Re: [PATCH v5 1/2] mm: Abstract THP allocation

[Dev Jain <dev.jain@xxxxxxx>]

On 9/24/24 16:50, Kefeng Wang wrote:
> On 2024/9/24 18:16, 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/
> >
> > Acked-by: David Hildenbrand <david@xxxxxxxxxx>
> > Signed-off-by: Dev Jain <dev.jain@xxxxxxx>
> > ---
> >   mm/huge_memory.c | 98 ++++++++++++++++++++++++++++--------------------
> >   1 file changed, 57 insertions(+), 41 deletions(-)
> >
> > diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> > index 4e34b7f89daf..bdbf67c18f6c 100644
> > --- a/mm/huge_memory.c
> > +++ b/mm/huge_memory.c
> > @@ -1148,47 +1148,81 @@ 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);
>
> There is a warning without NUMA,
>
> ../mm/huge_memory.c: In function ‘vma_alloc_anon_folio_pmd’:
> ../mm/huge_memory.c:1154:16: warning: unused variable ‘haddr’ 
> [-Wunused-variable]
>  1154 |  unsigned long haddr = addr & HPAGE_PMD_MASK;
>       |                ^~~~~

But why is this happening?

> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index c584e77efe10..147a6e069c71 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1151,11 +1151,11 @@ EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
>  static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct 
> *vma,
>                                               unsigned long addr)
>  {
> -       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);
> +       struct folio *folio;
>
> +       folio = vma_alloc_folio(gfp, order, vma, addr & 
> HPAGE_PMD_MASK, true);
>         if (unlikely(!folio)) {
>                 count_vm_event(THP_FAULT_FALLBACK);
>                 count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
>
> >   - 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;
>
> Maybe return NULL to omit the out?

Ah sorry, I have made a mess of unnecessary delayed returns :)
> Reviewed-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>

Thanks!
> > +    }
> >   +    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 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);
> > +    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);
> > +}
> > +
> > +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;
> > +    struct folio *folio;
> > +    pgtable_t pgtable;
> > +    vm_fault_t ret = 0;
> > +
> > +    folio = vma_alloc_anon_folio_pmd(vma, vmf->address);
> > +    if (unlikely(!folio))
> > +        return VM_FAULT_FALLBACK;
> > +
> > +    pgtable = pte_alloc_one(vma->vm_mm);
> > +    if (unlikely(!pgtable)) {
> > +        ret = VM_FAULT_OOM;
> > +        goto release;
> > +    }
> >         vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
> >       if (unlikely(!pmd_none(*vmf->pmd))) {
> >           goto unlock_release;
> >       } else {
> > -        pmd_t entry;
> > -
> >           ret = check_stable_address_space(vma->vm_mm);
> >           if (ret)
> >               goto unlock_release;
> > @@ -1202,21 +1236,11 @@ static vm_fault_t 
> > __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
> >               VM_BUG_ON(ret & VM_FAULT_FALLBACK);
> >               return ret;
> >           }
> > -
> > -        entry = mk_huge_pmd(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);
> >           pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
> > -        set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
> > -        update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
> > -        add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
> > +        map_anon_folio_pmd(folio, vmf->pmd, vma, haddr);
> >           mm_inc_nr_ptes(vma->vm_mm);
> >           deferred_split_folio(folio, false);
> >           spin_unlock(vmf->ptl);
> > -        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);
> >       }
> >         return 0;
> > @@ -1283,8 +1307,6 @@ static void set_huge_zero_folio(pgtable_t 
> > pgtable, struct mm_struct *mm,
> >   vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
> >   {
> >       struct vm_area_struct *vma = vmf->vma;
> > -    gfp_t gfp;
> > -    struct folio *folio;
> >       unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> >       vm_fault_t ret;
> >   @@ -1335,14 +1357,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct 
> > vm_fault *vmf)
> >           }
> >           return ret;
> >       }
> > -    gfp = vma_thp_gfp_mask(vma);
> > -    folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true);
> > -    if (unlikely(!folio)) {
> > -        count_vm_event(THP_FAULT_FALLBACK);
> > -        count_mthp_stat(HPAGE_PMD_ORDER, 
> > MTHP_STAT_ANON_FAULT_FALLBACK);
> > -        return VM_FAULT_FALLBACK;
> > -    }
> > -    return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp);
> > +
> > +    return __do_huge_pmd_anonymous_page(vmf);
> >   }
> >     static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned 
> > long addr,