[PATCH v2 06/19] mm/pagewalk: Check pfnmap for folio_walk_start()

[David Hildenbrand]

On 26.08.24 22:43, Peter Xu wrote:
> Teach folio_walk_start() to recognize special pmd/pud mappings, and fail
> them properly as it means there's no folio backing them.
> 
> Cc: David Hildenbrand <david at redhat.com>
> Signed-off-by: Peter Xu <peterx at redhat.com>
> ---
>   mm/pagewalk.c | 4 ++--
>   1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> index cd79fb3b89e5..12be5222d70e 100644
> --- a/mm/pagewalk.c
> +++ b/mm/pagewalk.c
> @@ -753,7 +753,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
>   		fw->pudp = pudp;
>   		fw->pud = pud;
>   
> -		if (!pud_present(pud) || pud_devmap(pud)) {
> +		if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) {
>   			spin_unlock(ptl);
>   			goto not_found;
>   		} else if (!pud_leaf(pud)) {
> @@ -783,7 +783,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
>   		fw->pmdp = pmdp;
>   		fw->pmd = pmd;
>   
> -		if (pmd_none(pmd)) {
> +		if (pmd_none(pmd) || pmd_special(pmd)) {
>   			spin_unlock(ptl);
>   			goto not_found;
>   		} else if (!pmd_leaf(pmd)) {

As raised, this is not the right way to to it. You should follow what
CONFIG_ARCH_HAS_PTE_SPECIAL and vm_normal_page() does.

It's even spelled out in vm_normal_page_pmd() that at the time it was
introduced there was no pmd_special(), so there was no way to handle that.



diff --git a/mm/memory.c b/mm/memory.c
index f0cf5d02b4740..272445e9db147 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -672,15 +672,29 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
  {
         unsigned long pfn = pmd_pfn(pmd);
  
-       /*
-        * There is no pmd_special() but there may be special pmds, e.g.
-        * in a direct-access (dax) mapping, so let's just replicate the
-        * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here.
-        */
+       if (IS_ENABLED(CONFIG_ARCH_HAS_PMD_SPECIAL)) {
+               if (likely(!pmd_special(pmd)))
+                       goto check_pfn;
+               if (vma->vm_ops && vma->vm_ops->find_special_page)
+                       return vma->vm_ops->find_special_page(vma, addr);
+               if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
+                       return NULL;
+               if (is_huge_zero_pmd(pmd))
+                       return NULL;
+               if (pmd_devmap(pmd))
+                       /* See vm_normal_page() */
+                       return NULL;
+               return NULL;
+       }
+
+       /* !CONFIG_ARCH_HAS_PMD_SPECIAL case follows: */
+
         if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
                 if (vma->vm_flags & VM_MIXEDMAP) {
                         if (!pfn_valid(pfn))
                                 return NULL;
+                       if (is_huge_zero_pmd(pmd))
+                               return NULL;
                         goto out;
                 } else {
                         unsigned long off;
@@ -692,6 +706,11 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
                 }
         }
  
+       /*
+        * For historical reasons, these might not have pmd_special() set,
+        * so we'll check them manually, in contrast to vm_normal_page().
+        */
+check_pfn:
         if (pmd_devmap(pmd))
                 return NULL;
         if (is_huge_zero_pmd(pmd))



We should then look into mapping huge zeropages also with pmd_special.
pmd_devmap we'll leave alone until removed. But that's indeoendent of your series.

I wonder if CONFIG_ARCH_HAS_PTE_SPECIAL is sufficient and we don't need additional
CONFIG_ARCH_HAS_PMD_SPECIAL.

As I said, if you need someone to add vm_normal_page_pud(), I can handle that.

-- 
Cheers,

David / dhildenb