Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2015-12-03

This series contains updates to i40e and i40evf only.

Mitch updates the i40evf driver by increasing the maximum number of queues,
since future devices will allow for more queue pairs.  Cleans up a
duplicate printing of the driver info string done in init, since it is
already done in probe.  Cleaned up the several allocations which did
not need to be at atomic level, where GFP_KERNEL would work just fine.
Then makes i40e_sync_vsi_filters() a more mature function, make having
a common exit point so it will properly release the busy lock on the VSI
and propagate errors to the callers.  Then does some whitespace
housekeeping in i40evf.

Kiran moves and updates the detection/recovery of transmit queue hang code
to service_task from tx_timeout function.  Also fixed memory leak when
users program flow-director filter using ethtool (sideband filter
programming), the cause being the check of 'tx_buffer->skb' was preventing
'raw_buf' from being freed as part of the cleanup.

Jesse enabled the ability to turn off/on packet split using ethtool priv
flags.  Then does some housekeeping for both the i40e and i40evf drivers
which includes: remove unused/useless code, correct whitespace, remove
duplicate #include, fix incorrect comment, etc...

Neerav cleans up functions to gather Flow Control Rx XOFF stats, since
the recent change in the driver logic for checking transmit hang has been
moved, so these functions do not do anything meaningful any longer.
====================

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

1 files changed, 112 insertions, 128 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0ddec19a9087..8cd395d1cd09 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -27,7 +27,7 @@
 /* Local includes */
 #include "i40e.h"
 #include "i40e_diag.h"
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 #include <net/vxlan.h>
 #endif
 
@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 4
-#define DRV_VERSION_BUILD 4
+#define DRV_VERSION_BUILD 7
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -792,75 +792,6 @@ static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
 
 #endif
 /**
- * i40e_update_link_xoff_rx - Update XOFF received in link flow control mode
- * @pf: the corresponding PF
- *
- * Update the Rx XOFF counter (PAUSE frames) in link flow control mode
- **/
-static void i40e_update_link_xoff_rx(struct i40e_pf *pf)
-{
-	struct i40e_hw_port_stats *osd = &pf->stats_offsets;
-	struct i40e_hw_port_stats *nsd = &pf->stats;
-	struct i40e_hw *hw = &pf->hw;
-	u64 xoff = 0;
-
-	if ((hw->fc.current_mode != I40E_FC_FULL) &&
-	    (hw->fc.current_mode != I40E_FC_RX_PAUSE))
-		return;
-
-	xoff = nsd->link_xoff_rx;
-	i40e_stat_update32(hw, I40E_GLPRT_LXOFFRXC(hw->port),
-			   pf->stat_offsets_loaded,
-			   &osd->link_xoff_rx, &nsd->link_xoff_rx);
-
-	/* No new LFC xoff rx */
-	if (!(nsd->link_xoff_rx - xoff))
-		return;
-
-}
-
-/**
- * i40e_update_prio_xoff_rx - Update XOFF received in PFC mode
- * @pf: the corresponding PF
- *
- * Update the Rx XOFF counter (PAUSE frames) in PFC mode
- **/
-static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
-{
-	struct i40e_hw_port_stats *osd = &pf->stats_offsets;
-	struct i40e_hw_port_stats *nsd = &pf->stats;
-	bool xoff[I40E_MAX_TRAFFIC_CLASS] = {false};
-	struct i40e_dcbx_config *dcb_cfg;
-	struct i40e_hw *hw = &pf->hw;
-	u16 i;
-	u8 tc;
-
-	dcb_cfg = &hw->local_dcbx_config;
-
-	/* Collect Link XOFF stats when PFC is disabled */
-	if (!dcb_cfg->pfc.pfcenable) {
-		i40e_update_link_xoff_rx(pf);
-		return;
-	}
-
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		u64 prio_xoff = nsd->priority_xoff_rx[i];
-
-		i40e_stat_update32(hw, I40E_GLPRT_PXOFFRXC(hw->port, i),
-				   pf->stat_offsets_loaded,
-				   &osd->priority_xoff_rx[i],
-				   &nsd->priority_xoff_rx[i]);
-
-		/* No new PFC xoff rx */
-		if (!(nsd->priority_xoff_rx[i] - prio_xoff))
-			continue;
-		/* Get the TC for given priority */
-		tc = dcb_cfg->etscfg.prioritytable[i];
-		xoff[tc] = true;
-	}
-}
-
-/**
  * i40e_update_vsi_stats - Update the vsi statistics counters.
  * @vsi: the VSI to be updated
  *
@@ -1054,12 +985,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 	i40e_stat_update32(hw, I40E_GLPRT_LXONTXC(hw->port),
 			   pf->stat_offsets_loaded,
 			   &osd->link_xon_tx, &nsd->link_xon_tx);
-	i40e_update_prio_xoff_rx(pf);  /* handles I40E_GLPRT_LXOFFRXC */
+	i40e_stat_update32(hw, I40E_GLPRT_LXOFFRXC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->link_xoff_rx, &nsd->link_xoff_rx);
 	i40e_stat_update32(hw, I40E_GLPRT_LXOFFTXC(hw->port),
 			   pf->stat_offsets_loaded,
 			   &osd->link_xoff_tx, &nsd->link_xoff_tx);
 
