X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmlock.c;h=2b8335a8940052874a18a9b3657c830c61e13284;hb=7707e61c70999a1f9f1fd9ac92e293c198585152;hp=e13918d4fc4f89ce6f48dd2782e9c503f2c4b7e4;hpb=408e82b78bcc9f1b47c76e833c3df97f675947de;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/mlock.c b/mm/mlock.c
index e13918d..2b8335a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -88,25 +88,22 @@ void mlock_vma_page(struct page *page)
 	}
 }
 
-/*
- * called from munlock()/munmap() path with page supposedly on the LRU.
+/**
+ * munlock_vma_page - munlock a vma page
+ * @page - page to be unlocked
  *
- * Note:  unlike mlock_vma_page(), we can't just clear the PageMlocked
- * [in try_to_munlock()] and then attempt to isolate the page.  We must
- * isolate the page to keep others from messing with its unevictable
- * and mlocked state while trying to munlock.  However, we pre-clear the
- * mlocked state anyway as we might lose the isolation race and we might
- * not get another chance to clear PageMlocked.  If we successfully
- * isolate the page and try_to_munlock() detects other VM_LOCKED vmas
- * mapping the page, it will restore the PageMlocked state, unless the page
- * is mapped in a non-linear vma.  So, we go ahead and SetPageMlocked(),
- * perhaps redundantly.
- * If we lose the isolation race, and the page is mapped by other VM_LOCKED
- * vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
- * either of which will restore the PageMlocked state by calling
- * mlock_vma_page() above, if it can grab the vma's mmap sem.
+ * called from munlock()/munmap() path with page supposedly on the LRU.
+ * When we munlock a page, because the vma where we found the page is being
+ * munlock()ed or munmap()ed, we want to check whether other vmas hold the
+ * page locked so that we can leave it on the unevictable lru list and not
+ * bother vmscan with it.  However, to walk the page's rmap list in
+ * try_to_munlock() we must isolate the page from the LRU.  If some other
+ * task has removed the page from the LRU, we won't be able to do that.
+ * So we clear the PageMlocked as we might not get another chance.  If we
+ * can't isolate the page, we leave it for putback_lru_page() and vmscan
+ * [page_referenced()/try_to_unmap()] to deal with.
  */
-static void munlock_vma_page(struct page *page)
+void munlock_vma_page(struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 
@@ -117,18 +114,18 @@ static void munlock_vma_page(struct page *page)
 			/*
 			 * did try_to_unlock() succeed or punt?
 			 */
-			if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
+			if (ret != SWAP_MLOCK)
 				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
 
 			putback_lru_page(page);
 		} else {
 			/*
-			 * We lost the race.  let try_to_unmap() deal
-			 * with it.  At least we get the page state and
-			 * mlock stats right.  However, page is still on
-			 * the noreclaim list.  We'll fix that up when
-			 * the page is eventually freed or we scan the
-			 * noreclaim list.
+			 * Some other task has removed the page from the LRU.
+			 * putback_lru_page() will take care of removing the
+			 * page from the unevictable list, if necessary.
+			 * vmscan [page_referenced()] will move the page back
+			 * to the unevictable list if some other vma has it
+			 * mlocked.
 			 */
 			if (PageUnevictable(page))
 				count_vm_event(UNEVICTABLE_PGSTRANDED);
@@ -166,9 +163,9 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	VM_BUG_ON(end   > vma->vm_end);
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
-	gup_flags = 0;
+	gup_flags = FOLL_TOUCH | FOLL_GET;
 	if (vma->vm_flags & VM_WRITE)
-		gup_flags = GUP_FLAGS_WRITE;
+		gup_flags |= FOLL_WRITE;
 
 	while (nr_pages > 0) {
 		int i;
@@ -198,17 +195,26 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 		for (i = 0; i < ret; i++) {
 			struct page *page = pages[i];
 
-			lock_page(page);
-			/*
-			 * Because we lock page here and migration is blocked
-			 * by the elevated reference, we need only check for
-			 * file-cache page truncation.  This page->mapping
-			 * check also neatly skips over the ZERO_PAGE(),
-			 * though if that's common we'd prefer not to lock it.
-			 */
-			if (page->mapping)
-				mlock_vma_page(page);
-			unlock_page(page);
+			if (page->mapping) {
+				/*
+				 * That preliminary check is mainly to avoid
+				 * the pointless overhead of lock_page on the
+				 * ZERO_PAGE: which might bounce very badly if
+				 * there is contention.  However, we're still
+				 * dirtying its cacheline with get/put_page:
+				 * we'll add another __get_user_pages flag to
+				 * avoid it if that case turns out to matter.
+				 */
+				lock_page(page);
+				/*
+				 * Because we lock page here and migration is
+				 * blocked by the elevated reference, we need
+				 * only check for file-cache page truncation.
+				 */
+				if (page->mapping)
+					mlock_vma_page(page);
+				unlock_page(page);
+			}
 			put_page(page);	/* ref from get_user_pages() */
 		}
 
@@ -309,9 +315,23 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 	vma->vm_flags &= ~VM_LOCKED;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		struct page *page = follow_page(vma, addr, FOLL_GET);
-		if (page) {
+		struct page *page;
+		/*
+		 * Although FOLL_DUMP is intended for get_dump_page(),
+		 * it just so happens that its special treatment of the
+		 * ZERO_PAGE (returning an error instead of doing get_page)
+		 * suits munlock very well (and if somehow an abnormal page
+		 * has sneaked into the range, we won't oops here: great).
+		 */
+		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
+		if (page && !IS_ERR(page)) {
 			lock_page(page);
+			/*
+			 * Like in __mlock_vma_pages_range(),
+			 * because we lock page here and migration is
+			 * blocked by the elevated reference, we need
+			 * only check for file-cache page truncation.
+			 */
 			if (page->mapping)
 				munlock_vma_page(page);
 			unlock_page(page);