1 files changed, 24 insertions, 2 deletions

diff --git a/mm/memory.c b/mm/memory.c
index a52663c0612d..e11ca9dd823f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -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)))
@@ -4077,8 +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);