Re: cgroup trace events acquire sleeping locks

2018-07-10 Thread Steven Rostedt
On Tue, 10 Jul 2018 11:26:35 +0200 Peter Zijlstra wrote: > > Hmm, good question. I could possibly make all the tracepoint code into > > its own section. And then look to see if any spin locks exist in them. > > That wouldn't be too trivial to implement though. > > pick a bit from the

Re: cgroup trace events acquire sleeping locks

2018-07-10 Thread Steven Rostedt
On Tue, 10 Jul 2018 11:26:35 +0200 Peter Zijlstra wrote: > > Hmm, good question. I could possibly make all the tracepoint code into > > its own section. And then look to see if any spin locks exist in them. > > That wouldn't be too trivial to implement though. > > pick a bit from the

Re: cgroup trace events acquire sleeping locks

2018-07-10 Thread Peter Zijlstra
On Mon, Jul 09, 2018 at 04:30:10PM -0400, Steven Rostedt wrote: > On Mon, 9 Jul 2018 22:22:15 +0200 > Sebastian Andrzej Siewior wrote: > > > On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > > > trace event

Re: cgroup trace events acquire sleeping locks

2018-07-10 Thread Peter Zijlstra
On Mon, Jul 09, 2018 at 04:30:10PM -0400, Steven Rostedt wrote: > On Mon, 9 Jul 2018 22:22:15 +0200 > Sebastian Andrzej Siewior wrote: > > > On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > > > trace event

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Steven Rostedt
On Mon, 9 Jul 2018 22:22:15 +0200 Sebastian Andrzej Siewior wrote: > On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > > trace event invokes cgroup_path() which acquires a spin_lock_t and this > > > is invoked

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Steven Rostedt
On Mon, 9 Jul 2018 22:22:15 +0200 Sebastian Andrzej Siewior wrote: > On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > > trace event invokes cgroup_path() which acquires a spin_lock_t and this > > > is invoked

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Sebastian Andrzej Siewior
On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > trace event invokes cgroup_path() which acquires a spin_lock_t and this > > is invoked within a preempt_disable()ed section. > > Correct. And I wish no trace event

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Sebastian Andrzej Siewior
On 2018-07-09 15:01:54 [-0400], Steven Rostedt wrote: > > which is the trace_cgroup_rmdir() trace event in cgroup_rmdir(). The > > trace event invokes cgroup_path() which acquires a spin_lock_t and this > > is invoked within a preempt_disable()ed section. > > Correct. And I wish no trace event

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Steven Rostedt
On Mon, 9 Jul 2018 18:38:05 +0200 Sebastian Andrzej Siewior wrote: > Clark showed me this: > > | BUG: sleeping function called from invalid context at > kernel/locking/rtmutex.c:974 > | in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: systemd > | 5 locks held by systemd/1: > | #0:

Re: cgroup trace events acquire sleeping locks

2018-07-09 Thread Steven Rostedt
On Mon, 9 Jul 2018 18:38:05 +0200 Sebastian Andrzej Siewior wrote: > Clark showed me this: > > | BUG: sleeping function called from invalid context at > kernel/locking/rtmutex.c:974 > | in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: systemd > | 5 locks held by systemd/1: > | #0:

cgroup trace events acquire sleeping locks

2018-07-09 Thread Sebastian Andrzej Siewior
Clark showed me this: | BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:974 | in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: systemd | 5 locks held by systemd/1: | #0: (sb_writers#7){.+.+}, at: [<(ptrval)>] mnt_want_write+0x1f/0x50 | #1:

cgroup trace events acquire sleeping locks

2018-07-09 Thread Sebastian Andrzej Siewior
Clark showed me this: | BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:974 | in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: systemd | 5 locks held by systemd/1: | #0: (sb_writers#7){.+.+}, at: [<(ptrval)>] mnt_want_write+0x1f/0x50 | #1: