[net-next-2.6 PATCH 01/23] igb: add support for seperate tx-usecs setting in ethtool

[net-next-2.6 PATCH 01/23] igb: add support for seperate tx-usecs setting in ethtool

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch adds support for a seperate tx-usecs interrupt moderation setting
in ethtool which is supported when tx and rx interrupt vectors are sperated.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb.h         |    5 +++-
 drivers/net/igb/igb_ethtool.c |   49 +++++++++++++++++++++++++++++++----------
 drivers/net/igb/igb_main.c    |   22 ++++++++++++------
 3 files changed, 54 insertions(+), 22 deletions(-)

diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index 6c35c90..bef8cdc 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -249,8 +249,8 @@ struct igb_adapter {
 	unsigned int total_rx_bytes;
 	unsigned int total_rx_packets;
 	/* Interrupt Throttle Rate */
-	u32 itr;
-	u32 itr_setting;
+	u32 rx_itr_setting;
+	u32 tx_itr_setting;
 	u16 tx_itr;
 	u16 rx_itr;
 
@@ -321,6 +321,7 @@ struct igb_adapter {
 #define IGB_FLAG_HAS_MSI           (1 << 0)
 #define IGB_FLAG_DCA_ENABLED       (1 << 1)
 #define IGB_FLAG_QUAD_PORT_A       (1 << 2)
+#define IGB_FLAG_QUEUE_PAIRS       (1 << 3)
 
 enum e1000_state_t {
 	__IGB_TESTING,
diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c
index 048a615..84fe25a 100644
--- a/drivers/net/igb/igb_ethtool.c
+++ b/drivers/net/igb/igb_ethtool.c
@@ -1827,18 +1827,37 @@ static int igb_set_coalesce(struct net_device *netdev,
 	    (ec->rx_coalesce_usecs == 2))
 		return -EINVAL;
 
+	if ((ec->tx_coalesce_usecs > IGB_MAX_ITR_USECS) ||
+	    ((ec->tx_coalesce_usecs > 3) &&
+	     (ec->tx_coalesce_usecs < IGB_MIN_ITR_USECS)) ||
+	    (ec->tx_coalesce_usecs == 2))
+		return -EINVAL;
+
+	if ((adapter->flags & IGB_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
+		return -EINVAL;
+
 	/* convert to rate of irq's per second */
-	if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3) {
-		adapter->itr_setting = ec->rx_coalesce_usecs;
-		adapter->itr = IGB_START_ITR;
-	} else {
-		adapter->itr_setting = ec->rx_coalesce_usecs << 2;
-		adapter->itr = adapter->itr_setting;
-	}
+	if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3)
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs;
+	else
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2;
+
+	/* convert to rate of irq's per second */
+	if (adapter->flags & IGB_FLAG_QUEUE_PAIRS)
+		adapter->tx_itr_setting = adapter->rx_itr_setting;
+	else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3)
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs;
+	else
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2;
 
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		struct igb_q_vector *q_vector = adapter->q_vector[i];
-		q_vector->itr_val = adapter->itr;
+		if (q_vector->rx_ring)
+			q_vector->itr_val = adapter->rx_itr_setting;
+		else
+			q_vector->itr_val = adapter->tx_itr_setting;
+		if (q_vector->itr_val && q_vector->itr_val <= 3)
+			q_vector->itr_val = IGB_START_ITR;
 		q_vector->set_itr = 1;
 	}
 
@@ -1850,15 +1869,21 @@ static int igb_get_coalesce(struct net_device *netdev,
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->itr_setting <= 3)
-		ec->rx_coalesce_usecs = adapter->itr_setting;
+	if (adapter->rx_itr_setting <= 3)
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting;
 	else
-		ec->rx_coalesce_usecs = adapter->itr_setting >> 2;
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
+
+	if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) {
+		if (adapter->tx_itr_setting <= 3)
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting;
+		else
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2;
+	}
 
 	return 0;
 }
 
-
 static int igb_nway_reset(struct net_device *netdev)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index c9fda11..5724ac8 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -734,6 +734,8 @@ msi_only:
 		dev_info(&adapter->pdev->dev, "IOV Disabled\n");
 	}
 #endif
+	adapter->vfs_allocated_count = 0;
+	adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
 	adapter->num_rx_queues = 1;
 	adapter->num_tx_queues = 1;
 	adapter->num_q_vectors = 1;
@@ -791,7 +793,9 @@ static void igb_map_rx_ring_to_vector(struct igb_adapter *adapter,
 	q_vector = adapter->q_vector[v_idx];
 	q_vector->rx_ring = &adapter->rx_ring[ring_idx];
 	q_vector->rx_ring->q_vector = q_vector;
-	q_vector->itr_val = adapter->itr;
+	q_vector->itr_val = adapter->rx_itr_setting;
+	if (q_vector->itr_val && q_vector->itr_val <= 3)
+		q_vector->itr_val = IGB_START_ITR;
 }
 
 static void igb_map_tx_ring_to_vector(struct igb_adapter *adapter,
@@ -802,7 +806,9 @@ static void igb_map_tx_ring_to_vector(struct igb_adapter *adapter,
 	q_vector = adapter->q_vector[v_idx];
 	q_vector->tx_ring = &adapter->tx_ring[ring_idx];
 	q_vector->tx_ring->q_vector = q_vector;
-	q_vector->itr_val = adapter->itr;
+	q_vector->itr_val = adapter->tx_itr_setting;
+	if (q_vector->itr_val && q_vector->itr_val <= 3)
+		q_vector->itr_val = IGB_START_ITR;
 }
 
 /**
@@ -1597,9 +1603,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	hw->fc.requested_mode = e1000_fc_default;
 	hw->fc.current_mode = e1000_fc_default;
 
-	adapter->itr_setting = IGB_DEFAULT_ITR;
-	adapter->itr = IGB_START_ITR;
-
 	igb_validate_mdi_setting(hw);
 
 	/* Initial Wake on LAN setting If APM wake is enabled in the EEPROM,
@@ -1854,6 +1857,9 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 
 	adapter->tx_ring_count = IGB_DEFAULT_TXD;
 	adapter->rx_ring_count = IGB_DEFAULT_RXD;
+	adapter->rx_itr_setting = IGB_DEFAULT_ITR;
+	adapter->tx_itr_setting = IGB_DEFAULT_ITR;
+
 	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
@@ -3052,7 +3058,6 @@ enum latency_range {
 	latency_invalid = 255
 };
 
-
 /**
  * igb_update_ring_itr - update the dynamic ITR value based on packet size
  *
@@ -3216,7 +3221,7 @@ static void igb_set_itr(struct igb_adapter *adapter)
 	current_itr = max(adapter->rx_itr, adapter->tx_itr);
 
 	/* conservative mode (itr 3) eliminates the lowest_latency setting */
-	if (adapter->itr_setting == 3 && current_itr == lowest_latency)
+	if (adapter->rx_itr_setting == 3 && current_itr == lowest_latency)
 		current_itr = low_latency;
 
 	switch (current_itr) {
@@ -4577,7 +4582,8 @@ static inline void igb_ring_irq_enable(struct igb_q_vector *q_vector)
 	struct igb_adapter *adapter = q_vector->adapter;
 	struct e1000_hw *hw = &adapter->hw;
 
-	if (adapter->itr_setting & 3) {
+	if ((q_vector->rx_ring && (adapter->rx_itr_setting & 3)) ||
+	    (!q_vector->rx_ring && (adapter->tx_itr_setting & 3))) {
 		if (!adapter->msix_entries)
 			igb_set_itr(adapter);
 		else

[net-next-2.6 PATCH 02/23] igb: cleanup some of the code related to hw timestamping

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

The code for the hw timestamping is a bit bulky and making some of the
functions difficult to read.  In order to clean things up a bit I am moving
the timestamping operations into seperate functions.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/e1000_82575.h   |   14 +
 drivers/net/igb/e1000_defines.h |   33 +++
 drivers/net/igb/e1000_regs.h    |   65 +-----
 drivers/net/igb/igb.h           |    1 
 drivers/net/igb/igb_main.c      |  397 ++++++++++++++++++---------------------
 5 files changed, 242 insertions(+), 268 deletions(-)

diff --git a/drivers/net/igb/e1000_82575.h b/drivers/net/igb/e1000_82575.h
index 9418683..cbe4757 100644
--- a/drivers/net/igb/e1000_82575.h
+++ b/drivers/net/igb/e1000_82575.h
@@ -66,6 +66,8 @@ extern void igb_rx_fifo_flush_82575(struct e1000_hw *hw);
     E1000_EICR_RX_QUEUE3)
 
 /* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */
+#define E1000_IMIREXT_SIZE_BP     0x00001000  /* Packet size bypass */
+#define E1000_IMIREXT_CTRL_BP     0x00080000  /* Bypass check of ctrl bits */
 
 /* Receive Descriptor - Advanced */
 union e1000_adv_rx_desc {
@@ -98,6 +100,7 @@ union e1000_adv_rx_desc {
 
 #define E1000_RXDADV_HDRBUFLEN_MASK      0x7FE0
 #define E1000_RXDADV_HDRBUFLEN_SHIFT     5
+#define E1000_RXDADV_STAT_TS             0x10000 /* Pkt was time stamped */
 
 /* Transmit Descriptor - Advanced */
 union e1000_adv_tx_desc {
@@ -167,6 +170,17 @@ struct e1000_adv_tx_context_desc {
 #define E1000_DCA_TXCTRL_CPUID_SHIFT 24 /* Tx CPUID now in the last byte */
 #define E1000_DCA_RXCTRL_CPUID_SHIFT 24 /* Rx CPUID now in the last byte */
 
+/* ETQF register bit definitions */
+#define E1000_ETQF_FILTER_ENABLE   (1 << 26)
+#define E1000_ETQF_1588            (1 << 30)
+
+/* FTQF register bit definitions */
+#define E1000_FTQF_VF_BP               0x00008000
+#define E1000_FTQF_1588_TIME_STAMP     0x08000000
+#define E1000_FTQF_MASK                0xF0000000
+#define E1000_FTQF_MASK_PROTO_BP       0x10000000
+#define E1000_FTQF_MASK_SOURCE_PORT_BP 0x80000000
+
 #define E1000_NVM_APME_82575          0x0400
 #define MAX_NUM_VFS                   8
 
diff --git a/drivers/net/igb/e1000_defines.h b/drivers/net/igb/e1000_defines.h
index cb91683..48fcab0 100644
--- a/drivers/net/igb/e1000_defines.h
+++ b/drivers/net/igb/e1000_defines.h
@@ -435,6 +435,39 @@
 /* Flow Control */
 #define E1000_FCRTL_XONE 0x80000000     /* Enable XON frame transmission */
 
+#define E1000_TSYNCTXCTL_VALID    0x00000001 /* tx timestamp valid */
+#define E1000_TSYNCTXCTL_ENABLED  0x00000010 /* enable tx timestampping */
+
+#define E1000_TSYNCRXCTL_VALID      0x00000001 /* rx timestamp valid */
+#define E1000_TSYNCRXCTL_TYPE_MASK  0x0000000E /* rx type mask */
+#define E1000_TSYNCRXCTL_TYPE_L2_V2       0x00
+#define E1000_TSYNCRXCTL_TYPE_L4_V1       0x02
+#define E1000_TSYNCRXCTL_TYPE_L2_L4_V2    0x04
+#define E1000_TSYNCRXCTL_TYPE_ALL         0x08
+#define E1000_TSYNCRXCTL_TYPE_EVENT_V2    0x0A
+#define E1000_TSYNCRXCTL_ENABLED    0x00000010 /* enable rx timestampping */
+
+#define E1000_TSYNCRXCFG_PTP_V1_CTRLT_MASK   0x000000FF
+#define E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE       0x00
+#define E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE  0x01
+#define E1000_TSYNCRXCFG_PTP_V1_FOLLOWUP_MESSAGE   0x02
+#define E1000_TSYNCRXCFG_PTP_V1_DELAY_RESP_MESSAGE 0x03
+#define E1000_TSYNCRXCFG_PTP_V1_MANAGEMENT_MESSAGE 0x04
+
+#define E1000_TSYNCRXCFG_PTP_V2_MSGID_MASK               0x00000F00
+#define E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE                 0x0000
+#define E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE            0x0100
+#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_REQ_MESSAGE       0x0200
+#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_RESP_MESSAGE      0x0300
+#define E1000_TSYNCRXCFG_PTP_V2_FOLLOWUP_MESSAGE             0x0800
+#define E1000_TSYNCRXCFG_PTP_V2_DELAY_RESP_MESSAGE           0x0900
+#define E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_FOLLOWUP_MESSAGE  0x0A00
+#define E1000_TSYNCRXCFG_PTP_V2_ANNOUNCE_MESSAGE             0x0B00
+#define E1000_TSYNCRXCFG_PTP_V2_SIGNALLING_MESSAGE           0x0C00
+#define E1000_TSYNCRXCFG_PTP_V2_MANAGEMENT_MESSAGE           0x0D00
+
+#define E1000_TIMINCA_16NS_SHIFT 24
+
 /* PCI Express Control */
 #define E1000_GCR_CMPL_TMOUT_MASK       0x0000F000
 #define E1000_GCR_CMPL_TMOUT_10ms       0x00001000
diff --git a/drivers/net/igb/e1000_regs.h b/drivers/net/igb/e1000_regs.h
index e06c3b7..24f2c24 100644
--- a/drivers/net/igb/e1000_regs.h
+++ b/drivers/net/igb/e1000_regs.h
@@ -76,59 +76,18 @@
 #define E1000_FCRTV    0x02460  /* Flow Control Refresh Timer Value - RW */
 
 /* IEEE 1588 TIMESYNCH */
-#define E1000_TSYNCTXCTL 0x0B614
-#define E1000_TSYNCTXCTL_VALID (1<<0)
-#define E1000_TSYNCTXCTL_ENABLED (1<<4)
-#define E1000_TSYNCRXCTL 0x0B620
-#define E1000_TSYNCRXCTL_VALID (1<<0)
-#define E1000_TSYNCRXCTL_ENABLED (1<<4)
-enum {
-	E1000_TSYNCRXCTL_TYPE_L2_V2 = 0,
-	E1000_TSYNCRXCTL_TYPE_L4_V1 = (1<<1),
-	E1000_TSYNCRXCTL_TYPE_L2_L4_V2 = (1<<2),
-	E1000_TSYNCRXCTL_TYPE_ALL = (1<<3),
-	E1000_TSYNCRXCTL_TYPE_EVENT_V2 = (1<<3) | (1<<1),
-};
-#define E1000_TSYNCRXCFG 0x05F50
-enum {
-	E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE = 0<<0,
-	E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE = 1<<0,
-	E1000_TSYNCRXCFG_PTP_V1_FOLLOWUP_MESSAGE = 2<<0,
-	E1000_TSYNCRXCFG_PTP_V1_DELAY_RESP_MESSAGE = 3<<0,
-	E1000_TSYNCRXCFG_PTP_V1_MANAGEMENT_MESSAGE = 4<<0,
-
-	E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE = 0<<8,
-	E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE = 1<<8,
-	E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_REQ_MESSAGE = 2<<8,
-	E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_RESP_MESSAGE = 3<<8,
-	E1000_TSYNCRXCFG_PTP_V2_FOLLOWUP_MESSAGE = 8<<8,
-	E1000_TSYNCRXCFG_PTP_V2_DELAY_RESP_MESSAGE = 9<<8,
-	E1000_TSYNCRXCFG_PTP_V2_PATH_DELAY_FOLLOWUP_MESSAGE = 0xA<<8,
-	E1000_TSYNCRXCFG_PTP_V2_ANNOUNCE_MESSAGE = 0xB<<8,
-	E1000_TSYNCRXCFG_PTP_V2_SIGNALLING_MESSAGE = 0xC<<8,
-	E1000_TSYNCRXCFG_PTP_V2_MANAGEMENT_MESSAGE = 0xD<<8,
-};
-#define E1000_SYSTIML 0x0B600
-#define E1000_SYSTIMH 0x0B604
-#define E1000_TIMINCA 0x0B608
-
-#define E1000_RXMTRL     0x0B634
-#define E1000_RXSTMPL 0x0B624
-#define E1000_RXSTMPH 0x0B628
-#define E1000_RXSATRL 0x0B62C
-#define E1000_RXSATRH 0x0B630
-
-#define E1000_TXSTMPL 0x0B618
-#define E1000_TXSTMPH 0x0B61C
-
-#define E1000_ETQF0   0x05CB0
-#define E1000_ETQF1   0x05CB4
-#define E1000_ETQF2   0x05CB8
-#define E1000_ETQF3   0x05CBC
-#define E1000_ETQF4   0x05CC0
-#define E1000_ETQF5   0x05CC4
-#define E1000_ETQF6   0x05CC8
-#define E1000_ETQF7   0x05CCC
+#define E1000_TSYNCRXCTL 0x0B620 /* Rx Time Sync Control register - RW */
+#define E1000_TSYNCTXCTL 0x0B614 /* Tx Time Sync Control register - RW */
+#define E1000_TSYNCRXCFG 0x05F50 /* Time Sync Rx Configuration - RW */
+#define E1000_RXSTMPL    0x0B624 /* Rx timestamp Low - RO */
+#define E1000_RXSTMPH    0x0B628 /* Rx timestamp High - RO */
+#define E1000_RXSATRL    0x0B62C /* Rx timestamp attribute low - RO */
+#define E1000_RXSATRH    0x0B630 /* Rx timestamp attribute high - RO */
+#define E1000_TXSTMPL    0x0B618 /* Tx timestamp value Low - RO */
+#define E1000_TXSTMPH    0x0B61C /* Tx timestamp value High - RO */
+#define E1000_SYSTIML    0x0B600 /* System time register Low - RO */
+#define E1000_SYSTIMH    0x0B604 /* System time register High - RO */
+#define E1000_TIMINCA    0x0B608 /* Increment attributes register - RW */
 
