[PATCH] fix garbage instead of zeroes in UFS

Looks like this is the problem, which point Al Viro some time ago:

ufs's get_block callback allocates 16k of disk at a time, and links that
entire 16k into the file's metadata.  But because get_block is called for only
a single buffer_head (a 2k buffer_head in this case?) we are only able to tell
the VFS that this 2k is buffer_new().

So when ufs_getfrag_block() is later called to map some more data in the file,
and when that data resides within the remaining 14k of this fragment,
ufs_getfrag_block() will incorrectly return a !buffer_new() buffer_head.

I don't see _right_ way to do nullification of whole block, if use inode
page cache, some pages may be outside of inode limits (inode size), and
will be lost; if use blockdev page cache it is possible to zero real data,
if later inode page cache will be used.

The simpliest way, as can I see usage of block device page cache, but not only
mark dirty, but also sync it during "nullification".  I use my simple tests
collection, which I used for check that create,open,write,read,close works on
ufs, and I see that this patch makes ufs code 18% slower then before.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 25 insertions, 0 deletions

diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index b82381475779..2e0021e8f366 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -275,6 +275,25 @@ static void ufs_change_blocknr(struct inode *inode, unsigned int baseblk,
         UFSD("EXIT\n");
 }
 
+static void ufs_clear_frags(struct inode *inode, sector_t beg, unsigned int n,
+                            int sync)
+{
+        struct buffer_head *bh;
+        sector_t end = beg + n;
+
+        for (; beg < end; ++beg) {
+                bh = sb_getblk(inode->i_sb, beg);
+                lock_buffer(bh);
+                memset(bh->b_data, 0, inode->i_sb->s_blocksize);
+                set_buffer_uptodate(bh);
+                mark_buffer_dirty(bh);
+                unlock_buffer(bh);
+                if (IS_SYNC(inode) || sync)
+                        sync_dirty_buffer(bh);
+                brelse(bh);
+        }
+}
+
 unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment,
                            unsigned goal, unsigned count, int * err, struct page *locked_page)
 {
@@ -350,6 +369,8 @@ unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment,
                         *p = cpu_to_fs32(sb, result);
                         *err = 0;
                         UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+                        ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+                                        locked_page != NULL);
                 }
                 unlock_super(sb);
                 UFSD("EXIT, result %u\n", result);
@@ -363,6 +384,8 @@ unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment,
         if (result) {
                 *err = 0;
                 UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+                ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+                                locked_page != NULL);
                 unlock_super(sb);
                 UFSD("EXIT, result %u\n", result);
                 return result;
@@ -398,6 +421,8 @@ unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment,
                 *p = cpu_to_fs32(sb, result);
                 *err = 0;
                 UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count);
+                ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
+                                locked_page != NULL);
                 unlock_super(sb);
                 if (newcount < request)
                         ufs_free_fragments (inode, result + newcount, request - newcount);