[PATCH] mm: Recheck page table entry with page table lock held

[Aneesh Kumar K.V]

We clear the pte temporarily during read/modify/write update of the pte. If we
take a page fault while the pte is cleared, the application can get SIGBUS. One
such case is with remap_pfn_range without a backing vm_ops->fault callback.
do_fault will return SIGBUS in that case.

Fix this by taking page table lock and rechecking for pte_none.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
---
 mm/memory.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index c467102a5cbc..c2f933184303 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3745,10 +3745,33 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret;
 
-	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
-	if (!vma->vm_ops->fault)
-		ret = VM_FAULT_SIGBUS;
-	else if (!(vmf->flags & FAULT_FLAG_WRITE))
+	/*
+	 * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
+	 */
+	if (!vma->vm_ops->fault) {
+
+		/*
+		 * pmd entries won't be marked none during a R/M/W cycle.
+		 */
+		if (unlikely(pmd_none(*vmf->pmd)))
+			ret = VM_FAULT_SIGBUS;
+		else {
+			vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
+			/*
+			 * Make sure this is not a temporary clearing of pte
+			 * by holding ptl and checking again. A R/M/W update
+			 * of pte involves: take ptl, clearing the pte so that
+			 * we don't have concurrent modification by hardware
+			 * followed by an update.
+			 */
+			spin_lock(vmf->ptl);
+			if (unlikely(pte_none(*vmf->pte)))
+				ret = VM_FAULT_SIGBUS;
+			else
+				ret = VM_FAULT_NOPAGE;
+			spin_unlock(vmf->ptl);
+		}
+	} else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
 	else if (!(vma->vm_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);
-- 
2.17.1