 	for (i = 0; i < 8; i++) {
+		i40e_stat_update32(hw, I40E_GLPRT_PXOFFRXC(hw->port, i),
+				   pf->stat_offsets_loaded,
+				   &osd->priority_xoff_rx[i],
+				   &nsd->priority_xoff_rx[i]);
 		i40e_stat_update32(hw, I40E_GLPRT_PXONRXC(hw->port, i),
 				   pf->stat_offsets_loaded,
 				   &osd->priority_xon_rx[i],
@@ -1553,11 +1490,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 	}
 
 	ether_addr_copy(netdev->dev_addr, addr->sa_data);
-	/* schedule our worker thread which will take care of
-	 * applying the new filter changes
-	 */
-	i40e_service_event_schedule(vsi->back);
-	return 0;
+
+	return i40e_sync_vsi_filters(vsi);
 }
 
 /**
@@ -1872,8 +1806,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 	bool add_happened = false;
 	int filter_list_len = 0;
 	u32 changed_flags = 0;
+	i40e_status aq_ret = 0;
 	bool err_cond = false;
-	i40e_status ret = 0;
+	int retval = 0;
 	struct i40e_pf *pf;
 	int num_add = 0;
 	int num_del = 0;
@@ -1936,8 +1871,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 		spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-		if (err_cond)
+		if (err_cond) {
 			i40e_cleanup_add_list(&tmp_add_list);
+			retval = -ENOMEM;
+			goto out;
+		}
 	}
 
 	/* Now process 'del_list' outside the lock */
@@ -1955,7 +1893,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			i40e_undo_del_filter_entries(vsi, &tmp_del_list);
 			i40e_undo_add_filter_entries(vsi);
 			spin_unlock_bh(&vsi->mac_filter_list_lock);
-			return -ENOMEM;
+			retval = -ENOMEM;
+			goto out;
 		}
 
 		list_for_each_entry_safe(f, ftmp, &tmp_del_list, list) {
@@ -1973,18 +1912,22 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 			/* flush a full buffer */
 			if (num_del == filter_list_len) {
-				ret = i40e_aq_remove_macvlan(&pf->hw,
-						  vsi->seid, del_list, num_del,
-						  NULL);
+				aq_ret = i40e_aq_remove_macvlan(&pf->hw,
+								vsi->seid,
+								del_list,
+								num_del,
+								NULL);
 				aq_err = pf->hw.aq.asq_last_status;
 				num_del = 0;
 				memset(del_list, 0, sizeof(*del_list));
 
-				if (ret && aq_err != I40E_AQ_RC_ENOENT)
+				if (aq_ret && aq_err != I40E_AQ_RC_ENOENT) {
+					retval = -EIO;
 					dev_err(&pf->pdev->dev,
 						"ignoring delete macvlan error, err %s, aq_err %s while flushing a full buffer\n",
-						i40e_stat_str(&pf->hw, ret),
+						i40e_stat_str(&pf->hw, aq_ret),
 						i40e_aq_str(&pf->hw, aq_err));
+				}
 			}
 			/* Release memory for MAC filter entries which were
 			 * synced up with HW.
@@ -1994,15 +1937,16 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 
 		if (num_del) {
-			ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid,
-						     del_list, num_del, NULL);
+			aq_ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid,
+							del_list, num_del,
+							NULL);
 			aq_err = pf->hw.aq.asq_last_status;
 			num_del = 0;
 
