Re: [PATCH -next v4 2/3] x86/mce: rename MCE_IN_KERNEL_COPYIN to MCE_IN_KERNEL_COPY_MC

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Fri, Feb 02, 2024 at 06:44:32PM +0000, Luck, Tony wrote:
> At least on Intel you can only get a machine check for operation on poison data LOAD.
> Not for a STORE. I believe that is generally true - other arches to confirm.

So what happens if you store to a poisoned cacheline on Intel? It'll
raise a poison consumption error when that cacheline is loaded in the
cache? Because you need to load that line into the cache for writing,
I'd presume...

What happens if you have bits flipped in the cacheline you want to write
to?

That's fine because you're overwriting them anyway?

I'd presume ECC check gets performed on cacheline load and then you'll
have to raise an #MC...

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette




[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux