ceph: fix __dcache_readdir()

If directory is fragmented, readdir() read its dirfrags one by one.
After reading all dirfrags, the corresponding dentries are sorted in
(frag_t, off) order in the dcache. If dentries of a directory are all
cached, __dcache_readdir() can use the cached dentries to satisfy
readdir syscall. But when checking if a given dentry is after the
position of readdir, __dcache_readdir() compares numerical value of
frag_t directly. This is wrong, it should use ceph_frag_compare().

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 2e3b30d..45eda6d 100644 (file)
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p)
        return p & 0xffffffff;
 }
 
+static int fpos_cmp(loff_t l, loff_t r)
+{
+       int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+       if (v)
+               return v;
+       return (int)(fpos_off(l) - fpos_off(r));
+}
+
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
@@ -156,7 +164,7 @@ more:
                if (!d_unhashed(dentry) && dentry->d_inode &&
                    ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
                    ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
-                   ctx->pos <= di->offset)
+                   fpos_cmp(ctx->pos, di->offset) <= 0)
                        break;
                dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
                     dentry->d_name.len, dentry->d_name.name, di->offset,