Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/ixgbe/Makefile

@@ -32,7 +32,7 @@
 
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
-ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\
+ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
               ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
               ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe_ptp.o
 
@@ -40,4 +40,5 @@ ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
 
 ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
+ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o
 ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o

drivers/net/ethernet/intel/ixgbe/ixgbe.h

@@ -35,6 +35,7 @@
 #include <linux/cpumask.h>
 #include <linux/aer.h>
 #include <linux/if_vlan.h>
+#include <linux/jiffies.h>
 
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
@@ -231,6 +232,7 @@ struct ixgbe_ring {
 		struct ixgbe_tx_buffer *tx_buffer_info;
 		struct ixgbe_rx_buffer *rx_buffer_info;
 	};
+	unsigned long last_rx_timestamp;
 	unsigned long state;
 	u8 __iomem *tail;
 	dma_addr_t dma;			/* phys. address of descriptor ring */
@@ -580,11 +582,14 @@ struct ixgbe_adapter {
 
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
+	struct work_struct ptp_tx_work;
+	struct sk_buff *ptp_tx_skb;
+	unsigned long ptp_tx_start;
 	unsigned long last_overflow_check;
+	unsigned long last_rx_ptp_check;
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
-	int rx_hwtstamp_filter;
 	u32 base_incval;
 
 	/* SR-IOV */
@@ -749,15 +754,32 @@ static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring)
 extern void ixgbe_ptp_init(struct ixgbe_adapter *adapter);
 extern void ixgbe_ptp_stop(struct ixgbe_adapter *adapter);
 extern void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter);
-extern void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector,
-				  struct sk_buff *skb);
-extern void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
-				  union ixgbe_adv_rx_desc *rx_desc,
-				  struct sk_buff *skb);
+extern void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter);
+extern void __ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+				    struct sk_buff *skb);
+static inline void ixgbe_ptp_rx_hwtstamp(struct ixgbe_ring *rx_ring,
+					 union ixgbe_adv_rx_desc *rx_desc,
+					 struct sk_buff *skb)
+{
+	if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS)))
+		return;
+
+	__ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, skb);
+
+	/*
+	 * Update the last_rx_timestamp timer in order to enable watchdog check
+	 * for error case of latched timestamp on a dropped packet.
+	 */
+	rx_ring->last_rx_timestamp = jiffies;
+}
+
 extern int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
 				    struct ifreq *ifr, int cmd);
 extern void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter);
 extern void ixgbe_ptp_reset(struct ixgbe_adapter *adapter);
 extern void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr);
+#ifdef CONFIG_PCI_IOV
+void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter);
+#endif
 
 #endif /* _IXGBE_H_ */

drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c

@@ -24,9 +24,6 @@
   Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
 
 *******************************************************************************/
-
-#ifdef CONFIG_DEBUG_FS
-
 #include <linux/debugfs.h>
 #include <linux/module.h>
 
@@ -277,5 +274,3 @@ void ixgbe_dbg_exit(void)
 {
 	debugfs_remove_recursive(ixgbe_dbg_root);
 }
-
-#endif /* CONFIG_DEBUG_FS */

drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c

@@ -1837,19 +1837,11 @@ static void ixgbe_diag_test(struct net_device *netdev,
                             struct ethtool_test *eth_test, u64 *data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
 	bool if_running = netif_running(netdev);
 
 	set_bit(__IXGBE_TESTING, &adapter->state);
 	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
-		/* Offline tests */
-
-		e_info(hw, "offline testing starting\n");
-
-		/* Link test performed before hardware reset so autoneg doesn't
-		 * interfere with test result */
-		if (ixgbe_link_test(adapter, &data[4]))
-			eth_test->flags |= ETH_TEST_FL_FAILED;
-
 		if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
 			int i;
 			for (i = 0; i < adapter->num_vfs; i++) {
@@ -1870,12 +1862,24 @@ static void ixgbe_diag_test(struct net_device *netdev,
 			}
 		}
 
+		/* Offline tests */
+		e_info(hw, "offline testing starting\n");
+
 		if (if_running)
 			/* indicate we're in test mode */
 			dev_close(netdev);
-		else
-			ixgbe_reset(adapter);
 
+		/* bringing adapter down disables SFP+ optics */
+		if (hw->mac.ops.enable_tx_laser)
+			hw->mac.ops.enable_tx_laser(hw);
+
+		/* Link test performed before hardware reset so autoneg doesn't
+		 * interfere with test result
+		 */
+		if (ixgbe_link_test(adapter, &data[4]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		ixgbe_reset(adapter);
 		e_info(hw, "register testing starting\n");
 		if (ixgbe_reg_test(adapter, &data[0]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1908,16 +1912,22 @@ static void ixgbe_diag_test(struct net_device *netdev,
 skip_loopback:
 		ixgbe_reset(adapter);
 
+		/* clear testing bit and return adapter to previous state */
 		clear_bit(__IXGBE_TESTING, &adapter->state);
 		if (if_running)
 			dev_open(netdev);
 	} else {
 		e_info(hw, "online testing starting\n");
+
+		/* if adapter is down, SFP+ optics will be disabled */
+		if (!if_running && hw->mac.ops.enable_tx_laser)
+			hw->mac.ops.enable_tx_laser(hw);
+
 		/* Online tests */
 		if (ixgbe_link_test(adapter, &data[4]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 
-		/* Online tests aren't run; pass by default */
+		/* Offline tests aren't run; pass by default */
 		data[0] = 0;
 		data[1] = 0;
 		data[2] = 0;
@@ -1925,6 +1935,10 @@ static void ixgbe_diag_test(struct net_device *netdev,
 
 		clear_bit(__IXGBE_TESTING, &adapter->state);
 	}
+
+	/* if adapter was down, ensure SFP+ optics are disabled again */
+	if (!if_running && hw->mac.ops.disable_tx_laser)
+		hw->mac.ops.disable_tx_laser(hw);
 skip_ol_tests:
 	msleep_interruptible(4 * 1000);
 }
@@ -2695,6 +2709,14 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 			(1 << HWTSTAMP_FILTER_NONE) |
 			(1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
 			(1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
 			(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
 		break;
 	default:

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -803,6 +803,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
 	/* Do the reset outside of interrupt context */
 	if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
 		adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
+		e_warn(drv, "initiating reset due to tx timeout\n");
 		ixgbe_service_event_schedule(adapter);
 	}
 }
@@ -850,9 +851,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
-		if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP))
-			ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb);
-
 		/* free the skb */
 		dev_kfree_skb_any(tx_buffer->skb);
 
@@ -1441,7 +1439,7 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
 
 	ixgbe_rx_checksum(rx_ring, rx_desc, skb);
 
-	ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
+	ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
 
 	if ((dev->features & NETIF_F_HW_VLAN_RX) &&
 	    ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
@@ -5534,6 +5532,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
 		break;
 	}
 
+	adapter->last_rx_ptp_check = jiffies;
+
 	if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED)
 		ixgbe_ptp_start_cyclecounter(adapter);
 
@@ -5614,6 +5614,7 @@ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter)
 			 * to get done, so reset controller to flush Tx.
 			 * (Do the reset outside of interrupt context).
 			 */
+			e_warn(drv, "initiating reset to clear Tx work after link loss\n");
 			adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
 		}
 	}
@@ -5878,7 +5879,6 @@ static void ixgbe_service_task(struct work_struct *work)
 	struct ixgbe_adapter *adapter = container_of(work,
 						     struct ixgbe_adapter,
 						     service_task);
-
 	ixgbe_reset_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
 	ixgbe_sfp_link_config_subtask(adapter);
@@ -5886,7 +5886,11 @@ static void ixgbe_service_task(struct work_struct *work)
 	ixgbe_watchdog_subtask(adapter);
 	ixgbe_fdir_reinit_subtask(adapter);
 	ixgbe_check_hang_subtask(adapter);
-	ixgbe_ptp_overflow_check(adapter);
+
+	if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) {
+		ixgbe_ptp_overflow_check(adapter);
+		ixgbe_ptp_rx_hang(adapter);
+	}
 
 	ixgbe_service_event_complete(adapter);
 }
@@ -6432,6 +6436,11 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IXGBE_TX_FLAGS_TSTAMP;
+
+		/* schedule check for Tx timestamp */
+		adapter->ptp_tx_skb = skb_get(skb);
+		adapter->ptp_tx_start = jiffies;
+		schedule_work(&adapter->ptp_tx_work);
 	}
 
