ceph: fix buffer free while holding i_ceph_lock in __ceph_build_xattrs_blob()

Calling ceph_buffer_put() in __ceph_build_xattrs_blob() may result in
freeing the i_xattrs.blob buffer while holding the i_ceph_lock.  This can
be fixed by having this function returning the old blob buffer and have
the callers of this function freeing it when the lock is released.

The following backtrace was triggered by fstests generic/117.

  BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
  in_atomic(): 1, irqs_disabled(): 0, pid: 649, name: fsstress
  4 locks held by fsstress/649:
   #0: 00000000a7478e7e (&type->s_umount_key#19){++++}, at: iterate_supers+0x77/0xf0
   #1: 00000000f8de1423 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: ceph_check_caps+0x7b/0xc60
   #2: 00000000562f2b27 (&s->s_mutex){+.+.}, at: ceph_check_caps+0x3bd/0xc60
   #3: 00000000f83ce16a (&mdsc->snap_rwsem){++++}, at: ceph_check_caps+0x3ed/0xc60
  CPU: 1 PID: 649 Comm: fsstress Not tainted 5.2.0+ #439
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
  Call Trace:
   dump_stack+0x67/0x90
   ___might_sleep.cold+0x9f/0xb1
   vfree+0x4b/0x60
   ceph_buffer_release+0x1b/0x60
   __ceph_build_xattrs_blob+0x12b/0x170
   __send_cap+0x302/0x540
   ? __lock_acquire+0x23c/0x1e40
   ? __mark_caps_flushing+0x15c/0x280
   ? _raw_spin_unlock+0x24/0x30
   ceph_check_caps+0x5f0/0xc60
   ceph_flush_dirty_caps+0x7c/0x150
   ? __ia32_sys_fdatasync+0x20/0x20
   ceph_sync_fs+0x5a/0x130
   iterate_supers+0x8f/0xf0
   ksys_sync+0x4f/0xb0
   __ia32_sys_sync+0xa/0x10
   do_syscall_64+0x50/0x1c0
   entry_SYSCALL_64_after_hwframe+0x49/0xbe
  RIP: 0033:0x7fc6409ab617

Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 8 insertions, 3 deletions

diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index c083557b3657..939eab7aa219 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -754,12 +754,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
 
 /*
  * If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place.  It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
  */
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 {
 	struct rb_node *p;
 	struct ceph_inode_xattr *xattr = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	void *dest;
 
 	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
@@ -790,12 +793,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 			dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
 
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
 		ci->i_xattrs.prealloc_blob = NULL;
 		ci->i_xattrs.dirty = false;
 		ci->i_xattrs.version++;
 	}
+
+	return old_blob;
 }
 
 static inline int __get_request_mask(struct inode *in) {