[PATCH] Make BH_Unwritten a first class bufferhead flag V2

Currently, XFS uses BH_PrivateStart for flagging unwritten extent state in a
bufferhead.  Recently, I found the long standing mmap/unwritten extent
conversion bug, and it was to do with partial page invalidation not clearing
the unwritten flag from bufferheads attached to the page but beyond EOF.  See
here for a full explaination:

http://oss.sgi.com/archives/xfs/2006-12/msg00196.html

The solution I have checked into the XFS dev tree involves duplicating code
from block_invalidatepage to clear the unwritten flag from the bufferhead(s),
and then calling block_invalidatepage() to do the rest.

Christoph suggested that this would be better solved by pushing the unwritten
flag into the common buffer head flags and just adding the call to
discard_buffer():

http://oss.sgi.com/archives/xfs/2006-12/msg00239.html

The following patch makes BH_Unwritten a first class citizen.

Signed-off-by: Dave Chinner <dgc@sgi.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 5 insertions, 11 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 7ff6e9346fae..a4b824234fb9 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1440,6 +1440,7 @@ static void discard_buffer(struct buffer_head * bh)
         clear_buffer_req(bh);
         clear_buffer_new(bh);
         clear_buffer_delay(bh);
+        clear_buffer_unwritten(bh);
         unlock_buffer(bh);
 }
 
@@ -1823,6 +1824,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page,
                         continue; 
                 }
                 if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
+                    !buffer_unwritten(bh) &&
                      (block_start < from || block_end > to)) {
                         ll_rw_block(READ, 1, &bh);
                         *wait_bh++=bh;
@@ -2544,7 +2546,7 @@ int block_truncate_page(struct address_space *mapping,
         if (PageUptodate(page))
                 set_buffer_uptodate(bh);
 
-        if (!buffer_uptodate(bh) && !buffer_delay(bh)) {
+        if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
                 err = -EIO;
                 ll_rw_block(READ, 1, &bh);
                 wait_on_buffer(bh);
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 2b0e0018738a..715adad7dd4d 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -109,16 +109,6 @@
 #undef  HAVE_PERCPU_SB  /* per cpu superblock counters are a 2.6 feature */
 #endif
 
-/*
- * State flag for unwritten extent buffers.
- *
- * We need to be able to distinguish between these and delayed
- * allocate buffers within XFS.  The generic IO path code does
- * not need to distinguish - we use the BH_Delay flag for both
- * delalloc and these ondisk-uninitialised buffers.
- */
-BUFFER_FNS(PrivateStart, unwritten);
-
 #define restricted_chown        xfs_params.restrict_chown.val
 #define irix_sgid_inherit       xfs_params.sgid_inherit.val
 #define irix_symlink_mode       xfs_params.symlink_mode.val
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 5d9fb0e94156..ffbdb6621f52 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -34,6 +34,7 @@ enum bh_state_bits {
         BH_Write_EIO,   /* I/O error on write */
         BH_Ordered,     /* ordered write */
         BH_Eopnotsupp,  /* operation not supported (barrier) */
+        BH_Unwritten,   /* Buffer is allocated on disk but not written */
 
         BH_PrivateStart,/* not a state bit, but the first bit available
                          * for private allocation by other entities
@@ -126,6 +127,7 @@ BUFFER_FNS(Boundary, boundary)
 BUFFER_FNS(Write_EIO, write_io_error)
 BUFFER_FNS(Ordered, ordered)
 BUFFER_FNS(Eopnotsupp, eopnotsupp)
+BUFFER_FNS(Unwritten, unwritten)
 
 #define bh_offset(bh)           ((unsigned long)(bh)->b_data & ~PAGE_MASK)
 #define touch_buffer(bh)        mark_page_accessed(bh->b_page)