1 files changed, 26 insertions, 12 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 852b319..9b2345c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -956,8 +956,10 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	struct task_struct *tsk;
 	unsigned long address;
 	struct mm_struct *mm;
-	int write;
 	int fault;
+	int write = error_code & PF_WRITE;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY |
+					(write ? FAULT_FLAG_WRITE : 0);
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1068,6 +1070,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 			bad_area_nosemaphore(regs, error_code, address);
 			return;
 		}
+retry:
 		down_read(&mm->mmap_sem);
 	} else {
 		/*
@@ -1111,8 +1114,6 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	 * we can handle it..
 	 */
 good_area:
-	write = error_code & PF_WRITE;
-
 	if (unlikely(access_error(error_code, write, vma))) {
 		bad_area_access_error(regs, error_code, address);
 		return;
@@ -1123,21 +1124,34 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault:
 	 */
-	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mm_fault_error(regs, error_code, address, fault);
 		return;
 	}
 
-	if (fault & VM_FAULT_MAJOR) {
-		tsk->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
-				     regs, address);
-	} else {
-		tsk->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
-				     regs, address);
+	/*
+	 * Major/minor page fault accounting is only done on the
+	 * initial attempt. If we go through a retry, it is extremely
+	 * likely that the page will be found in page cache at that point.
+	 */
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			tsk->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				      regs, address);
+		} else {
+			tsk->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				      regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			 * of starvation. */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			goto retry;
+		}
 	}
 
 	check_v8086_mode(regs, address, tsk);