Re: [PATCH v4 1/2] mm: Abstract THP allocation

[Dev Jain <dev.jain@xxxxxxx>]

On 9/17/24 17:17, David Hildenbrand wrote:
> On 16.09.24 11:43, Dev Jain wrote:
> > In preparation for the second patch, abstract away the THP allocation
> > logic present in the create_huge_pmd() path, which corresponds to the
> > faulting case when no page is present.
> >
> > There should be no functional change as a result of applying this patch,
> > except that, as David notes at [1], a PMD-aligned address should
> > be passed to update_mmu_cache_pmd().
> >
> > [1]: 
> > https://lore.kernel.org/all/ddd3fcd2-48b3-4170-bcaa-2fe66e093f43@xxxxxxxxxx/
> >
> > Signed-off-by: Dev Jain <dev.jain@xxxxxxx>
> > ---
> >   mm/huge_memory.c | 108 +++++++++++++++++++++++++++++------------------
> >   1 file changed, 66 insertions(+), 42 deletions(-)
> >
> > diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> > index 2a73efea02d7..cdc632b8dc9c 100644
> > --- a/mm/huge_memory.c
> > +++ b/mm/huge_memory.c
> > @@ -1146,47 +1146,88 @@ unsigned long thp_get_unmapped_area(struct 
> > file *filp, unsigned long addr,
> >   }
> >   EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
> >   -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
> > -            struct page *page, gfp_t gfp)
> > +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct 
> > *vma,
> > +                          unsigned long addr)
> >   {
> > -    struct vm_area_struct *vma = vmf->vma;
> > -    struct folio *folio = page_folio(page);
> > -    pgtable_t pgtable;
> > -    unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> > -    vm_fault_t ret = 0;
> > +    unsigned long haddr = addr & HPAGE_PMD_MASK;
> > +    gfp_t gfp = vma_thp_gfp_mask(vma);
> > +    const int order = HPAGE_PMD_ORDER;
> > +    struct folio *folio = vma_alloc_folio(gfp, order, vma, haddr, 
> > true);
> >   -    VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
> > +    if (unlikely(!folio)) {
> > +        count_vm_event(THP_FAULT_FALLBACK);
> > +        count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> > +        goto out;
> > +    }
> >   +    VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
> >       if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
> >           folio_put(folio);
> >           count_vm_event(THP_FAULT_FALLBACK);
> >           count_vm_event(THP_FAULT_FALLBACK_CHARGE);
> > -        count_mthp_stat(HPAGE_PMD_ORDER, 
> > MTHP_STAT_ANON_FAULT_FALLBACK);
> > -        count_mthp_stat(HPAGE_PMD_ORDER, 
> > MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> > -        return VM_FAULT_FALLBACK;
> > +        count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> > +        count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> > +        return NULL;
> >       }
> >       folio_throttle_swaprate(folio, gfp);
> >   -    pgtable = pte_alloc_one(vma->vm_mm);
> > -    if (unlikely(!pgtable)) {
> > -        ret = VM_FAULT_OOM;
> > -        goto release;
> > -    }
> > -
> > -    folio_zero_user(folio, vmf->address);
> > +    folio_zero_user(folio, addr);
> >       /*
> >        * The memory barrier inside __folio_mark_uptodate makes sure that
> >        * folio_zero_user writes become visible before the set_pmd_at()
> >        * write.
> >        */
> >       __folio_mark_uptodate(folio);
> > +out:
> > +    return folio;
> > +}
> > +
> > +static void __pmd_thp_fault_success_stats(struct vm_area_struct *vma)
> > +{
> > +    count_vm_event(THP_FAULT_ALLOC);
> > +    count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
> > +    count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
> > +}
>
> just inline that into map_anon_folio_pmd(), please. map_anon_folio_pmd 
> is perfectly readable ;)

If you are asking me to open code it in map_anon_folio_pmd(), I'll do that.
> > +
> > +static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd,
> > +                   struct vm_area_struct *vma, unsigned long haddr)
>
>
> > +{
> > +    pmd_t entry;
> > +
> > +    entry = mk_huge_pmd(&folio->page, vma->vm_page_prot);
> > +    entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> > +    folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
> > +    folio_add_lru_vma(folio, vma);
> > +    set_pmd_at(vma->vm_mm, haddr, pmd, entry);
> > +    update_mmu_cache_pmd(vma, haddr, pmd);
> > +    add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
> > +    __pmd_thp_fault_success_stats(vma);
> > +}
> > +
> > +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
> > +{
> > +    unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> > +    struct vm_area_struct *vma = vmf->vma;
> > +    pgtable_t pgtable = NULL;
> > +    struct folio *folio;
> > +    vm_fault_t ret = 0;
> > +
> > +    folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
> > +    if (unlikely(!folio)) {
> > +        ret = VM_FAULT_FALLBACK;
> > +        goto release;
>
> Why not simply "return VM_FAULT_FALLBACK;" ? There is nothing to 
> release. Then you can avoid the
>
> "if (folio)" below and even stop initializing pgtable to NULL.

Makes sense.
> With these things take care of
>
> Acked-by: David Hildenbrand <david@xxxxxxxxxx>

Thanks!