scsi: qla2xxx: Fix scheduling while atomic

In the Linux kernel, the following vulnerability has been resolved:

scsi: qla2xxx: Fix scheduling while atomic

The driver makes a call into midlayer (fc_remote_port_delete) which can put

the thread to sleep. The thread that originates the call is in interrupt

context. The combination of the two trigger a crash. 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