 /* Filtering Registers */
 #define E1000_SAQF(_n) (0x5980 + 4 * (_n))
diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index bef8cdc..1a0ae57 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -323,6 +323,7 @@ struct igb_adapter {
 #define IGB_FLAG_QUAD_PORT_A       (1 << 2)
 #define IGB_FLAG_QUEUE_PAIRS       (1 << 3)
 
+#define IGB_82576_TSYNC_SHIFT 19
 enum e1000_state_t {
 	__IGB_TESTING,
 	__IGB_RESETTING,
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 5724ac8..7e628ba 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -220,38 +220,6 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
 /**
- * Scale the NIC clock cycle by a large factor so that
- * relatively small clock corrections can be added or
- * substracted at each clock tick. The drawbacks of a
- * large factor are a) that the clock register overflows
- * more quickly (not such a big deal) and b) that the
- * increment per tick has to fit into 24 bits.
- *
- * Note that
- *   TIMINCA = IGB_TSYNC_CYCLE_TIME_IN_NANOSECONDS *
- *             IGB_TSYNC_SCALE
- *   TIMINCA += TIMINCA * adjustment [ppm] / 1e9
- *
- * The base scale factor is intentionally a power of two
- * so that the division in %struct timecounter can be done with
- * a shift.
- */
-#define IGB_TSYNC_SHIFT (19)
-#define IGB_TSYNC_SCALE (1<<IGB_TSYNC_SHIFT)
-
-/**
- * The duration of one clock cycle of the NIC.
- *
- * @todo This hard-coded value is part of the specification and might change
- * in future hardware revisions. Add revision check.
- */
-#define IGB_TSYNC_CYCLE_TIME_IN_NANOSECONDS 16
-
-#if (IGB_TSYNC_SCALE * IGB_TSYNC_CYCLE_TIME_IN_NANOSECONDS) >= (1<<24)
-# error IGB_TSYNC_SCALE and/or IGB_TSYNC_CYCLE_TIME_IN_NANOSECONDS are too large to fit into TIMINCA
-#endif
-
-/**
  * igb_read_clock - read raw cycle counter (to be used by time counter)
  */
 static cycle_t igb_read_clock(const struct cyclecounter *tc)
@@ -259,11 +227,11 @@ static cycle_t igb_read_clock(const struct cyclecounter *tc)
 	struct igb_adapter *adapter =
 		container_of(tc, struct igb_adapter, cycles);
 	struct e1000_hw *hw = &adapter->hw;
-	u64 stamp;
-
-	stamp =  rd32(E1000_SYSTIML);
-	stamp |= (u64)rd32(E1000_SYSTIMH) << 32ULL;
+	u64 stamp = 0;
+	int shift = 0;
 
+	stamp |= (u64)rd32(E1000_SYSTIML) << shift;
+	stamp |= (u64)rd32(E1000_SYSTIMH) << (shift + 32);
 	return stamp;
 }
 
@@ -1669,59 +1637,58 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 		dev_info(&pdev->dev, "DCA enabled\n");
 		igb_setup_dca(adapter);
 	}
-#endif
 
-	/*
-	 * Initialize hardware timer: we keep it running just in case
-	 * that some program needs it later on.
-	 */
-	memset(&adapter->cycles, 0, sizeof(adapter->cycles));
-	adapter->cycles.read = igb_read_clock;
-	adapter->cycles.mask = CLOCKSOURCE_MASK(64);
-	adapter->cycles.mult = 1;
-	adapter->cycles.shift = IGB_TSYNC_SHIFT;
-	wr32(E1000_TIMINCA,
-	     (1<<24) |
-	     IGB_TSYNC_CYCLE_TIME_IN_NANOSECONDS * IGB_TSYNC_SCALE);
-#if 0
-	/*
-	 * Avoid rollover while we initialize by resetting the time counter.
-	 */
-	wr32(E1000_SYSTIML, 0x00000000);
-	wr32(E1000_SYSTIMH, 0x00000000);
-#else
-	/*
-	 * Set registers so that rollover occurs soon to test this.
-	 */
-	wr32(E1000_SYSTIML, 0x00000000);
-	wr32(E1000_SYSTIMH, 0xFF800000);
 #endif
-	wrfl();
-	timecounter_init(&adapter->clock,
-			 &adapter->cycles,
-			 ktime_to_ns(ktime_get_real()));
 
-	/*
-	 * Synchronize our NIC clock against system wall clock. NIC
-	 * time stamp reading requires ~3us per sample, each sample
-	 * was pretty stable even under load => only require 10
-	 * samples for each offset comparison.
-	 */
-	memset(&adapter->compare, 0, sizeof(adapter->compare));
-	adapter->compare.source = &adapter->clock;
-	adapter->compare.target = ktime_get_real;
-	adapter->compare.num_samples = 10;
-	timecompare_update(&adapter->compare, 0);
-
-#ifdef DEBUG
-	{
-		char buffer[160];
-		printk(KERN_DEBUG
-			"igb: %s: hw %p initialized timer\n",
-			igb_get_time_str(adapter, buffer),
-			&adapter->hw);
+	switch (hw->mac.type) {
+	case e1000_82576:
+		/*
+		 * Initialize hardware timer: we keep it running just in case
+		 * that some program needs it later on.
+		 */
+		memset(&adapter->cycles, 0, sizeof(adapter->cycles));
+		adapter->cycles.read = igb_read_clock;
+		adapter->cycles.mask = CLOCKSOURCE_MASK(64);
+		adapter->cycles.mult = 1;
+		/**
+		 * Scale the NIC clock cycle by a large factor so that
+		 * relatively small clock corrections can be added or
+		 * substracted at each clock tick. The drawbacks of a large
+		 * factor are a) that the clock register overflows more quickly
+		 * (not such a big deal) and b) that the increment per tick has
+		 * to fit into 24 bits.  As a result we need to use a shift of
+		 * 19 so we can fit a value of 16 into the TIMINCA register.
+		 */
+		adapter->cycles.shift = IGB_82576_TSYNC_SHIFT;
+		wr32(E1000_TIMINCA,
+		                (1 << E1000_TIMINCA_16NS_SHIFT) |
+		                (16 << IGB_82576_TSYNC_SHIFT));
+
+		/* Set registers so that rollover occurs soon to test this. */
+		wr32(E1000_SYSTIML, 0x00000000);
+		wr32(E1000_SYSTIMH, 0xFF800000);
+		wrfl();
+
+		timecounter_init(&adapter->clock,
+				 &adapter->cycles,
+				 ktime_to_ns(ktime_get_real()));
+		/*
+		 * Synchronize our NIC clock against system wall clock. NIC
+		 * time stamp reading requires ~3us per sample, each sample
+		 * was pretty stable even under load => only require 10
+		 * samples for each offset comparison.
+		 */
+		memset(&adapter->compare, 0, sizeof(adapter->compare));
+		adapter->compare.source = &adapter->clock;
+		adapter->compare.target = ktime_get_real;
+		adapter->compare.num_samples = 10;
+		timecompare_update(&adapter->compare, 0);
+		break;
+	case e1000_82575:
+		/* 82575 does not support timesync */
+	default:
+		break;
 	}
-#endif
 
 	dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
 	/* print bus type/speed/width info */
@@ -3596,7 +3563,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 	u8 hdr_len = 0;
 	int count = 0;
 	int tso = 0;
-	union skb_shared_tx *shtx;
+	union skb_shared_tx *shtx = skb_tx(skb);
 
 	/* need: 1 descriptor per page,
 	 *       + 2 desc gap to keep tail from touching head,
@@ -3608,16 +3575,6 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
-	/*
-	 * TODO: check that there currently is no other packet with
-	 * time stamping in the queue
-	 *
-	 * When doing time stamping, keep the connection to the socket
-	 * a while longer: it is still needed by skb_hwtstamp_tx(),
-	 * called either in igb_tx_hwtstamp() or by our caller when
-	 * doing software time stamping.
-	 */
-	shtx = skb_tx(skb);
 	if (unlikely(shtx->hardware)) {
 		shtx->in_progress = 1;
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
@@ -4633,37 +4590,54 @@ static int igb_poll(struct napi_struct *napi, int budget)
 }
 
 /**
- * igb_hwtstamp - utility function which checks for TX time stamp
+ * igb_systim_to_hwtstamp - convert system time value to hw timestamp
  * @adapter: board private structure
+ * @shhwtstamps: timestamp structure to update
+ * @regval: unsigned 64bit system time value.
+ *
+ * We need to convert the system time value stored in the RX/TXSTMP registers
+ * into a hwtstamp which can be used by the upper level timestamping functions
+ */
+static void igb_systim_to_hwtstamp(struct igb_adapter *adapter,
+                                   struct skb_shared_hwtstamps *shhwtstamps,
+                                   u64 regval)
+{
+	u64 ns;
+
+	ns = timecounter_cyc2time(&adapter->clock, regval);
+	timecompare_update(&adapter->compare, ns);
+	memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps));
+	shhwtstamps->hwtstamp = ns_to_ktime(ns);
+	shhwtstamps->syststamp = timecompare_transform(&adapter->compare, ns);
+}
+
+/**
+ * igb_tx_hwtstamp - utility function which checks for TX time stamp
+ * @q_vector: pointer to q_vector containing needed info
  * @skb: packet that was just sent
  *
  * If we were asked to do hardware stamping and such a time stamp is
  * available, then it must have been for this skb here because we only
  * allow only one such packet into the queue.
  */
-static void igb_tx_hwtstamp(struct igb_adapter *adapter, struct sk_buff *skb)
+static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb)
 {
+	struct igb_adapter *adapter = q_vector->adapter;
 	union skb_shared_tx *shtx = skb_tx(skb);
 	struct e1000_hw *hw = &adapter->hw;
+	struct skb_shared_hwtstamps shhwtstamps;
+	u64 regval;
 
-	if (unlikely(shtx->hardware)) {
-		u32 valid = rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID;
-		if (valid) {
-			u64 regval = rd32(E1000_TXSTMPL);
-			u64 ns;
-			struct skb_shared_hwtstamps shhwtstamps;
-
-			memset(&shhwtstamps, 0, sizeof(shhwtstamps));
-			regval |= (u64)rd32(E1000_TXSTMPH) << 32;
-			ns = timecounter_cyc2time(&adapter->clock,
-						  regval);
-			timecompare_update(&adapter->compare, ns);
-			shhwtstamps.hwtstamp = ns_to_ktime(ns);
-			shhwtstamps.syststamp =
-				timecompare_transform(&adapter->compare, ns);
-			skb_tstamp_tx(skb, &shhwtstamps);
-		}
-	}
+	/* if skb does not support hw timestamp or TX stamp not valid exit */
+	if (likely(!shtx->hardware) ||
+	    !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID))
+		return;
+
+	regval = rd32(E1000_TXSTMPL);
+	regval |= (u64)rd32(E1000_TXSTMPH) << 32;
+
+	igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
+	skb_tstamp_tx(skb, &shhwtstamps);
 }
 
 /**
@@ -4706,7 +4680,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 				total_packets += segs;
 				total_bytes += bytecount;
 
-				igb_tx_hwtstamp(adapter, skb);
+				igb_tx_hwtstamp(q_vector, skb);
 			}
 
 			igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
@@ -4831,6 +4805,34 @@ static inline void igb_rx_checksum_adv(struct igb_ring *ring,
 	dev_dbg(&ring->pdev->dev, "cksum success: bits %08X\n", status_err);
 }
 
+static inline void igb_rx_hwtstamp(struct igb_q_vector *q_vector, u32 staterr,
+                                   struct sk_buff *skb)
+{
+	struct igb_adapter *adapter = q_vector->adapter;
+	struct e1000_hw *hw = &adapter->hw;
+	u64 regval;
+
+	/*
+	 * If this bit is set, then the RX registers contain the time stamp. No
+	 * other packet will be time stamped until we read these registers, so
+	 * read the registers to make them available again. Because only one
+	 * packet can be time stamped at a time, we know that the register
+	 * values must belong to this one here and therefore we don't need to
+	 * compare any of the additional attributes stored for it.
+	 *
+	 * If nothing went wrong, then it should have a skb_shared_tx that we
+	 * can turn into a skb_shared_hwtstamps.
+	 */
+	if (likely(!(staterr & E1000_RXDADV_STAT_TS)))
+		return;
+	if (!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID))
+		return;
+
+	regval = rd32(E1000_RXSTMPL);
+	regval |= (u64)rd32(E1000_RXSTMPH) << 32;
+
+	igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
+}
 static inline u16 igb_get_hlen(struct igb_ring *rx_ring,
                                union e1000_adv_rx_desc *rx_desc)
 {
@@ -4848,10 +4850,8 @@ static inline u16 igb_get_hlen(struct igb_ring *rx_ring,
 static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
                                  int *work_done, int budget)
 {
-	struct igb_adapter *adapter = q_vector->adapter;
 	struct igb_ring *rx_ring = q_vector->rx_ring;
 	struct net_device *netdev = rx_ring->netdev;
-	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = rx_ring->pdev;
 	union e1000_adv_rx_desc *rx_desc , *next_rxd;
 	struct igb_buffer *buffer_info , *next_buffer;
@@ -4930,52 +4930,12 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
 			goto next_desc;
 		}
 send_up:
-		/*
-		 * If this bit is set, then the RX registers contain
-		 * the time stamp. No other packet will be time
-		 * stamped until we read these registers, so read the
-		 * registers to make them available again. Because
-		 * only one packet can be time stamped at a time, we
-		 * know that the register values must belong to this
-		 * one here and therefore we don't need to compare
-		 * any of the additional attributes stored for it.
-		 *
-		 * If nothing went wrong, then it should have a
-		 * skb_shared_tx that we can turn into a
-		 * skb_shared_hwtstamps.
-		 *
-		 * TODO: can time stamping be triggered (thus locking
-		 * the registers) without the packet reaching this point
-		 * here? In that case RX time stamping would get stuck.
-		 *
-		 * TODO: in "time stamp all packets" mode this bit is
-		 * not set. Need a global flag for this mode and then
-		 * always read the registers. Cannot be done without
-		 * a race condition.
-		 */
-		if (unlikely(staterr & E1000_RXD_STAT_TS)) {
-			u64 regval;
-			u64 ns;
-			struct skb_shared_hwtstamps *shhwtstamps =
-				skb_hwtstamps(skb);
-
-			WARN(!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID),
-			     "igb: no RX time stamp available for time stamped packet");
-			regval = rd32(E1000_RXSTMPL);
-			regval |= (u64)rd32(E1000_RXSTMPH) << 32;
-			ns = timecounter_cyc2time(&adapter->clock, regval);
-			timecompare_update(&adapter->compare, ns);
-			memset(shhwtstamps, 0, sizeof(*shhwtstamps));
-			shhwtstamps->hwtstamp = ns_to_ktime(ns);
-			shhwtstamps->syststamp =
-				timecompare_transform(&adapter->compare, ns);
-		}
-
 		if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) {
 			dev_kfree_skb_irq(skb);
 			goto next_desc;
 		}
 
+		igb_rx_hwtstamp(q_vector, staterr, skb);
 		total_bytes += skb->len;
 		total_packets++;
 
