This patch fixes following deadlock caused by destroying of
an FCoE interface with active NPIV ports on that interface.
Call Trace:
[<ffffffff814b7e88>] schedule+0x64/0x66
[<ffffffff814b6b4f>] schedule_timeout+0x36/0xe3
[<ffffffff81070c55>] ? update_curr+0xd6/0x110
[<ffffffff81071f6b>] ? hrtick_update+0x1b/0x4d
[<ffffffff81072405>] ? dequeue_task_fair+0x1ca/0x1d9
[<ffffffff8106a369>] ? need_resched+0x1e/0x28
[<ffffffff814b7d14>] wait_for_common+0x9b/0xf1
[<ffffffff8106e7be>] ? try_to_wake_up+0x1e0/0x1e0
[<ffffffff814b7e22>] wait_for_completion+0x1d/0x1f
[<ffffffff8105ae82>] flush_workqueue+0x116/0x2a1
[<ffffffff8105b357>] drain_workqueue+0x66/0x14c
[<ffffffff8105b8ef>] destroy_workqueue+0x1a/0xcf
[<ffffffffa009211e>] fc_remove_host+0x154/0x17f [scsi_transport_fc]
[<ffffffffa00edbb8>] fcoe_if_destroy+0x184/0x1c9 [fcoe]
[<ffffffffa00edc28>] fcoe_destroy_work+0x2b/0x44 [fcoe]
[<ffffffff8105a82a>] process_one_work+0x1a8/0x2a4
[<ffffffffa00edbfd>] ? fcoe_if_destroy+0x1c9/0x1c9 [fcoe]
[<ffffffff8105c396>] worker_thread+0x1db/0x268
[<ffffffff810604a3>] ? wake_up_bit+0x2a/0x2a
[<ffffffff8105c1bb>] ? manage_workers.clone.16+0x1f6/0x1f6
[<ffffffff8105ffd6>] kthread+0x6f/0x77
[<ffffffff814c0304>] kernel_thread_helper+0x4/0x10
[<ffffffff8105ff67>] ? kthread_freezable_should_stop+0x4b/0x4b
Call Trace:
[<ffffffff814b7e88>] schedule+0x64/0x66
[<ffffffff814b8041>] schedule_preempt_disabled+0xe/0x10
[<ffffffff814b70a1>] __mutex_lock_common.clone.5+0x117/0x17a
[<ffffffff814b7117>] __mutex_lock_slowpath+0x13/0x15
[<ffffffff814b6f76>] mutex_lock+0x23/0x37
[<ffffffff8125b890>] ? list_del+0x11/0x30
[<ffffffffa00edc84>] fcoe_vport_destroy+0x43/0x5f [fcoe]
[<ffffffffa009130a>] fc_vport_terminate+0x48/0x110 [scsi_transport_fc]
[<ffffffffa00913ef>] fc_vport_sched_delete+0x1d/0x79 [scsi_transport_fc]
[<ffffffff8105a82a>] process_one_work+0x1a8/0x2a4
[<ffffffffa00913d2>] ? fc_vport_terminate+0x110/0x110 [scsi_transport_fc]
[<ffffffff8105c396>] worker_thread+0x1db/0x268
[<ffffffff8105c1bb>] ? manage_workers.clone.16+0x1f6/0x1f6
[<ffffffff8105ffd6>] kthread+0x6f/0x77
[<ffffffff814c0304>] kernel_thread_helper+0x4/0x10
[<ffffffff8105ff67>] ? kthread_freezable_should_stop+0x4b/0x4b
[<ffffffff814c0300>] ? gs_change+0x13/0x13
There is no need to grab the fcoe_config_mutex for the NPIV port
deletion path; and it can be protected by the physical port's
mutex. Hence, removing the fcoe_config_mutex usage from the
fcoe_vport_destroy() routine. Also, an additional check has been
added to make sure the NPIV port is still present in the physical
port's vport list before continuing with destroying of the NPIV port.
Signed-off-by: Neerav Parikh <neerav.par...@intel.com>
Tested-by: Ross Brattain <ross.b.bratt...@intel.com>
---
drivers/scsi/fcoe/fcoe.c | 19 +++++++++++++++----
1 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 666b7ac..ff5e45b 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -2712,14 +2712,25 @@ static int fcoe_vport_destroy(struct fc_vport *vport)
struct Scsi_Host *shost = vport_to_shost(vport);
struct fc_lport *n_port = shost_priv(shost);
struct fc_lport *vn_port = vport->dd_data;
+ struct fc_lport *v_port;
+ bool found = false;
mutex_lock(&n_port->lp_mutex);
- list_del(&vn_port->list);
- mutex_unlock(&n_port->lp_mutex);
+ list_for_each_entry(v_port, &n_port->vports, list) {
+ if (v_port->vport == vport) {
+ found = true;
+ break;
+ }
+ }
- mutex_lock(&fcoe_config_mutex);
+ if (!found) {
+ mutex_unlock(&n_port->lp_mutex);
+ return -ENOENT;
+ }
+
+ list_del(&vn_port->list);
fcoe_if_destroy(vn_port);
- mutex_unlock(&fcoe_config_mutex);
+ mutex_unlock(&n_port->lp_mutex);
return 0;
}
_______________________________________________
devel mailing list
devel@open-fcoe.org
https://lists.open-fcoe.org/mailman/listinfo/devel
