From 216590355cb0e79fa36c7220176ce850f0e3d276 Mon Sep 17 00:00:00 2001
From: Kiran Patil <kiran.patil@intel.com>
Date: Wed, 30 Sep 2015 14:09:03 -0400
Subject: [PATCH 01/17] i40e: Lock for VSI's MAC filter list

This patch introduces a spinlock which is to be used for synchronizing
access to VSI's MAC filter list.

This patch also synchronizes execution of other codepaths which are
accessing VSI's MAC filter list with execution of
service_task:sync_vsi_filters.

In function i40e_add_vsi, copied out LAA MAC address instead of cloning
MAC filter entry because only MAC address is needed to remove MAC VLAN
filter from FW/HW.

Change-ID: I0e10ac7c715d44aa994239642aa4d57c998573a2
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h        |   2 +
 drivers/net/ethernet/intel/i40e/i40e_fcoe.c   |   2 +
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 308 ++++++++++++++----
 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    |  26 +-
 4 files changed, 282 insertions(+), 56 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 7a58b1f9971f..b7818be0f06d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -468,6 +468,8 @@ struct i40e_vsi {
 #define I40E_VSI_FLAG_VEB_OWNER		BIT(1)
 	unsigned long flags;
 
+	/* Per VSI lock to protect elements/list (MAC filter) */
+	spinlock_t mac_filter_list_lock;
 	struct list_head mac_filter_list;
 
 	/* VSI stats */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 2ec241142e9d..fe5d9bf3ed6d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -1516,10 +1516,12 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi)
 	 * same PCI function.
 	 */
 	netdev->dev_port = 1;
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	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);
 	i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0, false, false);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* use san mac */
 	ether_addr_copy(netdev->dev_addr, hw->mac.san_addr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 87a5d09cb087..36cca7b93f36 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1355,6 +1355,9 @@ static int i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr)
  * @is_netdev: make sure its a netdev filter, else doesn't matter
  *
  * Returns ptr to the filter object or NULL when no memory available.
+ *
+ * NOTE: This function is expected to be called with mac_filter_list_lock
+ * being held.
  **/
 struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 					u8 *macaddr, s16 vlan,
@@ -1413,6 +1416,9 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
  * @vlan: the vlan
  * @is_vf: make sure it's a VF filter, else doesn't matter
  * @is_netdev: make sure it's a netdev filter, else doesn't matter
+ *
+ * NOTE: This function is expected to be called with mac_filter_list_lock
+ * being held.
  **/
 void i40e_del_filter(struct i40e_vsi *vsi,
 		     u8 *macaddr, s16 vlan,
@@ -1519,8 +1525,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
 		i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
 	} else {
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		i40e_del_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY,
 				false, false);
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
 	if (ether_addr_equal(addr->sa_data, hw->mac.addr)) {
@@ -1531,10 +1539,12 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH);
 		i40e_aq_add_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
 	} else {
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		f = i40e_add_filter(vsi, addr->sa_data, I40E_VLAN_ANY,
 				    false, false);
 		if (f)
 			f->is_laa = true;
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
 	i40e_sync_vsi_filters(vsi, false);
@@ -1707,6 +1717,8 @@ static void i40e_set_rx_mode(struct net_device *netdev)
 	struct netdev_hw_addr *mca;
 	struct netdev_hw_addr *ha;
 
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	/* add addr if not already in the filter list */
 	netdev_for_each_uc_addr(uca, netdev) {
 		if (!i40e_find_mac(vsi, uca->addr, false, true)) {
@@ -1754,6 +1766,7 @@ static void i40e_set_rx_mode(struct net_device *netdev)
 bottom_of_search_loop:
 		continue;
 	}
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* check for other flag changes */
 	if (vsi->current_netdev_flags != vsi->netdev->flags) {
@@ -1762,6 +1775,79 @@ static void i40e_set_rx_mode(struct net_device *netdev)
 	}
 }
 
+/**
+ * i40e_mac_filter_entry_clone - Clones a MAC filter entry
+ * @src: source MAC filter entry to be clones
+ *
+ * Returns the pointer to newly cloned MAC filter entry or NULL
+ * in case of error
+ **/
+static struct i40e_mac_filter *i40e_mac_filter_entry_clone(
+					struct i40e_mac_filter *src)
+{
+	struct i40e_mac_filter *f;
+
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	*f = *src;
+
+	INIT_LIST_HEAD(&f->list);
+
+	return f;
+}
+
+/**
+ * i40e_undo_del_filter_entries - Undo the changes made to MAC filter entries
+ * @vsi: pointer to vsi struct
+ * @from: Pointer to list which contains MAC filter entries - changes to
+ *        those entries needs to be undone.
+ *
+ * MAC filter entries from list were slated to be removed from device.
+ **/
+static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi,
+					 struct list_head *from)
+{
+	struct i40e_mac_filter *f, *ftmp;
+
+	list_for_each_entry_safe(f, ftmp, from, list) {
+		f->changed = true;
+		/* Move the element back into MAC filter list*/
+		list_move_tail(&f->list, &vsi->mac_filter_list);
+	}
+}
+
+/**
+ * i40e_undo_add_filter_entries - Undo the changes made to MAC filter entries
+ * @vsi: pointer to vsi struct
+ *
+ * MAC filter entries from list were slated to be added from device.
+ **/
+static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi)
+{
+	struct i40e_mac_filter *f, *ftmp;
+
+	list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+		if (!f->changed && f->counter)
+			f->changed = true;
+	}
+}
+
+/**
+ * i40e_cleanup_add_list - Deletes the element from add list and release
+ *			memory
+ * @add_list: Pointer to list which contains MAC filter entries
+ **/
+static void i40e_cleanup_add_list(struct list_head *add_list)
+{
+	struct i40e_mac_filter *f, *ftmp;
+
+	list_for_each_entry_safe(f, ftmp, add_list, list) {
+		list_del(&f->list);
+		kfree(f);
+	}
+}
+
 /**
  * i40e_sync_vsi_filters - Update the VSI filter list to the HW
  * @vsi: ptr to the VSI
@@ -1773,11 +1859,13 @@ static void i40e_set_rx_mode(struct net_device *netdev)
  **/
 int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 {
-	struct i40e_mac_filter *f, *ftmp;
+	struct list_head tmp_del_list, tmp_add_list;
+	struct i40e_mac_filter *f, *ftmp, *fclone;
 	bool promisc_forced_on = false;
 	bool add_happened = false;
 	int filter_list_len = 0;
 	u32 changed_flags = 0;
+	bool err_cond = false;
 	i40e_status ret = 0;
 	struct i40e_pf *pf;
 	int num_add = 0;
@@ -1798,17 +1886,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 		vsi->current_netdev_flags = vsi->netdev->flags;
 	}
 
+	INIT_LIST_HEAD(&tmp_del_list);
+	INIT_LIST_HEAD(&tmp_add_list);
+
 	if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) {
 		vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED;
 
-		filter_list_len = pf->hw.aq.asq_buf_size /
-			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
-		del_list = kcalloc(filter_list_len,
-			    sizeof(struct i40e_aqc_remove_macvlan_element_data),
-			    GFP_KERNEL);
-		if (!del_list)
-			return -ENOMEM;
-
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
 			if (!f->changed)
 				continue;
@@ -1816,6 +1900,58 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 			if (f->counter != 0)
 				continue;
 			f->changed = false;
+
+			/* Move the element into temporary del_list */
+			list_move_tail(&f->list, &tmp_del_list);
+		}
+
+		list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+			if (!f->changed)
+				continue;
+
+			if (f->counter == 0)
+				continue;
+			f->changed = false;
+
+			/* Clone MAC filter entry and add into temporary list */
+			fclone = i40e_mac_filter_entry_clone(f);
+			if (!fclone) {
+				err_cond = true;
+				break;
+			}
+			list_add_tail(&fclone->list, &tmp_add_list);
+		}
+
+		/* if failed to clone MAC filter entry - undo */
+		if (err_cond) {
+			i40e_undo_del_filter_entries(vsi, &tmp_del_list);
+			i40e_undo_add_filter_entries(vsi);
+		}
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
+
+		if (err_cond)
+			i40e_cleanup_add_list(&tmp_add_list);
+	}
+
+	/* Now process 'del_list' outside the lock */
+	if (!list_empty(&tmp_del_list)) {
+		filter_list_len = pf->hw.aq.asq_buf_size /
+			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
+		del_list = kcalloc(filter_list_len,
+			    sizeof(struct i40e_aqc_remove_macvlan_element_data),
+			    GFP_KERNEL);
+		if (!del_list) {
+			i40e_cleanup_add_list(&tmp_add_list);
+
+			/* Undo VSI's MAC filter entry element updates */
+			spin_lock_bh(&vsi->mac_filter_list_lock);
+			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;
+		}
+
+		list_for_each_entry_safe(f, ftmp, &tmp_del_list, list) {
 			cmd_flags = 0;
 
