Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next-2.6

drivers/net/igb/e1000_defines.h

@@ -770,4 +770,11 @@
 #define E1000_PCIEMISC_LX_DECISION      0x00000080 /* Lx power decision based
                                                       on DMA coal */
 
+/* Tx Rate-Scheduler Config fields */
+#define E1000_RTTBCNRC_RS_ENA		0x80000000
+#define E1000_RTTBCNRC_RF_DEC_MASK	0x00003FFF
+#define E1000_RTTBCNRC_RF_INT_SHIFT	14
+#define E1000_RTTBCNRC_RF_INT_MASK	\
+	(E1000_RTTBCNRC_RF_DEC_MASK << E1000_RTTBCNRC_RF_INT_SHIFT)
+
 #endif

drivers/net/igb/e1000_regs.h

@@ -106,6 +106,10 @@
 
 #define E1000_RQDPC(_n) (0x0C030 + ((_n) * 0x40))
 
+/* TX Rate Limit Registers */
+#define E1000_RTTDQSEL	0x3604	/* Tx Desc Plane Queue Select - WO */
+#define E1000_RTTBCNRC	0x36B0	/* Tx BCN Rate-Scheduler Config - WO */
+
 /* Split and Replication RX Control - RW */
 #define E1000_RXPBS    0x02404  /* Rx Packet Buffer Size - RW */
 /*

drivers/net/igb/igb.h

@@ -77,6 +77,7 @@ struct vf_data_storage {
 	unsigned long last_nack;
 	u16 pf_vlan; /* When set, guest VLAN config not allowed. */
 	u16 pf_qos;
+	u16 tx_rate;
 };
 
 #define IGB_VF_FLAG_CTS            0x00000001 /* VF is clear to send data */
@@ -323,6 +324,7 @@ struct igb_adapter {
 	u16 rx_ring_count;
 	unsigned int vfs_allocated_count;
 	struct vf_data_storage *vf_data;
+	int vf_rate_link_speed;
 	u32 rss_queues;
 	u32 wvbr;
 };

drivers/net/igb/igb_main.c

@@ -50,12 +50,12 @@
 #endif
 #include "igb.h"
 
-#define DRV_VERSION "2.1.0-k2"
+#define DRV_VERSION "2.4.13-k2"
 char igb_driver_name[] = "igb";
 char igb_driver_version[] = DRV_VERSION;
 static const char igb_driver_string[] =
 				"Intel(R) Gigabit Ethernet Network Driver";
-static const char igb_copyright[] = "Copyright (c) 2007-2009 Intel Corporation.";
+static const char igb_copyright[] = "Copyright (c) 2007-2011 Intel Corporation.";
 
 static const struct e1000_info *igb_info_tbl[] = {
 	[board_82575] = &e1000_82575_info,
@@ -150,6 +150,7 @@ static int igb_ndo_set_vf_vlan(struct net_device *netdev,
 static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate);
 static int igb_ndo_get_vf_config(struct net_device *netdev, int vf,
 				 struct ifla_vf_info *ivi);
+static void igb_check_vf_rate_limit(struct igb_adapter *);
 
 #ifdef CONFIG_PM
 static int igb_suspend(struct pci_dev *, pm_message_t);
@@ -3511,6 +3512,7 @@ static void igb_watchdog_task(struct work_struct *work)
 			netif_carrier_on(netdev);
 
 			igb_ping_all_vfs(adapter);
+			igb_check_vf_rate_limit(adapter);
 
 			/* link state has changed, schedule phy info update */
 			if (!test_bit(__IGB_DOWN, &adapter->state))
@@ -6599,9 +6601,91 @@ static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	return igb_set_vf_mac(adapter, vf, mac);
 }
 
