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 2019-12-31

This series contains updates to e1000e, igb and igc only.

Robert Beckett provide an igb change to assist in keeping packets from
being dropped due to receive descriptor ring being full when receive
flow control is enabled.  Create a separate function to setup SRRCTL to
ease in reuse and ensure that setting of the drop enable bit only if
receive flow control is not enabled.

Sasha adds support for scatter gather support in igc.  Improve the
direct memory address mapping flow by optimizing/simplifying and more
clear.  Update igc to use pci_release_mem_regions() instead of
pci_release_selected_regions().  Clean up function header comments to
align with the actual code.  Adds support for 64 bit DMA access, to help
handle socket buffer fragments in high memory.  Adds legacy power
management support in igc by implementing suspend, resume,
runtime_suspend/resume, and runtime_idle callbacks.  Clean up references
to Serdes interface in igc since that interface is not supported for
i225 devices.

Alex replaces the pr_info calls with netdev_info in all cases related to
netdev link state, as suggested by Joe Perches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -4723,7 +4723,7 @@ int e1000e_close(struct net_device *netdev)
 		e1000_free_irq(adapter);
 
 		/* Link status message must follow this format */
-		pr_info("%s NIC Link is Down\n", netdev->name);
+		netdev_info(netdev, "NIC Link is Down\n");
 	}
 
 	napi_disable(&adapter->napi);
@@ -5073,8 +5073,9 @@ static void e1000_print_link_info(struct e1000_adapter *adapter)
 	u32 ctrl = er32(CTRL);
 
 	/* Link status message must follow this format for user tools */
-	pr_info("%s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
-		adapter->netdev->name, adapter->link_speed,
+	netdev_info(adapter->netdev,
+		    "NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
+		    adapter->link_speed,
 		    adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half",
 		    (ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE) ? "Rx/Tx" :
 		    (ctrl & E1000_CTRL_RFCE) ? "Rx" :
@@ -5307,7 +5308,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			adapter->link_speed = 0;
 			adapter->link_duplex = 0;
 			/* Link status message must follow this format */
-			pr_info("%s NIC Link is Down\n", adapter->netdev->name);
+			netdev_info(netdev, "NIC Link is Down\n");
 			netif_carrier_off(netdev);
 			netif_stop_queue(netdev);
 			if (!test_bit(__E1000_DOWN, &adapter->state))

drivers/net/ethernet/intel/igb/igb.h

@@ -661,6 +661,7 @@ void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
+void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *);
 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 *);

drivers/net/ethernet/intel/igb/igb_ethtool.c

@@ -396,6 +396,7 @@ static int igb_set_pauseparam(struct net_device *netdev,
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	int retval = 0;
+	int i;
 
 	/* 100basefx does not support setting link flow control */
 	if (hw->dev_spec._82575.eth_flags.e100_base_fx)
@@ -428,6 +429,13 @@ static int igb_set_pauseparam(struct net_device *netdev,
 
 		retval = ((hw->phy.media_type == e1000_media_type_copper) ?
 			  igb_force_mac_fc(hw) : igb_setup_link(hw));
+
+		/* Make sure SRRCTL considers new fc settings for each ring */
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			struct igb_ring *ring = adapter->rx_ring[i];
+
+			igb_setup_srrctl(adapter, ring);
+		}
 	}
 
 	clear_bit(__IGB_RESETTING, &adapter->state);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -4467,6 +4467,37 @@ static inline void igb_set_vmolr(struct igb_adapter *adapter,
 	wr32(E1000_VMOLR(vfn), vmolr);
 }
 