@@ -5161,13 +5121,11 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev,
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	struct hwtstamp_config config;
-	u32 tsync_tx_ctl_bit = E1000_TSYNCTXCTL_ENABLED;
-	u32 tsync_rx_ctl_bit = E1000_TSYNCRXCTL_ENABLED;
-	u32 tsync_rx_ctl_type = 0;
+	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
+	u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
 	u32 tsync_rx_cfg = 0;
-	int is_l4 = 0;
-	int is_l2 = 0;
-	short port = 319; /* PTP */
+	bool is_l4 = false;
+	bool is_l2 = false;
 	u32 regval;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
@@ -5179,10 +5137,8 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev,
 
 	switch (config.tx_type) {
 	case HWTSTAMP_TX_OFF:
-		tsync_tx_ctl_bit = 0;
-		break;
+		tsync_tx_ctl = 0;
 	case HWTSTAMP_TX_ON:
-		tsync_tx_ctl_bit = E1000_TSYNCTXCTL_ENABLED;
 		break;
 	default:
 		return -ERANGE;
@@ -5190,7 +5146,7 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev,
 
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		tsync_rx_ctl_bit = 0;
+		tsync_rx_ctl = 0;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -5201,86 +5157,97 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev,
 		 * possible to time stamp both Sync and Delay_Req messages
 		 * => fall back to time stamping all packets
 		 */
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_ALL;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_L4_V1;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
 		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE;
-		is_l4 = 1;
+		is_l4 = true;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_L4_V1;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1;
 		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE;
-		is_l4 = 1;
+		is_l4 = true;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
 		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE;
-		is_l2 = 1;
-		is_l4 = 1;
+		is_l2 = true;
+		is_l4 = true;
 		config.rx_filter = HWTSTAMP_FILTER_SOME;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2;
 		tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE;
-		is_l2 = 1;
-		is_l4 = 1;
+		is_l2 = true;
+		is_l4 = true;
 		config.rx_filter = HWTSTAMP_FILTER_SOME;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		tsync_rx_ctl_type = E1000_TSYNCRXCTL_TYPE_EVENT_V2;
+		tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2;
 		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		is_l2 = 1;
+		is_l2 = true;
 		break;
 	default:
 		return -ERANGE;
 	}
 
+	if (hw->mac.type == e1000_82575) {
+		if (tsync_rx_ctl | tsync_tx_ctl)
+			return -EINVAL;
+		return 0;
+	}
+
 	/* enable/disable TX */
 	regval = rd32(E1000_TSYNCTXCTL);
-	regval = (regval & ~E1000_TSYNCTXCTL_ENABLED) | tsync_tx_ctl_bit;
+	regval &= ~E1000_TSYNCTXCTL_ENABLED;
+	regval |= tsync_tx_ctl;
 	wr32(E1000_TSYNCTXCTL, regval);
 
-	/* enable/disable RX, define which PTP packets are time stamped */
+	/* enable/disable RX */
 	regval = rd32(E1000_TSYNCRXCTL);
-	regval = (regval & ~E1000_TSYNCRXCTL_ENABLED) | tsync_rx_ctl_bit;
-	regval = (regval & ~0xE) | tsync_rx_ctl_type;
+	regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK);
+	regval |= tsync_rx_ctl;
 	wr32(E1000_TSYNCRXCTL, regval);
-	wr32(E1000_TSYNCRXCFG, tsync_rx_cfg);
 
-	/*
-	 * Ethertype Filter Queue Filter[0][15:0] = 0x88F7
-	 *                                          (Ethertype to filter on)
-	 * Ethertype Filter Queue Filter[0][26] = 0x1 (Enable filter)
-	 * Ethertype Filter Queue Filter[0][30] = 0x1 (Enable Timestamping)
-	 */
-	wr32(E1000_ETQF0, is_l2 ? 0x440088f7 : 0);
-
-	/* L4 Queue Filter[0]: only filter by source and destination port */
-	wr32(E1000_SPQF0, htons(port));
-	wr32(E1000_IMIREXT(0), is_l4 ?
-	     ((1<<12) | (1<<19) /* bypass size and control flags */) : 0);
-	wr32(E1000_IMIR(0), is_l4 ?
-	     (htons(port)
-	      | (0<<16) /* immediate interrupt disabled */
-	      | 0 /* (1<<17) bit cleared: do not bypass
-		     destination port check */)
-		: 0);
-	wr32(E1000_FTQF0, is_l4 ?
-	     (0x11 /* UDP */
-	      | (1<<15) /* VF not compared */
-	      | (1<<27) /* Enable Timestamping */
-	      | (7<<28) /* only source port filter enabled,
-			   source/target address and protocol
-			   masked */)
-	     : ((1<<15) | (15<<28) /* all mask bits set = filter not
-				      enabled */));
+	/* define which PTP packets are time stamped */
+	wr32(E1000_TSYNCRXCFG, tsync_rx_cfg);
 
+	/* define ethertype filter for timestamped packets */
+	if (is_l2)
+		wr32(E1000_ETQF(3),
+		                (E1000_ETQF_FILTER_ENABLE | /* enable filter */
+		                 E1000_ETQF_1588 | /* enable timestamping */
+		                 ETH_P_1588));     /* 1588 eth protocol type */
+	else
+		wr32(E1000_ETQF(3), 0);
+
+#define PTP_PORT 319
+	/* L4 Queue Filter[3]: filter by destination port and protocol */
+	if (is_l4) {
+		u32 ftqf = (IPPROTO_UDP /* UDP */
+			| E1000_FTQF_VF_BP /* VF not compared */
+			| E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */
+			| E1000_FTQF_MASK); /* mask all inputs */
+		ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */
+
+		wr32(E1000_IMIR(3), htons(PTP_PORT));
+		wr32(E1000_IMIREXT(3),
+		     (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP));
+		if (hw->mac.type == e1000_82576) {
+			/* enable source port check */
+			wr32(E1000_SPQF(3), htons(PTP_PORT));
+			ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP;
+		}
+		wr32(E1000_FTQF(3), ftqf);
+	} else {
+		wr32(E1000_FTQF(3), E1000_FTQF_MASK);
+	}
 	wrfl();
 
 	adapter->hwtstamp_config = config;

[net-next-2.6 PATCH 03/23] igb: misc cleanups within igb_ethtool.c

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch just goes thorugh and does several cleanups on igb_ethtool.c.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_ethtool.c |  105 +++++++++++++++++++++++------------------
 1 files changed, 60 insertions(+), 45 deletions(-)

diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c
index 84fe25a..d24b902 100644
--- a/drivers/net/igb/igb_ethtool.c
+++ b/drivers/net/igb/igb_ethtool.c
@@ -101,24 +101,25 @@ static const struct igb_stats igb_gstrings_stats[] = {
 };
 
 #define IGB_QUEUE_STATS_LEN \
-	(((((struct igb_adapter *)netdev_priv(netdev))->num_rx_queues)* \
+	((((struct igb_adapter *)netdev_priv(netdev))->num_rx_queues * \
 	  (sizeof(struct igb_rx_queue_stats) / sizeof(u64))) + \
-	 ((((struct igb_adapter *)netdev_priv(netdev))->num_tx_queues) * \
+	 (((struct igb_adapter *)netdev_priv(netdev))->num_tx_queues * \
 	  (sizeof(struct igb_tx_queue_stats) / sizeof(u64))))
 #define IGB_GLOBAL_STATS_LEN	\
-	sizeof(igb_gstrings_stats) / sizeof(struct igb_stats)
+	(sizeof(igb_gstrings_stats) / sizeof(struct igb_stats))
 #define IGB_STATS_LEN (IGB_GLOBAL_STATS_LEN + IGB_QUEUE_STATS_LEN)
 static const char igb_gstrings_test[][ETH_GSTRING_LEN] = {
 	"Register test  (offline)", "Eeprom test    (offline)",
 	"Interrupt test (offline)", "Loopback test  (offline)",
 	"Link test   (on/offline)"
 };
-#define IGB_TEST_LEN sizeof(igb_gstrings_test) / ETH_GSTRING_LEN
+#define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN)
 
 static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 status;
 
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
@@ -153,17 +154,20 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 
 	ecmd->transceiver = XCVR_INTERNAL;
 
-	if (rd32(E1000_STATUS) & E1000_STATUS_LU) {
+	status = rd32(E1000_STATUS);
 
-		adapter->hw.mac.ops.get_speed_and_duplex(hw,
-					&adapter->link_speed,
-					&adapter->link_duplex);
-		ecmd->speed = adapter->link_speed;
+	if (status & E1000_STATUS_LU) {
 
-		/* unfortunately FULL_DUPLEX != DUPLEX_FULL
-		 *          and HALF_DUPLEX != DUPLEX_HALF */
+		if ((status & E1000_STATUS_SPEED_1000) ||
+		    hw->phy.media_type != e1000_media_type_copper)
+			ecmd->speed = SPEED_1000;
+		else if (status & E1000_STATUS_SPEED_100)
+			ecmd->speed = SPEED_100;
+		else
+			ecmd->speed = SPEED_10;
 
-		if (adapter->link_duplex == FULL_DUPLEX)
+		if ((status & E1000_STATUS_FD) ||
+		    hw->phy.media_type != e1000_media_type_copper)
 			ecmd->duplex = DUPLEX_FULL;
 		else
 			ecmd->duplex = DUPLEX_HALF;
@@ -254,8 +258,9 @@ static int igb_set_pauseparam(struct net_device *netdev,
 		if (netif_running(adapter->netdev)) {
 			igb_down(adapter);
 			igb_up(adapter);
-		} else
+		} else {
 			igb_reset(adapter);
+		}
 	} else {
 		if (pause->rx_pause && pause->tx_pause)
 			hw->fc.requested_mode = e1000_fc_full;
@@ -308,7 +313,7 @@ static int igb_set_tx_csum(struct net_device *netdev, u32 data)
 
 	if (data) {
 		netdev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
-		if (adapter->hw.mac.type == e1000_82576)
+		if (adapter->hw.mac.type >= e1000_82576)
 			netdev->features |= NETIF_F_SCTP_CSUM;
 	} else {
 		netdev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -735,12 +740,12 @@ static int igb_set_ringparam(struct net_device *netdev,
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	new_rx_count = max(ring->rx_pending, (u32)IGB_MIN_RXD);
-	new_rx_count = min(new_rx_count, (u32)IGB_MAX_RXD);
+	new_rx_count = min(ring->rx_pending, (u32)IGB_MAX_RXD);
+	new_rx_count = max(new_rx_count, (u16)IGB_MIN_RXD);
 	new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE);
 
-	new_tx_count = max(ring->tx_pending, (u32)IGB_MIN_TXD);
-	new_tx_count = min(new_tx_count, (u32)IGB_MAX_TXD);
+	new_tx_count = min(ring->tx_pending, (u32)IGB_MAX_TXD);
+	new_tx_count = max(new_tx_count, (u16)IGB_MIN_TXD);
 	new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE);
 
 	if ((new_tx_count == adapter->tx_ring_count) &&
@@ -941,7 +946,7 @@ static bool reg_pattern_test(struct igb_adapter *adapter, u64 *data,
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 pat, val;
-	u32 _test[] =
+	static const u32 _test[] =
 		{0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF};
 	for (pat = 0; pat < ARRAY_SIZE(_test); pat++) {
 		wr32(reg, (_test[pat] & write));
@@ -954,6 +959,7 @@ static bool reg_pattern_test(struct igb_adapter *adapter, u64 *data,
 			return 1;
 		}
 	}
+
 	return 0;
 }
 
@@ -971,6 +977,7 @@ static bool reg_set_and_check(struct igb_adapter *adapter, u64 *data,
 		*data = reg;
 		return 1;
 	}
+
 	return 0;
 }
 
@@ -993,14 +1000,14 @@ static int igb_reg_test(struct igb_adapter *adapter, u64 *data)
 	u32 value, before, after;
 	u32 i, toggle;
 
-	toggle = 0x7FFFF3FF;
-
 	switch (adapter->hw.mac.type) {
 	case e1000_82576:
 		test = reg_test_82576;
+		toggle = 0x7FFFF3FF;
 		break;
 	default:
 		test = reg_test_82575;
+		toggle = 0x7FFFF3FF;
 		break;
 	}
 
@@ -1078,8 +1085,7 @@ static int igb_eeprom_test(struct igb_adapter *adapter, u64 *data)
 	*data = 0;
 	/* Read and add up the contents of the EEPROM */
 	for (i = 0; i < (NVM_CHECKSUM_REG + 1); i++) {
-		if ((adapter->hw.nvm.ops.read(&adapter->hw, i, 1, &temp))
-		    < 0) {
+		if ((adapter->hw.nvm.ops.read(&adapter->hw, i, 1, &temp)) < 0) {
 			*data = 1;
 			break;
 		}
@@ -1095,8 +1101,7 @@ static int igb_eeprom_test(struct igb_adapter *adapter, u64 *data)
 
 static irqreturn_t igb_test_intr(int irq, void *data)
 {
-	struct net_device *netdev = (struct net_device *) data;
-	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct igb_adapter *adapter = (struct igb_adapter *) data;
 	struct e1000_hw *hw = &adapter->hw;
 
 	adapter->test_icr |= rd32(E1000_ICR);
@@ -1120,7 +1125,6 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 			*data = 1;
 			return -1;
 		}
-
 	} else if (adapter->flags & IGB_FLAG_HAS_MSI) {
 		shared_int = false;
 		if (request_irq(irq,
@@ -1138,6 +1142,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 	}
 	dev_info(&adapter->pdev->dev, "testing %s interrupt\n",
 		(shared_int ? "shared" : "unshared"));
+
 	/* Disable all the interrupts */
 	wr32(E1000_IMC, ~0);
 	msleep(10);
@@ -1363,7 +1368,10 @@ static int igb_setup_loopback_test(struct igb_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 reg;
 
-	if (hw->phy.media_type == e1000_media_type_internal_serdes) {
+	reg = rd32(E1000_CTRL_EXT);
+
+	/* use CTRL_EXT to identify link type as SGMII can appear as copper */
+	if (reg & E1000_CTRL_EXT_LINK_MODE_MASK) {
 		reg = rd32(E1000_RCTL);
 		reg |= E1000_RCTL_LBM_TCVR;
 		wr32(E1000_RCTL, reg);
@@ -1394,11 +1402,9 @@ static int igb_setup_loopback_test(struct igb_adapter *adapter)
 		wr32(E1000_PCS_LCTL, reg);
 
 		return 0;
-	} else if (hw->phy.media_type == e1000_media_type_copper) {
-		return igb_set_phy_loopback(adapter);
 	}
 
-	return 7;
+	return igb_set_phy_loopback(adapter);
 }
 
 static void igb_loopback_cleanup(struct igb_adapter *adapter)
@@ -1424,19 +1430,21 @@ static void igb_create_lbtest_frame(struct sk_buff *skb,
 				    unsigned int frame_size)
 {
 	memset(skb->data, 0xFF, frame_size);
-	frame_size &= ~1;
-	memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1);
-	memset(&skb->data[frame_size / 2 + 10], 0xBE, 1);
-	memset(&skb->data[frame_size / 2 + 12], 0xAF, 1);
+	frame_size /= 2;
+	memset(&skb->data[frame_size], 0xAA, frame_size - 1);
+	memset(&skb->data[frame_size + 10], 0xBE, 1);
+	memset(&skb->data[frame_size + 12], 0xAF, 1);
 }
 
 static int igb_check_lbtest_frame(struct sk_buff *skb, unsigned int frame_size)
 {
-	frame_size &= ~1;
-	if (*(skb->data + 3) == 0xFF)
-		if ((*(skb->data + frame_size / 2 + 10) == 0xBE) &&
-		   (*(skb->data + frame_size / 2 + 12) == 0xAF))
+	frame_size /= 2;
+	if (*(skb->data + 3) == 0xFF) {
+		if ((*(skb->data + frame_size + 10) == 0xBE) &&
+		   (*(skb->data + frame_size + 12) == 0xAF)) {
 			return 0;
+		}
+	}
 	return 13;
 }
 
@@ -1513,7 +1521,8 @@ static int igb_run_loopback_test(struct igb_adapter *adapter)
 	igb_create_lbtest_frame(skb, size);
 	skb_put(skb, size);
 
-	/* Calculate the loop count based on the largest descriptor ring
+	/*
+	 * Calculate the loop count based on the largest descriptor ring
 	 * The idea is to wrap the largest ring a number of times using 64
 	 * send/receive pairs during each loop
 	 */
@@ -1605,8 +1614,7 @@ static int igb_link_test(struct igb_adapter *adapter, u64 *data)
 		if (hw->mac.autoneg)
 			msleep(4000);
 
-		if (!(rd32(E1000_STATUS) &
-		      E1000_STATUS_LU))
+		if (!(rd32(E1000_STATUS) & E1000_STATUS_LU))
 			*data = 1;
 	}
 	return *data;
@@ -1788,7 +1796,6 @@ static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		adapter->wol |= E1000_WUFC_BC;
 	if (wol->wolopts & WAKE_MAGIC)
 		adapter->wol |= E1000_WUFC_MAG;
-
 	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
 
 	return 0;
@@ -1801,12 +1808,19 @@ static int igb_phys_id(struct net_device *netdev, u32 data)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long timeout;
 
