On 12.03.2024 17:38, Krystian Hebel wrote: > On 8.02.2024 13:13, Jan Beulich wrote: >> On 14.11.2023 18:50, Krystian Hebel wrote: >>> @@ -320,6 +317,10 @@ void start_secondary(unsigned int cpu) >>> >>> /* Critical region without IDT or TSS. Any fault is deadly! */ >>> >>> + /* Wait until data set up by CPU_UP_PREPARE notifiers is ready. */ >>> + while ( cpu_data[cpu].cpu_state != CPU_STATE_CALLOUT ) >>> + cpu_relax(); >> I'm afraid I don't understand the comment (and hence whether this loop >> is actually needed here): __cpu_up() is called only after those >> notifiers completed. > Yes, but broadcasted INIT-SIPI-SIPI sequence added in next patch will be > sent before that call is made, and consequently APs potentially can get > to this point before that data is set up.
That's fine, and I was able to conclude this once having read that following patch. But the patch here, including its description, wants to the self- contained. Jan
