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

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2015-02-09

This series contains updates to i40e and i40evf only.

Rickard Strandqvist removes an unused function for i40e.

John Linville reorders a piece of code so that y_budget does not get used
by the FCoE code before it gets initialized.

Mitch adds a delay after VF reset with a minimum of 10ms to allow the
hardware internal FIFOs to flush.  Bumps up the ARQ descriptors, since
we can easily overrun the PF's admin receive queue.  Added locking around
the VF reset code, since during VF deallocation, we cannot depend on
simply masking the interrupt since this does not lock out the service task,
which can still call the reset routine.  Fix a potential multi-minute
delay on driver unload, VF disable or system shutdown.  When the module
is being unloaded, waiting for the PF to politely handle all of our admin
queue requests might take forever with a lot of VFs enabled, so just
stop everything and request a VF reset.  Also stops the watchdog during
shutdown to prevent a log full of admin queue errors and the occasional
hang when the system is shut down.

Anjali forces Tx descriptor writebacks on ITR by kicking off the SWINT
interrupt since we noticed that there are non-cache-aligned Tx
descriptors waiting in the ring while interrupts are disabled under NAPI.
Enables loopback for the FCoE VSI, so that VSIs can directly talk to each
other without going out on the wire.

Matthew fixes an LED blink issue by making sure to clear the GPIO blink
field, instead of OR'ing against zero if the field is already '1'.

Greg cleans up a function header comment.

Vasu helps biosdevname user tool to differentiate dev_port for PCoE netdev
and PF netdev, by setting different dev_port value for FCoE netdev.

Carolyn adds a call to u64_stats_init to the receive setup in order to
avoid lockdep errors with seqcount on newer kernels.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e.h

@@ -87,8 +87,8 @@
 #define I40E_MINIMUM_FCOE             1 /* minimum number of QPs for FCoE */
 #endif /* I40E_FCOE */
 #define I40E_MAX_AQ_BUF_SIZE          4096
-#define I40E_AQ_LEN                   128
-#define I40E_AQ_WORK_LIMIT            16
+#define I40E_AQ_LEN                   256
+#define I40E_AQ_WORK_LIMIT            32
 #define I40E_MAX_USER_PRIORITY        8
 #define I40E_DEFAULT_MSG_ENABLE       4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT   10
@@ -148,6 +148,7 @@ enum i40e_state_t {
 	__I40E_FD_FLUSH_REQUESTED,
 	__I40E_RESET_FAILED,
 	__I40E_PORT_TX_SUSPENDED,
+	__I40E_VF_DISABLE,
 };
 
 enum i40e_interrupt_policy {

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -1142,8 +1142,10 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
 		if (mode == I40E_LINK_ACTIVITY)
 			blink = false;
 
-		gpio_val |= (blink ? 1 : 0) <<
-			    I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT;
+		if (blink)
+			gpio_val |= (1 << I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT);
+		else
+			gpio_val &= ~(1 << I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT);
 
 		wr32(hw, I40E_GLGEN_GPIO_CTL(i), gpio_val);
 		break;

drivers/net/ethernet/intel/i40e/i40e_fcoe.c

@@ -38,15 +38,6 @@
 #include "i40e.h"
 #include "i40e_fcoe.h"
 
-/**
- * i40e_rx_is_fip - returns true if the rx packet type is FIP
- * @ptype: the packet type field from rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fip(u16 ptype)
-{
-	return ptype == I40E_RX_PTYPE_L2_FIP_PAY2;
-}
-
 /**
  * i40e_rx_is_fcoe - returns true if the rx packet type is FCoE
  * @ptype: the packet type field from rx descriptor write-back
@@ -404,6 +395,7 @@ int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt)
 					    I40E_AQ_VSI_PROP_INGRESS_UP_VALID |
 					    I40E_AQ_VSI_PROP_EGRESS_UP_VALID));
 
+	info->switch_id = cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
 	enabled_tc = i40e_get_fcoe_tc_map(pf);
 	i40e_vsi_setup_queue_map(vsi, ctxt, enabled_tc, true);
 
@@ -1511,6 +1503,12 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi)
 	strlcpy(netdev->name, "fcoe%d", IFNAMSIZ-1);
 	netdev->mtu = FCOE_MTU;
 	SET_NETDEV_DEV(netdev, &pf->pdev->dev);
+	/* set different dev_port value 1 for FCoE netdev than the default
+	 * zero dev_port value for PF netdev, this helps biosdevname user
+	 * tool to differentiate them correctly while both attached to the
+	 * same PCI function.
+	 */
+	netdev->dev_port = 1;
 	i40e_add_filter(vsi, hw->mac.san_addr, 0, false, false);
 	i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0, false, false);
 	i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0, false, false);

