Re: [RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-19 Thread Sergey Senozhatsky
Hello, On (12/19/16 11:20), Peter Zijlstra wrote: > On Sun, Dec 18, 2016 at 01:19:11AM +0900, Sergey Senozhatsky wrote: > > There is a race window between the point when __spin_lock_debug() > > detects spinlock lockup and the time when CPU that caused the > > lockup receives its backtrace

Re: [RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-19 Thread Sergey Senozhatsky
Hello, On (12/19/16 11:20), Peter Zijlstra wrote: > On Sun, Dec 18, 2016 at 01:19:11AM +0900, Sergey Senozhatsky wrote: > > There is a race window between the point when __spin_lock_debug() > > detects spinlock lockup and the time when CPU that caused the > > lockup receives its backtrace

Re: [RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-19 Thread Peter Zijlstra
On Sun, Dec 18, 2016 at 01:19:11AM +0900, Sergey Senozhatsky wrote: > There is a race window between the point when __spin_lock_debug() > detects spinlock lockup and the time when CPU that caused the > lockup receives its backtrace interrupt. > > Before __spin_lock_debug() triggers

Re: [RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-19 Thread Peter Zijlstra
On Sun, Dec 18, 2016 at 01:19:11AM +0900, Sergey Senozhatsky wrote: > There is a race window between the point when __spin_lock_debug() > detects spinlock lockup and the time when CPU that caused the > lockup receives its backtrace interrupt. > > Before __spin_lock_debug() triggers

[RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-17 Thread Sergey Senozhatsky
There is a race window between the point when __spin_lock_debug() detects spinlock lockup and the time when CPU that caused the lockup receives its backtrace interrupt. Before __spin_lock_debug() triggers all_cpu_backtrace() it calls spin_dump() to printk() the current state of the lock and CPU

[RFC][PATCH] spinlock_debug: report spinlock lockup from unlock

2016-12-17 Thread Sergey Senozhatsky
There is a race window between the point when __spin_lock_debug() detects spinlock lockup and the time when CPU that caused the lockup receives its backtrace interrupt. Before __spin_lock_debug() triggers all_cpu_backtrace() it calls spin_dump() to printk() the current state of the lock and CPU