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

[ Upstream commit af8a85a4 ]

Calling ceph_buffer_put() in fill_inode() may result in freeing the
i_xattrs.blob buffer while holding the i_ceph_lock.  This can be fixed by
postponing the call until later, when the lock is released.

The following backtrace was triggered by fstests generic/070.

  BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
  in_atomic(): 1, irqs_disabled(): 0, pid: 3852, name: kworker/0:4
  6 locks held by kworker/0:4/3852:
   #0: 000000004270f6bb ((wq_completion)ceph-msgr){+.+.}, at: process_one_work+0x1b8/0x5f0
   #1: 00000000eb420803 ((work_completion)(&(&con->work)->work)){+.+.}, at: process_one_work+0x1b8/0x5f0
   #2: 00000000be1c53a4 (&s->s_mutex){+.+.}, at: dispatch+0x288/0x1476
   #3: 00000000559cb958 (&mdsc->snap_rwsem){++++}, at: dispatch+0x2eb/0x1476
   #4: 000000000d5ebbae (&req->r_fill_mutex){+.+.}, at: dispatch+0x2fc/0x1476
   #5: 00000000a83d0514 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: fill_inode.isra.0+0xf8/0xf70
  CPU: 0 PID: 3852 Comm: kworker/0:4 Not tainted 5.2.0+ #441
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
  Workqueue: ceph-msgr ceph_con_workfn
  Call Trace:
   dump_stack+0x67/0x90
   ___might_sleep.cold+0x9f/0xb1
   vfree+0x4b/0x60
   ceph_buffer_release+0x1b/0x60
   fill_inode.isra.0+0xa9b/0xf70
   ceph_fill_trace+0x13b/0xc70
   ? dispatch+0x2eb/0x1476
   dispatch+0x320/0x1476
   ? __mutex_unlock_slowpath+0x4d/0x2a0
   ceph_con_workfn+0xc97/0x2ec0
   ? process_one_work+0x1b8/0x5f0
   process_one_work+0x244/0x5f0
   worker_thread+0x4d/0x3e0
   kthread+0x105/0x140
   ? process_one_work+0x5f0/0x5f0
   ? kthread_park+0x90/0x90
   ret_from_fork+0x3a/0x50
Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

fs/ceph/inode.c

@@ -742,6 +742,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	int issued, new_issued, info_caps;
 	struct timespec64 mtime, atime, ctime;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	struct ceph_string *pool_ns = NULL;
 	struct ceph_cap *new_cap = NULL;
 	int err = 0;
@@ -878,7 +879,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))  &&
 	    le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = xattr_blob;
 		if (xattr_blob)
 			memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1017,7 +1018,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 out:
 	if (new_cap)
 		ceph_put_cap(mdsc, new_cap);
-	if (xattr_blob)
+	ceph_buffer_put(old_blob);
 	ceph_buffer_put(xattr_blob);
 	ceph_put_string(pool_ns);
 	return err;