Re: [PATCH v5 0/6] Migrate on fault for device pages

[Alistair Popple]

On 2026-03-13 at 06:58 +1100, "David Hildenbrand (Arm)" <david@xxxxxxxxxx> wrote...
> On 2/11/26 09:12, mpenttil@xxxxxxxxxx wrote:
> > From: Mika Penttilä <mpenttil@xxxxxxxxxx>
> > 
> > Currently, the way device page faulting and migration works
> > is not optimal, if you want to do both fault handling and
> > migration at once.
> > 
> > Being able to migrate not present pages (or pages mapped with incorrect
> > permissions, eg. COW) to the GPU requires doing either of the
> > following sequences:
> > 
> > 1. hmm_range_fault() - fault in non-present pages with correct permissions, etc.
> > 2. migrate_vma_*() - migrate the pages
> > 
> > Or:
> > 
> > 1. migrate_vma_*() - migrate present pages
> > 2. If non-present pages detected by migrate_vma_*():
> >    a) call hmm_range_fault() to fault pages in
> >    b) call migrate_vma_*() again to migrate now present pages
> > 
> > The problem with the first sequence is that you always have to do two
> > page walks even when most of the time the pages are present or zero page
> > mappings so the common case takes a performance hit.
> > 
> > The second sequence is better for the common case, but far worse if
> > pages aren't present because now you have to walk the page tables three
> > times (once to find the page is not present, once so hmm_range_fault()
> > can find a non-present page to fault in and once again to setup the
> > migration). It is also tricky to code correctly. One page table walk
> > could costs over 1000 cpu cycles on X86-64, which is a significant hit.
> > 
> > We should be able to walk the page table once, faulting
> > pages in as required and replacing them with migration entries if
> > requested.
> > 
> > Add a new flag to HMM APIs, HMM_PFN_REQ_MIGRATE,
> > which tells to prepare for migration also during fault handling.
> > Also, for the migrate_vma_setup() call paths, a flag, MIGRATE_VMA_FAULT,
> > is added to tell to add fault handling to migrate.
> > 
> > One extra benefit of migrating with hmm_range_fault() path
> > is the migrate_vma.vma gets populated, so no need to
> > retrieve that separataly.
> > 
> > Tested in X86-64 VM with HMM test device, passing the selftests.
> > For performance, the migrate throughput tests from the selftests
> > show similar numbers (within error margin) as unmodified kernel.
> > Tested also rebased on the
> > "Remove device private pages from physical address space" series:
> > https://lore.kernel.org/linux-mm/20260130111050.53670-1-jniethe@xxxxxxxxxx/
> > plus a small patch to adjust with no problems.
> 
> Stumbling over this in my backlog, so far we have to RB tags.
> 
> I'm going to take a look at the core MM bits (soon I hope), but it would
> be great if other people could review the HMM bits and provide proper tags.

Yes, sorry I've been meaning to review this for a while but have been backlogged
for a while. I should be able to get to it early next week though.

> -- 
> Cheers,
> 
> David