On 2014-07-07 09:46, Daniel Cederman wrote:
Probably true. I could change rtems_cache_invalidate_entire_instruction_cpu_set(set) to rtems_cache_invalidate_entire_instruction_all_processors() instead. Or make the original rtems_cache_invalidate_entire_instruction() notify all processors when running SMP, but I guess that could be dangerous.
I would simply keep this rtems_cache_invalidate_entire_instruction() and add not additional function. What can be dangerous here? This SMP cache message stuff should be optional in the cache manager implementation (e.g. similar to CPU_CACHE_SUPPORT_PROVIDES_RANGE_FUNCTIONS) since on decent SMP processors the hardware will ensure this automatically.
-- Sebastian Huber, embedded brains GmbH Address : Dornierstr. 4, D-82178 Puchheim, Germany Phone : +49 89 189 47 41-16 Fax : +49 89 189 47 41-09 E-Mail : sebastian.hu...@embedded-brains.de PGP : Public key available on request. Diese Nachricht ist keine geschäftliche Mitteilung im Sinne des EHUG. _______________________________________________ devel mailing list devel@rtems.org http://lists.rtems.org/mailman/listinfo/devel