 #ifdef CONFIG_PCI_IOV
@@ -6827,6 +6836,26 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc)
 }
 
 #endif /* CONFIG_IXGBE_DCB */
+#ifdef CONFIG_PCI_IOV
+void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+
+	rtnl_lock();
+#ifdef CONFIG_IXGBE_DCB
+	ixgbe_setup_tc(netdev, netdev_get_num_tc(netdev));
+#else
+	if (netif_running(netdev))
+		ixgbe_close(netdev);
+	ixgbe_clear_interrupt_scheme(adapter);
+	ixgbe_init_interrupt_scheme(adapter);
+	if (netif_running(netdev))
+		ixgbe_open(netdev);
+#endif
+	rtnl_unlock();
+}
+
+#endif
 void ixgbe_do_reset(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
@@ -7353,7 +7382,15 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 #ifdef CONFIG_PCI_IOV
-	ixgbe_enable_sriov(adapter, ii);
+	/* SR-IOV not supported on the 82598 */
+	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+		goto skip_sriov;
+	/* Mailbox */
+	ixgbe_init_mbx_params_pf(hw);
+	memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops));
+	ixgbe_enable_sriov(adapter);
+	pci_sriov_set_totalvfs(pdev, 63);
+skip_sriov:
 
 #endif
 	netdev->features = NETIF_F_SG |
@@ -7609,8 +7646,14 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
-	ixgbe_disable_sriov(adapter);
-
+#ifdef CONFIG_PCI_IOV
+	/*
+	 * Only disable SR-IOV on unload if the user specified the now
+	 * deprecated max_vfs module parameter.
+	 */
+	if (max_vfs)
+		ixgbe_disable_sriov(adapter);
+#endif
 	ixgbe_clear_interrupt_scheme(adapter);
 
 	ixgbe_release_hw_control(adapter);
@@ -7824,6 +7867,7 @@ static struct pci_driver ixgbe_driver = {
 	.resume   = ixgbe_resume,
 #endif
 	.shutdown = ixgbe_shutdown,
+	.sriov_configure = ixgbe_pci_sriov_configure,
 	.err_handler = &ixgbe_err_handler
 };
 

drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c

@@ -96,15 +96,12 @@
 #define IXGBE_MAX_TIMEADJ_VALUE  0x7FFFFFFFFFFFFFFFULL
 
 #define IXGBE_OVERFLOW_PERIOD    (HZ * 30)
+#define IXGBE_PTP_TX_TIMEOUT     (HZ * 15)
 
 #ifndef NSECS_PER_SEC
 #define NSECS_PER_SEC 1000000000ULL
 #endif
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
-
 /**
  * ixgbe_ptp_setup_sdp
  * @hw: the hardware private structure
@@ -405,149 +402,145 @@ void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr)
 	}
 }
 
-
 /**
- * ixgbe_ptp_overflow_check - delayed work to detect SYSTIME overflow
- * @work: structure containing information about this work task
+ * ixgbe_ptp_overflow_check - watchdog task to detect SYSTIME overflow
+ * @adapter: private adapter struct
  *
- * this work function is scheduled to continue reading the timecounter
+ * this watchdog task periodically reads the timecounter
  * in order to prevent missing when the system time registers wrap
- * around. This needs to be run approximately twice a minute when no
- * PTP activity is occurring.
+ * around. This needs to be run approximately twice a minute.
  */
 void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter)
 {
-	unsigned long elapsed_jiffies = adapter->last_overflow_check - jiffies;
+	bool timeout = time_is_before_jiffies(adapter->last_overflow_check +
+					     IXGBE_OVERFLOW_PERIOD);
 	struct timespec ts;
 
