[PATCH] Fix sys_move_pages when a NULL node list is passed

[pandora-kernel.git] / mm / truncate.c

diff --git a/mm/truncate.c b/mm/truncate.c
index c6ab55e..e07b1e6 100644 (file)
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -16,6 +17,32 @@
                                   do_invalidatepage */
 
 
+/**
+ * do_invalidatepage - invalidate part of all of a page
+ * @page: the page which is affected
+ * @offset: the index of the truncation point
+ *
+ * do_invalidatepage() is called when all or part of the page has become
+ * invalidated by a truncate operation.
+ *
+ * do_invalidatepage() does not have to release all buffers, but it must
+ * ensure that no dirty buffer is left outside @offset and that no I/O
+ * is underway against any of the blocks which are outside the truncation
+ * point.  Because the caller is about to free (and possibly reuse) those
+ * blocks on-disk.
+ */
+void do_invalidatepage(struct page *page, unsigned long offset)
+{
+       void (*invalidatepage)(struct page *, unsigned long);
+       invalidatepage = page->mapping->a_ops->invalidatepage;
+#ifdef CONFIG_BLOCK
+       if (!invalidatepage)
+               invalidatepage = block_invalidatepage;
+#endif
+       if (invalidatepage)
+               (*invalidatepage)(page, offset);
+}
+
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
        memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
@@ -52,36 +79,25 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 /*
  * This is for invalidate_inode_pages().  That function can be called at
  * any time, and is not supposed to throw away dirty pages.  But pages can
- * be marked dirty at any time too.  So we re-check the dirtiness inside
- * ->tree_lock.  That provides exclusion against the __set_page_dirty
- * functions.
+ * be marked dirty at any time too, so use remove_mapping which safely
+ * discards clean, unused pages.
  *
  * Returns non-zero if the page was successfully invalidated.
  */
 static int
 invalidate_complete_page(struct address_space *mapping, struct page *page)
 {
+       int ret;
+
        if (page->mapping != mapping)
                return 0;
 
        if (PagePrivate(page) && !try_to_release_page(page, 0))
                return 0;
 
-       write_lock_irq(&mapping->tree_lock);
-       if (PageDirty(page))
-               goto failed;
-       if (page_count(page) != 2)      /* caller's ref + pagecache ref */
-               goto failed;
+       ret = remove_mapping(mapping, page);
 
-       BUG_ON(PagePrivate(page));
-       __remove_from_page_cache(page);
-       write_unlock_irq(&mapping->tree_lock);
-       ClearPageUptodate(page);
-       page_cache_release(page);       /* pagecache ref */
-       return 1;
-failed:
-       write_unlock_irq(&mapping->tree_lock);
-       return 0;
+       return ret;
 }
 
 /**
@@ -270,9 +286,39 @@ unsigned long invalidate_inode_pages(struct address_space *mapping)
 {
        return invalidate_mapping_pages(mapping, 0, ~0UL);
 }
-
 EXPORT_SYMBOL(invalidate_inode_pages);
 
+/*
+ * This is like invalidate_complete_page(), except it ignores the page's
+ * refcount.  We do this because invalidate_inode_pages2() needs stronger
+ * invalidation guarantees, and cannot afford to leave pages behind because
+ * shrink_list() has a temp ref on them, or because they're transiently sitting
+ * in the lru_cache_add() pagevecs.
+ */
+static int
+invalidate_complete_page2(struct address_space *mapping, struct page *page)
+{
+       if (page->mapping != mapping)
+               return 0;
+
+       if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+               return 0;
+
+       write_lock_irq(&mapping->tree_lock);
+       if (PageDirty(page))
+               goto failed;
+
+       BUG_ON(PagePrivate(page));
+       __remove_from_page_cache(page);
+       write_unlock_irq(&mapping->tree_lock);
+       ClearPageUptodate(page);
+       page_cache_release(page);       /* pagecache ref */
+       return 1;
+failed:
+       write_unlock_irq(&mapping->tree_lock);
+       return 0;
+}
+
 /**
  * invalidate_inode_pages2_range - remove range of pages from an address_space
  * @mapping: the address_space
@@ -339,7 +385,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                                }
                        }
                        was_dirty = test_clear_page_dirty(page);
-                       if (!invalidate_complete_page(mapping, page)) {
+                       if (!invalidate_complete_page2(mapping, page)) {
                                if (was_dirty)
                                        set_page_dirty(page);
                                ret = -EIO;
@@ -349,6 +395,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                pagevec_release(&pvec);
                cond_resched();
        }
+       WARN_ON_ONCE(ret);
        return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);