-	if (!data || data > (u32)(MAX_SCHEDULE_TIMEOUT / HZ))
-		data = (u32)(MAX_SCHEDULE_TIMEOUT / HZ);
+	timeout = data * 1000;
+
+	/*
+	 *  msleep_interruptable only accepts unsigned int so we are limited
+	 * in how long a duration we can wait
+	 */
+	if (!timeout || timeout > UINT_MAX)
+		timeout = UINT_MAX;
 
 	igb_blink_led(hw);
-	msleep_interruptible(data * 1000);
+	msleep_interruptible(timeout);
 
 	igb_led_off(hw);
 	clear_bit(IGB_LED_ON, &adapter->led_status);
@@ -1916,6 +1930,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 	char *p = NULL;
 
 	igb_update_stats(adapter);
+
 	for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) {
 		switch (igb_gstrings_stats[i].type) {
 		case NETDEV_STATS:

[net-next-2.6 PATCH 04/23] igb: use packet buffer sizes from RXPBS register

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch changes the configuration for 82576 so that it uses the actual
value of the 82576 rx packet buffer size instead of just assuming the
value.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/e1000_82575.h |    2 ++
 drivers/net/igb/e1000_regs.h  |    2 ++
 drivers/net/igb/igb_main.c    |    3 ++-
 3 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/drivers/net/igb/e1000_82575.h b/drivers/net/igb/e1000_82575.h
index cbe4757..b3808ca 100644
--- a/drivers/net/igb/e1000_82575.h
+++ b/drivers/net/igb/e1000_82575.h
@@ -228,6 +228,8 @@ struct e1000_adv_tx_context_desc {
 
 #define ALL_QUEUES   0xFFFF
 
+/* RX packet buffer size defines */
+#define E1000_RXPBS_SIZE_MASK_82576  0x0000007F
 void igb_vmdq_set_loopback_pf(struct e1000_hw *, bool);
 void igb_vmdq_set_replication_pf(struct e1000_hw *, bool);
 
diff --git a/drivers/net/igb/e1000_regs.h b/drivers/net/igb/e1000_regs.h
index 24f2c24..934e03b 100644
--- a/drivers/net/igb/e1000_regs.h
+++ b/drivers/net/igb/e1000_regs.h
@@ -102,7 +102,9 @@
 #define E1000_ETQF(_n)  (0x05CB0 + (4 * (_n))) /* EType Queue Fltr */
 
 #define E1000_RQDPC(_n) (0x0C030 + ((_n) * 0x40))
+
 /* Split and Replication RX Control - RW */
+#define E1000_RXPBS    0x02404  /* Rx Packet Buffer Size - RW */
 /*
  * Convenience macros
  *
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 7e628ba..2ed2694 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1215,7 +1215,8 @@ void igb_reset(struct igb_adapter *adapter)
 	 */
 	switch (mac->type) {
 	case e1000_82576:
-		pba = E1000_PBA_64K;
+		pba = rd32(E1000_RXPBS);
+		pba &= E1000_RXPBS_SIZE_MASK_82576;
 		break;
 	case e1000_82575:
 	default:

[net-next-2.6 PATCH 05/23] igb: replace the VF clear_to_send with a flags value

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

In order to support future features it is easiest to replace the
clear_to_send boolean with a flag value.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb.h      |    5 +-
 drivers/net/igb/igb_main.c |  125 +++++++++++++++++++++++---------------------
 2 files changed, 70 insertions(+), 60 deletions(-)

diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index 1a0ae57..7801d3f 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -73,9 +73,12 @@ struct vf_data_storage {
 	u16 vf_mc_hashes[IGB_MAX_VF_MC_ENTRIES];
 	u16 num_vf_mc_hashes;
 	u16 vlans_enabled;
-	bool clear_to_send;
+	u32 flags;
+	unsigned long last_nack;
 };
 
+#define IGB_VF_FLAG_CTS            0x00000001 /* VF is clear to send data */
+
 /* RX descriptor control thresholds.
  * PTHRESH - MAC will consider prefetch if it has fewer than this number of
  *           descriptors available in its onboard memory.
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 2ed2694..a9e8ba2 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -125,9 +125,8 @@ static void igb_restore_vlan(struct igb_adapter *);
 static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8);
 static void igb_ping_all_vfs(struct igb_adapter *);
 static void igb_msg_task(struct igb_adapter *);
-static int igb_rcv_msg_from_vf(struct igb_adapter *, u32);
 static void igb_vmm_control(struct igb_adapter *);
-static int igb_set_vf_mac(struct igb_adapter *adapter, int, unsigned char *);
+static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *);
 static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 
 static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
@@ -1291,10 +1290,10 @@ void igb_reset(struct igb_adapter *adapter)
 	if (adapter->vfs_allocated_count) {
 		int i;
 		for (i = 0 ; i < adapter->vfs_allocated_count; i++)
-			adapter->vf_data[i].clear_to_send = false;
+			adapter->vf_data[i].flags = 0;
 
 		/* ping all the active vfs to let them know we are going down */
-			igb_ping_all_vfs(adapter);
+		igb_ping_all_vfs(adapter);
 
 		/* disable transmits and receives */
 		wr32(E1000_VFRE, 0);
@@ -4096,7 +4095,7 @@ static void igb_ping_all_vfs(struct igb_adapter *adapter)
 
 	for (i = 0 ; i < adapter->vfs_allocated_count; i++) {
 		ping = E1000_PF_CONTROL_MSG;
-		if (adapter->vf_data[i].clear_to_send)
+		if (adapter->vf_data[i].flags & IGB_VF_FLAG_CTS)
 			ping |= E1000_VT_MSGTYPE_CTS;
 		igb_write_mbx(hw, &ping, 1, i);
 	}
@@ -4276,15 +4275,14 @@ static int igb_set_vf_vlan(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
 	return igb_vlvf_set(adapter, vid, add, vf);
 }
 
-static inline void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf)
+static inline void igb_vf_reset(struct igb_adapter *adapter, u32 vf)
 {
-	struct e1000_hw *hw = &adapter->hw;
-
-	/* disable mailbox functionality for vf */
-	adapter->vf_data[vf].clear_to_send = false;
+	/* clear all flags */
+	adapter->vf_data[vf].flags = 0;
+	adapter->vf_data[vf].last_nack = jiffies;
 
 	/* reset offloads to defaults */
-	igb_set_vmolr(hw, vf);
+	igb_set_vmolr(&adapter->hw, vf);
 
 	/* reset vlans for device */
 	igb_clear_vf_vfta(adapter, vf);
@@ -4296,7 +4294,18 @@ static inline void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf)
 	igb_set_rx_mode(adapter->netdev);
 }
 
-static inline void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
+static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf)
+{
+	unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses;
+
+	/* generate a new mac address as we were hotplug removed/added */
+	random_ether_addr(vf_mac);
+
+	/* process remaining reset events */
+	igb_vf_reset(adapter, vf);
+}
+
+static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses;
@@ -4305,7 +4314,7 @@ static inline void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 	u8 *addr = (u8 *)(&msgbuf[1]);
 
 	/* process all the same items cleared in a function level reset */
-	igb_vf_reset_event(adapter, vf);
+	igb_vf_reset(adapter, vf);
 
 	/* set vf mac address */
 	igb_rar_set_qsel(adapter, vf_mac, rar_entry, vf);
@@ -4316,8 +4325,7 @@ static inline void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 	reg = rd32(E1000_VFRE);
 	wr32(E1000_VFRE, reg | (1 << vf));
 
-	/* enable mailbox functionality for vf */
-	adapter->vf_data[vf].clear_to_send = true;
+	adapter->vf_data[vf].flags = IGB_VF_FLAG_CTS;
 
 	/* reply to reset with ack and vf mac address */
 	msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK;
@@ -4327,66 +4335,45 @@ static inline void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf)
 
 static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf)
 {
-		unsigned char *addr = (char *)&msg[1];
-		int err = -1;
+	unsigned char *addr = (char *)&msg[1];
+	int err = -1;
 
-		if (is_valid_ether_addr(addr))
-			err = igb_set_vf_mac(adapter, vf, addr);
-
-		return err;
+	if (is_valid_ether_addr(addr))
+		err = igb_set_vf_mac(adapter, vf, addr);
 
+	return err;
 }
 
 static void igb_rcv_ack_from_vf(struct igb_adapter *adapter, u32 vf)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
 	u32 msg = E1000_VT_MSGTYPE_NACK;
 
 	/* if device isn't clear to send it shouldn't be reading either */
-	if (!adapter->vf_data[vf].clear_to_send)
+	if (!(vf_data->flags & IGB_VF_FLAG_CTS) &&
+	    time_after(jiffies, vf_data->last_nack + (2 * HZ))) {
 		igb_write_mbx(hw, &msg, 1, vf);
-}
-
-
-static void igb_msg_task(struct igb_adapter *adapter)
-{
-	struct e1000_hw *hw = &adapter->hw;
-	u32 vf;
-
-	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
-		/* process any reset requests */
-		if (!igb_check_for_rst(hw, vf)) {
-			adapter->vf_data[vf].clear_to_send = false;
-			igb_vf_reset_event(adapter, vf);
-		}
-
-		/* process any messages pending */
-		if (!igb_check_for_msg(hw, vf))
-			igb_rcv_msg_from_vf(adapter, vf);
-
-		/* process any acks */
-		if (!igb_check_for_ack(hw, vf))
-			igb_rcv_ack_from_vf(adapter, vf);
-
+		vf_data->last_nack = jiffies;
 	}
 }
 
-static int igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
+static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 {
-	u32 mbx_size = E1000_VFMAILBOX_SIZE;
-	u32 msgbuf[mbx_size];
+	struct pci_dev *pdev = adapter->pdev;
+	u32 msgbuf[E1000_VFMAILBOX_SIZE];
 	struct e1000_hw *hw = &adapter->hw;
+	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
 	s32 retval;
 
-	retval = igb_read_mbx(hw, msgbuf, mbx_size, vf);
+	retval = igb_read_mbx(hw, msgbuf, E1000_VFMAILBOX_SIZE, vf);
 
 	if (retval)
-		dev_err(&adapter->pdev->dev,
-		        "Error receiving message from VF\n");
+		dev_err(&pdev->dev, "Error receiving message from VF\n");
 
 	/* this is a message we already processed, do nothing */
 	if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK))
-		return retval;
+		return;
 
 	/*
 	 * until the vf completes a reset it should not be
@@ -4395,14 +4382,16 @@ static int igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 
 	if (msgbuf[0] == E1000_VF_RESET) {
 		igb_vf_reset_msg(adapter, vf);
-
-		return retval;
+		return;
 	}
 
-	if (!adapter->vf_data[vf].clear_to_send) {
-		msgbuf[0] |= E1000_VT_MSGTYPE_NACK;
-		igb_write_mbx(hw, msgbuf, 1, vf);
-		return retval;
+	if (!(vf_data->flags & IGB_VF_FLAG_CTS)) {
+		msgbuf[0] = E1000_VT_MSGTYPE_NACK;
+		if (time_after(jiffies, vf_data->last_nack + (2 * HZ))) {
+			igb_write_mbx(hw, msgbuf, 1, vf);
+			vf_data->last_nack = jiffies;
+		}
+		return;
 	}
 
 	switch ((msgbuf[0] & 0xFFFF)) {
@@ -4433,8 +4422,26 @@ static int igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 	msgbuf[0] |= E1000_VT_MSGTYPE_CTS;
 
 	igb_write_mbx(hw, msgbuf, 1, vf);
+}
 
-	return retval;
+static void igb_msg_task(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 vf;
+
+	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
+		/* process any reset requests */
+		if (!igb_check_for_rst(hw, vf))
+			igb_vf_reset_event(adapter, vf);
+
+		/* process any messages pending */
+		if (!igb_check_for_msg(hw, vf))
+			igb_rcv_msg_from_vf(adapter, vf);
+
+		/* process any acks */
+		if (!igb_check_for_ack(hw, vf))
+			igb_rcv_ack_from_vf(adapter, vf);
+	}
 }
 
 /**

[net-next-2.6 PATCH 06/23] igb: rework use of VMOLR in regards to PF and VFs

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch updates the use of the VMOLR to include enabling multicast
promiscous for the VFs should they attempt to send over 30 multicast
addresses or if they use the new message type to enable multicast
promiscuous.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/e1000_mbx.h |   10 +-
 drivers/net/igb/igb.h       |    2 
 drivers/net/igb/igb_main.c  |  173 +++++++++++++++++++++++++++++--------------
 3 files changed, 125 insertions(+), 60 deletions(-)

diff --git a/drivers/net/igb/e1000_mbx.h b/drivers/net/igb/e1000_mbx.h
index ebc02ea..bb112fb 100644
--- a/drivers/net/igb/e1000_mbx.h
+++ b/drivers/net/igb/e1000_mbx.h
@@ -58,10 +58,12 @@
 #define E1000_VT_MSGINFO_MASK     (0xFF << E1000_VT_MSGINFO_SHIFT)
 
 #define E1000_VF_RESET            0x01 /* VF requests reset */
-#define E1000_VF_SET_MAC_ADDR     0x02 /* VF requests PF to set MAC addr */
-#define E1000_VF_SET_MULTICAST    0x03 /* VF requests PF to set MC addr */
-#define E1000_VF_SET_VLAN         0x04 /* VF requests PF to set VLAN */
-#define E1000_VF_SET_LPE          0x05 /* VF requests PF to set VMOLR.LPE */
+#define E1000_VF_SET_MAC_ADDR     0x02 /* VF requests to set MAC addr */
+#define E1000_VF_SET_MULTICAST    0x03 /* VF requests to set MC addr */
+#define E1000_VF_SET_VLAN         0x04 /* VF requests to set VLAN */
+#define E1000_VF_SET_LPE          0x05 /* VF requests to set VMOLR.LPE */
+#define E1000_VF_SET_PROMISC      0x06 /*VF requests to clear VMOLR.ROPE/MPME*/
+#define E1000_VF_SET_PROMISC_MULTICAST    (0x02 << E1000_VT_MSGINFO_SHIFT)
 
 #define E1000_PF_CONTROL_MSG      0x0100 /* PF control message */
 
diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index 7801d3f..c27dc1a 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -78,6 +78,8 @@ struct vf_data_storage {
 };
 
 #define IGB_VF_FLAG_CTS            0x00000001 /* VF is clear to send data */
+#define IGB_VF_FLAG_UNI_PROMISC    0x00000002 /* VF has unicast promisc */
+#define IGB_VF_FLAG_MULTI_PROMISC  0x00000004 /* VF has multicast promisc */
 
 /* RX descriptor control thresholds.
  * PTHRESH - MAC will consider prefetch if it has fewer than this number of
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index a9e8ba2..3ab2978 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -129,38 +129,6 @@ static void igb_vmm_control(struct igb_adapter *);
 static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *);
 static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 
-static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
-{
-	u32 reg_data;
-
-	reg_data = rd32(E1000_VMOLR(vfn));
-	reg_data |= E1000_VMOLR_BAM |	 /* Accept broadcast */
-	            E1000_VMOLR_ROMPE |  /* Accept packets matched in MTA */
-	            E1000_VMOLR_AUPE |   /* Accept untagged packets */
-	            E1000_VMOLR_STRVLAN; /* Strip vlan tags */
-	wr32(E1000_VMOLR(vfn), reg_data);
-}
-
-static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
-                                 int vfn)
-{
-	struct e1000_hw *hw = &adapter->hw;
-	u32 vmolr;
-
-	/* if it isn't the PF check to see if VFs are enabled and
-	 * increase the size to support vlan tags */
-	if (vfn < adapter->vfs_allocated_count &&
-	    adapter->vf_data[vfn].vlans_enabled)
-		size += VLAN_TAG_SIZE;
-
-	vmolr = rd32(E1000_VMOLR(vfn));
-	vmolr &= ~E1000_VMOLR_RLPML_MASK;
-	vmolr |= size | E1000_VMOLR_LPE;
-	wr32(E1000_VMOLR(vfn), vmolr);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int igb_suspend(struct pci_dev *, pm_message_t);
 static int igb_resume(struct pci_dev *);
@@ -1115,8 +1083,6 @@ int igb_up(struct igb_adapter *adapter)
 	if (adapter->msix_entries)
 		igb_configure_msix(adapter);
 
-	igb_set_vmolr(hw, adapter->vfs_allocated_count);
-
 	/* Clear any pending interrupts. */
 	rd32(E1000_ICR);
 	igb_irq_enable(adapter);
@@ -1892,8 +1858,6 @@ static int igb_open(struct net_device *netdev)
 	 * clean_rx handler before we do so.  */
 	igb_configure(adapter);
 
-	igb_set_vmolr(hw, adapter->vfs_allocated_count);
-
 	err = igb_request_irq(adapter);
 	if (err)
 		goto err_req_irq;
@@ -2331,22 +2295,33 @@ void igb_setup_rctl(struct igb_adapter *adapter)
 	 * if an un-trusted VF does not provide descriptors to hardware.
 	 */
 	if (adapter->vfs_allocated_count) {
-		u32 vmolr;
-
 		/* set all queue drop enable bits */
 		wr32(E1000_QDE, ALL_QUEUES);
-
-		vmolr = rd32(E1000_VMOLR(adapter->vfs_allocated_count));
-		if (rctl & E1000_RCTL_LPE)
-			vmolr |= E1000_VMOLR_LPE;
-		if (adapter->num_rx_queues > 1)
-			vmolr |= E1000_VMOLR_RSSE;
-		wr32(E1000_VMOLR(adapter->vfs_allocated_count), vmolr);
 	}
 
 	wr32(E1000_RCTL, rctl);
 }
 
+static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
+                                   int vfn)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 vmolr;
+
+	/* if it isn't the PF check to see if VFs are enabled and
+	 * increase the size to support vlan tags */
+	if (vfn < adapter->vfs_allocated_count &&
+	    adapter->vf_data[vfn].vlans_enabled)
+		size += VLAN_TAG_SIZE;
+
+	vmolr = rd32(E1000_VMOLR(vfn));
+	vmolr &= ~E1000_VMOLR_RLPML_MASK;
+	vmolr |= size | E1000_VMOLR_LPE;
+	wr32(E1000_VMOLR(vfn), vmolr);
+
+	return 0;
+}
+
 /**
  * igb_rlpml_set - set maximum receive packet size
  * @adapter: board private structure
@@ -2366,12 +2341,43 @@ static void igb_rlpml_set(struct igb_adapter *adapter)
 	 * size and set the VMOLR RLPML to the size we need */
 	if (pf_id) {
 		igb_set_vf_rlpml(adapter, max_frame_size, pf_id);
-		max_frame_size = MAX_STD_JUMBO_FRAME_SIZE + VLAN_TAG_SIZE;
+		max_frame_size = MAX_JUMBO_FRAME_SIZE;
 	}
 
 	wr32(E1000_RLPML, max_frame_size);
 }
 
+static inline void igb_set_vmolr(struct igb_adapter *adapter, int vfn)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 vmolr;
+
+	/*
+	 * This register exists only on 82576 and newer so if we are older then
+	 * we should exit and do nothing
+	 */
+	if (hw->mac.type < e1000_82576)
+		return;
+
+	vmolr = rd32(E1000_VMOLR(vfn));
+	vmolr |= E1000_VMOLR_AUPE |        /* Accept untagged packets */
+	         E1000_VMOLR_STRVLAN;      /* Strip vlan tags */
+
+	/* clear all bits that might not be set */
+	vmolr &= ~(E1000_VMOLR_BAM | E1000_VMOLR_RSSE);
+
+	if (adapter->num_rx_queues > 1 && vfn == adapter->vfs_allocated_count)
+		vmolr |= E1000_VMOLR_RSSE; /* enable RSS */
+	/*
+	 * for VMDq only allow the VFs and pool 0 to accept broadcast and
+	 * multicast packets
+	 */
+	if (vfn <= adapter->vfs_allocated_count)
+		vmolr |= E1000_VMOLR_BAM;	   /* Accept broadcast */
+
+	wr32(E1000_VMOLR(vfn), vmolr);
+}
+
 /**
  * igb_configure_rx_ring - Configure a receive ring after Reset
  * @adapter: board private structure
@@ -2425,6 +2431,9 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 
 	wr32(E1000_SRRCTL(reg_idx), srrctl);
 
+	/* set filtering for VMDQ pools */
+	igb_set_vmolr(adapter, reg_idx & 0x7);
+
 	/* enable receive descriptor fetching */
 	rxdctl = rd32(E1000_RXDCTL(reg_idx));
 	rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
@@ -4101,6 +4110,45 @@ static void igb_ping_all_vfs(struct igb_adapter *adapter)
 	}
 }
 
+static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 vmolr = rd32(E1000_VMOLR(vf));
+	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
+
+	vf_data->flags |= ~(IGB_VF_FLAG_UNI_PROMISC |
+	                    IGB_VF_FLAG_MULTI_PROMISC);
+	vmolr &= ~(E1000_VMOLR_ROPE | E1000_VMOLR_ROMPE | E1000_VMOLR_MPME);
+
+	if (*msgbuf & E1000_VF_SET_PROMISC_MULTICAST) {
+		vmolr |= E1000_VMOLR_MPME;
+		*msgbuf &= ~E1000_VF_SET_PROMISC_MULTICAST;
+	} else {
+		/*
+		 * if we have hashes and we are clearing a multicast promisc
+		 * flag we need to write the hashes to the MTA as this step
+		 * was previously skipped
+		 */
+		if (vf_data->num_vf_mc_hashes > 30) {
+			vmolr |= E1000_VMOLR_MPME;
+		} else if (vf_data->num_vf_mc_hashes) {
+			int j;
+			vmolr |= E1000_VMOLR_ROMPE;
+			for (j = 0; j < vf_data->num_vf_mc_hashes; j++)
+				igb_mta_set(hw, vf_data->vf_mc_hashes[j]);
+		}
+	}
+
+	wr32(E1000_VMOLR(vf), vmolr);
+
+	/* there are flags left unprocessed, likely not supported */
+	if (*msgbuf & E1000_VT_MSGINFO_MASK)
+		return -EINVAL;
+
+	return 0;
+
+}
+
 static int igb_set_vf_multicasts(struct igb_adapter *adapter,
 				  u32 *msgbuf, u32 vf)
 {
@@ -4109,18 +4157,17 @@ static int igb_set_vf_multicasts(struct igb_adapter *adapter,
 	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
 	int i;
 
-	/* only up to 30 hash values supported */
-	if (n > 30)
-		n = 30;
-
-	/* salt away the number of multi cast addresses assigned
+	/* salt away the number of multicast addresses assigned
 	 * to this VF for later use to restore when the PF multi cast
 	 * list changes
 	 */
 	vf_data->num_vf_mc_hashes = n;
 
-	/* VFs are limited to using the MTA hash table for their multicast
-	 * addresses */
+	/* only up to 30 hash values supported */
+	if (n > 30)
+		n = 30;
+
+	/* store the hashes for later use */
 	for (i = 0; i < n; i++)
 		vf_data->vf_mc_hashes[i] = hash_list[i];
 
@@ -4137,9 +4184,20 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter)
 	int i, j;
 
 	for (i = 0; i < adapter->vfs_allocated_count; i++) {
+		u32 vmolr = rd32(E1000_VMOLR(i));
+		vmolr &= ~(E1000_VMOLR_ROMPE | E1000_VMOLR_MPME);
+
 		vf_data = &adapter->vf_data[i];
-		for (j = 0; j < vf_data->num_vf_mc_hashes; j++)
-			igb_mta_set(hw, vf_data->vf_mc_hashes[j]);
+
+		if ((vf_data->num_vf_mc_hashes > 30) ||
+		    (vf_data->flags & IGB_VF_FLAG_MULTI_PROMISC)) {
+			vmolr |= E1000_VMOLR_MPME;
+		} else if (vf_data->num_vf_mc_hashes) {
+			vmolr |= E1000_VMOLR_ROMPE;
+			for (j = 0; j < vf_data->num_vf_mc_hashes; j++)
+				igb_mta_set(hw, vf_data->vf_mc_hashes[j]);
+		}
+		wr32(E1000_VMOLR(i), vmolr);
 	}
 }
 
@@ -4282,7 +4340,7 @@ static inline void igb_vf_reset(struct igb_adapter *adapter, u32 vf)
 	adapter->vf_data[vf].last_nack = jiffies;
 
 	/* reset offloads to defaults */
-	igb_set_vmolr(&adapter->hw, vf);
+	igb_set_vmolr(adapter, vf);
 
 	/* reset vlans for device */
 	igb_clear_vf_vfta(adapter, vf);
@@ -4398,6 +4456,9 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 	case E1000_VF_SET_MAC_ADDR:
 		retval = igb_set_vf_mac_addr(adapter, msgbuf, vf);
 		break;
+	case E1000_VF_SET_PROMISC:
+		retval = igb_set_vf_promisc(adapter, msgbuf, vf);
+		break;
 	case E1000_VF_SET_MULTICAST:
 		retval = igb_set_vf_multicasts(adapter, msgbuf, vf);
 		break;

[net-next-2.6 PATCH 07/23] igb: rework handling of the vfta and vlvf registers in relation to mng_vlan

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch corrects some errors in how vlans are being handled when vfs
start interacting with the management vlans.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   94 +++++++++++++++-----------------------------
 1 files changed, 32 insertions(+), 62 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 3ab2978..9170927 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -963,24 +963,23 @@ static void igb_irq_enable(struct igb_adapter *adapter)
 
 static void igb_update_mng_vlan(struct igb_adapter *adapter)
 {
-	struct net_device *netdev = adapter->netdev;
+	struct e1000_hw *hw = &adapter->hw;
 	u16 vid = adapter->hw.mng_cookie.vlan_id;
 	u16 old_vid = adapter->mng_vlan_id;
-	if (adapter->vlgrp) {
-		if (!vlan_group_get_device(adapter->vlgrp, vid)) {
-			if (adapter->hw.mng_cookie.status &
-				E1000_MNG_DHCP_COOKIE_STATUS_VLAN) {
-				igb_vlan_rx_add_vid(netdev, vid);
-				adapter->mng_vlan_id = vid;
-			} else
-				adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
 
-			if ((old_vid != (u16)IGB_MNG_VLAN_NONE) &&
-					(vid != old_vid) &&
-			    !vlan_group_get_device(adapter->vlgrp, old_vid))
-				igb_vlan_rx_kill_vid(netdev, old_vid);
-		} else
-			adapter->mng_vlan_id = vid;
+	if (hw->mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) {
+		/* add VID to filter table */
+		igb_vfta_set(hw, vid, true);
+		adapter->mng_vlan_id = vid;
+	} else {
+		adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
+	}
+
+	if ((old_vid != (u16)IGB_MNG_VLAN_NONE) &&
+	    (vid != old_vid) &&
+	    !vlan_group_get_device(adapter->vlgrp, old_vid)) {
+		/* remove VID from filter table */
+		igb_vfta_set(hw, old_vid, false);
 	}
 }
 
@@ -1847,11 +1846,6 @@ static int igb_open(struct net_device *netdev)
 
 	/* e1000_power_up_phy(adapter); */
 
-	adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
-	if ((adapter->hw.mng_cookie.status &
-	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN))
-		igb_update_mng_vlan(adapter);
-
 	/* before we allocate an interrupt, we must be ready to handle it.
 	 * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
 	 * as soon as we call pci_request_irq, so we have to setup our
@@ -1924,14 +1918,6 @@ static int igb_close(struct net_device *netdev)
 	igb_free_all_tx_resources(adapter);
 	igb_free_all_rx_resources(adapter);
 
-	/* kill manageability vlan ID if supported, but not if a vlan with
-	 * the same ID is registered on the host OS (let 8021q kill it) */
-	if ((adapter->hw.mng_cookie.status &
-			  E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
-	     !(adapter->vlgrp &&
-	       vlan_group_get_device(adapter->vlgrp, adapter->mng_vlan_id)))
-		igb_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id);
-
 	return 0;
 }
 
@@ -4235,7 +4221,11 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 reg, i;
 
-	/* It is an error to call this function when VFs are not enabled */
+	/* The vlvf table only exists on 82576 hardware and newer */
+	if (hw->mac.type < e1000_82576)
+		return -1;
+
+	/* we only need to do this if VMDq is enabled */
 	if (!adapter->vfs_allocated_count)
 		return -1;
 
@@ -4265,16 +4255,12 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
 
 			/* if !enabled we need to set this up in vfta */
 			if (!(reg & E1000_VLVF_VLANID_ENABLE)) {
-				/* add VID to filter table, if bit already set
-				 * PF must have added it outside of table */
-				if (igb_vfta_set(hw, vid, true))
-					reg |= 1 << (E1000_VLVF_POOLSEL_SHIFT +
-						adapter->vfs_allocated_count);
+				/* add VID to filter table */
+				igb_vfta_set(hw, vid, true);
 				reg |= E1000_VLVF_VLANID_ENABLE;
 			}
 			reg &= ~E1000_VLVF_VLANID_MASK;
 			reg |= vid;
-
 			wr32(E1000_VLVF(i), reg);
 
 			/* do not modify RLPML for PF devices */
@@ -4290,8 +4276,8 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
 				reg |= size;
 				wr32(E1000_VMOLR(vf), reg);
 			}
-			adapter->vf_data[vf].vlans_enabled++;
 
+			adapter->vf_data[vf].vlans_enabled++;
 			return 0;
 		}
 	} else {
@@ -5393,21 +5379,15 @@ static void igb_vlan_rx_register(struct net_device *netdev,
 		ctrl |= E1000_CTRL_VME;
 		wr32(E1000_CTRL, ctrl);
 
-		/* enable VLAN receive filtering */
+		/* Disable CFI check */
 		rctl = rd32(E1000_RCTL);
 		rctl &= ~E1000_RCTL_CFIEN;
 		wr32(E1000_RCTL, rctl);
-		igb_update_mng_vlan(adapter);
 	} else {
 		/* disable VLAN tag insert/strip */
 		ctrl = rd32(E1000_CTRL);
 		ctrl &= ~E1000_CTRL_VME;
 		wr32(E1000_CTRL, ctrl);
-
-		if (adapter->mng_vlan_id != (u16)IGB_MNG_VLAN_NONE) {
-			igb_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id);
-			adapter->mng_vlan_id = IGB_MNG_VLAN_NONE;
-		}
 	}
 
 	igb_rlpml_set(adapter);
@@ -5422,16 +5402,11 @@ static void igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	struct e1000_hw *hw = &adapter->hw;
 	int pf_id = adapter->vfs_allocated_count;
 
-	if ((hw->mng_cookie.status &
-	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
-	    (vid == adapter->mng_vlan_id))
-		return;
-
-	/* add vid to vlvf if sr-iov is enabled,
-	 * if that fails add directly to filter table */
-	if (igb_vlvf_set(adapter, vid, true, pf_id))
-		igb_vfta_set(hw, vid, true);
+	/* attempt to add filter to vlvf array */
+	igb_vlvf_set(adapter, vid, true, pf_id);
 
+	/* add the filter since PF can receive vlans w/o entry in vlvf */
+	igb_vfta_set(hw, vid, true);
 }
 
 static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
@@ -5439,6 +5414,7 @@ static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	int pf_id = adapter->vfs_allocated_count;
+	s32 err;
 
 	igb_irq_disable(adapter);
 	vlan_group_set_device(adapter->vlgrp, vid, NULL);
@@ -5446,17 +5422,11 @@ static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	if (!test_bit(__IGB_DOWN, &adapter->state))
 		igb_irq_enable(adapter);
 
-	if ((adapter->hw.mng_cookie.status &
-	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
-	    (vid == adapter->mng_vlan_id)) {
-		/* release control to f/w */
-		igb_release_hw_control(adapter);
-		return;
-	}
+	/* remove vlan from VLVF table array */
+	err = igb_vlvf_set(adapter, vid, false, pf_id);
 
-	/* remove vid from vlvf if sr-iov is enabled,
-	 * if not in vlvf remove from vfta */
-	if (igb_vlvf_set(adapter, vid, false, pf_id))
+	/* if vid was not present in VLVF just remove it from table */
+	if (err)
 		igb_vfta_set(hw, vid, false);
 }
 

[net-next-2.6 PATCH 08/23] igb: move vf init into a seperate function

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch moves VF initialization into a seperate function to help improve
the readability of igb_probe.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   98 +++++++++++++++++++++++++-------------------
 1 files changed, 56 insertions(+), 42 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 9170927..54e8f02 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1409,46 +1409,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	if (err)
 		goto err_sw_init;
 
