1 files changed, 481 insertions, 58 deletions

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index deaf670c160e..0f4be72116b8 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -10,6 +10,7 @@
 
 #include "wx_type.h"
 #include "wx_lib.h"
+#include "wx_sriov.h"
 #include "wx_hw.h"
 
 static int wx_phy_read_reg_mdi(struct mii_bus *bus, int phy_addr, int devnum, int regnum)
@@ -112,7 +113,7 @@ static void wx_intr_disable(struct wx *wx, u64 qmask)
 	if (mask)
 		wr32(wx, WX_PX_IMS(0), mask);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMS(1), mask);
@@ -126,7 +127,8 @@ void wx_intr_enable(struct wx *wx, u64 qmask)
 	mask = (qmask & U32_MAX);
 	if (mask)
 		wr32(wx, WX_PX_IMC(0), mask);
-	if (wx->mac.type == wx_mac_sp) {
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMC(1), mask);
@@ -278,22 +280,8 @@ static int wx_acquire_sw_sync(struct wx *wx, u32 mask)
 	return ret;
 }
 
-/**
- *  wx_host_interface_command - Issue command to manageability block
- *  @wx: pointer to the HW structure
- *  @buffer: contains the command to write and where the return status will
- *   be placed
- *  @length: length of buffer, must be multiple of 4 bytes
- *  @timeout: time in ms to wait for command completion
- *  @return_data: read and return data from the buffer (true) or not (false)
- *   Needed because FW structures are big endian and decoding of
- *   these fields can be 8 bit or 16 bit based on command. Decoding
- *   is not easily understood without making a table of commands.
- *   So we will leave this up to the caller to read back the data
- *   in these cases.
- **/
-int wx_host_interface_command(struct wx *wx, u32 *buffer,
-			      u32 length, u32 timeout, bool return_data)
+static int wx_host_interface_command_s(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
 {
 	u32 hdr_size = sizeof(struct wx_hic_hdr);
 	u32 hicr, i, bi, buf[64] = {};
@@ -301,22 +289,10 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	u32 dword_len;
 	u16 buf_len;
 
-	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
-		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
-		return -EINVAL;
-	}
-
 	status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	if (status != 0)
 		return status;
 
-	/* Calculate length in DWORDs. We must be DWORD aligned */
-	if ((length % (sizeof(u32))) != 0) {
-		wx_err(wx, "Buffer length failure, not aligned to dword");
-		status = -EINVAL;
-		goto rel_out;
-	}
-
 	dword_len = length >> 2;
 
 	/* The device driver writes the relevant command block
@@ -391,8 +367,166 @@ rel_out:
 	wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	return status;
 }
+
+static bool wx_poll_fw_reply(struct wx *wx, u32 *buffer, u8 send_cmd)
+{
+	u32 dword_len = sizeof(struct wx_hic_hdr) >> 2;
+	struct wx_hic_hdr *recv_hdr;
+	u32 i;
+
+	/* read hdr */
+	for (i = 0; i < dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+	/* check hdr */
+	recv_hdr = (struct wx_hic_hdr *)buffer;
+	if (recv_hdr->cmd == send_cmd &&
+	    recv_hdr->index == wx->swfw_index)
+		return true;
+
+	return false;
+}
+
+static int wx_host_interface_command_r(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
+{
+	struct wx_hic_hdr *hdr = (struct wx_hic_hdr *)buffer;
+	u32 hdr_size = sizeof(struct wx_hic_hdr);
+	bool busy, reply;
+	u32 dword_len;
+	u16 buf_len;
+	int err = 0;
+	u8 send_cmd;
+	u32 i;
+
+	/* wait to get lock */
+	might_sleep();
+	err = read_poll_timeout(test_and_set_bit, busy, !busy, 1000, timeout * 1000,
+				false, WX_STATE_SWFW_BUSY, wx->state);
+	if (err)
+		return err;
+
+	/* index to unique seq id for each mbox message */
+	hdr->index = wx->swfw_index;
+	send_cmd = hdr->cmd;
+
+	dword_len = length >> 2;
+	/* write data to SW-FW mbox array */
+	for (i = 0; i < dword_len; i++) {
+		wr32a(wx, WX_SW2FW_MBOX, i, (__force u32)cpu_to_le32(buffer[i]));
+		/* write flush */
+		rd32a(wx, WX_SW2FW_MBOX, i);
+	}
+
+	/* generate interrupt to notify FW */
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, 0);
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD);
+
+	/* polling reply from FW */
+	err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 2000,
+				timeout * 1000, true, wx, buffer, send_cmd);
+	if (err) {
+		wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n",
+		       send_cmd, wx->swfw_index);
+		goto rel_out;
+	}
+
+	if (hdr->cmd_or_resp.ret_status == 0x80) {
+		wx_err(wx, "Unknown FW command: 0x%x\n", send_cmd);
+		err = -EINVAL;
+		goto rel_out;
+	}
+
+	/* expect no reply from FW then return */
+	if (!return_data)
+		goto rel_out;
+
+	/* If there is any thing in data position pull it in */
+	buf_len = hdr->buf_len;
+	if (buf_len == 0)
+		goto rel_out;
+
+	if (length < buf_len + hdr_size) {
+		wx_err(wx, "Buffer not large enough for reply message.\n");
+		err = -EFAULT;
+		goto rel_out;
+	}
+
+	/* Calculate length in DWORDs, add 3 for odd lengths */
+	dword_len = (buf_len + 3) >> 2;
+	for (i = hdr_size >> 2; i <= dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+rel_out:
+	/* index++, index replace wx_hic_hdr.checksum */
+	if (wx->swfw_index == WX_HIC_HDR_INDEX_MAX)
+		wx->swfw_index = 0;
+	else
+		wx->swfw_index++;
+
+	clear_bit(WX_STATE_SWFW_BUSY, wx->state);
+	return err;
+}
+
+/**
+ *  wx_host_interface_command - Issue command to manageability block
+ *  @wx: pointer to the HW structure
+ *  @buffer: contains the command to write and where the return status will
+ *   be placed
+ *  @length: length of buffer, must be multiple of 4 bytes
+ *  @timeout: time in ms to wait for command completion
+ *  @return_data: read and return data from the buffer (true) or not (false)
+ *   Needed because FW structures are big endian and decoding of
+ *   these fields can be 8 bit or 16 bit based on command. Decoding
+ *   is not easily understood without making a table of commands.
+ *   So we will leave this up to the caller to read back the data
+ *   in these cases.
+ **/
+int wx_host_interface_command(struct wx *wx, u32 *buffer,
+			      u32 length, u32 timeout, bool return_data)
+{
+	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
+		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
+		return -EINVAL;
+	}
+
+	/* Calculate length in DWORDs. We must be DWORD aligned */
+	if ((length % (sizeof(u32))) != 0) {
+		wx_err(wx, "Buffer length failure, not aligned to dword");
+		return -EINVAL;
+	}
+
+	if (test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		return wx_host_interface_command_r(wx, buffer, length,
+						   timeout, return_data);
+
+	return wx_host_interface_command_s(wx, buffer, length, timeout, return_data);
+}
 EXPORT_SYMBOL(wx_host_interface_command);
 
+int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles)
+{
+	struct wx_hic_set_pps pps_cmd;
+
+	pps_cmd.hdr.cmd = FW_PPS_SET_CMD;
+	pps_cmd.hdr.buf_len = FW_PPS_SET_LEN;
+	pps_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+	pps_cmd.lan_id = wx->bus.func;
+	pps_cmd.enable = (u8)enable;
+	pps_cmd.nsec = nsec;
+	pps_cmd.cycles = cycles;
+	pps_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM;
+
+	return wx_host_interface_command(wx, (u32 *)&pps_cmd,
+					 sizeof(pps_cmd),
+					 WX_HI_COMMAND_TIMEOUT,
+					 false);
+}
+
 /**
  *  wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd
  *  assuming that the semaphore is already obtained.
@@ -423,7 +557,10 @@ static int wx_read_ee_hostif_data(struct wx *wx, u16 offset, u16 *data)
 	if (status != 0)
 		return status;
 
-	*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	else
+		*data = (u16)rd32a(wx, WX_FW2SW_MBOX, FW_NVM_DATA_OFFSET);
 
 	return status;
 }
@@ -467,6 +604,7 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 	u16 words_to_read;
 	u32 value = 0;
 	int status;
+	u32 mbox;
 	u32 i;
 
 	/* Take semaphore for the entire operation. */
@@ -499,8 +637,12 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 			goto out;
 		}
 
+		if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+			mbox = WX_MNG_MBOX;
+		else
+			mbox = WX_FW2SW_MBOX;
 		for (i = 0; i < words_to_read; i++) {
-			u32 reg = WX_MNG_MBOX + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
+			u32 reg = mbox + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
 
 			value = rd32(wx, reg);
 			data[current_word] = (u16)(value & 0xffff);
@@ -550,12 +692,18 @@ void wx_init_eeprom_params(struct wx *wx)
 		}
 	}
 
-	if (wx->mac.type == wx_mac_sp) {
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
+	case wx_mac_aml40:
 		if (wx_read_ee_hostif(wx, WX_SW_REGION_PTR, &data)) {
 			wx_err(wx, "NVM Read Error\n");
 			return;
 		}
 		data = data >> 1;
+		break;
+	default:
+		break;
 	}
 
 	eeprom->sw_region_offset = data;
@@ -616,7 +764,8 @@ static int wx_set_rar(struct wx *wx, u32 index, u8 *addr, u64 pools,
 
 	/* setup VMDq pool mapping */
 	wr32(wx, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF);
-	if (wx->mac.type == wx_mac_sp)
+
+	if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags))
 		wr32(wx, WX_PSR_MAC_SWC_VM_H, pools >> 32);
 
 	/* HW expects these in little endian so we reverse the byte
@@ -755,7 +904,7 @@ void wx_init_rx_addrs(struct wx *wx)
 
 		wx_set_rar(wx, 0, wx->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV);
 
-		if (wx->mac.type == wx_mac_sp) {
+		if (test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
 			/* clear VMDq pool/queue selection for RAR 0 */
 			wx_clear_vmdq(wx, 0, WX_CLEAR_VMDQ_ALL);
 		}
@@ -802,11 +951,28 @@ static void wx_sync_mac_table(struct wx *wx)
 	}
 }
 
+static void wx_full_sync_mac_table(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->mac.num_rar_entries; i++) {
+		if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) {
+			wx_set_rar(wx, i,
+				   wx->mac_table[i].addr,
+				   wx->mac_table[i].pools,
+				   WX_PSR_MAC_SWC_AD_H_AV);
+		} else {
+			wx_clear_rar(wx, i);
+		}
+		wx->mac_table[i].state &= ~(WX_MAC_STATE_MODIFIED);
+	}
+}
+
 /* this function destroys the first RAR entry */
 void wx_mac_set_default_filter(struct wx *wx, u8 *addr)
 {
 	memcpy(&wx->mac_table[0].addr, addr, ETH_ALEN);
-	wx->mac_table[0].pools = 1ULL;
+	wx->mac_table[0].pools = BIT(VMDQ_P(0));
 	wx->mac_table[0].state = (WX_MAC_STATE_DEFAULT | WX_MAC_STATE_IN_USE);
 	wx_set_rar(wx, 0, wx->mac_table[0].addr,
 		   wx->mac_table[0].pools,
@@ -831,7 +997,7 @@ void wx_flush_sw_mac_table(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_flush_sw_mac_table);
 
-static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -862,7 +1028,7 @@ static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 	return -ENOMEM;
 }
 
-static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -1044,6 +1210,35 @@ static void wx_update_mc_addr_list(struct wx *wx, struct net_device *netdev)
 	wx_dbg(wx, "Update mc addr list Complete\n");
 }
 
+static void wx_restore_vf_multicasts(struct wx *wx)
+{
+	u32 i, j, vector_bit, vector_reg;
+	struct vf_data_storage *vfinfo;
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(i));
+
+		vfinfo = &wx->vfinfo[i];
+		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
+			wx->addr_ctrl.mta_in_use++;
+			vector_reg = WX_PSR_MC_TBL_REG(vfinfo->vf_mc_hashes[j]);
+			vector_bit = WX_PSR_MC_TBL_BIT(vfinfo->vf_mc_hashes[j]);
+			wr32m(wx, WX_PSR_MC_TBL(vector_reg),
+			      BIT(vector_bit), BIT(vector_bit));
+			/* errata 5: maintain a copy of the reg table conf */
+			wx->mac.mta_shadow[vector_reg] |= BIT(vector_bit);
+		}
+		if (vfinfo->num_vf_mc_hashes)
+			vmolr |= WX_PSR_VM_L2CTL_ROMPE;
+		else
+			vmolr &= ~WX_PSR_VM_L2CTL_ROMPE;
+		wr32(wx, WX_PSR_VM_L2CTL(i), vmolr);
+	}
+
+	/* Restore any VF macvlans */
+	wx_full_sync_mac_table(wx);
+}
+
 /**
  * wx_write_mc_addr_list - write multicast addresses to MTA
  * @netdev: network interface device structure
@@ -1061,6 +1256,9 @@ static int wx_write_mc_addr_list(struct net_device *netdev)
 
 	wx_update_mc_addr_list(wx, netdev);
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		wx_restore_vf_multicasts(wx);
+
 	return netdev_mc_count(netdev);
 }
 
@@ -1081,7 +1279,7 @@ int wx_set_mac(struct net_device *netdev, void *p)
 	if (retval)
 		return retval;
 
-	wx_del_mac_filter(wx, wx->mac.addr, 0);
+	wx_del_mac_filter(wx, wx->mac.addr, VMDQ_P(0));
 	eth_hw_addr_set(netdev, addr->sa_data);
 	memcpy(wx->mac.addr, addr->sa_data, netdev->addr_len);
 
@@ -1183,6 +1381,10 @@ static int wx_hpbthresh(struct wx *wx)
 	/* Calculate delay value for device */
 	dv_id = WX_DV(link, tc);
 
+	/* Loopback switch introduces additional latency */
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		dv_id += WX_B2BT(tc);
+
 	/* Delay value is calculated in bit times convert to KB */
 	kb = WX_BT2KB(dv_id);
 	rx_pba = rd32(wx, WX_RDB_PB_SZ(0)) >> WX_RDB_PB_SZ_SHIFT;
@@ -1238,12 +1440,107 @@ static void wx_pbthresh_setup(struct wx *wx)
 		wx->fc.low_water = 0;
 }
 
+static void wx_set_ethertype_anti_spoofing(struct wx *wx, bool enable, int vf)
+{
+	u32 pfvfspoof, reg_offset, vf_shift;
+
+	vf_shift = WX_VF_IND_SHIFT(vf);
+	reg_offset = WX_VF_REG_OFFSET(vf);
+
+	pfvfspoof = rd32(wx, WX_TDM_ETYPE_AS(reg_offset));
+	if (enable)
+		pfvfspoof |= BIT(vf_shift);
+	else
+		pfvfspoof &= ~BIT(vf_shift);
+	wr32(wx, WX_TDM_ETYPE_AS(reg_offset), pfvfspoof);
+}
+
+int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	struct wx *wx = netdev_priv(netdev);
+	u32 regval;
+
+	if (vf >= wx->num_vfs)
+		return -EINVAL;
+
+	wx->vfinfo[vf].spoofchk_enabled = setting;
+
+	regval = (setting << vf_bit);
+	wr32m(wx, WX_TDM_MAC_AS(index), regval | BIT(vf_bit), regval);
+
+	if (wx->vfinfo[vf].vlan_count)
+		wr32m(wx, WX_TDM_VLAN_AS(index), regval | BIT(vf_bit), regval);
+
+	return 0;
+}
+
+static void wx_configure_virtualization(struct wx *wx)
+{
+	u16 pool = wx->num_rx_pools;
+	u32 reg_offset, vf_shift;
+	u32 i;
+
+	if (!test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		return;
+
+	wr32m(wx, WX_PSR_VM_CTL,
+	      WX_PSR_VM_CTL_POOL_MASK | WX_PSR_VM_CTL_REPLEN,
+	      FIELD_PREP(WX_PSR_VM_CTL_POOL_MASK, VMDQ_P(0)) |
+	      WX_PSR_VM_CTL_REPLEN);
+	while (pool--)
+		wr32m(wx, WX_PSR_VM_L2CTL(pool),
+		      WX_PSR_VM_L2CTL_AUPE, WX_PSR_VM_L2CTL_AUPE);
+
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		vf_shift = BIT(VMDQ_P(0));
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(0), vf_shift);
+		wr32(wx, WX_TDM_VF_TE(0), vf_shift);
+	} else {
+		vf_shift = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_offset = WX_VF_REG_OFFSET(VMDQ_P(0));
+
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_RDM_VF_RE(reg_offset ^ 1), reg_offset - 1);
+		wr32(wx, WX_TDM_VF_TE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_TDM_VF_TE(reg_offset ^ 1), reg_offset - 1);
+	}
+
+	/* clear VLAN promisc flag so VFTA will be updated if necessary */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		if (!wx->vfinfo[i].spoofchk_enabled)
+			wx_set_vf_spoofchk(wx->netdev, i, false);
+		/* enable ethertype anti spoofing if hw supports it */
+		wx_set_ethertype_anti_spoofing(wx, true, i);
+	}
+}
+
 static void wx_configure_port(struct wx *wx)
 {
 	u32 value, i;
 
-	value = WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		value = (wx->num_vfs == 0) ?
+			WX_CFG_PORT_CTL_NUM_VT_NONE :
+			WX_CFG_PORT_CTL_NUM_VT_8;
+	} else {
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+			if (wx->ring_feature[RING_F_RSS].indices == 4)
+				value = WX_CFG_PORT_CTL_NUM_VT_32;
+			else
+				value = WX_CFG_PORT_CTL_NUM_VT_64;
+		} else {
+			value = 0;
+		}
+	}
+
+	value |= WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
 	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_NUM_VT_MASK |
 	      WX_CFG_PORT_CTL_D_VLAN |
 	      WX_CFG_PORT_CTL_QINQ,
 	      value);
@@ -1304,6 +1601,83 @@ static void wx_vlan_strip_control(struct wx *wx, bool enable)
 	}
 }
 
+static void wx_vlan_promisc_enable(struct wx *wx)
+{
+	u32 vlnctrl, i, vind, bits, reg_idx;
+
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+		/* we need to keep the VLAN filter on in SRIOV */
+		vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	} else {
+		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+		return;
+	}
+	/* We are already in VLAN promisc, nothing to do */
+	if (test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	set_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	/* Add PF to all active pools */
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits |= BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* Set all bits in the VLAN filter table array */
+	for (i = 0; i < wx->mac.vft_size; i++)
+		wr32(wx, WX_PSR_VLAN_TBL(i), U32_MAX);
+}
+
+static void wx_scrub_vfta(struct wx *wx)
+{
+	u32 i, vid, bits, vfta, vind, vlvf, reg_idx;
+
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC_IDX);
+		/* pull VLAN ID from VLVF */
+		vid = vlvf & ~WX_PSR_VLAN_SWC_VIEN;
+		if (vlvf & WX_PSR_VLAN_SWC_VIEN) {
+			/* if PF is part of this then continue */
+			if (test_bit(vid, wx->active_vlans))
+				continue;
+		}
+		/* remove PF from the pool */
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits &= ~BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* extract values from vft_shadow and write back to VFTA */
+	for (i = 0; i < wx->mac.vft_size; i++) {
+		vfta = wx->mac.vft_shadow[i];
+		wr32(wx, WX_PSR_VLAN_TBL(i), vfta);
+	}
+}
+
+static void wx_vlan_promisc_disable(struct wx *wx)
+{
+	u32 vlnctrl;
+
+	/* configure vlan filtering */
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	/* We are not in VLAN promisc, nothing to do */
+	if (!test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	wx_scrub_vfta(wx);
+}
+
 void wx_set_rx_mode(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
@@ -1316,7 +1690,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	/* Check for Promiscuous and All Multicast modes */
 	fctrl = rd32(wx, WX_PSR_CTL);
 	fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE);
-	vmolr = rd32(wx, WX_PSR_VM_L2CTL(0));
+	vmolr = rd32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)));
 	vmolr &= ~(WX_PSR_VM_L2CTL_UPE |
 		   WX_PSR_VM_L2CTL_MPE |
 		   WX_PSR_VM_L2CTL_ROPE |
@@ -1337,7 +1711,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 		fctrl |= WX_PSR_CTL_UPE | WX_PSR_CTL_MPE;
 		/* pf don't want packets routing to vf, so clear UPE */
 		vmolr |= WX_PSR_VM_L2CTL_MPE;
-		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags) &&
+		    test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+			vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
 	}
 
 	if (netdev->flags & IFF_ALLMULTI) {
@@ -1360,7 +1737,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	 * sufficient space to store all the addresses then enable
 	 * unicast promiscuous mode
 	 */
-	count = wx_write_uc_addr_list(netdev, 0);
+	count = wx_write_uc_addr_list(netdev, VMDQ_P(0));
 	if (count < 0) {
 		vmolr &= ~WX_PSR_VM_L2CTL_ROPE;
 		vmolr |= WX_PSR_VM_L2CTL_UPE;
@@ -1378,7 +1755,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 
 	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
 	wr32(wx, WX_PSR_CTL, fctrl);
-	wr32(wx, WX_PSR_VM_L2CTL(0), vmolr);
+	wr32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)), vmolr);
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    (features & NETIF_F_HW_VLAN_STAG_RX))
@@ -1386,6 +1763,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 	else
 		wx_vlan_strip_control(wx, false);
 
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		wx_vlan_promisc_disable(wx);
+	else
+		wx_vlan_promisc_enable(wx);
 }
 EXPORT_SYMBOL(wx_set_rx_mode);
 
@@ -1635,6 +2016,13 @@ static void wx_setup_reta(struct wx *wx)
 	u32 random_key_size = WX_RSS_KEY_SIZE / 4;
 	u32 i, j;
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags)) {
+		if (wx->mac.type == wx_mac_em)
+			rss_i = 1;
+		else
+			rss_i = rss_i < 4 ? 4 : rss_i;
+	}
+
 	/* Fill out hash function seeds */
 	for (i = 0; i < random_key_size; i++)
 		wr32(wx, WX_RDB_RSSRK(i), wx->rss_key[i]);
@@ -1652,10 +2040,42 @@ static void wx_setup_reta(struct wx *wx)
 	wx_store_reta(wx);
 }
 
