1 files changed, 32 insertions, 11 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2dd2f9ab57f4..e11ca9dd823f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -400,10 +400,10 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	}
 }
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 {
 	spinlock_t *ptl;
-	pgtable_t new = pte_alloc_one(mm, address);
+	pgtable_t new = pte_alloc_one(mm);
 	if (!new)
 		return -ENOMEM;
 
@@ -434,9 +434,9 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
 	return 0;
 }
 
-int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
+int __pte_alloc_kernel(pmd_t *pmd)
 {
-	pte_t *new = pte_alloc_one_kernel(&init_mm, address);
+	pte_t *new = pte_alloc_one_kernel(&init_mm);
 	if (!new)
 		return -ENOMEM;
 
@@ -2896,7 +2896,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	 *
 	 * Here we only have down_read(mmap_sem).
 	 */
-	if (pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))
+	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
 
 	/* See the comment in pte_alloc_one_map() */
@@ -2994,6 +2994,28 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret;
 
+	/*
+	 * Preallocate pte before we take page_lock because this might lead to
+	 * deadlocks for memcg reclaim which waits for pages under writeback:
+	 *				lock_page(A)
+	 *				SetPageWriteback(A)
+	 *				unlock_page(A)
+	 * lock_page(B)
+	 *				lock_page(B)
+	 * pte_alloc_pne
+	 *   shrink_page_list
+	 *     wait_on_page_writeback(A)
+	 *				SetPageWriteback(B)
+	 *				unlock_page(B)
+	 *				# flush A, B to clear the writeback
+	 */
+	if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) {
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
+		if (!vmf->prealloc_pte)
+			return VM_FAULT_OOM;
+		smp_wmb(); /* See comment in __pte_alloc() */
+	}
+
 	ret = vma->vm_ops->fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
 			    VM_FAULT_DONE_COW)))
@@ -3043,7 +3065,7 @@ static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf)
 		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
 		spin_unlock(vmf->ptl);
 		vmf->prealloc_pte = NULL;
-	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))) {
+	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
 		return VM_FAULT_OOM;
 	}
 map_pte:
@@ -3122,7 +3144,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * related to pte entry. Use the preallocated table for that.
 	 */
 	if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm, vmf->address);
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
@@ -3360,8 +3382,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 			start_pgoff + nr_pages - 1);
 
 	if (pmd_none(*vmf->pmd)) {
-		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm,
-						  vmf->address);
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			goto out;
 		smp_wmb(); /* See comment in __pte_alloc() */
@@ -4078,8 +4099,8 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		goto out;
 
 	if (range) {
-		range->start = address & PAGE_MASK;
-		range->end = range->start + PAGE_SIZE;
+		mmu_notifier_range_init(range, mm, address & PAGE_MASK,
+				     (address & PAGE_MASK) + PAGE_SIZE);
 		mmu_notifier_invalidate_range_start(range);
 	}
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);