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -2940,7 +2940,7 @@ void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 /**
  * i40e_irq_dynamic_disable - Disable default interrupt generation settings
  * @vsi: pointer to a vsi
- * @vector: enable a particular Hw Interrupt vector
+ * @vector: disable a particular Hw Interrupt vector
  **/
 void i40e_irq_dynamic_disable(struct i40e_vsi *vsi, int vector)
 {
@@ -6933,17 +6933,17 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED)
 		other_vecs++;
 
+	/* Scale down if necessary, and the rings will share vectors */
+	pf->num_lan_msix = min_t(int, pf->num_lan_msix,
+			(hw->func_caps.num_msix_vectors - other_vecs));
+	v_budget = pf->num_lan_msix + other_vecs;
+
 #ifdef I40E_FCOE
 	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
 		pf->num_fcoe_msix = pf->num_fcoe_qps;
 		v_budget += pf->num_fcoe_msix;
 	}
-
 #endif
-	/* Scale down if necessary, and the rings will share vectors */
-	pf->num_lan_msix = min_t(int, pf->num_lan_msix,
-			(hw->func_caps.num_msix_vectors - other_vecs));
-	v_budget = pf->num_lan_msix + other_vecs;
 
 	pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
 				   GFP_KERNEL);
@@ -9736,6 +9736,8 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	set_bit(__I40E_SUSPENDED, &pf->state);
 	set_bit(__I40E_DOWN, &pf->state);
+	del_timer_sync(&pf->service_timer);
+	cancel_work_sync(&pf->service_task);
 	rtnl_lock();
 	i40e_prep_for_reset(pf);
 	rtnl_unlock();

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -836,8 +836,8 @@ static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
 {
 	u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
 		  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
-		  I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK
-		  /* allow 00 to be written to the index */;
+		  I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK;
+		  /* allow 00 to be written to the index */
 
 	wr32(&vsi->back->hw,
 	     I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1),
@@ -1098,6 +1098,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	if (!rx_ring->rx_bi)
 		goto err;
 
+		u64_stats_init(rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = ring_is_16byte_desc_enabled(rx_ring)
 		? rx_ring->count * sizeof(union i40e_16byte_rx_desc)

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -647,6 +647,9 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	int i;
 	u32 reg;
 
+	if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state))
+		return;
+
 	/* warn the VF */
 	clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
 
@@ -668,13 +671,13 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	/* poll VPGEN_VFRSTAT reg to make sure
 	 * that reset is complete
 	 */
-	for (i = 0; i < 100; i++) {
-		/* vf reset requires driver to first reset the
-		 * vf and then poll the status register to make sure
-		 * that the requested op was completed
-		 * successfully
+	for (i = 0; i < 10; i++) {
+		/* VF reset requires driver to first reset the VF and then
+		 * poll the status register to make sure that the reset
+		 * completed successfully. Due to internal HW FIFO flushes,
+		 * we must wait 10ms before the register will be valid.
 		 */
-		usleep_range(10, 20);
+		usleep_range(10000, 20000);
 		reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
 		if (reg & I40E_VPGEN_VFRSTAT_VFRD_MASK) {
 			rsd = true;
@@ -706,6 +709,7 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	/* tell the VF the reset is done */
 	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
 	i40e_flush(hw);
+	clear_bit(__I40E_VF_DISABLE, &pf->state);
 }
 
 /**
@@ -790,6 +794,8 @@ void i40e_free_vfs(struct i40e_pf *pf)
 
 	if (!pf->vf)
 		return;
+	while (test_and_set_bit(__I40E_VF_DISABLE, &pf->state))
+		usleep_range(1000, 2000);
 
 	/* Disable IOV before freeing resources. This lets any VF drivers
 	 * running in the host get themselves cleaned up before we yank
@@ -800,9 +806,6 @@ void i40e_free_vfs(struct i40e_pf *pf)
 
 	msleep(20); /* let any messages in transit get finished up */
 
-	/* Disable interrupt 0 so we don't try to handle the VFLR. */
-	i40e_irq_dynamic_disable_icr0(pf);
-
 	/* free up vf resources */
 	tmp = pf->num_alloc_vfs;
 	pf->num_alloc_vfs = 0;
@@ -834,9 +837,7 @@ void i40e_free_vfs(struct i40e_pf *pf)
 		dev_warn(&pf->pdev->dev,
 			 "unable to disable SR-IOV because VFs are assigned.\n");
 	}
-
-	/* Re-enable interrupt 0. */
-	i40e_irq_dynamic_enable_icr0(pf);
+	clear_bit(__I40E_VF_DISABLE, &pf->state);
 }
 
 #ifdef CONFIG_PCI_IOV

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -192,6 +192,8 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
 	return le32_to_cpu(*(volatile __le32 *)head);
 }
 
+#define WB_STRIDE 0x3
+
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
  * @tx_ring:  tx ring to clean
@@ -293,6 +295,14 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
+	if (budget &&
+	    !((i & WB_STRIDE) == WB_STRIDE) &&
+	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+		tx_ring->arm_wb = true;
+	else
+		tx_ring->arm_wb = false;
+
 	if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -343,6 +353,24 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	return budget > 0;
 }
 
+/**
+ * i40e_force_wb -Arm hardware to do a wb on noncache aligned descriptors
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+	u32 val = I40E_VFINT_DYN_CTLN_INTENA_MASK |
+		  I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK |
+		  I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK;
+		  /* allow 00 to be written to the index */
+
+	wr32(&vsi->back->hw,
+	     I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1),
+	     val);
+}
+
 /**
  * i40e_set_new_dynamic_itr - Find new ITR level
  * @rc: structure containing ring performance data
@@ -568,6 +596,8 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	if (!rx_ring->rx_bi)
 		goto err;
 
+		u64_stats_init(rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = ring_is_16byte_desc_enabled(rx_ring)
 		? rx_ring->count * sizeof(union i40e_16byte_rx_desc)
@@ -1065,6 +1095,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	struct i40e_vsi *vsi = q_vector->vsi;
 	struct i40e_ring *ring;
 	bool clean_complete = true;
+	bool arm_wb = false;
 	int budget_per_ring;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
@@ -1075,8 +1106,10 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
-	i40e_for_each_ring(ring, q_vector->tx)
+	i40e_for_each_ring(ring, q_vector->tx) {
 		clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+		arm_wb |= ring->arm_wb;
+	}
 
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
@@ -1087,8 +1120,11 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 		clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		if (arm_wb)
+			i40e_force_wb(vsi, q_vector);
 		return budget;
+	}
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete(napi);

drivers/net/ethernet/intel/i40evf/i40e_txrx.h

@@ -238,6 +238,7 @@ struct i40e_ring {
 	u8 atr_count;
 
 	bool ring_active;		/* is ring online or not */
+	bool arm_wb;		/* do something to arm write back */
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -1631,7 +1631,7 @@ static void i40evf_adminq_task(struct work_struct *work)
 	v_msg = (struct i40e_virtchnl_msg *)&event.desc;
 	do {
 		ret = i40evf_clean_arq_element(hw, &event, &pending);
-		if (ret)
+		if (ret || !v_msg->v_opcode)
 			break; /* No event to process or error cleaning ARQ */
 
 		i40evf_virtchnl_completion(adapter, v_msg->v_opcode,
@@ -2213,12 +2213,18 @@ static void i40evf_init_task(struct work_struct *work)
 static void i40evf_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev))
 		i40evf_close(netdev);
 
+	/* Prevent the watchdog from running. */
+	adapter->state = __I40EVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->aq_pending = 0;
+
 #ifdef CONFIG_PM
 	pci_save_state(pdev);
 
@@ -2423,7 +2429,6 @@ static void i40evf_remove(struct pci_dev *pdev)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40evf_mac_filter *f, *ftmp;
 	struct i40e_hw *hw = &adapter->hw;
-	int count = 50;
 
 	cancel_delayed_work_sync(&adapter->init_task);
 	cancel_work_sync(&adapter->reset_task);
@@ -2432,12 +2437,18 @@ static void i40evf_remove(struct pci_dev *pdev)
 		unregister_netdev(netdev);
 		adapter->netdev_registered = false;
 	}
-	while (count-- && adapter->aq_required)
-		msleep(50);
 
-	if (count < 0)
-		dev_err(&pdev->dev, "Timed out waiting for PF driver.\n");
+	/* Shut down all the garbage mashers on the detention level */
 	adapter->state = __I40EVF_REMOVE;
+	adapter->aq_required = 0;
+	adapter->aq_pending = 0;
+	i40evf_request_reset(adapter);
+	msleep(20);
+	/* If the FW isn't responding, kick it once, but only once. */
+	if (!i40evf_asq_done(hw)) {
+		i40evf_request_reset(adapter);
+		msleep(20);
+	}
 
 	if (adapter->msix_entries) {
 		i40evf_misc_irq_disable(adapter);