Re: The SMP alternatives code breaks exception fixup?

[Chuck Ebbert <cebbert@redhat.com>]

On 01/21/2008 03:47 PM, Chuck Ebbert wrote:
> Looking at the oops report from this bug:
> 
> [bugzilla]  https://bugzilla.redhat.com/show_bug.cgi?id=429412
> [oops]      https://bugzilla.redhat.com/attachment.cgi?id=292260
> 
> It was an unhandled page fault (protection violation.)
> 
> I tracked it down to the cmpxchg in this code:
> 
> include/asm-x86/futex_32.h::futex_atomic_cmpxchg_inatomic()
>          __asm__ __volatile__(
>                  "1:     " LOCK_PREFIX "cmpxchgl %3, %1          \n"
>                  "2:     .section .fixup, \"ax\"                 \n"
>                  "3:     mov     %2, %0                          \n"
>                  "       jmp     2b                              \n"
>                  "       .previous                               \n"
>                  "       .section __ex_table, \"a\"              \n"
>                  "       .align  8                               \n"
>                  "       .long   1b,3b                           \n"
>                  "       .previous                               \n"
> 
> There is a fixup, so this should never happen. But the lock instruction
> was replaced with a nop by the altinstruction code, and that makes the fixup
> address wrong. AFAICT we don't fix up the exception table when we replace
> a lock with a nop, which makes the fixup table point to the nop instead
> of the cmpxchg instruction and causes us to miss the fixup.
> 

The bug reporter has confirmed that booting with "noreplace-smp" prevents
the kernel oops.