4 files changed, 46 insertions, 24 deletions

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6bfaa6a4ec47..f0aef787a102 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -42,11 +42,11 @@ int ceph_init_dentry(struct dentry *dentry)
 
         if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
             ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
-                dentry->d_op = &ceph_dentry_ops;
+                d_set_d_op(dentry, &ceph_dentry_ops);
         else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
-                dentry->d_op = &ceph_snapdir_dentry_ops;
+                d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
         else
-                dentry->d_op = &ceph_snap_dentry_ops;
+                d_set_d_op(dentry, &ceph_snap_dentry_ops);
 
         di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
         if (!di)
@@ -113,7 +113,7 @@ static int __dcache_readdir(struct file *filp,
         dout("__dcache_readdir %p at %llu (last %p)\n", dir, filp->f_pos,
              last);
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
 
         /* start at beginning? */
         if (filp->f_pos == 2 || last == NULL ||
@@ -137,6 +137,7 @@ more:
                         fi->at_end = 1;
                         goto out_unlock;
                 }
+                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
                 if (!d_unhashed(dentry) && dentry->d_inode &&
                     ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
                     ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
@@ -146,13 +147,15 @@ more:
                      dentry->d_name.len, dentry->d_name.name, di->offset,
                      filp->f_pos, d_unhashed(dentry) ? " unhashed" : "",
                      !dentry->d_inode ? " null" : "");
+                spin_unlock(&dentry->d_lock);
                 p = p->prev;
                 dentry = list_entry(p, struct dentry, d_u.d_child);
                 di = ceph_dentry(dentry);
         }
 
-        atomic_inc(&dentry->d_count);
-        spin_unlock(&dcache_lock);
+        dget_dlock(dentry);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&parent->d_lock);
 
         dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
              dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -178,19 +181,19 @@ more:
 
         filp->f_pos++;
 
-        /* make sure a dentry wasn't dropped while we didn't have dcache_lock */
+        /* make sure a dentry wasn't dropped while we didn't have parent lock */
         if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
                 dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
                 err = -EAGAIN;
                 goto out;
         }
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         p = p->prev;    /* advance to next dentry */
         goto more;
 
 out_unlock:
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
 out:
         if (last)
                 dput(last);
@@ -988,7 +991,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
  */
 static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *dir = dentry->d_parent->d_inode;
+        struct inode *dir;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        dir = dentry->d_parent->d_inode;
 
         dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
              dentry->d_name.len, dentry->d_name.name, dentry->d_inode,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 50001de66c69..5625463aa479 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -370,6 +370,15 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
         return &ci->vfs_inode;
 }
 
+static void ceph_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct ceph_inode_info *ci = ceph_inode(inode);
+
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ceph_inode_cachep, ci);
+}
+
 void ceph_destroy_inode(struct inode *inode)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -409,7 +418,7 @@ void ceph_destroy_inode(struct inode *inode)
         if (ci->i_xattrs.prealloc_blob)
                 ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
-        kmem_cache_free(ceph_inode_cachep, ci);
+        call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
 
@@ -841,13 +850,13 @@ static void ceph_set_dentry_offset(struct dentry *dn)
         di->offset = ceph_inode(inode)->i_max_offset++;
         spin_unlock(&inode->i_lock);
 
-        spin_lock(&dcache_lock);
-        spin_lock(&dn->d_lock);
+        spin_lock(&dir->d_lock);
+        spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
         list_move(&dn->d_u.d_child, &dir->d_subdirs);
         dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
              dn->d_u.d_child.prev, dn->d_u.d_child.next);
         spin_unlock(&dn->d_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dir->d_lock);
 }
 
 /*
@@ -879,8 +888,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
         } else if (realdn) {
                 dout("dn %p (%d) spliced with %p (%d) "
                      "inode %p ino %llx.%llx\n",
-                     dn, atomic_read(&dn->d_count),
-                     realdn, atomic_read(&realdn->d_count),
+                     dn, dn->d_count,
+                     realdn, realdn->d_count,
                      realdn->d_inode, ceph_vinop(realdn->d_inode));
                 dput(dn);
                 dn = realdn;
@@ -1231,11 +1240,11 @@ retry_lookup:
                         goto retry_lookup;
                 } else {
                         /* reorder parent's d_subdirs */
-                        spin_lock(&dcache_lock);
-                        spin_lock(&dn->d_lock);
+                        spin_lock(&parent->d_lock);
+                        spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
                         list_move(&dn->d_u.d_child, &parent->d_subdirs);
                         spin_unlock(&dn->d_lock);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&parent->d_lock);
                 }
 
                 di = dn->d_fsdata;
@@ -1772,12 +1781,17 @@ int ceph_do_getattr(struct inode *inode, int mask)
  * Check inode permissions.  We verify we have a valid value for
  * the AUTH cap, then call the generic handler.
  */
-int ceph_permission(struct inode *inode, int mask)
+int ceph_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        int err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
+        int err;
+
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
 
         if (!err)
-                err = generic_permission(inode, mask, NULL);
+                err = generic_permission(inode, mask, flags, NULL);
         return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a6949cc7c69a..a1ee8fa3a8e7 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1502,7 +1502,7 @@ retry:
         *base = ceph_ino(temp->d_inode);
         *plen = len;
         dout("build_path on %p %d built %llx '%.*s'\n",
-             dentry, atomic_read(&dentry->d_count), *base, len, path);
+             dentry, dentry->d_count, *base, len, path);
         return path;
 }
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index c01aa646b407..88fcaa21b801 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -667,7 +667,7 @@ extern void ceph_queue_invalidate(struct inode *inode);
 extern void ceph_queue_writeback(struct inode *inode);
 
 extern int ceph_do_getattr(struct inode *inode, int mask);
-extern int ceph_permission(struct inode *inode, int mask);
+extern int ceph_permission(struct inode *inode, int mask, unsigned int flags);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
                         struct kstat *stat);