[PATCH] msync: check pte dirty earlier

[Hugh Dickins]

From: Abhijit Karmarkar <abhijitk@xxxxxxxxxxx>

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 <abhijitk@xxxxxxxxxxx>
Signed-off-by: Hugh Dickins <hugh@xxxxxxxxxxx>
---

 include/asm-generic/pgtable.h |    3 +++
 mm/msync.c                    |    2 ++
 2 files changed, 5 insertions(+)

--- 2.6.12-rc6/include/asm-generic/pgtable.h	2005-05-25 18:09:09.000000000 +0100
+++ linux/include/asm-generic/pgtable.h	2005-06-04 20:41:55.000000000 +0100
@@ -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
--- 2.6.12-rc6/mm/msync.c	2005-05-25 18:09:21.000000000 +0100
+++ linux/mm/msync.c	2005-06-04 20:41:55.000000000 +0100
@@ -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;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/