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

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-11-18

This series contains updates to i40e only.

Shannon provides a patch to clean up the driver to only warn once that
PTP is not supported when linked at 100Mbps.

Mitch provides a fix for i40e where the VF interrupt processing takes
a long time and it is possible that we could lose a VFLR event if it
happens while processing a VFLR on another VF.  To correct this situation,
we enable the VFLR interrupt cause before we begin processing any pending
resets.

Neerav provides several patches to update DCB support in i40e.  When
there are DCB configuration changes based on DCBx, the firmware suspends
the port's Tx and generates an event to the PF.  The PF is then
responsible to reconfigure the PF VSIs and switching topology as per the
updated DCB configuration and then resume the port's Tx by calling the
"Resume Port Tx" AQ command, so add this call to the flow that handles
DCB re-configuration in the PF.  Allow the driver to query and use DCB
configuration from firmware when firmware DCBx agent is in CEE mode.
Add a check whether LLDP Agent's default AdminStatus is enabled or
disabled on a given port, and sets DCBx status to disabled if the
status is disabled.  Fix an issue when the port TC configuration
changes as a result of DCBx and the driver modifies the enabled TCs for
the VEBs it manages but does not update the enabled_tc value that
was cached on a per VEB basis.  Add a new PF state so that if a port's
Tx is in suspended state the Tx queue disable flow would just put the
request for the queue to be disabled and return without waiting for the
queue to be actually disabled.  Allows the driver to enable/disable
the XPS based on the number of TCs being enabled for the given VSI.

v2: Dropped patch "i40e: Handle a single mss packet with more than 8 frags"
    while we rework the patch after we test a bit more based on feedback from
    Eric Dumazet.
====================

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

1 files changed, 151 insertions, 19 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a0bee83ab2de..c998d82da0fc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -38,8 +38,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 0
-#define DRV_VERSION_BUILD 21
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 23
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -2382,6 +2382,35 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_config_xps_tx_ring - Configure XPS for a Tx ring
+ * @ring: The Tx ring to configure
+ *
+ * This enables/disables XPS for a given Tx descriptor ring
+ * based on the TCs enabled for the VSI that ring belongs to.
+ **/
+static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
+{
+	struct i40e_vsi *vsi = ring->vsi;
+	cpumask_var_t mask;
+
+	if (ring->q_vector && ring->netdev) {
+		/* Single TC mode enable XPS */
+		if (vsi->tc_config.numtc <= 1 &&
+		    !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) {
+			netif_set_xps_queue(ring->netdev,
+					    &ring->q_vector->affinity_mask,
+					    ring->queue_index);
+		} else if (alloc_cpumask_var(&mask, GFP_KERNEL)) {
+			/* Disable XPS to allow selection based on TC */
+			bitmap_zero(cpumask_bits(mask), nr_cpumask_bits);
+			netif_set_xps_queue(ring->netdev, mask,
+					    ring->queue_index);
+			free_cpumask_var(mask);
+		}
+	}
+}
+
+/**
  * i40e_configure_tx_ring - Configure a transmit ring context and rest
  * @ring: The Tx ring to configure
  *
@@ -2404,13 +2433,8 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 		ring->atr_sample_rate = 0;
 	}
 
-	/* initialize XPS */
-	if (ring->q_vector && ring->netdev &&
-	    vsi->tc_config.numtc <= 1 &&
-	    !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state))
-		netif_set_xps_queue(ring->netdev,
-				    &ring->q_vector->affinity_mask,
-				    ring->queue_index);
+	/* configure XPS */
+	i40e_config_xps_tx_ring(ring);
 
 	/* clear the context structure first */
 	memset(&tx_ctx, 0, sizeof(tx_ctx));
@@ -3492,6 +3516,9 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 		}
 
 		wr32(hw, I40E_QTX_ENA(pf_q), tx_reg);
+		/* No waiting for the Tx queue to disable */
+		if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state))
+			continue;
 
 		/* wait for the change to finish */
 		ret = i40e_pf_txq_wait(pf, pf_q, enable);
@@ -3859,6 +3886,15 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
 	if (test_bit(__I40E_DOWN, &vsi->state))
 		return;
 
+	/* No need to disable FCoE VSI when Tx suspended */
+	if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
+	    vsi->type == I40E_VSI_FCOE) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"%s: VSI seid %d skipping FCoE VSI disable\n",
+			 __func__, vsi->seid);
+		return;
+	}
+
 	set_bit(__I40E_NEEDS_RESTART, &vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev)) {
 		vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
@@ -3911,6 +3947,57 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
 	}
 }
 