-#ifdef CONFIG_PCI_IOV
-	/* since iov functionality isn't critical to base device function we
-	 * can accept failure.  If it fails we don't allow iov to be enabled */
-	if (hw->mac.type == e1000_82576) {
-		/* 82576 supports a maximum of 7 VFs in addition to the PF */
-		unsigned int num_vfs = (max_vfs > 7) ? 7 : max_vfs;
-		int i;
-		unsigned char mac_addr[ETH_ALEN];
-
-		if (num_vfs) {
-			adapter->vf_data = kcalloc(num_vfs,
-						sizeof(struct vf_data_storage),
-						GFP_KERNEL);
-			if (!adapter->vf_data) {
-				dev_err(&pdev->dev,
-				        "Could not allocate VF private data - "
-					"IOV enable failed\n");
-			} else {
-				err = pci_enable_sriov(pdev, num_vfs);
-				if (!err) {
-					adapter->vfs_allocated_count = num_vfs;
-					dev_info(&pdev->dev,
-					         "%d vfs allocated\n",
-					         num_vfs);
-					for (i = 0;
-					     i < adapter->vfs_allocated_count;
-					     i++) {
-						random_ether_addr(mac_addr);
-						igb_set_vf_mac(adapter, i,
-						               mac_addr);
-					}
-				} else {
-					kfree(adapter->vf_data);
-					adapter->vf_data = NULL;
-				}
-			}
-		}
-	}
-
-#endif
 	/* setup the private structure */
 	err = igb_sw_init(adapter);
 	if (err)
@@ -1772,6 +1732,54 @@ static void __devexit igb_remove(struct pci_dev *pdev)
 }
 
 /**
+ * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space
+ * @adapter: board private structure to initialize
+ *
+ * This function initializes the vf specific data storage and then attempts to
+ * allocate the VFs.  The reason for ordering it this way is because it is much
+ * mor expensive time wise to disable SR-IOV than it is to allocate and free
+ * the memory for the VFs.
+ **/
+static void __devinit igb_probe_vfs(struct igb_adapter * adapter)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dev *pdev = adapter->pdev;
+
+	if (adapter->vfs_allocated_count > 7)
+		adapter->vfs_allocated_count = 7;
+
+	if (adapter->vfs_allocated_count) {
+		adapter->vf_data = kcalloc(adapter->vfs_allocated_count,
+		                           sizeof(struct vf_data_storage),
+		                           GFP_KERNEL);
+		/* if allocation failed then we do not support SR-IOV */
+		if (!adapter->vf_data) {
+			adapter->vfs_allocated_count = 0;
+			dev_err(&pdev->dev, "Unable to allocate memory for VF "
+			        "Data Storage\n");
+		}
+	}
+
+	if (pci_enable_sriov(pdev, adapter->vfs_allocated_count)) {
+		kfree(adapter->vf_data);
+		adapter->vf_data = NULL;
+#endif /* CONFIG_PCI_IOV */
+		adapter->vfs_allocated_count = 0;
+#ifdef CONFIG_PCI_IOV
+	} else {
+		unsigned char mac_addr[ETH_ALEN];
+		int i;
+		dev_info(&pdev->dev, "%d vfs allocated\n",
+		         adapter->vfs_allocated_count);
+		for (i = 0; i < adapter->vfs_allocated_count; i++) {
+			random_ether_addr(mac_addr);
+			igb_set_vf_mac(adapter, i, mac_addr);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+}
+
+/**
  * igb_sw_init - Initialize general software structures (struct igb_adapter)
  * @adapter: board private structure to initialize
  *
@@ -1795,13 +1803,19 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
-	/* This call may decrease the number of queues depending on
-	 * interrupt mode. */
+#ifdef CONFIG_PCI_IOV
+	if (hw->mac.type == e1000_82576)
+		adapter->vfs_allocated_count = max_vfs;
+
+#endif /* CONFIG_PCI_IOV */
+	/* This call may decrease the number of queues */
 	if (igb_init_interrupt_scheme(adapter)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}
 
+	igb_probe_vfs(adapter);
+
 	/* Explicitly disable IRQ since the NIC can be in any state. */
 	igb_irq_disable(adapter);
 

[net-next-2.6 PATCH 09/23] igb: only process global stats in igb_update_stats

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch moves the update of adapter->net_stats.rx/tx values out of the
interrupt routine and into igb_update_stats by just adding together the
tx/rx byte/packet counts for the rings.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   61 +++++++++++++++++++++-----------------------
 1 files changed, 29 insertions(+), 32 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 54e8f02..62b6876 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3769,7 +3769,10 @@ void igb_update_stats(struct igb_adapter *adapter)
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
+	u32 rnbc;
 	u16 phy_tmp;
+	int i;
+	u64 bytes, packets;
 
 #define PHY_IDLE_ERROR_COUNT_MASK 0x00FF
 
@@ -3782,6 +3785,29 @@ void igb_update_stats(struct igb_adapter *adapter)
 	if (pci_channel_offline(pdev))
 		return;
 
+	bytes = 0;
+	packets = 0;
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		u32 rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0x0FFF;
+		adapter->rx_ring[i].rx_stats.drops += rqdpc_tmp;
+		netdev->stats.rx_fifo_errors += rqdpc_tmp;
+		bytes += adapter->rx_ring[i].rx_stats.bytes;
+		packets += adapter->rx_ring[i].rx_stats.packets;
+	}
+
+	netdev->stats.rx_bytes = bytes;
+	netdev->stats.rx_packets = packets;
+
+	bytes = 0;
+	packets = 0;
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		bytes += adapter->tx_ring[i].tx_stats.bytes;
+		packets += adapter->tx_ring[i].tx_stats.packets;
+	}
+	netdev->stats.tx_bytes = bytes;
+	netdev->stats.tx_packets = packets;
+
+	/* read stats registers */
 	adapter->stats.crcerrs += rd32(E1000_CRCERRS);
 	adapter->stats.gprc += rd32(E1000_GPRC);
 	adapter->stats.gorc += rd32(E1000_GORCL);
@@ -3814,7 +3840,9 @@ void igb_update_stats(struct igb_adapter *adapter)
 	adapter->stats.gptc += rd32(E1000_GPTC);
 	adapter->stats.gotc += rd32(E1000_GOTCL);
 	rd32(E1000_GOTCH); /* clear GOTCL */
-	adapter->stats.rnbc += rd32(E1000_RNBC);
+	rnbc = rd32(E1000_RNBC);
+	adapter->stats.rnbc += rnbc;
+	netdev->stats.rx_fifo_errors += rnbc;
 	adapter->stats.ruc += rd32(E1000_RUC);
 	adapter->stats.rfc += rd32(E1000_RFC);
 	adapter->stats.rjc += rd32(E1000_RJC);
@@ -3861,33 +3889,6 @@ void igb_update_stats(struct igb_adapter *adapter)
 
 	/* Rx Errors */
 
-	if (hw->mac.type != e1000_82575) {
-		u32 rqdpc_tmp;
-		u64 rqdpc_total = 0;
-		int i;
-		/* Read out drops stats per RX queue.  Notice RQDPC (Receive
-		 * Queue Drop Packet Count) stats only gets incremented, if
-		 * the DROP_EN but it set (in the SRRCTL register for that
-		 * queue).  If DROP_EN bit is NOT set, then the some what
-		 * equivalent count is stored in RNBC (not per queue basis).
-		 * Also note the drop count is due to lack of available
-		 * descriptors.
-		 */
-		for (i = 0; i < adapter->num_rx_queues; i++) {
-			rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0xFFF;
-			adapter->rx_ring[i].rx_stats.drops += rqdpc_tmp;
-			rqdpc_total += adapter->rx_ring[i].rx_stats.drops;
-		}
-		netdev->stats.rx_fifo_errors = rqdpc_total;
-	}
-
-	/* Note RNBC (Receive No Buffers Count) is an not an exact
-	 * drop count as the hardware FIFO might save the day.  Thats
-	 * one of the reason for saving it in rx_fifo_errors, as its
-	 * potentially not a true drop.
-	 */
-	netdev->stats.rx_fifo_errors += adapter->stats.rnbc;
-
 	/* RLEC on some newer hardware can be incorrect so build
 	 * our own version based on RUC and ROC */
 	netdev->stats.rx_errors = adapter->stats.rxerrc +
@@ -4818,8 +4819,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 	tx_ring->total_packets += total_packets;
 	tx_ring->tx_stats.bytes += total_bytes;
 	tx_ring->tx_stats.packets += total_packets;
-	netdev->stats.tx_bytes += total_bytes;
-	netdev->stats.tx_packets += total_packets;
 	return (count < tx_ring->count);
 }
 
@@ -5043,8 +5042,6 @@ next_desc:
 	rx_ring->total_bytes += total_bytes;
 	rx_ring->rx_stats.packets += total_packets;
 	rx_ring->rx_stats.bytes += total_bytes;
-	netdev->stats.rx_bytes += total_bytes;
-	netdev->stats.rx_packets += total_packets;
 	return cleaned;
 }
 

[net-next-2.6 PATCH 10/23] igb: move global_quad_port_a from global into local static define

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This change moves global_quad_port_a into igb_probe as a static define
since it doesn't actually need to be global.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |    8 ++------
 1 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 62b6876..7f32211 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -179,8 +179,6 @@ static struct pci_driver igb_driver = {
 	.err_handler = &igb_err_handler
 };
 
-static int global_quad_port_a; /* global quad port a indication */
-
 MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver");
 MODULE_LICENSE("GPL");
@@ -252,12 +250,9 @@ static int __init igb_init_module(void)
 
 	printk(KERN_INFO "%s\n", igb_copyright);
 
-	global_quad_port_a = 0;
-
 #ifdef CONFIG_IGB_DCA
 	dca_register_notify(&dca_notifier);
 #endif
-
 	ret = pci_register_driver(&igb_driver);
 	return ret;
 }
@@ -1318,10 +1313,11 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	struct net_device *netdev;
 	struct igb_adapter *adapter;
 	struct e1000_hw *hw;
+	u16 eeprom_data = 0;
+	static int global_quad_port_a; /* global quad port a indication */
 	const struct e1000_info *ei = igb_info_tbl[ent->driver_data];
 	unsigned long mmio_start, mmio_len;
 	int err, pci_using_dac;
-	u16 eeprom_data = 0;
 	u16 eeprom_apme_mask = IGB_EEPROM_APME;
 	u32 part_num;
 

[net-next-2.6 PATCH 11/23] igb: make tx hang check multiqueue, check eop descriptor

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This change makes the tx hang check run over all tx queues instead of just
queue 0.  Also have hang display info on EOP descriptor instead of the
descriptor at the start of the chain.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   10 ++++++----
 1 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 7f32211..f75f90f 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3002,6 +3002,10 @@ link_up:
 		}
 	}
 
+	/* Force detection of hung controller every watchdog period */
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		adapter->tx_ring[i].detect_tx_hung = true;
+
 	/* Cause software interrupt to ensure rx ring is cleaned */
 	if (adapter->msix_entries) {
 		u32 eics = 0;
@@ -3014,9 +3018,6 @@ link_up:
 		wr32(E1000_ICS, E1000_ICS_RXDMT0);
 	}
 
-	/* Force detection of hung controller every watchdog period */
-	tx_ring->detect_tx_hung = true;
-
 	/* Reset the timer */
 	if (!test_bit(__IGB_DOWN, &adapter->state))
 		mod_timer(&adapter->watchdog_timer,
@@ -3667,6 +3668,7 @@ static void igb_tx_timeout(struct net_device *netdev)
 
 	/* Do the reset outside of interrupt context */
 	adapter->tx_timeout_count++;
+
 	schedule_work(&adapter->reset_task);
 	wr32(E1000_EICS,
 	     (adapter->eims_enable_mask & ~adapter->eims_other));
@@ -4804,7 +4806,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 				readl(tx_ring->tail),
 				tx_ring->next_to_use,
 				tx_ring->next_to_clean,
-				tx_ring->buffer_info[i].time_stamp,
+				tx_ring->buffer_info[eop].time_stamp,
 				eop,
 				jiffies,
 				eop_desc->wb.status);

[net-next-2.6 PATCH 12/23] igb: cleanup code related to ring resource allocation and free

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch cleans up some of the ring alloc and free code to better handle
exceptions such as attempting to free resources on an already freed ring.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   29 +++++++++++++++++------------
 1 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index f75f90f..e67ff0e 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1952,7 +1952,8 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
 	tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 
-	tx_ring->desc = pci_alloc_consistent(pdev, tx_ring->size,
+	tx_ring->desc = pci_alloc_consistent(pdev,
+	                                     tx_ring->size,
 					     &tx_ring->dma);
 
 	if (!tx_ring->desc)
@@ -1978,13 +1979,13 @@ err:
  **/
 static int igb_setup_all_tx_resources(struct igb_adapter *adapter)
 {
+	struct pci_dev *pdev = adapter->pdev;
 	int i, err = 0;
-	int r_idx;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		err = igb_setup_tx_resources(&adapter->tx_ring[i]);
 		if (err) {
-			dev_err(&adapter->pdev->dev,
+			dev_err(&pdev->dev,
 				"Allocation for Tx Queue %u failed\n", i);
 			for (i--; i >= 0; i--)
 				igb_free_tx_resources(&adapter->tx_ring[i]);
@@ -1993,7 +1994,7 @@ static int igb_setup_all_tx_resources(struct igb_adapter *adapter)
 	}
 
 	for (i = 0; i < IGB_MAX_TX_QUEUES; i++) {
-		r_idx = i % adapter->num_tx_queues;
+		int r_idx = i % adapter->num_tx_queues;
 		adapter->multi_tx_table[i] = &adapter->tx_ring[r_idx];
 	}
 	return err;
@@ -2116,6 +2117,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 
 err:
 	vfree(rx_ring->buffer_info);
+	rx_ring->buffer_info = NULL;
 	dev_err(&pdev->dev, "Unable to allocate memory for "
 		"the receive descriptor ring\n");
 	return -ENOMEM;
@@ -2130,12 +2132,13 @@ err:
  **/
 static int igb_setup_all_rx_resources(struct igb_adapter *adapter)
 {
+	struct pci_dev *pdev = adapter->pdev;
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		err = igb_setup_rx_resources(&adapter->rx_ring[i]);
 		if (err) {
-			dev_err(&adapter->pdev->dev,
+			dev_err(&pdev->dev,
 				"Allocation for Rx Queue %u failed\n", i);
 			for (i--; i >= 0; i--)
 				igb_free_rx_resources(&adapter->rx_ring[i]);
@@ -2476,6 +2479,10 @@ void igb_free_tx_resources(struct igb_ring *tx_ring)
 	vfree(tx_ring->buffer_info);
 	tx_ring->buffer_info = NULL;
 
+	/* if not set, then don't free */
+	if (!tx_ring->desc)
+		return;
+
 	pci_free_consistent(tx_ring->pdev, tx_ring->size,
 	                    tx_ring->desc, tx_ring->dma);
 
@@ -2534,14 +2541,10 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 	memset(tx_ring->buffer_info, 0, size);
 
 	/* Zero out the descriptor ring */
-
 	memset(tx_ring->desc, 0, tx_ring->size);
 
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
-
-	writel(0, tx_ring->head);
-	writel(0, tx_ring->tail);
 }
 
 /**
@@ -2569,6 +2572,10 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
 	vfree(rx_ring->buffer_info);
 	rx_ring->buffer_info = NULL;
 
+	/* if not set, then don't free */
+	if (!rx_ring->desc)
+		return;
+
 	pci_free_consistent(rx_ring->pdev, rx_ring->size,
 	                    rx_ring->desc, rx_ring->dma);
 
@@ -2601,6 +2608,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 
 	if (!rx_ring->buffer_info)
 		return;
+
 	/* Free all the Rx ring sk_buffs */
 	for (i = 0; i < rx_ring->count; i++) {
 		buffer_info = &rx_ring->buffer_info[i];
@@ -2638,9 +2646,6 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
-
-	writel(0, rx_ring->head);
-	writel(0, rx_ring->tail);
 }
 
 /**

[net-next-2.6 PATCH 13/23] igb: change queue ordering for 82576 based adapters

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch changes the queue ordering for 82576 adapters so that if VFs are
enabled the queues will first be allocated out of the PF pool.  Any
remaining queues will be allocated out of other VMDq pools.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   25 +++++++++++++------------
 1 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index e67ff0e..52c4302 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -285,7 +285,7 @@ module_exit(igb_exit_module);
  **/
 static void igb_cache_ring_register(struct igb_adapter *adapter)
 {
-	int i;
+	int i = 0, j = 0;
 	u32 rbase_offset = adapter->vfs_allocated_count;
 
 	switch (adapter->hw.mac.type) {
@@ -295,19 +295,20 @@ static void igb_cache_ring_register(struct igb_adapter *adapter)
 		 * In order to avoid collision we start at the first free queue
 		 * and continue consuming queues in the same sequence
 		 */
-		for (i = 0; i < adapter->num_rx_queues; i++)
-			adapter->rx_ring[i].reg_idx = rbase_offset +
-			                              Q_IDX_82576(i);
-		for (i = 0; i < adapter->num_tx_queues; i++)
-			adapter->tx_ring[i].reg_idx = rbase_offset +
-			                              Q_IDX_82576(i);
-		break;
+		if (adapter->vfs_allocated_count) {
+			for (; i < adapter->num_rx_queues; i++)
+				adapter->rx_ring[i].reg_idx = rbase_offset +
+				                              Q_IDX_82576(i);
+			for (; j < adapter->num_tx_queues; j++)
+				adapter->tx_ring[j].reg_idx = rbase_offset +
+				                              Q_IDX_82576(j);
+		}
 	case e1000_82575:
 	default:
-		for (i = 0; i < adapter->num_rx_queues; i++)
-			adapter->rx_ring[i].reg_idx = i;
-		for (i = 0; i < adapter->num_tx_queues; i++)
-			adapter->tx_ring[i].reg_idx = i;
+		for (; i < adapter->num_rx_queues; i++)
+			adapter->rx_ring[i].reg_idx = rbase_offset + i;
+		for (; j < adapter->num_tx_queues; j++)
+			adapter->tx_ring[j].reg_idx = rbase_offset + j;
 		break;
 	}
 }

[net-next-2.6 PATCH 14/23] igb: cleanup interrupt enablement in regards to msix_other

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch changes a few things so that instead of firing a link status
interrupt directly the get_link_status bit is set and the watchdog is
scheduled.  In addition the mailbox bit is now only enabled if VFs are
enabled.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   31 +++++++++++++++++++++++--------
 1 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 52c4302..5b0f939 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -919,6 +919,11 @@ static void igb_irq_disable(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 
+	/*
+	 * we need to be careful when disabling interrupts.  The VFs are also
+	 * mapped into these registers and so clearing the bits can cause
+	 * issues on the VF drivers so we only need to clear what we set
+	 */
 	if (adapter->msix_entries) {
 		u32 regval = rd32(E1000_EIAM);
 		wr32(E1000_EIAM, regval & ~adapter->eims_enable_mask);
@@ -942,15 +947,17 @@ static void igb_irq_enable(struct igb_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 
 	if (adapter->msix_entries) {
+		u32 ims = E1000_IMS_LSC | E1000_IMS_DOUTSYNC;
 		u32 regval = rd32(E1000_EIAC);
 		wr32(E1000_EIAC, regval | adapter->eims_enable_mask);
 		regval = rd32(E1000_EIAM);
 		wr32(E1000_EIAM, regval | adapter->eims_enable_mask);
 		wr32(E1000_EIMS, adapter->eims_enable_mask);
-		if (adapter->vfs_allocated_count)
+		if (adapter->vfs_allocated_count) {
 			wr32(E1000_MBVFIMR, 0xFF);
-		wr32(E1000_IMS, (E1000_IMS_LSC | E1000_IMS_VMMB |
-		                 E1000_IMS_DOUTSYNC));
+			ims |= E1000_IMS_VMMB;
+		}
+		wr32(E1000_IMS, ims);
 	} else {
 		wr32(E1000_IMS, IMS_ENABLE_MASK);
 		wr32(E1000_IAM, IMS_ENABLE_MASK);
@@ -1091,8 +1098,10 @@ int igb_up(struct igb_adapter *adapter)
 
 	netif_tx_start_all_queues(adapter->netdev);
 
-	/* Fire a link change interrupt to start the watchdog. */
-	wr32(E1000_ICS, E1000_ICS_LSC);
+	/* start the watchdog. */
+	hw->mac.get_link_status = 1;
+	schedule_work(&adapter->watchdog_task);
+
 	return 0;
 }
 
@@ -1889,8 +1898,9 @@ static int igb_open(struct net_device *netdev)
 
 	netif_tx_start_all_queues(netdev);
 
-	/* Fire a link status change interrupt to start the watchdog. */
-	wr32(E1000_ICS, E1000_ICS_LSC);
+	/* start the watchdog. */
+	hw->mac.get_link_status = 1;
+	schedule_work(&adapter->watchdog_task);
 
 	return 0;
 
@@ -3952,7 +3962,12 @@ static irqreturn_t igb_msix_other(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
-	wr32(E1000_IMS, E1000_IMS_LSC | E1000_IMS_DOUTSYNC | E1000_IMS_VMMB);
+	if (adapter->vfs_allocated_count)
+		wr32(E1000_IMS, E1000_IMS_LSC |
+				E1000_IMS_VMMB |
+				E1000_IMS_DOUTSYNC);
+	else
+		wr32(E1000_IMS, E1000_IMS_LSC | E1000_IMS_DOUTSYNC);
 	wr32(E1000_EIMS, adapter->eims_other);
 
 	return IRQ_HANDLED;

[net-next-2.6 PATCH 15/23] igb: Remove invalid stats counters

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

There are several counters being used like they are static when in fact
they are clear on read.  In order to prevent the values from being
incorrect I am removing the defunct counters.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb.h      |    6 ------
 drivers/net/igb/igb_main.c |   18 +-----------------
 2 files changed, 1 insertions(+), 23 deletions(-)

diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index c27dc1a..b9fcfd3 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -269,10 +269,6 @@ struct igb_adapter {
 	/* TX */
 	struct igb_ring *tx_ring;      /* One per active queue */
 	unsigned long tx_queue_len;
-	u32 gotc;
-	u64 gotc_old;
-	u64 tpt_old;
-	u64 colc_old;
 	u32 tx_timeout_count;
 
 	/* RX */
@@ -280,8 +276,6 @@ struct igb_adapter {
 	int num_tx_queues;
 	int num_rx_queues;
 
-	u32 gorc;
-	u64 gorc_old;
 	u32 max_frame_size;
 	u32 min_frame_size;
 
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 5b0f939..cb1acca 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -2925,9 +2925,6 @@ static void igb_watchdog_task(struct work_struct *work)
 	int i;
 
 	link = igb_has_link(adapter);
-	if ((netif_carrier_ok(netdev)) && link)
-		goto link_up;
-
 	if (link) {
 		if (!netif_carrier_ok(netdev)) {
 			u32 ctrl;
@@ -2990,20 +2987,8 @@ static void igb_watchdog_task(struct work_struct *work)
 		}
 	}
 
-link_up:
 	igb_update_stats(adapter);
-
-	hw->mac.tx_packet_delta = adapter->stats.tpt - adapter->tpt_old;
-	adapter->tpt_old = adapter->stats.tpt;
-	hw->mac.collision_delta = adapter->stats.colc - adapter->colc_old;
-	adapter->colc_old = adapter->stats.colc;
-
-	adapter->gorc = adapter->stats.gorc - adapter->gorc_old;
-	adapter->gorc_old = adapter->stats.gorc;
-	adapter->gotc = adapter->stats.gotc - adapter->gotc_old;
-	adapter->gotc_old = adapter->stats.gotc;
-
-	igb_update_adaptive(&adapter->hw);
+	igb_update_adaptive(hw);
 
 	if (!netif_carrier_ok(netdev)) {
 		if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) {
@@ -3875,7 +3860,6 @@ void igb_update_stats(struct igb_adapter *adapter)
 	adapter->stats.bptc += rd32(E1000_BPTC);
 
 	/* used for adaptive IFS */
-
 	hw->mac.tx_packet_delta = rd32(E1000_TPT);
 	adapter->stats.tpt += hw->mac.tx_packet_delta;
 	hw->mac.collision_delta = rd32(E1000_COLC);

[net-next-2.6 PATCH 16/23] igb: cleanup igb.h header whitespace and some structure formatting

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch changes the layout of the ring and adapter structs to fill a few
holes in the structure.  It also cleans up some whitespace and formatting
issues.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb.h |   12 ++++++------
 1 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h
index b9fcfd3..3298f5a 100644
--- a/drivers/net/igb/igb.h
+++ b/drivers/net/igb/igb.h
@@ -185,16 +185,15 @@ struct igb_ring {
 	dma_addr_t dma;                /* phys address of the ring */
 	void *desc;                    /* descriptor ring memory */
 	unsigned int size;             /* length of desc. ring in bytes */
-	unsigned int count;            /* number of desc. in the ring */
+	u16 count;                     /* number of desc. in the ring */
 	u16 next_to_use;
 	u16 next_to_clean;
+	u8 queue_index;
+	u8 reg_idx;
 	void __iomem *head;
 	void __iomem *tail;
 	struct igb_buffer *buffer_info; /* array of buffer info structs */
 
-	u8 queue_index;
-	u8 reg_idx;
-
 	unsigned int total_bytes;
 	unsigned int total_packets;
 
@@ -249,6 +248,7 @@ struct igb_adapter {
 	u32 en_mng_pt;
 	u16 link_speed;
 	u16 link_duplex;
+
 	unsigned int total_tx_bytes;
 	unsigned int total_tx_packets;
 	unsigned int total_rx_bytes;
@@ -311,8 +311,8 @@ struct igb_adapter {
 	u32 eeprom_wol;
 
 	struct igb_ring *multi_tx_table[IGB_ABS_MAX_TX_QUEUES];
-	unsigned int tx_ring_count;
-	unsigned int rx_ring_count;
+	u16 tx_ring_count;
+	u16 rx_ring_count;
 	unsigned int vfs_allocated_count;
 	struct vf_data_storage *vf_data;
 };

[net-next-2.6 PATCH 17/23] igb: cleanup igb xmit frame path

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch cleans up the xmit frame path for igb to better handle xmit
frame errors and avoid null pointer exceptions.  It also cleans up some
whitespace issues found in the xmit frame path.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   30 +++++++++++++++---------------
 1 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index cb1acca..8f8b7cc 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3245,9 +3245,9 @@ set_itr_now:
 #define IGB_TX_FLAGS_VLAN		0x00000002
 #define IGB_TX_FLAGS_TSO		0x00000004
 #define IGB_TX_FLAGS_IPV4		0x00000008
-#define IGB_TX_FLAGS_TSTAMP             0x00000010
-#define IGB_TX_FLAGS_VLAN_MASK	0xffff0000
-#define IGB_TX_FLAGS_VLAN_SHIFT	16
+#define IGB_TX_FLAGS_TSTAMP		0x00000010
+#define IGB_TX_FLAGS_VLAN_MASK		0xffff0000
+#define IGB_TX_FLAGS_VLAN_SHIFT		        16
 
 static inline int igb_tso_adv(struct igb_ring *tx_ring,
 			      struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
@@ -3346,6 +3346,7 @@ static inline bool igb_tx_csum_adv(struct igb_ring *tx_ring,
 
 		if (tx_flags & IGB_TX_FLAGS_VLAN)
 			info |= (tx_flags & IGB_TX_FLAGS_VLAN_MASK);
+
 		info |= (skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT);
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			info |= skb_network_header_len(skb);
@@ -3462,17 +3463,17 @@ static inline int igb_tx_map_adv(struct igb_ring *tx_ring, struct sk_buff *skb,
 	tx_ring->buffer_info[i].skb = skb;
 	tx_ring->buffer_info[first].next_to_watch = i;
 
-	return count + 1;
+	return ++count;
 }
 
 static inline void igb_tx_queue_adv(struct igb_ring *tx_ring,
 				    int tx_flags, int count, u32 paylen,
 				    u8 hdr_len)
 {
-	union e1000_adv_tx_desc *tx_desc = NULL;
+	union e1000_adv_tx_desc *tx_desc;
 	struct igb_buffer *buffer_info;
 	u32 olinfo_status = 0, cmd_type_len;
-	unsigned int i;
+	unsigned int i = tx_ring->next_to_use;
 
 	cmd_type_len = (E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_IFCS |
 			E1000_ADVTXD_DCMD_DEXT);
@@ -3505,18 +3506,18 @@ static inline void igb_tx_queue_adv(struct igb_ring *tx_ring,
 
 	olinfo_status |= ((paylen - hdr_len) << E1000_ADVTXD_PAYLEN_SHIFT);
 
-	i = tx_ring->next_to_use;
-	while (count--) {
+	do {
 		buffer_info = &tx_ring->buffer_info[i];
 		tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
 		tx_desc->read.buffer_addr = cpu_to_le64(buffer_info->dma);
 		tx_desc->read.cmd_type_len =
 			cpu_to_le32(cmd_type_len | buffer_info->length);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+		count--;
 		i++;
 		if (i == tx_ring->count)
 			i = 0;
-	}
+	} while (count > 0);
 
 	tx_desc->read.cmd_type_len |= cpu_to_le32(IGB_ADVTXD_DCMD);
 	/* Force memory writes to complete before letting h/w
@@ -3568,8 +3569,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 	unsigned int first;
 	unsigned int tx_flags = 0;
 	u8 hdr_len = 0;
-	int count = 0;
-	int tso = 0;
+	int tso = 0, count;
 	union skb_shared_tx *shtx = skb_tx(skb);
 
 	/* need: 1 descriptor per page,
@@ -3587,7 +3587,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
 	}
 
-	if (adapter->vlgrp && vlan_tx_tag_present(skb)) {
+	if (vlan_tx_tag_present(skb) && adapter->vlgrp) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
 		tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
 	}
@@ -3598,6 +3598,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 	first = tx_ring->next_to_use;
 	if (skb_is_gso(skb)) {
 		tso = igb_tso_adv(tx_ring, skb, tx_flags, &hdr_len);
+
 		if (tso < 0) {
 			dev_kfree_skb_any(skb);
 			return NETDEV_TX_OK;
@@ -3611,12 +3612,11 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb,
 		tx_flags |= IGB_TX_FLAGS_CSUM;
 
 	/*
-	 * count reflects descriptors mapped, if 0 then mapping error
+	 * count reflects descriptors mapped, if 0 or less then mapping error
 	 * has occured and we need to rewind the descriptor queue
 	 */
 	count = igb_tx_map_adv(tx_ring, skb, first);
-
-	if (!count) {
+	if (count <= 0) {
 		dev_kfree_skb_any(skb);
 		tx_ring->buffer_info[first].time_stamp = 0;
 		tx_ring->next_to_use = first;

[net-next-2.6 PATCH 18/23] igb: cleanup clean_rx_irq_adv and alloc_rx_buffers_adv

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch cleans up some whitespace issues in clean_rx_irq_adv.  It also
adds NUMA aware page allocation and dma error handling to
alloc_rx_buffers_adv.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   24 +++++++++++++++++++-----
 1 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 8f8b7cc..d3e8316 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -4952,6 +4952,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
 		i++;
 		if (i == rx_ring->count)
 			i = 0;
+
 		next_rxd = E1000_RX_DESC_ADV(*rx_ring, i);
 		prefetch(next_rxd);
 		next_buffer = &rx_ring->buffer_info[i];
@@ -4989,7 +4990,6 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
 
 			skb->len += length;
 			skb->data_len += length;
-
 			skb->truesize += length;
 		}
 
@@ -5071,7 +5071,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 
 		if ((bufsz < IGB_RXBUFFER_1024) && !buffer_info->page_dma) {
 			if (!buffer_info->page) {
-				buffer_info->page = alloc_page(GFP_ATOMIC);
+				buffer_info->page = netdev_alloc_page(netdev);
 				if (!buffer_info->page) {
 					rx_ring->rx_stats.alloc_failed++;
 					goto no_buffers;
@@ -5085,9 +5085,16 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 					     buffer_info->page_offset,
 					     PAGE_SIZE / 2,
 					     PCI_DMA_FROMDEVICE);
+			if (pci_dma_mapping_error(rx_ring->pdev,
+			                          buffer_info->page_dma)) {
+				buffer_info->page_dma = 0;
+				rx_ring->rx_stats.alloc_failed++;
+				goto no_buffers;
+			}
 		}
 
-		if (!buffer_info->skb) {
+		skb = buffer_info->skb;
+		if (!skb) {
 			skb = netdev_alloc_skb_ip_align(netdev, bufsz);
 			if (!skb) {
 				rx_ring->rx_stats.alloc_failed++;
@@ -5095,10 +5102,18 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 			}
 
 			buffer_info->skb = skb;
+		}
+		if (!buffer_info->dma) {
 			buffer_info->dma = pci_map_single(rx_ring->pdev,
 			                                  skb->data,
 							  bufsz,
 							  PCI_DMA_FROMDEVICE);
+			if (pci_dma_mapping_error(rx_ring->pdev,
+			                          buffer_info->dma)) {
+				buffer_info->dma = 0;
+				rx_ring->rx_stats.alloc_failed++;
+				goto no_buffers;
+			}
 		}
 		/* Refresh the desc even if buffer_addrs didn't change because
 		 * each write-back erases this info. */
@@ -5107,8 +5122,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 			     cpu_to_le64(buffer_info->page_dma);
 			rx_desc->read.hdr_addr = cpu_to_le64(buffer_info->dma);
 		} else {
-			rx_desc->read.pkt_addr =
-			     cpu_to_le64(buffer_info->dma);
+			rx_desc->read.pkt_addr = cpu_to_le64(buffer_info->dma);
 			rx_desc->read.hdr_addr = 0;
 		}
 

[net-next-2.6 PATCH 19/23] igb: replace unecessary &adapter->hw with just hw where applicable

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch just cleans up some unecessary references to the adapter->hw
member when it has already been placed in a local variable named hw.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   26 ++++++++++++--------------
 1 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index d3e8316..b2c0c97 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1107,8 +1107,8 @@ int igb_up(struct igb_adapter *adapter)
 
 void igb_down(struct igb_adapter *adapter)
 {
-	struct e1000_hw *hw = &adapter->hw;
 	struct net_device *netdev = adapter->netdev;
+	struct e1000_hw *hw = &adapter->hw;
 	u32 tctl, rctl;
 	int i;
 
@@ -1271,10 +1271,10 @@ void igb_reset(struct igb_adapter *adapter)
 	}
 
 	/* Allow time for pending master requests to run */
-	adapter->hw.mac.ops.reset_hw(&adapter->hw);
+	hw->mac.ops.reset_hw(hw);
 	wr32(E1000_WUC, 0);
 
-	if (adapter->hw.mac.ops.init_hw(&adapter->hw))
+	if (hw->mac.ops.init_hw(hw))
 		dev_err(&adapter->pdev->dev, "Hardware Error\n");
 
 	igb_update_mng_vlan(adapter);
@@ -1282,8 +1282,8 @@ void igb_reset(struct igb_adapter *adapter)
 	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
 	wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);
 
-	igb_reset_adaptive(&adapter->hw);
-	igb_get_phy_info(&adapter->hw);
+	igb_reset_adaptive(hw);
+	igb_get_phy_info(hw);
 }
 
 static const struct net_device_ops igb_netdev_ops = {
@@ -1404,8 +1404,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	hw->subsystem_vendor_id = pdev->subsystem_vendor;
 	hw->subsystem_device_id = pdev->subsystem_device;
 
-	/* setup the private structure */
-	hw->back = adapter;
 	/* Copy the default MAC, PHY and NVM function pointers */
 	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
 	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));
@@ -1460,7 +1458,7 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	if (adapter->hw.mac.type == e1000_82576)
 		netdev->features |= NETIF_F_SCTP_CSUM;
 
-	adapter->en_mng_pt = igb_enable_mng_pass_thru(&adapter->hw);
+	adapter->en_mng_pt = igb_enable_mng_pass_thru(hw);
 
 	/* before reading the NVM, reset the controller to put the device in a
 	 * known good starting state */
@@ -1705,8 +1703,8 @@ static void __devexit igb_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
-	if (!igb_check_reset_block(&adapter->hw))
-		igb_reset_phy(&adapter->hw);
+	if (!igb_check_reset_block(hw))
+		igb_reset_phy(hw);
 
 	igb_clear_interrupt_scheme(adapter);
 
@@ -2928,9 +2926,9 @@ static void igb_watchdog_task(struct work_struct *work)
 	if (link) {
 		if (!netif_carrier_ok(netdev)) {
 			u32 ctrl;
-			hw->mac.ops.get_speed_and_duplex(&adapter->hw,
-						   &adapter->link_speed,
-						   &adapter->link_duplex);
+			hw->mac.ops.get_speed_and_duplex(hw,
+			                                 &adapter->link_speed,
+			                                 &adapter->link_duplex);
 
 			ctrl = rd32(E1000_CTRL);
 			/* Links status message must follow this format */
@@ -5552,7 +5550,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake)
 		wr32(E1000_CTRL, ctrl);
 
 		/* Allow time for pending master requests to run */
-		igb_disable_pcie_master(&adapter->hw);
+		igb_disable_pcie_master(hw);
 
 		wr32(E1000_WUC, E1000_WUC_PME_EN);
 		wr32(E1000_WUFC, wufc);

[net-next-2.6 PATCH 20/23] igb: add pci_dev in few spots to clean up use of dev_err/info/warn

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch relpaces several references to adapter->pdev->dev with just
pdev->dev.  This allows for cleanup of several multiline dev_err/info
calls.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   24 ++++++++++++------------
 1 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index b2c0c97..264ff00 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1173,6 +1173,7 @@ void igb_reinit_locked(struct igb_adapter *adapter)
 
 void igb_reset(struct igb_adapter *adapter)
 {
+	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
 	struct e1000_mac_info *mac = &hw->mac;
 	struct e1000_fc_info *fc = &hw->fc;
@@ -1275,7 +1276,7 @@ void igb_reset(struct igb_adapter *adapter)
 	wr32(E1000_WUC, 0);
 
 	if (hw->mac.ops.init_hw(hw))
-		dev_err(&adapter->pdev->dev, "Hardware Error\n");
+		dev_err(&pdev->dev, "Hardware Error\n");
 
 	igb_update_mng_vlan(adapter);
 
@@ -3704,17 +3705,18 @@ static struct net_device_stats *igb_get_stats(struct net_device *netdev)
 static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct pci_dev *pdev = adapter->pdev;
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 	u32 rx_buffer_len, i;
 
 	if ((max_frame < ETH_ZLEN + ETH_FCS_LEN) ||
 	    (max_frame > MAX_JUMBO_FRAME_SIZE)) {
-		dev_err(&adapter->pdev->dev, "Invalid MTU setting\n");
+		dev_err(&pdev->dev, "Invalid MTU setting\n");
 		return -EINVAL;
 	}
 
 	if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) {
-		dev_err(&adapter->pdev->dev, "MTU > 9216 not supported.\n");
+		dev_err(&pdev->dev, "MTU > 9216 not supported.\n");
 		return -EINVAL;
 	}
 
@@ -3739,7 +3741,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev))
 		igb_down(adapter);
 
-	dev_info(&adapter->pdev->dev, "changing MTU from %d to %d\n",
+	dev_info(&pdev->dev, "changing MTU from %d to %d\n",
 		 netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 
@@ -4053,6 +4055,7 @@ static int __igb_notify_dca(struct device *dev, void *data)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned long event = *(unsigned long *)data;
 
@@ -4061,12 +4064,9 @@ static int __igb_notify_dca(struct device *dev, void *data)
 		/* if already enabled, don't do it again */
 		if (adapter->flags & IGB_FLAG_DCA_ENABLED)
 			break;
-		/* Always use CB2 mode, difference is masked
-		 * in the CB driver. */
-		wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_CB2);
 		if (dca_add_requester(dev) == 0) {
 			adapter->flags |= IGB_FLAG_DCA_ENABLED;
-			dev_info(&adapter->pdev->dev, "DCA enabled\n");
+			dev_info(&pdev->dev, "DCA enabled\n");
 			igb_setup_dca(adapter);
 			break;
 		}
@@ -4076,7 +4076,7 @@ static int __igb_notify_dca(struct device *dev, void *data)
 			/* without this a class_device is left
 			 * hanging around in the sysfs model */
 			dca_remove_requester(dev);
-			dev_info(&adapter->pdev->dev, "DCA disabled\n");
+			dev_info(&pdev->dev, "DCA disabled\n");
 			adapter->flags &= ~IGB_FLAG_DCA_ENABLED;
 			wr32(E1000_DCA_CTRL, E1000_DCA_CTRL_DCA_MODE_DISABLE);
 		}
@@ -4471,7 +4471,7 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf)
 		retval = igb_set_vf_vlan(adapter, msgbuf, vf);
 		break;
 	default:
-		dev_err(&adapter->pdev->dev, "Unhandled Msg %08x\n", msgbuf[0]);
+		dev_err(&pdev->dev, "Unhandled Msg %08x\n", msgbuf[0]);
 		retval = -1;
 		break;
 	}
@@ -5472,6 +5472,7 @@ static void igb_restore_vlan(struct igb_adapter *adapter)
 
 int igb_set_spd_dplx(struct igb_adapter *adapter, u16 spddplx)
 {
+	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_mac_info *mac = &adapter->hw.mac;
 
 	mac->autoneg = 0;
@@ -5495,8 +5496,7 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u16 spddplx)
 		break;
 	case SPEED_1000 + DUPLEX_HALF: /* not supported */
 	default:
-		dev_err(&adapter->pdev->dev,
-			"Unsupported Speed/Duplex configuration\n");
+		dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n");
 		return -EINVAL;
 	}
 	return 0;

[net-next-2.6 PATCH 21/23] igb: limit minimum mtu to 68 to keep ip bound to interface

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

Limit the minimum mtu to 68 in order to prevent ip from being unbound from
the interface.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 264ff00..846e64f 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3709,8 +3709,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 	u32 rx_buffer_len, i;
 
-	if ((max_frame < ETH_ZLEN + ETH_FCS_LEN) ||
-	    (max_frame > MAX_JUMBO_FRAME_SIZE)) {
+	if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) {
 		dev_err(&pdev->dev, "Invalid MTU setting\n");
 		return -EINVAL;
 	}

[net-next-2.6 PATCH 22/23] igb: open up SCTP checksum offloads to all MACs 82576 and newer

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

Going forward the plan is to have the MACs support SCTP checksum offloads
so change the check from == to >=.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 846e64f..1a6c074 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1456,7 +1456,7 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	if (pci_using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;
 
-	if (adapter->hw.mac.type == e1000_82576)
+	if (hw->mac.type >= e1000_82576)
 		netdev->features |= NETIF_F_SCTP_CSUM;
 
 	adapter->en_mng_pt = igb_enable_mng_pass_thru(hw);

[net-next-2.6 PATCH 23/23] igb: cleanup whitespace issues in igb_main.c

[Jeff Kirsher]

From: Alexander Duyck <alexander.h.duyck@intel.com>

This patch goes through and cleans up whitespace issues in igb_main.c
to help improve readability.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   41 +++++++++++++++++++----------------------
 1 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 1a6c074..b044c98 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -1006,7 +1006,6 @@ static void igb_release_hw_control(struct igb_adapter *adapter)
 			ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD);
 }
 
-
 /**
  * igb_get_hw_control - get control of the h/w from f/w
  * @adapter: address of board private structure
@@ -1067,7 +1066,6 @@ static void igb_configure(struct igb_adapter *adapter)
  * igb_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
  **/
-
 int igb_up(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
@@ -1288,7 +1286,7 @@ void igb_reset(struct igb_adapter *adapter)
 }
 
 static const struct net_device_ops igb_netdev_ops = {
-	.ndo_open 		= igb_open,
+	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
 	.ndo_start_xmit		= igb_xmit_frame_adv,
 	.ndo_get_stats		= igb_get_stats,
@@ -1444,7 +1442,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_IPV6_CSUM;
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
-
 	netdev->features |= NETIF_F_GRO;
 
 	netdev->vlan_features |= NETIF_F_TSO;
@@ -1569,7 +1566,6 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	}
 
 #endif
-
 	switch (hw->mac.type) {
 	case e1000_82576:
 		/*
@@ -1624,8 +1620,8 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 	/* print bus type/speed/width info */
 	dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n",
 		 netdev->name,
-		 ((hw->bus.speed == e1000_bus_speed_2500)
-		  ? "2.5Gb/s" : "unknown"),
+		 ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" :
+		                                            "unknown"),
 		 ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" :
 		  (hw->bus.width == e1000_bus_width_pcie_x2) ? "Width x2" :
 		  (hw->bus.width == e1000_bus_width_pcie_x1) ? "Width x1" :
@@ -1658,8 +1654,8 @@ err_sw_init:
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
-	pci_release_selected_regions(pdev, pci_select_bars(pdev,
-	                             IORESOURCE_MEM));
+	pci_release_selected_regions(pdev,
+	                             pci_select_bars(pdev, IORESOURCE_MEM));
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -1723,11 +1719,12 @@ static void __devexit igb_remove(struct pci_dev *pdev)
 		dev_info(&pdev->dev, "IOV Disabled\n");
 	}
 #endif
+
 	iounmap(hw->hw_addr);
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
-	pci_release_selected_regions(pdev, pci_select_bars(pdev,
-	                             IORESOURCE_MEM));
+	pci_release_selected_regions(pdev,
+	                             pci_select_bars(pdev, IORESOURCE_MEM));
 
 	free_netdev(netdev);
 
@@ -2288,9 +2285,7 @@ void igb_setup_rctl(struct igb_adapter *adapter)
 	 */
 	rctl |= E1000_RCTL_SECRC;
 
-	/*
-	 * disable store bad packets and clear size bits.
-	 */
+	/* disable store bad packets and clear size bits. */
 	rctl &= ~(E1000_RCTL_SBP | E1000_RCTL_SZ_256);
 
 	/* enable LPE to prevent packets larger than max_frame_size */
@@ -2916,7 +2911,8 @@ static void igb_watchdog(unsigned long data)
 static void igb_watchdog_task(struct work_struct *work)
 {
 	struct igb_adapter *adapter = container_of(work,
-					struct igb_adapter, watchdog_task);
+	                                           struct igb_adapter,
+                                                   watchdog_task);
 	struct e1000_hw *hw = &adapter->hw;
 	struct net_device *netdev = adapter->netdev;
 	struct igb_ring *tx_ring = adapter->tx_ring;
@@ -2935,14 +2931,14 @@ static void igb_watchdog_task(struct work_struct *work)
 			/* Links status message must follow this format */
 			printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s, "
 				 "Flow Control: %s\n",
-			         netdev->name,
-				 adapter->link_speed,
-				 adapter->link_duplex == FULL_DUPLEX ?
+			       netdev->name,
+			       adapter->link_speed,
+			       adapter->link_duplex == FULL_DUPLEX ?
 				 "Full Duplex" : "Half Duplex",
-				 ((ctrl & E1000_CTRL_TFCE) && (ctrl &
-				 E1000_CTRL_RFCE)) ? "RX/TX" : ((ctrl &
-				 E1000_CTRL_RFCE) ? "RX" : ((ctrl &
-				 E1000_CTRL_TFCE) ? "TX" : "None")));
+			       ((ctrl & E1000_CTRL_TFCE) &&
+			        (ctrl & E1000_CTRL_RFCE)) ? "RX/TX" :
+			       ((ctrl & E1000_CTRL_RFCE) ?  "RX" :
+			       ((ctrl & E1000_CTRL_TFCE) ?  "TX" : "None")));
 
 			/* tweak tx_queue_len according to speed/duplex and
 			 * adjust the timeout factor */
@@ -3724,6 +3720,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 
 	/* igb_down has a dependency on max_frame_size */
 	adapter->max_frame_size = max_frame;
+
 	/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
 	 * means we reserve 2 more, this pushes us to allocate from the next
 	 * larger slab size.

Re: [net-next-2.6 PATCH 01/23] igb: add support for seperate tx-usecs setting in ethtool

[David Miller]

All applied to net-next-2.6, but then I had to add the following
patch to kill a warning:

igb: Fix warnings in igb_set_ringparam()

drivers/net/igb/igb_ethtool.c: In function ‘igb_set_ringparam’:
drivers/net/igb/igb_ethtool.c:744: warning: comparison of distinct pointer types lacks a cast
drivers/net/igb/igb_ethtool.c:748: warning: comparison of distinct pointer types lacks a cast

Casts were to u16 on the constant, but the type of new_{r,t}x_count is
u32.  Cast to u32 instead.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/igb/igb_ethtool.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c
index d24b902..90b89a8 100644
--- a/drivers/net/igb/igb_ethtool.c
+++ b/drivers/net/igb/igb_ethtool.c
@@ -741,11 +741,11 @@ static int igb_set_ringparam(struct net_device *netdev,
 		return -EINVAL;
 
 	new_rx_count = min(ring->rx_pending, (u32)IGB_MAX_RXD);
-	new_rx_count = max(new_rx_count, (u16)IGB_MIN_RXD);
+	new_rx_count = max(new_rx_count, (u32)IGB_MIN_RXD);
 	new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE);
 
 	new_tx_count = min(ring->tx_pending, (u32)IGB_MAX_TXD);
-	new_tx_count = max(new_tx_count, (u16)IGB_MIN_TXD);
+	new_tx_count = max(new_tx_count, (u32)IGB_MIN_TXD);
 	new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE);
 
 	if ((new_tx_count == adapter->tx_ring_count) &&
-- 
1.6.5.1

Re: [net-next-2.6 PATCH 01/23] igb: add support for seperate tx-usecs setting in ethtool

[Stephen Hemminger]

On Wed, 28 Oct 2009 03:39:22 -0700 (PDT)
David Miller <davem@davemloft.net> wrote:

> +	new_rx_count = max(new_rx_count, (u32)IGB_MIN_RXD);

new_rx_count = max_t(u32, new_rx_count, IGB_MIN_RXD)
  is slightly cleaner (hides cast)

--