Merge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
1GbE Intel Wired LAN Driver Updates 2017-06-06

This series contains updates and fixes to e1000e and igb.

Matwey V Kornilov fixes an issue where igb_get_phy_id_82575() relies on
the fact that page 0 is already selected, but this is not the case after
igb_read_phy_reg_gs40g()/igb_write_phy_reg_gs40g() were removed in a
previous commit.  This leads to initialization failure and some devices
not working.  To fix the issue, explicitly select page 0 before first
access to PHY registers.

Arnd Bergmann modifies the driver to avoid a "defined but not used"
warning by removing #ifdefs and using __maybe_unused annotation instead
for new power management functions.

Jake provides most of the changes in the series, all around PTP and
timestamp fixes/updates.  Resolved several race conditions based on
the hardware can only handle one transmit timestamp at a time, so
fix the locking logic, as well as create a statistic for "skipped"
timestamps to help administrators identify issues.

Benjamin Poirier provides 2 changes, first to igb to remove the
second argument to igb_update_stats() since it always passes the
same two arguments.  So instead of having to pass the second argument,
just update the function to the necessary information from the adapter
structure.  Second modifies the e1000e_get_stats64() call to
dev_get_stats() to avoid ethtool garbage being reported.

Konstantin Khlebnikov modifies e1000e to use disable_hardirq(), instead
of disable_irq() for MSIx vectors in e1000_netpoll().
====================

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

8 files changed, 103 insertions, 43 deletions

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index c7c994eb410e..98e68888abb1 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -268,6 +268,7 @@ struct e1000_adapter {
 	u32 tx_fifo_size;
 	u32 tx_dma_failed;
 	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
 
 	/* Rx */
 	bool (*clean_rx)(struct e1000_ring *ring, int *work_done,
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index e23dbd9190d6..003cbd605799 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -105,6 +105,7 @@ static const struct e1000_stats e1000_gstrings_stats[] = {
 	E1000_STAT("uncorr_ecc_errors", uncorr_errors),
 	E1000_STAT("corr_ecc_errors", corr_errors),
 	E1000_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+	E1000_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
 };
 
 #define E1000_GLOBAL_STATS_LEN	ARRAY_SIZE(e1000_gstrings_stats)
@@ -2072,7 +2073,7 @@ static void e1000_get_ethtool_stats(struct net_device *netdev,
 
 	pm_runtime_get_sync(netdev->dev.parent);
 
-	e1000e_get_stats64(netdev, &net_stats);
+	dev_get_stats(netdev, &net_stats);
 
 	pm_runtime_put_sync(netdev->dev.parent);
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 6ed3bc419b96..e1d46c11cb61 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1183,6 +1183,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work)
 	struct e1000_hw *hw = &adapter->hw;
 
 	if (er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID) {
+		struct sk_buff *skb = adapter->tx_hwtstamp_skb;
 		struct skb_shared_hwtstamps shhwtstamps;
 		u64 txstmp;
 
@@ -1191,9 +1192,14 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work)
 
 		e1000e_systim_to_hwtstamp(adapter, &shhwtstamps, txstmp);
 
-		skb_tstamp_tx(adapter->tx_hwtstamp_skb, &shhwtstamps);
-		dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
+		/* Clear the global tx_hwtstamp_skb pointer and force writes
+		 * prior to notifying the stack of a Tx timestamp.
+		 */
 		adapter->tx_hwtstamp_skb = NULL;
+		wmb(); /* force write prior to skb_tstamp_tx */
+
+		skb_tstamp_tx(skb, &shhwtstamps);
+		dev_kfree_skb_any(skb);
 	} else if (time_after(jiffies, adapter->tx_hwtstamp_start
 			      + adapter->tx_timeout_factor * HZ)) {
 		dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
@@ -5861,13 +5867,16 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 			     nr_frags);
 	if (count) {
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-		    (adapter->flags & FLAG_HAS_HW_TIMESTAMP) &&
-		    !adapter->tx_hwtstamp_skb) {
-			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-			tx_flags |= E1000_TX_FLAGS_HWTSTAMP;
-			adapter->tx_hwtstamp_skb = skb_get(skb);
-			adapter->tx_hwtstamp_start = jiffies;
-			schedule_work(&adapter->tx_hwtstamp_work);
+		    (adapter->flags & FLAG_HAS_HW_TIMESTAMP)) {
+			if (!adapter->tx_hwtstamp_skb) {
+				skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+				tx_flags |= E1000_TX_FLAGS_HWTSTAMP;
+				adapter->tx_hwtstamp_skb = skb_get(skb);
+				adapter->tx_hwtstamp_start = jiffies;
+				schedule_work(&adapter->tx_hwtstamp_work);
+			} else {
+				adapter->tx_hwtstamp_skipped++;
+			}
 		}
 
 		skb_tx_timestamp(skb);
@@ -6734,20 +6743,20 @@ static irqreturn_t e1000_intr_msix(int __always_unused irq, void *data)
 
 		vector = 0;
 		msix_irq = adapter->msix_entries[vector].vector;
-		disable_irq(msix_irq);
-		e1000_intr_msix_rx(msix_irq, netdev);
+		if (disable_hardirq(msix_irq))
+			e1000_intr_msix_rx(msix_irq, netdev);
 		enable_irq(msix_irq);
 
 		vector++;
 		msix_irq = adapter->msix_entries[vector].vector;
-		disable_irq(msix_irq);
-		e1000_intr_msix_tx(msix_irq, netdev);
+		if (disable_hardirq(msix_irq))
+			e1000_intr_msix_tx(msix_irq, netdev);
 		enable_irq(msix_irq);
 
 		vector++;
 		msix_irq = adapter->msix_entries[vector].vector;
-		disable_irq(msix_irq);
-		e1000_msix_other(msix_irq, netdev);
+		if (disable_hardirq(msix_irq))
+			e1000_msix_other(msix_irq, netdev);
 		enable_irq(msix_irq);
 	}
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index ee443985581f..4a50870e0fa7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -257,6 +257,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	}
 
 	/* Set phy->phy_addr and phy->id. */
+	igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0);
 	ret_val = igb_get_phy_id_82575(hw);
 	if (ret_val)
 		return ret_val;
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index bf9bf9056d0c..06ffb2bc713e 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -563,6 +563,7 @@ struct igb_adapter {
 	struct cyclecounter cc;
 	struct timecounter tc;
 	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
 	u32 rx_hwtstamp_cleared;
 	bool pps_sys_wrap_on;
 
@@ -666,7 +667,7 @@ void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
 void igb_alloc_rx_buffers(struct igb_ring *, u16);
-void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
+void igb_update_stats(struct igb_adapter *);
 bool igb_has_link(struct igb_adapter *adapter);
 void igb_set_ethtool_ops(struct net_device *);
 void igb_power_up_link(struct igb_adapter *);
@@ -676,6 +677,7 @@ void igb_ptp_stop(struct igb_adapter *adapter);
 void igb_ptp_reset(struct igb_adapter *adapter);
 void igb_ptp_suspend(struct igb_adapter *adapter);
 void igb_ptp_rx_hang(struct igb_adapter *adapter);
+void igb_ptp_tx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
 void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			 struct sk_buff *skb);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 0efb62db6efd..d06a8db514d4 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -90,6 +90,7 @@ static const struct igb_stats igb_gstrings_stats[] = {
 	IGB_STAT("os2bmc_tx_by_host", stats.o2bspc),
 	IGB_STAT("os2bmc_rx_by_host", stats.b2ogprc),
 	IGB_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+	IGB_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
 	IGB_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 };
 
@@ -2315,7 +2316,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 	char *p;
 
 	spin_lock(&adapter->stats64_lock);
-	igb_update_stats(adapter, net_stats);
+	igb_update_stats(adapter);
 
 	for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) {
 		p = (char *)adapter + igb_gstrings_stats[i].stat_offset;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 1cf74aa4ebd9..7e433344a13c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -191,10 +191,7 @@ static int igb_disable_sriov(struct pci_dev *dev);
 static int igb_pci_disable_sriov(struct pci_dev *dev);
 #endif
 
-#ifdef CONFIG_PM
-#ifdef CONFIG_PM_SLEEP
 static int igb_suspend(struct device *);
-#endif
 static int igb_resume(struct device *);
 static int igb_runtime_suspend(struct device *dev);
 static int igb_runtime_resume(struct device *dev);
@@ -204,7 +201,6 @@ static const struct dev_pm_ops igb_pm_ops = {
 	SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume,
 			igb_runtime_idle)
 };
-#endif
 static void igb_shutdown(struct pci_dev *);
 static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
 #ifdef CONFIG_IGB_DCA
@@ -1822,7 +1818,7 @@ void igb_down(struct igb_adapter *adapter)
 
 	/* record the stats before reset*/
 	spin_lock(&adapter->stats64_lock);
-	igb_update_stats(adapter, &adapter->stats64);
+	igb_update_stats(adapter);
 	spin_unlock(&adapter->stats64_lock);
 
 	adapter->link_speed = 0;
@@ -4690,7 +4686,7 @@ no_wait:
 	}
 
 	spin_lock(&adapter->stats64_lock);
-	igb_update_stats(adapter, &adapter->stats64);
+	igb_update_stats(adapter);
 	spin_unlock(&adapter->stats64_lock);
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
@@ -4726,6 +4722,7 @@ no_wait:
 
 	igb_spoof_check(adapter);
 	igb_ptp_rx_hang(adapter);
+	igb_ptp_tx_hang(adapter);
 
 	/* Check LVMMC register on i350/i354 only */
 	if ((adapter->hw.mac.type == e1000_i350) ||
@@ -5201,9 +5198,9 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size)
 	return __igb_maybe_stop_tx(tx_ring, size);
 }
 
-static void igb_tx_map(struct igb_ring *tx_ring,
-		       struct igb_tx_buffer *first,
-		       const u8 hdr_len)
+static int igb_tx_map(struct igb_ring *tx_ring,
+		      struct igb_tx_buffer *first,
+		      const u8 hdr_len)
 {
 	struct sk_buff *skb = first->skb;
 	struct igb_tx_buffer *tx_buffer;
@@ -5314,7 +5311,7 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 		 */
 		mmiowb();
 	}
-	return;
+	return 0;
 
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
@@ -5345,6 +5342,8 @@ dma_error:
 	tx_buffer->skb = NULL;
 
 	tx_ring->next_to_use = i;
+
+	return -1;
 }
 
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
@@ -5390,6 +5389,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 			adapter->ptp_tx_start = jiffies;
 			if (adapter->hw.mac.type == e1000_82576)
 				schedule_work(&adapter->ptp_tx_work);
+		} else {
+			adapter->tx_hwtstamp_skipped++;
 		}
 	}
 
@@ -5410,13 +5411,24 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	else if (!tso)
 		igb_tx_csum(tx_ring, first);
 
-	igb_tx_map(tx_ring, first, hdr_len);
+	if (igb_tx_map(tx_ring, first, hdr_len))
+		goto cleanup_tx_tstamp;
 
 	return NETDEV_TX_OK;
 
 out_drop:
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
+cleanup_tx_tstamp:
+	if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP)) {
+		struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);
+
+		dev_kfree_skb_any(adapter->ptp_tx_skb);
+		adapter->ptp_tx_skb = NULL;
+		if (adapter->hw.mac.type == e1000_82576)
+			cancel_work_sync(&adapter->ptp_tx_work);
+		clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -5487,7 +5499,7 @@ static void igb_get_stats64(struct net_device *netdev,
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
 	spin_lock(&adapter->stats64_lock);
-	igb_update_stats(adapter, &adapter->stats64);
+	igb_update_stats(adapter);
 	memcpy(stats, &adapter->stats64, sizeof(*stats));
 	spin_unlock(&adapter->stats64_lock);
 }
@@ -5536,9 +5548,9 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
  *  igb_update_stats - Update the board statistics counters
  *  @adapter: board private structure
  **/
-void igb_update_stats(struct igb_adapter *adapter,
-		      struct rtnl_link_stats64 *net_stats)
+void igb_update_stats(struct igb_adapter *adapter)
 {
+	struct rtnl_link_stats64 *net_stats = &adapter->stats64;
 	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
 	u32 reg, mpc;
@@ -8015,9 +8027,7 @@ static void igb_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-#ifdef CONFIG_PM
-#ifdef CONFIG_PM_SLEEP
-static int igb_suspend(struct device *dev)
+static int __maybe_unused igb_suspend(struct device *dev)
 {
 	int retval;
 	bool wake;
@@ -8036,9 +8046,8 @@ static int igb_suspend(struct device *dev)
 
 	return 0;
 }
-#endif /* CONFIG_PM_SLEEP */
 
-static int igb_resume(struct device *dev)
+static int __maybe_unused igb_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -8092,7 +8101,7 @@ static int igb_resume(struct device *dev)
 	return err;
 }
 
-static int igb_runtime_idle(struct device *dev)
+static int __maybe_unused igb_runtime_idle(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -8104,7 +8113,7 @@ static int igb_runtime_idle(struct device *dev)
 	return -EBUSY;
 }
 
-static int igb_runtime_suspend(struct device *dev)
+static int __maybe_unused igb_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int retval;
@@ -8124,11 +8133,10 @@ static int igb_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int igb_runtime_resume(struct device *dev)
+static int __maybe_unused igb_runtime_resume(struct device *dev)
 {
 	return igb_resume(dev);
 }
-#endif /* CONFIG_PM */
 
 static void igb_shutdown(struct pci_dev *pdev)
 {
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index d333d6d80194..841c2a083349 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -712,6 +712,35 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter)
 }
 
 /**
+ * igb_ptp_tx_hang - detect error case where Tx timestamp never finishes
+ * @adapter: private network adapter structure
+ */
+void igb_ptp_tx_hang(struct igb_adapter *adapter)
+{
+	bool timeout = time_is_before_jiffies(adapter->ptp_tx_start +
+					      IGB_PTP_TX_TIMEOUT);
+
+	if (!adapter->ptp_tx_skb)
+		return;
+
+	if (!test_bit(__IGB_PTP_TX_IN_PROGRESS, &adapter->state))
+		return;
+
+	/* If we haven't received a timestamp within the timeout, it is
+	 * reasonable to assume that it will never occur, so we can unlock the
+	 * timestamp bit when this occurs.
+	 */
+	if (timeout) {
+		cancel_work_sync(&adapter->ptp_tx_work);
+		dev_kfree_skb_any(adapter->ptp_tx_skb);
+		adapter->ptp_tx_skb = NULL;
+		clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
+		adapter->tx_hwtstamp_timeouts++;
+		dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n");
+	}
+}
+
+/**
  * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp
  * @adapter: Board private structure.
  *
@@ -721,6 +750,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter)
  **/
 static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 {
+	struct sk_buff *skb = adapter->ptp_tx_skb;
 	struct e1000_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps shhwtstamps;
 	u64 regval;
@@ -748,10 +778,17 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 	shhwtstamps.hwtstamp =
 		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
 
-	skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
-	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	/* Clear the lock early before calling skb_tstamp_tx so that
+	 * applications are not woken up before the lock bit is clear. We use
+	 * a copy of the skb pointer to ensure other threads can't change it
+	 * while we're notifying the stack.
+	 */
 	adapter->ptp_tx_skb = NULL;
 	clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
+
+	/* Notify the stack and free the skb after we've unlocked */
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
 }
 
 /**