-	if ((adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) &&
-	    (elapsed_jiffies >= IXGBE_OVERFLOW_PERIOD)) {
+	if (timeout) {
 		ixgbe_ptp_gettime(&adapter->ptp_caps, &ts);
 		adapter->last_overflow_check = jiffies;
 	}
 }
 
 /**
- * ixgbe_ptp_match - determine if this skb matches a ptp packet
- * @skb: pointer to the skb
- * @hwtstamp: pointer to the hwtstamp_config to check
- *
- * Determine whether the skb should have been timestamped, assuming the
- * hwtstamp was set via the hwtstamp ioctl. Returns non-zero when the packet
- * should have a timestamp waiting in the registers, and 0 otherwise.
+ * ixgbe_ptp_rx_hang - detect error case when Rx timestamp registers latched
+ * @adapter: private network adapter structure
  *
- * V1 packets have to check the version type to determine whether they are
- * correct. However, we can't directly access the data because it might be
- * fragmented in the SKB, in paged memory. In order to work around this, we
- * use skb_copy_bits which will properly copy the data whether it is in the
- * paged memory fragments or not. We have to copy the IP header as well as the
- * message type.
+ * this watchdog task is scheduled to detect error case where hardware has
+ * dropped an Rx packet that was timestamped when the ring is full. The
+ * particular error is rare but leaves the device in a state unable to timestamp
+ * any future packets.
  */
-static int ixgbe_ptp_match(struct sk_buff *skb, int rx_filter)
+void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter)
 {
-	struct iphdr iph;
-	u8 msgtype;
-	unsigned int type, offset;
-
-	if (rx_filter == HWTSTAMP_FILTER_NONE)
-		return 0;
-
-	type = sk_run_filter(skb, ptp_filter);
-
-	if (likely(rx_filter == HWTSTAMP_FILTER_PTP_V2_EVENT))
-		return type & PTP_CLASS_V2;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_ring *rx_ring;
+	u32 tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
+	unsigned long rx_event;
+	int n;
 
-	/* For the remaining cases actually check message type */
-	switch (type) {
-	case PTP_CLASS_V1_IPV4:
-		skb_copy_bits(skb, OFF_IHL, &iph, sizeof(iph));
-		offset = ETH_HLEN + (iph.ihl << 2) + UDP_HLEN + OFF_PTP_CONTROL;
-		break;
-	case PTP_CLASS_V1_IPV6:
-		offset = OFF_PTP6 + OFF_PTP_CONTROL;
-		break;
-	default:
-		/* other cases invalid or handled above */
-		return 0;
+	/* if we don't have a valid timestamp in the registers, just update the
+	 * timeout counter and exit
+	 */
+	if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) {
+		adapter->last_rx_ptp_check = jiffies;
+		return;
 	}
 
-	/* Make sure our buffer is long enough */
-	if (skb->len < offset)
-		return 0;
+	/* determine the most recent watchdog or rx_timestamp event */
+	rx_event = adapter->last_rx_ptp_check;
+	for (n = 0; n < adapter->num_rx_queues; n++) {
+		rx_ring = adapter->rx_ring[n];
+		if (time_after(rx_ring->last_rx_timestamp, rx_event))
+			rx_event = rx_ring->last_rx_timestamp;
+	}
 
-	skb_copy_bits(skb, offset, &msgtype, sizeof(msgtype));
+	/* only need to read the high RXSTMP register to clear the lock */
+	if (time_is_before_jiffies(rx_event + 5*HZ)) {
+		IXGBE_READ_REG(hw, IXGBE_RXSTMPH);
+		adapter->last_rx_ptp_check = jiffies;
 
-	switch (rx_filter) {
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-		return (msgtype == IXGBE_RXMTRL_V1_SYNC_MSG);
-		break;
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		return (msgtype == IXGBE_RXMTRL_V1_DELAY_REQ_MSG);
-		break;
-	default:
-		return 0;
+		e_warn(drv, "clearing RX Timestamp hang");
 	}
 }
 
 /**
  * ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp
- * @q_vector: structure containing interrupt and ring information
- * @skb: particular skb to send timestamp with
+ * @adapter: the private adapter struct
  *
  * if the timestamp is valid, we convert it into the timecounter ns
  * value, then store that result into the shhwtstamps structure which
  * is passed up the network stack
  */
-void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector,
-			   struct sk_buff *skb)
+static void ixgbe_ptp_tx_hwtstamp(struct ixgbe_adapter *adapter)
 {
-	struct ixgbe_adapter *adapter;
-	struct ixgbe_hw *hw;
+	struct ixgbe_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps shhwtstamps;
 	u64 regval = 0, ns;
-	u32 tsynctxctl;
 	unsigned long flags;
 
-	/* we cannot process timestamps on a ring without a q_vector */
-	if (!q_vector || !q_vector->adapter)
-		return;
-
-	adapter = q_vector->adapter;
-	hw = &adapter->hw;
-
-	tsynctxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL);
 	regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPL);
 	regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPH) << 32;
 
-	/*
-	 * if TX timestamp is not valid, exit after clearing the
-	 * timestamp registers
-	 */
-	if (!(tsynctxctl & IXGBE_TSYNCTXCTL_VALID))
-		return;
-
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	ns = timecounter_cyc2time(&adapter->tc, regval);
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 	shhwtstamps.hwtstamp = ns_to_ktime(ns);
-	skb_tstamp_tx(skb, &shhwtstamps);
+	skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
+
+	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	adapter->ptp_tx_skb = NULL;
+}
+
+/**
+ * ixgbe_ptp_tx_hwtstamp_work
+ * @work: pointer to the work struct
+ *
+ * This work item polls TSYNCTXCTL valid bit to determine when a Tx hardware
+ * timestamp has been taken for the current skb. It is necesary, because the
+ * descriptor's "done" bit does not correlate with the timestamp event.
+ */
+static void ixgbe_ptp_tx_hwtstamp_work(struct work_struct *work)
+{
+	struct ixgbe_adapter *adapter = container_of(work, struct ixgbe_adapter,
+						     ptp_tx_work);
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool timeout = time_is_before_jiffies(adapter->ptp_tx_start +
+					      IXGBE_PTP_TX_TIMEOUT);
+	u32 tsynctxctl;
+
+	/* we have to have a valid skb */
+	if (!adapter->ptp_tx_skb)
+		return;
+
+	if (timeout) {
+		dev_kfree_skb_any(adapter->ptp_tx_skb);
+		adapter->ptp_tx_skb = NULL;
+		e_warn(drv, "clearing Tx Timestamp hang");
+		return;
+	}
+
+	tsynctxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL);
+	if (tsynctxctl & IXGBE_TSYNCTXCTL_VALID)
+		ixgbe_ptp_tx_hwtstamp(adapter);
+	else
+		/* reschedule to keep checking if it's not available yet */
+		schedule_work(&adapter->ptp_tx_work);
 }
 
 /**
- * ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp
+ * __ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp
  * @q_vector: structure containing interrupt and ring information
- * @rx_desc: the rx descriptor
  * @skb: particular skb to send timestamp with
  *
  * if the timestamp is valid, we convert it into the timecounter ns
  * value, then store that result into the shhwtstamps structure which
  * is passed up the network stack
  */
-void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
-			   union ixgbe_adv_rx_desc *rx_desc,
-			   struct sk_buff *skb)
+void __ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+			     struct sk_buff *skb)
 {
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_hw *hw;
@@ -563,37 +556,17 @@ void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
 	adapter = q_vector->adapter;
 	hw = &adapter->hw;
 
-	if (likely(!ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter)))
-		return;
-
+	/*
+	 * Read the tsyncrxctl register afterwards in order to prevent taking an
+	 * I/O hit on every packet.
+	 */
 	tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
-
-	/* Check if we have a valid timestamp and make sure the skb should
-	 * have been timestamped */
 	if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID))
 		return;
 
-	/*
-	 * Always read the registers, in order to clear a possible fault
-	 * because of stagnant RX timestamp values for a packet that never
-	 * reached the queue.
-	 */
 	regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL);
 	regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32;
 
-	/*
-	 * If the timestamp bit is set in the packet's descriptor, we know the
-	 * timestamp belongs to this packet. No other packet can be
-	 * timestamped until the registers for timestamping have been read.
-	 * Therefor only one packet with this bit can be in the queue at a
-	 * time, and the rx timestamp values that were in the registers belong
-	 * to this packet.
-	 *
-	 * If nothing went wrong, then it should have a skb_shared_tx that we
-	 * can turn into a skb_shared_hwtstamps.
-	 */
-	if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS)))
-		return;
 
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	ns = timecounter_cyc2time(&adapter->tc, regval);
@@ -660,11 +633,11 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_mtrl = IXGBE_RXMTRL_V1_SYNC_MSG;
+		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
+		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
@@ -698,9 +671,6 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
 		return 0;
 	}
 
-	/* Store filter value for later use */
-	adapter->rx_hwtstamp_filter = config.rx_filter;
-
 	/* define ethertype filter for timestamping L2 packets */
 	if (is_l2)
 		IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588),
@@ -902,11 +872,8 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
 		return;
 	}
 
-	/* initialize the ptp filter */
-	if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter)))
-		e_dev_warn("ptp_filter_init failed\n");
-
 	spin_lock_init(&adapter->tmreg_lock);
+	INIT_WORK(&adapter->ptp_tx_work, ixgbe_ptp_tx_hwtstamp_work);
 
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
@@ -938,6 +905,12 @@ void ixgbe_ptp_stop(struct ixgbe_adapter *adapter)
 
 	ixgbe_ptp_setup_sdp(adapter);
 
+	cancel_work_sync(&adapter->ptp_tx_work);
+	if (adapter->ptp_tx_skb) {
+		dev_kfree_skb_any(adapter->ptp_tx_skb);
+		adapter->ptp_tx_skb = NULL;
+	}
+
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		adapter->ptp_clock = NULL;

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c

@@ -44,50 +44,11 @@
 #include "ixgbe_sriov.h"
 
 #ifdef CONFIG_PCI_IOV
-void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
-			 const struct ixgbe_info *ii)
+static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	int num_vf_macvlans, i;
 	struct vf_macvlans *mv_list;
-	int pre_existing_vfs = 0;
-
-	pre_existing_vfs = pci_num_vf(adapter->pdev);
-	if (!pre_existing_vfs && !adapter->num_vfs)
-		return;
-
-	/* If there are pre-existing VFs then we have to force
-	 * use of that many because they were not deleted the last
-	 * time someone removed the PF driver.  That would have
-	 * been because they were allocated to guest VMs and can't
-	 * be removed.  Go ahead and just re-enable the old amount.
-	 * If the user wants to change the number of VFs they can
-	 * use ethtool while making sure no VFs are allocated to
-	 * guest VMs... i.e. the right way.
-	 */
-	if (pre_existing_vfs) {
-		adapter->num_vfs = pre_existing_vfs;
-		dev_warn(&adapter->pdev->dev, "Virtual Functions already "
-			 "enabled for this device - Please reload all "
-			 "VF drivers to avoid spoofed packet errors\n");
-	} else {
-		int err;
-		/*
-		 * The 82599 supports up to 64 VFs per physical function
-		 * but this implementation limits allocation to 63 so that
-		 * basic networking resources are still available to the
-		 * physical function.  If the user requests greater thn
-		 * 63 VFs then it is an error - reset to default of zero.
-		 */
-		adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, 63);
-
-		err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
-		if (err) {
-			e_err(probe, "Failed to enable PCI sriov: %d\n", err);
-			adapter->num_vfs = 0;
-			return;
-		}
-	}
 
