Re: [PATCH, i386]: Fix PR 59432, sync/atomic FAILs on 32bit x86 systems without .cfi directives

2014-10-16 Thread Uros Bizjak
On Thu, Oct 16, 2014 at 11:06 AM, Andi Kleen wrote: >> Now that %ebx is no more fixed, we can remove all PIC related >> complications in atomic_compare_and_swap_doubleword pattern. The >> immediate consequence is, that we avoid "hidden" xchgs that clobbered >> unwinding state. > > Could also do t

Re: [PATCH, i386]: Fix PR 59432, sync/atomic FAILs on 32bit x86 systems without .cfi directives

2014-10-16 Thread Andi Kleen
Uros Bizjak writes: > Hello! > > Now that %ebx is no more fixed, we can remove all PIC related > complications in atomic_compare_and_swap_doubleword pattern. The > immediate consequence is, that we avoid "hidden" xchgs that clobbered > unwinding state. Could also do the same in cpuid.h now -And

[PATCH, i386]: Fix PR 59432, sync/atomic FAILs on 32bit x86 systems without .cfi directives

2014-10-15 Thread Uros Bizjak
Hello! Now that %ebx is no more fixed, we can remove all PIC related complications in atomic_compare_and_swap_doubleword pattern. The immediate consequence is, that we avoid "hidden" xchgs that clobbered unwinding state. Earlier fix by Ian [1] partly solved this issue using various .cfi directive