1 files changed, 85 insertions, 66 deletions

diff --git a/src/dpdk/drivers/net/mlx5/mlx5_ethdev.c b/src/dpdk/drivers/net/mlx5/mlx5_ethdev.c
index 85b81360..2145965f 100644
--- a/src/dpdk/drivers/net/mlx5/mlx5_ethdev.c
+++ b/src/dpdk/drivers/net/mlx5/mlx5_ethdev.c
@@ -43,9 +43,11 @@
 #include <net/if.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
+#include <sys/utsname.h>
 #include <netinet/in.h>
 #include <linux/ethtool.h>
 #include <linux/sockios.h>
+#include <linux/version.h>
 #include <fcntl.h>
 
 /* DPDK headers don't like -pedantic. */
@@ -67,6 +69,57 @@
 #include "mlx5_rxtx.h"
 #include "mlx5_utils.h"
 
+/* Add defines in case the running kernel is not the same as user headers. */
+#ifndef ETHTOOL_GLINKSETTINGS
+struct ethtool_link_settings {
+	uint32_t cmd;
+	uint32_t speed;
+	uint8_t duplex;
+	uint8_t port;
+	uint8_t phy_address;
+	uint8_t autoneg;
+	uint8_t mdio_support;
+	uint8_t eth_to_mdix;
+	uint8_t eth_tp_mdix_ctrl;
+	int8_t link_mode_masks_nwords;
+	uint32_t reserved[8];
+	uint32_t link_mode_masks[];
+};
+
+#define ETHTOOL_GLINKSETTINGS 0x0000004c
+#define ETHTOOL_LINK_MODE_1000baseT_Full_BIT 5
+#define ETHTOOL_LINK_MODE_Autoneg_BIT 6
+#define ETHTOOL_LINK_MODE_1000baseKX_Full_BIT 17
+#define ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT 18
+#define ETHTOOL_LINK_MODE_10000baseKR_Full_BIT 19
+#define ETHTOOL_LINK_MODE_10000baseR_FEC_BIT 20
+#define ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT 21
+#define ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT 22
+#define ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT 23
+#define ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT 24
+#define ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT 25
+#define ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT 26
+#define ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT 27
+#define ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT 28
+#define ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT 29
+#define ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT 30
+#endif
+#ifndef HAVE_ETHTOOL_LINK_MODE_25G
+#define ETHTOOL_LINK_MODE_25000baseCR_Full_BIT 31
+#define ETHTOOL_LINK_MODE_25000baseKR_Full_BIT 32
+#define ETHTOOL_LINK_MODE_25000baseSR_Full_BIT 33
+#endif
+#ifndef HAVE_ETHTOOL_LINK_MODE_50G
+#define ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT 34
+#define ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT 35
+#endif
+#ifndef HAVE_ETHTOOL_LINK_MODE_100G
+#define ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT 36
+#define ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT 37
+#define ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT 38
+#define ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT 39
+#endif
+
 /**
  * Return private structure associated with an Ethernet device.
  *
@@ -562,6 +615,8 @@ mlx5_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info)
 	unsigned int max;
 	char ifname[IF_NAMESIZE];
 
+	info->pci_dev = RTE_DEV_TO_PCI(dev->device);
+
 	priv_lock(priv);
 	/* FIXME: we should ask the device for these values. */
 	info->min_rx_bufsize = 32;
@@ -626,7 +681,7 @@ mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 }
 
 /**
- * Retrieve physical link information (unlocked version using legacy ioctl).
+ * DPDK callback to retrieve physical link information.
  *
  * @param dev
  *   Pointer to Ethernet device structure.
@@ -644,6 +699,8 @@ mlx5_link_update_unlocked_gset(struct rte_eth_dev *dev, int wait_to_complete)
 	struct rte_eth_link dev_link;
 	int link_speed = 0;
 
+	/* priv_lock() is not taken to allow concurrent calls. */
+
 	(void)wait_to_complete;
 	if (priv_ifreq(priv, SIOCGIFFLAGS, &ifr)) {
 		WARN("ioctl(SIOCGIFFLAGS) failed: %s", strerror(errno));
@@ -690,8 +747,7 @@ mlx5_link_update_unlocked_gset(struct rte_eth_dev *dev, int wait_to_complete)
 }
 
 /**
- * Retrieve physical link information (unlocked version using new ioctl from
- * Linux 4.5).
+ * Retrieve physical link information (unlocked version using new ioctl).
  *
  * @param dev
  *   Pointer to Ethernet device structure.
@@ -701,7 +757,6 @@ mlx5_link_update_unlocked_gset(struct rte_eth_dev *dev, int wait_to_complete)
 static int
 mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev, int wait_to_complete)
 {
-#ifdef ETHTOOL_GLINKSETTINGS
 	struct priv *priv = mlx5_get_priv(dev);
 	struct ethtool_link_settings edata = {
 		.cmd = ETHTOOL_GLINKSETTINGS,
@@ -728,7 +783,6 @@ mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev, int wait_to_complete)
 	sc = edata.link_mode_masks[0] |
 		((uint64_t)edata.link_mode_masks[1] << 32);
 	priv->link_speed_capa = 0;
-	/* Link speeds available in kernel v4.5. */
 	if (sc & ETHTOOL_LINK_MODE_Autoneg_BIT)
 		priv->link_speed_capa |= ETH_LINK_SPEED_AUTONEG;
 	if (sc & (ETHTOOL_LINK_MODE_1000baseT_Full_BIT |
@@ -751,25 +805,18 @@ mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev, int wait_to_complete)
 		  ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT |
 		  ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT))
 		priv->link_speed_capa |= ETH_LINK_SPEED_56G;
-	/* Link speeds available in kernel v4.6. */
-#ifdef HAVE_ETHTOOL_LINK_MODE_25G
 	if (sc & (ETHTOOL_LINK_MODE_25000baseCR_Full_BIT |
 		  ETHTOOL_LINK_MODE_25000baseKR_Full_BIT |
 		  ETHTOOL_LINK_MODE_25000baseSR_Full_BIT))
 		priv->link_speed_capa |= ETH_LINK_SPEED_25G;
-#endif
-#ifdef HAVE_ETHTOOL_LINK_MODE_50G
 	if (sc & (ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT |
 		  ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT))
 		priv->link_speed_capa |= ETH_LINK_SPEED_50G;
-#endif
-#ifdef HAVE_ETHTOOL_LINK_MODE_100G
 	if (sc & (ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT |
 		  ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT |
 		  ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT |
 		  ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT))
 		priv->link_speed_capa |= ETH_LINK_SPEED_100G;
-#endif
 	dev_link.link_duplex = ((edata.duplex == DUPLEX_HALF) ?
 				ETH_LINK_HALF_DUPLEX : ETH_LINK_FULL_DUPLEX);
 	dev_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
@@ -779,34 +826,11 @@ mlx5_link_update_unlocked_gs(struct rte_eth_dev *dev, int wait_to_complete)
 		dev->data->dev_link = dev_link;
 		return 0;
 	}
-#else
-	(void)dev;
-	(void)wait_to_complete;
-#endif
 	/* Link status is still the same. */
 	return -1;
 }
 
 /**
- * DPDK callback to retrieve physical link information (unlocked version).
- *
- * @param dev
- *   Pointer to Ethernet device structure.
- * @param wait_to_complete
- *   Wait for request completion (ignored).
- */
-int
-mlx5_link_update_unlocked(struct rte_eth_dev *dev, int wait_to_complete)
-{
-	int ret;
-
-	ret = mlx5_link_update_unlocked_gs(dev, wait_to_complete);
-	if (ret < 0)
-		ret = mlx5_link_update_unlocked_gset(dev, wait_to_complete);
-	return ret;
-}
-
-/**
  * DPDK callback to retrieve physical link information.
  *
  * @param dev
@@ -817,13 +841,15 @@ mlx5_link_update_unlocked(struct rte_eth_dev *dev, int wait_to_complete)
 int
 mlx5_link_update(struct rte_eth_dev *dev, int wait_to_complete)
 {
-	struct priv *priv = mlx5_get_priv(dev);
-	int ret;
-
-	priv_lock(priv);
-	ret = mlx5_link_update_unlocked(dev, wait_to_complete);
-	priv_unlock(priv);
-	return ret;
+	struct utsname utsname;
+	int ver[3];
+
+	if (uname(&utsname) == -1 ||
+	    sscanf(utsname.release, "%d.%d.%d",
+		   &ver[0], &ver[1], &ver[2]) != 3 ||
+	    KERNEL_VERSION(ver[0], ver[1], ver[2]) < KERNEL_VERSION(4, 9, 0))
+		return mlx5_link_update_unlocked_gset(dev, wait_to_complete);
+	return mlx5_link_update_unlocked_gs(dev, wait_to_complete);
 }
 
 /**
@@ -1141,7 +1167,7 @@ static int
 priv_dev_link_status_handler(struct priv *priv, struct rte_eth_dev *dev)
 {
 	struct ibv_async_event event;
-	int port_change = 0;
+	struct rte_eth_link *link = &dev->data->dev_link;
 	int ret = 0;
 
 	/* Read all message and acknowledge them. */
@@ -1149,29 +1175,24 @@ priv_dev_link_status_handler(struct priv *priv, struct rte_eth_dev *dev)
 		if (ibv_get_async_event(priv->ctx, &event))
 			break;
 
-		if (event.event_type == IBV_EVENT_PORT_ACTIVE ||
-		    event.event_type == IBV_EVENT_PORT_ERR)
-			port_change = 1;
-		else
+		if (event.event_type != IBV_EVENT_PORT_ACTIVE &&
+		    event.event_type != IBV_EVENT_PORT_ERR)
 			DEBUG("event type %d on port %d not handled",
 			      event.event_type, event.element.port_num);
 		ibv_ack_async_event(&event);
 	}
-
-	if (port_change ^ priv->pending_alarm) {
-		struct rte_eth_link *link = &dev->data->dev_link;
-
-		priv->pending_alarm = 0;
-		mlx5_link_update_unlocked(dev, 0);
-		if (((link->link_speed == 0) && link->link_status) ||
-		    ((link->link_speed != 0) && !link->link_status)) {
+	mlx5_link_update(dev, 0);
+	if (((link->link_speed == 0) && link->link_status) ||
+	    ((link->link_speed != 0) && !link->link_status)) {
+		if (!priv->pending_alarm) {
 			/* Inconsistent status, check again later. */
 			priv->pending_alarm = 1;
 			rte_eal_alarm_set(MLX5_ALARM_TIMEOUT_US,
 					  mlx5_dev_link_status_handler,
 					  dev);
-		} else
-			ret = 1;
+		}
+	} else {
+		ret = 1;
 	}
 	return ret;
 }
@@ -1191,10 +1212,11 @@ mlx5_dev_link_status_handler(void *arg)
 
 	priv_lock(priv);
 	assert(priv->pending_alarm == 1);
+	priv->pending_alarm = 0;
 	ret = priv_dev_link_status_handler(priv, dev);
 	priv_unlock(priv);
-	//if (ret)
-	//	_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
+	if (ret)
+		_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
 }
 
 /**
@@ -1216,8 +1238,8 @@ mlx5_dev_interrupt_handler(struct rte_intr_handle *intr_handle, void *cb_arg)
 	priv_lock(priv);
 	ret = priv_dev_link_status_handler(priv, dev);
 	priv_unlock(priv);
-	//if (ret)
-	//	_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
+	if (ret)
+		_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
 }
 
 /**
@@ -1515,14 +1537,11 @@ void
 priv_select_tx_function(struct priv *priv)
 {
 	priv->dev->tx_pkt_burst = mlx5_tx_burst;
-	/* Display warning for unsupported configurations. */
-	if (priv->sriov && priv->mps)
-		WARN("multi-packet send WQE cannot be used on a SR-IOV setup");
 	/* Select appropriate TX function. */
-	if ((priv->sriov == 0) && priv->mps && priv->txq_inline) {
+	if (priv->mps && priv->txq_inline) {
 		priv->dev->tx_pkt_burst = mlx5_tx_burst_mpw_inline;
 		DEBUG("selected MPW inline TX function");
-	} else if ((priv->sriov == 0) && priv->mps) {
+	} else if (priv->mps) {
 		priv->dev->tx_pkt_burst = mlx5_tx_burst_mpw;
 		DEBUG("selected MPW TX function");
 	}