-			if (ret && aq_err != I40E_AQ_RC_ENOENT)
+			if (aq_ret && aq_err != I40E_AQ_RC_ENOENT)
 				dev_info(&pf->pdev->dev,
 					 "ignoring delete macvlan error, err %s aq_err %s\n",
-					 i40e_stat_str(&pf->hw, ret),
+					 i40e_stat_str(&pf->hw, aq_ret),
 					 i40e_aq_str(&pf->hw, aq_err));
 		}
 
@@ -2026,7 +1970,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			spin_lock_bh(&vsi->mac_filter_list_lock);
 			i40e_undo_add_filter_entries(vsi);
 			spin_unlock_bh(&vsi->mac_filter_list_lock);
-			return -ENOMEM;
+			retval = -ENOMEM;
+			goto out;
 		}
 
 		list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) {
@@ -2047,13 +1992,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 
 			/* flush a full buffer */
 			if (num_add == filter_list_len) {
-				ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
-							  add_list, num_add,
-							  NULL);
+				aq_ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
+							     add_list, num_add,
+							     NULL);
 				aq_err = pf->hw.aq.asq_last_status;
 				num_add = 0;
 
-				if (ret)
+				if (aq_ret)
 					break;
 				memset(add_list, 0, sizeof(*add_list));
 			}
@@ -2065,18 +2010,19 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		}
 
 		if (num_add) {
-			ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
-						  add_list, num_add, NULL);
+			aq_ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
+						     add_list, num_add, NULL);
 			aq_err = pf->hw.aq.asq_last_status;
 			num_add = 0;
 		}
 		kfree(add_list);
 		add_list = NULL;
 
-		if (add_happened && ret && aq_err != I40E_AQ_RC_EINVAL) {
+		if (add_happened && aq_ret && aq_err != I40E_AQ_RC_EINVAL) {
+			retval = i40e_aq_rc_to_posix(aq_ret, aq_err);
 			dev_info(&pf->pdev->dev,
 				 "add filter failed, err %s aq_err %s\n",
-				 i40e_stat_str(&pf->hw, ret),
+				 i40e_stat_str(&pf->hw, aq_ret),
 				 i40e_aq_str(&pf->hw, aq_err));
 			if ((pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOSPC) &&
 			    !test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
@@ -2094,16 +2040,19 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		bool cur_multipromisc;
 
 		cur_multipromisc = !!(vsi->current_netdev_flags & IFF_ALLMULTI);
-		ret = i40e_aq_set_vsi_multicast_promiscuous(&vsi->back->hw,
-							    vsi->seid,
-							    cur_multipromisc,
-							    NULL);
-		if (ret)
+		aq_ret = i40e_aq_set_vsi_multicast_promiscuous(&vsi->back->hw,
+							       vsi->seid,
+							       cur_multipromisc,
+							       NULL);
+		if (aq_ret) {
+			retval = i40e_aq_rc_to_posix(aq_ret,
+						     pf->hw.aq.asq_last_status);
 			dev_info(&pf->pdev->dev,
 				 "set multi promisc failed, err %s aq_err %s\n",
-				 i40e_stat_str(&pf->hw, ret),
+				 i40e_stat_str(&pf->hw, aq_ret),
 				 i40e_aq_str(&pf->hw,
 					     pf->hw.aq.asq_last_status));
+		}
 	}
 	if ((changed_flags & IFF_PROMISC) || promisc_forced_on) {
 		bool cur_promisc;
@@ -2122,36 +2071,47 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
 			}
 		} else {
-			ret = i40e_aq_set_vsi_unicast_promiscuous(
+			aq_ret = i40e_aq_set_vsi_unicast_promiscuous(
 							  &vsi->back->hw,
 							  vsi->seid,
 							  cur_promisc, NULL);
-			if (ret)
+			if (aq_ret) {
+				retval =
+				i40e_aq_rc_to_posix(aq_ret,
+						    pf->hw.aq.asq_last_status);
 				dev_info(&pf->pdev->dev,
 					 "set unicast promisc failed, err %d, aq_err %d\n",
-					 ret, pf->hw.aq.asq_last_status);
-			ret = i40e_aq_set_vsi_multicast_promiscuous(
+					 aq_ret, pf->hw.aq.asq_last_status);
+			}
+			aq_ret = i40e_aq_set_vsi_multicast_promiscuous(
 							  &vsi->back->hw,
 							  vsi->seid,
 							  cur_promisc, NULL);
-			if (ret)
+			if (aq_ret) {
+				retval =
+				i40e_aq_rc_to_posix(aq_ret,
+						    pf->hw.aq.asq_last_status);
 				dev_info(&pf->pdev->dev,
 					 "set multicast promisc failed, err %d, aq_err %d\n",
-					 ret, pf->hw.aq.asq_last_status);
+					 aq_ret, pf->hw.aq.asq_last_status);
+			}
 		}
-		ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
-						vsi->seid,
-						cur_promisc, NULL);
-		if (ret)
+		aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
+						   vsi->seid,
+						   cur_promisc, NULL);
+		if (aq_ret) {
+			retval = i40e_aq_rc_to_posix(aq_ret,
+						     pf->hw.aq.asq_last_status);
 			dev_info(&pf->pdev->dev,
 				 "set brdcast promisc failed, err %s, aq_err %s\n",
-				 i40e_stat_str(&pf->hw, ret),
+				 i40e_stat_str(&pf->hw, aq_ret),
 				 i40e_aq_str(&pf->hw,
 					     pf->hw.aq.asq_last_status));
+		}
 	}
-
+out:
 	clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
-	return 0;
+	return retval;
 }
 
 /**
@@ -4368,17 +4328,41 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
 	else
 		val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
 
+	/* Bail out if interrupts are disabled because napi_poll
+	 * execution in-progress or will get scheduled soon.
+	 * napi_poll cleans TX and RX queues and updates 'next_to_clean'.
+	 */
+	if (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))
+		return;
+
 	head = i40e_get_head(tx_ring);
 
 	tx_pending = i40e_get_tx_pending(tx_ring);
 
-	/* Interrupts are disabled and TX pending is non-zero,
-	 * trigger the SW interrupt (don't wait). Worst case
-	 * there will be one extra interrupt which may result
-	 * into not cleaning any queues because queues are cleaned.
+	/* HW is done executing descriptors, updated HEAD write back,
+	 * but SW hasn't processed those descriptors. If interrupt is
+	 * not generated from this point ON, it could result into
+	 * dev_watchdog detecting timeout on those netdev_queue,
+	 * hence proactively trigger SW interrupt.
 	 */
-	if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
-		i40e_force_wb(vsi, tx_ring->q_vector);
+	if (tx_pending) {
+		/* NAPI Poll didn't run and clear since it was set */
+		if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT,
+				       &tx_ring->q_vector->hung_detected)) {
+			netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
+				    vsi->seid, q_idx, tx_pending,
+				    tx_ring->next_to_clean, head,
+				    tx_ring->next_to_use,
+				    readl(tx_ring->tail));
+			netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n",
+				    vsi->seid, q_idx, val);
+			i40e_force_wb(vsi, tx_ring->q_vector);
+		} else {
+			/* First Chance - detected possible hung */
+			set_bit(I40E_Q_VECTOR_HUNG_DETECT,
+				&tx_ring->q_vector->hung_detected);
+		}
+	}
 }
 
 /**
@@ -5310,7 +5294,7 @@ int i40e_open(struct net_device *netdev)
 						       TCP_FLAG_CWR) >> 16);
 	wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
 
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 	vxlan_get_rx_port(netdev);
 #endif
 
@@ -7006,7 +6990,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	i40e_flush(hw);
 }
 
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 /**
  * i40e_sync_vxlan_filters_subtask - Sync the VSI filter list with HW
  * @pf: board private structure
@@ -7073,7 +7057,7 @@ static void i40e_service_task(struct work_struct *work)
 	i40e_watchdog_subtask(pf);
 	i40e_fdir_reinit_subtask(pf);
 	i40e_sync_filters_subtask(pf);
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 	i40e_sync_vxlan_filters_subtask(pf);
 #endif
 	i40e_clean_adminq_subtask(pf);
@@ -8449,7 +8433,7 @@ static int i40e_set_features(struct net_device *netdev,
 	return 0;
 }
 
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 /**
  * i40e_get_vxlan_port_idx - Lookup a possibly offloaded for Rx UDP port
  * @pf: board private structure
@@ -8769,7 +8753,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_get_vf_config	= i40e_ndo_get_vf_config,
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofchk,
-#ifdef CONFIG_I40E_VXLAN
+#if IS_ENABLED(CONFIG_VXLAN)
 	.ndo_add_vxlan_port	= i40e_add_vxlan_port,
 	.ndo_del_vxlan_port	= i40e_del_vxlan_port,
 #endif