This is the mail archive of the libstdc++@gcc.gnu.org mailing list for the libstdc++ project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH] Optimized __cxa_guard_{acquire,release,abort} for Linux

Jakub Jelinek wrote: 
We could do a non-atomic store I guess (provided __cxa_abort is never
called by mistake when the the var has been initialized already and
the first byte set), but then we'd need to do an unconditional
FUTEX_WAKE.  I guess we could use instead __sync_lock_test_and_set
aka. atimic exchange, to atomically swap in 0 and read previous value
to see if we need FUTEX_WAKE or not.  The unconditional FUTEX_WAKE
is IMHO more costly than __sync_lock_test_and_set and conditional
FUTEX_WAKE.

Good point, I think you're right. I still don't see why you need the loop, however; I don't see any way oldv can != old. The only thing other threads can do is add waiting_bit; once we've established that waiting_bit is set what could cause the second compare_and_swap to fail?

Jason

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]