Re: [PATCH v10 6/6] x86/split_lock: Enable split lock detection by kernel parameter

[Andy Lutomirski]

> On Nov 21, 2019, at 11:56 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> 
> ïOn Thu, Nov 21, 2019 at 09:51:03AM -0800, Andy Lutomirski wrote:
> 
>> Can we really not just change the lock asm to use 32-bit accesses for
>> set_bit(), etc?  Sure, it will fail if the bit index is greater than
>> 2^32, but that seems nuts.
> 
> There are 64bit architectures that do exactly that: Alpha, IA64.
> 
> And because of the byte 'optimization' from x86 we already could not
> rely on word atomicity (we actually play games with multi-bit atomicity
> for PG_waiters and clear_bit_unlock_is_negative_byte).

I read a couple pages of the paper you linked and I didnât spot what youâre talking about as it refers to x86.  What are the relevant word properties of x86 bitops or the byte optimization?