+static int igb_link_mbps(int internal_link_speed)
+{
+	switch (internal_link_speed) {
+	case SPEED_100:
+		return 100;
+	case SPEED_1000:
+		return 1000;
+	default:
+		return 0;
+	}
+}
+
+static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate,
+				  int link_speed)
+{
+	int rf_dec, rf_int;
+	u32 bcnrc_val;
+
+	if (tx_rate != 0) {
+		/* Calculate the rate factor values to set */
+		rf_int = link_speed / tx_rate;
+		rf_dec = (link_speed - (rf_int * tx_rate));
+		rf_dec = (rf_dec * (1<<E1000_RTTBCNRC_RF_INT_SHIFT)) / tx_rate;
+
+		bcnrc_val = E1000_RTTBCNRC_RS_ENA;
+		bcnrc_val |= ((rf_int<<E1000_RTTBCNRC_RF_INT_SHIFT) &
+		               E1000_RTTBCNRC_RF_INT_MASK);
+		bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK);
+	} else {
+		bcnrc_val = 0;
+	}
+
+	wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */
+	wr32(E1000_RTTBCNRC, bcnrc_val);
+}
+
+static void igb_check_vf_rate_limit(struct igb_adapter *adapter)
+{
+	int actual_link_speed, i;
+	bool reset_rate = false;
+
+	/* VF TX rate limit was not set or not supported */
+	if ((adapter->vf_rate_link_speed == 0) ||
+	    (adapter->hw.mac.type != e1000_82576))
+		return;
+
+	actual_link_speed = igb_link_mbps(adapter->link_speed);
+	if (actual_link_speed != adapter->vf_rate_link_speed) {
+		reset_rate = true;
+		adapter->vf_rate_link_speed = 0;
+		dev_info(&adapter->pdev->dev,
+		         "Link speed has been changed. VF Transmit "
+		         "rate is disabled\n");
+	}
+
+	for (i = 0; i < adapter->vfs_allocated_count; i++) {
+		if (reset_rate)
+			adapter->vf_data[i].tx_rate = 0;
+
+		igb_set_vf_rate_limit(&adapter->hw, i,
+		                      adapter->vf_data[i].tx_rate,
+		                      actual_link_speed);
+	}
+}
+
 static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
 {
-	return -EOPNOTSUPP;
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	int actual_link_speed;
+
+	if (hw->mac.type != e1000_82576)
+		return -EOPNOTSUPP;
+
+	actual_link_speed = igb_link_mbps(adapter->link_speed);
+	if ((vf >= adapter->vfs_allocated_count) ||
+	    (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) ||
+	    (tx_rate < 0) || (tx_rate > actual_link_speed))
+		return -EINVAL;
+
+	adapter->vf_rate_link_speed = actual_link_speed;
+	adapter->vf_data[vf].tx_rate = (u16)tx_rate;
+	igb_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);
+
+	return 0;
 }
 
 static int igb_ndo_get_vf_config(struct net_device *netdev,
@@ -6612,7 +6696,7 @@ static int igb_ndo_get_vf_config(struct net_device *netdev,
 		return -EINVAL;
 	ivi->vf = vf;
 	memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN);
-	ivi->tx_rate = 0;
+	ivi->tx_rate = adapter->vf_data[vf].tx_rate;
 	ivi->vlan = adapter->vf_data[vf].pf_vlan;
 	ivi->qos = adapter->vf_data[vf].pf_qos;
 	return 0;

drivers/net/igbvf/igbvf.h

@@ -201,9 +201,6 @@ struct igbvf_adapter {
 	unsigned int restart_queue;
 	u32 txd_cmd;
 
-	bool detect_tx_hung;
-	u8 tx_timeout_factor;
-
 	u32 tx_int_delay;
 	u32 tx_abs_int_delay;
 

drivers/net/igbvf/netdev.c

@@ -396,35 +396,6 @@ static void igbvf_put_txbuf(struct igbvf_adapter *adapter,
 	buffer_info->time_stamp = 0;
 }
 
-static void igbvf_print_tx_hang(struct igbvf_adapter *adapter)
-{
-	struct igbvf_ring *tx_ring = adapter->tx_ring;
-	unsigned int i = tx_ring->next_to_clean;
-	unsigned int eop = tx_ring->buffer_info[i].next_to_watch;
-	union e1000_adv_tx_desc *eop_desc = IGBVF_TX_DESC_ADV(*tx_ring, eop);
-
-	/* detected Tx unit hang */
-	dev_err(&adapter->pdev->dev,
-	        "Detected Tx Unit Hang:\n"
-	        "  TDH                  <%x>\n"
-	        "  TDT                  <%x>\n"
-	        "  next_to_use          <%x>\n"
-	        "  next_to_clean        <%x>\n"
-	        "buffer_info[next_to_clean]:\n"
-	        "  time_stamp           <%lx>\n"
-	        "  next_to_watch        <%x>\n"
-	        "  jiffies              <%lx>\n"
-	        "  next_to_watch.status <%x>\n",
-	        readl(adapter->hw.hw_addr + tx_ring->head),
-	        readl(adapter->hw.hw_addr + tx_ring->tail),
-	        tx_ring->next_to_use,
-	        tx_ring->next_to_clean,
-	        tx_ring->buffer_info[eop].time_stamp,
-	        eop,
-	        jiffies,
-	        eop_desc->wb.status);
-}
-
 /**
  * igbvf_setup_tx_resources - allocate Tx resources (Descriptors)
  * @adapter: board private structure
@@ -771,7 +742,6 @@ static void igbvf_set_itr(struct igbvf_adapter *adapter)
 static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring)
 {
 	struct igbvf_adapter *adapter = tx_ring->adapter;
-	struct e1000_hw *hw = &adapter->hw;
 	struct net_device *netdev = adapter->netdev;
 	struct igbvf_buffer *buffer_info;
 	struct sk_buff *skb;
@@ -832,22 +802,6 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring)
 		}
 	}
 
-	if (adapter->detect_tx_hung) {
-		/* Detect a transmit hang in hardware, this serializes the
-		 * check with the clearing of time_stamp and movement of i */
-		adapter->detect_tx_hung = false;
-		if (tx_ring->buffer_info[i].time_stamp &&
-		    time_after(jiffies, tx_ring->buffer_info[i].time_stamp +
-		               (adapter->tx_timeout_factor * HZ)) &&
-		    !(er32(STATUS) & E1000_STATUS_TXOFF)) {
-
-			tx_desc = IGBVF_TX_DESC_ADV(*tx_ring, i);
-			/* detected Tx unit hang */
-			igbvf_print_tx_hang(adapter);
-
-			netif_stop_queue(netdev);
-		}
-	}
 	adapter->net_stats.tx_bytes += total_bytes;
 	adapter->net_stats.tx_packets += total_packets;
 	return count < tx_ring->count;
@@ -1863,17 +1817,6 @@ static void igbvf_watchdog_task(struct work_struct *work)
 			                          &adapter->link_duplex);
 			igbvf_print_link_info(adapter);
 
-			/* adjust timeout factor according to speed/duplex */
-			adapter->tx_timeout_factor = 1;
-			switch (adapter->link_speed) {
-			case SPEED_10:
-				adapter->tx_timeout_factor = 16;
-				break;
-			case SPEED_100:
-				/* maybe add some timeout factor ? */
-				break;
-			}
-
 			netif_carrier_on(netdev);
 			netif_wake_queue(netdev);
 		}
@@ -1907,9 +1850,6 @@ static void igbvf_watchdog_task(struct work_struct *work)
 	/* Cause software interrupt to ensure Rx ring is cleaned */
 	ew32(EICS, adapter->rx_ring->eims_value);
 
-	/* Force detection of hung controller every watchdog period */
-	adapter->detect_tx_hung = 1;
-
 	/* Reset the timer */
 	if (!test_bit(__IGBVF_DOWN, &adapter->state))
 		mod_timer(&adapter->watchdog_timer,

drivers/net/ixgbe/ixgbe_main.c

@@ -3077,6 +3077,14 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	ixgbe_configure_srrctl(adapter, ring);
 	ixgbe_configure_rscctl(adapter, ring);
 
+	/* If operating in IOV mode set RLPML for X540 */
+	if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) &&
+	    hw->mac.type == ixgbe_mac_X540) {
+		rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
+		rxdctl |= ((ring->netdev->mtu + ETH_HLEN +
+			    ETH_FCS_LEN + VLAN_HLEN) | IXGBE_RXDCTL_RLPML_EN);
+	}
+
 	if (hw->mac.type == ixgbe_mac_82598EB) {
 		/*
 		 * enable cache line friendly hardware writes:
@@ -5441,8 +5449,14 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 
 	/* MTU < 68 is an error and causes problems on some kernels */
-	if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE))
-		return -EINVAL;
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED &&
+	    hw->mac.type != ixgbe_mac_X540) {
+		if ((new_mtu < 68) || (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE))
+			return -EINVAL;
+	} else {
+		if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE))
+			return -EINVAL;
+	}
 
 	e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);
 	/* must set new MTU before calling down or up */

drivers/net/ixgbe/ixgbe_sriov.c

@@ -110,6 +110,33 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
 	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
 }
 
+void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int new_mtu = msgbuf[1];
+	u32 max_frs;
+	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+
+	/* Only X540 supports jumbo frames in IOV mode */
+	if (adapter->hw.mac.type != ixgbe_mac_X540)
+		return;
+
+	/* MTU < 68 is an error and causes problems on some kernels */
+	if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) {
+		e_err(drv, "VF mtu %d out of range\n", new_mtu);
+		return;
+	}
+
+	max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) &
+		   IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
+	if (max_frs < new_mtu) {
+		max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT;
+		IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs);
+	}
+
+	e_info(hw, "VF requests change max MTU to %d\n", new_mtu);
+}
+
 static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
 {
 	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
@@ -302,7 +329,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 		                                 hash_list, vf);
 		break;
 	case IXGBE_VF_SET_LPE:
-		WARN_ON((msgbuf[0] & 0xFFFF) == IXGBE_VF_SET_LPE);
+		ixgbe_set_vf_lpe(adapter, msgbuf);
 		break;
 	case IXGBE_VF_SET_VLAN:
 		add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)

drivers/net/ixgbe/ixgbe_type.h

@@ -1680,6 +1680,8 @@
 #define IXGBE_RXCTRL_DMBYPS     0x00000002  /* Descriptor Monitor Bypass */
 #define IXGBE_RXDCTL_ENABLE     0x02000000  /* Enable specific Rx Queue */
 #define IXGBE_RXDCTL_VME        0x40000000  /* VLAN mode enable */
+#define IXGBE_RXDCTL_RLPMLMASK  0x00003FFF  /* Only supported on the X540 */
+#define IXGBE_RXDCTL_RLPML_EN   0x00008000
 
 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */
 #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/

drivers/net/ixgbevf/defines.h

@@ -65,6 +65,8 @@ typedef u32 ixgbe_link_speed;
 #define IXGBE_RXCTRL_DMBYPS     0x00000002  /* Descriptor Monitor Bypass */
 #define IXGBE_RXDCTL_ENABLE     0x02000000  /* Enable specific Rx Queue */
 #define IXGBE_RXDCTL_VME        0x40000000  /* VLAN mode enable */
+#define IXGBE_RXDCTL_RLPMLMASK  0x00003FFF  /* Only supported on the X540 */
+#define IXGBE_RXDCTL_RLPML_EN   0x00008000
 
 /* DCA Control */
 #define IXGBE_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */

drivers/net/ixgbevf/ixgbevf_main.c

@@ -51,7 +51,7 @@ char ixgbevf_driver_name[] = "ixgbevf";
 static const char ixgbevf_driver_string[] =
 	"Intel(R) 82599 Virtual Function";
 
