Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

23 files changed, 3445 insertions, 1339 deletions

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 9cae5a3090..529172a87a 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -391,7 +391,9 @@ static void umac_reset(struct bcmasp_intf *intf)
 	umac_wl(intf, 0x0, UMC_CMD);
 	umac_wl(intf, UMC_CMD_SW_RESET, UMC_CMD);
 	usleep_range(10, 100);
-	umac_wl(intf, 0x0, UMC_CMD);
+	/* We hold the umac in reset and bring it out of
+	 * reset when phy link is up.
+	 */
 }
 
 static void umac_set_hw_addr(struct bcmasp_intf *intf,
@@ -411,6 +413,8 @@ static void umac_enable_set(struct bcmasp_intf *intf, u32 mask,
 	u32 reg;
 
 	reg = umac_rl(intf, UMC_CMD);
+	if (reg & UMC_CMD_SW_RESET)
+		return;
 	if (enable)
 		reg |= mask;
 	else
@@ -429,13 +433,10 @@ static void umac_init(struct bcmasp_intf *intf)
 	umac_wl(intf, 0x800, UMC_FRM_LEN);
 	umac_wl(intf, 0xffff, UMC_PAUSE_CNTRL);
 	umac_wl(intf, 0x800, UMC_RX_MAX_PKT_SZ);
-	umac_enable_set(intf, UMC_CMD_PROMISC, 1);
 }
 
-static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
+static int bcmasp_tx_reclaim(struct bcmasp_intf *intf)
 {
-	struct bcmasp_intf *intf =
-		container_of(napi, struct bcmasp_intf, tx_napi);
 	struct bcmasp_intf_stats64 *stats = &intf->stats64;
 	struct device *kdev = &intf->parent->pdev->dev;
 	unsigned long read, released = 0;
@@ -478,10 +479,16 @@ static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
 							DESC_RING_COUNT);
 	}
 
-	/* Ensure all descriptors have been written to DRAM for the hardware
-	 * to see updated contents.
-	 */
-	wmb();
+	return released;
+}
+
+static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
+{
+	struct bcmasp_intf *intf =
+		container_of(napi, struct bcmasp_intf, tx_napi);
+	int released = 0;
+
+	released = bcmasp_tx_reclaim(intf);
 
 	napi_complete(&intf->tx_napi);
 
@@ -656,6 +663,12 @@ static void bcmasp_adj_link(struct net_device *dev)
 			UMC_CMD_HD_EN | UMC_CMD_RX_PAUSE_IGNORE |
 			UMC_CMD_TX_PAUSE_IGNORE);
 		reg |= cmd_bits;
+		if (reg & UMC_CMD_SW_RESET) {
+			reg &= ~UMC_CMD_SW_RESET;
+			umac_wl(intf, reg, UMC_CMD);
+			udelay(2);
+			reg |= UMC_CMD_TX_EN | UMC_CMD_RX_EN | UMC_CMD_PROMISC;
+		}
 		umac_wl(intf, reg, UMC_CMD);
 
 		intf->eee.eee_active = phy_init_eee(phydev, 0) >= 0;
@@ -684,6 +697,8 @@ static int bcmasp_init_rx(struct bcmasp_intf *intf)
 
 	intf->rx_buf_order = get_order(RING_BUFFER_SIZE);
 	buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order);
+	if (!buffer_pg)
+		return -ENOMEM;
 
 	dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE,
 			   DMA_FROM_DEVICE);
@@ -785,6 +800,7 @@ static int bcmasp_init_tx(struct bcmasp_intf *intf)
 
 	intf->tx_spb_index = 0;
 	intf->tx_spb_clean_index = 0;
+	memset(intf->tx_cbs, 0, sizeof(struct bcmasp_tx_cb) * DESC_RING_COUNT);
 
 	netif_napi_add_tx(intf->ndev, &intf->tx_napi, bcmasp_tx_poll);
 
@@ -895,6 +911,8 @@ static void bcmasp_netif_deinit(struct net_device *dev)
 	} while (timeout-- > 0);
 	tx_spb_dma_wl(intf, 0x0, TX_SPB_DMA_FIFO_CTRL);
 
+	bcmasp_tx_reclaim(intf);
+
 	umac_enable_set(intf, UMC_CMD_TX_EN, 0);
 
 	phy_stop(dev->phydev);
@@ -1061,9 +1079,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 
 	umac_init(intf);
 
-	/* Disable the UniMAC RX/TX */
-	umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 0);
-
 	umac_set_hw_addr(intf, dev->dev_addr);
 
 	intf->old_duplex = -1;
@@ -1083,9 +1098,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 
 	bcmasp_enable_rx(intf, 1);
 
-	/* Turn on UniMAC TX/RX */
-	umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 1);
-
 	intf->crc_fwd = !!(umac_rl(intf, UMC_CMD) & UMC_CMD_CRC_FWD);
 
 	bcmasp_netif_start(dev);
@@ -1095,6 +1107,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 	return 0;
 
 err_reclaim_tx:
+	netif_napi_del(&intf->tx_napi);
 	bcmasp_reclaim_free_all_tx(intf);
 err_phy_disconnect:
 	if (phydev)
@@ -1321,7 +1334,14 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf)
 	if (intf->wolopts & WAKE_FILTER)
 		bcmasp_netfilt_suspend(intf);
 
-	/* UniMAC receive needs to be turned on */
+	/* Bring UniMAC out of reset if needed and enable RX */
+	reg = umac_rl(intf, UMC_CMD);
+	if (reg & UMC_CMD_SW_RESET)
+		reg &= ~UMC_CMD_SW_RESET;
+
+	reg |= UMC_CMD_RX_EN | UMC_CMD_PROMISC;
+	umac_wl(intf, reg, UMC_CMD);
+
 	umac_enable_set(intf, UMC_CMD_RX_EN, 1);
 
 	if (intf->parent->wol_irq > 0) {
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 3e4fb3c3e8..1be6d14030 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2009,12 +2009,14 @@ static int b44_set_pauseparam(struct net_device *dev,
 		bp->flags |= B44_FLAG_TX_PAUSE;
 	else
 		bp->flags &= ~B44_FLAG_TX_PAUSE;
-	if (bp->flags & B44_FLAG_PAUSE_AUTO) {
-		b44_halt(bp);
-		b44_init_rings(bp);
-		b44_init_hw(bp, B44_FULL_RESET);
-	} else {
-		__b44_set_flow_ctrl(bp, bp->flags);
+	if (netif_running(dev)) {
+		if (bp->flags & B44_FLAG_PAUSE_AUTO) {
+			b44_halt(bp);
+			b44_init_rings(bp);
+			b44_init_hw(bp, B44_FULL_RESET);
+		} else {
+			__b44_set_flow_ctrl(bp, bp->flags);
+		}
 	}
 	spin_unlock_irq(&bp->lock);
 
diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 3e7c8671cd..72df1bb101 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -793,5 +793,6 @@ static struct platform_driver bcm4908_enet_driver = {
 };
 module_platform_driver(bcm4908_enet_driver);
 
+MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
index 9b83d53616..50b8e97a81 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c
@@ -260,4 +260,5 @@ void bcma_mdio_mii_unregister(struct mii_bus *mii_bus)
 EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6e4f36aaf5..36f9bad28e 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -362,4 +362,5 @@ module_init(bgmac_init)
 module_exit(bgmac_exit)
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 0b21fd5bd4..77425c7a32 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -298,4 +298,5 @@ static struct platform_driver bgmac_enet_driver = {
 };
 
 module_platform_driver(bgmac_enet_driver);
+MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 448a1b90de..6ffdc42294 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1626,4 +1626,5 @@ int bgmac_enet_resume(struct bgmac *bgmac)
 EXPORT_SYMBOL_GPL(bgmac_enet_resume);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e9c1e1bb55..528441b28c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -147,10 +147,11 @@ void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len)
 
 		phy_fw_ver[0] = '\0';
 		bnx2x_get_ext_phy_fw_version(&bp->link_params,
-					     phy_fw_ver, PHY_FW_VER_LEN);
-		strscpy(buf, bp->fw_ver, buf_len);
-		snprintf(buf + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
-			 "bc %d.%d.%d%s%s",
+					     phy_fw_ver, sizeof(phy_fw_ver));
+		/* This may become truncated. */
+		scnprintf(buf, buf_len,
+			 "%sbc %d.%d.%d%s%s",
+			 bp->fw_ver,
 			 (bp->common.bc_ver & 0xff0000) >> 16,
 			 (bp->common.bc_ver & 0xff00) >> 8,
 			 (bp->common.bc_ver & 0xff),
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index bda3ccc28e..0bc7690cde 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1132,7 +1132,7 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 	}
 
 	memset(version, 0, sizeof(version));
-	bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN);
+	bnx2x_fill_fw_str(bp, version, sizeof(version));
 	strlcat(info->fw_version, version, sizeof(info->fw_version));
 
 	strscpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
@@ -3486,16 +3486,15 @@ static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 	return T_ETH_INDIRECTION_TABLE_SIZE;
 }
 
-static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int bnx2x_get_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
 	size_t i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	/* Get the current configuration of the RSS indirection table */
@@ -3511,13 +3510,14 @@ static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	 * queue.
 	 */
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++)
-		indir[i] = ind_table[i] - bp->fp->cl_id;
+		rxfh->indir[i] = ind_table[i] - bp->fp->cl_id;
 
 	return 0;
 }
 
-static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int bnx2x_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
@@ -3525,11 +3525,12 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
@@ -3542,7 +3543,7 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		 * align the received table to the Client ID of the leading RSS
 		 * queue
 		 */
-		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
+		bp->rss_conf_obj.ind_table[i] = rxfh->indir[i] + bp->fp->cl_id;
 	}
 
 	if (bp->state == BNX2X_STATE_OPEN)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 02808513ff..ea310057fe 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6163,8 +6163,8 @@ static void bnx2x_link_int_ack(struct link_params *params,
 
 static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 {
-	str[0] = '\0';
-	(*len)--;
+	if (*len)
+		str[0] = '\0';
 	return 0;
 }
 
@@ -6173,7 +6173,7 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len)
 	u16 ret;
 
 	if (*len < 10) {
-		/* Need more than 10chars for this format */
+		/* Need more than 10 chars for this format */
 		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
@@ -6188,8 +6188,8 @@ static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len)
 {
 	u16 ret;
 
-	if (*len < 10) {
-		/* Need more than 10chars for this format */
+	if (*len < 9) {
+		/* Need more than 9 chars for this format */
 		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
@@ -6208,7 +6208,7 @@ int bnx2x_get_ext_phy_fw_version(struct link_params *params, u8 *version,
 	int status = 0;
 	u8 *ver_p = version;
 	u16 remain_len = len;
-	if (version == NULL || params == NULL)
+	if (version == NULL || params == NULL || len == 0)
 		return -EINVAL;
 	bp = params->bp;
 
@@ -11546,7 +11546,7 @@ static int bnx2x_7101_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 	str[2] = (spirom_ver & 0xFF0000) >> 16;
 	str[3] = (spirom_ver & 0xFF000000) >> 24;
 	str[4] = '\0';
-	*len -= 5;
+	*len -= 4;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 22c8bfb5ed..e133a412a1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -120,6 +120,10 @@ static const struct {
 	[BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
 	[BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
 	[BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" },
+	[BCM57608] = { "Broadcom BCM57608 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
+	[BCM57604] = { "Broadcom BCM57604 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
+	[BCM57602] = { "Broadcom BCM57602 NetXtreme-E 10Gb/25Gb/50Gb/100Gb Ethernet" },
+	[BCM57601] = { "Broadcom BCM57601 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb/400Gb Ethernet" },
 	[BCM57508_NPAR] = { "Broadcom BCM57508 NetXtreme-E Ethernet Partition" },
 	[BCM57504_NPAR] = { "Broadcom BCM57504 NetXtreme-E Ethernet Partition" },
 	[BCM57502_NPAR] = { "Broadcom BCM57502 NetXtreme-E Ethernet Partition" },
@@ -174,6 +178,10 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 },
 	{ PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 },
 	{ PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 },
+	{ PCI_VDEVICE(BROADCOM, 0x1760), .driver_data = BCM57608 },
+	{ PCI_VDEVICE(BROADCOM, 0x1761), .driver_data = BCM57604 },
+	{ PCI_VDEVICE(BROADCOM, 0x1762), .driver_data = BCM57602 },
+	{ PCI_VDEVICE(BROADCOM, 0x1763), .driver_data = BCM57601 },
 	{ PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57502_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57508_NPAR },
@@ -254,22 +262,28 @@ static bool bnxt_vf_pciid(enum board_idx idx)
 		writel(DB_CP_IRQ_DIS_FLAGS, db)
 
 #define BNXT_DB_CQ(db, idx)						\
-	writel(DB_CP_FLAGS | RING_CMP(idx), (db)->doorbell)
+	writel(DB_CP_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
 
 #define BNXT_DB_NQ_P5(db, idx)						\
-	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ | RING_CMP(idx),	\
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ | DB_RING_IDX(db, idx),\
 		    (db)->doorbell)
 
+#define BNXT_DB_NQ_P7(db, idx)						\
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_MASK |		\
+		    DB_RING_IDX(db, idx), (db)->doorbell)
+
 #define BNXT_DB_CQ_ARM(db, idx)						\
-	writel(DB_CP_REARM_FLAGS | RING_CMP(idx), (db)->doorbell)
+	writel(DB_CP_REARM_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
 
 #define BNXT_DB_NQ_ARM_P5(db, idx)					\
-	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_ARM | RING_CMP(idx),\
-		    (db)->doorbell)
+	bnxt_writeq(bp, (db)->db_key64 | DBR_TYPE_NQ_ARM |		\
+		    DB_RING_IDX(db, idx), (db)->doorbell)
 
 static void bnxt_db_nq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P7)
+		BNXT_DB_NQ_P7(db, idx);
+	else if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		BNXT_DB_NQ_P5(db, idx);
 	else
 		BNXT_DB_CQ(db, idx);
@@ -277,7 +291,7 @@ static void bnxt_db_nq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 
 static void bnxt_db_nq_arm(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		BNXT_DB_NQ_ARM_P5(db, idx);
 	else
 		BNXT_DB_CQ_ARM(db, idx);
@@ -285,9 +299,9 @@ static void bnxt_db_nq_arm(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 
 static void bnxt_db_cq(struct bnxt *bp, struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_writeq(bp, db->db_key64 | DBR_TYPE_CQ_ARMALL |
-			    RING_CMP(idx), db->doorbell);
+			    DB_RING_IDX(db, idx), db->doorbell);
 	else
 		BNXT_DB_CQ(db, idx);
 }
@@ -321,7 +335,7 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
 		rxr->bnapi->in_reset = true;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
 		else
 			set_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event);
@@ -331,16 +345,16 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 }
 
 void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  int idx)
+			  u16 curr)
 {
 	struct bnxt_napi *bnapi = txr->bnapi;
 
 	if (bnapi->tx_fault)
 		return;
 
-	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_pkts:%d cons:%u prod:%u i:%d)",
-		   txr->txq_index, bnapi->tx_pkts,
-		   txr->tx_cons, txr->tx_prod, idx);
+	netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_hw_cons:%u cons:%u prod:%u curr:%u)",
+		   txr->txq_index, txr->tx_hw_cons,
+		   txr->tx_cons, txr->tx_prod, curr);
 	WARN_ON_ONCE(1);
 	bnapi->tx_fault = 1;
 	bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT);
@@ -381,6 +395,8 @@ static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb)
 static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			     u16 prod)
 {
+	/* Sync BD data before updating doorbell */
+	wmb();
 	bnxt_db_write(bp, &txr->tx_db, prod);
 	txr->kick_pending = 0;
 }
@@ -388,7 +404,7 @@ static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	struct tx_bd *txbd;
+	struct tx_bd *txbd, *txbd0;
 	struct tx_bd_ext *txbd1;
 	struct netdev_queue *txq;
 	int i;
@@ -430,11 +446,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = skb_headlen(skb);
 	last_frag = skb_shinfo(skb)->nr_frags;
 
-	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
-	txbd->tx_bd_opaque = prod;
-
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	tx_buf->skb = skb;
 	tx_buf->nr_frags = last_frag;
 
@@ -519,12 +533,15 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type;
 		txbd->tx_bd_haddr = txr->data_mapping;
+		txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2);
 		prod = NEXT_TX(prod);
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		tx_push->tx_bd_opaque = txbd->tx_bd_opaque;
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 		memcpy(txbd, tx_push1, sizeof(*txbd));
 		prod = NEXT_TX(prod);
 		tx_push->doorbell =
-			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
+			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH |
+				    DB_RING_IDX(&txr->tx_db, prod));
 		WRITE_ONCE(txr->tx_prod, prod);
 
 		tx_buf->is_push = 1;
@@ -562,19 +579,29 @@ normal_tx:
 		((last_frag + 2) << TX_BD_FLAGS_BD_CNT_SHIFT);
 
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
+	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 2 + last_frag);
 
 	prod = NEXT_TX(prod);
 	txbd1 = (struct tx_bd_ext *)
-		&txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 	txbd1->tx_bd_hsize_lflags = lflags;
 	if (skb_is_gso(skb)) {
+		bool udp_gso = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4);
 		u32 hdr_len;
 
-		if (skb->encapsulation)
-			hdr_len = skb_inner_tcp_all_headers(skb);
-		else
+		if (skb->encapsulation) {
+			if (udp_gso)
+				hdr_len = skb_inner_transport_offset(skb) +
+					  sizeof(struct udphdr);
+			else
+				hdr_len = skb_inner_tcp_all_headers(skb);
+		} else if (udp_gso) {
+			hdr_len = skb_transport_offset(skb) +
+				  sizeof(struct udphdr);
+		} else {
 			hdr_len = skb_tcp_all_headers(skb);
+		}
 
 		txbd1->tx_bd_hsize_lflags |= cpu_to_le32(TX_BD_FLAGS_LSO |
 					TX_BD_FLAGS_T_IPID |
@@ -601,11 +628,12 @@ normal_tx:
 	txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
 	txbd1->tx_bd_cfa_action =
 			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
+	txbd0 = txbd;
 	for (i = 0; i < last_frag; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 		prod = NEXT_TX(prod);
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 		len = skb_frag_size(frag);
 		mapping = skb_frag_dma_map(&pdev->dev, frag, 0, len,
@@ -614,7 +642,7 @@ normal_tx:
 		if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
 			goto tx_dma_error;
 
-		tx_buf = &txr->tx_buf_ring[prod];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		dma_unmap_addr_set(tx_buf, mapping, mapping);
 
 		txbd->tx_bd_haddr = cpu_to_le64(mapping);
@@ -632,22 +660,26 @@ normal_tx:
 
 	skb_tx_timestamp(skb);
 
-	/* Sync BD data before updating doorbell */
-	wmb();
-
 	prod = NEXT_TX(prod);
 	WRITE_ONCE(txr->tx_prod, prod);
 
-	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
 		bnxt_txr_db_kick(bp, txr, prod);
-	else
+	} else {
+		if (free_size >= bp->tx_wake_thresh)
+			txbd0->tx_bd_len_flags_type |=
+				cpu_to_le32(TX_BD_FLAGS_NO_CMPL);
 		txr->kick_pending = 1;
+	}
 
 tx_done:
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
-		if (netdev_xmit_more() && !tx_buf->is_push)
+		if (netdev_xmit_more() && !tx_buf->is_push) {
+			txbd0->tx_bd_len_flags_type &=
+				cpu_to_le32(~TX_BD_FLAGS_NO_CMPL);
 			bnxt_txr_db_kick(bp, txr, prod);
+		}
 
 		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
 				   bp->tx_wake_thresh);
@@ -662,7 +694,7 @@ tx_dma_error:
 
 	/* start back at beginning and unmap skb */
 	prod = txr->tx_prod;
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			 skb_headlen(skb), DMA_TO_DEVICE);
 	prod = NEXT_TX(prod);
@@ -670,7 +702,7 @@ tx_dma_error:
 	/* unmap remaining mapped pages */
 	for (i = 0; i < last_frag; i++) {
 		prod = NEXT_TX(prod);
-		tx_buf = &txr->tx_buf_ring[prod];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		dma_unmap_page(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
 			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
 			       DMA_TO_DEVICE);
@@ -686,31 +718,32 @@ tx_kick_pending:
 	return NETDEV_TX_OK;
 }
 
-static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
+static void __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			  int budget)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
 	struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
-	u16 cons = txr->tx_cons;
 	struct pci_dev *pdev = bp->pdev;
-	int nr_pkts = bnapi->tx_pkts;
-	int i;
+	u16 hw_cons = txr->tx_hw_cons;
 	unsigned int tx_bytes = 0;
+	u16 cons = txr->tx_cons;
+	int tx_pkts = 0;
 
-	for (i = 0; i < nr_pkts; i++) {
+	while (RING_TX(bp, cons) != hw_cons) {
 		struct bnxt_sw_tx_bd *tx_buf;
 		struct sk_buff *skb;
 		int j, last;
 
-		tx_buf = &txr->tx_buf_ring[cons];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
 		cons = NEXT_TX(cons);
 		skb = tx_buf->skb;
 		tx_buf->skb = NULL;
 
 		if (unlikely(!skb)) {
-			bnxt_sched_reset_txr(bp, txr, i);
+			bnxt_sched_reset_txr(bp, txr, cons);
 			return;
 		}
 
+		tx_pkts++;
 		tx_bytes += skb->len;
 
 		if (tx_buf->is_push) {
@@ -724,7 +757,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 
 		for (j = 0; j < last; j++) {
 			cons = NEXT_TX(cons);
-			tx_buf = &txr->tx_buf_ring[cons];
+			tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
 			dma_unmap_page(
 				&pdev->dev,
 				dma_unmap_addr(tx_buf, mapping),
@@ -732,7 +765,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 				DMA_TO_DEVICE);
 		}
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (BNXT_CHIP_P5(bp)) {
 				/* PTP worker takes ownership of the skb */
 				if (!bnxt_get_tx_ts_p5(bp, skb))
 					skb = NULL;
@@ -747,14 +780,25 @@ next_tx_int:
 		dev_consume_skb_any(skb);
 	}
 
-	bnapi->tx_pkts = 0;
 	WRITE_ONCE(txr->tx_cons, cons);
 
-	__netif_txq_completed_wake(txq, nr_pkts, tx_bytes,
+	__netif_txq_completed_wake(txq, tx_pkts, tx_bytes,
 				   bnxt_tx_avail(bp, txr), bp->tx_wake_thresh,
 				   READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING);
 }
 
+static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
+{
+	struct bnxt_tx_ring_info *txr;
+	int i;
+
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		if (txr->tx_hw_cons != RING_TX(bp, txr->tx_cons))
+			__bnxt_tx_int(bp, txr, budget);
+	}
+	bnapi->events &= ~BNXT_TX_CMP_EVENT;
+}
+
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 					 struct bnxt_rx_ring_info *rxr,
 					 unsigned int *offset,
@@ -803,8 +847,8 @@ static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		       u16 prod, gfp_t gfp)
 {
-	struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
-	struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[prod];
+	struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
+	struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	dma_addr_t mapping;
 
 	if (BNXT_RX_PAGE_MODE(bp)) {
@@ -837,9 +881,10 @@ void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data)
 {
 	u16 prod = rxr->rx_prod;
 	struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
+	struct bnxt *bp = rxr->bnapi->bp;
 	struct rx_bd *cons_bd, *prod_bd;
 
-	prod_rx_buf = &rxr->rx_buf_ring[prod];
+	prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
 
 	prod_rx_buf->data = data;
@@ -847,8 +892,8 @@ void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data)
 
 	prod_rx_buf->mapping = cons_rx_buf->mapping;
 
-	prod_bd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
-	cons_bd = &rxr->rx_desc_ring[RX_RING(cons)][RX_IDX(cons)];
+	prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
+	cons_bd = &rxr->rx_desc_ring[RX_RING(bp, cons)][RX_IDX(cons)];
 
 	prod_bd->rx_bd_haddr = cons_bd->rx_bd_haddr;
 }
@@ -868,7 +913,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 				     u16 prod, gfp_t gfp)
 {
 	struct rx_bd *rxbd =
-		&rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+		&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
 	struct page *page;
 	dma_addr_t mapping;
@@ -885,7 +930,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 
 	__set_bit(sw_prod, rxr->rx_agg_bmap);
 	rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
-	rxr->rx_sw_agg_prod = NEXT_RX_AGG(sw_prod);
+	rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 
 	rx_agg_buf->page = page;
 	rx_agg_buf->offset = offset;
@@ -927,7 +972,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 	bool p5_tpa = false;
 	u32 i;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
@@ -961,13 +1006,13 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 
 		prod_rx_buf->mapping = cons_rx_buf->mapping;
 
-		prod_bd = &rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+		prod_bd = &rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
 
 		prod_bd->rx_bd_haddr = cpu_to_le64(cons_rx_buf->mapping);
 		prod_bd->rx_bd_opaque = sw_prod;
 
 		prod = NEXT_RX_AGG(prod);
-		sw_prod = NEXT_RX_AGG(sw_prod);
+		sw_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
 	}
 	rxr->rx_agg_prod = prod;
 	rxr->rx_sw_agg_prod = sw_prod;
@@ -1094,7 +1139,7 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
@@ -1249,7 +1294,7 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
 		struct rx_tpa_end_cmp *tpa_end = cmp;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			return 0;
 
 		agg_bufs = TPA_END_AGG_BUFS(tpa_end);
@@ -1290,8 +1335,39 @@ static u16 bnxt_lookup_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id)
 	return map->agg_id_tbl[agg_id];
 }
 
+static void bnxt_tpa_metadata(struct bnxt_tpa_info *tpa_info,
+			      struct rx_tpa_start_cmp *tpa_start,
+			      struct rx_tpa_start_cmp_ext *tpa_start1)
+{
+	tpa_info->cfa_code_valid = 1;
+	tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
+	tpa_info->vlan_valid = 0;
+	if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
+		tpa_info->vlan_valid = 1;
+		tpa_info->metadata =
+			le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
+	}
+}
+
+static void bnxt_tpa_metadata_v2(struct bnxt_tpa_info *tpa_info,
+				 struct rx_tpa_start_cmp *tpa_start,
+				 struct rx_tpa_start_cmp_ext *tpa_start1)
+{
+	tpa_info->vlan_valid = 0;
+	if (TPA_START_VLAN_VALID(tpa_start)) {
+		u32 tpid_sel = TPA_START_VLAN_TPID_SEL(tpa_start);
+		u32 vlan_proto = ETH_P_8021Q;
+
+		tpa_info->vlan_valid = 1;
+		if (tpid_sel == RX_TPA_START_METADATA1_TPID_8021AD)
+			vlan_proto = ETH_P_8021AD;
+		tpa_info->metadata = vlan_proto << 16 |
+				     TPA_START_METADATA0_TCI(tpa_start1);
+	}
+}
+
 static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
-			   struct rx_tpa_start_cmp *tpa_start,
+			   u8 cmp_type, struct rx_tpa_start_cmp *tpa_start,
 			   struct rx_tpa_start_cmp_ext *tpa_start1)
 {
 	struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf;
@@ -1300,7 +1376,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	struct rx_bd *prod_bd;
 	dma_addr_t mapping;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		agg_id = TPA_START_AGG_ID_P5(tpa_start);
 		agg_id = bnxt_alloc_agg_idx(rxr, agg_id);
 	} else {
@@ -1309,7 +1385,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	cons = tpa_start->rx_tpa_start_cmp_opaque;
 	prod = rxr->rx_prod;
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
-	prod_rx_buf = &rxr->rx_buf_ring[prod];
+	prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bp, prod)];
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons ||
@@ -1320,17 +1396,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		bnxt_sched_reset_rxr(bp, rxr);
 		return;
 	}
-	/* Store cfa_code in tpa_info to use in tpa_end
-	 * completion processing.
-	 */
-	tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1);
 	prod_rx_buf->data = tpa_info->data;
 	prod_rx_buf->data_ptr = tpa_info->data_ptr;
 
 	mapping = tpa_info->mapping;
 	prod_rx_buf->mapping = mapping;
 
-	prod_bd = &rxr->rx_desc_ring[RX_RING(prod)][RX_IDX(prod)];
+	prod_bd = &rxr->rx_desc_ring[RX_RING(bp, prod)][RX_IDX(prod)];
 
 	prod_bd->rx_bd_haddr = cpu_to_le64(mapping);
 
@@ -1343,12 +1415,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		le32_to_cpu(tpa_start->rx_tpa_start_cmp_len_flags_type) >>
 				RX_TPA_START_CMP_LEN_SHIFT;
 	if (likely(TPA_START_HASH_VALID(tpa_start))) {
-		u32 hash_type = TPA_START_HASH_TYPE(tpa_start);
-
 		tpa_info->hash_type = PKT_HASH_TYPE_L4;
 		tpa_info->gso_type = SKB_GSO_TCPV4;
+		if (TPA_START_IS_IPV6(tpa_start1))
+			tpa_info->gso_type = SKB_GSO_TCPV6;
 		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type == 3 || TPA_START_IS_IPV6(tpa_start1))
+		else if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP &&
+			 TPA_START_HASH_TYPE(tpa_start) == 3)
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		tpa_info->rss_hash =
 			le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash);
@@ -1358,13 +1431,16 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		netif_warn(bp, rx_err, bp->dev, "TPA packet without valid hash\n");
 	}
 	tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2);
-	tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
 	tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info);
+	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP)
+		bnxt_tpa_metadata(tpa_info, tpa_start, tpa_start1);
+	else
+		bnxt_tpa_metadata_v2(tpa_info, tpa_start, tpa_start1);
 	tpa_info->agg_count = 0;
 
 	rxr->rx_prod = NEXT_RX(prod);
-	cons = NEXT_RX(cons);
-	rxr->rx_next_cons = NEXT_RX(cons);
+	cons = RING_RX(bp, NEXT_RX(cons));
+	rxr->rx_next_cons = RING_RX(bp, NEXT_RX(cons));
 	cons_rx_buf = &rxr->rx_buf_ring[cons];
 
 	bnxt_reuse_rx_data(rxr, cons, cons_rx_buf->data);
@@ -1563,7 +1639,7 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
 	skb_shinfo(skb)->gso_size =
 		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
 	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		payload_off = TPA_END_PAYLOAD_OFF_P5(tpa_end1);
 	else
 		payload_off = TPA_END_PAYLOAD_OFF(tpa_end);
@@ -1594,6 +1670,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	struct net_device *dev = bp->dev;
 	u8 *data_ptr, agg_bufs;
 	unsigned int len;
 	struct bnxt_tpa_info *tpa_info;
@@ -1611,7 +1688,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		return NULL;
 	}
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		agg_id = TPA_END_AGG_ID_P5(tpa_end);
 		agg_id = bnxt_lookup_agg_idx(rxr, agg_id);
 		agg_bufs = TPA_END_AGG_BUFS_P5(tpa_end1);
@@ -1658,7 +1735,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
 		if (!skb) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
-			cpr->sw_stats.rx.rx_oom_discards += 1;
+			cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 	} else {
@@ -1668,7 +1745,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC);
 		if (!new_data) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
-			cpr->sw_stats.rx.rx_oom_discards += 1;
+			cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 
@@ -1684,7 +1761,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		if (!skb) {
 			skb_free_frag(data);
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
-			cpr->sw_stats.rx.rx_oom_discards += 1;
+			cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 		skb_reserve(skb, bp->rx_offset);
@@ -1695,19 +1772,20 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
 		if (!skb) {
 			/* Page reuse already handled by bnxt_rx_pages(). */
-			cpr->sw_stats.rx.rx_oom_discards += 1;
+			cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
 			return NULL;
 		}
 	}
 
-	skb->protocol =
-		eth_type_trans(skb, bnxt_get_pkt_dev(bp, tpa_info->cfa_code));
+	if (tpa_info->cfa_code_valid)
+		dev = bnxt_get_pkt_dev(bp, tpa_info->cfa_code);
+	skb->protocol = eth_type_trans(skb, dev);
 
 	if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
 		skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
 
-	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
-	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
+	if (tpa_info->vlan_valid &&
+	    (dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
 		__be16 vlan_proto = htons(tpa_info->metadata >>
 					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
 		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
@@ -1774,6 +1852,64 @@ ts_valid:
 	return true;
 }
 
+static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
+				    struct rx_cmp *rxcmp,
+				    struct rx_cmp_ext *rxcmp1)
+{
+	__be16 vlan_proto;
+	u16 vtag;
+
+	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
+		__le32 flags2 = rxcmp1->rx_cmp_flags2;
+		u32 meta_data;
+
+		if (!(flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)))
+			return skb;
+
+		meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
+		vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
+		vlan_proto = htons(meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT);
+		if (eth_type_vlan(vlan_proto))
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		else
+			goto vlan_err;
+	} else if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
+		if (RX_CMP_VLAN_VALID(rxcmp)) {
+			u32 tpid_sel = RX_CMP_VLAN_TPID_SEL(rxcmp);
+
+			if (tpid_sel == RX_CMP_METADATA1_TPID_8021Q)
+				vlan_proto = htons(ETH_P_8021Q);
+			else if (tpid_sel == RX_CMP_METADATA1_TPID_8021AD)
+				vlan_proto = htons(ETH_P_8021AD);
+			else
+				goto vlan_err;
+			vtag = RX_CMP_METADATA0_TCI(rxcmp1);
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		}
+	}
+	return skb;
+vlan_err:
+	dev_kfree_skb(skb);
+	return NULL;
+}
+
+static enum pkt_hash_types bnxt_rss_ext_op(struct bnxt *bp,
+					   struct rx_cmp *rxcmp)
+{
+	u8 ext_op;
+
+	ext_op = RX_CMP_V3_HASH_TYPE(bp, rxcmp);
+	switch (ext_op) {
+	case EXT_OP_INNER_4:
+	case EXT_OP_OUTER_4:
+	case EXT_OP_INNFL_3:
+	case EXT_OP_OUTFL_3:
+		return PKT_HASH_TYPE_L4;
+	default:
+		return PKT_HASH_TYPE_L3;
+	}
+}
+
 /* returns the following:
  * 1       - 1 packet successfully received
  * 0       - successful TPA_START, packet not completed yet
@@ -1790,7 +1926,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp *rxcmp;
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
-	u16 cfa_code, cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -1827,8 +1963,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	dma_rmb();
 	prod = rxr->rx_prod;
 
-	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) {
-		bnxt_tpa_start(bp, rxr, (struct rx_tpa_start_cmp *)rxcmp,
+	if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP ||
+	    cmp_type == CMP_TYPE_RX_L2_TPA_START_V3_CMP) {
+		bnxt_tpa_start(bp, rxr, cmp_type,
+			       (struct rx_tpa_start_cmp *)rxcmp,
 			       (struct rx_tpa_start_cmp_ext *)rxcmp1);
 
 		*event |= BNXT_RX_EVENT;
@@ -1893,7 +2031,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		rc = -EIO;
 		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
 			bnapi->cp_ring.sw_stats.rx.rx_buf_errors++;
-			if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+			if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 			    !(bp->fw_cap & BNXT_FW_CAP_RING_MONITOR)) {
 				netdev_warn_once(bp->dev, "RX buffer error %x\n",
 						 rx_err);
@@ -1913,11 +2051,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
 							     cp_cons, agg_bufs,
 							     false);
-			if (!frag_len) {
-				cpr->sw_stats.rx.rx_oom_discards += 1;
-				rc = -ENOMEM;
-				goto next_rx;
-			}
+			if (!frag_len)
+				goto oom_next_rx;
 		}
 		xdp_active = true;
 	}
@@ -1940,9 +2075,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 				else
 					bnxt_xdp_buff_frags_free(rxr, &xdp);
 			}
-			cpr->sw_stats.rx.rx_oom_discards += 1;
-			rc = -ENOMEM;
-			goto next_rx;
+			goto oom_next_rx;
 		}
 	} else {
 		u32 payload;
@@ -1953,60 +2086,52 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			payload = 0;
 		skb = bp->rx_skb_func(bp, rxr, cons, data, data_ptr, dma_addr,
 				      payload | len);
-		if (!skb) {
-			cpr->sw_stats.rx.rx_oom_discards += 1;
-			rc = -ENOMEM;
-			goto next_rx;
-		}
+		if (!skb)
+			goto oom_next_rx;
 	}
 
 	if (agg_bufs) {
 		if (!xdp_active) {
 			skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
-			if (!skb) {
-				cpr->sw_stats.rx.rx_oom_discards += 1;
-				rc = -ENOMEM;
-				goto next_rx;
-			}
+			if (!skb)
+				goto oom_next_rx;
 		} else {
 			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
-				cpr->sw_stats.rx.rx_oom_discards += 1;
-				rc = -ENOMEM;
-				goto next_rx;
+				goto oom_next_rx;
 			}
 		}
 	}
 
 	if (RX_CMP_HASH_VALID(rxcmp)) {
-		u32 hash_type = RX_CMP_HASH_TYPE(rxcmp);
-		enum pkt_hash_types type = PKT_HASH_TYPE_L4;
+		enum pkt_hash_types type;
 
-		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type != 1 && hash_type != 3)
-			type = PKT_HASH_TYPE_L3;
+		if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
+			type = bnxt_rss_ext_op(bp, rxcmp);
+		} else {
+			u32 hash_type = RX_CMP_HASH_TYPE(rxcmp);
+
+			/* RSS profiles 1 and 3 with extract code 0 for inner
+			 * 4-tuple
+			 */
+			if (hash_type != 1 && hash_type != 3)
+				type = PKT_HASH_TYPE_L3;
+			else
+				type = PKT_HASH_TYPE_L4;
+		}
 		skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type);
 	}
 
-	cfa_code = RX_CMP_CFA_CODE(rxcmp1);
-	skb->protocol = eth_type_trans(skb, bnxt_get_pkt_dev(bp, cfa_code));
-
-	if ((rxcmp1->rx_cmp_flags2 &
-	     cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
-	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
-		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
-		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
-		__be16 vlan_proto = htons(meta_data >>
-					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
+	if (cmp_type == CMP_TYPE_RX_L2_CMP)
+		dev = bnxt_get_pkt_dev(bp, RX_CMP_CFA_CODE(rxcmp1));
+	skb->protocol = eth_type_trans(skb, dev);
 
-		if (eth_type_vlan(vlan_proto)) {
-			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
-		} else {
-			dev_kfree_skb(skb);
+	if (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX) {
+		skb = bnxt_rx_vlan(skb, cmp_type, rxcmp, rxcmp1);
+		if (!skb)
 			goto next_rx;
-		}
 	}
 
 	skb_checksum_none_assert(skb);
@@ -2023,7 +2148,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) {
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			u64 ns, ts;
 
 			if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
@@ -2047,12 +2172,17 @@ next_rx:
 
 next_rx_no_len:
 	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
+	rxr->rx_next_cons = RING_RX(bp, NEXT_RX(cons));
 
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
 	return rc;
+
+oom_next_rx:
+	cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+	rc = -ENOMEM;
+	goto next_rx;
 }
 
 /* In netpoll mode, if we are using a combined completion ring, we need to
@@ -2086,7 +2216,8 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	 */
 	dma_rmb();
 	cmp_type = RX_CMP_TYPE(rxcmp);
-	if (cmp_type == CMP_TYPE_RX_L2_CMP) {
+	if (cmp_type == CMP_TYPE_RX_L2_CMP ||
+	    cmp_type == CMP_TYPE_RX_L2_V3_CMP) {
 		rxcmp1->rx_cmp_cfa_code_errors_v2 |=
 			cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR);
 	} else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) {
@@ -2098,7 +2229,7 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	}
 	rc = bnxt_rx_pkt(bp, cpr, raw_cons, event);
 	if (rc && rc != -EBUSY)
-		cpr->sw_stats.rx.rx_netpoll_discards += 1;
+		cpr->bnapi->cp_ring.sw_stats.rx.rx_netpoll_discards += 1;
 	return rc;
 }
 
@@ -2146,6 +2277,10 @@ static u16 bnxt_agg_ring_id_to_grp_idx(struct bnxt *bp, u16 ring_id)
 
 static u16 bnxt_get_force_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2)
+		return link_info->force_link_speed2;
 	if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4)
 		return link_info->force_pam4_link_speed;
 	return link_info->force_link_speed;
@@ -2153,6 +2288,28 @@ static u16 bnxt_get_force_speed(struct bnxt_link_info *link_info)
 
 static void bnxt_set_force_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		link_info->req_link_speed = link_info->force_link_speed2;
+		link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
+		switch (link_info->req_link_speed) {
+		case BNXT_LINK_SPEED_50GB_PAM4:
+		case BNXT_LINK_SPEED_100GB_PAM4:
+		case BNXT_LINK_SPEED_200GB_PAM4:
+		case BNXT_LINK_SPEED_400GB_PAM4:
+			link_info->req_signal_mode = BNXT_SIG_MODE_PAM4;
+			break;
+		case BNXT_LINK_SPEED_100GB_PAM4_112:
+		case BNXT_LINK_SPEED_200GB_PAM4_112:
+		case BNXT_LINK_SPEED_400GB_PAM4_112:
+			link_info->req_signal_mode = BNXT_SIG_MODE_PAM4_112;
+			break;
+		default:
+			link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
+		}
+		return;
+	}
 	link_info->req_link_speed = link_info->force_link_speed;
 	link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
 	if (link_info->force_pam4_link_speed) {
@@ -2163,12 +2320,25 @@ static void bnxt_set_force_speed(struct bnxt_link_info *link_info)
 
 static void bnxt_set_auto_speed(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		link_info->advertising = link_info->auto_link_speeds2;
+		return;
+	}
 	link_info->advertising = link_info->auto_link_speeds;
 	link_info->advertising_pam4 = link_info->auto_pam4_link_speeds;
 }
 
 static bool bnxt_force_speed_updated(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (link_info->req_link_speed != link_info->force_link_speed2)
+			return true;
+		return false;
+	}
 	if (link_info->req_signal_mode == BNXT_SIG_MODE_NRZ &&
 	    link_info->req_link_speed != link_info->force_link_speed)
 		return true;
@@ -2180,6 +2350,13 @@ static bool bnxt_force_speed_updated(struct bnxt_link_info *link_info)
 
 static bool bnxt_auto_speed_updated(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (link_info->advertising != link_info->auto_link_speeds2)
+			return true;
+		return false;
+	}
 	if (link_info->advertising != link_info->auto_link_speeds ||
 	    link_info->advertising_pam4 != link_info->auto_pam4_link_speeds)
 		return true;
@@ -2430,7 +2607,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		struct bnxt_rx_ring_info *rxr;
 		u16 grp_idx;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			goto async_event_process_exit;
 
 		netdev_warn(bp->dev, "Ring monitor event, ring type %lu id 0x%x\n",
@@ -2603,7 +2780,6 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
 	u32 cons;
-	int tx_pkts = 0;
 	int rx_pkts = 0;
 	u8 event = 0;
 	struct tx_cmp *txcmp;
@@ -2611,6 +2787,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	cpr->has_more_work = 0;
 	cpr->had_work_done = 1;
 	while (1) {
+		u8 cmp_type;
 		int rc;
 
 		cons = RING_CMP(raw_cons);
@@ -2623,17 +2800,31 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		 * reading any further.
 		 */
 		dma_rmb();
-		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) {
-			tx_pkts++;
+		cmp_type = TX_CMP_TYPE(txcmp);
+		if (cmp_type == CMP_TYPE_TX_L2_CMP ||
+		    cmp_type == CMP_TYPE_TX_L2_COAL_CMP) {
+			u32 opaque = txcmp->tx_cmp_opaque;
+			struct bnxt_tx_ring_info *txr;
+			u16 tx_freed;
+
+			txr = bnapi->tx_ring[TX_OPAQUE_RING(opaque)];
+			event |= BNXT_TX_CMP_EVENT;
+			if (cmp_type == CMP_TYPE_TX_L2_COAL_CMP)
+				txr->tx_hw_cons = TX_CMP_SQ_CONS_IDX(txcmp);
+			else
+				txr->tx_hw_cons = TX_OPAQUE_PROD(bp, opaque);
+			tx_freed = (txr->tx_hw_cons - txr->tx_cons) &
+				   bp->tx_ring_mask;
 			/* return full budget so NAPI will complete. */
-			if (unlikely(tx_pkts >= bp->tx_wake_thresh)) {
+			if (unlikely(tx_freed >= bp->tx_wake_thresh)) {
 				rx_pkts = budget;
 				raw_cons = NEXT_RAW_CMP(raw_cons);
 				if (budget)
 					cpr->has_more_work = 1;
 				break;
 			}
-		} else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) {
+		} else if (cmp_type >= CMP_TYPE_RX_L2_CMP &&
+			   cmp_type <= CMP_TYPE_RX_L2_TPA_START_V3_CMP) {
 			if (likely(budget))
 				rc = bnxt_rx_pkt(bp, cpr, &raw_cons, &event);
 			else
@@ -2650,12 +2841,9 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
-		} else if (unlikely((TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_DONE) ||
-				    (TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_FWD_REQ) ||
-				    (TX_CMP_TYPE(txcmp) ==
-				     CMPL_BASE_TYPE_HWRM_ASYNC_EVENT))) {
+		} else if (unlikely(cmp_type == CMPL_BASE_TYPE_HWRM_DONE ||
+				    cmp_type == CMPL_BASE_TYPE_HWRM_FWD_REQ ||
+				    cmp_type == CMPL_BASE_TYPE_HWRM_ASYNC_EVENT)) {
 			bnxt_hwrm_handler(bp, txcmp);
 		}
 		raw_cons = NEXT_RAW_CMP(raw_cons);
@@ -2670,7 +2858,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		xdp_do_flush();
 
 	if (event & BNXT_TX_EVENT) {
-		struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
+		struct bnxt_tx_ring_info *txr = bnapi->tx_ring[0];
 		u16 prod = txr->tx_prod;
 
 		/* Sync BD data before updating doorbell */
@@ -2680,7 +2868,6 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cpr->cp_raw_cons = raw_cons;
-	bnapi->tx_pkts += tx_pkts;
 	bnapi->events |= event;
 	return rx_pkts;
 }
@@ -2688,7 +2875,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 				  int budget)
 {
-	if (bnapi->tx_pkts && !bnapi->tx_fault)
+	if ((bnapi->events & BNXT_TX_CMP_EVENT) && !bnapi->tx_fault)
 		bnapi->tx_int(bp, bnapi, budget);
 
 	if ((bnapi->events & BNXT_RX_EVENT) && !(bnapi->in_reset)) {
@@ -2701,7 +2888,7 @@ static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 	}
-	bnapi->events = 0;
+	bnapi->events &= BNXT_TX_CMP_EVENT;
 }
 
 static int bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
@@ -2841,10 +3028,10 @@ static int __bnxt_poll_cqs(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	int i, work_done = 0;
 
-	for (i = 0; i < 2; i++) {
-		struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[i];
+	for (i = 0; i < cpr->cp_ring_count; i++) {
+		struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[i];
 
-		if (cpr2) {
+		if (cpr2->had_nqe_notify) {
 			work_done += __bnxt_poll_work(bp, cpr2,
 						      budget - work_done);
 			cpr->has_more_work |= cpr2->has_more_work;
@@ -2859,14 +3046,22 @@ static void __bnxt_poll_cqs_done(struct bnxt *bp, struct bnxt_napi *bnapi,
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	int i;
 
-	for (i = 0; i < 2; i++) {
-		struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[i];
+	for (i = 0; i < cpr->cp_ring_count; i++) {
+		struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[i];
 		struct bnxt_db_info *db;
 
-		if (cpr2 && cpr2->had_work_done) {
+		if (cpr2->had_work_done) {
+			u32 tgl = 0;
+
+			if (dbr_type == DBR_TYPE_CQ_ARMALL) {
+				cpr2->had_nqe_notify = 0;
+				tgl = cpr2->toggle;
+			}
 			db = &cpr2->cp_db;
-			bnxt_writeq(bp, db->db_key64 | dbr_type |
-				    RING_CMP(cpr2->cp_raw_cons), db->doorbell);
+			bnxt_writeq(bp,
+				    db->db_key64 | dbr_type | DB_TOGGLE(tgl) |
+				    DB_RING_IDX(db, cpr2->cp_raw_cons),
+				    db->doorbell);
 			cpr2->had_work_done = 0;
 		}
 	}
@@ -2893,6 +3088,8 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		work_done = __bnxt_poll_cqs(bp, bnapi, budget);
 	}
 	while (1) {
+		u16 type;
+
 		cons = RING_CMP(raw_cons);
 		nqcmp = &cpr->nq_desc_ring[CP_RING(cons)][CP_IDX(cons)];
 
@@ -2914,15 +3111,21 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		 */
 		dma_rmb();
 
-		if (nqcmp->type == cpu_to_le16(NQ_CN_TYPE_CQ_NOTIFICATION)) {
+		type = le16_to_cpu(nqcmp->type);
+		if (NQE_CN_TYPE(type) == NQ_CN_TYPE_CQ_NOTIFICATION) {
 			u32 idx = le32_to_cpu(nqcmp->cq_handle_low);
+			u32 cq_type = BNXT_NQ_HDL_TYPE(idx);
 			struct bnxt_cp_ring_info *cpr2;
 
 			/* No more budget for RX work */
-			if (budget && work_done >= budget && idx == BNXT_RX_HDL)
+			if (budget && work_done >= budget &&
+			    cq_type == BNXT_NQ_HDL_TYPE_RX)
 				break;
 
-			cpr2 = cpr->cp_ring_arr[idx];
+			idx = BNXT_NQ_HDL_IDX(idx);
+			cpr2 = &cpr->cp_ring_arr[idx];
+			cpr2->had_nqe_notify = 1;
+			cpr2->toggle = NQE_CN_TOGGLE(type);
 			work_done += __bnxt_poll_work(bp, cpr2,
 						      budget - work_done);
 			cpr->has_more_work |= cpr2->has_more_work;
@@ -2937,8 +3140,9 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 		BNXT_DB_NQ_P5(&cpr->cp_db, raw_cons);
 	}
 poll_done:
-	cpr_rx = cpr->cp_ring_arr[BNXT_RX_HDL];
-	if (cpr_rx && (bp->flags & BNXT_FLAG_DIM)) {
+	cpr_rx = &cpr->cp_ring_arr[0];
+	if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX &&
+	    (bp->flags & BNXT_FLAG_DIM)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3112,20 +3316,20 @@ static void bnxt_free_skbs(struct bnxt *bp)
 	bnxt_free_rx_skbs(bp);
 }
 
-static void bnxt_init_ctx_mem(struct bnxt_mem_init *mem_init, void *p, int len)
+static void bnxt_init_ctx_mem(struct bnxt_ctx_mem_type *ctxm, void *p, int len)
 {
-	u8 init_val = mem_init->init_val;
-	u16 offset = mem_init->offset;
+	u8 init_val = ctxm->init_value;
+	u16 offset = ctxm->init_offset;
 	u8 *p2 = p;
 	int i;
 
 	if (!init_val)
 		return;
-	if (offset == BNXT_MEM_INVALID_OFFSET) {
+	if (offset == BNXT_CTX_INIT_INVALID_OFFSET) {
 		memset(p, init_val, len);
 		return;
 	}
-	for (i = 0; i < len; i += mem_init->size)
+	for (i = 0; i < len; i += ctxm->entry_size)
 		*(p2 + i + offset) = init_val;
 }
 
@@ -3192,8 +3396,8 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		if (!rmem->pg_arr[i])
 			return -ENOMEM;
 
-		if (rmem->mem_init)
-			bnxt_init_ctx_mem(rmem->mem_init, rmem->pg_arr[i],
+		if (rmem->ctx_mem)
+			bnxt_init_ctx_mem(rmem->ctx_mem, rmem->pg_arr[i],
 					  rmem->page_size);
 		if (rmem->nr_pages > 1 || rmem->depth > 0) {
 			if (i == rmem->nr_pages - 2 &&
@@ -3240,7 +3444,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 	int i, j;
 
 	bp->max_tpa = MAX_TPA;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		if (!bp->max_tpa_v2)
 			return 0;
 		bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5);
@@ -3255,7 +3459,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 		if (!rxr->rx_tpa)
 			return -ENOMEM;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 		for (j = 0; j < bp->max_tpa; j++) {
 			agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
@@ -3313,6 +3517,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 		pp.pool_size += bp->rx_ring_size;
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
+	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
 	pp.max_len = PAGE_SIZE;
@@ -3410,6 +3615,15 @@ static void bnxt_free_tx_rings(struct bnxt *bp)
 	}
 }
 
+#define BNXT_TC_TO_RING_BASE(bp, tc)	\
+	((tc) * (bp)->tx_nr_rings_per_tc)
+
+#define BNXT_RING_TO_TC_OFF(bp, tx)	\
+	((tx) % (bp)->tx_nr_rings_per_tc)
+
+#define BNXT_RING_TO_TC(bp, tx)		\
+	((tx) / (bp)->tx_nr_rings_per_tc)
+
 static int bnxt_alloc_tx_rings(struct bnxt *bp)
 {
 	int i, j, rc;
@@ -3465,7 +3679,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		spin_lock_init(&txr->xdp_tx_lock);
 		if (i < bp->tx_nr_rings_xdp)
 			continue;
-		if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
+		if (BNXT_RING_TO_TC_OFF(bp, i) == (bp->tx_nr_rings_per_tc - 1))
 			j++;
 	}
 	return 0;
@@ -3548,36 +3762,33 @@ static void bnxt_free_cp_rings(struct bnxt *bp)
 
 		bnxt_free_ring(bp, &ring->ring_mem);
 
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		if (!cpr->cp_ring_arr)
+			continue;
 
-			if (cpr2) {
-				ring = &cpr2->cp_ring_struct;
-				bnxt_free_ring(bp, &ring->ring_mem);
-				bnxt_free_cp_arrays(cpr2);
-				kfree(cpr2);
-				cpr->cp_ring_arr[j] = NULL;
-			}
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
+
+			ring = &cpr2->cp_ring_struct;
+			bnxt_free_ring(bp, &ring->ring_mem);
+			bnxt_free_cp_arrays(cpr2);
 		}
+		kfree(cpr->cp_ring_arr);
+		cpr->cp_ring_arr = NULL;
+		cpr->cp_ring_count = 0;
 	}
 }
 
-static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
+static int bnxt_alloc_cp_sub_ring(struct bnxt *bp,
+				  struct bnxt_cp_ring_info *cpr)
 {
 	struct bnxt_ring_mem_info *rmem;
 	struct bnxt_ring_struct *ring;
-	struct bnxt_cp_ring_info *cpr;
 	int rc;
 
-	cpr = kzalloc(sizeof(*cpr), GFP_KERNEL);
-	if (!cpr)
-		return NULL;
-
 	rc = bnxt_alloc_cp_arrays(cpr, bp->cp_nr_pages);
 	if (rc) {
 		bnxt_free_cp_arrays(cpr);
-		kfree(cpr);
-		return NULL;
+		return -ENOMEM;
 	}
 	ring = &cpr->cp_ring_struct;
 	rmem = &ring->ring_mem;
@@ -3590,23 +3801,26 @@ static struct bnxt_cp_ring_info *bnxt_alloc_cp_sub_ring(struct bnxt *bp)
 	if (rc) {
 		bnxt_free_ring(bp, rmem);
 		bnxt_free_cp_arrays(cpr);
-		kfree(cpr);
-		cpr = NULL;
 	}
-	return cpr;
+	return rc;
 }
 
 static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
-	int i, rc, ulp_base_vec, ulp_msix;
+	int i, j, rc, ulp_base_vec, ulp_msix;
+	int tcs = bp->num_tc;
 
+	if (!tcs)
+		tcs = 1;
 	ulp_msix = bnxt_get_ulp_msix_num(bp);
 	ulp_base_vec = bnxt_get_ulp_msix_base(bp);
-	for (i = 0; i < bp->cp_nr_rings; i++) {
+	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
-		struct bnxt_cp_ring_info *cpr;
+		struct bnxt_cp_ring_info *cpr, *cpr2;
 		struct bnxt_ring_struct *ring;
+		int cp_count = 0, k;
+		int rx = 0, tx = 0;
 
 		if (!bnapi)
 			continue;
@@ -3624,35 +3838,55 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		else
 			ring->map_idx = i;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 
 		if (i < bp->rx_nr_rings) {
-			struct bnxt_cp_ring_info *cpr2 =
-				bnxt_alloc_cp_sub_ring(bp);
-
-			cpr->cp_ring_arr[BNXT_RX_HDL] = cpr2;
-			if (!cpr2)
-				return -ENOMEM;
-			cpr2->bnapi = bnapi;
+			cp_count++;
+			rx = 1;
+		}
+		if (i < bp->tx_nr_rings_xdp) {
+			cp_count++;
+			tx = 1;
+		} else if ((sh && i < bp->tx_nr_rings) ||
+			 (!sh && i >= bp->rx_nr_rings)) {
+			cp_count += tcs;
+			tx = 1;
 		}
-		if ((sh && i < bp->tx_nr_rings) ||
-		    (!sh && i >= bp->rx_nr_rings)) {
-			struct bnxt_cp_ring_info *cpr2 =
-				bnxt_alloc_cp_sub_ring(bp);
 
-			cpr->cp_ring_arr[BNXT_TX_HDL] = cpr2;
-			if (!cpr2)
-				return -ENOMEM;
+		cpr->cp_ring_arr = kcalloc(cp_count, sizeof(*cpr),
+					   GFP_KERNEL);
+		if (!cpr->cp_ring_arr)
+			return -ENOMEM;
+		cpr->cp_ring_count = cp_count;
+
+		for (k = 0; k < cp_count; k++) {
+			cpr2 = &cpr->cp_ring_arr[k];
+			rc = bnxt_alloc_cp_sub_ring(bp, cpr2);
+			if (rc)
+				return rc;
 			cpr2->bnapi = bnapi;
+			cpr2->cp_idx = k;
+			if (!k && rx) {
+				bp->rx_ring[i].rx_cpr = cpr2;
+				cpr2->cp_ring_type = BNXT_NQ_HDL_TYPE_RX;
+			} else {
+				int n, tc = k - rx;
+
+				n = BNXT_TC_TO_RING_BASE(bp, tc) + j;
+				bp->tx_ring[n].tx_cpr = cpr2;
+				cpr2->cp_ring_type = BNXT_NQ_HDL_TYPE_TX;
+			}
 		}
+		if (tx)
+			j++;
 	}
 	return 0;
 }
 
 static void bnxt_init_ring_struct(struct bnxt *bp)
 {
-	int i;
+	int i, j;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
@@ -3697,18 +3931,16 @@ static void bnxt_init_ring_struct(struct bnxt *bp)
 		rmem->vmem = (void **)&rxr->rx_agg_ring;
 
 skip_rx:
-		txr = bnapi->tx_ring;
-		if (!txr)
-			continue;
-
-		ring = &txr->tx_ring_struct;
-		rmem = &ring->ring_mem;
-		rmem->nr_pages = bp->tx_nr_pages;
-		rmem->page_size = HW_RXBD_RING_SIZE;
-		rmem->pg_arr = (void **)txr->tx_desc_ring;
-		rmem->dma_arr = txr->tx_desc_mapping;
-		rmem->vmem_size = SW_TXBD_RING_SIZE * bp->tx_nr_pages;
-		rmem->vmem = (void **)&txr->tx_buf_ring;
+		bnxt_for_each_napi_tx(j, bnapi, txr) {
+			ring = &txr->tx_ring_struct;
+			rmem = &ring->ring_mem;
+			rmem->nr_pages = bp->tx_nr_pages;
+			rmem->page_size = HW_TXBD_RING_SIZE;
+			rmem->pg_arr = (void **)txr->tx_desc_ring;
+			rmem->dma_arr = txr->tx_desc_mapping;
+			rmem->vmem_size = SW_TXBD_RING_SIZE * bp->tx_nr_pages;
+			rmem->vmem = (void **)&txr->tx_buf_ring;
+		}
 	}
 }
 
@@ -3799,6 +4031,9 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
 	ring = &rxr->rx_ring_struct;
 	bnxt_init_rxbd_pages(ring, type);
 
+	netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX,
+			     &rxr->bnapi->napi);
+
 	if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) {
 		bpf_prog_add(bp->xdp_prog, 1);
 		rxr->xdp_prog = bp->xdp_prog;
@@ -3829,11 +4064,10 @@ static void bnxt_init_cp_rings(struct bnxt *bp)
 		ring->fw_ring_id = INVALID_HW_RING_ID;
 		cpr->rx_ring_coal.coal_ticks = bp->rx_coal.coal_ticks;
 		cpr->rx_ring_coal.coal_bufs = bp->rx_coal.coal_bufs;
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
-
-			if (!cpr2)
-				continue;
+		if (!cpr->cp_ring_arr)
+			continue;
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 
 			ring = &cpr2->cp_ring_struct;
 			ring->fw_ring_id = INVALID_HW_RING_ID;
@@ -3876,6 +4110,11 @@ static int bnxt_init_tx_rings(struct bnxt *bp)
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
 
 		ring->fw_ring_id = INVALID_HW_RING_ID;
+
+		if (i >= bp->tx_nr_rings_xdp)
+			netif_queue_set_napi(bp->dev, i - bp->tx_nr_rings_xdp,
+					     NETDEV_QUEUE_TYPE_TX,
+					     &txr->bnapi->napi);
 	}
 
 	return 0;
@@ -3921,7 +4160,7 @@ static int bnxt_alloc_vnics(struct bnxt *bp)
 	int num_vnics = 1;
 
 #ifdef CONFIG_RFS_ACCEL
-	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5_PLUS)) == BNXT_FLAG_RFS)
 		num_vnics += bp->rx_nr_rings;
 #endif
 
@@ -3952,13 +4191,22 @@ static void bnxt_init_vnics(struct bnxt *bp)
 		vnic->fw_l2_ctx_id = INVALID_HW_RING_ID;
 
 		if (bp->vnic_info[i].rss_hash_key) {
-			if (i == 0)
+			if (!i) {
+				u8 *key = (void *)vnic->rss_hash_key;
+				int k;
+
+				bp->toeplitz_prefix = 0;
 				get_random_bytes(vnic->rss_hash_key,
 					      HW_HASH_KEY_SIZE);
-			else
+				for (k = 0; k < 8; k++) {
+					bp->toeplitz_prefix <<= 8;
+					bp->toeplitz_prefix |= key[k];
+				}
+			} else {
 				memcpy(vnic->rss_hash_key,
 				       bp->vnic_info[0].rss_hash_key,
 				       HW_HASH_KEY_SIZE);
+			}
 		}
 	}
 }
@@ -4194,7 +4442,7 @@ static int bnxt_alloc_vnic_attributes(struct bnxt *bp)
 			}
 		}
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			goto vnic_skip_grps;
 
 		if (vnic->flags & BNXT_VNIC_RSS_FLAG)
@@ -4208,13 +4456,13 @@ static int bnxt_alloc_vnic_attributes(struct bnxt *bp)
 			goto out;
 		}
 vnic_skip_grps:
-		if ((bp->flags & BNXT_FLAG_NEW_RSS_CAP) &&
+		if ((bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP) &&
 		    !(vnic->flags & BNXT_VNIC_RSS_FLAG))
 			continue;
 
 		/* Allocate rss table and hash key */
 		size = L1_CACHE_ALIGN(HW_HASH_INDEX_SIZE * sizeof(u16));
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			size = L1_CACHE_ALIGN(BNXT_MAX_RSS_TABLE_SIZE_P5);
 
 		vnic->rss_table_size = size + HW_HASH_KEY_SIZE;
@@ -4324,7 +4572,7 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp,
 	int rc;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED) ||
-	    !(bp->flags & BNXT_FLAG_CHIP_P5))
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return -EOPNOTSUPP;
 
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_QSTATS_EXT);
@@ -4362,7 +4610,7 @@ static void bnxt_init_stats(struct bnxt *bp)
 	stats = &cpr->stats;
 	rc = bnxt_hwrm_func_qstat_ext(bp, stats);
 	if (rc) {
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			mask = (1ULL << 48) - 1;
 		else
 			mask = -1ULL;
@@ -4508,7 +4756,7 @@ alloc_tx_ext_stats:
 
 static void bnxt_clear_ring_indices(struct bnxt *bp)
 {
-	int i;
+	int i, j;
 
 	if (!bp->bnapi)
 		return;
@@ -4525,10 +4773,10 @@ static void bnxt_clear_ring_indices(struct bnxt *bp)
 		cpr = &bnapi->cp_ring;
 		cpr->cp_raw_cons = 0;
 
-		txr = bnapi->tx_ring;
-		if (txr) {
+		bnxt_for_each_napi_tx(j, bnapi, txr) {
 			txr->tx_prod = 0;
 			txr->tx_cons = 0;
+			txr->tx_hw_cons = 0;
 		}
 
 		rxr = bnapi->rx_ring;
@@ -4538,12 +4786,12 @@ static void bnxt_clear_ring_indices(struct bnxt *bp)
 			rxr->rx_sw_agg_prod = 0;
 			rxr->rx_next_cons = 0;
 		}
+		bnapi->events = 0;
 	}
 }
 
-static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
+static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i;
 
 	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
@@ -4555,40 +4803,73 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
 		struct bnxt_ntuple_filter *fltr;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
-			hlist_del(&fltr->hash);
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			bnxt_del_l2_filter(bp, fltr->l2_fltr);
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+			bp->ntp_fltr_count--;
 			kfree(fltr);
 		}
 	}
-	if (irq_reinit) {
-		bitmap_free(bp->ntp_fltr_bmap);
-		bp->ntp_fltr_bmap = NULL;
-	}
+	if (!all)
+		return;
+
+	bitmap_free(bp->ntp_fltr_bmap);
+	bp->ntp_fltr_bmap = NULL;
 	bp->ntp_fltr_count = 0;
-#endif
 }
 
 static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
-	if (!(bp->flags & BNXT_FLAG_RFS))
+	if (!(bp->flags & BNXT_FLAG_RFS) || bp->ntp_fltr_bmap)
 		return 0;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_NTP_FLTR_MAX_FLTR, GFP_KERNEL);
+	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_MAX_FLTR, GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
 		rc = -ENOMEM;
 
 	return rc;
-#else
-	return 0;
-#endif
+}
+
+static void bnxt_free_l2_filters(struct bnxt *bp, bool all)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++) {
+		struct hlist_head *head;
+		struct hlist_node *tmp;
+		struct bnxt_l2_filter *fltr;
+
+		head = &bp->l2_fltr_hash_tbl[i];
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			if (fltr->base.flags) {
+				clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+				bp->ntp_fltr_count--;
+			}
+			kfree(fltr);
+		}
+	}
+}
+
+static void bnxt_init_l2_fltr_tbl(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&bp->l2_fltr_hash_tbl[i]);
+	get_random_bytes(&bp->hash_seed, sizeof(bp->hash_seed));
 }
 
 static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
@@ -4598,7 +4879,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_rx_rings(bp);
 	bnxt_free_cp_rings(bp);
 	bnxt_free_all_cp_arrays(bp);
-	bnxt_free_ntp_fltrs(bp, irq_re_init);
+	bnxt_free_ntp_fltrs(bp, false);
+	bnxt_free_l2_filters(bp, false);
 	if (irq_re_init) {
 		bnxt_free_ring_stats(bp);
 		if (!(bp->phy_flags & BNXT_PHY_FL_PORT_STATS_NO_RESET) ||
@@ -4641,7 +4923,7 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 			bp->bnapi[i] = bnapi;
 			bp->bnapi[i]->index = i;
 			bp->bnapi[i]->bp = bp;
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 				struct bnxt_cp_ring_info *cpr =
 					&bp->bnapi[i]->cp_ring;
 
@@ -4659,11 +4941,13 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 		for (i = 0; i < bp->rx_nr_rings; i++) {
 			struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 
-			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 				rxr->rx_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
 				rxr->rx_agg_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
+			} else {
+				rxr->rx_cpr =  &bp->bnapi[i]->cp_ring;
 			}
 			rxr->bnapi = bp->bnapi[i];
 			bp->bnapi[i]->rx_ring = &bp->rx_ring[i];
@@ -4686,22 +4970,33 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init)
 		else
 			j = bp->rx_nr_rings;
 
-		for (i = 0; i < bp->tx_nr_rings; i++, j++) {
+		for (i = 0; i < bp->tx_nr_rings; i++) {
 			struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
+			struct bnxt_napi *bnapi2;
 
-			if (bp->flags & BNXT_FLAG_CHIP_P5)
+			if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 				txr->tx_ring_struct.ring_mem.flags =
 					BNXT_RMEM_RING_PTE_FLAG;
-			txr->bnapi = bp->bnapi[j];
-			bp->bnapi[j]->tx_ring = txr;
 			bp->tx_ring_map[i] = bp->tx_nr_rings_xdp + i;
 			if (i >= bp->tx_nr_rings_xdp) {
+				int k = j + BNXT_RING_TO_TC_OFF(bp, i);
+
+				bnapi2 = bp->bnapi[k];
 				txr->txq_index = i - bp->tx_nr_rings_xdp;
-				bp->bnapi[j]->tx_int = bnxt_tx_int;
+				txr->tx_napi_idx =
+					BNXT_RING_TO_TC(bp, txr->txq_index);
+				bnapi2->tx_ring[txr->tx_napi_idx] = txr;
+				bnapi2->tx_int = bnxt_tx_int;
 			} else {
-				bp->bnapi[j]->flags |= BNXT_NAPI_FLAG_XDP;
-				bp->bnapi[j]->tx_int = bnxt_tx_int_xdp;
+				bnapi2 = bp->bnapi[j];
+				bnapi2->flags |= BNXT_NAPI_FLAG_XDP;
+				bnapi2->tx_ring[0] = txr;
+				bnapi2->tx_int = bnxt_tx_int_xdp;
+				j++;
 			}
+			txr->bnapi = bnapi2;
+			if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+				txr->tx_cpr = &bnapi2->cp_ring;
 		}
 
 		rc = bnxt_alloc_stats(bp);
@@ -4913,6 +5208,8 @@ int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp)
 	return hwrm_req_send(bp, req);
 }
 
+static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa);
+
 static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 {
 	struct hwrm_tunnel_dst_port_free_input *req;
@@ -4942,6 +5239,11 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 		bp->nge_port = 0;
 		bp->nge_fw_dst_port_id = INVALID_HW_RING_ID;
 		break;
+	case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE:
+		req->tunnel_dst_port_id = cpu_to_le16(bp->vxlan_gpe_fw_dst_port_id);
+		bp->vxlan_gpe_port = 0;
+		bp->vxlan_gpe_fw_dst_port_id = INVALID_HW_RING_ID;
+		break;
 	default:
 		break;
 	}
@@ -4950,6 +5252,8 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type)
 	if (rc)
 		netdev_err(bp->dev, "hwrm_tunnel_dst_port_free failed. rc:%d\n",
 			   rc);
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_set_tpa(bp, true);
 	return rc;
 }
 
@@ -4985,9 +5289,16 @@ static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port,
 		bp->nge_port = port;
 		bp->nge_fw_dst_port_id = le16_to_cpu(resp->tunnel_dst_port_id);
 		break;
+	case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE:
+		bp->vxlan_gpe_port = port;
+		bp->vxlan_gpe_fw_dst_port_id =
+			le16_to_cpu(resp->tunnel_dst_port_id);
+		break;
 	default:
 		break;
 	}
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_set_tpa(bp, true);
 
 err_out:
 	hwrm_req_drop(bp, req);
@@ -5013,25 +5324,301 @@ static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id)
 	return hwrm_req_send_silent(bp, req);
 }
 
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	if (!atomic_dec_and_test(&fltr->refcnt))
+		return;
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	if (fltr->base.flags) {
+		clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+		bp->ntp_fltr_count--;
+	}
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	kfree_rcu(fltr, base.rcu);
+}
+
+static struct bnxt_l2_filter *__bnxt_lookup_l2_filter(struct bnxt *bp,
+						      struct bnxt_l2_key *key,
+						      u32 idx)
+{
+	struct hlist_head *head = &bp->l2_fltr_hash_tbl[idx];
+	struct bnxt_l2_filter *fltr;
+
+	hlist_for_each_entry_rcu(fltr, head, base.hash) {
+		struct bnxt_l2_key *l2_key = &fltr->l2_key;
+
+		if (ether_addr_equal(l2_key->dst_mac_addr, key->dst_mac_addr) &&
+		    l2_key->vlan == key->vlan)
+			return fltr;
+	}
+	return NULL;
+}
+
+static struct bnxt_l2_filter *bnxt_lookup_l2_filter(struct bnxt *bp,
+						    struct bnxt_l2_key *key,
+						    u32 idx)
+{
+	struct bnxt_l2_filter *fltr = NULL;
+
+	rcu_read_lock();
+	fltr = __bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		atomic_inc(&fltr->refcnt);
+	rcu_read_unlock();
+	return fltr;
+}
+
+#define BNXT_IPV4_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4))
+
+#define BNXT_IPV6_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6))
+
+static u32 bnxt_get_rss_flow_tuple_len(struct bnxt *bp, struct flow_keys *fkeys)
+{
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		if (BNXT_IPV4_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v4addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4)
+			return sizeof(fkeys->addrs.v4addrs);
+	}
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IPV6)) {
+		if (BNXT_IPV6_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v6addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
+			return sizeof(fkeys->addrs.v6addrs);
+	}
+
+	return 0;
+}
+
+static u32 bnxt_toeplitz(struct bnxt *bp, struct flow_keys *fkeys,
+			 const unsigned char *key)
+{
+	u64 prefix = bp->toeplitz_prefix, hash = 0;
+	struct bnxt_ipv4_tuple tuple4;
+	struct bnxt_ipv6_tuple tuple6;
+	int i, j, len = 0;
+	u8 *four_tuple;
+
+	len = bnxt_get_rss_flow_tuple_len(bp, fkeys);
+	if (!len)
+		return 0;
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		tuple4.v4addrs = fkeys->addrs.v4addrs;
+		tuple4.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple4;
+	} else {
+		tuple6.v6addrs = fkeys->addrs.v6addrs;
+		tuple6.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple6;
+	}
+
+	for (i = 0, j = 8; i < len; i++, j++) {
+		u8 byte = four_tuple[i];
+		int bit;
+
+		for (bit = 0; bit < 8; bit++, prefix <<= 1, byte <<= 1) {
+			if (byte & 0x80)
+				hash ^= prefix;
+		}
+		prefix |= (j < HW_HASH_KEY_SIZE) ? key[j] : 0;
+	}
+
+	/* The valid part of the hash is in the upper 32 bits. */
+	return (hash >> 32) & BNXT_NTP_FLTR_HASH_MASK;
+}
+
 #ifdef CONFIG_RFS_ACCEL
-static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
-					    struct bnxt_ntuple_filter *fltr)
+static struct bnxt_l2_filter *
+bnxt_lookup_l2_filter_from_key(struct bnxt *bp, struct bnxt_l2_key *key)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	return fltr;
+}
+#endif
+
+static int bnxt_init_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr,
+			       struct bnxt_l2_key *key, u32 idx)
+{
+	struct hlist_head *head;
+
+	ether_addr_copy(fltr->l2_key.dst_mac_addr, key->dst_mac_addr);
+	fltr->l2_key.vlan = key->vlan;
+	fltr->base.type = BNXT_FLTR_TYPE_L2;
+	if (fltr->base.flags) {
+		int bit_id;
+
+		bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
+						 BNXT_MAX_FLTR, 0);
+		if (bit_id < 0)
+			return -ENOMEM;
+		fltr->base.sw_id = (u16)bit_id;
+	}
+	head = &bp->l2_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	atomic_set(&fltr->refcnt, 1);
+	return 0;
+}
+
+static struct bnxt_l2_filter *bnxt_alloc_l2_filter(struct bnxt *bp,
+						   struct bnxt_l2_key *key,
+						   gfp_t gfp)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+	int rc;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		return fltr;
+
+	fltr = kzalloc(sizeof(*fltr), gfp);
+	if (!fltr)
+		return ERR_PTR(-ENOMEM);
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	rc = bnxt_init_l2_filter(bp, fltr, key, idx);
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	if (rc) {
+		bnxt_del_l2_filter(bp, fltr);
+		fltr = ERR_PTR(rc);
+	}
+	return fltr;
+}
+
+static u16 bnxt_vf_target_id(struct bnxt_pf_info *pf, u16 vf_idx)
+{
+#ifdef CONFIG_BNXT_SRIOV
+	struct bnxt_vf_info *vf = &pf->vf[vf_idx];
+
+	return vf->fw_fid;
+#else
+	return INVALID_HW_RING_ID;
+#endif
+}
+
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_free_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+		if (target_id == INVALID_HW_RING_ID)
+			return -EINVAL;
+	}
+
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->l2_filter_id = fltr->base.filter_id;
+	return hwrm_req_send(bp, req);
+}
+
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_alloc_output *resp;
+	struct hwrm_cfa_l2_filter_alloc_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+	}
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
+
+	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
+		req->flags |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
+	req->dst_id = cpu_to_le16(fltr->base.fw_vnic_id);
+	req->enables =
+		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
+	ether_addr_copy(req->l2_addr, fltr->l2_key.dst_mac_addr);
+	eth_broadcast_addr(req->l2_addr_mask);
+
+	if (fltr->l2_key.vlan) {
+		req->enables |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS);
+		req->num_vlans = 1;
+		req->l2_ivlan = cpu_to_le16(fltr->l2_key.vlan);
+		req->l2_ivlan_mask = cpu_to_le16(0xfff);
+	}
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
+		fltr->base.filter_id = resp->l2_filter_id;
+		set_bit(BNXT_FLTR_VALID, &fltr->base.state);
+	}
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+				     struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_free_input *req;
 	int rc;
 
+	set_bit(BNXT_FLTR_FW_DELETED, &fltr->base.state);
 	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
 	if (rc)
 		return rc;
 
-	req->ntuple_filter_id = fltr->filter_id;
+	req->ntuple_filter_id = fltr->base.filter_id;
 	return hwrm_req_send(bp, req);
 }
 
 #define BNXT_NTP_FLTR_FLAGS					\
 	(CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE |	\
-	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK |	\
@@ -5047,12 +5634,21 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 #define BNXT_NTP_TUNNEL_FLTR_FLAG				\
 		CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE
 
-static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
-					     struct bnxt_ntuple_filter *fltr)
+void bnxt_fill_ipv6_mask(__be32 mask[4])
+{
+	int i;
+
+	for (i = 0; i < 4; i++)
+		mask[i] = cpu_to_be32(~0);
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+				      struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct hwrm_cfa_ntuple_filter_alloc_input *req;
 	struct flow_keys *keys = &fltr->fkeys;
+	struct bnxt_l2_filter *l2_fltr;
 	struct bnxt_vnic_info *vnic;
 	u32 flags = 0;
 	int rc;
@@ -5061,42 +5657,47 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	if (rc)
 		return rc;
 
-	req->l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
+	l2_fltr = fltr->l2_fltr;
+	req->l2_filter_id = l2_fltr->base.filter_id;
+
 
 	if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
 		flags = CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX;
-		req->dst_id = cpu_to_le16(fltr->rxq);
+		req->dst_id = cpu_to_le16(fltr->base.rxq);
 	} else {
-		vnic = &bp->vnic_info[fltr->rxq + 1];
+		vnic = &bp->vnic_info[fltr->base.rxq + 1];
 		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	}
 	req->flags = cpu_to_le32(flags);
 	req->enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
 
 	req->ethertype = htons(ETH_P_IP);
-	memcpy(req->src_macaddr, fltr->src_mac_addr, ETH_ALEN);
 	req->ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
 	req->ip_protocol = keys->basic.ip_proto;
 
 	if (keys->basic.n_proto == htons(ETH_P_IPV6)) {
-		int i;
-
 		req->ethertype = htons(ETH_P_IPV6);
 		req->ip_addr_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6;
-		*(struct in6_addr *)&req->src_ipaddr[0] =
-			keys->addrs.v6addrs.src;
-		*(struct in6_addr *)&req->dst_ipaddr[0] =
-			keys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			req->src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
-			req->dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			*(struct in6_addr *)&req->src_ipaddr[0] =
+				keys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(req->src_ipaddr_mask);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			*(struct in6_addr *)&req->dst_ipaddr[0] =
+				keys->addrs.v6addrs.dst;
+			bnxt_fill_ipv6_mask(req->dst_ipaddr_mask);
 		}
 	} else {
-		req->src_ipaddr[0] = keys->addrs.v4addrs.src;
-		req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
-		req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
-		req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			req->src_ipaddr[0] = keys->addrs.v4addrs.src;
+			req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
+			req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		}
 	}
 	if (keys->control.flags & FLOW_DIS_ENCAPSULATION) {
 		req->enables |= cpu_to_le32(BNXT_NTP_TUNNEL_FLTR_FLAG);
@@ -5104,80 +5705,85 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 			CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL;
 	}
 
-	req->src_port = keys->ports.src;
-	req->src_port_mask = cpu_to_be16(0xffff);
-	req->dst_port = keys->ports.dst;
-	req->dst_port_mask = cpu_to_be16(0xffff);
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+		req->src_port = keys->ports.src;
+		req->src_port_mask = cpu_to_be16(0xffff);
+	}
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+		req->dst_port = keys->ports.dst;
+		req->dst_port_mask = cpu_to_be16(0xffff);
+	}
 
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
 	if (!rc)
-		fltr->filter_id = resp->ntuple_filter_id;
+		fltr->base.filter_id = resp->ntuple_filter_id;
 	hwrm_req_drop(bp, req);
 	return rc;
 }
-#endif
 
 static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx,
 				     const u8 *mac_addr)
 {
-	struct hwrm_cfa_l2_filter_alloc_output *resp;
-	struct hwrm_cfa_l2_filter_alloc_input *req;
+	struct bnxt_l2_filter *fltr;
+	struct bnxt_l2_key key;
 	int rc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
-	if (rc)
-		return rc;
+	ether_addr_copy(key.dst_mac_addr, mac_addr);
+	key.vlan = 0;
+	fltr = bnxt_alloc_l2_filter(bp, &key, GFP_KERNEL);
+	if (IS_ERR(fltr))
+		return PTR_ERR(fltr);
 
-	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
-	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
-		req->flags |=
-			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
-	req->dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id);
-	req->enables =
-		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
-	memcpy(req->l2_addr, mac_addr, ETH_ALEN);
-	req->l2_addr_mask[0] = 0xff;
-	req->l2_addr_mask[1] = 0xff;
-	req->l2_addr_mask[2] = 0xff;
-	req->l2_addr_mask[3] = 0xff;
-	req->l2_addr_mask[4] = 0xff;
-	req->l2_addr_mask[5] = 0xff;
-
-	resp = hwrm_req_hold(bp, req);
-	rc = hwrm_req_send(bp, req);
-	if (!rc)
-		bp->vnic_info[vnic_id].fw_l2_filter_id[idx] =
-							resp->l2_filter_id;
-	hwrm_req_drop(bp, req);
+	fltr->base.fw_vnic_id = bp->vnic_info[vnic_id].fw_vnic_id;
+	rc = bnxt_hwrm_l2_filter_alloc(bp, fltr);
+	if (rc)
+		bnxt_del_l2_filter(bp, fltr);
+	else
+		bp->vnic_info[vnic_id].l2_filters[idx] = fltr;
 	return rc;
 }
 
-static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
+static void bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
 {
-	struct hwrm_cfa_l2_filter_free_input *req;
 	u16 i, j, num_of_vnics = 1; /* only vnic 0 supported */
-	int rc;
 
 	/* Any associated ntuple filters will also be cleared by firmware. */
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_of_vnics; i++) {
 		struct bnxt_vnic_info *vnic = &bp->vnic_info[i];
 
 		for (j = 0; j < vnic->uc_filter_count; j++) {
-			req->l2_filter_id = vnic->fw_l2_filter_id[j];
+			struct bnxt_l2_filter *fltr = vnic->l2_filters[j];
 
-			rc = hwrm_req_send(bp, req);
+			bnxt_hwrm_l2_filter_free(bp, fltr);
+			bnxt_del_l2_filter(bp, fltr);
 		}
 		vnic->uc_filter_count = 0;
 	}
-	hwrm_req_drop(bp, req);
-	return rc;
+}
+
+#define BNXT_DFLT_TUNL_TPA_BMAP				\
+	(VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE |	\
+	 VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4 |	\
+	 VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6)
+
+static void bnxt_hwrm_vnic_update_tunl_tpa(struct bnxt *bp,
+					   struct hwrm_vnic_tpa_cfg_input *req)
+{
+	u32 tunl_tpa_bmap = BNXT_DFLT_TUNL_TPA_BMAP;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_VNIC_TUNNEL_TPA))
+		return;
+
+	if (bp->vxlan_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN;
+	if (bp->vxlan_gpe_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE;
+	if (bp->nge_port)
+		tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE;
+
+	req->enables |= cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN);
+	req->tnl_tpa_en_bitmap = cpu_to_le32(tunl_tpa_bmap);
 }
 
 static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
@@ -5226,7 +5832,7 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 			nsegs = (MAX_SKB_FRAGS - n) / n;
 		}
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			segs = MAX_TPA_SEGS_P5;
 			max_aggs = bp->max_tpa;
 		} else {
@@ -5236,6 +5842,7 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
 		req->max_aggs = cpu_to_le16(max_aggs);
 
 		req->min_agg_len = cpu_to_le32(512);
+		bnxt_hwrm_vnic_update_tunl_tpa(bp, req);
 	}
 	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 
@@ -5252,35 +5859,25 @@ static u16 bnxt_cp_ring_from_grp(struct bnxt *bp, struct bnxt_ring_struct *ring)
 
 static u16 bnxt_cp_ring_for_rx(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		struct bnxt_napi *bnapi = rxr->bnapi;
-		struct bnxt_cp_ring_info *cpr;
-
-		cpr = bnapi->cp_ring.cp_ring_arr[BNXT_RX_HDL];
-		return cpr->cp_ring_struct.fw_ring_id;
-	} else {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		return rxr->rx_cpr->cp_ring_struct.fw_ring_id;
+	else
 		return bnxt_cp_ring_from_grp(bp, &rxr->rx_ring_struct);
-	}
 }
 
 static u16 bnxt_cp_ring_for_tx(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		struct bnxt_napi *bnapi = txr->bnapi;
-		struct bnxt_cp_ring_info *cpr;
-
-		cpr = bnapi->cp_ring.cp_ring_arr[BNXT_TX_HDL];
-		return cpr->cp_ring_struct.fw_ring_id;
-	} else {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		return txr->tx_cpr->cp_ring_struct.fw_ring_id;
+	else
 		return bnxt_cp_ring_from_grp(bp, &txr->tx_ring_struct);
-	}
 }
 
 static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
 {
 	int entries;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		entries = BNXT_MAX_RSS_TABLE_ENTRIES_P5;
 	else
 		entries = HW_HASH_INDEX_SIZE;
@@ -5330,8 +5927,12 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
 
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		if (!rx_rings)
+			return 0;
+		return bnxt_calc_nr_ring_pages(rx_rings - 1,
+					       BNXT_RSS_TABLE_ENTRIES_P5);
+	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 2;
 	return 1;
@@ -5376,7 +5977,7 @@ static void
 __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
 			 struct bnxt_vnic_info *vnic)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_fill_hw_rss_tbl_p5(bp, vnic);
 	else
 		bnxt_fill_hw_rss_tbl(bp, vnic);
@@ -5401,7 +6002,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	struct hwrm_vnic_rss_cfg_input *req;
 	int rc;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) ||
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) ||
 	    vnic->fw_rss_cos_lb_ctx[0] == INVALID_HW_RING_ID)
 		return 0;
 
@@ -5566,7 +6167,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0];
 
 		req->default_rx_ring_id =
@@ -5666,7 +6267,7 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		goto vnic_no_ring_grps;
 
 	/* map ring groups to this vnic */
@@ -5701,7 +6302,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	int rc;
 
 	bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats);
-	bp->flags &= ~(BNXT_FLAG_NEW_RSS_CAP | BNXT_FLAG_ROCE_MIRROR_CAP);
+	bp->flags &= ~BNXT_FLAG_ROCE_MIRROR_CAP;
+	bp->rss_cap &= ~BNXT_RSS_CAP_NEW_RSS_CAP;
 	if (bp->hwrm_spec_code < 0x10600)
 		return 0;
 
@@ -5714,9 +6316,9 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	if (!rc) {
 		u32 flags = le32_to_cpu(resp->flags);
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 		    (flags & VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP))
-			bp->flags |= BNXT_FLAG_NEW_RSS_CAP;
+			bp->rss_cap |= BNXT_RSS_CAP_NEW_RSS_CAP;
 		if (flags &
 		    VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP)
 			bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP;
@@ -5725,18 +6327,22 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 		 * VLAN_STRIP_CAP properly.
 		 */
 		if ((flags & VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP) ||
-		    (BNXT_CHIP_P5_THOR(bp) &&
+		    (BNXT_CHIP_P5(bp) &&
 		     !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED)))
 			bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP)
-			bp->fw_cap |= BNXT_FW_CAP_RSS_HASH_TYPE_DELTA;
+			bp->rss_cap |= BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED)
+			bp->rss_cap |= BNXT_RSS_CAP_RSS_TCAM;
 		bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported);
 		if (bp->max_tpa_v2) {
-			if (BNXT_CHIP_P5_THOR(bp))
+			if (BNXT_CHIP_P5(bp))
 				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5;
 			else
-				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5_SR2;
+				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P7;
 		}
+		if (flags & VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP)
+			bp->fw_cap |= BNXT_FW_CAP_VNIC_TUNNEL_TPA;
 	}
 	hwrm_req_drop(bp, req);
 	return rc;
@@ -5749,7 +6355,7 @@ static int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp)
 	int rc;
 	u16 i;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	rc = hwrm_req_init(bp, req, HWRM_RING_GRP_ALLOC);
@@ -5782,7 +6388,7 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 	struct hwrm_ring_grp_free_input *req;
 	u16 i;
 
-	if (!bp->grp_info || (bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!bp->grp_info || (bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return;
 
 	if (hwrm_req_init(bp, req, HWRM_RING_GRP_FREE))
@@ -5842,12 +6448,15 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		req->length = cpu_to_le32(bp->tx_ring_mask + 1);
 		req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
 		req->queue_id = cpu_to_le16(ring->queue_id);
+		if (bp->flags & BNXT_FLAG_TX_COAL_CMPL)
+			req->cmpl_coal_cnt =
+				RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64;
 		break;
 	}
 	case HWRM_RING_ALLOC_RX:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
 		req->length = cpu_to_le32(bp->rx_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			u16 flags = 0;
 
 			/* Association of rx ring with stats context */
@@ -5862,7 +6471,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		}
 		break;
 	case HWRM_RING_ALLOC_AGG:
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
 			/* Association of agg ring with rx ring */
 			grp_info = &bp->grp_info[ring->grp_idx];
@@ -5880,7 +6489,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
 		req->length = cpu_to_le32(bp->cp_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			/* Association of cp ring with nq */
 			grp_info = &bp->grp_info[map_index];
 			req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
@@ -5948,14 +6557,34 @@ static int bnxt_hwrm_set_async_event_cr(struct bnxt *bp, int idx)
 	}
 }
 
+static void bnxt_set_db_mask(struct bnxt *bp, struct bnxt_db_info *db,
+			     u32 ring_type)
+{
+	switch (ring_type) {
+	case HWRM_RING_ALLOC_TX:
+		db->db_ring_mask = bp->tx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_RX:
+		db->db_ring_mask = bp->rx_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_AGG:
+		db->db_ring_mask = bp->rx_agg_ring_mask;
+		break;
+	case HWRM_RING_ALLOC_CMPL:
+	case HWRM_RING_ALLOC_NQ:
+		db->db_ring_mask = bp->cp_ring_mask;
+		break;
+	}
+	if (bp->flags & BNXT_FLAG_CHIP_P7) {
+		db->db_epoch_mask = db->db_ring_mask + 1;
+		db->db_epoch_shift = DBR_EPOCH_SFT - ilog2(db->db_epoch_mask);
+	}
+}
+
 static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			u32 map_idx, u32 xid)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		if (BNXT_PF(bp))
-			db->doorbell = bp->bar1 + DB_PF_OFFSET_P5;
-		else
-			db->doorbell = bp->bar1 + DB_VF_OFFSET_P5;
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		switch (ring_type) {
 		case HWRM_RING_ALLOC_TX:
 			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
@@ -5972,6 +6601,11 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			break;
 		}
 		db->db_key64 |= (u64)xid << DBR_XID_SFT;
+
+		if (bp->flags & BNXT_FLAG_CHIP_P7)
+			db->db_key64 |= DBR_VALID;
+
+		db->doorbell = bp->bar1 + bp->db_offset;
 	} else {
 		db->doorbell = bp->bar1 + map_idx * 0x80;
 		switch (ring_type) {
@@ -5987,6 +6621,7 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 			break;
 		}
 	}
+	bnxt_set_db_mask(bp, db, ring_type);
 }
 
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
@@ -5995,7 +6630,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 	int i, rc = 0;
 	u32 type;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = HWRM_RING_ALLOC_NQ;
 	else
 		type = HWRM_RING_ALLOC_CMPL;
@@ -6031,15 +6666,13 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_ring_struct *ring;
 		u32 map_idx;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr;
 			struct bnxt_napi *bnapi = txr->bnapi;
-			struct bnxt_cp_ring_info *cpr, *cpr2;
 			u32 type2 = HWRM_RING_ALLOC_CMPL;
 
-			cpr = &bnapi->cp_ring;
-			cpr2 = cpr->cp_ring_arr[BNXT_TX_HDL];
 			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_TX_HDL;
+			ring->handle = BNXT_SET_NQ_HDL(cpr2);
 			map_idx = bnapi->index;
 			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
 			if (rc)
@@ -6071,14 +6704,12 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (!agg_rings)
 			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr;
 			u32 type2 = HWRM_RING_ALLOC_CMPL;
-			struct bnxt_cp_ring_info *cpr2;
 
-			cpr2 = cpr->cp_ring_arr[BNXT_RX_HDL];
 			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_RX_HDL;
+			ring->handle = BNXT_SET_NQ_HDL(cpr2);
 			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
 			if (rc)
 				goto err_out;
@@ -6186,7 +6817,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		}
 	}
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = RING_FREE_REQ_RING_TYPE_RX_AGG;
 	else
 		type = RING_FREE_REQ_RING_TYPE_RX;
@@ -6213,7 +6844,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	 */
 	bnxt_disable_int_sync(bp);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		type = RING_FREE_REQ_RING_TYPE_NQ;
 	else
 		type = RING_FREE_REQ_RING_TYPE_L2_CMPL;
@@ -6223,18 +6854,16 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_ring_struct *ring;
 		int j;
 
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 
-			if (cpr2) {
-				ring = &cpr2->cp_ring_struct;
-				if (ring->fw_ring_id == INVALID_HW_RING_ID)
-					continue;
-				hwrm_ring_free_send_msg(bp, ring,
-					RING_FREE_REQ_RING_TYPE_L2_CMPL,
-					INVALID_HW_RING_ID);
-				ring->fw_ring_id = INVALID_HW_RING_ID;
-			}
+			ring = &cpr2->cp_ring_struct;
+			if (ring->fw_ring_id == INVALID_HW_RING_ID)
+				continue;
+			hwrm_ring_free_send_msg(bp, ring,
+						RING_FREE_REQ_RING_TYPE_L2_CMPL,
+						INVALID_HW_RING_ID);
+			ring->fw_ring_id = INVALID_HW_RING_ID;
 		}
 		ring = &cpr->cp_ring_struct;
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
@@ -6246,6 +6875,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	}
 }
 
+static int __bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			     bool shared);
 static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 			   bool shared);
 
@@ -6282,14 +6913,16 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		cp = le16_to_cpu(resp->alloc_cmpl_rings);
 		stats = le16_to_cpu(resp->alloc_stat_ctx);
 		hw_resc->resv_irqs = cp;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			int rx = hw_resc->resv_rx_rings;
 			int tx = hw_resc->resv_tx_rings;
 
 			if (bp->flags & BNXT_FLAG_AGG_RINGS)
 				rx >>= 1;
 			if (cp < (rx + tx)) {
-				bnxt_trim_rings(bp, &rx, &tx, cp, false);
+				rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
+				if (rc)
+					goto get_rings_exit;
 				if (bp->flags & BNXT_FLAG_AGG_RINGS)
 					rx <<= 1;
 				hw_resc->resv_rx_rings = rx;
@@ -6301,8 +6934,9 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_cp_rings = cp;
 		hw_resc->resv_stat_ctxs = stats;
 	}
+get_rings_exit:
 	hwrm_req_drop(bp, req);
-	return 0;
+	return rc;
 }
 
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
@@ -6346,7 +6980,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
 		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
@@ -6362,16 +6996,17 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		enables |= vnics ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0;
 
 		req->num_rx_rings = cpu_to_le16(rx_rings);
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 			req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 			req->num_msix = cpu_to_le16(cp_rings);
-			req->num_rsscos_ctxs =
-				cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+			req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 		} else {
 			req->num_cmpl_rings = cpu_to_le16(cp_rings);
 			req->num_hw_ring_grps = cpu_to_le16(ring_grps);
 			req->num_rsscos_ctxs = cpu_to_le16(1);
-			if (!(bp->flags & BNXT_FLAG_NEW_RSS_CAP) &&
+			if (!(bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP) &&
 			    bnxt_rfs_supported(bp))
 				req->num_rsscos_ctxs =
 					cpu_to_le16(ring_grps + 1);
@@ -6397,7 +7032,7 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		enables |= tx_rings + ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
@@ -6412,9 +7047,11 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	req->num_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	req->num_rx_rings = cpu_to_le16(rx_rings);
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 		req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
-		req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+		req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 	} else {
 		req->num_cmpl_rings = cpu_to_le16(cp_rings);
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
@@ -6508,7 +7145,7 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 {
 	int cp;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return bnxt_nq_rings_in_use(bp);
 
 	cp = bp->tx_nr_rings + bp->rx_nr_rings;
@@ -6565,7 +7202,8 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		bnxt_check_rss_tbl_no_rmgr(bp);
 		return false;
 	}
-	if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5))
+	if ((bp->flags & BNXT_FLAG_RFS) &&
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
@@ -6573,9 +7211,9 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 	if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	    hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat ||
 	    (hw_resc->resv_hw_ring_grps != grp &&
-	     !(bp->flags & BNXT_FLAG_CHIP_P5)))
+	     !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)))
 		return true;
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && BNXT_PF(bp) &&
 	    hw_resc->resv_irqs != nq)
 		return true;
 	return false;
@@ -6590,13 +7228,15 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	int grp, rx_rings, rc;
 	int vnic = 1, stat;
 	bool sh = false;
+	int tx_cp;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
 		sh = true;
-	if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5))
+	if ((bp->flags & BNXT_FLAG_RFS) &&
+	    !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
@@ -6639,7 +7279,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	rc = bnxt_trim_rings(bp, &rx_rings, &tx, cp, sh);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx = rx_rings << 1;
-	cp = sh ? max_t(int, tx, rx_rings) : tx + rx_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, tx);
+	cp = sh ? max_t(int, tx_cp, rx_rings) : tx_cp + rx_rings;
 	bp->tx_nr_rings = tx;
 
 	/* If we cannot reserve all the RX rings, reset the RSS map only
@@ -6686,7 +7327,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST;
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		flags |= FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST;
 
 	req->flags = cpu_to_le32(flags);
@@ -6708,7 +7349,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			 FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			flags |= FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST |
 				 FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST;
 		else
@@ -6902,10 +7543,40 @@ int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi)
 	return hwrm_req_send(bp, req_rx);
 }
 
+static int
+bnxt_hwrm_set_rx_coal(struct bnxt *bp, struct bnxt_napi *bnapi,
+		      struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
+{
+	u16 ring_id = bnxt_cp_ring_for_rx(bp, bnapi->rx_ring);
+
+	req->ring_id = cpu_to_le16(ring_id);
+	return hwrm_req_send(bp, req);
+}
+
+static int
+bnxt_hwrm_set_tx_coal(struct bnxt *bp, struct bnxt_napi *bnapi,
+		      struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
+{
+	struct bnxt_tx_ring_info *txr;
+	int i, rc;
+
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		u16 ring_id;
+
+		ring_id = bnxt_cp_ring_for_tx(bp, txr);
+		req->ring_id = cpu_to_le16(ring_id);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			return rc;
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+			return 0;
+	}
+	return 0;
+}
+
 int bnxt_hwrm_set_coal(struct bnxt *bp)
 {
-	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx, *req_tx,
-							   *req;
+	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req_rx, *req_tx;
 	int i, rc;
 
 	rc = hwrm_req_init(bp, req_rx, HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS);
@@ -6926,29 +7597,19 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_coal *hw_coal;
-		u16 ring_id;
 