+#define WX_RDB_RSS_PL_2		FIELD_PREP(GENMASK(31, 29), 1)
+#define WX_RDB_RSS_PL_4		FIELD_PREP(GENMASK(31, 29), 2)
+static void wx_setup_psrtype(struct wx *wx)
+{
+	int rss_i = wx->ring_feature[RING_F_RSS].indices;
+	u32 psrtype;
+	int pool;
+
+	psrtype = WX_RDB_PL_CFG_L4HDR |
+		  WX_RDB_PL_CFG_L3HDR |
+		  WX_RDB_PL_CFG_L2HDR |
+		  WX_RDB_PL_CFG_TUN_OUTL2HDR |
+		  WX_RDB_PL_CFG_TUN_TUNHDR;
+
+	if (!test_bit(WX_FLAG_MULTI_64_FUNC, wx->flags)) {
+		for_each_set_bit(pool, &wx->fwd_bitmask, 8)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	} else {
+		if (rss_i > 3)
+			psrtype |= WX_RDB_RSS_PL_4;
+		else if (rss_i > 1)
+			psrtype |= WX_RDB_RSS_PL_2;
+
+		for_each_set_bit(pool, &wx->fwd_bitmask, 32)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	}
+}
+
 static void wx_setup_mrqc(struct wx *wx)
 {
 	u32 rss_field = 0;
 
+	/* VT, and RSS do not coexist at the same time */
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return;
+
 	/* Disable indicating checksum in descriptor, enables RSS hash */
 	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
 
@@ -1685,21 +2105,16 @@ static void wx_setup_mrqc(struct wx *wx)
  **/
 void wx_configure_rx(struct wx *wx)
 {
-	u32 psrtype, i;
 	int ret;
+	u32 i;
 
 	wx_disable_rx(wx);
-
-	psrtype = WX_RDB_PL_CFG_L4HDR |
-		  WX_RDB_PL_CFG_L3HDR |
-		  WX_RDB_PL_CFG_L2HDR |
-		  WX_RDB_PL_CFG_TUN_TUNHDR;
-	wr32(wx, WX_RDB_PL_CFG(0), psrtype);
+	wx_setup_psrtype(wx);
 
 	/* enable hw crc stripping */
 	wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) {
 		u32 psrctl;
 
 		/* RSC Setup */
@@ -1742,6 +2157,7 @@ void wx_configure(struct wx *wx)
 {
 	wx_set_rxpba(wx);
 	wx_pbthresh_setup(wx);
+	wx_configure_virtualization(wx);
 	wx_configure_port(wx);
 
 	wx_set_rx_mode(wx->netdev);
@@ -1836,10 +2252,8 @@ int wx_stop_adapter(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_stop_adapter);
 
-void wx_reset_misc(struct wx *wx)
+void wx_reset_mac(struct wx *wx)
 {
-	int i;
-
 	/* receive packets that size > 2048 */
 	wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE);
 
@@ -1851,6 +2265,14 @@ void wx_reset_misc(struct wx *wx)
 	      WX_MAC_RX_FLOW_CTRL_RFE, WX_MAC_RX_FLOW_CTRL_RFE);
 
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
+}
+EXPORT_SYMBOL(wx_reset_mac);
+
+void wx_reset_misc(struct wx *wx)
+{
+	int i;
+
+	wx_reset_mac(wx);
 
 	wr32m(wx, WX_MIS_RST_ST,
 	      WX_MIS_RST_ST_RST_INIT, 0x1E00);
@@ -2100,7 +2522,7 @@ static int wx_set_vlvf(struct wx *wx, u32 vlan, u32 vind, bool vlan_on,
  *
  *  Turn on/off specified VLAN in the VLAN filter table.
  **/
-static int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
+int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
 {
 	u32 bitindex, vfta, targetbit;
 	bool vfta_changed = false;
@@ -2351,12 +2773,13 @@ void wx_update_stats(struct wx *wx)
 	hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT);
 	hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 		hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH);
 		hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS);
 	}
 
-	for (i = 0; i < wx->mac.max_rx_queues; i++)
+	for (i = wx->num_vfs * wx->num_rx_queues_per_pool;
+	     i < wx->mac.max_rx_queues; i++)
 		hwstats->qmprc += rd32(wx, WX_PX_MPRC(i));
 }
 EXPORT_SYMBOL(wx_update_stats);