-#define DRV_VERSION "1.0.19-k0"
+#define DRV_VERSION "1.1.0-k0"
 const char ixgbevf_driver_version[] = DRV_VERSION;
 static char ixgbevf_copyright[] =
 	"Copyright (c) 2009 - 2010 Intel Corporation.";
@@ -107,7 +107,7 @@ static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw,
 }
 
 /*
- * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
+ * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors
  * @adapter: pointer to adapter struct
  * @direction: 0 for Rx, 1 for Tx, -1 for other causes
  * @queue: queue to map the corresponding interrupt to
@@ -1017,7 +1017,7 @@ static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data)
 }
 
 /**
- * ixgbe_msix_clean_rx - single unshared vector rx clean (all queues)
+ * ixgbevf_msix_clean_rx - single unshared vector rx clean (all queues)
  * @irq: unused
  * @data: pointer to our q_vector struct for this interrupt vector
  **/
@@ -1665,6 +1665,11 @@ static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 		j = adapter->rx_ring[i].reg_idx;
 		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
 		rxdctl |= IXGBE_RXDCTL_ENABLE;
+		if (hw->mac.type == ixgbe_mac_X540_vf) {
+			rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
+			rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) |
+				   IXGBE_RXDCTL_RLPML_EN);
+		}
 		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl);
 		ixgbevf_rx_desc_queue_enable(adapter, i);
 	}
@@ -1967,7 +1972,7 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
 }
 
 /*
- * ixgbe_set_num_queues: Allocate queues for device, feature dependant
+ * ixgbevf_set_num_queues: Allocate queues for device, feature dependant
  * @adapter: board private structure to initialize
  *
  * This is the top level queue allocation routine.  The order here is very
@@ -3217,10 +3222,16 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p)
 static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+	int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE;
+	u32 msg[2];
+
+	if (adapter->hw.mac.type == ixgbe_mac_X540_vf)
+		max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE;
 
 	/* MTU < 68 is an error and causes problems on some kernels */
-	if ((new_mtu < 68) || (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE))
+	if ((new_mtu < 68) || (max_frame > max_possible_frame))
 		return -EINVAL;
 
 	hw_dbg(&adapter->hw, "changing MTU from %d to %d\n",
@@ -3228,6 +3239,10 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	/* must set new MTU before calling down or up */
 	netdev->mtu = new_mtu;
 
+	msg[0] = IXGBE_VF_SET_LPE;
+	msg[1] = max_frame;
+	hw->mbx.ops.write_posted(hw, msg, 2);
+
 	if (netif_running(netdev))
 		ixgbevf_reinit_locked(adapter);
 
@@ -3519,9 +3534,9 @@ static struct pci_driver ixgbevf_driver = {
 };
 
 /**
- * ixgbe_init_module - Driver Registration Routine
+ * ixgbevf_init_module - Driver Registration Routine
  *
- * ixgbe_init_module is the first routine called when the driver is
+ * ixgbevf_init_module is the first routine called when the driver is
  * loaded. All it does is register with the PCI subsystem.
  **/
 static int __init ixgbevf_init_module(void)
@@ -3539,9 +3554,9 @@ static int __init ixgbevf_init_module(void)
 module_init(ixgbevf_init_module);
 
 /**
- * ixgbe_exit_module - Driver Exit Cleanup Routine
+ * ixgbevf_exit_module - Driver Exit Cleanup Routine
  *
- * ixgbe_exit_module is called just before the driver is removed
+ * ixgbevf_exit_module is called just before the driver is removed
  * from memory.
  **/
 static void __exit ixgbevf_exit_module(void)
@@ -3551,7 +3566,7 @@ static void __exit ixgbevf_exit_module(void)
 
 #ifdef DEBUG
 /**
- * ixgbe_get_hw_dev_name - return device name string
+ * ixgbevf_get_hw_dev_name - return device name string
  * used by hardware layer to print debugging information
  **/
 char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw)