This is the mail archive of the libc-hacker@sources.redhat.com mailing list for the glibc project.

Note that libc-hacker is a closed list. You may look at the archives of this list, but subscription and posting are not open.

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: lll_lock on PPC

From: Steve Munroe <sjmunroe at us dot ibm dot com>
To: Thorsten Kukuk <kukuk at suse dot de>
Cc: libc-hacker at sources dot redhat dot com
Date: Tue, 22 Jun 2004 16:13:13 -0500
Subject: Re: lll_lock on PPC

Thorsten Kukuk <kukuk@suse.de> wrote on 06/22/2004 02:35:04 PM:

> 
> Hi,
> 
> if I look at the lll_lock implementation on ix86 and PPC, it seems
> to me, that on ix86, lll_lock will only call lll_mutex_lock, if
> the program is linked against libpthread. But on PPC, lll_lock is
> always called, which can lead to a deadlock.
> 
> Is this correct?

For POWER lll_mutex_lock is a inline macro using 
atomic_compare_and_exchange_val_acq. lll_lock is just an alias for 
lll_mutex_lock:

        #define lll_lock(lock)          lll_mutex_lock (lock)

There is no call. See 
libc/nptl/sysdeps/unix/sysv/linux/powerpc/lowlevellock.h

Steven J. Munroe
Linux on Power Toolchain Architect
IBM Corporation, Linux Technology Center

References:
- lll_lock on PPC
  - From: Thorsten Kukuk

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