Question about dec_lock_cnt method in Context class
ryx at gwmail.gwu.edu
Mon Sep 8 17:54:32 CEST 2014
Unfortunately this modification does not help.
I have a question about the switch_lock code.
bool have_no_locks = o->_lock_cnt < 1;
assert_kdb (current_cpu() == o->home_cpu());
if (EXPECT_TRUE(mp_cas(&o->_running_under_lock, Mword(false),
In which case, the variable "_running_under_lock" is set to true but the
lock_cnt is 0?
Now in my test, the kernel goes into this dead loop.
I cannot figure out how to solve this problem.
Thank you very much.
On Sun, Aug 31, 2014 at 5:58 PM, Adam Lackorzynski <
adam at os.inf.tu-dresden.de> wrote:
> On Fri Aug 29, 2014 at 13:46:38 -0400, Yuxin Ren wrote:
> > I have some further understanding about the code.
> > If thread A can go back to its home cpu(core 1), this means it is not
> > running on the core 2.
> > And when A release its lock, it will switch to its helper.
> > During the context switch from thread A to its helper on core 2, the "
> > _running_under_lock"
> > of thread A should be set to false. Thus thread A is able to continue to
> > run on its home cpu.
> > I think this logic has no problem. But I observed a thread going into
> > the infinite loop in Switch_lock::set_lock_owner method.
> > in my test program.
> > Because of inappropriate memory barrier, or anything else?
> > On Wed, Aug 27, 2014 at 2:28 PM, Yuxin Ren <ryx at gwmail.gwu.edu> wrote:
> > > I have a question about the dec_lock_cnt method in Context class under
> > > multiple processor.
> > > In its implementation, it checks if thread's home cpu is equal to
> > > cpu.
> > > If not, it does not unset "_running_under_lock" variable, even if the
> > > _lock_cnt is 0.
> > > Why does it check if home cpu is equal to current cpu?
> This one should work better:
> int n = _lock_cnt - 1;
> write_now(&_lock_cnt, n);
> if (EXPECT_TRUE(!n && home_cpu() == current_cpu()))
> write_now(&_running_under_lock, Mword(false));
> Adam adam at os.inf.tu-dresden.de
> Lackorzynski http://os.inf.tu-dresden.de/~adam/
> l4-hackers mailing list
> l4-hackers at os.inf.tu-dresden.de
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the l4-hackers