RDMA/rxe: Fix the use-before-initialization error of resp_pkts

In the following:

  Call Trace:
   <TASK>
   __dump_stack lib/dump_stack.c:88 [inline]
   dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106
   assign_lock_key kernel/locking/lockdep.c:982 [inline]
   register_lock_class+0xdb6/0x1120 kernel/locking/lockdep.c:1295
   __lock_acquire+0x10a/0x5df0 kernel/locking/lockdep.c:4951
   lock_acquire kernel/locking/lockdep.c:5691 [inline]
   lock_acquire+0x1b1/0x520 kernel/locking/lockdep.c:5656
   __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
   _raw_spin_lock_irqsave+0x3d/0x60 kernel/locking/spinlock.c:162
   skb_dequeue+0x20/0x180 net/core/skbuff.c:3639
   drain_resp_pkts drivers/infiniband/sw/rxe/rxe_comp.c:555 [inline]
   rxe_completer+0x250d/0x3cc0 drivers/infiniband/sw/rxe/rxe_comp.c:652
   rxe_qp_do_cleanup+0x1be/0x820 drivers/infiniband/sw/rxe/rxe_qp.c:761
   execute_in_process_context+0x3b/0x150 kernel/workqueue.c:3473
   __rxe_cleanup+0x21e/0x370 drivers/infiniband/sw/rxe/rxe_pool.c:233
   rxe_create_qp+0x3f6/0x5f0 drivers/infiniband/sw/rxe/rxe_verbs.c:583

This is a use-before-initialization problem.

It happens because rxe_qp_do_cleanup is called during error unwind before
the struct has been fully initialized.

Move the initialization of the skb earlier.

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20230602035408.741534-1-yanjun.zhu@intel.com
Reported-by: syzbot+eba589d8f49c73d356da@syzkaller.appspotmail.com
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 61a2eb77d9999ea135a509f02ea5a4ca6712163c..a0f206431cf8eb82d21573888290f2826367b803 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -176,6 +176,9 @@ static void rxe_qp_init_misc(struct rxe_dev *rxe, struct rxe_qp *qp,
        spin_lock_init(&qp->rq.producer_lock);
        spin_lock_init(&qp->rq.consumer_lock);
 
+       skb_queue_head_init(&qp->req_pkts);
+       skb_queue_head_init(&qp->resp_pkts);
+
        atomic_set(&qp->ssn, 0);
        atomic_set(&qp->skb_out, 0);
 }
@@ -234,8 +237,6 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
        qp->req.opcode          = -1;
        qp->comp.opcode         = -1;
 
-       skb_queue_head_init(&qp->req_pkts);
-
        rxe_init_task(&qp->req.task, qp, rxe_requester);
        rxe_init_task(&qp->comp.task, qp, rxe_completer);
 
@@ -279,8 +280,6 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp,
                }
        }
 
-       skb_queue_head_init(&qp->resp_pkts);
-
        rxe_init_task(&qp->resp.task, qp, rxe_responder);
 
        qp->resp.opcode         = OPCODE_NONE;