Revise the interface between vm_object_madvise() and vm_page_dontneed() so

that pointless calls to pmap_is_modified() can be easily avoided when
performing madvise(..., MADV_FREE).

Sponsored by:	EMC / Isilon Storage Division

3 files changed, 30 insertions, 31 deletions

diff --git a/sys/vm/vm_object.c b/sys/vm/vm_object.c
index 9ddd141..97d8557 100644
--- a/sys/vm/vm_object.c
+++ b/sys/vm/vm_object.c
@@ -1175,28 +1175,8 @@ shadowlookup:
 		}
 		if (advise == MADV_WILLNEED) {
 			vm_page_activate(m);
-		} else if (advise == MADV_DONTNEED) {
-			vm_page_dontneed(m);
-		} else if (advise == MADV_FREE) {
-			/*
-			 * Mark the page clean.  This will allow the page
-			 * to be freed up by the system.  However, such pages
-			 * are often reused quickly by malloc()/free()
-			 * so we do not do anything that would cause
-			 * a page fault if we can help it.
-			 *
-			 * Specifically, we do not try to actually free
-			 * the page now nor do we try to put it in the
-			 * cache (which would cause a page fault on reuse).
-			 *
-			 * But we do make the page is freeable as we
-			 * can without actually taking the step of unmapping
-			 * it.
-			 */
-			pmap_clear_modify(m);
-			m->dirty = 0;
-			m->act_count = 0;
-			vm_page_dontneed(m);
+		} else {
+			vm_page_advise(m, advise);
 		}
 		vm_page_unlock(m);
 		if (advise == MADV_FREE && tobject->type == OBJT_SWAP)
diff --git a/sys/vm/vm_page.c b/sys/vm/vm_page.c
index 300b20a..2dde31f 100644
--- a/sys/vm/vm_page.c
+++ b/sys/vm/vm_page.c
@@ -93,6 +93,7 @@ __FBSDID("$FreeBSD$");
 #include <sys/kernel.h>
 #include <sys/limits.h>
 #include <sys/malloc.h>
+#include <sys/mman.h>
 #include <sys/msgbuf.h>
 #include <sys/mutex.h>
 #include <sys/proc.h>
@@ -2238,15 +2239,15 @@ vm_page_cache(vm_page_t m)
 }
 
 /*
- * vm_page_dontneed
+ * vm_page_advise
  *
  *	Cache, deactivate, or do nothing as appropriate.  This routine
- *	is typically used by madvise() MADV_DONTNEED.
+ *	is used by madvise().
  *
  *	Generally speaking we want to move the page into the cache so
  *	it gets reused quickly.  However, this can result in a silly syndrome
  *	due to the page recycling too quickly.  Small objects will not be
- *	fully cached.  On the otherhand, if we move the page to the inactive
+ *	fully cached.  On the other hand, if we move the page to the inactive
  *	queue we wind up with a problem whereby very large objects 
  *	unnecessarily blow away our inactive and cache queues.
  *
@@ -2261,13 +2262,31 @@ vm_page_cache(vm_page_t m)
  *	The object and page must be locked.
  */
 void
-vm_page_dontneed(vm_page_t m)
+vm_page_advise(vm_page_t m, int advice)
 {
-	int dnw;
-	int head;
+	int dnw, head;
 
-	vm_page_lock_assert(m, MA_OWNED);
+	vm_page_assert_locked(m);
 	VM_OBJECT_ASSERT_WLOCKED(m->object);
+	if (advice == MADV_FREE) {
+		/*
+		 * Mark the page clean.  This will allow the page to be freed
+		 * up by the system.  However, such pages are often reused
+		 * quickly by malloc() so we do not do anything that would
+		 * cause a page fault if we can help it.
+		 *
+		 * Specifically, we do not try to actually free the page now
+		 * nor do we try to put it in the cache (which would cause a
+		 * page fault on reuse).
+		 *
+		 * But we do make the page is freeable as we can without
+		 * actually taking the step of unmapping it.
+		 */
+		pmap_clear_modify(m);
+		m->dirty = 0;
+		m->act_count = 0;
+	} else if (advice != MADV_DONTNEED)
+		return;
 	dnw = PCPU_GET(dnweight);
 	PCPU_INC(dnweight);
 
@@ -2294,7 +2313,7 @@ vm_page_dontneed(vm_page_t m)
 	pmap_clear_reference(m);
 	vm_page_aflag_clear(m, PGA_REFERENCED);
 
-	if (m->dirty == 0 && pmap_is_modified(m))
+	if (advice != MADV_FREE && m->dirty == 0 && pmap_is_modified(m))
 		vm_page_dirty(m);
 
 	if (m->dirty || (dnw & 0x0070) == 0) {
diff --git a/sys/vm/vm_page.h b/sys/vm/vm_page.h
index e8b0795..4fe5d7e 100644
--- a/sys/vm/vm_page.h
+++ b/sys/vm/vm_page.h
@@ -370,6 +370,7 @@ void vm_page_free_zero(vm_page_t m);
 void vm_page_wakeup(vm_page_t m);
 
 void vm_page_activate (vm_page_t);
+void vm_page_advise(vm_page_t m, int advice);
 vm_page_t vm_page_alloc (vm_object_t, vm_pindex_t, int);
 vm_page_t vm_page_alloc_contig(vm_object_t object, vm_pindex_t pindex, int req,
     u_long npages, vm_paddr_t low, vm_paddr_t high, u_long alignment,
@@ -381,7 +382,6 @@ void vm_page_cache_free(vm_object_t, vm_pindex_t, vm_pindex_t);
 void vm_page_cache_transfer(vm_object_t, vm_pindex_t, vm_object_t);
 int vm_page_try_to_cache (vm_page_t);
 int vm_page_try_to_free (vm_page_t);
-void vm_page_dontneed(vm_page_t);
 void vm_page_deactivate (vm_page_t);
 void vm_page_dequeue(vm_page_t m);
 void vm_page_dequeue_locked(vm_page_t m);