kernel.org, VMware Inc <[email protected]>, 
[email protected], [email protected], 
[email protected], Arnd Bergmann <[email protected]>, 
[email protected], [email protected], [email protected], 
[email protected], [email protected], [email protected], Borislav 
Petkov <[email protected]>, [email protected], [email protected], 
[email protected], [email protected], [email protected], 
[email protected], [email protected], [email protected], 
[email protected], [email protected], [email protected], "H. Peter 
Anvin" <[email protected]>, [email protected], 
[email protected], [email protected], Isaku Yamahata 
<[email protected]>, [email protected], 
[email protected], [email protected], Richard Weinberger <[email protected]>, 
X86 ML <[email protected]>, [email protected], Ingo Molnar 
<[email protected]>, Albert Ou <[email protected]>, paulmck@ker
 nel.org, [email protected], [email protected], 
[email protected], Paul Walmsley <[email protected]>, 
[email protected], Namhyung Kim <[email protected]>, Andy 
Shevchenko <[email protected]>, [email protected], Juergen 
Gross <[email protected]>, [email protected], [email protected], Palmer 
Dabbelt <[email protected]>, Anup Patel <[email protected]>, 
[email protected], Johannes Berg <[email protected]>, 
[email protected]
Errors-To: [email protected]
Sender: "Linuxppc-dev" 
<[email protected]>

On Wed, Jun 8, 2022 at 10:48 PM Peter Zijlstra <[email protected]> wrote:
>
> Now that arch_cpu_idle() is expected to return with IRQs disabled,
> avoid the useless STI/CLI dance.
>
> Per the specs this is supposed to work, but nobody has yet relied up
> this behaviour so broken implementations are possible.

I'm totally newbie here.

The point of safe_halt() is that STI must be used and be used
directly before HLT to enable IRQ during the halting and stop
the halting if there is any IRQ.

In TDX case, STI must be used directly before the hypercall.
Otherwise, no IRQ can come and the vcpu would be stalled forever.

Although the hypercall has an "irq_disabled" argument.
But the hypervisor doesn't (and can't) touch the IRQ flags no matter
what the "irq_disabled" argument is.  The IRQ is not enabled during
the halting if the IRQ is disabled before the hypercall even if
irq_disabled=false.

The "irq_disabled" argument is used for workaround purposes:
https://lore.kernel.org/kvm/c020ee0b90c424a7010e979c9b32a28e9c488a51.1651774251.git.isaku.yamah...@intel.com/

Hope my immature/incorrect reply elicits a real response from
others.

Thanks
Lai

Reply via email to