> On Dec 23, 2021, at 11:07 PM, Nilesh Javali <njavali@xxxxxxxxxxx> wrote: > > From: Quinn Tran <qutran@xxxxxxxxxxx> > > QLA makes a call into midlayer (fc_remote_port_delete) which > can put the thread to sleep. The thread that originate the call > is in interrupt context. The combination of the 2 trigger a > crash. This patch schedule the call in non-interrupt context > where it is more safe. > > kernel: BUG: scheduling while atomic: swapper/7/0/0x00010000 > kernel: Call Trace: > kernel: <IRQ> > kernel: dump_stack+0x66/0x81 > kernel: __schedule_bug.cold.90+0x5/0x1d > kernel: __schedule+0x7af/0x960 > kernel: schedule+0x28/0x80 > kernel: schedule_timeout+0x26d/0x3b0 > kernel: wait_for_completion+0xb4/0x140 > kernel: ? wake_up_q+0x70/0x70 > kernel: __wait_rcu_gp+0x12c/0x160 > kernel: ? sdev_evt_alloc+0xc0/0x180 [scsi_mod] > kernel: synchronize_sched+0x6c/0x80 > kernel: ? call_rcu_bh+0x20/0x20 > kernel: ? __bpf_trace_rcu_invoke_callback+0x10/0x10 > kernel: sdev_evt_alloc+0xfd/0x180 [scsi_mod] > kernel: starget_for_each_device+0x85/0xb0 [scsi_mod] > kernel: ? scsi_init_io+0x360/0x3d0 [scsi_mod] > kernel: scsi_init_io+0x388/0x3d0 [scsi_mod] > kernel: device_for_each_child+0x54/0x90 > kernel: fc_remote_port_delete+0x70/0xe0 [scsi_transport_fc] > kernel: qla2x00_schedule_rport_del+0x62/0xf0 [qla2xxx] > kernel: qla2x00_mark_device_lost+0x9c/0xd0 [qla2xxx] > kernel: qla24xx_handle_plogi_done_event+0x55f/0x570 [qla2xxx] > kernel: qla2x00_async_login_sp_done+0xd2/0x100 [qla2xxx] > kernel: qla24xx_logio_entry+0x13a/0x3c0 [qla2xxx] > kernel: qla24xx_process_response_queue+0x306/0x400 [qla2xxx] > kernel: qla24xx_msix_rsp_q+0x3f/0xb0 [qla2xxx] > kernel: __handle_irq_event_percpu+0x40/0x180 > kernel: handle_irq_event_percpu+0x30/0x80 > kernel: handle_irq_event+0x36/0x60 > > Cc: stable@xxxxxxxxxxxxxxx > Signed-off-by: Quinn Tran <qutran@xxxxxxxxxxx> > Signed-off-by: Nilesh Javali <njavali@xxxxxxxxxxx> > --- > drivers/scsi/qla2xxx/qla_init.c | 7 +------ > 1 file changed, 1 insertion(+), 6 deletions(-) > > diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c > index e54c31296fab..ac25d2bfa90b 100644 > --- a/drivers/scsi/qla2xxx/qla_init.c > +++ b/drivers/scsi/qla2xxx/qla_init.c > @@ -2231,12 +2231,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) > ql_dbg(ql_dbg_disc, vha, 0x20eb, "%s %d %8phC cmd error %x\n", > __func__, __LINE__, ea->fcport->port_name, ea->data[1]); > > - ea->fcport->flags &= ~FCF_ASYNC_SENT; > - qla2x00_set_fcport_disc_state(ea->fcport, DSC_LOGIN_FAILED); > - if (ea->data[1] & QLA_LOGIO_LOGIN_RETRIED) > - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); > - else > - qla2x00_mark_device_lost(vha, ea->fcport, 1); > + qlt_schedule_sess_for_deletion(ea->fcport); > break; > case MBS_LOOP_ID_USED: > /* data[1] = IO PARAM 1 = nport ID */ > -- > 2.23.1 > Looks Good. Reviewed-by: Himanshu Madhani <himanshu.madhani@xxxxxxxxxx> -- Himanshu Madhani Oracle Linux Engineering