+/**
+ *  igb_setup_srrctl - configure the split and replication receive control
+ *                     registers
+ *  @adapter: Board private structure
+ *  @ring: receive ring to be configured
+ **/
+void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int reg_idx = ring->reg_idx;
+	u32 srrctl = 0;
+
+	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	if (ring_uses_large_buffer(ring))
+		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	else
+		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
+	if (hw->mac.type >= e1000_82580)
+		srrctl |= E1000_SRRCTL_TIMESTAMP;
+	/* Only set Drop Enable if VFs allocated, or we are supporting multiple
+	 * queues and rx flow control is disabled
+	 */
+	if (adapter->vfs_allocated_count ||
+	    (!(hw->fc.current_mode & e1000_fc_rx_pause) &&
+	     adapter->num_rx_queues > 1))
+		srrctl |= E1000_SRRCTL_DROP_EN;
+
+	wr32(E1000_SRRCTL(reg_idx), srrctl);
+}
+
 /**
  *  igb_configure_rx_ring - Configure a receive ring after Reset
  *  @adapter: board private structure
@@ -4481,7 +4512,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	union e1000_adv_rx_desc *rx_desc;
 	u64 rdba = ring->dma;
 	int reg_idx = ring->reg_idx;
-	u32 srrctl = 0, rxdctl = 0;
+	u32 rxdctl = 0;
 
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
@@ -4499,19 +4530,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	writel(0, ring->tail);
 
 	/* set descriptor configuration */
-	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	if (ring_uses_large_buffer(ring))
-		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
-	else
-		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
-	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
-	if (hw->mac.type >= e1000_82580)
-		srrctl |= E1000_SRRCTL_TIMESTAMP;
-	/* Only set Drop Enable if we are supporting multiple queues */
-	if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1)
-		srrctl |= E1000_SRRCTL_DROP_EN;
-
-	wr32(E1000_SRRCTL(reg_idx), srrctl);
+	igb_setup_srrctl(adapter, ring);
 
 	/* set filtering for VMDQ pools */
 	igb_set_vmolr(adapter, reg_idx & 0x7, true);

drivers/net/ethernet/intel/igc/igc.h

@@ -370,6 +370,8 @@ struct igc_adapter {
 	struct timer_list dma_err_timer;
 	struct timer_list phy_info_timer;
 
+	u32 wol;
+	u32 en_mng_pt;
 	u16 link_speed;
 	u16 link_duplex;
 

drivers/net/ethernet/intel/igc/igc_defines.h

@@ -10,6 +10,37 @@
 
 #define IGC_CTRL_EXT_DRV_LOAD	0x10000000 /* Drv loaded bit for FW */
 
+/* Definitions for power management and wakeup registers */
+/* Wake Up Control */
+#define IGC_WUC_PME_EN	0x00000002 /* PME Enable */
+
+/* Wake Up Filter Control */
+#define IGC_WUFC_LNKC	0x00000001 /* Link Status Change Wakeup Enable */
+#define IGC_WUFC_MC	0x00000008 /* Directed Multicast Wakeup Enable */
+
+#define IGC_CTRL_ADVD3WUC	0x00100000  /* D3 WUC */
+
+/* Wake Up Status */
+#define IGC_WUS_EX	0x00000004 /* Directed Exact */
+#define IGC_WUS_ARPD	0x00000020 /* Directed ARP Request */
+#define IGC_WUS_IPV4	0x00000040 /* Directed IPv4 */
+#define IGC_WUS_IPV6	0x00000080 /* Directed IPv6 */
+#define IGC_WUS_NSD	0x00000400 /* Directed IPv6 Neighbor Solicitation */
+
+/* Packet types that are enabled for wake packet delivery */
+#define WAKE_PKT_WUS ( \
+	IGC_WUS_EX   | \
+	IGC_WUS_ARPD | \
+	IGC_WUS_IPV4 | \
+	IGC_WUS_IPV6 | \
+	IGC_WUS_NSD)
+
+/* Wake Up Packet Length */
+#define IGC_WUPL_MASK	0x00000FFF
+
+/* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */
+#define IGC_WUPM_BYTES	128
+
 /* Physical Func Reset Done Indication */
 #define IGC_CTRL_EXT_LINK_MODE_MASK	0x00C00000
 

drivers/net/ethernet/intel/igc/igc_main.c

@@ -8,6 +8,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/ip.h>
+#include <linux/pm_runtime.h>
 
 #include <net/ipv6.h>
 
@@ -114,7 +115,7 @@ void igc_reset(struct igc_adapter *adapter)
 }
 
 /**
- * igc_power_up_link - Power up the phy/serdes link
+ * igc_power_up_link - Power up the phy link
  * @adapter: address of board private structure
  */
 static void igc_power_up_link(struct igc_adapter *adapter)
@@ -128,7 +129,7 @@ static void igc_power_up_link(struct igc_adapter *adapter)
 }
 
 /**
- * igc_power_down_link - Power down the phy/serdes link
+ * igc_power_down_link - Power down the phy link
  * @adapter: address of board private structure
  */
 static void igc_power_down_link(struct igc_adapter *adapter)
@@ -1485,7 +1486,6 @@ static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer)
  * igc_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
  * @rx_desc: Rx descriptor for current buffer
- * @skb: current socket buffer containing buffer in progress
  *
  * This function updates next to clean.  If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
@@ -1567,7 +1567,8 @@ static void igc_put_rx_buffer(struct igc_ring *rx_ring,
 
 /**
  * igc_alloc_rx_buffers - Replace used receive buffers; packet split
- * @adapter: address of board private structure
+ * @rx_ring: rx descriptor ring
+ * @cleaned_count: number of buffers to clean
  */
 static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count)
 {
@@ -3109,7 +3110,7 @@ bool igc_has_link(struct igc_adapter *adapter)
 
 /**
  * igc_watchdog - Timer Call-back
- * @data: pointer to adapter cast into an unsigned long
+ * @t: timer for the watchdog
  */
 static void igc_watchdog(struct timer_list *t)
 {
@@ -3638,6 +3639,7 @@ static int igc_poll(struct napi_struct *napi, int budget)
 /**
  * igc_set_interrupt_capability - set MSI or MSI-X if supported
  * @adapter: Pointer to adapter structure
+ * @msix: boolean value for MSI-X capability
  *
  * Attempt to configure interrupts using the best available
  * capabilities of the hardware and kernel.
@@ -3906,6 +3908,7 @@ static void igc_cache_ring_register(struct igc_adapter *adapter)
 /**
  * igc_init_interrupt_scheme - initialize interrupts, allocate queues/vectors
  * @adapter: Pointer to adapter structure
+ * @msix: boolean for MSI-X capability
  *
  * This function initializes the interrupts and allocates all of the queues.
  */
@@ -4073,8 +4076,9 @@ static void igc_write_itr(struct igc_q_vector *q_vector)
 }
 
 /**
- * igc_open - Called when a network interface is made active
+ * __igc_open - Called when a network interface is made active
  * @netdev: network interface device structure
+ * @resuming: boolean indicating if the device is resuming
  *
  * Returns 0 on success, negative value on failure
  *
@@ -4164,8 +4168,9 @@ static int igc_open(struct net_device *netdev)
 }
 
 /**
- * igc_close - Disables a network interface
+ * __igc_close - Disables a network interface
  * @netdev: network interface device structure
+ * @suspending: boolean indicating the device is suspending
  *
  * Returns 0, this is not allowed to fail
  *
@@ -4345,32 +4350,26 @@ static int igc_probe(struct pci_dev *pdev,
 	struct net_device *netdev;
 	struct igc_hw *hw;
 	const struct igc_info *ei = igc_info_tbl[ent->driver_data];
-	int err;
+	int err, pci_using_dac;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
 		return err;
 
