Content-Type: multipart/mixed; boundary="===============0975338151210500471==" MIME-Version: 1.0 From: Oleg Nesterov To: lkp@lists.01.org Subject: Re: [rfcomm_run] WARNING: CPU: 1 PID: 79 at kernel/sched/core.c:7156 __might_sleep() Date: Mon, 06 Oct 2014 16:24:07 +0000 Message-ID: <20141006162109.GA29890@redhat.com> In-Reply-To: <20141006091915.GC6758@twins.programming.kicks-ass.net> List-Id: --===============0975338151210500471== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On 10/06, Peter Zijlstra wrote: > > On Mon, Oct 06, 2014 at 02:25:09AM +0200, Oleg Nesterov wrote: > > > > Hmm. I specially checked Documentation/memory-barriers.txt, > > > > (*) smp_mb__before_atomic(); > > (*) smp_mb__after_atomic(); > > > > These are for use with atomic (such as add, subtract, increment and > > decrement) functions that don't return a value, especially when us= ed for > > reference counting. These functions do not imply memory barriers. > > > > These are also used for atomic bitop functions that do not return a > > value (such as set_bit and clear_bit). > > ^^^^^^^^^^^^^^^^^^^^^ > > > > Either you or memory-barriers.txt should be fixed ;) Heh. > Its in there, just not explicitly. All those functions listed are > read-modify-write ops, test_bit() is not, its just a read. OOPS! I was hypnotized by "_bit" suffix, I guess. Of course, of course, test_bit() must be a plain LOAD in any case, can't understand what I was thinking about. So in this particular case kthread_kill() needs smp_mb__AFTER_atomic(), and "after" applies to set_bit(KTHREAD_SHOULD_STOP). > --- a/Documentation/memory-barriers.txt > +++ b/Documentation/memory-barriers.txt > @@ -1594,12 +1594,9 @@ CPU from reordering them. > (*) smp_mb__before_atomic(); > (*) smp_mb__after_atomic(); > > - These are for use with atomic (such as add, subtract, increment and > - decrement) functions that don't return a value, especially when use= d for > - reference counting. These functions do not imply memory barriers. > - > - These are also used for atomic bitop functions that do not return a > - value (such as set_bit and clear_bit). > + These are for use with atomic/bitop (r-m-w) functions that don't re= turn > + a value (eg. atomic_{add,sub,inc,dec}(), {set,clear}_bit()). These > + functions do not imply memory barriers. Thanks! Oleg. --===============0975338151210500471==--