RFC: implement VF reset for i40e, e1000 and ixgbe

index 2f1905e13..45714959a 100644
@@ -1047,6 +1047,9 @@ struct i40e_adapter {
 	struct rte_timecounter rx_tstamp_tc;
 	struct rte_timecounter tx_tstamp_tc;
 
+	/* For VF reset */
+	uint8_t reset_number;
+
 	/* ptype mapping table */
 	uint32_t ptype_tbl[I40E_MAX_PKT_TYPE] __rte_cache_min_aligned;
 	/* flow type to pctype mapping table */

73 lines not on this page · raw message

index f21c1c5d2..3d5125260 100644
@@ -1745,6 +1745,7 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	uint32_t ring_size;
 	uint16_t len, i;
 	uint16_t reg_idx, base, bsf, tc_mapping;
+	struct rte_eth_rxconf conf = *rx_conf;
 	int q_offset, use_def_burst_func = 1;
 
 	if (hw->mac.type == I40E_MAC_VF || hw->mac.type == I40E_MAC_X722_VF) {

@@ -1789,6 +1790,8 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev,
 		return -ENOMEM;
 	}
 	rxq->mp = mp;
+	rxq->socket_id = socket_id;
+	rxq->rxconf = conf;
 	rxq->nb_rx_desc = nb_desc;
 	rxq->rx_free_thresh = rx_conf->rx_free_thresh;
 	rxq->queue_id = queue_idx;

@@ -2024,6 +2027,8 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	uint16_t reg_idx, i, base, bsf, tc_mapping;
 	int q_offset;
 
+	struct rte_eth_txconf conf = *tx_conf;
+
 	if (hw->mac.type == I40E_MAC_VF || hw->mac.type == I40E_MAC_X722_VF) {
 		vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
 		vsi = &vf->vsi;

@@ -2149,6 +2154,8 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	}
 
 	txq->nb_tx_desc = nb_desc;
+	txq->socket_id = socket_id;
+	txq->txconf = conf;
 	txq->tx_rs_thresh = tx_rs_thresh;
 	txq->tx_free_thresh = tx_free_thresh;
 	txq->pthresh = tx_conf->tx_thresh.pthresh;

@@ -2628,8 +2635,12 @@ void
 i40e_dev_free_queues(struct rte_eth_dev *dev)
 {
 	uint16_t i;
+	struct i40e_adapter *adapter =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
 
 	PMD_INIT_FUNC_TRACE();
+	if (adapter->reset_number)
+		return;
 
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		if (!dev->data->rx_queues[i])

index 06c6a6592..43e227a52 100644
@@ -136,6 +136,8 @@ struct i40e_rx_queue {
 	bool rx_deferred_start; /**< don't start this queue in dev start */
 	uint16_t rx_using_sse; /**<flag indicate the usage of vPMD for rx */
 	uint8_t dcb_tc;         /**< Traffic class of rx queue */
+	uint8_t socket_id;
+	struct rte_eth_rxconf rxconf;
 };
 
 struct i40e_tx_entry {

@@ -177,6 +179,8 @@ struct i40e_tx_queue {
 	bool q_set; /**< indicate if tx queue has been configured */
 	bool tx_deferred_start; /**< don't start this queue in dev start */
 	uint8_t dcb_tc;         /**< Traffic class of tx queue */
+	uint8_t socket_id;
+	struct rte_eth_txconf txconf;
 };
 
 /** Offload features */

index 003bdf0f6..1211d5371 100644
@@ -280,6 +280,7 @@ static void eth_igb_configure_msix_intr(struct rte_eth_dev *dev);
 static void eth_igbvf_interrupt_handler(void *param);
 static void igbvf_mbx_process(struct rte_eth_dev *dev);
 static int igb_filter_restore(struct rte_eth_dev *dev);
+static int igbvf_dev_reset(struct rte_eth_dev *dev);
 
 /*
  * Define VF Stats MACRO for Non "cleared on read" register

@@ -468,6 +469,7 @@ static const struct eth_dev_ops igbvf_eth_dev_ops = {
 	.txq_info_get         = igb_txq_info_get,
 	.mac_addr_set         = igbvf_default_mac_addr_set,
 	.get_reg              = igbvf_get_regs,
+	.dev_reset            = igbvf_dev_reset,
 };
 
 /* store statistics names and its offset in stats structure */

@@ -2975,6 +2977,63 @@ void igbvf_mbx_process(struct rte_eth_dev *dev)
 }
 
 static int
+igbvf_dev_reset(struct rte_eth_dev *dev)
+{
+	struct e1000_hw *hw =
+		 E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	int diag = 0;
+	uint32_t eiam;
+	/* Reference igbvf_intr_enable */
+	uint32_t eiam_mbx = 1 << E1000_VTIVAR_MISC_MAILBOX;
+
+	/* Nothing needs to be done if the device is not started. */
+	if (!dev->data->dev_started)
+		 return -EAGAIN;
+
+	PMD_DRV_LOG(DEBUG, "Link up/down event detected.");
+
+	/* Performance VF reset. */
+	do {
+		 dev->data->dev_started = 0;
+		 igbvf_dev_stop(dev);
+		 if (dev->data->dev_conf.intr_conf.lsc == 0)
+			  diag = eth_igb_link_update(dev, 0);
+		 if (diag) {
+			  PMD_INIT_LOG(INFO, "Igb VF reset: "
+					 "Failed to update link.");
+		 }
+		 rte_delay_ms(1000);
+
+		 diag = igbvf_dev_start(dev);
+		 dev->data->dev_started = 1;
+		 if (diag) {
+			  PMD_INIT_LOG(ERR, "Igb VF reset: "
+					 "Failed to start device.");
+			  return -EAGAIN;
+		 }
+		 eth_igbvf_stats_reset(dev);
+		 if (dev->data->dev_conf.intr_conf.lsc == 0)
+			  diag = eth_igb_link_update(dev, 0);
+		 if (diag) {
+			  PMD_INIT_LOG(INFO, "Igb VF reset: "
+					 "Failed to update link.");
+		 }
+
+		 /**
+		  * When the PF link is down, there is a chance
+		  * that the VF cannot operate its registers.
+		  * Check if the registers are written
+		  * successfully. If not, repeat stop/start until
+		  * the PF link is up, in other words, until the
+		  * registers can be written.
+		  */
+		 eiam = E1000_READ_REG(hw, E1000_EIAM);
+	} while (!(eiam & eiam_mbx));
+
+	return 0;
+}
+
+static int
 eth_igbvf_interrupt_action(struct rte_eth_dev *dev, struct rte_intr_handle *intr_handle)
 {
 	struct e1000_interrupt *intr =

index 14b9c5303..13307466b 100644
@@ -5026,7 +5026,9 @@ ixgbevf_dev_start(struct rte_eth_dev *dev)
 		ETH_VLAN_EXTEND_MASK;
 	ixgbevf_vlan_offload_set(dev, mask);
 
-	ixgbevf_dev_rxtx_start(dev);
+	err = ixgbevf_dev_rxtx_start(dev);
+	if (err)
+		return err;
 
 	/* check and configure queue intr-vector mapping */
 	if (dev->data->dev_conf.intr_conf.rxq != 0) {

@@ -5127,15 +5129,59 @@ ixgbevf_dev_close(struct rte_eth_dev *dev)
 static int
 ixgbevf_dev_reset(struct rte_eth_dev *dev)
 {
-	int ret;
+	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	int diag = 0;
+	uint32_t vteiam;
 
-	ret = eth_ixgbevf_dev_uninit(dev);
-	if (ret)
-		return ret;
+	/* Nothing needs to be done if the device is not started. */
+	if (!dev->data->dev_started)
+		return -EAGAIN;
 
-	ret = eth_ixgbevf_dev_init(dev);
+	PMD_DRV_LOG(DEBUG, "Link up/down event detected.");
 
-	return ret;
+	/* Performance VF reset. */
+	do {
+		dev->data->dev_started = 0;
+		ixgbevf_dev_stop(dev);
+		if (dev->data->dev_conf.intr_conf.lsc == 0)
+			diag = ixgbe_dev_link_update(dev, 0);
+		if (diag) {
+			PMD_INIT_LOG(INFO, "Ixgbe VF reset: "
+					"Failed to update link.");
+		}
+		rte_delay_ms(1000);
+
+		diag = ixgbevf_dev_start(dev);
+		/* If fail to start the device, need to stop/start it again. */
+		if (diag) {
+			PMD_INIT_LOG(ERR, "Ixgbe VF reset: "
+					"Failed to start device.");
+			dev->data->dev_started = 1;
+			return -EAGAIN;
+		}
+		dev->data->dev_started = 1;
+		ixgbevf_dev_stats_reset(dev);
+		if (dev->data->dev_conf.intr_conf.lsc == 0)
+			diag = ixgbe_dev_link_update(dev, 0);
+		if (diag) {
+			PMD_INIT_LOG(INFO, "Ixgbe VF reset: "
+					"Failed to update link.");
+			diag = 0;
+		}
+
+		/**
+		 * When the PF link is down, there is a chance
+		 * that the VF cannot operate its registers.
+		 * Check if the registers are written
+		 * successfully. If not, repeat stop/start until
+		 * the PF link is up, or in other words, until the
+		 * registers can be written.
+		 */
+		vteiam = IXGBE_READ_REG(hw, IXGBE_VTEIAM);
+	/* Reference ixgbevf_intr_enable when checking */
+	} while (diag || vteiam != IXGBE_VF_IRQ_ENABLE_MASK);
+
+	return 0;
 }
 
 static void ixgbevf_set_vfta_all(struct rte_eth_dev *dev, bool on)

index e28c8567e..87b929518 100644
@@ -595,7 +595,7 @@ int ixgbevf_dev_rx_init(struct rte_eth_dev *dev);
 
 void ixgbevf_dev_tx_init(struct rte_eth_dev *dev);
 
-void ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev);
+int ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev);
 
 uint16_t ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		uint16_t nb_pkts);

index 0038dfbb4..5a0be2cfe 100644
@@ -5419,7 +5419,7 @@ ixgbevf_dev_tx_init(struct rte_eth_dev *dev)
 /*
  * [VF] Start Transmit and Receive Units.
  */
-void __attribute__((cold))
+int __attribute__((cold))
 ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev)
 {
 	struct ixgbe_hw     *hw;

@@ -5455,8 +5455,10 @@ ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev)
 			rte_delay_ms(1);
 			txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i));
 		} while (--poll_ms && !(txdctl & IXGBE_TXDCTL_ENABLE));
-		if (!poll_ms)
+		if (!poll_ms) {
 			PMD_INIT_LOG(ERR, "Could not enable Tx Queue %d", i);
+			return -1;
+		}
 	}
 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 

@@ -5472,12 +5474,16 @@ ixgbevf_dev_rxtx_start(struct rte_eth_dev *dev)
 			rte_delay_ms(1);
 			rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i));
 		} while (--poll_ms && !(rxdctl & IXGBE_RXDCTL_ENABLE));
-		if (!poll_ms)
+		if (!poll_ms) {
 			PMD_INIT_LOG(ERR, "Could not enable Rx Queue %d", i);
+			return -1;
+		}
 		rte_wmb();
 		IXGBE_WRITE_REG(hw, IXGBE_VFRDT(i), rxq->nb_rx_desc - 1);
 
 	}
+
+	return 0;
 }
 
 /* Stubs needed for linkage when CONFIG_RTE_IXGBE_INC_VECTOR is set to 'n' */