#
✕ nick:amonakov
#asahi · 2021-04-05 06:54
amonakovI believe he did the work on OS X
#asahi · 2021-04-05 06:51
amonakovJaehyuk[m]: Dougal Johnson was using the counters to study the microarchitecture: https://dougallj.github.io/applecpu/firestorm.html
#asahi · 2021-03-24 18:09
amonakov(slander, libel, etc., were criminal acts long before the Internet)
#asahi · 2021-03-24 17:59
amonakoveta: also, their previous message seems to bring up the paradox of tolerance in pretty much its pure form?
#asahi · 2021-03-11 13:54
amonakovmaz|: alright, then perhaps I was not too off base with my initial understanding. thank you
#asahi · 2021-03-11 13:18
amonakovI couldn't find any explanation as to why local_irq_save is sufficient in that context (apart from "netconsole in those drivers is unsafe on SMP")
#asahi · 2021-03-11 13:18
amonakovthe issue is, some drivers do disable_irq/enable_irq (which is fine), but other drivers do local_irq_save/restore, which looks quite suspicious as it wouldn't do anything to prevent the handler running on another CPU as a result of a hardware interrupt
#asahi · 2021-03-11 13:18
amonakovmaz|: for netconsole, drivers implement "ndo_poll_controller" callback which in many cases is implemented as invoking the device's interrupt handler, bracketed by interrupt disable-enable
#asahi · 2021-03-11 13:06
amonakovmaz|: thank you, this helps, but unfortunately doesn't answer my Real Question about interrupt disabling for netconsole (from the link)
#asahi · 2021-03-11 12:43
amonakovafaict it is not covered in the usual books and docs. details and context of my curiousity: https://lore.kernel.org/netdev/alpine.LNX.2.20.13.1802012234510.5946@monopod.intra.ispras.ru/T/
#asahi · 2021-03-11 12:43
amonakovhi folks. I wonder if someone could enlighten me about interrupt handling conventions on Linux: is there some mechanism that would prevent invoking a handler while it is in progress on another CPU for a previous interrupt from the same device?