 	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
 	e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs);
@@ -128,12 +89,6 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
 		kcalloc(adapter->num_vfs,
 			sizeof(struct vf_data_storage), GFP_KERNEL);
 	if (adapter->vfinfo) {
-		/* Now that we're sure SR-IOV is enabled
-		 * and memory allocated set up the mailbox parameters
-		 */
-		ixgbe_init_mbx_params_pf(hw);
-		memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops));
-
 		/* limit trafffic classes based on VFs enabled */
 		if ((adapter->hw.mac.type == ixgbe_mac_82599EB) &&
 		    (adapter->num_vfs < 16)) {
@@ -157,10 +112,62 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
 		/* enable spoof checking for all VFs */
 		for (i = 0; i < adapter->num_vfs; i++)
 			adapter->vfinfo[i].spoofchk_enabled = true;
+		return 0;
+	}
+
+	return -ENOMEM;
+}
+
+/* Note this function is called when the user wants to enable SR-IOV
+ * VFs using the now deprecated module parameter
+ */
+void ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
+{
+	int pre_existing_vfs = 0;
+
+	pre_existing_vfs = pci_num_vf(adapter->pdev);
+	if (!pre_existing_vfs && !adapter->num_vfs)
 		return;
+
+	if (!pre_existing_vfs)
+		dev_warn(&adapter->pdev->dev,
+			 "Enabling SR-IOV VFs using the module parameter is deprecated - please use the pci sysfs interface.\n");
+
+	/* If there are pre-existing VFs then we have to force
+	 * use of that many - over ride any module parameter value.
+	 * This may result from the user unloading the PF driver
+	 * while VFs were assigned to guest VMs or because the VFs
+	 * have been created via the new PCI SR-IOV sysfs interface.
+	 */
+	if (pre_existing_vfs) {
+		adapter->num_vfs = pre_existing_vfs;
+		dev_warn(&adapter->pdev->dev,
+			 "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n");
+	} else {
+		int err;
+		/*
+		 * The 82599 supports up to 64 VFs per physical function
+		 * but this implementation limits allocation to 63 so that
+		 * basic networking resources are still available to the
+		 * physical function.  If the user requests greater thn
+		 * 63 VFs then it is an error - reset to default of zero.
+		 */
+		adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, 63);
+
+		err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+		if (err) {
+			e_err(probe, "Failed to enable PCI sriov: %d\n", err);
+			adapter->num_vfs = 0;
+			return;
+		}
 	}
 
-	/* Oh oh */
+	if (!__ixgbe_enable_sriov(adapter))
+		return;
+
+	/* If we have gotten to this point then there is no memory available
+	 * to manage the VF devices - print message and bail.
+	 */
 	e_err(probe, "Unable to allocate memory for VF Data Storage - "
 	      "SRIOV disabled\n");
 	ixgbe_disable_sriov(adapter);
@@ -200,11 +207,12 @@ static bool ixgbe_vfs_are_assigned(struct ixgbe_adapter *adapter)
 }
 
 #endif /* #ifdef CONFIG_PCI_IOV */
-void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
+int ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 gpie;
 	u32 vmdctl;
+	int rss;
 
 	/* set num VFs to 0 to prevent access to vfinfo */
 	adapter->num_vfs = 0;
@@ -219,7 +227,7 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 
 	/* if SR-IOV is already disabled then there is nothing to do */
 	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
-		return;
+		return 0;
 
 #ifdef CONFIG_PCI_IOV
 	/*
@@ -229,7 +237,7 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 	 */
 	if (ixgbe_vfs_are_assigned(adapter)) {
 		e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n");
-		return;
+		return -EPERM;
 	}
 	/* disable iov and allow time for transactions to clear */
 	pci_disable_sriov(adapter->pdev);
@@ -252,10 +260,94 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
 	adapter->ring_feature[RING_F_VMDQ].offset = 0;
 