 			/* add to delete list */
@@ -1828,10 +1964,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 			del_list[num_del].flags = cmd_flags;
 			num_del++;
 
-			/* unlink from filter list */
-			list_del(&f->list);
-			kfree(f);
-
 			/* flush a full buffer */
 			if (num_del == filter_list_len) {
 				ret = i40e_aq_remove_macvlan(&pf->hw,
@@ -1842,12 +1974,18 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 				memset(del_list, 0, sizeof(*del_list));
 
 				if (ret && aq_err != I40E_AQ_RC_ENOENT)
-					dev_info(&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_aq_str(&pf->hw, aq_err));
+					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_aq_str(&pf->hw, aq_err));
 			}
+			/* Release memory for MAC filter entries which were
+			 * synced up with HW.
+			 */
+			list_del(&f->list);
+			kfree(f);
 		}
+
 		if (num_del) {
 			ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid,
 						     del_list, num_del, NULL);
@@ -1863,6 +2001,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 
 		kfree(del_list);
 		del_list = NULL;
+	}
+
+	if (!list_empty(&tmp_add_list)) {
 
 		/* do all the adds now */
 		filter_list_len = pf->hw.aq.asq_buf_size /
@@ -1870,16 +2011,19 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 		add_list = kcalloc(filter_list_len,
 			       sizeof(struct i40e_aqc_add_macvlan_element_data),
 			       GFP_KERNEL);
-		if (!add_list)
+		if (!add_list) {
+			/* Purge element from temporary lists */
+			i40e_cleanup_add_list(&tmp_add_list);
+
+			/* Undo add filter entries from VSI MAC filter list */
+			spin_lock_bh(&vsi->mac_filter_list_lock);
+			i40e_undo_add_filter_entries(vsi);
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			return -ENOMEM;
+		}
 
-		list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
-			if (!f->changed)
-				continue;
+		list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) {
 
-			if (f->counter == 0)
-				continue;
-			f->changed = false;
 			add_happened = true;
 			cmd_flags = 0;
 
@@ -1906,7 +2050,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 					break;
 				memset(add_list, 0, sizeof(*add_list));
 			}
+			/* Entries from tmp_add_list were cloned from MAC
+			 * filter list, hence clean those cloned entries
+			 */
+			list_del(&f->list);
+			kfree(f);
 		}
+
 		if (num_add) {
 			ret = i40e_aq_add_macvlan(&pf->hw, vsi->seid,
 						  add_list, num_add, NULL);
@@ -2158,6 +2308,9 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 	is_vf = (vsi->type == I40E_VSI_SRIOV);
 	is_netdev = !!(vsi->netdev);
 
+	/* Locked once because all functions invoked below iterates list*/
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	if (is_netdev) {
 		add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid,
 					is_vf, is_netdev);
@@ -2165,6 +2318,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 			dev_info(&vsi->back->pdev->dev,
 				 "Could not add vlan filter %d for %pM\n",
 				 vid, vsi->netdev->dev_addr);
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			return -ENOMEM;
 		}
 	}
@@ -2175,6 +2329,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 			dev_info(&vsi->back->pdev->dev,
 				 "Could not add vlan filter %d for %pM\n",
 				 vid, f->macaddr);
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			return -ENOMEM;
 		}
 	}
@@ -2196,6 +2351,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 				dev_info(&vsi->back->pdev->dev,
 					 "Could not add filter 0 for %pM\n",
 					 vsi->netdev->dev_addr);
+				spin_unlock_bh(&vsi->mac_filter_list_lock);
 				return -ENOMEM;
 			}
 		}
@@ -2204,22 +2360,28 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 	/* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */
 	if (vid > 0 && !vsi->info.pvid) {
 		list_for_each_entry(f, &vsi->mac_filter_list, list) {
-			if (i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY,
-					     is_vf, is_netdev)) {
-				i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY,
-						is_vf, is_netdev);
-				add_f = i40e_add_filter(vsi, f->macaddr,
-							0, is_vf, is_netdev);
-				if (!add_f) {
-					dev_info(&vsi->back->pdev->dev,
-						 "Could not add filter 0 for %pM\n",
-						 f->macaddr);
-					return -ENOMEM;
-				}
+			if (!i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY,
+					      is_vf, is_netdev))
+				continue;
+			i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY,
+					is_vf, is_netdev);
+			add_f = i40e_add_filter(vsi, f->macaddr,
+						0, is_vf, is_netdev);
+			if (!add_f) {
+				dev_info(&vsi->back->pdev->dev,
+					 "Could not add filter 0 for %pM\n",
+					f->macaddr);
+				spin_unlock_bh(&vsi->mac_filter_list_lock);
+				return -ENOMEM;
 			}
 		}
 	}
 
+	/* Make sure to release before sync_vsi_filter because that
+	 * function will lock/unlock as necessary
+	 */
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
 	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
 	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
 		return 0;
@@ -2244,6 +2406,9 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
 	is_vf = (vsi->type == I40E_VSI_SRIOV);
 	is_netdev = !!(netdev);
 
+	/* Locked once because all functions invoked below iterates list */
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	if (is_netdev)
 		i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev);
 
@@ -2274,6 +2439,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
 			dev_info(&vsi->back->pdev->dev,
 				 "Could not add filter %d for %pM\n",
 				 I40E_VLAN_ANY, netdev->dev_addr);
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			return -ENOMEM;
 		}
 	}
@@ -2282,16 +2448,22 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
 		list_for_each_entry(f, &vsi->mac_filter_list, list) {
 			i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev);
 			add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY,
-					    is_vf, is_netdev);
+						is_vf, is_netdev);
 			if (!add_f) {
 				dev_info(&vsi->back->pdev->dev,
 					 "Could not add filter %d for %pM\n",
 					 I40E_VLAN_ANY, f->macaddr);
+				spin_unlock_bh(&vsi->mac_filter_list_lock);
 				return -ENOMEM;
 			}
 		}
 	}
 
+	/* Make sure to release before sync_vsi_filter because that
+	 * function with lock/unlock as necessary
+	 */
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
 	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
 	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
 		return 0;
@@ -7062,6 +7234,8 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	/* Setup default MSIX irq handler for VSI */
 	i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings);
 
+	/* Initialize VSI lock */
+	spin_lock_init(&vsi->mac_filter_list_lock);
 	pf->vsi[vsi_idx] = vsi;
 	ret = vsi_idx;
 	goto unlock_pf;
@@ -8477,17 +8651,26 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 		 * default a MAC-VLAN filter that accepts any tagged packet
 		 * which must be replaced by a normal filter.
 		 */
-		if (!i40e_rm_default_mac_filter(vsi, mac_addr))
+		if (!i40e_rm_default_mac_filter(vsi, mac_addr)) {
+			spin_lock_bh(&vsi->mac_filter_list_lock);
 			i40e_add_filter(vsi, mac_addr,
 					I40E_VLAN_ANY, false, true);
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
+		}
 	} else {
 		/* relate the VSI_VMDQ name to the VSI_MAIN name */
 		snprintf(netdev->name, IFNAMSIZ, "%sv%%d",
 			 pf->vsi[pf->lan_vsi]->netdev->name);
 		random_ether_addr(mac_addr);
+
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, false);
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
+
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	i40e_add_filter(vsi, brdcast, I40E_VLAN_ANY, false, false);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	ether_addr_copy(netdev->dev_addr, mac_addr);
 	ether_addr_copy(netdev->perm_addr, mac_addr);
@@ -8561,10 +8744,13 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi)
 static int i40e_add_vsi(struct i40e_vsi *vsi)
 {
 	int ret = -ENODEV;
-	struct i40e_mac_filter *f, *ftmp;
+	u8 laa_macaddr[ETH_ALEN];
+	bool found_laa_mac_filter = false;
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_vsi_context ctxt;
+	struct i40e_mac_filter *f, *ftmp;
+
 	u8 enabled_tc = 0x1; /* TC0 enabled */
 	int f_count = 0;
 
@@ -8736,32 +8922,41 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		vsi->id = ctxt.vsi_number;
 	}
 
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* If macvlan filters already exist, force them to get loaded */
 	list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
 		f->changed = true;
 		f_count++;
 
+		/* Expected to have only one MAC filter entry for LAA in list */
 		if (f->is_laa && vsi->type == I40E_VSI_MAIN) {
-			struct i40e_aqc_remove_macvlan_element_data element;
+			ether_addr_copy(laa_macaddr, f->macaddr);
+			found_laa_mac_filter = true;
+		}
+	}
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-			memset(&element, 0, sizeof(element));
-			ether_addr_copy(element.mac_addr, f->macaddr);
-			element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
-			ret = i40e_aq_remove_macvlan(hw, vsi->seid,
-						     &element, 1, NULL);
-			if (ret) {
-				/* some older FW has a different default */
-				element.flags |=
-					       I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
-				i40e_aq_remove_macvlan(hw, vsi->seid,
-						       &element, 1, NULL);
-			}
+	if (found_laa_mac_filter) {
+		struct i40e_aqc_remove_macvlan_element_data element;
 
-			i40e_aq_mac_address_write(hw,
-						  I40E_AQC_WRITE_TYPE_LAA_WOL,
-						  f->macaddr, NULL);
+		memset(&element, 0, sizeof(element));
+		ether_addr_copy(element.mac_addr, laa_macaddr);
+		element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+		ret = i40e_aq_remove_macvlan(hw, vsi->seid,
+					     &element, 1, NULL);
+		if (ret) {
+			/* some older FW has a different default */
+			element.flags |=
+				       I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
+			i40e_aq_remove_macvlan(hw, vsi->seid,
+					       &element, 1, NULL);
 		}
+
+		i40e_aq_mac_address_write(hw,
+					  I40E_AQC_WRITE_TYPE_LAA_WOL,
+					  laa_macaddr, NULL);
 	}
+
 	if (f_count) {
 		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
 		pf->flags |= I40E_FLAG_FILTER_SYNC;
@@ -8824,9 +9019,12 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		i40e_vsi_disable_irq(vsi);
 	}
 
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list)
 		i40e_del_filter(vsi, f->macaddr, f->vlan,
 				f->is_vf, f->is_netdev);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
 	i40e_sync_vsi_filters(vsi, false);
 
 	i40e_vsi_delete(vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index a35a204b4eeb..b2d95ee7ec69 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -547,6 +547,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 		 */
 		if (vf->port_vlan_id)
 			i40e_vsi_add_pvid(vsi, vf->port_vlan_id);
+
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
 				    vf->port_vlan_id ? vf->port_vlan_id : -1,
 				    true, false);
@@ -559,6 +561,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 		if (!f)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
 	/* program mac filter */
@@ -1598,6 +1601,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
+	/* Lock once, because all function inside for loop accesses VSI's
+	 * MAC filter list which needs to be protected using same lock.
+	 */
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	/* add new addresses to the list */
 	for (i = 0; i < al->num_elements; i++) {
 		struct i40e_mac_filter *f;
@@ -1616,9 +1624,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 			dev_err(&pf->pdev->dev,
 				"Unable to add VF MAC filter\n");
 			ret = I40E_ERR_PARAM;
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
 			goto error_param;
 		}
 	}
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
 	if (i40e_sync_vsi_filters(vsi, false))
@@ -1666,10 +1676,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
+	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* delete addresses from the list */
 	for (i = 0; i < al->num_elements; i++)
 		i40e_del_filter(vsi, al->list[i].addr,
 				I40E_VLAN_ANY, true, false);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
 	if (i40e_sync_vsi_filters(vsi, false))
@@ -2066,6 +2078,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 	}
 
+	/* Lock once because below invoked function add/del_filter requires
+	 * mac_filter_list_lock to be held
+	 */
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+
 	/* delete the temporary mac address */
 	i40e_del_filter(vsi, vf->default_lan_addr.addr,
 			vf->port_vlan_id ? vf->port_vlan_id : -1,
@@ -2077,6 +2094,8 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	list_for_each_entry(f, &vsi->mac_filter_list, list)
 		i40e_del_filter(vsi, f->macaddr, f->vlan, true, false);
 
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
 	dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id);
 	/* program mac filter */
 	if (i40e_sync_vsi_filters(vsi, false)) {
@@ -2109,6 +2128,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 	u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT);
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
+	bool is_vsi_in_vlan = false;
 	struct i40e_vsi *vsi;
 	struct i40e_vf *vf;
 	int ret = 0;
@@ -2138,7 +2158,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 		/* duplicate request, so just return success */
 		goto error_pvid;
 
-	if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) {
+	spin_lock_bh(&vsi->mac_filter_list_lock);
+	is_vsi_in_vlan = i40e_is_vsi_in_vlan(vsi);
+	spin_unlock_bh(&vsi->mac_filter_list_lock);
+
+	if (le16_to_cpu(vsi->info.pvid) == 0 && is_vsi_in_vlan) {
 		dev_err(&pf->pdev->dev,
 			"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
 			vf_id);

From d08f55585f22c38db5fcbed509a71d925e0509c1 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Wed, 16 Sep 2015 19:01:08 -0700
Subject: [PATCH 02/17] i40evf: fix overlong BIT defines

The defines from the RSS enabling call were mistakenly
missed in the patches to the i40e which should have been
to i40evf as well.

This is a follow up to (commit ed921559886dd40528) "fix
32 bit build warnings".

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40e_common.c |  5 -----
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h   | 14 +++++++-------
 2 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 7435fb396dcd..a4c5a49ddbcf 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -443,9 +443,6 @@ static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
 					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
 
-	cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)lut));
-	cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)lut));
-
 	status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL);
 
 	return status;
@@ -520,8 +517,6 @@ static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 					  I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
 					  I40E_AQC_SET_RSS_KEY_VSI_ID_MASK));
 	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID);
-	cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)key));
-	cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)key));
 
 	status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index c4f5a4eb2907..03275eb54cc4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -89,16 +89,16 @@ enum i40e_dyn_idx_t {
 	BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
 
 #define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \
-		BIT(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 #define i40e_pf_get_default_rss_hena(pf) \
 	(((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \
-		I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
+	  I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
 
 /* Supported Rx Buffer Sizes */
 #define I40E_RXBUFFER_512   512    /* Used for packet split */

From 07f89be81fa51ec85456559d7db9bc71379a20c1 Mon Sep 17 00:00:00 2001
From: Anjali Singhai <anjali.singhai@intel.com>
Date: Thu, 24 Sep 2015 15:26:32 -0700
Subject: [PATCH 03/17] i40e: Fix basic support for X722 devices

Acquire NVM, before issuing an AQ read nvm command for X722.
We need to acquire the NVM before issuing an AQ read to the NVM
otherwise we will get EBUSY from the FW. Also release when done.

This fixes the two X722 issues with respect to eeprom checksum verify
and reading NVM version info.

