[S390] mm: add page fault retry handling

s390 arch backend for d065bd81 "mm: retry page fault when blocking on
disk transfer".

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index b57723aee848f634a03d51ff4bcbc140f5505424..fe103e891e7a0eb32dc7c67fc0cea3217bd4b6e3 100644 (file)
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -280,7 +280,8 @@ static inline int do_exception(struct pt_regs *regs, int access,
        struct mm_struct *mm;
        struct vm_area_struct *vma;
        unsigned long address;
-       int fault, write;
+       unsigned int flags;
+       int fault;
 
        if (notify_page_fault(regs))
                return 0;
@@ -299,6 +300,10 @@ static inline int do_exception(struct pt_regs *regs, int access,
 
        address = trans_exc_code & __FAIL_ADDR_MASK;
        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+       flags = FAULT_FLAG_ALLOW_RETRY;
+       if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
+               flags |= FAULT_FLAG_WRITE;
+retry:
        down_read(&mm->mmap_sem);
 
        fault = VM_FAULT_BADMAP;
@@ -328,21 +333,31 @@ static inline int do_exception(struct pt_regs *regs, int access,
         * make sure we exit gracefully rather than endlessly redo
         * the fault.
         */
-       write = (access == VM_WRITE ||
-                (trans_exc_code & store_indication) == 0x400) ?
-               FAULT_FLAG_WRITE : 0;
-       fault = handle_mm_fault(mm, vma, address, write);
+       fault = handle_mm_fault(mm, vma, address, flags);
        if (unlikely(fault & VM_FAULT_ERROR))
                goto out_up;
 
-       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;
+               }
        }
        /*
         * The instruction that caused the program check will