Re: [PATCH v9 2/3] x86/mce: Add per-bank CMCI storm mitigation

From: Yazen Ghannam
Date: Tue Nov 28 2023 - 10:32:18 EST


On 11/27/2023 7:42 PM, Tony Luck wrote:
On Mon, Nov 27, 2023 at 12:14:28PM -0800, Tony Luck wrote:
On Mon, Nov 27, 2023 at 11:50:26AM -0800, Tony Luck wrote:
On Tue, Nov 21, 2023 at 12:54:48PM +0100, Borislav Petkov wrote:
On Tue, Nov 14, 2023 at 02:04:46PM -0800, Tony Luck wrote:
But it isn't doing the same thing. The timer calls:

machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));

and cmci_mc_poll_banks() calls:

machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));

machine_check_poll(0, this_cpu_ptr(&mce_banks_owned));


Bah ... I've cut & pasted the same thing ... but I think there
are separate bit maps ... maybe I'm wrong. Will go back and
look again.


This mutually exclusive behavior is not enforced on AMD systems. A bank can be polled and signaled using hardware interrupts.

I've been thinking to change this in order to save polling cycles. Now it seems there's another reason. :)

Thanks,
Yazen