They do not address the same problem. I can not see that flush_icache_all is modified, so this will not solve our problem. This patch will only minimize the effect.
Ulrich Mit freundlichen Grüßen / Kind regards Dipl.-Ing. (FH) Ulrich Wulff Senior Software Developer kumkeo GmbH Heidenkampsweg 82a 20097 Hamburg Germany T: +49 40 2846761-0 F: +49 40 2846761-99 [email protected] www.kumkeo.de Amtsgericht Hamburg / Hamburg District Court, HRB 108558 Geschäftsführer / Managing Director: Dipl.-Ing. Bernd Sager; Dipl.-Ing. Sven Tanneberger, MBA -----Ursprüngliche Nachricht----- Von: Oliver Schwartz <[email protected]> Gesendet: Freitag, 2. Juni 2023 11:05 An: Sebastian Andrzej Siewior <[email protected]> Cc: [email protected]; Jan Kiszka <[email protected]>; Martin Kaistra <[email protected]>; Ulrich Wulff <[email protected]> Betreff: [Extern] Re: [RFC PATCH 0/4] arm64: Limit cache invalidate to local CPU. > The problem is the cache flush/ invalidation which is performed > locally and signal to the other CPUs in the same cacheable domain. > This is required on SMP systems where the memory is shared between > CPUs but can be omitted in setup where each CPU has exclusive memory. You might want to take a look at the patches in this thread: https://lore.kernel.org/linux-arm-kernel/[email protected]/t/#u They address the same problem but offer a kernel-only solution (rough summary: tlbi broadcast instructions are only issued if more than one CPU is online in Linux). The obvious advantage is that it doesn’t rely on the cooperation of Linux and the hypervisor. There may even be a chance that they make it into mainline. Oliver -- You received this message because you are subscribed to the Google Groups "Jailhouse" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/jailhouse-dev/a31396bb7a77423097daa430eb011f6e%40kumkeo.de.
