From: Abhijit Karmarkar It's common practice to msync a large address range regularly, in which often only a few ptes have actually been dirtied since the previous pass. sync_pte_range then goes much faster if it tests whether pte is dirty before locating and accessing each struct page cacheline; and it is hardly slowed by ptep_clear_flush_dirty repeating that test in the opposite case, when every pte actually is dirty. But beware, s390's pte_dirty always says false, since its dirty bit is kept in the storage key, located via the struct page address. So skip this optimization in its case: use a pte_maybe_dirty macro which just says true if page_test_and_clear_dirty is implemented. Signed-off-by: Abhijit Karmarkar Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton --- include/asm-generic/pgtable.h | 3 +++ mm/msync.c | 2 ++ 2 files changed, 5 insertions(+) diff -puN include/asm-generic/pgtable.h~msync-check-pte-dirty-earlier include/asm-generic/pgtable.h --- 25/include/asm-generic/pgtable.h~msync-check-pte-dirty-earlier Mon Jun 6 15:25:13 2005 +++ 25-akpm/include/asm-generic/pgtable.h Mon Jun 6 15:25:13 2005 @@ -125,6 +125,9 @@ static inline void ptep_set_wrprotect(st #ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY #define page_test_and_clear_dirty(page) (0) +#define pte_maybe_dirty(pte) pte_dirty(pte) +#else +#define pte_maybe_dirty(pte) (1) #endif #ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG diff -puN mm/msync.c~msync-check-pte-dirty-earlier mm/msync.c --- 25/mm/msync.c~msync-check-pte-dirty-earlier Mon Jun 6 15:25:13 2005 +++ 25-akpm/mm/msync.c Mon Jun 6 15:25:13 2005 @@ -34,6 +34,8 @@ static void sync_pte_range(struct vm_are if (!pte_present(*pte)) continue; + if (!pte_maybe_dirty(*pte)) + continue; pfn = pte_pfn(*pte); if (!pfn_valid(pfn)) continue; _