Re: [LSF/MM/BPF TOPIC] Per-process page size

[Matthew Wilcox]

On Mon, Feb 23, 2026 at 10:37:55AM +0530, Dev Jain wrote:
> I didn't understand the reclaimable reference, but yes we need to make this efficient.

this goes over 80 columns so much and so often, it's painful to read.
so i didn't.

> So for the above example I gave, native_set_ptes knows the virtual address to set -
> walking the native hierarchy from native_pgd->native_pmd->native_pte (in case of 64K native
> geometry) is inefficient. So we need to maintain a lookup mechanism from a linux pgtable
> pointer to the native pgtable pointer.
> The idea we have currently is to store such lookup in the struct ptdesc of the pagetable page.
> For 4K Linux pagetable and 64K native pagetable, 512M/2M = 256 Linux PTE tables correspond
> to different sections of the native PTE table. We will maintain the pointer to the relevant
> section in the native PTE table, in the struct ptdesc of the pagetable page of the Linux
> PTE table.
> The other case is that a single Linux pgtable leaf entry corresponds to multiple native
> leaf entries - take the case of a Linux PMD table which maps 1G of memory, this corresponds
> to 2 native PTE tables (2 x 512M). We will have to store a list of pointers here.
> 
> >
>