With this patch in place, i40e driver will provide basic support
for X722 devices.

Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_common.c |  3 ++
 drivers/net/ethernet/intel/i40e/i40e_nvm.c    | 31 +++++++++++++++----
 drivers/net/ethernet/intel/i40e/i40e_type.h   |  3 ++
 3 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index daa6b177fdb7..7f456e91cd93 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -958,6 +958,9 @@ i40e_status i40e_init_shared_code(struct i40e_hw *hw)
 	else
 		hw->pf_id = (u8)(func_rid & 0x7);
 
+	if (hw->mac.type == I40E_MAC_X722)
+		hw->flags |= I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE;
+
 	status = i40e_init_nvm(hw);
 	return status;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 875a8ccc2611..58e384a372a0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -290,9 +290,18 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset,
 i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 			       u16 *data)
 {
-	if (hw->mac.type == I40E_MAC_X722)
-		return i40e_read_nvm_word_aq(hw, offset, data);
-	return i40e_read_nvm_word_srctl(hw, offset, data);
+	enum i40e_status_code ret_code = 0;
+
+	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
+		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+		if (!ret_code) {
+			ret_code = i40e_read_nvm_word_aq(hw, offset, data);
+			i40e_release_nvm(hw);
+		}
+	} else {
+		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
+	}
+	return ret_code;
 }
 
 /**
@@ -397,9 +406,19 @@ static i40e_status i40e_read_nvm_buffer_aq(struct i40e_hw *hw, u16 offset,
 i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
 				 u16 *words, u16 *data)
 {
-	if (hw->mac.type == I40E_MAC_X722)
-		return i40e_read_nvm_buffer_aq(hw, offset, words, data);
-	return i40e_read_nvm_buffer_srctl(hw, offset, words, data);
+	enum i40e_status_code ret_code = 0;
+
+	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
+		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+		if (!ret_code) {
+			ret_code = i40e_read_nvm_buffer_aq(hw, offset, words,
+							   data);
+			i40e_release_nvm(hw);
+		}
+	} else {
+		ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data);
+	}
+	return ret_code;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 9c4a4573c28f..f631ca017d81 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -544,6 +544,9 @@ struct i40e_hw {
 	struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */
 	struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */
 
+#define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0)
+	u64 flags;
+
 	/* debug mask */
 	u32 debug_mask;
 	char err_str[16];

From 5d3465a1e4c01be455ef00834ec365e578942d67 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 29 Sep 2015 15:19:50 -0700
Subject: [PATCH 04/17] i40e/i40evf: use napi_schedule_irqoff()

The i40e_intr and i40e/i40evf_msix_clean_rings functions run from hard
interrupt context or with interrupts already disabled in netpoll.

They can use napi_schedule_irqoff() instead of napi_schedule()

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c     | 6 ++++--
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 36cca7b93f36..7d52092947dc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3267,7 +3267,7 @@ static irqreturn_t i40e_msix_clean_rings(int irq, void *data)
 	if (!q_vector->tx.ring && !q_vector->rx.ring)
 		return IRQ_HANDLED;
 
-	napi_schedule(&q_vector->napi);
+	napi_schedule_irqoff(&q_vector->napi);
 
 	return IRQ_HANDLED;
 }
@@ -3436,6 +3436,8 @@ static irqreturn_t i40e_intr(int irq, void *data)
 
 	/* only q0 is used in MSI/Legacy mode, and none are used in MSIX */
 	if (icr0 & I40E_PFINT_ICR0_QUEUE_0_MASK) {
+		struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+		struct i40e_q_vector *q_vector = vsi->q_vectors[0];
 
 		/* temporarily disable queue cause for NAPI processing */
 		u32 qval = rd32(hw, I40E_QINT_RQCTL(0));
@@ -3448,7 +3450,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 		wr32(hw, I40E_QINT_TQCTL(0), qval);
 
 		if (!test_bit(__I40E_DOWN, &pf->state))
-			napi_schedule(&pf->vsi[pf->lan_vsi]->q_vectors[0]->napi);
+			napi_schedule_irqoff(&q_vector->napi);
 	}
 
 	if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 4c4340cc4f45..1dd5245cbc94 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -334,7 +334,7 @@ static irqreturn_t i40evf_msix_clean_rings(int irq, void *data)
 	if (!q_vector->tx.ring && !q_vector->rx.ring)
 		return IRQ_HANDLED;
 
-	napi_schedule(&q_vector->napi);
+	napi_schedule_irqoff(&q_vector->napi);
 
 	return IRQ_HANDLED;
 }

From b9029e941dd66d2bc2ab529807a1eef4444f62f0 Mon Sep 17 00:00:00 2001
From: Mitch Williams <mitch.a.williams@intel.com>
Date: Mon, 28 Sep 2015 14:16:50 -0400
Subject: [PATCH 05/17] i40evf: don't give up

When the VF driver is unable to communicate with the PF, it just gives
up and never tries again. Aside from the obvious character flaw that
this shows, it's also a lousy user experience.

When PF communications fail, wait five seconds, and try again. And
again. Don't give up, little VF driver! Your prince will come!

Change-ID: Ia1378a39879883563b8faffce819f375821f9585
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1dd5245cbc94..ce997902f5a3 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2357,9 +2357,12 @@ static void i40evf_init_task(struct work_struct *work)
 err:
 	/* Things went into the weeds, so try again later */
 	if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) {
-		dev_err(&pdev->dev, "Failed to communicate with PF; giving up\n");
+		dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n");
 		adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
-		return; /* do not reschedule */
+		i40evf_shutdown_adminq(hw);
+		adapter->state = __I40EVF_STARTUP;
+		schedule_delayed_work(&adapter->init_task, HZ * 5);
+		return;
 	}
 	schedule_delayed_work(&adapter->init_task, HZ);
 }

From 8f5e39ce9214888464d34ef7949e56bdc999b46c Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 28 Sep 2015 14:16:51 -0400
Subject: [PATCH 06/17] i40e/i40evf: refactor IRQ enable function

This change moves a multi-line register setting into a function
which simplifies reading the flow of the enable function.

This also fixes a bug where the enable function was enabling
the interrupt twice while trying to update the two interrupt
throttle rate thresholds for Rx and Tx.

Change-ID: Ie308f9d0d48540204590cb9d7a5a7b1196f959bb
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 112 +++++++++++-------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 108 ++++++++++-------
 2 files changed, 128 insertions(+), 92 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 512707c2898e..889d25d6fde2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -815,6 +815,8 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
  * i40e_set_new_dynamic_itr - Find new ITR level
  * @rc: structure containing ring performance data
  *
+ * Returns true if ITR changed, false if not
+ *
  * Stores a new ITR value based on packets and byte counts during
  * the last interrupt.  The advantage of per interrupt computation
  * is faster updates and more accurate ITR for the current traffic
@@ -823,14 +825,14 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
  * testing data as well as attempting to minimize response time
  * while increasing bulk throughput.
  **/
-static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
+static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
 
 	if (rc->total_packets == 0 || !rc->itr)
-		return;
+		return false;
 
 	/* simple throttlerate management
 	 *   0-10MB/s   lowest (100000 ints/s)
@@ -874,11 +876,15 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		break;
 	}
 
-	if (new_itr != rc->itr)
-		rc->itr = new_itr;
-
 	rc->total_bytes = 0;
 	rc->total_packets = 0;
+
+	if (new_itr != rc->itr) {
+		rc->itr = new_itr;
+		return true;
+	}
+
+	return false;
 }
 
 /**
@@ -1747,6 +1753,21 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 	return total_rx_packets;
 }
 
+static u32 i40e_buildreg_itr(const int type, const u16 itr)
+{
+	u32 val;
+
+	val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
+	      I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
+	      (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
+	      (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
+
+	return val;
+}
+
+/* a small macro to shorten up some long lines */
+#define INTREG I40E_PFINT_DYN_CTLN
+
 /**
  * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt
  * @vsi: the VSI we care about
@@ -1757,54 +1778,53 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 					  struct i40e_q_vector *q_vector)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	u16 old_itr;
+	bool rx = false, tx = false;
+	u32 rxval, txval;
 	int vector;
-	u32 val;
 
 	vector = (q_vector->v_idx + vsi->base_vector);
+
+	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
+
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
-		old_itr = q_vector->rx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->rx);
-		if (old_itr != q_vector->rx.itr) {
-			val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-			I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
-			(I40E_RX_ITR <<
-				I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
-			(q_vector->rx.itr <<
-				I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
-		} else {
-			val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-			I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
-			(I40E_ITR_NONE <<
-				I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val);
-	} else {
-		i40e_irq_dynamic_enable(vsi, q_vector->v_idx);
+		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
+		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
 	}
+
 	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) {
-		old_itr = q_vector->tx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->tx);
-		if (old_itr != q_vector->tx.itr) {
-			val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-				I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
-				(I40E_TX_ITR <<
-				   I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) |
-				(q_vector->tx.itr <<
-				   I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT);
-		} else {
-			val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
-				I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
-				(I40E_ITR_NONE <<
-				   I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->v_idx +
-			      vsi->base_vector - 1), val);
-	} else {
-		i40e_irq_dynamic_enable(vsi, q_vector->v_idx);
+		tx = i40e_set_new_dynamic_itr(&q_vector->tx);
+		txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr);
 	}
+
+	if (rx || tx) {
+		/* get the higher of the two ITR adjustments and
+		 * use the same value for both ITR registers
+		 * when in adaptive mode (Rx and/or Tx)
+		 */
+		u16 itr = max(q_vector->tx.itr, q_vector->rx.itr);
+
+		q_vector->tx.itr = q_vector->rx.itr = itr;
+		txval = i40e_buildreg_itr(I40E_TX_ITR, itr);
+		tx = true;
+		rxval = i40e_buildreg_itr(I40E_RX_ITR, itr);
+		rx = true;
+	}
+
+	/* only need to enable the interrupt once, but need
+	 * to possibly update both ITR values
+	 */
+	if (rx) {
+		/* set the INTENA_MSK_MASK so that this first write
+		 * won't actually enable the interrupt, instead just
+		 * updating the ITR (it's bit 31 PF and VF)
+		 */
+		rxval |= BIT(31);
+		/* don't check _DOWN because interrupt isn't being enabled */
+		wr32(hw, INTREG(vector - 1), rxval);
+	}
+
+	if (!test_bit(__I40E_DOWN, &vsi->state))
+		wr32(hw, INTREG(vector - 1), txval);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 97493a4164eb..597e0964c232 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -318,6 +318,8 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector
  * i40e_set_new_dynamic_itr - Find new ITR level
  * @rc: structure containing ring performance data
  *
+ * Returns true if ITR changed, false if not
+ *
  * Stores a new ITR value based on packets and byte counts during
  * the last interrupt.  The advantage of per interrupt computation
  * is faster updates and more accurate ITR for the current traffic
@@ -326,14 +328,14 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector
  * testing data as well as attempting to minimize response time
  * while increasing bulk throughput.
  **/
-static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
+static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
 
 	if (rc->total_packets == 0 || !rc->itr)
-		return;
+		return false;
 
 	/* simple throttlerate management
 	 *   0-10MB/s   lowest (100000 ints/s)
@@ -377,11 +379,15 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		break;
 	}
 
-	if (new_itr != rc->itr)
-		rc->itr = new_itr;
-
 	rc->total_bytes = 0;
 	rc->total_packets = 0;
+
+	if (new_itr != rc->itr) {
+		rc->itr = new_itr;
+		return true;
+	}
+
+	return false;
 }
 
 /*
@@ -1187,6 +1193,21 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 	return total_rx_packets;
 }
 
+static u32 i40e_buildreg_itr(const int type, const u16 itr)
+{
+	u32 val;
+
+	val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
+	      I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
+	      (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
+	      (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
+
+	return val;
+}
+
+/* a small macro to shorten up some long lines */
+#define INTREG I40E_VFINT_DYN_CTLN1
+
 /**
  * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt
  * @vsi: the VSI we care about
@@ -1197,55 +1218,50 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 					  struct i40e_q_vector *q_vector)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	u16 old_itr;
+	bool rx = false, tx = false;
+	u32 rxval, txval;
 	int vector;
-	u32 val;
 
 	vector = (q_vector->v_idx + vsi->base_vector);
+	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
+
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
-		old_itr = q_vector->rx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->rx);
-		if (old_itr != q_vector->rx.itr) {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-			(I40E_RX_ITR <<
-				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
-			(q_vector->rx.itr <<
-				I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
-		} else {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-			(I40E_ITR_NONE <<
-				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
-	} else {
-		i40evf_irq_enable_queues(vsi->back, 1
-			<< q_vector->v_idx);
+		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
+		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
 	}
 	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) {
-		old_itr = q_vector->tx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->tx);
-		if (old_itr != q_vector->tx.itr) {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-				(I40E_TX_ITR <<
-				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
-				(q_vector->tx.itr <<
-				   I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
+		tx = i40e_set_new_dynamic_itr(&q_vector->tx);
+		txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr);
+	}
+	if (rx || tx) {
+		/* get the higher of the two ITR adjustments and
+		 * use the same value for both ITR registers
+		 * when in adaptive mode (Rx and/or Tx)
+		 */
+		u16 itr = max(q_vector->tx.itr, q_vector->rx.itr);
 
-		} else {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-				(I40E_ITR_NONE <<
-				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
-	} else {
-		i40evf_irq_enable_queues(vsi->back, BIT(q_vector->v_idx));
+		q_vector->tx.itr = q_vector->rx.itr = itr;
+		txval = i40e_buildreg_itr(I40E_TX_ITR, itr);
+		tx = true;
+		rxval = i40e_buildreg_itr(I40E_RX_ITR, itr);
+		rx = true;
 	}
+
+	/* only need to enable the interrupt once, but need
+	 * to possibly update both ITR values
+	 */
+	if (rx) {
+		/* set the INTENA_MSK_MASK so that this first write
+		 * won't actually enable the interrupt, instead just
+		 * updating the ITR (it's bit 31 PF and VF)
+		 */
+		rxval |= BIT(31);
+		/* don't check _DOWN because interrupt isn't being enabled */
+		wr32(hw, INTREG(vector - 1), rxval);
+	}
+
+	if (!test_bit(__I40E_DOWN, &vsi->state))
+		wr32(hw, INTREG(vector - 1), txval);
 }
 
 /**

From 51cc6d9fccde27310b7dfba2be268ff5b8dcf52d Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 28 Sep 2015 14:16:52 -0400
Subject: [PATCH 07/17] i40e/i40evf: fix bug in throttle rate math

The driver was using a value expressed in 2us increments
for the divisor to figure out our bytes/usec values.

Fix the usecs variable to contain a value in microseconds.

Change-ID: I5c20493103c295d6f201947bb908add7040b7c41
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 9 ++++++++-
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 9 ++++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 889d25d6fde2..c96e581cc2b7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -830,6 +830,7 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
+	int usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
@@ -838,8 +839,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 *   0-10MB/s   lowest (100000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
 	 *  20-1249MB/s bulk   (8000 ints/s)
+	 *
+	 * The math works out because the divisor is in 10^(-6) which
+	 * turns the bytes/us input value into MB/s values, but
+	 * make sure to use usecs, as the register values written
+	 * are in 2 usec increments in the ITR registers.
 	 */
-	bytes_per_int = rc->total_bytes / rc->itr;
+	usecs = (rc->itr << 1);
+	bytes_per_int = rc->total_bytes / usecs;
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 597e0964c232..7d98042338e0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -333,6 +333,7 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	enum i40e_latency_range new_latency_range = rc->latency_range;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
+	int usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
@@ -341,8 +342,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 *   0-10MB/s   lowest (100000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
 	 *  20-1249MB/s bulk   (8000 ints/s)
+	 *
+	 * The math works out because the divisor is in 10^(-6) which
+	 * turns the bytes/us input value into MB/s values, but
+	 * make sure to use usecs, as the register values written
+	 * are in 2 usec increments in the ITR registers.
 	 */
-	bytes_per_int = rc->total_bytes / rc->itr;
+	usecs = (rc->itr << 1);
+	bytes_per_int = rc->total_bytes / usecs;
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)

From c56625d59726ee2dc4dfd91c8b6c22098abe1ac4 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 28 Sep 2015 14:16:53 -0400
Subject: [PATCH 08/17] i40e/i40evf: change dynamic interrupt thresholds

The dynamic algorithm, while now working, doesn't have good
performance in 40G mode.

One part of this patch addresses the high CPU utilization of some small
streaming workloads that the driver should reduce CPU in.

It also changes the minimum ITR that the dynamic algorithm
will settle on, causing our minimum latency to go from 12us
to about 14us, when using adaptive mode.

It also changes the BULK interrupt rate to allow maximum throughput
on a 40Gb connection with a single thread of transmit, clamping
interrupt rate to 8000 for TX makes single thread traffic go too
slow.

The new ULTRA bulk setting is introduced and is used
when the Rx packet rate on this queue exceeds 40000 packets per
second.  This value of 40000 was chosen because the automatic tuning
of minimum ITR=20us means that a single queue can't quite achieve
that many packets per second from a round-robin test.

Change-ID: Icce8faa128688ca5fd2c4229bdd9726877a92ea2
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 27 ++++++++++++++-----
 drivers/net/ethernet/intel/i40e/i40e_txrx.h   |  3 +++
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 27 ++++++++++++++-----
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h |  3 +++
 4 files changed, 48 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c96e581cc2b7..7aea14389d7b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -828,6 +828,7 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
 static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
+	struct i40e_q_vector *qv = rc->ring->q_vector;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
 	int usecs;
@@ -836,9 +837,10 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		return false;
 
 	/* simple throttlerate management
-	 *   0-10MB/s   lowest (100000 ints/s)
+	 *   0-10MB/s   lowest (50000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
-	 *  20-1249MB/s bulk   (8000 ints/s)
+	 *  20-1249MB/s bulk   (18000 ints/s)
+	 *  > 40000 Rx packets per second (8000 ints/s)
 	 *
 	 * The math works out because the divisor is in 10^(-6) which
 	 * turns the bytes/us input value into MB/s values, but
@@ -859,24 +861,37 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
-		if (bytes_per_int <= 20)
-			new_latency_range = I40E_LOW_LATENCY;
-		break;
+	case I40E_ULTRA_LATENCY:
 	default:
 		if (bytes_per_int <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
+
+	/* this is to adjust RX more aggressively when streaming small
+	 * packets.  The value of 40000 was picked as it is just beyond
+	 * what the hardware can receive per second if in low latency
+	 * mode.
+	 */
+#define RX_ULTRA_PACKET_RATE 40000
+
+	if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) &&
+	    (&qv->rx == rc))
+		new_latency_range = I40E_ULTRA_LATENCY;
+
 	rc->latency_range = new_latency_range;
 
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		new_itr = I40E_ITR_100K;
+		new_itr = I40E_ITR_50K;
 		break;
 	case I40E_LOW_LATENCY:
 		new_itr = I40E_ITR_20K;
 		break;
 	case I40E_BULK_LATENCY:
+		new_itr = I40E_ITR_18K;
+		break;
+	case I40E_ULTRA_LATENCY:
 		new_itr = I40E_ITR_8K;
 		break;
 	default:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 7c0ed84b296d..0fe7eb77cae5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -32,7 +32,9 @@
 #define I40E_MAX_ITR               0x0FF0  /* reg uses 2 usec resolution */
 #define I40E_MIN_ITR               0x0001  /* reg uses 2 usec resolution */
 #define I40E_ITR_100K              0x0005
+#define I40E_ITR_50K               0x000A
 #define I40E_ITR_20K               0x0019
+#define I40E_ITR_18K               0x001B
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
@@ -296,6 +298,7 @@ enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
 	I40E_BULK_LATENCY = 2,
+	I40E_ULTRA_LATENCY = 3,
 };
 
 struct i40e_ring_container {
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 7d98042338e0..d76fe4a948df 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -331,6 +331,7 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector
 static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
+	struct i40e_q_vector *qv = rc->ring->q_vector;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
 	int usecs;
@@ -339,9 +340,10 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 		return false;
 
 	/* simple throttlerate management
-	 *   0-10MB/s   lowest (100000 ints/s)
+	 *   0-10MB/s   lowest (50000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
-	 *  20-1249MB/s bulk   (8000 ints/s)
+	 *  20-1249MB/s bulk   (18000 ints/s)
+	 *  > 40000 Rx packets per second (8000 ints/s)
 	 *
 	 * The math works out because the divisor is in 10^(-6) which
 	 * turns the bytes/us input value into MB/s values, but
@@ -362,24 +364,37 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
-		if (bytes_per_int <= 20)
-			new_latency_range = I40E_LOW_LATENCY;
-		break;
+	case I40E_ULTRA_LATENCY:
 	default:
 		if (bytes_per_int <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
+
+	/* this is to adjust RX more aggressively when streaming small
+	 * packets.  The value of 40000 was picked as it is just beyond
+	 * what the hardware can receive per second if in low latency
+	 * mode.
+	 */
+#define RX_ULTRA_PACKET_RATE 40000
+
+	if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) &&
+	    (&qv->rx == rc))
+		new_latency_range = I40E_ULTRA_LATENCY;
+
 	rc->latency_range = new_latency_range;
 
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		new_itr = I40E_ITR_100K;
+		new_itr = I40E_ITR_50K;
 		break;
 	case I40E_LOW_LATENCY:
 		new_itr = I40E_ITR_20K;
 		break;
 	case I40E_BULK_LATENCY:
+		new_itr = I40E_ITR_18K;
+		break;
+	case I40E_ULTRA_LATENCY:
 		new_itr = I40E_ITR_8K;
 		break;
 	default:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 03275eb54cc4..e2352b886b77 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -32,7 +32,9 @@
 #define I40E_MAX_ITR               0x0FF0  /* reg uses 2 usec resolution */
 #define I40E_MIN_ITR               0x0001  /* reg uses 2 usec resolution */
 #define I40E_ITR_100K              0x0005
+#define I40E_ITR_50K               0x000A
 #define I40E_ITR_20K               0x0019
+#define I40E_ITR_18K               0x001B
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
@@ -291,6 +293,7 @@ enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
 	I40E_BULK_LATENCY = 2,
+	I40E_ULTRA_LATENCY = 3,
 };
 
 struct i40e_ring_container {

From ee2319cf17ee64bbd0096f2f8f3f8390c93b1e39 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 28 Sep 2015 14:16:54 -0400
Subject: [PATCH 09/17] i40e/i40evf: adjust interrupt throttle less frequently

The adaptive ITR (interrupt throttle rate) algorithm was adjusting
the hardware's interrupt rate too frequently.  This caused a lot
of variation in the interrupt rate for fairly constant workloads.

Change the code to have a counter and adjust only once every N
number of interrupts.

Change-ID: I0460f1f86571037484eca5aca36ac4d889cb8389
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h        |  2 ++
 drivers/net/ethernet/intel/i40e/i40e_main.c   |  2 ++
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 22 ++++++++++++++++--
 drivers/net/ethernet/intel/i40e/i40e_txrx.h   |  4 ++--
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 23 +++++++++++++++++--
 drivers/net/ethernet/intel/i40evf/i40e_txrx.h |  4 ++--
 drivers/net/ethernet/intel/i40evf/i40evf.h    |  2 ++
 .../net/ethernet/intel/i40evf/i40evf_main.c   |  2 ++
 8 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index b7818be0f06d..7c2b2e891f62 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -577,6 +577,8 @@ struct i40e_q_vector {
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
+#define ITR_COUNTDOWN_START 100
+	u8 itr_countdown;	/* when 0 should adjust ITR */
 } ____cacheline_internodealigned_in_smp;
 
 /* lan device */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7d52092947dc..e0142de018e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3087,6 +3087,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
 		struct i40e_q_vector *q_vector = vsi->q_vectors[i];
 
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
 		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
 		q_vector->rx.latency_range = I40E_LOW_LATENCY;
 		wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
@@ -3182,6 +3183,7 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 	u32 val;
 
 	/* set the ITR configuration */
+	q_vector->itr_countdown = ITR_COUNTDOWN_START;
 	q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
 	q_vector->rx.latency_range = I40E_LOW_LATENCY;
 	wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 7aea14389d7b..006f0fb4720c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -845,10 +845,12 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 * The math works out because the divisor is in 10^(-6) which
 	 * turns the bytes/us input value into MB/s values, but
 	 * make sure to use usecs, as the register values written
-	 * are in 2 usec increments in the ITR registers.
+	 * are in 2 usec increments in the ITR registers, and make sure
+	 * to use the smoothed values that the countdown timer gives us.
 	 */
-	usecs = (rc->itr << 1);
+	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
 	bytes_per_int = rc->total_bytes / usecs;
+
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
@@ -1806,8 +1808,17 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 
 	vector = (q_vector->v_idx + vsi->base_vector);
 
+	/* avoid dynamic calculation if in countdown mode OR if
+	 * all dynamic is disabled
+	 */
 	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
 
+	if (q_vector->itr_countdown > 0 ||
+	    (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) &&
+	     !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) {
+		goto enable_int;
+	}
+
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
 		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
 		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
@@ -1845,8 +1856,15 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 		wr32(hw, INTREG(vector - 1), rxval);
 	}
 
+enable_int:
 	if (!test_bit(__I40E_DOWN, &vsi->state))
 		wr32(hw, INTREG(vector - 1), txval);
+
+	if (q_vector->itr_countdown)
+		q_vector->itr_countdown--;
+	else
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 0fe7eb77cae5..6779fb771d6a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -38,8 +38,8 @@
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
-#define I40E_ITR_RX_DEF            I40E_ITR_8K
-#define I40E_ITR_TX_DEF            I40E_ITR_4K
+#define I40E_ITR_RX_DEF            I40E_ITR_20K
+#define I40E_ITR_TX_DEF            I40E_ITR_20K
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index d76fe4a948df..47e9a90d6b10 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -348,10 +348,12 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 * The math works out because the divisor is in 10^(-6) which
 	 * turns the bytes/us input value into MB/s values, but
 	 * make sure to use usecs, as the register values written
-	 * are in 2 usec increments in the ITR registers.
+	 * are in 2 usec increments in the ITR registers, and make sure
+	 * to use the smoothed values that the countdown timer gives us.
 	 */
-	usecs = (rc->itr << 1);
+	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
 	bytes_per_int = rc->total_bytes / usecs;
+
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
@@ -1245,8 +1247,18 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	int vector;
 
 	vector = (q_vector->v_idx + vsi->base_vector);
+
+	/* avoid dynamic calculation if in countdown mode OR if
+	 * all dynamic is disabled
+	 */
 	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
 
+	if (q_vector->itr_countdown > 0 ||
+	    (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) &&
+	     !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) {
+		goto enable_int;
+	}
+
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
 		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
 		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
@@ -1282,8 +1294,15 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 		wr32(hw, INTREG(vector - 1), rxval);
 	}
 
+enable_int:
 	if (!test_bit(__I40E_DOWN, &vsi->state))
 		wr32(hw, INTREG(vector - 1), txval);
+
+	if (q_vector->itr_countdown)
+		q_vector->itr_countdown--;
+	else
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index e2352b886b77..ebc1bf77f036 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -38,8 +38,8 @@
 #define I40E_ITR_8K                0x003E
 #define I40E_ITR_4K                0x007A
 #define I40E_MAX_INTRL             0x3B    /* reg uses 4 usec resolution */
-#define I40E_ITR_RX_DEF            I40E_ITR_8K
-#define I40E_ITR_TX_DEF            I40E_ITR_4K
+#define I40E_ITR_RX_DEF            I40E_ITR_20K
+#define I40E_ITR_TX_DEF            I40E_ITR_20K
 #define I40E_ITR_DYNAMIC           0x8000  /* use top bit as a flag */
 #define I40E_MIN_INT_RATE          250     /* ~= 1000000 / (I40E_MAX_ITR * 2) */
 #define I40E_MAX_INT_RATE          500000  /* == 1000000 / (I40E_MIN_ITR * 2) */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 22841c619f37..22fc3d49c4b9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -112,6 +112,8 @@ struct i40e_q_vector {
 	struct i40e_ring_container tx;
 	u32 ring_mask;
 	u8 num_ringpairs;	/* total number of ring pairs in vector */
+#define ITR_COUNTDOWN_START 100
+	u8 itr_countdown;	/* when 0 or 1 update ITR */
 	int v_idx;	  /* vector index in list */
 	char name[IFNAMSIZ + 9];
 	bool arm_wb_state;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index ce997902f5a3..a44a42bb83c0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -357,6 +357,7 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx)
 	q_vector->rx.ring = rx_ring;
 	q_vector->rx.count++;
 	q_vector->rx.latency_range = I40E_LOW_LATENCY;
+	q_vector->itr_countdown = ITR_COUNTDOWN_START;
 }
 
 /**
@@ -377,6 +378,7 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
 	q_vector->tx.ring = tx_ring;
 	q_vector->tx.count++;
 	q_vector->tx.latency_range = I40E_LOW_LATENCY;
+	q_vector->itr_countdown = ITR_COUNTDOWN_START;
 	q_vector->num_ringpairs++;
 	q_vector->ring_mask |= BIT(t_idx);
 }

From bcab2db97d2423b97b248ba35eb2277168e71fcc Mon Sep 17 00:00:00 2001
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
Date: Mon, 28 Sep 2015 14:16:55 -0400
Subject: [PATCH 10/17] i40e: Fix for Tools loopback test failing after driver
 load

This patch fixes a problem where our Tools MAC Loopback test, after
driver unbind would fail.  This was because the hw was configured
for multiqueue and unbind operation did not clear this configuration.
The problem is fixed by resetting this configuration in i40e_remove.

Change-ID: I130c05138319182ed1476d3a0b5222d6a6320af9
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e0142de018e6..5157be51e829 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10630,6 +10630,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 static void i40e_remove(struct pci_dev *pdev)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
+	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret_code;
 	int i;
 
@@ -10637,6 +10638,10 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	i40e_ptp_stop(pf);
 
+	/* Disable RSS in hw */
+	wr32(hw, I40E_PFQF_HENA(0), 0);
+	wr32(hw, I40E_PFQF_HENA(1), 0);
+
 	/* no more scheduling of any task */
 	set_bit(__I40E_DOWN, &pf->state);
 	del_timer_sync(&pf->service_timer);

From 8589af70d0879a68c93ef77505a6234d22b1b1a7 Mon Sep 17 00:00:00 2001
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
Date: Mon, 28 Sep 2015 14:16:56 -0400
Subject: [PATCH 11/17] i40e: fix for PHY NVM interaction problem

This patch fixes a problem where the NVMUpdate Tool, when using the PHY
NVM feature, gets bad data from the PHY because of contention on the
MDIO interface from get PHY capability calls from the driver during
regular operations.  The problem is fixed by adding a check if media
is available before calling get PHY capability function because that
bit is not set when device is in PHY interaction mode.

Change-ID: Ib89991b0f841808dd92410f5e8683d6ee3301cd0
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_common.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 7f456e91cd93..c51f2fb94716 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -2278,13 +2278,15 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw)
 	if (status)
 		return status;
 
-	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
-					      NULL);
-	if (status)
-		return status;
+	if (hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) {
+		status = i40e_aq_get_phy_capabilities(hw, false, false,
+						      &abilities, NULL);
+		if (status)
+			return status;
 
-	memcpy(hw->phy.link_info.module_type, &abilities.module_type,
-	       sizeof(hw->phy.link_info.module_type));
+		memcpy(hw->phy.link_info.module_type, &abilities.module_type,
+		       sizeof(hw->phy.link_info.module_type));
+	}
 
 	return status;
 }

From a03dc368547a7a4e9fcedc6f64dd64a9ff5e0593 Mon Sep 17 00:00:00 2001
From: Anjali Singhai Jain <anjali.singhai@intel.com>
Date: Mon, 28 Sep 2015 14:16:57 -0400
Subject: [PATCH 12/17] i40e/i40evf: Fix an accidental error with BIT_ULL
 replacement

A mask value of 0x1FF was accidentally replaced with a bit mask
causing flow director sideband to be broken.

Change-ID: Id3387f67dd1b567b41692b570b383c58671e1eae
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_type.h   | 4 ++--
 drivers/net/ethernet/intel/i40evf/i40e_type.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index f631ca017d81..dd2da356d9a1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1068,8 +1068,8 @@ enum i40e_filter_program_desc_fd_status {
 };
 
 #define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT	23
-#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK \
-				       BIT_ULL(I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
+#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK	(0x1FFUL << \
+					 I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
 
 #define I40E_TXD_FLTR_QW1_CMD_SHIFT	4
 #define I40E_TXD_FLTR_QW1_CMD_MASK	(0xFFFFULL << \
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 85af3b48effc..301fe2b6dd03 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -1055,8 +1055,8 @@ enum i40e_filter_program_desc_fd_status {
 };
 
 #define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT	23
-#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK \
-				       BIT_ULL(I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
+#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK	(0x1FFUL << \
+					 I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
 
 #define I40E_TXD_FLTR_QW1_CMD_SHIFT	4
 #define I40E_TXD_FLTR_QW1_CMD_MASK	(0xFFFFULL << \

From 3ce12ee9d8f9ae245f38e6acbd32625d8e002c5b Mon Sep 17 00:00:00 2001
From: Catherine Sullivan <catherine.sullivan@intel.com>
Date: Mon, 28 Sep 2015 14:16:58 -0400
Subject: [PATCH 13/17] i40e: Fix order of checks when enabling/disabling
 autoneg in ethtool

We were previously checking if autoneg was allowed to change before
checking if autoneg was changing. We need to do this in the other order
or else we will erroneously return EINVAL when autoneg is not changing.

Change-ID: Iff9f7d1c9bddc1ad1e5d227d4f42754f90155410
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_ethtool.c    | 29 ++++++++++---------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 767b1db1005f..6e5f9314994b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -661,28 +661,31 @@ static int i40e_set_settings(struct net_device *netdev,
 
 	/* Check autoneg */
 	if (autoneg == AUTONEG_ENABLE) {
-		/* If autoneg is not supported, return error */
-		if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) {
-			netdev_info(netdev, "Autoneg not supported on this phy\n");
-			return -EINVAL;
-		}
 		/* If autoneg was not already enabled */
 		if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) {
+			/* If autoneg is not supported, return error */
+			if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) {
+				netdev_info(netdev, "Autoneg not supported on this phy\n");
+				return -EINVAL;
+			}
+			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities |
 					   I40E_AQ_PHY_ENABLE_AN;
 			change = true;
 		}
 	} else {
-		/* If autoneg is supported 10GBASE_T is the only phy that
-		 * can disable it, so otherwise return error
-		 */
-		if (safe_ecmd.supported & SUPPORTED_Autoneg &&
-		    hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) {
-			netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
-			return -EINVAL;
-		}
 		/* If autoneg is currently enabled */
 		if (hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED) {
+			/* If autoneg is supported 10GBASE_T is the only PHY
+			 * that can disable it, so otherwise return error
+			 */
+			if (safe_ecmd.supported & SUPPORTED_Autoneg &&
+			    hw->phy.link_info.phy_type !=
+			    I40E_PHY_TYPE_10GBASE_T) {
+				netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
+				return -EINVAL;
+			}
+			/* Autoneg is allowed to change */
 			config.abilities = abilities.abilities &
 					   ~I40E_AQ_PHY_ENABLE_AN;
 			change = true;

From 52e9689e4ef070eff1e0f9e6e84a8451b86813b5 Mon Sep 17 00:00:00 2001
From: Catherine Sullivan <catherine.sullivan@intel.com>
Date: Mon, 28 Sep 2015 14:16:59 -0400
Subject: [PATCH 14/17] i40e: Move error message to debug level

There is an error coming back from get_phy_capabilities that does not
seem to have any functional implications. We will continue looking into
why this error message is occurring, but in the meantime, we will move it
to debug to avoid confusion.

Change-ID: I9091754bf62c066ddedeb249923d85606e2d68ed
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 6e5f9314994b..8fd26fdd7705 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -751,9 +751,9 @@ static int i40e_set_settings(struct net_device *netdev,
 
 		status = i40e_update_link_info(hw);
 		if (status)
-			netdev_info(netdev, "Updating link info failed with err %s aq_err %s\n",
-				    i40e_stat_str(hw, status),
-				    i40e_aq_str(hw, hw->aq.asq_last_status));
+			netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n",
+				   i40e_stat_str(hw, status),
+				   i40e_aq_str(hw, hw->aq.asq_last_status));
 
 	} else {
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");

From 2bc11c634eaebb936345b136a196f555045a47ea Mon Sep 17 00:00:00 2001
From: Jean Sacren <sakiwit@gmail.com>
Date: Sat, 19 Sep 2015 05:08:43 -0600
Subject: [PATCH 15/17] i40e: fix kernel-doc argument name

The second argument name in the kernel-doc argument list for
i40e_features_check() was slightly off. Fix it for the kernel doc.

Signed-off-by: Jean Sacren <sakiwit@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5157be51e829..96b9385be469 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8542,7 +8542,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 /**
  * i40e_features_check - Validate encapsulated packet conforms to limits
  * @skb: skb buff
- * @netdev: This physical port's netdev
+ * @dev: This physical port's netdev
  * @features: Offload features that the stack believes apply
  **/
 static netdev_features_t i40e_features_check(struct sk_buff *skb,

From 6f66a484f1ff644b4600368fe3091e31b65d3c50 Mon Sep 17 00:00:00 2001
From: Jean Sacren <sakiwit@gmail.com>
Date: Sat, 19 Sep 2015 05:08:45 -0600
Subject: [PATCH 16/17] i40e: declare rather than initialize int object

'err' would be overwritten immediately, so we should declare it only
rather than initialize it to zero.

Signed-off-by: Jean Sacren <sakiwit@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 96b9385be469..f0ba384a0291 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10159,7 +10159,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	static u16 pfs_found;
 	u16 wol_nvm_bits;
 	u16 link_status;
-	int err = 0;
+	int err;
 	u32 len;
 	u32 i;
 

From a1f192cf70b187ab01b8b03cdeea82b8820c927a Mon Sep 17 00:00:00 2001
From: Catherine Sullivan <catherine.sullivan@intel.com>
Date: Mon, 28 Sep 2015 14:17:00 -0400
Subject: [PATCH 17/17] i40e/i40evf: Bump i40e to 1.3.38 and i40evf to 1.3.25

Bump.

Change-ID: Id0a7ecaa491f88ce94c9eba4901e592a56044ee0
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c     | 2 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f0ba384a0291..69e9c3e2def7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 34
+#define DRV_VERSION_BUILD 38
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index a44a42bb83c0..10b2a4a33c68 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf";
 static const char i40evf_driver_string[] =
 	"Intel(R) XL710/X710 Virtual Function Network Driver";
 
-#define DRV_VERSION "1.3.21"
+#define DRV_VERSION "1.3.25"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2015 Intel Corporation.";