[PATCH 08/13] huge_memory: Allow mappings of PMD sized pages

[Alistair Popple]

Currently DAX folio/page reference counts are managed differently to
normal pages. To allow these to be managed the same as normal pages
introduce dax_insert_pfn_pmd. This will map the entire PMD-sized folio
and take references as it would for a normally mapped page.

This is distinct from the current mechanism, vmf_insert_pfn_pmd, which
simply inserts a special devmap PMD entry into the page table without
holding a reference to the page for the mapping.

Signed-off-by: Alistair Popple <apopple at nvidia.com>
---
 include/linux/huge_mm.h |  1 +-
 mm/huge_memory.c        | 70 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 71 insertions(+)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b98a3cc..9207d8e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -39,6 +39,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
 vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
+vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
 vm_fault_t dax_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
 
 enum transparent_hugepage_flag {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e1f053e..a9874ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1202,6 +1202,76 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
+vm_fault_t dax_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address & PMD_MASK;
+	pmd_t *pmd = vmf->pmd;
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t entry;
+	spinlock_t *ptl;
+	pgtable_t pgtable = NULL;
+	struct folio *folio;
+	struct page *page;
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	if (arch_needs_pgtable_deposit()) {
+		pgtable = pte_alloc_one(vma->vm_mm);
+		if (!pgtable)
+			return VM_FAULT_OOM;
+	}
+
+	track_pfn_insert(vma, &vma->vm_page_prot, pfn);
+
+	ptl = pmd_lock(mm, pmd);
+	if (!pmd_none(*pmd)) {
+		if (write) {
+			if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+				WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
+				goto out_unlock;
+			}
+			entry = pmd_mkyoung(*pmd);
+			entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+			if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
+				update_mmu_cache_pmd(vma, addr, pmd);
+		}
+
+		goto out_unlock;
+	}
+
+	entry = pmd_mkhuge(pfn_t_pmd(pfn, vma->vm_page_prot));
+	if (pfn_t_devmap(pfn))
+		entry = pmd_mkdevmap(entry);
+	if (write) {
+		entry = pmd_mkyoung(pmd_mkdirty(entry));
+		entry = maybe_pmd_mkwrite(entry, vma);
+	}
+
+	if (pgtable) {
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
+		mm_inc_nr_ptes(mm);
+		pgtable = NULL;
+	}
+
+	page = pfn_t_to_page(pfn);
+	folio = page_folio(page);
+	folio_get(folio);
+	folio_add_file_rmap_pmd(folio, page, vma);
+	add_mm_counter(mm, mm_counter_file(folio), HPAGE_PMD_NR);
+	set_pmd_at(mm, addr, pmd, entry);
+	update_mmu_cache_pmd(vma, addr, pmd);
+
+out_unlock:
+	spin_unlock(ptl);
+	if (pgtable)
+		pte_free(mm, pgtable);
+
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(dax_insert_pfn_pmd);
+
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
 {
-- 
git-series 0.9.1