Excessive TLB flush ranges

[Nadav Amit]

> On May 15, 2023, at 9:43 AM, Thomas Gleixner <tglx at linutronix.de> wrote:
> 
> 
> So while ARM32, CSKY, NIOS, PPC (some variants), _should_ arguably have
> a fallback to tlb_flush_all() when the range is too large, there is
> another issue. I've seen a couple of instances where _vm_unmap_aliases()
> collects one page and the actual va list has only 2 pages, which might
> be eventually worth to flush one by one.
> 
> I'm not sure whether that's worth it as checking for those gaps might be
> too expensive for the case where a large number of va entries needs to
> be flushed.

I know you were cc’d, but for the record, here's a related discussion:

https://lore.kernel.org/all/CA+55aFwVUkdaf0_rBk7uJHQjWXu+OcLTHc6FKuCn0Cb2Kvg9NA@mail.gmail.com/