Merge ../linux-2.6-watchdog-mm

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

diff --git a/mm/truncate.c b/mm/truncate.c
index 8fde658..5df947d 100644 (file)
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/buffer_head.h> /* grr. try_to_release_page,
                                   do_invalidatepage */
 
@@ -50,6 +51,33 @@ static inline void truncate_partial_page(struct page *page, unsigned partial)
                do_invalidatepage(page, partial);
 }
 
+/*
+ * This cancels just the dirty bit on the kernel page itself, it
+ * does NOT actually remove dirty bits on any mmap's that may be
+ * around. It also leaves the page tagged dirty, so any sync
+ * activity will still find it on the dirty lists, and in particular,
+ * clear_page_dirty_for_io() will still look at the dirty bits in
+ * the VM.
+ *
+ * Doing this should *normally* only ever be done when a page
+ * is truncated, and is not actually mapped anywhere at all. However,
+ * fs/buffer.c does this when it notices that somebody has cleaned
+ * out all the buffers on a page without actually doing it through
+ * the VM. Can you say "ext3 is horribly ugly"? Tought you could.
+ */
+void cancel_dirty_page(struct page *page, unsigned int account_size)
+{
+       if (TestClearPageDirty(page)) {
+               struct address_space *mapping = page->mapping;
+               if (mapping && mapping_cap_account_dirty(mapping)) {
+                       dec_zone_page_state(page, NR_FILE_DIRTY);
+                       if (account_size)
+                               task_io_account_cancelled_write(account_size);
+               }
+       }
+}
+EXPORT_SYMBOL(cancel_dirty_page);
+
 /*
  * If truncate cannot remove the fs-private metadata from the page, the page
  * becomes anonymous.  It will be left on the LRU and may even be mapped into
@@ -66,10 +94,11 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
        if (page->mapping != mapping)
                return;
 
+       cancel_dirty_page(page, PAGE_CACHE_SIZE);
+
        if (PagePrivate(page))
                do_invalidatepage(page, 0);
 
-       clear_page_dirty(page);
        ClearPageUptodate(page);
        ClearPageMappedToDisk(page);
        remove_from_page_cache(page);
@@ -96,7 +125,6 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
                return 0;
 
        ret = remove_mapping(mapping, page);
-       ClearPageUptodate(page);
 
        return ret;
 }
@@ -287,9 +315,48 @@ 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;
+}
+
+static int do_launder_page(struct address_space *mapping, struct page *page)
+{
+       if (!PageDirty(page))
+               return 0;
+       if (page->mapping != mapping || mapping->a_ops->launder_page == NULL)
+               return 0;
+       return mapping->a_ops->launder_page(page);
+}
+
 /**
  * invalidate_inode_pages2_range - remove range of pages from an address_space
  * @mapping: the address_space
@@ -319,7 +386,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                for (i = 0; !ret && i < pagevec_count(&pvec); i++) {
                        struct page *page = pvec.pages[i];
                        pgoff_t page_index;
-                       int was_dirty;
 
                        lock_page(page);
                        if (page->mapping != mapping) {
@@ -355,12 +421,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                                          PAGE_CACHE_SIZE, 0);
                                }
                        }
-                       was_dirty = test_clear_page_dirty(page);
-                       if (!invalidate_complete_page(mapping, page)) {
-                               if (was_dirty)
-                                       set_page_dirty(page);
+                       ret = do_launder_page(mapping, page);
+                       if (ret == 0 && !invalidate_complete_page2(mapping, page))
                                ret = -EIO;
-                       }
                        unlock_page(page);
                }
                pagevec_release(&pvec);