From: Ahmed Zaki <[email protected]>
If a reset event is received from the PF early in the init cycle, the
state machine hangs for about 25 seconds.
Reproducer:
echo 1 > /sys/class/net/$PF0/device/sriov_numvfs
ip link set dev $PF0 vf 0 mac $NEW_MAC
The log shows:
[792.620416] ice 0000:5e:00.0: Enabling 1 VFs
[792.738812] iavf 0000:5e:01.0: enabling device (0000 -> 0002)
[792.744182] ice 0000:5e:00.0: Enabling 1 VFs with 17 vectors and 16 queues
per VF
[792.839964] ice 0000:5e:00.0: Setting MAC 52:54:00:00:00:11 on VF 0. VF
driver will be reinitialized
[813.389684] iavf 0000:5e:01.0: Failed to communicate with PF; waiting before
retry
[818.635918] iavf 0000:5e:01.0: Hardware came out of reset. Attempting reinit.
[818.766273] iavf 0000:5e:01.0: Multiqueue Enabled: Queue pair count = 16
Fix it by scheduling the reset task and making the reset task capable of
resetting early in the init cycle.
Fixes: ef8693eb90ae3 ("i40evf: refactor reset handling")
Signed-off-by: Ahmed Zaki <[email protected]>
Tested-by: Przemek Kitszel <[email protected]>
Reviewed-by: Przemek Kitszel <[email protected]>
Signed-off-by: Marcin Szycik <[email protected]>
---
This should be applied after "iavf: get rid of the crit lock"
---
drivers/net/ethernet/intel/iavf/iavf_main.c | 11 +++++++++++
drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 17 +++++++++++++++++
2 files changed, 28 insertions(+)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c
b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2c0bb41809a4..81d7249d1149 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work)
}
continue_reset:
+ /* If we are still early in the state machine, just restart. */
+ if (adapter->state <= __IAVF_INIT_FAILED) {
+ iavf_shutdown_adminq(hw);
+ iavf_change_state(adapter, __IAVF_STARTUP);
+ iavf_startup(adapter);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ msecs_to_jiffies(30));
+ netdev_unlock(netdev);
+ return;
+ }
+
/* We don't use netif_running() because it may be true prior to
* ndo_open() returning, so we can't assume it means all our open
* tasks have finished, since we're not holding the rtnl_lock here.
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index a6f0e5990be2..07f0d0a0f1e2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -79,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct
iavf_arq_event_info *event,
return iavf_status_to_errno(status);
received_op =
(enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high);
+
+ if (received_op == VIRTCHNL_OP_EVENT) {
+ struct iavf_adapter *adapter = hw->back;
+ struct virtchnl_pf_event *vpe =
+ (struct virtchnl_pf_event *)event->msg_buf;
+
+ if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING)
+ continue;
+
+ dev_info(&adapter->pdev->dev, "Reset indication
received from the PF\n");
+ if (!(adapter->flags & IAVF_FLAG_RESET_PENDING))
+ iavf_schedule_reset(adapter,
+ IAVF_FLAG_RESET_PENDING);
+
+ return -EIO;
+ }
+
if (op_to_poll == received_op)
break;
}
--
2.49.0
