mm/huge_memory: don't mark refcounted folios special in vmf_insert_folio_pud()

Marking PUDs that map a "normal" refcounted folios as special is against
our rules documented for vm_normal_page().  normal (refcounted) folios
shall never have the page table mapping marked as special.

Fortunately, there are not that many pud_special() check that can be
mislead and are right now rather harmless: e.g., none so far bases
decisions whether to grab a folio reference on that decision.

Well, and GUP-fast will fallback to GUP-slow.  All in all, so far no big
implications as it seems.

Getting this right will get more important as we introduce
folio_normal_page_pud() and start using it in more place where we
currently special-case based on other VMA flags.

Fix it just like we fixed vmf_insert_folio_pmd().

Add folio_mk_pud() to mimic what we do with folio_mk_pmd().

Link: https://lkml.kernel.org/r/20250613092702.1943533-4-david@redhat.com
Fixes: dbe54153296d ("mm/huge_memory: add vmf_insert_folio_pud()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667af03b121dd7311fa392042c29c56c..b7e2abd8ce0dfb58f0a796bca712ccf237074bf6 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1816,7 +1816,24 @@ static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot)
 {
        return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot));
 }
-#endif
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/**
+ * folio_mk_pud - Create a PUD for this folio
+ * @folio: The folio to create a PUD for
+ * @pgprot: The page protection bits to use
+ *
+ * Create a page table entry for the first page of this folio.
+ * This is suitable for passing to set_pud_at().
+ *
+ * Return: A page table entry suitable for mapping this folio.
+ */
+static inline pud_t folio_mk_pud(struct folio *folio, pgprot_t pgprot)
+{
+       return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot));
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif /* CONFIG_MMU */
 
 static inline bool folio_has_pincount(const struct folio *folio)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d1e3e253c714ae8e9e33b40adbed9d8194ce9e5e..bbc1dab98f2f7e202636a846fc4e07eb6f956c27 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1536,15 +1536,18 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
        return pud;
 }
 
-static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
-               pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
+               pud_t *pud, struct folio_or_pfn fop, pgprot_t prot, bool write)
 {
        struct mm_struct *mm = vma->vm_mm;
        pud_t entry;
 
        if (!pud_none(*pud)) {
+               const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
+                                         pfn_t_to_pfn(fop.pfn);
+
                if (write) {
-                       if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
+                       if (WARN_ON_ONCE(pud_pfn(*pud) != pfn))
                                return;
                        entry = pud_mkyoung(*pud);
                        entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
@@ -1554,11 +1557,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
                return;
        }
 
-       entry = pud_mkhuge(pfn_t_pud(pfn, prot));
-       if (pfn_t_devmap(pfn))
-               entry = pud_mkdevmap(entry);
-       else
-               entry = pud_mkspecial(entry);
+       if (fop.is_folio) {
+               entry = folio_mk_pud(fop.folio, vma->vm_page_prot);
+
+               folio_get(fop.folio);
+               folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma);
+               add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR);
+       } else {
+               entry = pud_mkhuge(pfn_t_pud(fop.pfn, prot));
+
+               if (pfn_t_devmap(fop.pfn))
+                       entry = pud_mkdevmap(entry);
+               else
+                       entry = pud_mkspecial(entry);
+       }
        if (write) {
                entry = pud_mkyoung(pud_mkdirty(entry));
                entry = maybe_pud_mkwrite(entry, vma);
@@ -1582,6 +1594,9 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
        unsigned long addr = vmf->address & PUD_MASK;
        struct vm_area_struct *vma = vmf->vma;
        pgprot_t pgprot = vma->vm_page_prot;
+       struct folio_or_pfn fop = {
+               .pfn = pfn,
+       };
        spinlock_t *ptl;
 
        /*
@@ -1601,7 +1616,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
        pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
 
        ptl = pud_lock(vma->vm_mm, vmf->pud);
-       insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
+       insert_pud(vma, addr, vmf->pud, fop, pgprot, write);
        spin_unlock(ptl);
 
        return VM_FAULT_NOPAGE;
@@ -1623,6 +1638,10 @@ vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
        unsigned long addr = vmf->address & PUD_MASK;
        pud_t *pud = vmf->pud;
        struct mm_struct *mm = vma->vm_mm;
+       struct folio_or_pfn fop = {
+               .folio = folio,
+               .is_folio = true,
+       };
        spinlock_t *ptl;
 
        if (addr < vma->vm_start || addr >= vma->vm_end)
@@ -1632,20 +1651,7 @@ vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
                return VM_FAULT_SIGBUS;
 
        ptl = pud_lock(mm, pud);
-
-       /*
-        * If there is already an entry present we assume the folio is
-        * already mapped, hence no need to take another reference. We
-        * still call insert_pfn_pud() though in case the mapping needs
-        * upgrading to writeable.
-        */
-       if (pud_none(*vmf->pud)) {
-               folio_get(folio);
-               folio_add_file_rmap_pud(folio, &folio->page, vma);
-               add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
-       }
-       insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)),
-                      vma->vm_page_prot, write);
+       insert_pud(vma, addr, vmf->pud, fop, vma->vm_page_prot, write);
        spin_unlock(ptl);
 
        return VM_FAULT_NOPAGE;