[PATCH 5.4 12/98] smb3: Handle error case during offload read path

[Greg Kroah-Hartman]

From: Rohith Surabattula <rohiths@xxxxxxxxxxxxx>

commit 1254100030b3377e8302f9c75090ab191d73ee7c upstream.

Mid callback needs to be called only when valid data is
read into pages.

These patches address a problem found during decryption offload:
      CIFS: VFS: trying to dequeue a deleted mid
that could cause a refcount use after free:
      Workqueue: smb3decryptd smb2_decrypt_offload [cifs]

Signed-off-by: Rohith Surabattula <rohiths@xxxxxxxxxxxxx>
Reviewed-by: Pavel Shilovsky <pshilov@xxxxxxxxxxxxx>
CC: Stable <stable@xxxxxxxxxxxxxxx> #5.4+
Signed-off-by: Steve French <stfrench@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 fs/cifs/smb2ops.c |   20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4183,7 +4183,25 @@ static void smb2_decrypt_offload(struct
 				      dw->server->vals->read_rsp_size,
 				      dw->ppages, dw->npages, dw->len,
 				      true);
-		mid->callback(mid);
+		if (rc >= 0) {
+#ifdef CONFIG_CIFS_STATS2
+			mid->when_received = jiffies;
+#endif
+			mid->callback(mid);
+		} else {
+			spin_lock(&GlobalMid_Lock);
+			if (dw->server->tcpStatus == CifsNeedReconnect) {
+				mid->mid_state = MID_RETRY_NEEDED;
+				spin_unlock(&GlobalMid_Lock);
+				mid->callback(mid);
+			} else {
+				mid->mid_state = MID_REQUEST_SUBMITTED;
+				mid->mid_flags &= ~(MID_DELETED);
+				list_add_tail(&mid->qhead,
+					&dw->server->pending_mid_q);
+				spin_unlock(&GlobalMid_Lock);
+			}
+		}
 		cifs_mid_q_entry_release(mid);
 	}