Would an asm clobber of GPR13 in the schedule routines (or a wrapper for them, or whatever) work?No. The address is cse'd symbolically long before the r13 reference is exposed.
Current GCC won't ever do that over a (non-local, non-inlinable) function call though. _Current_ GCC. Segher - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
- References:
- [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: Paul Mackerras <[email protected]>
- Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: Richard Henderson <[email protected]>
- Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: "David S. Miller" <[email protected]>
- Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: Paul Mackerras <[email protected]>
- Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: Segher Boessenkool <[email protected]>
- Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- From: Richard Henderson <[email protected]>
- [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- Prev by Date: Re: [dm-crypt] dm-crypt is broken and causes massive data corruption
- Next by Date: Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- Previous by thread: Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- Next by thread: Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
- Index(es):
 |