Fix race in create_empty_buffers() vs __set_page_dirty_buffers()

Nick Piggin noticed this (very unlikely) race between setting a page
dirty and creating the buffers for it - we need to hold the mapping
private_lock until we've set the page dirty bit in order to make sure
that create_empty_buffers() might not build up a set of buffers without
the dirty bits set when the page is dirty.

I doubt anybody has ever hit this race (and it didn't solve the issue
Nick was looking at), but as Nick says: "Still, it does appear to solve
a real race, which we should close."

Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/buffer.c b/fs/buffer.c
index 9f697419ed8e34ec041c92d8f6794c8b4b06ab33..891e1c78e4f1cdf2fef0a5737983f245901371a3 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -760,15 +760,9 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
  */
-static int __set_page_dirty(struct page *page,
+static void __set_page_dirty(struct page *page,
                struct address_space *mapping, int warn)
 {
-       if (unlikely(!mapping))
-               return !TestSetPageDirty(page);
-
-       if (TestSetPageDirty(page))
-               return 0;
-
        spin_lock_irq(&mapping->tree_lock);
        if (page->mapping) {    /* Race with truncate? */
                WARN_ON_ONCE(warn && !PageUptodate(page));
@@ -785,8 +779,6 @@ static int __set_page_dirty(struct page *page,
        }
        spin_unlock_irq(&mapping->tree_lock);
        __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-
-       return 1;
 }
 
 /*
@@ -816,6 +808,7 @@ static int __set_page_dirty(struct page *page,
  */
 int __set_page_dirty_buffers(struct page *page)
 {
+       int newly_dirty;
        struct address_space *mapping = page_mapping(page);
 
        if (unlikely(!mapping))
@@ -831,9 +824,12 @@ int __set_page_dirty_buffers(struct page *page)
                        bh = bh->b_this_page;
                } while (bh != head);
        }
+       newly_dirty = !TestSetPageDirty(page);
        spin_unlock(&mapping->private_lock);
 
-       return __set_page_dirty(page, mapping, 1);
+       if (newly_dirty)
+               __set_page_dirty(page, mapping, 1);
+       return newly_dirty;
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
 
@@ -1262,8 +1258,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
                        return;
        }
 
-       if (!test_set_buffer_dirty(bh))
-               __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
+       if (!test_set_buffer_dirty(bh)) {
+               struct page *page = bh->b_page;
+               if (!TestSetPageDirty(page))
+                       __set_page_dirty(page, page_mapping(page), 0);
+       }
 }
 
 /*