mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required

Although all architectures use a deposited page table for THP on
anonymous VMAs, some architectures (s390 and powerpc) require the
deposited storage even for file backed VMAs due to quirks of their MMUs.

This patch adds support for depositing a table in DAX PMD fault handling
path for archs that require it.  Other architectures should see no
functional changes.

Link: http://lkml.kernel.org/r/20170411174233.21902-3-oohall@gmail.com
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Cc: Reza Arbab <arbab@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: linux-nvdimm@ml01.01.org
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/huge_memory.c

@@ -715,7 +715,8 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 }
 
 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write)
+		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
+		pgtable_t pgtable)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t entry;
@@ -729,6 +730,12 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 		entry = pmd_mkyoung(pmd_mkdirty(entry));
 		entry = maybe_pmd_mkwrite(entry, vma);
 	}
+
+	if (pgtable) {
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
+		atomic_long_inc(&mm->nr_ptes);
+	}
+
 	set_pmd_at(mm, addr, pmd, entry);
 	update_mmu_cache_pmd(vma, addr, pmd);
 	spin_unlock(ptl);
@@ -738,6 +745,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 			pmd_t *pmd, pfn_t pfn, bool write)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
+	pgtable_t pgtable = NULL;
 	/*
 	 * If we had pmd_special, we could avoid all these restrictions,
 	 * but we need to be consistent with PTEs and architectures that
@@ -752,9 +760,15 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	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, addr);
+		if (!pgtable)
+			return VM_FAULT_OOM;
+	}
+
 	track_pfn_insert(vma, &pgprot, pfn);
 
-	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
+	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
@@ -1611,6 +1625,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			tlb->fullmm);
 	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 	if (vma_is_dax(vma)) {
+		if (arch_needs_pgtable_deposit())
+			zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
 		if (is_huge_zero_pmd(orig_pmd))
 			tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);