X-Git-Url: http://pilppa.org/gitweb/?a=blobdiff_plain;f=mm%2Fmigrate.c;h=449d77d409f52622bbf825b7fd17d43df7ff5fbf;hb=26c9e17531d4b01943d3135c236a6a0f355c5163;hp=417bbda14e5b749b9c8512ac1b44ebcb31c346f1;hpb=8a9f3ccd24741b50200c3f33d62534c7271f3dfc;p=linux-2.6-omap-h63xx.git

diff --git a/mm/migrate.c b/mm/migrate.c
index 417bbda14e5..449d77d409f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -153,11 +153,6 @@ static void remove_migration_pte(struct vm_area_struct *vma,
  		return;
  	}
 
-	if (mem_cgroup_charge(new, mm)) {
-		pte_unmap(ptep);
-		return;
-	}
-
  	ptl = pte_lockptr(mm, pmd);
  	spin_lock(ptl);
 	pte = *ptep;
@@ -169,6 +164,20 @@ static void remove_migration_pte(struct vm_area_struct *vma,
 	if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
 		goto out;
 
+	/*
+	 * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
+	 * Failure is not an option here: we're now expected to remove every
+	 * migration pte, and will cause crashes otherwise.  Normally this
+	 * is not an issue: mem_cgroup_prepare_migration bumped up the old
+	 * page_cgroup count for safety, that's now attached to the new page,
+	 * so this charge should just be another incrementation of the count,
+	 * to keep in balance with rmap.c's mem_cgroup_uncharging.  But if
+	 * there's been a force_empty, those reference counts may no longer
+	 * be reliable, and this charge can actually fail: oh well, we don't
+	 * make the situation any worse by proceeding as if it had succeeded.
+	 */
+	mem_cgroup_charge(new, mm, GFP_ATOMIC);
+
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
@@ -374,7 +383,14 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 
 	if (PageDirty(page)) {
 		clear_page_dirty_for_io(page);
-		set_page_dirty(newpage);
+		/*
+		 * Want to mark the page and the radix tree as dirty, and
+		 * redo the accounting that clear_page_dirty_for_io undid,
+		 * but we can't use set_page_dirty because that function
+		 * is actually a signal that all of the page has become dirty.
+		 * Wheras only part of our page may be dirty.
+		 */
+		__set_page_dirty_nobuffers(newpage);
  	}
 
 #ifdef CONFIG_SWAP
@@ -593,9 +609,10 @@ static int move_to_new_page(struct page *newpage, struct page *page)
 	else
 		rc = fallback_migrate_page(mapping, newpage, page);
 
-	if (!rc)
+	if (!rc) {
+		mem_cgroup_page_migration(page, newpage);
 		remove_migration_ptes(page, newpage);
-	else
+	} else
 		newpage->mapping = NULL;
 
 	unlock_page(newpage);
@@ -614,6 +631,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	int *result = NULL;
 	struct page *newpage = get_new_page(page, private, &result);
 	int rcu_locked = 0;
+	int charge = 0;
 
 	if (!newpage)
 		return -ENOMEM;
@@ -673,14 +691,19 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		goto rcu_unlock;
 	}
 
+	charge = mem_cgroup_prepare_migration(page);
 	/* Establish migration ptes or remove ptes */
 	try_to_unmap(page, 1);
 
 	if (!page_mapped(page))
 		rc = move_to_new_page(newpage, page);
 
-	if (rc)
+	if (rc) {
 		remove_migration_ptes(page, page);
+		if (charge)
+			mem_cgroup_end_migration(page);
+	} else if (charge)
+ 		mem_cgroup_end_migration(newpage);
 rcu_unlock:
 	if (rcu_locked)
 		rcu_read_unlock();