-	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+	pci_using_dac = 0;
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (!err) {
-		err = dma_set_coherent_mask(&pdev->dev,
-					    DMA_BIT_MASK(64));
+		pci_using_dac = 1;
 	} else {
-		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
-			err = dma_set_coherent_mask(&pdev->dev,
-						    DMA_BIT_MASK(32));
-			if (err) {
-				dev_err(&pdev->dev, "igc: Wrong DMA config\n");
+			dev_err(&pdev->dev,
+				"No usable DMA configuration, aborting\n");
 			goto err_dma;
 		}
 	}
-	}
 
-	err = pci_request_selected_regions(pdev,
-					   pci_select_bars(pdev,
-							   IORESOURCE_MEM),
-					   igc_driver_name);
+	err = pci_request_mem_regions(pdev, igc_driver_name);
 	if (err)
 		goto err_pci_reg;
 
@@ -4433,6 +4432,7 @@ static int igc_probe(struct pci_dev *pdev,
 		goto err_sw_init;
 
 	/* Add supported features to the features list*/
+	netdev->features |= NETIF_F_SG;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;
@@ -4446,6 +4446,9 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->hw_features |= NETIF_F_NTUPLE;
 	netdev->hw_features |= netdev->features;
 
+	if (pci_using_dac)
+		netdev->features |= NETIF_F_HIGHDMA;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -4532,8 +4535,7 @@ static int igc_probe(struct pci_dev *pdev,
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -4580,11 +4582,214 @@ static void igc_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake,
+			  bool runtime)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u32 wufc = runtime ? IGC_WUFC_LNKC : adapter->wol;
+	struct igc_hw *hw = &adapter->hw;
+	u32 ctrl, rctl, status;
+	bool wake;
+
+	rtnl_lock();
+	netif_device_detach(netdev);
+
+	if (netif_running(netdev))
+		__igc_close(netdev, true);
+
+	igc_clear_interrupt_scheme(adapter);
+	rtnl_unlock();
+
+	status = rd32(IGC_STATUS);
+	if (status & IGC_STATUS_LU)
+		wufc &= ~IGC_WUFC_LNKC;
+
+	if (wufc) {
+		igc_setup_rctl(adapter);
+		igc_set_rx_mode(netdev);
+
+		/* turn on all-multi mode if wake on multicast is enabled */
+		if (wufc & IGC_WUFC_MC) {
+			rctl = rd32(IGC_RCTL);
+			rctl |= IGC_RCTL_MPE;
+			wr32(IGC_RCTL, rctl);
+		}
+
+		ctrl = rd32(IGC_CTRL);
+		ctrl |= IGC_CTRL_ADVD3WUC;
+		wr32(IGC_CTRL, ctrl);
+
+		/* Allow time for pending master requests to run */
+		igc_disable_pcie_master(hw);
+
+		wr32(IGC_WUC, IGC_WUC_PME_EN);
+		wr32(IGC_WUFC, wufc);
+	} else {
+		wr32(IGC_WUC, 0);
+		wr32(IGC_WUFC, 0);
+	}
+
+	wake = wufc || adapter->en_mng_pt;
+	if (!wake)
+		igc_power_down_link(adapter);
+	else
+		igc_power_up_link(adapter);
+
+	if (enable_wake)
+		*enable_wake = wake;
+
+	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
+	 * would have already happened in close and is redundant.
+	 */
+	igc_release_hw_control(adapter);
+
+	pci_disable_device(pdev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int __maybe_unused igc_runtime_suspend(struct device *dev)
+{
+	return __igc_shutdown(to_pci_dev(dev), NULL, 1);
+}
+
+static void igc_deliver_wake_packet(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	struct sk_buff *skb;
+	u32 wupl;
+
+	wupl = rd32(IGC_WUPL) & IGC_WUPL_MASK;
+
