Re: [RFC] IRQ handlers run with some high-priority interrupts(not NMI) enabled on some platform

[Geert Uytterhoeven]

Hi Arnd,

On Thu, Feb 18, 2021 at 12:20 PM Arnd Bergmann <arnd@xxxxxxxxxx> wrote:
> Most of these are normal short-lived interrupts that only transfer
> a few bytes or schedule deferred processing of some sort.
> Most of the scsi and network drivers process the data in
> a softirq, so those are generally fine here, but I do see that 8390
> (ne2000) ethernet and the drivers/ide drivers do transfer their
> data in hardirq context.

The reason drivers/ide is doing that may be related to IDE hard drive
quirks.  The old WD Caviar drives didn't obey disabling the IDE interrupt
at the drive level.  On PC, that worked fine, as IRQs 14 and 15 weren't
shared with other devices.  On systems with shared interrupts, that
broke badly, and led to an interrupt storm.

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@xxxxxxxxxxxxxx

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds