/0x114) from 
 [c008f54c] (check_prev_add+0x680/0x698)
 [   85.193023] [c008f54c] (check_prev_add+0x680/0x698) from [c008f640] 
 (check_prevs_add+0xdc/0x150)
 [   85.212524] [c008f640] (check_prevs_add+0xdc/0x150) from [c008fc18] 
 (validate_chain.clone.24+0x564/0x694)
 [   85.212524] [c008fc18] (validate_chain.clone.24+0x564/0x694) from 
 [c0090cdc] (__lock_acquire+0x49c/0x980)
 [   85.233306] [c0090cdc] (__lock_acquire+0x49c/0x980) from [c0091838] 
 (lock_acquire+0x98/0x100)
 [   85.233306] [c0091838] (lock_acquire+0x98/0x100) from [c047e280] 
 (mutex_lock_nested+0x3c/0x2f4)
 [   85.242614] [c047e280] (mutex_lock_nested+0x3c/0x2f4) from [c0275358] 
 (gpio_value_store+0x24/0xcc)
 [   85.261840] [c0275358] (gpio_value_store+0x24/0xcc) from [c02c18dc] 
 (dev_attr_store+0x18/0x24)
 [   85.261840] [c02c18dc] (dev_attr_store+0x18/0x24) from [c0169990] 
 (sysfs_write_file+0x100/0x184)
 [   85.271240] [c0169990] (sysfs_write_file+0x100/0x184) from [c0109d48] 
 (vfs_write+0xb4/0x148)
 [   85.290008] [c0109d48] (vfs_write+0xb4/0x148) from [c0109fd0]