1 files changed, 52 insertions, 36 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 7d23b5050248..6bf2b471e30c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3008,13 +3008,6 @@ static int do_set_pmd(struct vm_fault *vmf, struct page *page)
 	ret = 0;
 	count_vm_event(THP_FILE_MAPPED);
 out:
-	/*
-	 * If we are going to fallback to pte mapping, do a
-	 * withdraw with pmd lock held.
-	 */
-	if (arch_needs_pgtable_deposit() && ret == VM_FAULT_FALLBACK)
-		vmf->prealloc_pte = pgtable_trans_huge_withdraw(vma->vm_mm,
-								vmf->pmd);
 	spin_unlock(vmf->ptl);
 	return ret;
 }
@@ -3055,20 +3048,18 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 
 		ret = do_set_pmd(vmf, page);
 		if (ret != VM_FAULT_FALLBACK)
-			goto fault_handled;
+			return ret;
 	}
 
 	if (!vmf->pte) {
 		ret = pte_alloc_one_map(vmf);
 		if (ret)
-			goto fault_handled;
+			return ret;
 	}
 
 	/* Re-check under ptl */
-	if (unlikely(!pte_none(*vmf->pte))) {
-		ret = VM_FAULT_NOPAGE;
-		goto fault_handled;
-	}
+	if (unlikely(!pte_none(*vmf->pte)))
+		return VM_FAULT_NOPAGE;
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -3088,15 +3079,8 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 
 	/* no need to invalidate: a not-present page won't be cached */
 	update_mmu_cache(vma, vmf->address, vmf->pte);
-	ret = 0;
 
-fault_handled:
-	/* preallocated pagetable is unused: free it */
-	if (vmf->prealloc_pte) {
-		pte_free(vmf->vma->vm_mm, vmf->prealloc_pte);
-		vmf->prealloc_pte = 0;
-	}
-	return ret;
+	return 0;
 }
 
 
@@ -3360,15 +3344,24 @@ static int do_shared_fault(struct vm_fault *vmf)
 static int do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	int ret;
 
 	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
 	if (!vma->vm_ops->fault)
-		return VM_FAULT_SIGBUS;
-	if (!(vmf->flags & FAULT_FLAG_WRITE))
-		return do_read_fault(vmf);
-	if (!(vma->vm_flags & VM_SHARED))
-		return do_cow_fault(vmf);
-	return do_shared_fault(vmf);
+		ret = VM_FAULT_SIGBUS;
+	else if (!(vmf->flags & FAULT_FLAG_WRITE))
+		ret = do_read_fault(vmf);
+	else if (!(vma->vm_flags & VM_SHARED))
+		ret = do_cow_fault(vmf);
+	else
+		ret = do_shared_fault(vmf);
+
+	/* preallocated pagetable is unused: free it */
+	if (vmf->prealloc_pte) {
+		pte_free(vma->vm_mm, vmf->prealloc_pte);
+		vmf->prealloc_pte = 0;
+	}
+	return ret;
 }
 
 static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
@@ -3779,8 +3772,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte(struct mm_struct *mm, unsigned long address,
-		pte_t **ptepp, spinlock_t **ptlp)
+static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -3797,11 +3790,20 @@ static int __follow_pte(struct mm_struct *mm, unsigned long address,
 
 	pmd = pmd_offset(pud, address);
 	VM_BUG_ON(pmd_trans_huge(*pmd));
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		goto out;
 
-	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
-	if (pmd_huge(*pmd))
+	if (pmd_huge(*pmd)) {
+		if (!pmdpp)
+			goto out;
+
+		*ptlp = pmd_lock(mm, pmd);
+		if (pmd_huge(*pmd)) {
+			*pmdpp = pmd;
+			return 0;
+		}
+		spin_unlock(*ptlp);
+	}
+
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
@@ -3817,16 +3819,30 @@ out:
 	return -EINVAL;
 }
 
-int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
-	       spinlock_t **ptlp)
+static inline int follow_pte(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, spinlock_t **ptlp)
+{
+	int res;
+
+	/* (void) is needed to make gcc happy */
+	(void) __cond_lock(*ptlp,
+			   !(res = __follow_pte_pmd(mm, address, ptepp, NULL,
+					   ptlp)));
+	return res;
+}
+
+int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	int res;
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
+			   !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp,
+					   ptlp)));
 	return res;
 }
+EXPORT_SYMBOL(follow_pte_pmd);
 
 /**
  * follow_pfn - look up PFN at a user virtual address