-		req = req_rx;
-		if (!bnapi->rx_ring) {
-			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
-			req = req_tx;
-		} else {
-			ring_id = bnxt_cp_ring_for_rx(bp, bnapi->rx_ring);
-		}
-		req->ring_id = cpu_to_le16(ring_id);
-
-		rc = hwrm_req_send(bp, req);
+		if (!bnapi->rx_ring)
+			rc = bnxt_hwrm_set_tx_coal(bp, bnapi, req_tx);
+		else
+			rc = bnxt_hwrm_set_rx_coal(bp, bnapi, req_rx);
 		if (rc)
 			break;
 
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
 
-		if (bnapi->rx_ring && bnapi->tx_ring) {
-			req = req_tx;
-			ring_id = bnxt_cp_ring_for_tx(bp, bnapi->tx_ring);
-			req->ring_id = cpu_to_le16(ring_id);
-			rc = hwrm_req_send(bp, req);
+		if (bnapi->rx_ring && bnapi->tx_ring[0]) {
+			rc = bnxt_hwrm_set_tx_coal(bp, bnapi, req_tx);
 			if (rc)
 				break;
 		}
@@ -7044,7 +7705,6 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 {
 	struct hwrm_func_qcfg_output *resp;
 	struct hwrm_func_qcfg_input *req;
-	u32 min_db_offset = 0;
 	u16 flags;
 	int rc;
 
@@ -7102,16 +7762,17 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	if (bp->db_size)
 		goto func_qcfg_exit;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	bp->db_offset = le16_to_cpu(resp->legacy_l2_db_size_kb) * 1024;
+	if (BNXT_CHIP_P5(bp)) {
 		if (BNXT_PF(bp))
-			min_db_offset = DB_PF_OFFSET_P5;
+			bp->db_offset = DB_PF_OFFSET_P5;
 		else
-			min_db_offset = DB_VF_OFFSET_P5;
+			bp->db_offset = DB_VF_OFFSET_P5;
 	}
 	bp->db_size = PAGE_ALIGN(le16_to_cpu(resp->l2_doorbell_bar_size_kb) *
 				 1024);
 	if (!bp->db_size || bp->db_size > pci_resource_len(bp->pdev, 2) ||
-	    bp->db_size <= min_db_offset)
+	    bp->db_size <= bp->db_offset)
 		bp->db_size = pci_resource_len(bp->pdev, 2);
 
 func_qcfg_exit:
@@ -7119,37 +7780,99 @@ func_qcfg_exit:
 	return rc;
 }
 
-static void bnxt_init_ctx_initializer(struct bnxt_ctx_mem_info *ctx,
-			struct hwrm_func_backing_store_qcaps_output *resp)
+static void bnxt_init_ctx_initializer(struct bnxt_ctx_mem_type *ctxm,
+				      u8 init_val, u8 init_offset,
+				      bool init_mask_set)
 {
-	struct bnxt_mem_init *mem_init;
-	u16 init_mask;
-	u8 init_val;
-	u8 *offset;
-	int i;
+	ctxm->init_value = init_val;
+	ctxm->init_offset = BNXT_CTX_INIT_INVALID_OFFSET;
+	if (init_mask_set)
+		ctxm->init_offset = init_offset * 4;
+	else
+		ctxm->init_value = 0;
+}
+
+static int bnxt_alloc_all_ctx_pg_info(struct bnxt *bp, int ctx_max)
+{
+	struct bnxt_ctx_mem_info *ctx = bp->ctx;
+	u16 type;
+
+	for (type = 0; type < ctx_max; type++) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		int n = 1;
 
-	init_val = resp->ctx_kind_initializer;
-	init_mask = le16_to_cpu(resp->ctx_init_mask);
-	offset = &resp->qp_init_offset;
-	mem_init = &ctx->mem_init[BNXT_CTX_MEM_INIT_QP];
-	for (i = 0; i < BNXT_CTX_MEM_INIT_MAX; i++, mem_init++, offset++) {
-		mem_init->init_val = init_val;
-		mem_init->offset = BNXT_MEM_INVALID_OFFSET;
-		if (!init_mask)
+		if (!ctxm->max_entries)
 			continue;
-		if (i == BNXT_CTX_MEM_INIT_STAT)
-			offset = &resp->stat_init_offset;
-		if (init_mask & (1 << i))
-			mem_init->offset = *offset * 4;
-		else
-			mem_init->init_val = 0;
+
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		ctxm->pg_info = kcalloc(n, sizeof(*ctxm->pg_info), GFP_KERNEL);
+		if (!ctxm->pg_info)
+			return -ENOMEM;
 	}
-	ctx->mem_init[BNXT_CTX_MEM_INIT_QP].size = ctx->qp_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_SRQ].size = ctx->srq_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_CQ].size = ctx->cq_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_VNIC].size = ctx->vnic_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_STAT].size = ctx->stat_entry_size;
-	ctx->mem_init[BNXT_CTX_MEM_INIT_MRAV].size = ctx->mrav_entry_size;
+	return 0;
+}
+
+#define BNXT_CTX_INIT_VALID(flags)	\
+	(!!((flags) &			\
+	    FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT))
+
+static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
+{
+	struct hwrm_func_backing_store_qcaps_v2_output *resp;
+	struct hwrm_func_backing_store_qcaps_v2_input *req;
+	struct bnxt_ctx_mem_info *ctx;
+	u16 type;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2);
+	if (rc)
+		return rc;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	bp->ctx = ctx;
+
+	resp = hwrm_req_hold(bp, req);
+
+	for (type = 0; type < BNXT_CTX_V2_MAX; ) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		u8 init_val, init_off, i;
+		__le32 *p;
+		u32 flags;
+
+		req->type = cpu_to_le16(type);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			goto ctx_done;
+		flags = le32_to_cpu(resp->flags);
+		type = le16_to_cpu(resp->next_valid_type);
+		if (!(flags & FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID))
+			continue;
+
+		ctxm->type = le16_to_cpu(resp->type);
+		ctxm->entry_size = le16_to_cpu(resp->entry_size);
+		ctxm->flags = flags;
+		ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map);
+		ctxm->entry_multiple = resp->entry_multiple;
+		ctxm->max_entries = le32_to_cpu(resp->max_num_entries);
+		ctxm->min_entries = le32_to_cpu(resp->min_num_entries);
+		init_val = resp->ctx_init_value;
+		init_off = resp->ctx_init_offset;
+		bnxt_init_ctx_initializer(ctxm, init_val, init_off,
+					  BNXT_CTX_INIT_VALID(flags));
+		ctxm->split_entry_cnt = min_t(u8, resp->subtype_valid_cnt,
+					      BNXT_MAX_SPLIT_ENTRY);
+		for (i = 0, p = &resp->split_entry_0; i < ctxm->split_entry_cnt;
+		     i++, p++)
+			ctxm->split[i] = le32_to_cpu(*p);
+	}
+	rc = bnxt_alloc_all_ctx_pg_info(bp, BNXT_CTX_V2_MAX);
+
+ctx_done:
+	hwrm_req_drop(bp, req);
+	return rc;
 }
 
 static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
@@ -7161,6 +7884,9 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10902 || BNXT_VF(bp) || bp->ctx)
 		return 0;
 
+	if (bp->fw_cap & BNXT_FW_CAP_BACKING_STORE_V2)
+		return bnxt_hwrm_func_backing_store_qcaps_v2(bp);
+
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS);
 	if (rc)
 		return rc;
@@ -7168,48 +7894,84 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send_silent(bp, req);
 	if (!rc) {
-		struct bnxt_ctx_pg_info *ctx_pg;
+		struct bnxt_ctx_mem_type *ctxm;
 		struct bnxt_ctx_mem_info *ctx;
-		int i, tqm_rings;
+		u8 init_val, init_idx = 0;
+		u16 init_mask;
 
-		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+		ctx = bp->ctx;
 		if (!ctx) {
-			rc = -ENOMEM;
-			goto ctx_err;
-		}
-		ctx->qp_max_entries = le32_to_cpu(resp->qp_max_entries);
-		ctx->qp_min_qp1_entries = le16_to_cpu(resp->qp_min_qp1_entries);
-		ctx->qp_max_l2_entries = le16_to_cpu(resp->qp_max_l2_entries);
-		ctx->qp_entry_size = le16_to_cpu(resp->qp_entry_size);
-		ctx->srq_max_l2_entries = le16_to_cpu(resp->srq_max_l2_entries);
-		ctx->srq_max_entries = le32_to_cpu(resp->srq_max_entries);
-		ctx->srq_entry_size = le16_to_cpu(resp->srq_entry_size);
-		ctx->cq_max_l2_entries = le16_to_cpu(resp->cq_max_l2_entries);
-		ctx->cq_max_entries = le32_to_cpu(resp->cq_max_entries);
-		ctx->cq_entry_size = le16_to_cpu(resp->cq_entry_size);
-		ctx->vnic_max_vnic_entries =
-			le16_to_cpu(resp->vnic_max_vnic_entries);
-		ctx->vnic_max_ring_table_entries =
+			ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+			if (!ctx) {
+				rc = -ENOMEM;
+				goto ctx_err;
+			}
+			bp->ctx = ctx;
+		}
+		init_val = resp->ctx_kind_initializer;
+		init_mask = le16_to_cpu(resp->ctx_init_mask);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+		ctxm->max_entries = le32_to_cpu(resp->qp_max_entries);
+		ctxm->qp_qp1_entries = le16_to_cpu(resp->qp_min_qp1_entries);
+		ctxm->qp_l2_entries = le16_to_cpu(resp->qp_max_l2_entries);
+		ctxm->qp_fast_qpmd_entries = le16_to_cpu(resp->fast_qpmd_qp_num_entries);
+		ctxm->entry_size = le16_to_cpu(resp->qp_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->qp_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+		ctxm->srq_l2_entries = le16_to_cpu(resp->srq_max_l2_entries);
+		ctxm->max_entries = le32_to_cpu(resp->srq_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->srq_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->srq_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+		ctxm->cq_l2_entries = le16_to_cpu(resp->cq_max_l2_entries);
+		ctxm->max_entries = le32_to_cpu(resp->cq_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->cq_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val, resp->cq_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+		ctxm->vnic_entries = le16_to_cpu(resp->vnic_max_vnic_entries);
+		ctxm->max_entries = ctxm->vnic_entries +
 			le16_to_cpu(resp->vnic_max_ring_table_entries);
-		ctx->vnic_entry_size = le16_to_cpu(resp->vnic_entry_size);
-		ctx->stat_max_entries = le32_to_cpu(resp->stat_max_entries);
-		ctx->stat_entry_size = le16_to_cpu(resp->stat_entry_size);
-		ctx->tqm_entry_size = le16_to_cpu(resp->tqm_entry_size);
-		ctx->tqm_min_entries_per_ring =
-			le32_to_cpu(resp->tqm_min_entries_per_ring);
-		ctx->tqm_max_entries_per_ring =
-			le32_to_cpu(resp->tqm_max_entries_per_ring);
-		ctx->tqm_entries_multiple = resp->tqm_entries_multiple;
-		if (!ctx->tqm_entries_multiple)
-			ctx->tqm_entries_multiple = 1;
-		ctx->mrav_max_entries = le32_to_cpu(resp->mrav_max_entries);
-		ctx->mrav_entry_size = le16_to_cpu(resp->mrav_entry_size);
-		ctx->mrav_num_entries_units =
+		ctxm->entry_size = le16_to_cpu(resp->vnic_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->vnic_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+		ctxm->max_entries = le32_to_cpu(resp->stat_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->stat_entry_size);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->stat_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
+		ctxm->entry_size = le16_to_cpu(resp->tqm_entry_size);
+		ctxm->min_entries = le32_to_cpu(resp->tqm_min_entries_per_ring);
+		ctxm->max_entries = le32_to_cpu(resp->tqm_max_entries_per_ring);
+		ctxm->entry_multiple = resp->tqm_entries_multiple;
+		if (!ctxm->entry_multiple)
+			ctxm->entry_multiple = 1;
+
+		memcpy(&ctx->ctx_arr[BNXT_CTX_FTQM], ctxm, sizeof(*ctxm));
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
+		ctxm->max_entries = le32_to_cpu(resp->mrav_max_entries);
+		ctxm->entry_size = le16_to_cpu(resp->mrav_entry_size);
+		ctxm->mrav_num_entries_units =
 			le16_to_cpu(resp->mrav_num_entries_units);
-		ctx->tim_entry_size = le16_to_cpu(resp->tim_entry_size);
-		ctx->tim_max_entries = le32_to_cpu(resp->tim_max_entries);
+		bnxt_init_ctx_initializer(ctxm, init_val,
+					  resp->mrav_init_offset,
+					  (init_mask & (1 << init_idx++)) != 0);
 
-		bnxt_init_ctx_initializer(ctx, resp);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+		ctxm->entry_size = le16_to_cpu(resp->tim_entry_size);
+		ctxm->max_entries = le32_to_cpu(resp->tim_max_entries);
 
 		ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count;
 		if (!ctx->tqm_fp_rings_count)
@@ -7217,16 +7979,11 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 		else if (ctx->tqm_fp_rings_count > BNXT_MAX_TQM_FP_RINGS)
 			ctx->tqm_fp_rings_count = BNXT_MAX_TQM_FP_RINGS;
 
-		tqm_rings = ctx->tqm_fp_rings_count + BNXT_MAX_TQM_SP_RINGS;
-		ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL);
-		if (!ctx_pg) {
-			kfree(ctx);
-			rc = -ENOMEM;
-			goto ctx_err;
-		}
-		for (i = 0; i < tqm_rings; i++, ctx_pg++)
-			ctx->tqm_mem[i] = ctx_pg;
-		bp->ctx = ctx;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_FTQM];
+		memcpy(ctxm, &ctx->ctx_arr[BNXT_CTX_STQM], sizeof(*ctxm));
+		ctxm->instance_bmap = (1 << ctx->tqm_fp_rings_count) - 1;
+
+		rc = bnxt_alloc_all_ctx_pg_info(bp, BNXT_CTX_MAX);
 	} else {
 		rc = 0;
 	}
@@ -7265,6 +8022,7 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	struct hwrm_func_backing_store_cfg_input *req;
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
 	struct bnxt_ctx_pg_info *ctx_pg;
+	struct bnxt_ctx_mem_type *ctxm;
 	void **__req = (void **)&req;
 	u32 req_len = sizeof(*req);
 	__le32 *num_entries;
@@ -7286,82 +8044,102 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 
 	req->enables = cpu_to_le32(enables);
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP) {
-		ctx_pg = &ctx->qp_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+		ctx_pg = ctxm->pg_info;
 		req->qp_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->qp_num_qp1_entries = cpu_to_le16(ctx->qp_min_qp1_entries);
-		req->qp_num_l2_entries = cpu_to_le16(ctx->qp_max_l2_entries);
-		req->qp_entry_size = cpu_to_le16(ctx->qp_entry_size);
+		req->qp_num_qp1_entries = cpu_to_le16(ctxm->qp_qp1_entries);
+		req->qp_num_l2_entries = cpu_to_le16(ctxm->qp_l2_entries);
+		req->qp_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->qpc_pg_size_qpc_lvl,
 				      &req->qpc_page_dir);
+
+		if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD)
+			req->qp_num_fast_qpmd_entries = cpu_to_le16(ctxm->qp_fast_qpmd_entries);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ) {
-		ctx_pg = &ctx->srq_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+		ctx_pg = ctxm->pg_info;
 		req->srq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->srq_num_l2_entries = cpu_to_le16(ctx->srq_max_l2_entries);
-		req->srq_entry_size = cpu_to_le16(ctx->srq_entry_size);
+		req->srq_num_l2_entries = cpu_to_le16(ctxm->srq_l2_entries);
+		req->srq_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->srq_pg_size_srq_lvl,
 				      &req->srq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ) {
-		ctx_pg = &ctx->cq_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+		ctx_pg = ctxm->pg_info;
 		req->cq_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->cq_num_l2_entries = cpu_to_le16(ctx->cq_max_l2_entries);
-		req->cq_entry_size = cpu_to_le16(ctx->cq_entry_size);
+		req->cq_num_l2_entries = cpu_to_le16(ctxm->cq_l2_entries);
+		req->cq_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->cq_pg_size_cq_lvl,
 				      &req->cq_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC) {
-		ctx_pg = &ctx->vnic_mem;
-		req->vnic_num_vnic_entries =
-			cpu_to_le16(ctx->vnic_max_vnic_entries);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+		ctx_pg = ctxm->pg_info;
+		req->vnic_num_vnic_entries = cpu_to_le16(ctxm->vnic_entries);
 		req->vnic_num_ring_table_entries =
-			cpu_to_le16(ctx->vnic_max_ring_table_entries);
-		req->vnic_entry_size = cpu_to_le16(ctx->vnic_entry_size);
+			cpu_to_le16(ctxm->max_entries - ctxm->vnic_entries);
+		req->vnic_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->vnic_pg_size_vnic_lvl,
 				      &req->vnic_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT) {
-		ctx_pg = &ctx->stat_mem;
-		req->stat_num_entries = cpu_to_le32(ctx->stat_max_entries);
-		req->stat_entry_size = cpu_to_le16(ctx->stat_entry_size);
+		ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+		ctx_pg = ctxm->pg_info;
+		req->stat_num_entries = cpu_to_le32(ctxm->max_entries);
+		req->stat_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->stat_pg_size_stat_lvl,
 				      &req->stat_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
-		ctx_pg = &ctx->mrav_mem;
+		u32 units;
+
+		ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
+		ctx_pg = ctxm->pg_info;
 		req->mrav_num_entries = cpu_to_le32(ctx_pg->entries);
-		if (ctx->mrav_num_entries_units)
-			flags |=
-			FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
-		req->mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
+		units = ctxm->mrav_num_entries_units;
+		if (units) {
+			u32 num_mr, num_ah = ctxm->mrav_av_entries;
+			u32 entries;
+
+			num_mr = ctx_pg->entries - num_ah;
+			entries = ((num_mr / units) << 16) | (num_ah / units);
+			req->mrav_num_entries = cpu_to_le32(entries);
+			flags |= FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
+		}
+		req->mrav_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->mrav_pg_size_mrav_lvl,
 				      &req->mrav_page_dir);
 	}
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM) {
-		ctx_pg = &ctx->tim_mem;
+		ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+		ctx_pg = ctxm->pg_info;
 		req->tim_num_entries = cpu_to_le32(ctx_pg->entries);
-		req->tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
+		req->tim_entry_size = cpu_to_le16(ctxm->entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req->tim_pg_size_tim_lvl,
 				      &req->tim_page_dir);
 	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
 	for (i = 0, num_entries = &req->tqm_sp_num_entries,
 	     pg_attr = &req->tqm_sp_pg_size_tqm_sp_lvl,
 	     pg_dir = &req->tqm_sp_page_dir,
-	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP;
+	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP,
+	     ctx_pg = ctxm->pg_info;
 	     i < BNXT_MAX_TQM_RINGS;
+	     ctx_pg = &ctx->ctx_arr[BNXT_CTX_FTQM].pg_info[i],
 	     i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
 		if (!(enables & ena))
 			continue;
 
-		req->tqm_entry_size = cpu_to_le16(ctx->tqm_entry_size);
-		ctx_pg = ctx->tqm_mem[i];
+		req->tqm_entry_size = cpu_to_le16(ctxm->entry_size);
 		*num_entries = cpu_to_le32(ctx_pg->entries);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, pg_attr, pg_dir);
 	}
@@ -7385,7 +8163,7 @@ static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
 
 static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size,
-				  u8 depth, struct bnxt_mem_init *mem_init)
+				  u8 depth, struct bnxt_ctx_mem_type *ctxm)
 {
 	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
 	int rc;
@@ -7423,7 +8201,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 			rmem->pg_tbl_map = ctx_pg->ctx_dma_arr[i];
 			rmem->depth = 1;
 			rmem->nr_pages = MAX_CTX_PAGES;
-			rmem->mem_init = mem_init;
+			rmem->ctx_mem = ctxm;
 			if (i == (nr_tbls - 1)) {
 				int rem = ctx_pg->nr_pages % MAX_CTX_PAGES;
 
@@ -7438,7 +8216,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 		rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 		if (rmem->nr_pages > 1 || depth)
 			rmem->depth = 1;
-		rmem->mem_init = mem_init;
+		rmem->ctx_mem = ctxm;
 		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
 	}
 	return rc;
@@ -7473,41 +8251,144 @@ static void bnxt_free_ctx_pg_tbls(struct bnxt *bp,
 	ctx_pg->nr_pages = 0;
 }
 
+static int bnxt_setup_ctxm_pg_tbls(struct bnxt *bp,
+				   struct bnxt_ctx_mem_type *ctxm, u32 entries,
+				   u8 pg_lvl)
+{
+	struct bnxt_ctx_pg_info *ctx_pg = ctxm->pg_info;
+	int i, rc = 0, n = 1;
+	u32 mem_size;
+
+	if (!ctxm->entry_size || !ctx_pg)
+		return -EINVAL;
+	if (ctxm->instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	if (ctxm->entry_multiple)
+		entries = roundup(entries, ctxm->entry_multiple);
+	entries = clamp_t(u32, entries, ctxm->min_entries, ctxm->max_entries);
+	mem_size = entries * ctxm->entry_size;
+	for (i = 0; i < n && !rc; i++) {
+		ctx_pg[i].entries = entries;
+		rc = bnxt_alloc_ctx_pg_tbls(bp, &ctx_pg[i], mem_size, pg_lvl,
+					    ctxm->init_value ? ctxm : NULL);
+	}
+	return rc;
+}
+
+static int bnxt_hwrm_func_backing_store_cfg_v2(struct bnxt *bp,
+					       struct bnxt_ctx_mem_type *ctxm,
+					       bool last)
+{
+	struct hwrm_func_backing_store_cfg_v2_input *req;
+	u32 instance_bmap = ctxm->instance_bmap;
+	int i, j, rc = 0, n = 1;
+	__le32 *p;
+
+	if (!(ctxm->flags & BNXT_CTX_MEM_TYPE_VALID) || !ctxm->pg_info)
+		return 0;
+
+	if (instance_bmap)
+		n = hweight32(ctxm->instance_bmap);
+	else
+		instance_bmap = 1;
+
+	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_CFG_V2);
+	if (rc)
+		return rc;
+	hwrm_req_hold(bp, req);
+	req->type = cpu_to_le16(ctxm->type);
+	req->entry_size = cpu_to_le16(ctxm->entry_size);
+	req->subtype_valid_cnt = ctxm->split_entry_cnt;
+	for (i = 0, p = &req->split_entry_0; i < ctxm->split_entry_cnt; i++)
+		p[i] = cpu_to_le32(ctxm->split[i]);
+	for (i = 0, j = 0; j < n && !rc; i++) {
+		struct bnxt_ctx_pg_info *ctx_pg;
+
+		if (!(instance_bmap & (1 << i)))
+			continue;
+		req->instance = cpu_to_le16(i);
+		ctx_pg = &ctxm->pg_info[j++];
+		if (!ctx_pg->entries)
+			continue;
+		req->num_entries = cpu_to_le32(ctx_pg->entries);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req->page_size_pbl_level,
+				      &req->page_dir);
+		if (last && j == n)
+			req->flags =
+				cpu_to_le32(FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE);
+		rc = hwrm_req_send(bp, req);
+	}
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_backing_store_cfg_v2(struct bnxt *bp, u32 ena)
+{
+	struct bnxt_ctx_mem_info *ctx = bp->ctx;
+	struct bnxt_ctx_mem_type *ctxm;
+	u16 last_type;
+	int rc = 0;
+	u16 type;
+
+	if (!ena)
+		return 0;
+	else if (ena & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM)
+		last_type = BNXT_CTX_MAX - 1;
+	else
+		last_type = BNXT_CTX_L2_MAX - 1;
+	ctx->ctx_arr[last_type].last = 1;
+
+	for (type = 0 ; type < BNXT_CTX_V2_MAX; type++) {
+		ctxm = &ctx->ctx_arr[type];
+
+		rc = bnxt_hwrm_func_backing_store_cfg_v2(bp, ctxm, ctxm->last);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
 void bnxt_free_ctx_mem(struct bnxt *bp)
 {
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
-	int i;
+	u16 type;
 
 	if (!ctx)
 		return;
 
-	if (ctx->tqm_mem[0]) {
-		for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
-			bnxt_free_ctx_pg_tbls(bp, ctx->tqm_mem[i]);
-		kfree(ctx->tqm_mem[0]);
-		ctx->tqm_mem[0] = NULL;
+	for (type = 0; type < BNXT_CTX_V2_MAX; type++) {
+		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
+		struct bnxt_ctx_pg_info *ctx_pg = ctxm->pg_info;
+		int i, n = 1;
+
+		if (!ctx_pg)
+			continue;
+		if (ctxm->instance_bmap)
+			n = hweight32(ctxm->instance_bmap);
+		for (i = 0; i < n; i++)
+			bnxt_free_ctx_pg_tbls(bp, &ctx_pg[i]);
+
+		kfree(ctx_pg);
+		ctxm->pg_info = NULL;
 	}
 