+	rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus());
+	adapter->ring_feature[RING_F_RSS].limit = rss;
+
 	/* take a breather then clean up driver data */
 	msleep(100);
 
 	adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+	return 0;
+}
+
+static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs)
+{
+#ifdef CONFIG_PCI_IOV
+	struct ixgbe_adapter *adapter = pci_get_drvdata(dev);
+	int err = 0;
+	int i;
+	int pre_existing_vfs = pci_num_vf(dev);
+
+	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
+		err = ixgbe_disable_sriov(adapter);
+	else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
+		goto out;
+
+	if (err)
+		goto err_out;
+
+	/* While the SR-IOV capability structure reports total VFs to be
+	 * 64 we limit the actual number that can be allocated to 63 so
+	 * that some transmit/receive resources can be reserved to the
+	 * PF.  The PCI bus driver already checks for other values out of
+	 * range.
+	 */
+	if (num_vfs > 63) {
+		err = -EPERM;
+		goto err_out;
+	}
+
+	adapter->num_vfs = num_vfs;
+
+	err = __ixgbe_enable_sriov(adapter);
+	if (err)
+		goto err_out;
+
+	for (i = 0; i < adapter->num_vfs; i++)
+		ixgbe_vf_configuration(dev, (i | 0x10000000));
+
+	err = pci_enable_sriov(dev, num_vfs);
+	if (err) {
+		e_dev_warn("Failed to enable PCI sriov: %d\n", err);
+		goto err_out;
+	}
+	ixgbe_sriov_reinit(adapter);
+
+out:
+	return num_vfs;
+
+err_out:
+	return err;
+#endif
+	return 0;
+}
+
+static int ixgbe_pci_sriov_disable(struct pci_dev *dev)
+{
+	struct ixgbe_adapter *adapter = pci_get_drvdata(dev);
+	int err;
+	u32 current_flags = adapter->flags;
+
+	err = ixgbe_disable_sriov(adapter);
+
+	/* Only reinit if no error and state changed */
+	if (!err && current_flags != adapter->flags) {
+		/* ixgbe_disable_sriov() doesn't clear VMDQ flag */
+		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
+#ifdef CONFIG_PCI_IOV
+		ixgbe_sriov_reinit(adapter);
+#endif
+	}
+
+	return err;
+}
+
+int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
+{
+	if (num_vfs == 0)
+		return ixgbe_pci_sriov_disable(dev);
+	else
+		return ixgbe_pci_sriov_enable(dev, num_vfs);
 }
 
 static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h

@@ -41,11 +41,11 @@ int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi);
 void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter);
-void ixgbe_disable_sriov(struct ixgbe_adapter *adapter);
+int ixgbe_disable_sriov(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
-void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
-			const struct ixgbe_info *ii);
+void ixgbe_enable_sriov(struct ixgbe_adapter *adapter);
 #endif
+int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
 
 static inline void ixgbe_set_vmvir(struct ixgbe_adapter *adapter,
 				   u16 vid, u16 qos, u32 vf)

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -2245,10 +2245,23 @@ static void ixgbevf_watchdog_task(struct work_struct *work)
 
 	if (link_up) {
 		if (!netif_carrier_ok(netdev)) {
+			char *link_speed_string;
+			switch (link_speed) {
+			case IXGBE_LINK_SPEED_10GB_FULL:
+				link_speed_string = "10 Gbps";
+				break;
+			case IXGBE_LINK_SPEED_1GB_FULL:
+				link_speed_string = "1 Gbps";
+				break;
+			case IXGBE_LINK_SPEED_100_FULL:
+				link_speed_string = "100 Mbps";
+				break;
+			default:
+				link_speed_string = "unknown speed";
+				break;
+			}
 			dev_info(&adapter->pdev->dev,
-				"NIC Link is Up, %u Gbps\n",
-				(link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
-				10 : 1);
+				"NIC Link is Up, %s\n", link_speed_string);
 			netif_carrier_on(netdev);
 			netif_tx_wake_all_queues(netdev);
 		}