In case siw module can't be inserted successfully, and if the kthread
(siw_run_sq) is not run which means wait_queue_head (tx_task->waiting)
is not initialized. Then siw_stop_tx_thread is called from siw_init_module,
so below trace appeared.
kernel: BUG: spinlock bad magic on CPU#0, modprobe/2073
kernel: lock: 0xffff88babbd380e8, .magic: 00000000, .owner: <none>/-1, .owner_cpu: 0
kernel: CPU: 0 PID: 2073 Comm: modprobe Tainted: G OE 6.5.0-rc3+ #16
kernel: Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552c-rebuilt.opensuse.org 04/01/2014
kernel: Call Trace:
kernel: <TASK>
kernel: dump_stack_lvl+0x77/0xd0
kernel: dump_stack+0x10/0x20
kernel: spin_bug+0xa5/0xd0
kernel: do_raw_spin_lock+0x90/0xd0
kernel: _raw_spin_lock_irqsave+0x56/0x80
kernel: ? __wake_up_common_lock+0x63/0xd0
kernel: __wake_up_common_lock+0x63/0xd0
kernel: __wake_up+0x13/0x30
kernel: siw_stop_tx_thread+0x49/0x70 [siw]
kernel: siw_init_module+0x15b/0xff0 [siw]
kernel: ? __pfx_siw_init_module+0x10/0x10 [siw]
kernel: do_one_initcall+0x60/0x390
...
kernel: </TASK>
kernel: BUG: kernel NULL pointer dereference, address: 0000000000000000
To prevent the issue, add 'running' to tx_task_t, which is set to after
siw_run_sq is triggered. Then only wake up waitqueue after it is true.
Signed-off-by: Guoqing Jiang <guoqing.jiang@xxxxxxxxx>
---
drivers/infiniband/sw/siw/siw_qp_tx.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 7c7a51d36d0c..70acc4cd553f 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -1204,14 +1204,18 @@ static void siw_sq_resume(struct siw_qp *qp)
struct tx_task_t {
struct llist_head active;
wait_queue_head_t waiting;
+ bool running;
};
static DEFINE_PER_CPU(struct tx_task_t, siw_tx_task_g);
void siw_stop_tx_thread(int nr_cpu)
{
+ struct tx_task_t *tx_task = &per_cpu(siw_tx_task_g, nr_cpu);
+
kthread_stop(siw_tx_thread[nr_cpu]);
- wake_up(&per_cpu(siw_tx_task_g, nr_cpu).waiting);
+ if (tx_task->running)
+ wake_up(&per_cpu(siw_tx_task_g, nr_cpu).waiting);
}
int siw_run_sq(void *data)
@@ -1223,6 +1227,7 @@ int siw_run_sq(void *data)
init_llist_head(&tx_task->active);
init_waitqueue_head(&tx_task->waiting);
+ tx_task->running = true;
while (1) {
struct llist_node *fifo_list = NULL;
--
2.34.1
