Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394...

[pandora-kernel.git] / mm / page-writeback.c

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8d9b19f..1d2fc89 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -21,6 +21,7 @@
 #include <linux/writeback.h>
 #include <linux/init.h>
 #include <linux/backing-dev.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/blkdev.h>
 #include <linux/mpage.h>
 #include <linux/rmap.h>
@@ -761,23 +762,24 @@ int __set_page_dirty_nobuffers(struct page *page)
                struct address_space *mapping = page_mapping(page);
                struct address_space *mapping2;
 
-               if (mapping) {
-                       write_lock_irq(&mapping->tree_lock);
-                       mapping2 = page_mapping(page);
-                       if (mapping2) { /* Race with truncate? */
-                               BUG_ON(mapping2 != mapping);
-                               if (mapping_cap_account_dirty(mapping))
-                                       __inc_zone_page_state(page,
-                                                               NR_FILE_DIRTY);
-                               radix_tree_tag_set(&mapping->page_tree,
-                                       page_index(page), PAGECACHE_TAG_DIRTY);
-                       }
-                       write_unlock_irq(&mapping->tree_lock);
-                       if (mapping->host) {
-                               /* !PageAnon && !swapper_space */
-                               __mark_inode_dirty(mapping->host,
-                                                       I_DIRTY_PAGES);
+               if (!mapping)
+                       return 1;
+
+               write_lock_irq(&mapping->tree_lock);
+               mapping2 = page_mapping(page);
+               if (mapping2) { /* Race with truncate? */
+                       BUG_ON(mapping2 != mapping);
+                       if (mapping_cap_account_dirty(mapping)) {
+                               __inc_zone_page_state(page, NR_FILE_DIRTY);
+                               task_io_account_write(PAGE_CACHE_SIZE);
                        }
+                       radix_tree_tag_set(&mapping->page_tree,
+                               page_index(page), PAGECACHE_TAG_DIRTY);
+               }
+               write_unlock_irq(&mapping->tree_lock);
+               if (mapping->host) {
+                       /* !PageAnon && !swapper_space */
+                       __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
                }
                return 1;
        }
@@ -842,39 +844,6 @@ int set_page_dirty_lock(struct page *page)
 }
 EXPORT_SYMBOL(set_page_dirty_lock);
 
-/*
- * Clear a page's dirty flag, while caring for dirty memory accounting. 
- * Returns true if the page was previously dirty.
- */
-int test_clear_page_dirty(struct page *page)
-{
-       struct address_space *mapping = page_mapping(page);
-       unsigned long flags;
-
-       if (mapping) {
-               write_lock_irqsave(&mapping->tree_lock, flags);
-               if (TestClearPageDirty(page)) {
-                       radix_tree_tag_clear(&mapping->page_tree,
-                                               page_index(page),
-                                               PAGECACHE_TAG_DIRTY);
-                       write_unlock_irqrestore(&mapping->tree_lock, flags);
-                       /*
-                        * We can continue to use `mapping' here because the
-                        * page is locked, which pins the address_space
-                        */
-                       if (mapping_cap_account_dirty(mapping)) {
-                               page_mkclean(page);
-                               dec_zone_page_state(page, NR_FILE_DIRTY);
-                       }
-                       return 1;
-               }
-               write_unlock_irqrestore(&mapping->tree_lock, flags);
-               return 0;
-       }
-       return TestClearPageDirty(page);
-}
-EXPORT_SYMBOL(test_clear_page_dirty);
-
 /*
  * Clear a page's dirty flag, while caring for dirty memory accounting.
  * Returns true if the page was previously dirty.
@@ -893,12 +862,41 @@ int clear_page_dirty_for_io(struct page *page)
 {
        struct address_space *mapping = page_mapping(page);
 
-       if (mapping) {
+       if (mapping && mapping_cap_account_dirty(mapping)) {
+               /*
+                * Yes, Virginia, this is indeed insane.
+                *
+                * We use this sequence to make sure that
+                *  (a) we account for dirty stats properly
+                *  (b) we tell the low-level filesystem to
+                *      mark the whole page dirty if it was
+                *      dirty in a pagetable. Only to then
+                *  (c) clean the page again and return 1 to
+                *      cause the writeback.
+                *
+                * This way we avoid all nasty races with the
+                * dirty bit in multiple places and clearing
+                * them concurrently from different threads.
+                *
+                * Note! Normally the "set_page_dirty(page)"
+                * has no effect on the actual dirty bit - since
+                * that will already usually be set. But we
+                * need the side effects, and it can help us
+                * avoid races.
+                *
+                * We basically use the page "master dirty bit"
+                * as a serialization point for all the different
+                * threads doing their things.
+                *
+                * FIXME! We still have a race here: if somebody
+                * adds the page back to the page tables in
+                * between the "page_mkclean()" and the "TestClearPageDirty()",
+                * we might have it mapped without the dirty bit set.
+                */
+               if (page_mkclean(page))
+                       set_page_dirty(page);
                if (TestClearPageDirty(page)) {
-                       if (mapping_cap_account_dirty(mapping)) {
-                               page_mkclean(page);
-                               dec_zone_page_state(page, NR_FILE_DIRTY);
-                       }
+                       dec_zone_page_state(page, NR_FILE_DIRTY);
                        return 1;
                }
                return 0;