+#ifdef CONFIG_I40E_DCB
+/**
+ * i40e_vsi_wait_txq_disabled - Wait for VSI's queues to be disabled
+ * @vsi: the VSI being configured
+ *
+ * This function waits for the given VSI's Tx queues to be disabled.
+ **/
+static int i40e_vsi_wait_txq_disabled(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+	int i, pf_q, ret;
+
+	pf_q = vsi->base_queue;
+	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+		/* Check and wait for the disable status of the queue */
+		ret = i40e_pf_txq_wait(pf, pf_q, false);
+		if (ret) {
+			dev_info(&pf->pdev->dev,
+				 "%s: VSI seid %d Tx ring %d disable timeout\n",
+				 __func__, vsi->seid, pf_q);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_pf_wait_txq_disabled - Wait for all queues of PF VSIs to be disabled
+ * @pf: the PF
+ *
+ * This function waits for the Tx queues to be in disabled state for all the
+ * VSIs that are managed by this PF.
+ **/
+static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf)
+{
+	int v, ret = 0;
+
+	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+		/* No need to wait for FCoE VSI queues */
+		if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
+			ret = i40e_vsi_wait_txq_disabled(pf->vsi[v]);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+#endif
 /**
  * i40e_dcb_get_num_tc -  Get the number of TCs from DCBx config
  * @dcbcfg: the corresponding DCBx configuration structure
@@ -4382,6 +4469,31 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_resume_port_tx - Resume port Tx
+ * @pf: PF struct
+ *
+ * Resume a port's Tx and issue a PF reset in case of failure to
+ * resume.
+ **/
+static int i40e_resume_port_tx(struct i40e_pf *pf)
+{
+	struct i40e_hw *hw = &pf->hw;
+	int ret;
+
+	ret = i40e_aq_resume_port_tx(hw, NULL);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "AQ command Resume Port Tx failed = %d\n",
+			  pf->hw.aq.asq_last_status);
+		/* Schedule PF reset to recover */
+		set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
+		i40e_service_event_schedule(pf);
+	}
+
+	return ret;
+}
+
+/**
  * i40e_init_pf_dcb - Initialize DCB configuration
  * @pf: PF being configured
  *
@@ -4417,6 +4529,8 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			/* Enable DCB tagging only when more than one TC */
 			if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
 				pf->flags |= I40E_FLAG_DCB_ENABLED;
+			dev_dbg(&pf->pdev->dev,
+				"DCBX offload is supported for this PF.\n");
 		}
 	} else {
 		dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n",
@@ -4998,6 +5112,8 @@ bool i40e_dcb_need_reconfig(struct i40e_pf *pf,
 		dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
 	}
 
+	dev_dbg(&pf->pdev->dev, "%s: need_reconfig=%d\n", __func__,
+		need_reconfig);
 	return need_reconfig;
 }
 
@@ -5025,11 +5141,16 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	/* Ignore if event is not for Nearest Bridge */
 	type = ((mib->type >> I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT)
 		& I40E_AQ_LLDP_BRIDGE_TYPE_MASK);
+	dev_dbg(&pf->pdev->dev,
+		"%s: LLDP event mib bridge type 0x%x\n", __func__, type);
 	if (type != I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE)
 		return ret;
 
 	/* Check MIB Type and return if event for Remote MIB update */
 	type = mib->type & I40E_AQ_LLDP_MIB_TYPE_MASK;
+	dev_dbg(&pf->pdev->dev,
+		"%s: LLDP event mib type %s\n", __func__,
+		type ? "remote" : "local");
 	if (type == I40E_AQ_LLDP_MIB_REMOTE) {
 		/* Update the remote cached instance and return */
 		ret = i40e_aq_get_dcb_config(hw, I40E_AQ_LLDP_MIB_REMOTE,
@@ -5038,12 +5159,14 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		goto exit;
 	}
 
-	/* Convert/store the DCBX data from LLDPDU temporarily */
 	memset(&tmp_dcbx_cfg, 0, sizeof(tmp_dcbx_cfg));
-	ret = i40e_lldp_to_dcb_config(e->msg_buf, &tmp_dcbx_cfg);
+	/* Store the old configuration */
+	tmp_dcbx_cfg = *dcbx_cfg;
+
+	/* Get updated DCBX data from firmware */
+	ret = i40e_get_dcb_config(&pf->hw);
 	if (ret) {
-		/* Error in LLDPDU parsing return */
-		dev_info(&pf->pdev->dev, "Failed parsing LLDPDU from event buffer\n");
+		dev_info(&pf->pdev->dev, "Failed querying DCB configuration data from firmware.\n");
 		goto exit;
 	}
 
@@ -5053,12 +5176,9 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		goto exit;
 	}
 
-	need_reconfig = i40e_dcb_need_reconfig(pf, dcbx_cfg, &tmp_dcbx_cfg);
+	need_reconfig = i40e_dcb_need_reconfig(pf, &tmp_dcbx_cfg, dcbx_cfg);
 
-	i40e_dcbnl_flush_apps(pf, &tmp_dcbx_cfg);
-
-	/* Overwrite the new configuration */
-	*dcbx_cfg = tmp_dcbx_cfg;
+	i40e_dcbnl_flush_apps(pf, dcbx_cfg);
 
 	if (!need_reconfig)
 		goto exit;
@@ -5069,13 +5189,24 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	else
 		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
 
+	set_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
 	/* Reconfiguration needed quiesce all VSIs */
 	i40e_pf_quiesce_all_vsi(pf);
 
 	/* Changes in configuration update VEB/VSI */
 	i40e_dcb_reconfigure(pf);
 
-	i40e_pf_unquiesce_all_vsi(pf);
+	ret = i40e_resume_port_tx(pf);
+
+	clear_bit(__I40E_PORT_TX_SUSPENDED, &pf->state);
+	/* In case of error no point in resuming VSIs */
+	if (ret)
+		goto exit;
+
+	/* Wait for the PF's Tx queues to be disabled */
+	ret = i40e_pf_wait_txq_disabled(pf);
+	if (!ret)
+		i40e_pf_unquiesce_all_vsi(pf);
 exit:
 	return ret;
 }
@@ -8242,6 +8373,7 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb)
 	veb->bw_limit = le16_to_cpu(ets_data.port_bw_limit);
 	veb->bw_max_quanta = ets_data.tc_bw_max;
 	veb->is_abs_credits = bw_data.absolute_credits_enable;
+	veb->enabled_tc = ets_data.tc_valid_bits;
 	tc_bw_max = le16_to_cpu(bw_data.tc_bw_max[0]) |
 		    (le16_to_cpu(bw_data.tc_bw_max[1]) << 16);
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {