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

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2015-10-23

This series contains updates to i40e, i40evf, if_link, ixgbe and ixgbevf.

Anjali adds a workaround to drop any flow control frames from being
transmitted from any VSI, so that a malicious VF cannot send flow control
or PFC packets out on the wire.  Also fixed a bug in debugfs by grabbing
the filter list lock before adding or deleting a filter.

Akeem fixes an issue where we were unconditionally returning VEB bridge
mode before allowing LB in the add VSI routine, resolve by checking if
the bridge is actually in VEB mode first.

Mitch fixed an issue where the incorrect structure was being used for
VLAN filter list, which meant the VLAN filter list did not get
processed correctly and VLAN filters would not be re-enabled after any
kind of reset.

Helin fixed a problem of possibly getting inconsistent flow control
status after a PF reset.  The issue was requested_mode was being set
with a default value during probe, but the hardware state could be a
different value from this mode.

Carolyn fixed a problem where the driver output of the OEM version
string varied from the other tools.

Jean Sacren fixes up kernel documentation by fixing function header
comments to match actual variables used in the functions.  Also
cleaned up variable initialization, when the variable would be
over-written immediately.

Hiroshi Shimanoto provides three patches to add "trusted" VF by adding
netlink directives and an NDO entry.  Then implement these new controls
in ixgbe and ixgbevf.  This series has gone through several iterations
to address all the suggested community changes and concerns.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -109,8 +109,10 @@
 #define I40E_NVM_VERSION_LO_MASK   (0xff << I40E_NVM_VERSION_LO_SHIFT)
 #define I40E_NVM_VERSION_HI_SHIFT  12
 #define I40E_NVM_VERSION_HI_MASK   (0xf << I40E_NVM_VERSION_HI_SHIFT)
-#define I40E_OEM_VER_BUILD_MASK    0xff00
+#define I40E_OEM_VER_BUILD_MASK    0xffff
 #define I40E_OEM_VER_PATCH_MASK    0xff
+#define I40E_OEM_VER_BUILD_SHIFT   8
+#define I40E_OEM_VER_SHIFT         24
 
 /* The values in here are decimal coded as hex as is the case in the NVM map*/
 #define I40E_CURRENT_NVM_VERSION_HI 0x2
@@ -594,6 +596,15 @@ struct i40e_device {
 static inline char *i40e_nvm_version_str(struct i40e_hw *hw)
 {
 	static char buf[32];
+	u32 full_ver;
+	u8 ver, patch;
+	u16 build;
+
+	full_ver = hw->nvm.oem_ver;
+	ver = (u8)(full_ver >> I40E_OEM_VER_SHIFT);
+	build = (u16)((full_ver >> I40E_OEM_VER_BUILD_SHIFT)
+		 & I40E_OEM_VER_BUILD_MASK);
+	patch = (u8)(full_ver & I40E_OEM_VER_PATCH_MASK);
 
 	snprintf(buf, sizeof(buf),
 		 "%x.%02x 0x%x %d.%d.%d",
@@ -601,9 +612,7 @@ static inline char *i40e_nvm_version_str(struct i40e_hw *hw)
 			I40E_NVM_VERSION_HI_SHIFT,
 		 (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >>
 			I40E_NVM_VERSION_LO_SHIFT,
-		 hw->nvm.eetrack, (hw->nvm.oem_ver >> 24),
-		 (hw->nvm.oem_ver & I40E_OEM_VER_BUILD_MASK) >> 8,
-		 hw->nvm.oem_ver & I40E_OEM_VER_PATCH_MASK);
+		 hw->nvm.eetrack, ver, build, patch);
 
 	return buf;
 }

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

@@ -331,25 +331,11 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 			len = buf_len;
 		/* write the full 16-byte chunks */
 		for (i = 0; i < (len - 16); i += 16)
-			i40e_debug(hw, mask,
-				   "\t0x%04X  %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-				   i, buf[i], buf[i + 1], buf[i + 2],
-				   buf[i + 3], buf[i + 4], buf[i + 5],
-				   buf[i + 6], buf[i + 7], buf[i + 8],
-				   buf[i + 9], buf[i + 10], buf[i + 11],
-				   buf[i + 12], buf[i + 13], buf[i + 14],
-				   buf[i + 15]);
+			i40e_debug(hw, mask, "\t0x%04X  %16ph\n", i, buf + i);
 		/* write whatever's left over without overrunning the buffer */
-		if (i < len) {
-			char d_buf[80];
-			int j = 0;
-
-			memset(d_buf, 0, sizeof(d_buf));
-			j += sprintf(d_buf, "\t0x%04X ", i);
-			while (i < len)
-				j += sprintf(&d_buf[j], " %02X", buf[i++]);
-			i40e_debug(hw, mask, "%s\n", d_buf);
-		}
+		if (i < len)
+			i40e_debug(hw, mask, "\t0x%04X  %*ph\n",
+					     i, len - i, buf + i);
 	}
 }
 
@@ -3828,6 +3814,28 @@ i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
 	return status;
 }
 
+/**
+ * i40e_add_filter_to_drop_tx_flow_control_frames- filter to drop flow control
+ * @hw: pointer to the hw struct
+ * @seid: VSI seid to add ethertype filter from
+ **/
+#define I40E_FLOW_CONTROL_ETHTYPE 0x8808
+void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
+						    u16 seid)
+{
+	u16 flag = I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC |
+		   I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP |
+		   I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX;
+	u16 ethtype = I40E_FLOW_CONTROL_ETHTYPE;
+	i40e_status status;
+
+	status = i40e_aq_add_rem_control_packet_filter(hw, NULL, ethtype, flag,
+						       seid, 0, true, NULL,
+						       NULL);
+	if (status)
+		hw_dbg(hw, "Ethtype Filter Add failed: Error pruning Tx flow control frames\n");
+}
+
 /**
  * i40e_aq_alternate_read
  * @hw: pointer to the hardware structure

drivers/net/ethernet/intel/i40e/i40e_debugfs.c

@@ -1137,7 +1137,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			goto command_write_done;
 		}
 
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		f = i40e_add_filter(vsi, ma, vlan, false, false);
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 		ret = i40e_sync_vsi_filters(vsi, true);
 		if (f && !ret)
 			dev_info(&pf->pdev->dev,
@@ -1174,7 +1176,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			goto command_write_done;
 		}
 
+		spin_lock_bh(&vsi->mac_filter_list_lock);
 		i40e_del_filter(vsi, ma, vlan, false, false);
+		spin_unlock_bh(&vsi->mac_filter_list_lock);
 		ret = i40e_sync_vsi_filters(vsi, true);
 		if (!ret)
 			dev_info(&pf->pdev->dev,

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 38
+#define DRV_VERSION_BUILD 46
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -6837,6 +6837,15 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
 		ret = i40e_setup_misc_vector(pf);
 
+	/* Add a filter to drop all Flow control frames from any VSI from being
+	 * transmitted. By doing so we stop a malicious VF from sending out
+	 * PAUSE or PFC frames and potentially controlling traffic for other
+	 * PF/VF VSIs.
+	 * The FW can still send Flow control frames if enabled.
+	 */
+	i40e_add_filter_to_drop_tx_flow_control_frames(&pf->hw,
+						       pf->main_vsi_seid);
+
 	/* restart the VSIs that were rebuilt and running before the reset */
 	i40e_pf_unquiesce_all_vsi(pf);
 
@@ -8732,12 +8741,22 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi)
 		return 1;
 
 	veb = pf->veb[vsi->veb_idx];
+	if (!veb) {
+		dev_info(&pf->pdev->dev,
+			 "There is no veb associated with the bridge\n");
+		return -ENOENT;
+	}
+
 	/* Uplink is a bridge in VEPA mode */
-	if (veb && (veb->bridge_mode & BRIDGE_MODE_VEPA))
+	if (veb->bridge_mode & BRIDGE_MODE_VEPA) {
 		return 0;
+	} else {
+		/* Uplink is a bridge in VEB mode */
+		return 1;
+	}
 
-	/* Uplink is a bridge in VEB mode */
-	return 1;
+	/* VEPA is now default bridge, so return 0 */
+	return 0;
 }
 
 /**
@@ -10164,6 +10183,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int err;
 	u32 len;
 	u32 i;
+	u8 set_fc_aq_fail;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
@@ -10428,6 +10448,25 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
 		goto err_vsis;
 	}
+
+	/* Make sure flow control is set according to current settings */
+	err = i40e_set_fc(hw, &set_fc_aq_fail, true);
+	if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_GET)
+		dev_dbg(&pf->pdev->dev,
+			"Set fc with err %s aq_err %s on get_phy_cap\n",
+			i40e_stat_str(hw, err),
+			i40e_aq_str(hw, hw->aq.asq_last_status));
+	if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_SET)
+		dev_dbg(&pf->pdev->dev,
+			"Set fc with err %s aq_err %s on set_phy_config\n",
+			i40e_stat_str(hw, err),
+			i40e_aq_str(hw, hw->aq.asq_last_status));
+	if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_UPDATE)
+		dev_dbg(&pf->pdev->dev,
+			"Set fc with err %s aq_err %s on get_link_info\n",
+			i40e_stat_str(hw, err),
+			i40e_aq_str(hw, hw->aq.asq_last_status));
+
 	/* if FDIR VSI was set up, start it now */
 	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
@@ -10585,6 +10624,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 	pf->hw.phy.phy_types = le32_to_cpu(abilities.phy_type);
 
+	/* Add a filter to drop all Flow control frames from any VSI from being
+	 * transmitted. By doing so we stop a malicious VF from sending out
+	 * PAUSE or PFC frames and potentially controlling traffic for other
+	 * PF/VF VSIs.
+	 * The FW can still send Flow control frames if enabled.
+	 */
+	i40e_add_filter_to_drop_tx_flow_control_frames(&pf->hw,
+						       pf->main_vsi_seid);
+
 	/* print a string summarizing features */
 	i40e_print_features(pf);
 

drivers/net/ethernet/intel/i40e/i40e_nvm.c

@@ -484,7 +484,7 @@ static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer,
 static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw,
 						    u16 *checksum)
 {
-	i40e_status ret_code = 0;
+	i40e_status ret_code;
 	struct i40e_virt_mem vmem;
 	u16 pcie_alt_module = 0;
 	u16 checksum_local = 0;
@@ -564,15 +564,16 @@ static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw,
  **/
 i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw)
 {
-	i40e_status ret_code = 0;
+	i40e_status ret_code;
 	u16 checksum;
 	__le16 le_sum;
 
 	ret_code = i40e_calc_nvm_checksum(hw, &checksum);
-	le_sum = cpu_to_le16(checksum);
-	if (!ret_code)
+	if (!ret_code) {
+		le_sum = cpu_to_le16(checksum);
 		ret_code = i40e_write_nvm_aq(hw, 0x00, I40E_SR_SW_CHECKSUM_WORD,
 					     1, &le_sum, true);
+	}
 
 	return ret_code;
 }

drivers/net/ethernet/intel/i40e/i40e_prototype.h

@@ -322,4 +322,6 @@ i40e_status i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 			       void *buff, u16 *ret_buff_size,
 			       u8 *ret_next_table, u32 *ret_next_index,
 			       struct i40e_asq_cmd_details *cmd_details);
+void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
+						    u16 vsi_seid);
 #endif /* _I40E_PROTOTYPE_H_ */

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

@@ -2187,6 +2187,7 @@ static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
  * @hdr_len:  ptr to the size of the packet header
+ * @cd_type_cmd_tso_mss: ptr to u64 object
  * @cd_tunneling: ptr to context descriptor bits
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
@@ -2246,6 +2247,7 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
  * @tx_flags: the collected send information
+ * @cd_type_cmd_tso_mss: ptr to u64 object
  *
  * Returns 0 if no Tx timestamp can happen and 1 if the timestamp will happen
  **/
@@ -2288,6 +2290,7 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
+ * @tx_ring: Tx descriptor ring
  * @cd_tunneling: ptr to context desc bits
  **/
 static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,

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

@@ -944,6 +944,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 	if (pci_num_vf(pf->pdev) != num_alloc_vfs) {
 		ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
 		if (ret) {
+			pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
 			pf->num_alloc_vfs = 0;
 			goto err_iov;
 		}

drivers/net/ethernet/intel/i40evf/i40e_common.c

@@ -331,25 +331,11 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 			len = buf_len;
 		/* write the full 16-byte chunks */
 		for (i = 0; i < (len - 16); i += 16)
-			i40e_debug(hw, mask,
-				   "\t0x%04X  %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-				   i, buf[i], buf[i + 1], buf[i + 2],
-				   buf[i + 3], buf[i + 4], buf[i + 5],
-				   buf[i + 6], buf[i + 7], buf[i + 8],
-				   buf[i + 9], buf[i + 10], buf[i + 11],
-				   buf[i + 12], buf[i + 13], buf[i + 14],
-				   buf[i + 15]);
+			i40e_debug(hw, mask, "\t0x%04X  %16ph\n", i, buf + i);
 		/* write whatever's left over without overrunning the buffer */
-		if (i < len) {
-			char d_buf[80];
-			int j = 0;
-
-			memset(d_buf, 0, sizeof(d_buf));
-			j += sprintf(d_buf, "\t0x%04X ", i);
-			while (i < len)
-				j += sprintf(&d_buf[j], " %02X", buf[i++]);
-			i40e_debug(hw, mask, "%s\n", d_buf);
-		}
+		if (i < len)
+			i40e_debug(hw, mask, "\t0x%04X  %*ph\n",
+					     i, len - i, buf + i);
 	}
 }
 

drivers/net/ethernet/intel/i40evf/i40e_prototype.h

@@ -101,4 +101,6 @@ i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
 				u16 vsi_seid, u16 queue, bool is_add,
 				struct i40e_control_filter_stats *stats,
 				struct i40e_asq_cmd_details *cmd_details);
+void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
+						    u16 vsi_seid);
 #endif /* _I40E_PROTOTYPE_H_ */

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 "1.3.25"
+#define DRV_VERSION "1.3.33"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2015 Intel Corporation.";
@@ -282,6 +282,7 @@ static void i40evf_fire_sw_int(struct i40evf_adapter *adapter, u32 mask)
 /**
  * i40evf_irq_enable - Enable default interrupt generation settings
  * @adapter: board private structure
+ * @flush: boolean value whether to run rd32()
  **/
 void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush)
 {
@@ -305,15 +306,14 @@ static irqreturn_t i40evf_msix_aq(int irq, void *data)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40e_hw *hw = &adapter->hw;
 	u32 val;
-	u32 ena_mask;
 
 	/* handle non-queue interrupts */
-	val = rd32(hw, I40E_VFINT_ICR01);
-	ena_mask = rd32(hw, I40E_VFINT_ICR0_ENA1);
+	rd32(hw, I40E_VFINT_ICR01);
+	rd32(hw, I40E_VFINT_ICR0_ENA1);
 
 
-	val = rd32(hw, I40E_VFINT_DYN_CTL01);
-	val = val | I40E_VFINT_DYN_CTL01_CLEARPBA_MASK;
+	val = rd32(hw, I40E_VFINT_DYN_CTL01) |
+	      I40E_VFINT_DYN_CTL01_CLEARPBA_MASK;
 	wr32(hw, I40E_VFINT_DYN_CTL01, val);
 
 	/* schedule work on the private workqueue */
@@ -1609,6 +1609,7 @@ static void i40evf_reset_task(struct work_struct *work)
 						      reset_task);
 	struct net_device *netdev = adapter->netdev;
 	struct i40e_hw *hw = &adapter->hw;
+	struct i40evf_vlan_filter *vlf;
 	struct i40evf_mac_filter *f;
 	u32 reg_val;
 	int i = 0, err;
@@ -1732,8 +1733,8 @@ static void i40evf_reset_task(struct work_struct *work)
 		f->add = true;
 	}
 	/* re-add all VLAN filters */
-	list_for_each_entry(f, &adapter->vlan_filter_list, list) {
-		f->add = true;
+	list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
+		vlf->add = true;
 	}
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;

drivers/net/ethernet/intel/ixgbe/ixgbe.h

@@ -152,9 +152,17 @@ struct vf_data_storage {
 	u16 vlan_count;
 	u8 spoofchk_enabled;
 	bool rss_query_enabled;
+	u8 trusted;
+	int xcast_mode;
 	unsigned int vf_api;
 };
 
+enum ixgbevf_xcast_modes {
+	IXGBEVF_XCAST_MODE_NONE = 0,
+	IXGBEVF_XCAST_MODE_MULTI,
+	IXGBEVF_XCAST_MODE_ALLMULTI,
+};
+
 struct vf_macvlans {
 	struct list_head l;
 	int vf;

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -8407,6 +8407,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_set_vf_rate	= ixgbe_ndo_set_vf_bw,
 	.ndo_set_vf_spoofchk	= ixgbe_ndo_set_vf_spoofchk,
 	.ndo_set_vf_rss_query_en = ixgbe_ndo_set_vf_rss_query_en,
+	.ndo_set_vf_trust	= ixgbe_ndo_set_vf_trust,
 	.ndo_get_vf_config	= ixgbe_ndo_get_vf_config,
 	.ndo_get_stats64	= ixgbe_get_stats64,
 #ifdef CONFIG_IXGBE_DCB

drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h

@@ -102,6 +102,8 @@ enum ixgbe_pfvf_api_rev {
 #define IXGBE_VF_GET_RETA	0x0a	/* VF request for RETA */
 #define IXGBE_VF_GET_RSS_KEY	0x0b	/* get RSS key */
 
+#define IXGBE_VF_UPDATE_XCAST_MODE	0x0c
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN 4
 /* word in permanent address message with the current multicast type */

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c

@@ -116,6 +116,12 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
 			 * we want to disable the querying by default.
 			 */
 			adapter->vfinfo[i].rss_query_enabled = 0;
+
+			/* Untrust all VFs */
+			adapter->vfinfo[i].trusted = false;
+
+			/* set the default xcast mode */
+			adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE;
 		}
 
 		return 0;
@@ -1001,6 +1007,59 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
+static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter,
+				      u32 *msgbuf, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int xcast_mode = msgbuf[1];
+	u32 vmolr, disable, enable;
+
+	/* verify the PF is supporting the correct APIs */
+	switch (adapter->vfinfo[vf].vf_api) {
+	case ixgbe_mbox_api_12:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (xcast_mode > IXGBEVF_XCAST_MODE_MULTI &&
+	    !adapter->vfinfo[vf].trusted) {
+		xcast_mode = IXGBEVF_XCAST_MODE_MULTI;
+	}
+
+	if (adapter->vfinfo[vf].xcast_mode == xcast_mode)
+		goto out;
+
+	switch (xcast_mode) {
+	case IXGBEVF_XCAST_MODE_NONE:
+		disable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE;
+		enable = 0;
+		break;
+	case IXGBEVF_XCAST_MODE_MULTI:
+		disable = IXGBE_VMOLR_MPE;
+		enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE;
+		break;
+	case IXGBEVF_XCAST_MODE_ALLMULTI:
+		disable = 0;
+		enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
+	vmolr &= ~disable;
+	vmolr |= enable;
+	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
+
+	adapter->vfinfo[vf].xcast_mode = xcast_mode;
+
+out:
+	msgbuf[1] = xcast_mode;
+
+	return 0;
+}
+
 static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 {
 	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
@@ -1063,6 +1122,9 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 	case IXGBE_VF_GET_RSS_KEY:
 		retval = ixgbe_get_vf_rss_key(adapter, msgbuf, vf);
 		break;
+	case IXGBE_VF_UPDATE_XCAST_MODE:
+		retval = ixgbe_update_vf_xcast_mode(adapter, msgbuf, vf);
+		break;
 	default:
 		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
 		retval = IXGBE_ERR_MBX;
@@ -1124,6 +1186,17 @@ void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
 	IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
 }
 
+static inline void ixgbe_ping_vf(struct ixgbe_adapter *adapter, int vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 ping;
+
+	ping = IXGBE_PF_CONTROL_MSG;
+	if (adapter->vfinfo[vf].clear_to_send)
+		ping |= IXGBE_VT_MSGTYPE_CTS;
+	ixgbe_write_mbx(hw, &ping, 1, vf);
+}
+
 void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1416,6 +1489,28 @@ int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 	return 0;
 }
 
+int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
+
+	/* nothing to do */
+	if (adapter->vfinfo[vf].trusted == setting)
+		return 0;
+
+	adapter->vfinfo[vf].trusted = setting;
+
+	/* reset VF to reconfigure features */
+	adapter->vfinfo[vf].clear_to_send = false;
+	ixgbe_ping_vf(adapter, vf);
+
+	e_info(drv, "VF %u is %strusted\n", vf, setting ? "" : "not ");
+
+	return 0;
+}
+
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi)
 {
@@ -1430,5 +1525,6 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 	ivi->qos = adapter->vfinfo[vf].pf_qos;
 	ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled;
 	ivi->rss_query_en = adapter->vfinfo[vf].rss_query_enabled;
+	ivi->trusted = adapter->vfinfo[vf].trusted;
 	return 0;
 }

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h

@@ -49,6 +49,7 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
 int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
 int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf,
 				  bool setting);
+int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting);
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi);
 void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter);

drivers/net/ethernet/intel/ixgbevf/ixgbevf.h

@@ -471,6 +471,12 @@ enum ixgbevf_boards {
 	board_X550EM_x_vf,
 };
 
+enum ixgbevf_xcast_modes {
+	IXGBEVF_XCAST_MODE_NONE = 0,
+	IXGBEVF_XCAST_MODE_MULTI,
+	IXGBEVF_XCAST_MODE_ALLMULTI,
+};
+
 extern const struct ixgbevf_info ixgbevf_82599_vf_info;
 extern const struct ixgbevf_info ixgbevf_X540_vf_info;
 extern const struct ixgbevf_info ixgbevf_X550_vf_info;

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -1894,9 +1894,17 @@ static void ixgbevf_set_rx_mode(struct net_device *netdev)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	unsigned int flags = netdev->flags;
+	int xcast_mode;
+
+	xcast_mode = (flags & IFF_ALLMULTI) ? IXGBEVF_XCAST_MODE_ALLMULTI :
+		     (flags & (IFF_BROADCAST | IFF_MULTICAST)) ?
+		     IXGBEVF_XCAST_MODE_MULTI : IXGBEVF_XCAST_MODE_NONE;
 
 	spin_lock_bh(&adapter->mbx_lock);
 
+	hw->mac.ops.update_xcast_mode(hw, netdev, xcast_mode);
+
 	/* reprogram multicast list */
 	hw->mac.ops.update_mc_addr_list(hw, netdev);
 

drivers/net/ethernet/intel/ixgbevf/mbx.h

@@ -112,6 +112,8 @@ enum ixgbe_pfvf_api_rev {
 #define IXGBE_VF_GET_RETA	0x0a	/* VF request for RETA */
 #define IXGBE_VF_GET_RSS_KEY	0x0b	/* get RSS hash key */
 
+#define IXGBE_VF_UPDATE_XCAST_MODE	0x0c
+
 /* length of permanent address message returned from PF */
 #define IXGBE_VF_PERMADDR_MSG_LEN	4
 /* word in permanent address message with the current multicast type */

drivers/net/ethernet/intel/ixgbevf/vf.c

@@ -468,6 +468,46 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
 	return 0;
 }
 
+/**
+ *  ixgbevf_update_xcast_mode - Update Multicast mode
+ *  @hw: pointer to the HW structure
+ *  @netdev: pointer to net device structure
+ *  @xcast_mode: new multicast mode
+ *
+ *  Updates the Multicast Mode of VF.
+ **/
+static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw,
+				     struct net_device *netdev, int xcast_mode)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	u32 msgbuf[2];
+	s32 err;
+
+	switch (hw->api_version) {
+	case ixgbe_mbox_api_12:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	msgbuf[0] = IXGBE_VF_UPDATE_XCAST_MODE;
+	msgbuf[1] = xcast_mode;
+
+	err = mbx->ops.write_posted(hw, msgbuf, 2);
+	if (err)
+		return err;
+
+	err = mbx->ops.read_posted(hw, msgbuf, 2);
+	if (err)
+		return err;
+
+	msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS;
+	if (msgbuf[0] == (IXGBE_VF_UPDATE_XCAST_MODE | IXGBE_VT_MSGTYPE_NACK))
+		return -EPERM;
+
+	return 0;
+}
+
 /**
  *  ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address
  *  @hw: pointer to the HW structure
@@ -727,6 +767,7 @@ static const struct ixgbe_mac_operations ixgbevf_mac_ops = {
 	.check_link		= ixgbevf_check_mac_link_vf,
 	.set_rar		= ixgbevf_set_rar_vf,
 	.update_mc_addr_list	= ixgbevf_update_mc_addr_list_vf,
+	.update_xcast_mode	= ixgbevf_update_xcast_mode,
 	.set_uc_addr		= ixgbevf_set_uc_addr_vf,
 	.set_vfta		= ixgbevf_set_vfta_vf,
 };

drivers/net/ethernet/intel/ixgbevf/vf.h

@@ -63,6 +63,7 @@ struct ixgbe_mac_operations {
 	s32 (*set_uc_addr)(struct ixgbe_hw *, u32, u8 *);
 	s32 (*init_rx_addrs)(struct ixgbe_hw *);
 	s32 (*update_mc_addr_list)(struct ixgbe_hw *, struct net_device *);
+	s32 (*update_xcast_mode)(struct ixgbe_hw *, struct net_device *, int);
 	s32 (*enable_mc)(struct ixgbe_hw *);
 	s32 (*disable_mc)(struct ixgbe_hw *);
 	s32 (*clear_vfta)(struct ixgbe_hw *);

include/linux/if_link.h

@@ -24,5 +24,6 @@ struct ifla_vf_info {
 	__u32 min_tx_rate;
 	__u32 max_tx_rate;
 	__u32 rss_query_en;
+	__u32 trusted;
 };
 #endif /* _LINUX_IF_LINK_H */

include/linux/netdevice.h

@@ -881,6 +881,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
  *			  int max_tx_rate);
  * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
+ * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting);
  * int (*ndo_get_vf_config)(struct net_device *dev,
  *			    int vf, struct ifla_vf_info *ivf);
  * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
@@ -1109,6 +1110,8 @@ struct net_device_ops {
 						   int max_tx_rate);
 	int			(*ndo_set_vf_spoofchk)(struct net_device *dev,
 						       int vf, bool setting);
+	int			(*ndo_set_vf_trust)(struct net_device *dev,
+						    int vf, bool setting);
 	int			(*ndo_get_vf_config)(struct net_device *dev,
 						     int vf,
 						     struct ifla_vf_info *ivf);

include/uapi/linux/if_link.h

@@ -550,6 +550,7 @@ enum {
 				 * on/off switch
 				 */
 	IFLA_VF_STATS,		/* network device statistics */
+	IFLA_VF_TRUST,		/* Trust VF */
 	__IFLA_VF_MAX,
 };
 
@@ -611,6 +612,11 @@ enum {
 
 #define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1)
 
+struct ifla_vf_trust {
+	__u32 vf;
+	__u32 setting;
+};
+
 /* VF ports management section
  *
  *	Nested layout of set/get msg is:

net/core/rtnetlink.c

@@ -838,7 +838,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			 /* IFLA_VF_STATS_BROADCAST */
 			 nla_total_size(sizeof(__u64)) +
 			 /* IFLA_VF_STATS_MULTICAST */
-			 nla_total_size(sizeof(__u64)));
+			 nla_total_size(sizeof(__u64)) +
+			 nla_total_size(sizeof(struct ifla_vf_trust)));
 		return size;
 	} else
 		return 0;
@@ -1161,6 +1162,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_link_state vf_linkstate;
 			struct ifla_vf_rss_query_en vf_rss_query_en;
 			struct ifla_vf_stats vf_stats;
+			struct ifla_vf_trust vf_trust;
 
 			/*
 			 * Not all SR-IOV capable drivers support the
@@ -1170,6 +1172,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			 */
 			ivi.spoofchk = -1;
 			ivi.rss_query_en = -1;
+			ivi.trusted = -1;
 			memset(ivi.mac, 0, sizeof(ivi.mac));
 			/* The default value for VF link state is "auto"
 			 * IFLA_VF_LINK_STATE_AUTO which equals zero
@@ -1183,7 +1186,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
 				vf_linkstate.vf =
-				vf_rss_query_en.vf = ivi.vf;
+				vf_rss_query_en.vf =
+				vf_trust.vf = ivi.vf;
 
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
@@ -1194,6 +1198,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf_rss_query_en.setting = ivi.rss_query_en;
+			vf_trust.setting = ivi.trusted;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
 			if (!vf) {
 				nla_nest_cancel(skb, vfinfo);
@@ -1211,7 +1216,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				    &vf_linkstate) ||
 			    nla_put(skb, IFLA_VF_RSS_QUERY_EN,
 				    sizeof(vf_rss_query_en),
-				    &vf_rss_query_en))
+				    &vf_rss_query_en) ||
+			    nla_put(skb, IFLA_VF_TRUST,
+				    sizeof(vf_trust), &vf_trust))
 				goto nla_put_failure;
 			memset(&vf_stats, 0, sizeof(vf_stats));
 			if (dev->netdev_ops->ndo_get_vf_stats)
@@ -1348,6 +1355,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_LINK_STATE]	= { .len = sizeof(struct ifla_vf_link_state) },
 	[IFLA_VF_RSS_QUERY_EN]	= { .len = sizeof(struct ifla_vf_rss_query_en) },
 	[IFLA_VF_STATS]		= { .type = NLA_NESTED },
+	[IFLA_VF_TRUST]		= { .len = sizeof(struct ifla_vf_trust) },
 };
 
 static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = {
@@ -1587,6 +1595,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 			return err;
 	}
 
+	if (tb[IFLA_VF_TRUST]) {
+		struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_trust)
+			err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }