[PATCH v3 15/25] 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 vmf_insert_folio_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        | 60 +++++++++++++++++++++++++++++++++++-------
 2 files changed, 51 insertions(+), 10 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e804e41..120d0ac 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -40,6 +40,7 @@ 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 vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, bool write);
 vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write);
 
 enum transparent_hugepage_flag {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c51ef3e..b3bf909 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1340,14 +1340,12 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t entry;
-	spinlock_t *ptl;
 
-	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;
+				return;
 			}
 			entry = pmd_mkyoung(*pmd);
 			entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -1355,7 +1353,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 				update_mmu_cache_pmd(vma, addr, pmd);
 		}
 
-		goto out_unlock;
+		return;
 	}
 
 	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
@@ -1376,11 +1374,6 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	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);
 }
 
 /**
@@ -1399,6 +1392,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t pgprot = vma->vm_page_prot;
 	pgtable_t pgtable = NULL;
+	spinlock_t *ptl;
 
 	/*
 	 * If we had pmd_special, we could avoid all these restrictions,
@@ -1421,12 +1415,58 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 	}
 
 	track_pfn_insert(vma, &pgprot, pfn);
-
+	ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
+	spin_unlock(ptl);
+	if (pgtable)
+		pte_free(vma->vm_mm, pgtable);
+
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
+vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, bool write)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address & PMD_MASK;
+	pfn_t pfn = pfn_to_pfn_t(folio_pfn(folio));
+	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
+	pgtable_t pgtable = NULL;
+	struct page *page;
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER))
+		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, vmf->pmd);
+	if (pmd_none(*vmf->pmd)) {
+		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);
+	}
+	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, vma->vm_page_prot,
+		write, pgtable);
+	spin_unlock(ptl);
+	if (pgtable)
+		pte_free(mm, pgtable);
+
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(vmf_insert_folio_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