+	/* WUPM stores only the first 128 bytes of the wake packet.
+	 * Read the packet only if we have the whole thing.
+	 */
+	if (wupl == 0 || wupl > IGC_WUPM_BYTES)
+		return;
+
+	skb = netdev_alloc_skb_ip_align(netdev, IGC_WUPM_BYTES);
+	if (!skb)
+		return;
+
+	skb_put(skb, wupl);
+
+	/* Ensure reads are 32-bit aligned */
+	wupl = roundup(wupl, 4);
+
+	memcpy_fromio(skb->data, hw->hw_addr + IGC_WUPM_REG(0), wupl);
+
+	skb->protocol = eth_type_trans(skb, netdev);
+	netif_rx(skb);
+}
+
+static int __maybe_unused igc_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 err, val;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+
+	if (!pci_device_is_present(pdev))
+		return -ENODEV;
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"igc: Cannot enable PCI device from suspend\n");
+		return err;
+	}
+	pci_set_master(pdev);
+
+	pci_enable_wake(pdev, PCI_D3hot, 0);
+	pci_enable_wake(pdev, PCI_D3cold, 0);
+
+	if (igc_init_interrupt_scheme(adapter, true)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		return -ENOMEM;
+	}
+
+	igc_reset(adapter);
+
+	/* let the f/w know that the h/w is now under the control of the
+	 * driver.
+	 */
+	igc_get_hw_control(adapter);
+
+	val = rd32(IGC_WUS);
+	if (val & WAKE_PKT_WUS)
+		igc_deliver_wake_packet(netdev);
+
+	wr32(IGC_WUS, ~0);
+
+	rtnl_lock();
+	if (!err && netif_running(netdev))
+		err = __igc_open(netdev, true);
+
+	if (!err)
+		netif_device_attach(netdev);
+	rtnl_unlock();
+
+	return err;
+}
+
+static int __maybe_unused igc_runtime_resume(struct device *dev)
+{
+	return igc_resume(dev);
+}
+
+static int __maybe_unused igc_suspend(struct device *dev)
+{
+	return __igc_shutdown(to_pci_dev(dev), NULL, 0);
+}
+
+static int __maybe_unused igc_runtime_idle(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (!igc_has_link(adapter))
+		pm_schedule_suspend(dev, MSEC_PER_SEC * 5);
+
+	return -EBUSY;
+}
+#endif /* CONFIG_PM */
+
+static void igc_shutdown(struct pci_dev *pdev)
+{
+	bool wake;
+
+	__igc_shutdown(pdev, &wake, 0);
+
+	if (system_state == SYSTEM_POWER_OFF) {
+		pci_wake_from_d3(pdev, wake);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+}
+
+#ifdef CONFIG_PM
+static const struct dev_pm_ops igc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume)
+	SET_RUNTIME_PM_OPS(igc_runtime_suspend, igc_runtime_resume,
+			   igc_runtime_idle)
+};
+#endif
+
 static struct pci_driver igc_driver = {
 	.name     = igc_driver_name,
 	.id_table = igc_pci_tbl,
 	.probe    = igc_probe,
 	.remove   = igc_remove,
+#ifdef CONFIG_PM
+	.driver.pm = &igc_pm_ops,
+#endif
+	.shutdown = igc_shutdown,
 };
 
 void igc_set_flag_queue_pairs(struct igc_adapter *adapter,

drivers/net/ethernet/intel/igc/igc_regs.h

@@ -215,6 +215,15 @@
 /* Shadow Ram Write Register - RW */
 #define IGC_SRWR	0x12018
 
+/* Wake Up registers */
+#define IGC_WUC		0x05800  /* Wakeup Control - RW */
+#define IGC_WUFC	0x05808  /* Wakeup Filter Control - RW */
+#define IGC_WUS		0x05810  /* Wakeup Status - R/W1C */
+#define IGC_WUPL	0x05900  /* Wakeup Packet Length - RW */
+
+/* Wake Up packet memory */
+#define IGC_WUPM_REG(_i)	(0x05A00 + ((_i) * 4))
+
 /* forward declaration */
 struct igc_hw;
 u32 igc_rd32(struct igc_hw *hw, u32 reg);