[PATCH 24.11] net/iavf: fix duplicate VF reset during PF reset recovery

[Anurag Mandal]

[ upstream commit ece7d7eef04f82503faa148f46ad296d30b5880f]

During PF initiated reset recovery, iavf_dev_close() sends an
extra 'VIRTCHNL_OP_RESET_VF' while recovery is already in progress.
That second reset can leave PF/VF virtchnl state inconsistent and
cause 'VIRTCHNL_OP_CONFIG_VSI_QUEUES' to fail with 'ERR_PARAM' after
ToR link flap/power-cycle, leaving the VF unable to recover.
This results in connection loss.

This patch introduces a new flag 'pf_reset_in_progress', which
is set only when iavf_handle_hw_reset() is entered for a
PF-initiated reset (vf_initiated_reset is false), and
it is cleared on exit.
The aforesaid flag is used to prevent sending close-time VF
reset and related close-time virtchnl operation messages to the
AdminQ when PF triggered reset recovery is set.
This is done to avoid duplicate VF reset requests while preserving
normal behavior for application-driven close or VF-initiated reinit.

Fixes: 675a104 ("net/iavf: fix abnormal disable HW interrupt")
Fixes: b34fe66 ("net/iavf: delay VF reset command")
Fixes: 5e03e31 ("net/iavf: handle virtchnl event message without interrupt")
Cc: stable at dpdk.org

Signed-off-by: Anurag Mandal <anurag.mandal at intel.com>
Acked-by: Ciara Loftus <ciara.loftus at intel.com>
---
 drivers/net/iavf/iavf.h        |  1 +
 drivers/net/iavf/iavf_ethdev.c | 42 ++++++++++++++++++++++------------
 drivers/net/iavf/iavf_vchnl.c  | 18 ++++++++++++---
 3 files changed, 44 insertions(+), 17 deletions(-)

diff --git a/drivers/net/iavf/iavf.h b/drivers/net/iavf/iavf.h
index dc34429f52..89249416b6 100644
--- a/drivers/net/iavf/iavf.h
+++ b/drivers/net/iavf/iavf.h
@@ -285,6 +285,7 @@ struct iavf_info {
 
 	bool in_reset_recovery;
 	bool reset_pending;
+	bool pf_reset_in_progress;
 
 	uint32_t ptp_caps;
 	rte_spinlock_t phc_time_aq_lock;
diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 02c3227e9d..a2efa6bec1 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+++ b/drivers/net/iavf/iavf_ethdev.c
@@ -2971,22 +2971,29 @@ iavf_dev_close(struct rte_eth_dev *dev)
 	ret = iavf_dev_stop(dev);
 
 	/*
-	 * Release redundant queue resource when close the dev
-	 * so that other vfs can re-use the queues.
+	 * Prevent sending close-time virtchnl messages to the AdminQ
+	 * during PF-initiated reset recovery.
 	 */
-	if (vf->lv_enabled) {
-		ret = iavf_request_queues(dev, IAVF_MAX_NUM_QUEUES_DFLT);
-		if (ret)
-			PMD_DRV_LOG(ERR, "Reset the num of queues failed");
+	if (!vf->pf_reset_in_progress) {
 
-		vf->max_rss_qregion = IAVF_MAX_NUM_QUEUES_DFLT;
-	}
+		/*
+		 * Release redundant queue resource when close the dev
+		 * so that other vfs can re-use the queues.
+		 */
+		if (vf->lv_enabled) {
+			ret = iavf_request_queues(dev, IAVF_MAX_NUM_QUEUES_DFLT);
+			if (ret)
+				PMD_DRV_LOG(ERR, "Reset the num of queues failed");
+			vf->max_rss_qregion = IAVF_MAX_NUM_QUEUES_DFLT;
+		}
 
-	/* Disable promiscuous mode before resetting the VF. This is to avoid
-	 * potential issues when the PF is bound to the kernel driver.
-	 */
-	if (vf->promisc_unicast_enabled || vf->promisc_multicast_enabled)
-		iavf_config_promisc(adapter, false, false);
+		/*
+		 * Disable promiscuous mode before resetting the VF. This is to avoid
+		 * potential issues when the PF is bound to the kernel driver.
+		 */
+		if (vf->promisc_unicast_enabled || vf->promisc_multicast_enabled)
+			iavf_config_promisc(adapter, false, false);
+	}
 
 	adapter->closed = true;
 
@@ -2996,7 +3003,12 @@ iavf_dev_close(struct rte_eth_dev *dev)
 	iavf_flow_flush(dev, NULL);
 	iavf_flow_uninit(adapter);
 
-	iavf_vf_reset(hw);
+	/*
+	 * Prevent sending VIRTCHNL_OP_RESET_VF during PF-initiated
+	 * reset recovery.
+	 */
+	if (!vf->pf_reset_in_progress)
+		iavf_vf_reset(hw);
 	/*
 	 * If a reset is pending, wait for the PF to disable the VF's admin
 	 * receive queue (its first reset action) before we shut it down
@@ -3149,6 +3161,7 @@ iavf_handle_hw_reset(struct rte_eth_dev *dev)
 	}
 
 	vf->in_reset_recovery = true;
+	vf->pf_reset_in_progress = !vf_initiated_reset;
 	iavf_set_no_poll(adapter, false);
 
 	ret = iavf_dev_reset(dev);
@@ -3174,6 +3187,7 @@ iavf_handle_hw_reset(struct rte_eth_dev *dev)
 	PMD_DRV_LOG(DEBUG, "RESET recover with error code=%d", ret);
 exit:
 	vf->in_reset_recovery = false;
+	vf->pf_reset_in_progress = false;
 	iavf_set_no_poll(adapter, false);
 
 	return;
diff --git a/drivers/net/iavf/iavf_vchnl.c b/drivers/net/iavf/iavf_vchnl.c
index 4481d67177..8259273f45 100644
--- a/drivers/net/iavf/iavf_vchnl.c
+++ b/drivers/net/iavf/iavf_vchnl.c
@@ -317,9 +317,21 @@ iavf_read_msg_from_pf(struct iavf_adapter *adapter, uint16_t buf_len,
 			iavf_handle_link_change_event(vf->eth_dev, vpe);
 			break;
 		case VIRTCHNL_EVENT_RESET_IMPENDING:
-			vf->vf_reset = true;
-			iavf_set_no_poll(adapter, false);
-			PMD_DRV_LOG(INFO, "VF is resetting");
+			/*
+			 * Force link down on impending reset to drop
+			 * the cached link-up state; a fresh LSC up
+			 * event will be re-issued by the PF once the
+			 * VF is reinitialised.
+			 */
+			vf->link_up = false;
+			if (!vf->vf_reset) {
+				vf->vf_reset = true;
+				iavf_set_no_poll(adapter, false);
+				iavf_dev_event_post(vf->eth_dev,
+					RTE_ETH_EVENT_INTR_RESET,
+					NULL, 0);
+			}
+			PMD_DRV_LOG(DEBUG, "VF is resetting");
 			break;
 		case VIRTCHNL_EVENT_PF_DRIVER_CLOSE:
 			vf->dev_closed = true;
-- 
2.34.1