-	bnxt_free_ctx_pg_tbls(bp, &ctx->tim_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->mrav_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->stat_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->vnic_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->cq_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->srq_mem);
-	bnxt_free_ctx_pg_tbls(bp, &ctx->qp_mem);
 	ctx->flags &= ~BNXT_CTX_FLAG_INITED;
+	kfree(ctx);
+	bp->ctx = NULL;
 }
 
 static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 {
-	struct bnxt_ctx_pg_info *ctx_pg;
+	struct bnxt_ctx_mem_type *ctxm;
 	struct bnxt_ctx_mem_info *ctx;
-	struct bnxt_mem_init *init;
-	u32 mem_size, ena, entries;
-	u32 entries_sp, min;
+	u32 l2_qps, qp1_qps, max_qps;
+	u32 ena, entries_sp, entries;
+	u32 srqs, max_srqs, min;
 	u32 num_mr, num_ah;
 	u32 extra_srqs = 0;
 	u32 extra_qps = 0;
+	u32 fast_qpmd_qps;
 	u8 pg_lvl = 1;
 	int i, rc;
 
@@ -7521,120 +8402,98 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
+	ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+	l2_qps = ctxm->qp_l2_entries;
+	qp1_qps = ctxm->qp_qp1_entries;
+	fast_qpmd_qps = ctxm->qp_fast_qpmd_entries;
+	max_qps = ctxm->max_entries;
+	ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+	srqs = ctxm->srq_l2_entries;
+	max_srqs = ctxm->max_entries;
+	ena = 0;
 	if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) {
 		pg_lvl = 2;
-		extra_qps = 65536;
-		extra_srqs = 8192;
+		extra_qps = min_t(u32, 65536, max_qps - l2_qps - qp1_qps);
+		/* allocate extra qps if fw supports RoCE fast qp destroy feature */
+		extra_qps += fast_qpmd_qps;
+		extra_srqs = min_t(u32, 8192, max_srqs - srqs);
+		if (fast_qpmd_qps)
+			ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD;
 	}
 
-	ctx_pg = &ctx->qp_mem;
-	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries +
-			  extra_qps;
-	if (ctx->qp_entry_size) {
-		mem_size = ctx->qp_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_QP];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_QP];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, l2_qps + qp1_qps + extra_qps,
+				     pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->srq_mem;
-	ctx_pg->entries = ctx->srq_max_l2_entries + extra_srqs;
-	if (ctx->srq_entry_size) {
-		mem_size = ctx->srq_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_SRQ];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_SRQ];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, srqs + extra_srqs, pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->cq_mem;
-	ctx_pg->entries = ctx->cq_max_l2_entries + extra_qps * 2;
-	if (ctx->cq_entry_size) {
-		mem_size = ctx->cq_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_CQ];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_CQ];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->cq_l2_entries +
+				     extra_qps * 2, pg_lvl);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->vnic_mem;
-	ctx_pg->entries = ctx->vnic_max_vnic_entries +
-			  ctx->vnic_max_ring_table_entries;
-	if (ctx->vnic_entry_size) {
-		mem_size = ctx->vnic_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_VNIC];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_VNIC];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
 
-	ctx_pg = &ctx->stat_mem;
-	ctx_pg->entries = ctx->stat_max_entries;
-	if (ctx->stat_entry_size) {
-		mem_size = ctx->stat_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_STAT];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, init);
-		if (rc)
-			return rc;
-	}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STAT];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, ctxm->max_entries, 1);
+	if (rc)
+		return rc;
 
-	ena = 0;
 	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
 		goto skip_rdma;
 
-	ctx_pg = &ctx->mrav_mem;
+	ctxm = &ctx->ctx_arr[BNXT_CTX_MRAV];
 	/* 128K extra is needed to accommodate static AH context
 	 * allocation by f/w.
 	 */
-	num_mr = 1024 * 256;
-	num_ah = 1024 * 128;
-	ctx_pg->entries = num_mr + num_ah;
-	if (ctx->mrav_entry_size) {
-		mem_size = ctx->mrav_entry_size * ctx_pg->entries;
-		init = &ctx->mem_init[BNXT_CTX_MEM_INIT_MRAV];
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 2, init);
-		if (rc)
-			return rc;
-	}
-	ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
-	if (ctx->mrav_num_entries_units)
-		ctx_pg->entries =
-			((num_mr / ctx->mrav_num_entries_units) << 16) |
-			 (num_ah / ctx->mrav_num_entries_units);
-
-	ctx_pg = &ctx->tim_mem;
-	ctx_pg->entries = ctx->qp_mem.entries;
-	if (ctx->tim_entry_size) {
-		mem_size = ctx->tim_entry_size * ctx_pg->entries;
-		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, NULL);
-		if (rc)
-			return rc;
-	}
+	num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256);
+	num_ah = min_t(u32, num_mr, 1024 * 128);
+	ctxm->split_entry_cnt = BNXT_CTX_MRAV_AV_SPLIT_ENTRY + 1;
+	if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah)
+		ctxm->mrav_av_entries = num_ah;
+
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, num_mr + num_ah, 2);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
+
+	ctxm = &ctx->ctx_arr[BNXT_CTX_TIM];
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, l2_qps + qp1_qps + extra_qps, 1);
+	if (rc)
+		return rc;
 	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
 
 skip_rdma:
-	min = ctx->tqm_min_entries_per_ring;
-	entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries +
-		     2 * (extra_qps + ctx->qp_min_qp1_entries) + min;
-	entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple);
-	entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries);
-	entries = roundup(entries, ctx->tqm_entries_multiple);
-	entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring);
-	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
-		ctx_pg = ctx->tqm_mem[i];
-		ctx_pg->entries = i ? entries : entries_sp;
-		if (ctx->tqm_entry_size) {
-			mem_size = ctx->tqm_entry_size * ctx_pg->entries;
-			rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1,
-						    NULL);
-			if (rc)
-				return rc;
-		}
+	ctxm = &ctx->ctx_arr[BNXT_CTX_STQM];
+	min = ctxm->min_entries;
+	entries_sp = ctx->ctx_arr[BNXT_CTX_VNIC].vnic_entries + l2_qps +
+		     2 * (extra_qps + qp1_qps) + min;
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, entries_sp, 2);
+	if (rc)
+		return rc;
+
+	ctxm = &ctx->ctx_arr[BNXT_CTX_FTQM];
+	entries = l2_qps + 2 * (extra_qps + qp1_qps);
+	rc = bnxt_setup_ctxm_pg_tbls(bp, ctxm, entries, 2);
+	if (rc)
+		return rc;
+	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
 		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
-	}
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
-	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
+
+	if (bp->fw_cap & BNXT_FW_CAP_BACKING_STORE_V2)
+		rc = bnxt_backing_store_cfg_v2(bp, ena);
+	else
+		rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
 	if (rc) {
 		netdev_err(bp->dev, "Failed configuring context mem, rc = %d.\n",
 			   rc);
@@ -7682,7 +8541,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	hw_resc->min_stat_ctxs = le16_to_cpu(resp->min_stat_ctx);
 	hw_resc->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		u16 max_msix = le16_to_cpu(resp->max_msix);
 
 		hw_resc->max_nqs = max_msix;
@@ -7711,7 +8570,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	u8 flags;
 	int rc;
 
-	if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) {
+	if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5(bp)) {
 		rc = -ENODEV;
 		goto no_ptp;
 	}
@@ -7743,7 +8602,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp)
 	if (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK) {
 		ptp->refclk_regs[0] = le32_to_cpu(resp->ts_ref_clock_reg_lower);
 		ptp->refclk_regs[1] = le32_to_cpu(resp->ts_ref_clock_reg_upper);
-	} else if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	} else if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		ptp->refclk_regs[0] = BNXT_TS_REG_TIMESYNC_TS0_LOWER;
 		ptp->refclk_regs[1] = BNXT_TS_REG_TIMESYNC_TS0_UPPER;
 	} else {
@@ -7815,10 +8674,16 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_BACKING_STORE_V2;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP)
+		bp->flags |= BNXT_FLAG_TX_COAL_CMPL;
 
 	flags_ext2 = le32_to_cpu(resp->flags_ext2);
 	if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_RX_ALL_PKT_TS;
+	if (flags_ext2 & FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED)
+		bp->flags |= BNXT_FLAG_UDP_GSO_CAP;
 
 	bp->tx_push_thresh = 0;
 	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
@@ -8033,7 +8898,7 @@ static void bnxt_try_map_fw_health_reg(struct bnxt *bp)
 					     BNXT_FW_HEALTH_WIN_BASE +
 					     BNXT_GRC_REG_CHIP_NUM);
 		}
-		if (!BNXT_CHIP_P5(bp))
+		if (!BNXT_CHIP_P5_PLUS(bp))
 			return;
 
 		status_loc = BNXT_GRC_REG_STATUS_P5 |
@@ -8450,7 +9315,7 @@ static void bnxt_accumulate_all_stats(struct bnxt *bp)
 	int i;
 
 	/* Chip bug.  Counter intermittently becomes 0. */
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		ignore_zero = true;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -8644,7 +9509,7 @@ static void bnxt_clear_vnic(struct bnxt *bp)
 		return;
 
 	bnxt_hwrm_clear_vnic_filter(bp);
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5)) {
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)) {
 		/* clear all RSS setting before free vnic ctx */
 		bnxt_hwrm_clear_vnic_rss(bp);
 		bnxt_hwrm_vnic_ctx_free(bp);
@@ -8653,7 +9518,7 @@ static void bnxt_clear_vnic(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, false);
 	bnxt_hwrm_vnic_free(bp);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		bnxt_hwrm_vnic_ctx_free(bp);
 }
 
@@ -8810,7 +9675,7 @@ static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
 
 static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return __bnxt_setup_vnic_p5(bp, vnic_id);
 	else
 		return __bnxt_setup_vnic(bp, vnic_id);
@@ -8818,10 +9683,9 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 
 static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
@@ -8834,7 +9698,7 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 
 		vnic = &bp->vnic_info[vnic_id];
 		vnic->flags |= BNXT_VNIC_RFS_FLAG;
-		if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+		if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 			vnic->flags |= BNXT_VNIC_RFS_NEW_RSS_FLAG;
 		rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, ring_id, 1);
 		if (rc) {
@@ -8847,9 +9711,6 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 			break;
 	}
 	return rc;
-#else
-	return 0;
-#endif
 }
 
 /* Allow PF, trusted VFs and VFs with default VLAN to be in promiscuous mode */
@@ -8928,7 +9789,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	rc = bnxt_setup_vnic(bp, 0);
 	if (rc)
 		goto err_out;
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bnxt_hwrm_update_rss_hash_cfg(bp);
 
 	if (bp->flags & BNXT_FLAG_RFS) {
@@ -9046,8 +9907,8 @@ static int bnxt_set_real_num_queues(struct bnxt *bp)
 	return rc;
 }
 
-static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
-			   bool shared)
+static int __bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			     bool shared)
 {
 	int _rx = *rx, _tx = *tx;
 
@@ -9070,19 +9931,59 @@ static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 	return 0;
 }
 
+static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp)
+{
+	return (tx - tx_xdp) / tx_sets + tx_xdp;
+}
+
+int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
+{
+	int tcs = bp->num_tc;
+
+	if (!tcs)
+		tcs = 1;
+	return __bnxt_num_tx_to_cp(bp, tx, tcs, bp->tx_nr_rings_xdp);
+}
+
+static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
+{
+	int tcs = bp->num_tc;
+
+	return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
+	       bp->tx_nr_rings_xdp;
+}
+
+static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
+			   bool sh)
+{
+	int tx_cp = bnxt_num_tx_to_cp(bp, *tx);
+
+	if (tx_cp != *tx) {
+		int tx_saved = tx_cp, rc;
+
+		rc = __bnxt_trim_rings(bp, rx, &tx_cp, max, sh);
+		if (rc)
+			return rc;
+		if (tx_cp != tx_saved)
+			*tx = bnxt_num_cp_to_tx(bp, tx_cp);
+		return 0;
+	}
+	return __bnxt_trim_rings(bp, rx, tx, max, sh);
+}
+
 static void bnxt_setup_msix(struct bnxt *bp)
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
 	struct net_device *dev = bp->dev;
 	int tcs, i;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	if (tcs) {
 		int i, off, count;
 
 		for (i = 0; i < tcs; i++) {
 			count = bp->tx_nr_rings_per_tc;
-			off = i * count;
+			off = BNXT_TC_TO_RING_BASE(bp, i);
 			netdev_set_tc_queue(dev, i, count, off);
 		}
 	}
@@ -9108,8 +10009,10 @@ static void bnxt_setup_inta(struct bnxt *bp)
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
 
-	if (netdev_get_num_tc(bp->dev))
+	if (bp->num_tc) {
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
+	}
 
 	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
 		 0);
@@ -9137,7 +10040,6 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
 static unsigned int bnxt_get_max_func_rss_ctxs(struct bnxt *bp)
 {
 	return bp->hw_resc.max_rsscos_ctxs;
@@ -9147,7 +10049,6 @@ static unsigned int bnxt_get_max_func_vnics(struct bnxt *bp)
 {
 	return bp->hw_resc.max_vnics;
 }
-#endif
 
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 {
@@ -9163,7 +10064,7 @@ static unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
 	unsigned int cp = bp->hw_resc.max_cp_rings;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		cp -= bnxt_get_ulp_msix_num(bp);
 
 	return cp;
@@ -9173,7 +10074,7 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_nqs);
 
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
@@ -9189,7 +10090,7 @@ unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
 	unsigned int cp;
 
 	cp = bnxt_get_max_func_cp_rings_for_en(bp);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return cp - bp->rx_nr_rings - bp->tx_nr_rings;
 	else
 		return cp - bp->cp_nr_rings;
@@ -9208,7 +10109,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 	int max_idx, avail_msix;
 
 	max_idx = bp->total_irqs;
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		max_idx = min_t(int, bp->total_irqs, max_cp);
 	avail_msix = max_idx - bp->cp_nr_rings;
 	if (!BNXT_NEW_RM(bp) || avail_msix >= num)
@@ -9232,7 +10133,7 @@ static int bnxt_get_num_msix(struct bnxt *bp)
 
 static int bnxt_init_msix(struct bnxt *bp)
 {
-	int i, total_vecs, max, rc = 0, min = 1, ulp_msix;
+	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp;
 	struct msix_entry *msix_ent;
 
 	total_vecs = bnxt_get_num_msix(bp);
@@ -9274,9 +10175,10 @@ static int bnxt_init_msix(struct bnxt *bp)
 		if (rc)
 			goto msix_setup_exit;
 
+		tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
 		bp->cp_nr_rings = (min == 1) ?
-				  max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-				  bp->tx_nr_rings + bp->rx_nr_rings;
+				  max_t(int, tx_cp, bp->rx_nr_rings) :
+				  tx_cp + bp->rx_nr_rings;
 
 	} else {
 		rc = -ENOMEM;
@@ -9336,8 +10238,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
 	bool irq_cleared = false;
+	int tcs = bp->num_tc;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
@@ -9363,6 +10265,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 		    bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
 		if (bp->tx_nr_rings_xdp)
 			bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
 		else
@@ -9439,6 +10342,7 @@ static int bnxt_request_irq(struct bnxt *bp)
 		if (rc)
 			break;
 
+		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
@@ -9466,6 +10370,11 @@ static void bnxt_del_napi(struct bnxt *bp)
 	if (!bp->bnapi)
 		return;
 
+	for (i = 0; i < bp->rx_nr_rings; i++)
+		netif_queue_set_napi(bp->dev, i, NETDEV_QUEUE_TYPE_RX, NULL);
+	for (i = 0; i < bp->tx_nr_rings - bp->tx_nr_rings_xdp; i++)
+		netif_queue_set_napi(bp->dev, i, NETDEV_QUEUE_TYPE_TX, NULL);
+
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
@@ -9486,7 +10395,7 @@ static void bnxt_init_napi(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_USING_MSIX) {
 		int (*poll_fn)(struct napi_struct *, int) = bnxt_poll;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			poll_fn = bnxt_poll_p5;
 		else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 			cp_nr_rings--;
@@ -9542,8 +10451,6 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		cpr = &bnapi->cp_ring;
 		bnapi->in_reset = false;
 
-		bnapi->tx_pkts = 0;
-
 		if (bnapi->rx_ring) {
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
 			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
@@ -9647,7 +10554,10 @@ void bnxt_report_link(struct bnxt *bp)
 				signal = "(NRZ) ";
 				break;
 			case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4:
-				signal = "(PAM4) ";
+				signal = "(PAM4 56Gbps) ";
+				break;
+			case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112:
+				signal = "(PAM4 112Gbps) ";
 				break;
 			default:
 				break;
@@ -9675,7 +10585,9 @@ static bool bnxt_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp)
 	if (!resp->supported_speeds_auto_mode &&
 	    !resp->supported_speeds_force_mode &&
 	    !resp->supported_pam4_speeds_auto_mode &&
-	    !resp->supported_pam4_speeds_force_mode)
+	    !resp->supported_pam4_speeds_force_mode &&
+	    !resp->supported_speeds2_auto_mode &&
+	    !resp->supported_speeds2_force_mode)
 		return true;
 	return false;
 }
@@ -9721,6 +10633,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 			/* Phy re-enabled, reprobe the speeds */
 			link_info->support_auto_speeds = 0;
 			link_info->support_pam4_auto_speeds = 0;
+			link_info->support_auto_speeds2 = 0;
 		}
 	}
 	if (resp->supported_speeds_auto_mode)
@@ -9729,6 +10642,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	if (resp->supported_pam4_speeds_auto_mode)
 		link_info->support_pam4_auto_speeds =
 			le16_to_cpu(resp->supported_pam4_speeds_auto_mode);
+	if (resp->supported_speeds2_auto_mode)
+		link_info->support_auto_speeds2 =
+			le16_to_cpu(resp->supported_speeds2_auto_mode);
 
 	bp->port_count = resp->port_cnt;
 
@@ -9746,9 +10662,19 @@ static bool bnxt_support_dropped(u16 advertising, u16 supported)
 
 static bool bnxt_support_speed_dropped(struct bnxt_link_info *link_info)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+
 	/* Check if any advertised speeds are no longer supported. The caller
 	 * holds the link_lock mutex, so we can modify link_info settings.
 	 */
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		if (bnxt_support_dropped(link_info->advertising,
+					 link_info->support_auto_speeds2)) {
+			link_info->advertising = link_info->support_auto_speeds2;
+			return true;
+		}
+		return false;
+	}
 	if (bnxt_support_dropped(link_info->advertising,
 				 link_info->support_auto_speeds)) {
 		link_info->advertising = link_info->support_auto_speeds;
@@ -9797,18 +10723,25 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	link_info->lp_pause = resp->link_partner_adv_pause;
 	link_info->force_pause_setting = resp->force_pause;
 	link_info->duplex_setting = resp->duplex_cfg;
-	if (link_info->phy_link_status == BNXT_LINK_LINK)
+	if (link_info->phy_link_status == BNXT_LINK_LINK) {
 		link_info->link_speed = le16_to_cpu(resp->link_speed);
-	else
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2)
+			link_info->active_lanes = resp->active_lanes;
+	} else {
 		link_info->link_speed = 0;
+		link_info->active_lanes = 0;
+	}
 	link_info->force_link_speed = le16_to_cpu(resp->force_link_speed);
 	link_info->force_pam4_link_speed =
 		le16_to_cpu(resp->force_pam4_link_speed);
+	link_info->force_link_speed2 = le16_to_cpu(resp->force_link_speeds2);
 	link_info->support_speeds = le16_to_cpu(resp->support_speeds);
 	link_info->support_pam4_speeds = le16_to_cpu(resp->support_pam4_speeds);
+	link_info->support_speeds2 = le16_to_cpu(resp->support_speeds2);
 	link_info->auto_link_speeds = le16_to_cpu(resp->auto_link_speed_mask);
 	link_info->auto_pam4_link_speeds =
 		le16_to_cpu(resp->auto_pam4_link_speed_mask);
+	link_info->auto_link_speeds2 = le16_to_cpu(resp->auto_link_speeds2);
 	link_info->lp_auto_link_speeds =
 		le16_to_cpu(resp->link_partner_adv_speeds);
 	link_info->lp_auto_pam4_link_speeds =
@@ -9947,7 +10880,11 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_
 {
 	if (bp->link_info.autoneg & BNXT_AUTONEG_SPEED) {
 		req->auto_mode |= PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK;
-		if (bp->link_info.advertising) {
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			req->enables |=
+				cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK);
+			req->auto_link_speeds2_mask = cpu_to_le16(bp->link_info.advertising);
+		} else if (bp->link_info.advertising) {
 			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK);
 			req->auto_link_speed_mask = cpu_to_le16(bp->link_info.advertising);
 		}
@@ -9961,7 +10898,12 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_
 		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG);
 	} else {
 		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE);
-		if (bp->link_info.req_signal_mode == BNXT_SIG_MODE_PAM4) {
+		if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			req->force_link_speeds2 = cpu_to_le16(bp->link_info.req_link_speed);
+			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2);
+			netif_info(bp, link, bp->dev, "Forcing FW speed2: %d\n",
+				   (u32)bp->link_info.req_link_speed);
+		} else if (bp->link_info.req_signal_mode == BNXT_SIG_MODE_PAM4) {
 			req->force_pam4_link_speed = cpu_to_le16(bp->link_info.req_link_speed);
 			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED);
 		} else {
@@ -10226,8 +11168,6 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_stop(bp);
 			bnxt_free_ctx_mem(bp);
-			kfree(bp->ctx);
-			bp->ctx = NULL;
 			bnxt_dcb_free(bp);
 			rc = bnxt_fw_init_one(bp);
 			if (rc) {
@@ -10578,6 +11518,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
 		bnxt_vf_reps_open(bp);
+	if (bp->ptp_cfg)
+		atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
 	return 0;
@@ -11115,7 +12057,6 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
 	struct net_device *dev = bp->dev;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-	struct hwrm_cfa_l2_filter_free_input *req;
 	struct netdev_hw_addr *ha;
 	int i, off = 0, rc;
 	bool uc_update;
@@ -11127,16 +12068,12 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 	if (!uc_update)
 		goto skip_uc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 1; i < vnic->uc_filter_count; i++) {
-		req->l2_filter_id = vnic->fw_l2_filter_id[i];
+		struct bnxt_l2_filter *fltr = vnic->l2_filters[i];
 
-		rc = hwrm_req_send(bp, req);
+		bnxt_hwrm_l2_filter_free(bp, fltr);
+		bnxt_del_l2_filter(bp, fltr);
 	}
-	hwrm_req_drop(bp, req);
 
 	vnic->uc_filter_count = 1;
 
@@ -11213,7 +12150,7 @@ static bool bnxt_can_reserve_rings(struct bnxt *bp)
 /* If the chip and firmware supports RFS */
 static bool bnxt_rfs_supported(struct bnxt *bp)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2)
 			return true;
 		return false;
@@ -11223,7 +12160,7 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 		return false;
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
-	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+	if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 		return true;
 	return false;
 }
@@ -11231,10 +12168,9 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 /* If runtime conditions support RFS */
 static bool bnxt_rfs_capable(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int vnics, max_vnics, max_rss_ctxs;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return bnxt_rfs_supported(bp);
 	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
 		return false;
@@ -11244,7 +12180,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
 
 	/* RSS contexts not a limiting factor */
-	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+	if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 		max_rss_ctxs = max_vnics;
 	if (vnics > max_vnics || vnics > max_rss_ctxs) {
 		if (bp->rx_nr_rings > 1)
@@ -11267,9 +12203,6 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	netdev_warn(bp->dev, "Unable to reserve resources to support NTUPLE filters.\n");
 	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, 1);
 	return false;
-#else
-	return false;
-#endif
 }
 
 static netdev_features_t bnxt_fix_features(struct net_device *dev,
@@ -11336,7 +12269,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
 		update_tpa = true;
 		if ((bp->flags & BNXT_FLAG_TPA) == 0 ||
 		    (flags & BNXT_FLAG_TPA) == 0 ||
-		    (bp->flags & BNXT_FLAG_CHIP_P5))
+		    (bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			re_init = true;
 	}
 
@@ -11445,9 +12378,10 @@ static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb)
 	struct udphdr *uh = udp_hdr(skb);
 	__be16 udp_port = uh->dest;
 
-	if (udp_port != bp->vxlan_port && udp_port != bp->nge_port)
+	if (udp_port != bp->vxlan_port && udp_port != bp->nge_port &&
+	    udp_port != bp->vxlan_gpe_port)
 		return false;
-	if (skb->inner_protocol_type == ENCAP_TYPE_ETHER) {
+	if (skb->inner_protocol == htons(ETH_P_TEB)) {
 		struct ethhdr *eh = inner_eth_hdr(skb);
 
 		switch (eh->h_proto) {
@@ -11458,6 +12392,11 @@ static bool bnxt_udp_tunl_check(struct bnxt *bp, struct sk_buff *skb)
 						 skb_inner_network_offset(skb),
 						 NULL);
 		}
+	} else if (skb->inner_protocol == htons(ETH_P_IP)) {
+		return true;
+	} else if (skb->inner_protocol == htons(ETH_P_IPV6)) {
+		return bnxt_exthdr_check(bp, skb, skb_inner_network_offset(skb),
+					 NULL);
 	}
 	return false;
 }
@@ -11578,15 +12517,13 @@ static int bnxt_dbg_hwrm_ring_info_get(struct bnxt *bp, u8 ring_type,
 
 static void bnxt_dump_tx_sw_state(struct bnxt_napi *bnapi)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
-	int i = bnapi->index;
-
-	if (!txr)
-		return;
+	struct bnxt_tx_ring_info *txr;
+	int i = bnapi->index, j;
 
-	netdev_info(bnapi->bp->dev, "[%d]: tx{fw_ring: %d prod: %x cons: %x}\n",
-		    i, txr->tx_ring_struct.fw_ring_id, txr->tx_prod,
-		    txr->tx_cons);
+	bnxt_for_each_napi_tx(j, bnapi, txr)
+		netdev_info(bnapi->bp->dev, "[%d.%d]: tx{fw_ring: %d prod: %x cons: %x}\n",
+			    i, j, txr->tx_ring_struct.fw_ring_id, txr->tx_prod,
+			    txr->tx_cons);
 }
 
 static void bnxt_dump_rx_sw_state(struct bnxt_napi *bnapi)
@@ -11749,8 +12686,7 @@ static void bnxt_timer(struct timer_list *t)
 	if (test_bit(BNXT_STATE_L2_FILTER_RETRY, &bp->state))
 		bnxt_queue_sp_work(bp, BNXT_RX_MASK_SP_EVENT);
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) && !bp->chip_rev &&
-	    netif_carrier_ok(dev))
+	if ((BNXT_CHIP_P5(bp)) && !bp->chip_rev && netif_carrier_ok(dev))
 		bnxt_queue_sp_work(bp, BNXT_RING_COAL_NOW_SP_EVENT);
 
 bnxt_restart_timer:
@@ -11832,6 +12768,16 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 	bnxt_rtnl_unlock_sp(bp);
 }
 
+static void bnxt_fw_fatal_close(struct bnxt *bp)
+{
+	bnxt_tx_disable(bp);
+	bnxt_disable_napi(bp);
+	bnxt_disable_int_sync(bp);
+	bnxt_free_irq(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(bp->pdev);
+}
+
 static void bnxt_fw_reset_close(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
@@ -11845,12 +12791,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 		pci_read_config_word(bp->pdev, PCI_SUBSYSTEM_ID, &val);
 		if (val == 0xffff)
 			bp->fw_reset_min_dsecs = 0;
-		bnxt_tx_disable(bp);
-		bnxt_disable_napi(bp);
-		bnxt_disable_int_sync(bp);
-		bnxt_free_irq(bp);
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(bp->pdev);
+		bnxt_fw_fatal_close(bp);
 	}
 	__bnxt_close_nic(bp, true, false);
 	bnxt_vf_reps_free(bp);
@@ -11859,8 +12800,6 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 	if (pci_is_enabled(bp->pdev))
 		pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 }
 
 static bool is_bnxt_fw_ok(struct bnxt *bp)
@@ -12003,7 +12942,7 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 {
 	int i;
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
@@ -12016,12 +12955,11 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 			continue;
 
 		cpr = &bnapi->cp_ring;
-		for (j = 0; j < 2; j++) {
-			struct bnxt_cp_ring_info *cpr2 = cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count; j++) {
+			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
 			u32 val[2];
 
-			if (!cpr2 || cpr2->has_more_work ||
-			    !bnxt_has_work(bp, cpr2))
+			if (cpr2->has_more_work || !bnxt_has_work(bp, cpr2))
 				continue;
 
 			if (cpr2->cp_raw_cons != cpr2->last_cp_raw_cons) {
@@ -12182,36 +13120,42 @@ static void bnxt_sp_task(struct work_struct *work)
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 }
 
+static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
+				int *max_cp);
+
 /* Under rtnl_lock */
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
-	int max_rx, max_tx, tx_sets = 1;
+	int max_rx, max_tx, max_cp, tx_sets = 1, tx_cp;
 	int tx_rings_needed, stats;
 	int rx_rings = rx;
-	int cp, vnics, rc;
+	int cp, vnics;
 
 	if (tcs)
 		tx_sets = tcs;
 
-	rc = bnxt_get_max_rings(bp, &max_rx, &max_tx, sh);
-	if (rc)
-		return rc;
+	_bnxt_get_max_rings(bp, &max_rx, &max_tx, &max_cp);
 
-	if (max_rx < rx)
+	if (max_rx < rx_rings)
 		return -ENOMEM;
 
+	if (bp->flags & BNXT_FLAG_AGG_RINGS)
+		rx_rings <<= 1;
+
 	tx_rings_needed = tx * tx_sets + tx_xdp;
 	if (max_tx < tx_rings_needed)
 		return -ENOMEM;
 
 	vnics = 1;
-	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
-		vnics += rx_rings;
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5_PLUS)) ==
+	    BNXT_FLAG_RFS)
+		vnics += rx;
 
-	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		rx_rings <<= 1;
-	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
+	tx_cp = __bnxt_num_tx_to_cp(bp, tx_rings_needed, tx_sets, tx_xdp);
+	cp = sh ? max_t(int, tx_cp, rx) : tx_cp + rx;
+	if (max_cp < cp)
+		return -ENOMEM;
 	stats = cp;
 	if (BNXT_NEW_RM(bp)) {
 		cp += bnxt_get_ulp_msix_num(bp);
@@ -12286,10 +13230,10 @@ static bool bnxt_fw_pre_resv_vnics(struct bnxt *bp)
 {
 	u16 fw_maj = BNXT_FW_MAJ(bp), fw_bld = BNXT_FW_BLD(bp);
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (fw_maj > 218 || (fw_maj == 218 && fw_bld >= 18)))
 		return true;
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (fw_maj > 216 || (fw_maj == 216 && fw_bld >= 172)))
 		return true;
 	return false;
@@ -12372,15 +13316,15 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 
 static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp)
 {
-	bp->flags &= ~BNXT_FLAG_UDP_RSS_CAP;
+	bp->rss_cap &= ~BNXT_RSS_CAP_UDP_RSS_CAP;
 	bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bp->rss_hash_delta = bp->rss_hash_cfg;
 	if (BNXT_CHIP_P4_PLUS(bp) && bp->hwrm_spec_code >= 0x10501) {
-		bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
+		bp->rss_cap |= BNXT_RSS_CAP_UDP_RSS_CAP;
 		bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
 				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
 	}
@@ -12850,7 +13794,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool sh = false;
-	int rc;
+	int rc, tx_cp;
 
 	if (tc > bp->max_tc) {
 		netdev_err(dev, "Too many traffic classes requested: %d. Max supported is %d.\n",
@@ -12858,7 +13802,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		return -EINVAL;
 	}
 
-	if (netdev_get_num_tc(dev) == tc)
+	if (bp->num_tc == tc)
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -12876,13 +13820,16 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	if (tc) {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc;
 		netdev_set_num_tc(dev, tc);
+		bp->num_tc = tc;
 	} else {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 		netdev_reset_tc(dev);
+		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-			       bp->tx_nr_rings + bp->rx_nr_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
@@ -12932,38 +13879,102 @@ static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-#ifdef CONFIG_RFS_ACCEL
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb)
+{
+	struct bnxt_vnic_info *vnic;
+
+	if (skb)
+		return skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
+
+	vnic = &bp->vnic_info[0];
+	return bnxt_toeplitz(bp, fkeys, (void *)vnic->rss_hash_key);
+}
+
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx)
+{
+	struct hlist_head *head;
+	int bit_id;
+
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap, BNXT_MAX_FLTR, 0);
+	if (bit_id < 0) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return -ENOMEM;
+	}
+
+	fltr->base.sw_id = (u16)bit_id;
+	fltr->base.type = BNXT_FLTR_TYPE_NTUPLE;
+	fltr->base.flags |= BNXT_ACT_RING_DST;
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	bp->ntp_fltr_count++;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	return 0;
+}
+
 static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 			    struct bnxt_ntuple_filter *f2)
 {
 	struct flow_keys *keys1 = &f1->fkeys;
 	struct flow_keys *keys2 = &f2->fkeys;
 
+	if (f1->ntuple_flags != f2->ntuple_flags)
+		return false;
+
 	if (keys1->basic.n_proto != keys2->basic.n_proto ||
 	    keys1->basic.ip_proto != keys2->basic.ip_proto)
 		return false;
 
 	if (keys1->basic.n_proto == htons(ETH_P_IP)) {
-		if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
-		    keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst))
 			return false;
 	} else {
-		if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
-			   sizeof(keys1->addrs.v6addrs.src)) ||
-		    memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
-			   sizeof(keys1->addrs.v6addrs.dst)))
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.src,
+			    &keys2->addrs.v6addrs.src,
+			    sizeof(keys1->addrs.v6addrs.src))) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.dst,
+			    &keys2->addrs.v6addrs.dst,
+			    sizeof(keys1->addrs.v6addrs.dst))))
 			return false;
 	}
 
-	if (keys1->ports.ports == keys2->ports.ports &&
-	    keys1->control.flags == keys2->control.flags &&
-	    ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
-	    ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
+	if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) &&
+	     keys1->ports.src != keys2->ports.src) ||
+	    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) &&
+	     keys1->ports.dst != keys2->ports.dst))
+		return false;
+
+	if (keys1->control.flags == keys2->control.flags &&
+	    f1->l2_fltr == f2->l2_fltr)
 		return true;
 
 	return false;
 }
 
+struct bnxt_ntuple_filter *
+bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx)
+{
+	struct bnxt_ntuple_filter *f;
+	struct hlist_head *head;
+
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_for_each_entry_rcu(f, head, base.hash) {
+		if (bnxt_fltr_match(f, fltr))
+			return f;
+	}
+	return NULL;
+}
+
+#ifdef CONFIG_RFS_ACCEL
 static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 			      u16 rxq_index, u32 flow_id)
 {
@@ -12971,29 +13982,31 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	struct bnxt_ntuple_filter *fltr, *new_fltr;
 	struct flow_keys *fkeys;
 	struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
-	int rc = 0, idx, bit_id, l2_idx = 0;
-	struct hlist_head *head;
+	struct bnxt_l2_filter *l2_fltr;
+	int rc = 0, idx;
 	u32 flags;
 
-	if (!ether_addr_equal(dev->dev_addr, eth->h_dest)) {
-		struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-		int off = 0, j;
+	if (ether_addr_equal(dev->dev_addr, eth->h_dest)) {
+		l2_fltr = bp->vnic_info[0].l2_filters[0];
+		atomic_inc(&l2_fltr->refcnt);
+	} else {
+		struct bnxt_l2_key key;
 
-		netif_addr_lock_bh(dev);
-		for (j = 0; j < vnic->uc_filter_count; j++, off += ETH_ALEN) {
-			if (ether_addr_equal(eth->h_dest,
-					     vnic->uc_list + off)) {
-				l2_idx = j + 1;
-				break;
-			}
-		}
-		netif_addr_unlock_bh(dev);
-		if (!l2_idx)
+		ether_addr_copy(key.dst_mac_addr, eth->h_dest);
+		key.vlan = 0;
+		l2_fltr = bnxt_lookup_l2_filter_from_key(bp, &key);
+		if (!l2_fltr)
 			return -EINVAL;
+		if (l2_fltr->base.flags & BNXT_ACT_FUNC_DST) {
+			bnxt_del_l2_filter(bp, l2_fltr);
+			return -EINVAL;
+		}
 	}
 	new_fltr = kzalloc(sizeof(*new_fltr), GFP_ATOMIC);
-	if (!new_fltr)
+	if (!new_fltr) {
+		bnxt_del_l2_filter(bp, l2_fltr);
 		return -ENOMEM;
+	}
 
 	fkeys = &new_fltr->fkeys;
 	if (!skb_flow_dissect_flow_keys(skb, fkeys, 0)) {
@@ -13020,49 +14033,52 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		goto err_free;
 	}
 
-	memcpy(new_fltr->dst_mac_addr, eth->h_dest, ETH_ALEN);
-	memcpy(new_fltr->src_mac_addr, eth->h_source, ETH_ALEN);
+	new_fltr->l2_fltr = l2_fltr;
+	new_fltr->ntuple_flags = BNXT_NTUPLE_MATCH_ALL;
 
-	idx = skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
-	head = &bp->ntp_fltr_hash_tbl[idx];
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, skb);
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(fltr, head, hash) {
-		if (bnxt_fltr_match(fltr, new_fltr)) {
-			rc = fltr->sw_id;
-			rcu_read_unlock();
-			goto err_free;
-		}
-	}
-	rcu_read_unlock();
-
-	spin_lock_bh(&bp->ntp_fltr_lock);
-	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
-					 BNXT_NTP_FLTR_MAX_FLTR, 0);
-	if (bit_id < 0) {
-		spin_unlock_bh(&bp->ntp_fltr_lock);
-		rc = -ENOMEM;
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
+		rc = fltr->base.sw_id;
+		rcu_read_unlock();
 		goto err_free;
 	}
+	rcu_read_unlock();
 
-	new_fltr->sw_id = (u16)bit_id;
 	new_fltr->flow_id = flow_id;
-	new_fltr->l2_fltr_idx = l2_idx;
-	new_fltr->rxq = rxq_index;
-	hlist_add_head_rcu(&new_fltr->hash, head);
-	bp->ntp_fltr_count++;
-	spin_unlock_bh(&bp->ntp_fltr_lock);
-
-	bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
-
-	return new_fltr->sw_id;
+	new_fltr->base.rxq = rxq_index;
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
+		bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
+		return new_fltr->base.sw_id;
+	}
 
 err_free:
+	bnxt_del_l2_filter(bp, l2_fltr);
 	kfree(new_fltr);
 	return rc;
 }
+#endif
+
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr)
+{
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	bp->ntp_fltr_count--;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	bnxt_del_l2_filter(bp, fltr->l2_fltr);
+	clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+	kfree_rcu(fltr, base.rcu);
+}
 
 static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 {
+#ifdef CONFIG_RFS_ACCEL
 	int i;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
@@ -13072,13 +14088,15 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 		int rc;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
 			bool del = false;
 
-			if (test_bit(BNXT_FLTR_VALID, &fltr->state)) {
-				if (rps_may_expire_flow(bp->dev, fltr->rxq,
+			if (test_bit(BNXT_FLTR_VALID, &fltr->base.state)) {
+				if (fltr->base.flags & BNXT_ACT_NO_AGING)
+					continue;
+				if (rps_may_expire_flow(bp->dev, fltr->base.rxq,
 							fltr->flow_id,
-							fltr->sw_id)) {
+							fltr->base.sw_id)) {
 					bnxt_hwrm_cfa_ntuple_filter_free(bp,
 									 fltr);
 					del = true;
@@ -13089,30 +14107,16 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 				if (rc)
 					del = true;
 				else
-					set_bit(BNXT_FLTR_VALID, &fltr->state);
+					set_bit(BNXT_FLTR_VALID, &fltr->base.state);
 			}
 
-			if (del) {
-				spin_lock_bh(&bp->ntp_fltr_lock);
-				hlist_del_rcu(&fltr->hash);
-				bp->ntp_fltr_count--;
-				spin_unlock_bh(&bp->ntp_fltr_lock);
-				synchronize_rcu();
-				clear_bit(fltr->sw_id, bp->ntp_fltr_bmap);
-				kfree(fltr);
-			}
+			if (del)
+				bnxt_del_ntp_filter(bp, fltr);
 		}
 	}
+#endif
 }
 
-#else
-
-static void bnxt_cfg_ntp_filters(struct bnxt *bp)
-{
-}
-
-#endif /* CONFIG_RFS_ACCEL */
-
 static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 				    unsigned int entry, struct udp_tunnel_info *ti)
 {
@@ -13120,9 +14124,11 @@ static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int tabl
 	unsigned int cmd;
 
 	if (ti->type == UDP_TUNNEL_TYPE_VXLAN)
-		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN;
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN;
+	else if (ti->type == UDP_TUNNEL_TYPE_GENEVE)
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE;
 	else
-		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE;
+		cmd = TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE;
 
 	return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti->port, cmd);
 }
@@ -13135,8 +14141,10 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta
 
 	if (ti->type == UDP_TUNNEL_TYPE_VXLAN)
 		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN;
-	else
+	else if (ti->type == UDP_TUNNEL_TYPE_GENEVE)
 		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE;
+	else
+		cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE;
 
 	return bnxt_hwrm_tunnel_dst_port_free(bp, cmd);
 }
@@ -13150,6 +14158,16 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
 	},
+}, bnxt_udp_tunnels_p7 = {
+	.set_port	= bnxt_udp_tunnel_set_port,
+	.unset_port	= bnxt_udp_tunnel_unset_port,
+	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
+			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN_GPE, },
+	},
 };
 
 static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
@@ -13257,6 +14275,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_free_l2_filters(bp, true);
+	bnxt_free_ntp_fltrs(bp, true);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	/* Flush any pending tasks */
 	cancel_work_sync(&bp->sp_task);
@@ -13279,8 +14299,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 	bnxt_free_port_stats(bp);
@@ -13349,7 +14367,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	max_irq = min_t(int, bnxt_get_max_func_irqs(bp) -
 			bnxt_get_ulp_msix_num(bp),
 			hw_resc->max_stat_ctxs - bnxt_get_ulp_stat_ctxs(bp));
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		*max_cp = min_t(int, *max_cp, max_irq);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) {
@@ -13358,8 +14376,14 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	}
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		*max_rx >>= 1;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_trim_rings(bp, max_rx, max_tx, *max_cp, false);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		int rc;
+
+		rc = __bnxt_trim_rings(bp, max_rx, max_tx, *max_cp, false);
+		if (rc) {
+			*max_rx = 0;
+			*max_tx = 0;
+		}
 		/* On P5 chips, max_cp output param should be available NQs */
 		*max_cp = max_irq;
 	}
@@ -13660,7 +14684,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	max_irqs = bnxt_get_max_irq(pdev);
-	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
+	dev = alloc_etherdev_mqs(sizeof(*bp), max_irqs * BNXT_MAX_QUEUE,
+				 max_irqs);
 	if (!dev)
 		return -ENOMEM;
 
@@ -13702,10 +14727,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (BNXT_PF(bp))
 		bnxt_vpd_read_info(bp);
 
-	if (BNXT_CHIP_P5(bp)) {
-		bp->flags |= BNXT_FLAG_CHIP_P5;
-		if (BNXT_CHIP_SR2(bp))
-			bp->flags |= BNXT_FLAG_CHIP_SR2;
+	if (BNXT_CHIP_P5_PLUS(bp)) {
+		bp->flags |= BNXT_FLAG_CHIP_P5_PLUS;
+		if (BNXT_CHIP_P7(bp))
+			bp->flags |= BNXT_FLAG_CHIP_P7;
 	}
 
 	rc = bnxt_alloc_rss_indir_tbl(bp);
@@ -13730,6 +14755,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			   NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
 			   NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH |
 			   NETIF_F_RXCSUM | NETIF_F_GRO;
+	if (bp->flags & BNXT_FLAG_UDP_GSO_CAP)
+		dev->hw_features |= NETIF_F_GSO_UDP_L4;
 
 	if (BNXT_SUPPORTS_TPA(bp))
 		dev->hw_features |= NETIF_F_LRO;
@@ -13740,7 +14767,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
 			NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
 			NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_PARTIAL;
-	dev->udp_tunnel_nic_info = &bnxt_udp_tunnels;
+	if (bp->flags & BNXT_FLAG_UDP_GSO_CAP)
+		dev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
+	if (bp->flags & BNXT_FLAG_CHIP_P7)
+		dev->udp_tunnel_nic_info = &bnxt_udp_tunnels_p7;
+	else
+		dev->udp_tunnel_nic_info = &bnxt_udp_tunnels;
 
 	dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM |
 				    NETIF_F_GSO_GRE_CSUM;
@@ -13768,7 +14800,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bp->gro_func = bnxt_gro_func_5730x;
 		if (BNXT_CHIP_P4(bp))
 			bp->gro_func = bnxt_gro_func_5731x;
-		else if (BNXT_CHIP_P5(bp))
+		else if (BNXT_CHIP_P5_PLUS(bp))
 			bp->gro_func = bnxt_gro_func_5750x;
 	}
 	if (!BNXT_CHIP_P4_PLUS(bp))
@@ -13794,6 +14826,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	bnxt_init_l2_fltr_tbl(bp);
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
@@ -13876,8 +14909,6 @@ init_err_pci_clean:
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 
@@ -13930,8 +14961,6 @@ static int bnxt_suspend(struct device *device)
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	rtnl_unlock();
 	return rc;
 }
@@ -14008,6 +15037,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(netdev);
+	bool abort = false;
 
 	netdev_info(netdev, "PCI I/O error detected\n");
 
@@ -14016,22 +15046,31 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 
 	bnxt_ulp_stop(bp);
 
-	if (state == pci_channel_io_perm_failure) {
+	if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
+		netdev_err(bp->dev, "Firmware reset already in progress\n");
+		abort = true;
+	}
+
+	if (abort || state == pci_channel_io_perm_failure) {
 		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
-	if (state == pci_channel_io_frozen)
+	/* Link is not reliable anymore if state is pci_channel_io_frozen
+	 * so we disable bus master to prevent any potential bad DMAs before
+	 * freeing kernel memory.
+	 */
+	if (state == pci_channel_io_frozen) {
 		set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state);
+		bnxt_fw_fatal_close(bp);
+	}
 
 	if (netif_running(netdev))
-		bnxt_close(netdev);
+		__bnxt_close_nic(bp, true, true);
 
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	rtnl_unlock();
 
 	/* Request a slot slot reset. */
@@ -14111,6 +15150,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	}
 
 reset_exit:
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	bnxt_clear_reservations(bp, true);
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a7d7b09ea1..47338b48ca 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -18,7 +18,7 @@
  */
 #define DRV_VER_MAJ	1
 #define DRV_VER_MIN	10
-#define DRV_VER_UPD	2
+#define DRV_VER_UPD	3
 
 #include <linux/ethtool.h>
 #include <linux/interrupt.h>
@@ -61,6 +61,24 @@ struct tx_bd {
 	__le64 tx_bd_haddr;
 } __packed;
 
+#define TX_OPAQUE_IDX_MASK	0x0000ffff
+#define TX_OPAQUE_BDS_MASK	0x00ff0000
+#define TX_OPAQUE_BDS_SHIFT	16
+#define TX_OPAQUE_RING_MASK	0xff000000
+#define TX_OPAQUE_RING_SHIFT	24
+
+#define SET_TX_OPAQUE(bp, txr, idx, bds)				\
+	(((txr)->tx_napi_idx << TX_OPAQUE_RING_SHIFT) |			\
+	 ((bds) << TX_OPAQUE_BDS_SHIFT) | ((idx) & (bp)->tx_ring_mask))
+
+#define TX_OPAQUE_IDX(opq)	((opq) & TX_OPAQUE_IDX_MASK)
+#define TX_OPAQUE_RING(opq)	(((opq) & TX_OPAQUE_RING_MASK) >>	\
+				 TX_OPAQUE_RING_SHIFT)
+#define TX_OPAQUE_BDS(opq)	(((opq) & TX_OPAQUE_BDS_MASK) >>	\
+				 TX_OPAQUE_BDS_SHIFT)
+#define TX_OPAQUE_PROD(bp, opq)	((TX_OPAQUE_IDX(opq) + TX_OPAQUE_BDS(opq)) &\
+				 (bp)->tx_ring_mask)
+
 struct tx_bd_ext {
 	__le32 tx_bd_hsize_lflags;
 	#define TX_BD_FLAGS_TCP_UDP_CHKSUM			(1 << 0)
@@ -121,11 +139,15 @@ struct tx_cmp {
 	__le32 tx_cmp_flags_type;
 	#define CMP_TYPE					(0x3f << 0)
 	 #define CMP_TYPE_TX_L2_CMP				 0
+	 #define CMP_TYPE_TX_L2_COAL_CMP			 2
+	 #define CMP_TYPE_TX_L2_PKT_TS_CMP			 4
 	 #define CMP_TYPE_RX_L2_CMP				 17
 	 #define CMP_TYPE_RX_AGG_CMP				 18
 	 #define CMP_TYPE_RX_L2_TPA_START_CMP			 19
 	 #define CMP_TYPE_RX_L2_TPA_END_CMP			 21
 	 #define CMP_TYPE_RX_TPA_AGG_CMP			 22
+	 #define CMP_TYPE_RX_L2_V3_CMP				 23
+	 #define CMP_TYPE_RX_L2_TPA_START_V3_CMP		 25
 	 #define CMP_TYPE_STATUS_CMP				 32
 	 #define CMP_TYPE_REMOTE_DRIVER_REQ			 34
 	 #define CMP_TYPE_REMOTE_DRIVER_RESP			 36
@@ -152,9 +174,13 @@ struct tx_cmp {
 	 #define TX_CMP_ERRORS_DMA_ERROR			 (1 << 6)
 	 #define TX_CMP_ERRORS_HINT_TOO_SHORT			 (1 << 7)
 
-	__le32 tx_cmp_unsed_3;
+	__le32 sq_cons_idx;
+	#define TX_CMP_SQ_CONS_IDX_MASK				0x00ffffff
 };
 
+#define TX_CMP_SQ_CONS_IDX(txcmp)					\
+	(le32_to_cpu((txcmp)->sq_cons_idx) & TX_CMP_SQ_CONS_IDX_MASK)
+
 struct rx_cmp {
 	__le32 rx_cmp_len_flags_type;
 	#define RX_CMP_CMP_TYPE					(0x3f << 0)
@@ -182,8 +208,20 @@ struct rx_cmp {
 	 #define RX_CMP_AGG_BUFS_SHIFT				 1
 	#define RX_CMP_RSS_HASH_TYPE				(0x7f << 9)
 	 #define RX_CMP_RSS_HASH_TYPE_SHIFT			 9
+	#define RX_CMP_V3_RSS_EXT_OP_LEGACY			(0xf << 12)
+	 #define RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT		 12
+	#define RX_CMP_V3_RSS_EXT_OP_NEW			(0xf << 8)
+	 #define RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT			 8
 	#define RX_CMP_PAYLOAD_OFFSET				(0xff << 16)
 	 #define RX_CMP_PAYLOAD_OFFSET_SHIFT			 16
+	#define RX_CMP_SUB_NS_TS				(0xf << 16)
+	 #define RX_CMP_SUB_NS_TS_SHIFT				 16
+	#define RX_CMP_METADATA1				(0xf << 28)
+	 #define RX_CMP_METADATA1_SHIFT				 28
+	#define RX_CMP_METADATA1_TPID_SEL			(0x7 << 28)
+	#define RX_CMP_METADATA1_TPID_8021Q			(0x1 << 28)
+	#define RX_CMP_METADATA1_TPID_8021AD			(0x0 << 28)
+	#define RX_CMP_METADATA1_VALID				(0x8 << 28)
 
 	__le32 rx_cmp_rss_hash;
 };
@@ -203,6 +241,30 @@ struct rx_cmp {
 	(((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\
 	  RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
 
+#define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp)				\
+	((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_LEGACY) >>\
+	 RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT)
+
+#define RX_CMP_V3_HASH_TYPE_NEW(rxcmp)				\
+	((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_NEW) >>\
+	 RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT)
+
+#define RX_CMP_V3_HASH_TYPE(bp, rxcmp)				\
+	(((bp)->rss_cap & BNXT_RSS_CAP_RSS_TCAM) ?		\
+	  RX_CMP_V3_HASH_TYPE_NEW(rxcmp) :			\
+	  RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp))
+
+#define EXT_OP_INNER_4		0x0
+#define EXT_OP_OUTER_4		0x2
+#define EXT_OP_INNFL_3		0x8
+#define EXT_OP_OUTFL_3		0xa
+
+#define RX_CMP_VLAN_VALID(rxcmp)				\
+	((rxcmp)->rx_cmp_misc_v1 & cpu_to_le32(RX_CMP_METADATA1_VALID))
+
+#define RX_CMP_VLAN_TPID_SEL(rxcmp)				\
+	(le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_METADATA1_TPID_SEL)
+
 struct rx_cmp_ext {
 	__le32 rx_cmp_flags2;
 	#define RX_CMP_FLAGS2_IP_CS_CALC			0x1
@@ -250,6 +312,9 @@ struct rx_cmp_ext {
 
 	#define RX_CMPL_CFA_CODE_MASK				(0xffff << 16)
 	 #define RX_CMPL_CFA_CODE_SFT				 16
+	#define RX_CMPL_METADATA0_TCI_MASK			(0xffff << 16)
+	#define RX_CMPL_METADATA0_VID_MASK			(0x0fff << 16)
+	 #define RX_CMPL_METADATA0_SFT				 16
 
 	__le32 rx_cmp_timestamp;
 };
@@ -275,6 +340,10 @@ struct rx_cmp_ext {
 	((le32_to_cpu((rxcmpl1)->rx_cmp_cfa_code_errors_v2) &		\
 	  RX_CMPL_CFA_CODE_MASK) >> RX_CMPL_CFA_CODE_SFT)
 
+#define RX_CMP_METADATA0_TCI(rxcmp1)					\
+	((le32_to_cpu((rxcmp1)->rx_cmp_cfa_code_errors_v2) &		\
+	  RX_CMPL_METADATA0_TCI_MASK) >> RX_CMPL_METADATA0_SFT)
+
 struct rx_agg_cmp {
 	__le32 rx_agg_cmp_len_flags_type;
 	#define RX_AGG_CMP_TYPE					(0x3f << 0)
@@ -317,10 +386,18 @@ struct rx_tpa_start_cmp {
 	#define RX_TPA_START_CMP_V1				(0x1 << 0)
 	#define RX_TPA_START_CMP_RSS_HASH_TYPE			(0x7f << 9)
 	 #define RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT		 9
+	#define RX_TPA_START_CMP_V3_RSS_HASH_TYPE		(0x1ff << 7)
+	 #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT	 7
 	#define RX_TPA_START_CMP_AGG_ID				(0x7f << 25)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT			 25
 	#define RX_TPA_START_CMP_AGG_ID_P5			(0xffff << 16)
 	 #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5		 16
+	#define RX_TPA_START_CMP_METADATA1			(0xf << 28)
+	 #define RX_TPA_START_CMP_METADATA1_SHIFT		 28
+	#define RX_TPA_START_METADATA1_TPID_SEL			(0x7 << 28)
+	#define RX_TPA_START_METADATA1_TPID_8021Q		(0x1 << 28)
+	#define RX_TPA_START_METADATA1_TPID_8021AD		(0x0 << 28)
+	#define RX_TPA_START_METADATA1_VALID			(0x8 << 28)
 
 	__le32 rx_tpa_start_cmp_rss_hash;
 };
@@ -334,6 +411,11 @@ struct rx_tpa_start_cmp {
 	   RX_TPA_START_CMP_RSS_HASH_TYPE) >>				\
 	  RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
 
+#define TPA_START_V3_HASH_TYPE(rx_tpa_start)				\
+	(((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
+	   RX_TPA_START_CMP_V3_RSS_HASH_TYPE) >>			\
+	  RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK)
+
 #define TPA_START_AGG_ID(rx_tpa_start)					\
 	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
 	 RX_TPA_START_CMP_AGG_ID) >> RX_TPA_START_CMP_AGG_ID_SHIFT)
@@ -346,6 +428,14 @@ struct rx_tpa_start_cmp {
 	((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type &		\
 	 cpu_to_le32(RX_TPA_START_CMP_FLAGS_ERROR))
 
+#define TPA_START_VLAN_VALID(rx_tpa_start)				\
+	((rx_tpa_start)->rx_tpa_start_cmp_misc_v1 &			\
+	 cpu_to_le32(RX_TPA_START_METADATA1_VALID))
+
+#define TPA_START_VLAN_TPID_SEL(rx_tpa_start)				\
+	(le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) &	\
+	 RX_TPA_START_METADATA1_TPID_SEL)
+
 struct rx_tpa_start_cmp_ext {
 	__le32 rx_tpa_start_cmp_flags2;
 	#define RX_TPA_START_CMP_FLAGS2_IP_CS_CALC		(0x1 << 0)
@@ -356,6 +446,8 @@ struct rx_tpa_start_cmp_ext {
 	#define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_VALID		(0x1 << 9)
 	#define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT		(0x3 << 10)
 	 #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT_SHIFT	 10
+	#define RX_TPA_START_CMP_V3_FLAGS2_T_IP_TYPE		(0x1 << 10)
+	#define RX_TPA_START_CMP_V3_FLAGS2_AGG_GRO		(0x1 << 11)
 	#define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL		(0xffff << 16)
 	 #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_SHIFT	 16
 
@@ -369,6 +461,9 @@ struct rx_tpa_start_cmp_ext {
 	 #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_FLUSH	 (0x5 << 1)
 	#define RX_TPA_START_CMP_CFA_CODE			(0xffff << 16)
 	 #define RX_TPA_START_CMPL_CFA_CODE_SHIFT		 16
+	#define RX_TPA_START_CMP_METADATA0_TCI_MASK		(0xffff << 16)
+	#define RX_TPA_START_CMP_METADATA0_VID_MASK		(0x0fff << 16)
+	 #define RX_TPA_START_CMP_METADATA0_SFT			 16
 	__le32 rx_tpa_start_cmp_hdr_info;
 };
 
@@ -385,6 +480,11 @@ struct rx_tpa_start_cmp_ext {
 	  RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK) >>			\
 	 RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT)
 
+#define TPA_START_METADATA0_TCI(rx_tpa_start)				\
+	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) &	\
+	  RX_TPA_START_CMP_METADATA0_TCI_MASK) >>			\
+	 RX_TPA_START_CMP_METADATA0_SFT)
+
 struct rx_tpa_end_cmp {
 	__le32 rx_tpa_end_cmp_len_flags_type;
 	#define RX_TPA_END_CMP_TYPE				(0x3f << 0)
@@ -529,6 +629,8 @@ struct nqe_cn {
 	#define NQ_CN_TYPE_SFT            0
 	#define NQ_CN_TYPE_CQ_NOTIFICATION  0x30UL
 	#define NQ_CN_TYPE_LAST            NQ_CN_TYPE_CQ_NOTIFICATION
+	#define NQ_CN_TOGGLE_MASK         0xc0UL
+	#define NQ_CN_TOGGLE_SFT          6
 	__le16	reserved16;
 	__le32	cq_handle_low;
 	__le32	v;
@@ -536,6 +638,23 @@ struct nqe_cn {
 	__le32	cq_handle_high;
 };
 
+#define BNXT_NQ_HDL_IDX_MASK	0x00ffffff
+#define BNXT_NQ_HDL_TYPE_MASK	0xff000000
+#define BNXT_NQ_HDL_TYPE_SHIFT	24
+#define BNXT_NQ_HDL_TYPE_RX	0x00
+#define BNXT_NQ_HDL_TYPE_TX	0x01
+
+#define BNXT_NQ_HDL_IDX(hdl)	((hdl) & BNXT_NQ_HDL_IDX_MASK)
+#define BNXT_NQ_HDL_TYPE(hdl)	(((hdl) & BNXT_NQ_HDL_TYPE_MASK) >>	\
+				 BNXT_NQ_HDL_TYPE_SHIFT)
+
+#define BNXT_SET_NQ_HDL(cpr)						\
+	(((cpr)->cp_ring_type << BNXT_NQ_HDL_TYPE_SHIFT) | (cpr)->cp_idx)
+
+#define NQE_CN_TYPE(type)	((type) & NQ_CN_TYPE_MASK)
+#define NQE_CN_TOGGLE(type)	(((type) & NQ_CN_TOGGLE_MASK) >>	\
+				 NQ_CN_TOGGLE_SFT)
+
 #define DB_IDX_MASK						0xffffff
 #define DB_IDX_VALID						(0x1 << 26)
 #define DB_IRQ_DIS						(0x1 << 27)
@@ -551,9 +670,14 @@ struct nqe_cn {
 
 /* 64-bit doorbell */
 #define DBR_INDEX_MASK					0x0000000000ffffffULL
+#define DBR_EPOCH_MASK					0x01000000UL
+#define DBR_EPOCH_SFT					24
+#define DBR_TOGGLE_MASK					0x06000000UL
+#define DBR_TOGGLE_SFT					25
 #define DBR_XID_MASK					0x000fffff00000000ULL
 #define DBR_XID_SFT					32
 #define DBR_PATH_L2					(0x1ULL << 56)
+#define DBR_VALID					(0x1ULL << 58)
 #define DBR_TYPE_SQ					(0x0ULL << 60)
 #define DBR_TYPE_RQ					(0x1ULL << 60)
 #define DBR_TYPE_SRQ					(0x2ULL << 60)
@@ -566,6 +690,7 @@ struct nqe_cn {
 #define DBR_TYPE_CQ_CUTOFF_ACK				(0x9ULL << 60)
 #define DBR_TYPE_NQ					(0xaULL << 60)
 #define DBR_TYPE_NQ_ARM					(0xbULL << 60)
+#define DBR_TYPE_NQ_MASK				(0xeULL << 60)
 #define DBR_TYPE_NULL					(0xfULL << 60)
 
 #define DB_PF_OFFSET_P5					0x10000
@@ -661,10 +786,12 @@ struct nqe_cn {
  */
 #define BNXT_MIN_TX_DESC_CNT		(MAX_SKB_FRAGS + 2)
 
-#define RX_RING(x)	(((x) & ~(RX_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
+#define RX_RING(bp, x)	(((x) & (bp)->rx_ring_mask) >> (BNXT_PAGE_SHIFT - 4))
+#define RX_AGG_RING(bp, x)	(((x) & (bp)->rx_agg_ring_mask) >>	\
+				 (BNXT_PAGE_SHIFT - 4))
 #define RX_IDX(x)	((x) & (RX_DESC_CNT - 1))
 
-#define TX_RING(x)	(((x) & ~(TX_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
+#define TX_RING(bp, x)	(((x) & (bp)->tx_ring_mask) >> (BNXT_PAGE_SHIFT - 4))
 #define TX_IDX(x)	((x) & (TX_DESC_CNT - 1))
 
 #define CP_RING(x)	(((x) & ~(CP_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4))
@@ -691,11 +818,14 @@ struct nqe_cn {
 #define RX_CMP_TYPE(rxcmp)					\
 	(le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_CMP_TYPE)
 
-#define NEXT_RX(idx)		(((idx) + 1) & bp->rx_ring_mask)
+#define RING_RX(bp, idx)	((idx) & (bp)->rx_ring_mask)
+#define NEXT_RX(idx)		((idx) + 1)
 
-#define NEXT_RX_AGG(idx)	(((idx) + 1) & bp->rx_agg_ring_mask)
+#define RING_RX_AGG(bp, idx)	((idx) & (bp)->rx_agg_ring_mask)
+#define NEXT_RX_AGG(idx)	((idx) + 1)
 
-#define NEXT_TX(idx)		(((idx) + 1) & bp->tx_ring_mask)
+#define RING_TX(bp, idx)	((idx) & (bp)->tx_ring_mask)
+#define NEXT_TX(idx)		((idx) + 1)
 
 #define ADV_RAW_CMP(idx, n)	((idx) + (n))
 #define NEXT_RAW_CMP(idx)	ADV_RAW_CMP(idx, 1)
@@ -708,6 +838,7 @@ struct nqe_cn {
 #define BNXT_AGG_EVENT		2
 #define BNXT_TX_EVENT		4
 #define BNXT_REDIRECT_EVENT	8
+#define BNXT_TX_CMP_EVENT	0x10
 
 struct bnxt_sw_tx_bd {
 	union {
@@ -736,13 +867,6 @@ struct bnxt_sw_rx_agg_bd {
 	dma_addr_t		mapping;
 };
 
-struct bnxt_mem_init {
-	u8	init_val;
-	u16	offset;
-#define	BNXT_MEM_INVALID_OFFSET	0xffff
-	u16	size;
-};
-
 struct bnxt_ring_mem_info {
 	int			nr_pages;
 	int			page_size;
@@ -752,7 +876,7 @@ struct bnxt_ring_mem_info {
 #define BNXT_RMEM_USE_FULL_PAGE_FLAG	4
 
 	u16			depth;
-	struct bnxt_mem_init	*mem_init;
+	struct bnxt_ctx_mem_type	*ctx_mem;
 
 	void			**pg_arr;
 	dma_addr_t		*dma_arr;
@@ -794,13 +918,27 @@ struct bnxt_db_info {
 		u64		db_key64;
 		u32		db_key32;
 	};
+	u32			db_ring_mask;
+	u32			db_epoch_mask;
+	u8			db_epoch_shift;
 };
 
+#define DB_EPOCH(db, idx)	(((idx) & (db)->db_epoch_mask) <<	\
+				 ((db)->db_epoch_shift))
+
+#define DB_TOGGLE(tgl)		((tgl) << DBR_TOGGLE_SFT)
+
+#define DB_RING_IDX(db, idx)	(((idx) & (db)->db_ring_mask) |		\
+				 DB_EPOCH(db, idx))
+
 struct bnxt_tx_ring_info {
 	struct bnxt_napi	*bnapi;
+	struct bnxt_cp_ring_info	*tx_cpr;
 	u16			tx_prod;
 	u16			tx_cons;
+	u16			tx_hw_cons;
 	u16			txq_index;
+	u8			tx_napi_idx;
 	u8			kick_pending;
 	struct bnxt_db_info	tx_db;
 
@@ -895,6 +1033,8 @@ struct bnxt_tpa_info {
 
 	u16			cfa_code; /* cfa_code in TPA start compl */
 	u8			agg_count;
+	u8			vlan_valid:1;
+	u8			cfa_code_valid:1;
 	struct rx_agg_cmp	*agg_arr;
 };
 
@@ -907,6 +1047,7 @@ struct bnxt_tpa_idx_map {
 
 struct bnxt_rx_ring_info {
 	struct bnxt_napi	*bnapi;
+	struct bnxt_cp_ring_info	*rx_cpr;
 	u16			rx_prod;
 	u16			rx_agg_prod;
 	u16			rx_sw_agg_prod;
@@ -986,6 +1127,11 @@ struct bnxt_cp_ring_info {
 
 	u8			had_work_done:1;
 	u8			has_more_work:1;
+	u8			had_nqe_notify:1;
+	u8			toggle;
+
+	u8			cp_ring_type;
+	u8			cp_idx;
 
 	u32			last_cp_raw_cons;
 
@@ -1010,11 +1156,18 @@ struct bnxt_cp_ring_info {
 
 	struct bnxt_ring_struct	cp_ring_struct;
 
-	struct bnxt_cp_ring_info *cp_ring_arr[2];
-#define BNXT_RX_HDL	0
-#define BNXT_TX_HDL	1
+	int			cp_ring_count;
+	struct bnxt_cp_ring_info *cp_ring_arr;
 };
 
+#define BNXT_MAX_QUEUE		8
+#define BNXT_MAX_TXR_PER_NAPI	BNXT_MAX_QUEUE
+
+#define bnxt_for_each_napi_tx(iter, bnapi, txr)		\
+	for (iter = 0, txr = (bnapi)->tx_ring[0]; txr;	\
+	     txr = (iter < BNXT_MAX_TXR_PER_NAPI - 1) ?	\
+	     (bnapi)->tx_ring[++iter] : NULL)
+
 struct bnxt_napi {
 	struct napi_struct	napi;
 	struct bnxt		*bp;
@@ -1022,11 +1175,10 @@ struct bnxt_napi {
 	int			index;
 	struct bnxt_cp_ring_info	cp_ring;
 	struct bnxt_rx_ring_info	*rx_ring;
-	struct bnxt_tx_ring_info	*tx_ring;
+	struct bnxt_tx_ring_info	*tx_ring[BNXT_MAX_TXR_PER_NAPI];
 
 	void			(*tx_int)(struct bnxt *, struct bnxt_napi *,
 					  int budget);
-	int			tx_pkts;
 	u8			events;
 	u8			tx_fault:1;
 
@@ -1067,7 +1219,7 @@ struct bnxt_vnic_info {
 	u16		fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC];
 	u16		fw_l2_ctx_id;
 #define BNXT_MAX_UC_ADDRS	4
-	__le64		fw_l2_filter_id[BNXT_MAX_UC_ADDRS];
+	struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS];
 				/* index 0 always dev_addr */
 	u16		uc_filter_count;
 	u8		*uc_list;
@@ -1180,19 +1332,71 @@ struct bnxt_pf_info {
 	struct bnxt_vf_info	*vf;
 };
 
-struct bnxt_ntuple_filter {
+struct bnxt_filter_base {
 	struct hlist_node	hash;
-	u8			dst_mac_addr[ETH_ALEN];
-	u8			src_mac_addr[ETH_ALEN];
-	struct flow_keys	fkeys;
 	__le64			filter_id;
+	u8			type;
+#define BNXT_FLTR_TYPE_NTUPLE	1
+#define BNXT_FLTR_TYPE_L2	2
+	u8			flags;
+#define BNXT_ACT_DROP		1
+#define BNXT_ACT_RING_DST	2
+#define BNXT_ACT_FUNC_DST	4
+#define BNXT_ACT_NO_AGING	8
 	u16			sw_id;
-	u8			l2_fltr_idx;
 	u16			rxq;
-	u32			flow_id;
+	u16			fw_vnic_id;
+	u16			vf_idx;
 	unsigned long		state;
 #define BNXT_FLTR_VALID		0
-#define BNXT_FLTR_UPDATE	1
+#define BNXT_FLTR_INSERTED	1
+#define BNXT_FLTR_FW_DELETED	2
+
+	struct rcu_head         rcu;
+};
+
+struct bnxt_ntuple_filter {
+	struct bnxt_filter_base	base;
+	struct flow_keys	fkeys;
+	struct bnxt_l2_filter	*l2_fltr;
+	u32			ntuple_flags;
+#define BNXT_NTUPLE_MATCH_SRC_IP	1
+#define BNXT_NTUPLE_MATCH_DST_IP	2
+#define BNXT_NTUPLE_MATCH_SRC_PORT	4
+#define BNXT_NTUPLE_MATCH_DST_PORT	8
+#define BNXT_NTUPLE_MATCH_ALL		(BNXT_NTUPLE_MATCH_SRC_IP |	\
+					 BNXT_NTUPLE_MATCH_DST_IP |	\
+					 BNXT_NTUPLE_MATCH_SRC_PORT |	\
+					 BNXT_NTUPLE_MATCH_DST_PORT)
+	u32			flow_id;
+};
+
+struct bnxt_l2_key {
+	union {
+		struct {
+			u8	dst_mac_addr[ETH_ALEN];
+			u16	vlan;
+		};
+		u32	filter_key;
+	};
+};
+
+struct bnxt_ipv4_tuple {
+	struct flow_dissector_key_ipv4_addrs v4addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+struct bnxt_ipv6_tuple {
+	struct flow_dissector_key_ipv6_addrs v6addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+#define BNXT_L2_KEY_SIZE	(sizeof(struct bnxt_l2_key) / 4)
+
+struct bnxt_l2_filter {
+	struct bnxt_filter_base	base;
+	struct bnxt_l2_key	l2_key;
+	atomic_t		refcnt;
 };
 
 struct bnxt_link_info {
@@ -1214,6 +1418,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_STATE_DOWN	1
 #define BNXT_LINK_STATE_UP	2
 #define BNXT_LINK_IS_UP(bp)	((bp)->link_info.link_state == BNXT_LINK_STATE_UP)
+	u8			active_lanes;
 	u8			duplex;
 #define BNXT_LINK_DUPLEX_HALF	PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF
 #define BNXT_LINK_DUPLEX_FULL	PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
@@ -1248,8 +1453,11 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_50GB	PORT_PHY_QCFG_RESP_LINK_SPEED_50GB
 #define BNXT_LINK_SPEED_100GB	PORT_PHY_QCFG_RESP_LINK_SPEED_100GB
 #define BNXT_LINK_SPEED_200GB	PORT_PHY_QCFG_RESP_LINK_SPEED_200GB
+#define BNXT_LINK_SPEED_400GB	PORT_PHY_QCFG_RESP_LINK_SPEED_400GB
 	u16			support_speeds;
 	u16			support_pam4_speeds;
+	u16			support_speeds2;
+
 	u16			auto_link_speeds;	/* fw adv setting */
 #define BNXT_LINK_SPEED_MSK_100MB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB
 #define BNXT_LINK_SPEED_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB
@@ -1265,12 +1473,52 @@ struct bnxt_link_info {
 #define BNXT_LINK_PAM4_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G
 #define BNXT_LINK_PAM4_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G
 #define BNXT_LINK_PAM4_SPEED_MSK_200GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G
+	u16			auto_link_speeds2;
+#define BNXT_LINK_SPEEDS2_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB
+#define BNXT_LINK_SPEEDS2_MSK_10GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB
+#define BNXT_LINK_SPEEDS2_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB
+#define BNXT_LINK_SPEEDS2_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB
+#define BNXT_LINK_SPEEDS2_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB
+#define BNXT_LINK_SPEEDS2_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB
+#define BNXT_LINK_SPEEDS2_MSK_50GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_100GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_200GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_400GB_PAM4	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56
+#define BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112
+#define BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112
+#define BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112	\
+	PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112
+
 	u16			support_auto_speeds;
 	u16			support_pam4_auto_speeds;
+	u16			support_auto_speeds2;
+
 	u16			lp_auto_link_speeds;
 	u16			lp_auto_pam4_link_speeds;
 	u16			force_link_speed;
 	u16			force_pam4_link_speed;
+	u16			force_link_speed2;
+#define BNXT_LINK_SPEED_50GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56
+#define BNXT_LINK_SPEED_100GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56
+#define BNXT_LINK_SPEED_200GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56
+#define BNXT_LINK_SPEED_400GB_PAM4	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56
+#define BNXT_LINK_SPEED_100GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112
+#define BNXT_LINK_SPEED_200GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112
+#define BNXT_LINK_SPEED_400GB_PAM4_112	\
+	PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112
+
 	u32			preemphasis;
 	u8			module_status;
 	u8			active_fec_sig_mode;
@@ -1301,6 +1549,7 @@ struct bnxt_link_info {
 	u8			req_signal_mode;
 #define BNXT_SIG_MODE_NRZ	PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ
 #define BNXT_SIG_MODE_PAM4	PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
+#define BNXT_SIG_MODE_PAM4_112	PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
 #define BNXT_SIG_MODE_MAX	(PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST + 1)
 	u8			req_duplex;
 	u8			req_flow_ctrl;
@@ -1361,8 +1610,6 @@ struct bnxt_link_info {
 	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE |		\
 	 BNXT_FEC_RS_OFF(link_info))
 
-#define BNXT_MAX_QUEUE	8
-
 struct bnxt_queue_info {
 	u8	queue_id;
 	u8	queue_profile;
@@ -1391,7 +1638,7 @@ struct bnxt_test_info {
 };
 
 #define CHIMP_REG_VIEW_ADDR				\
-	((bp->flags & BNXT_FLAG_CHIP_P5) ? 0x80000000 : 0xb1000000)
+	((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) ? 0x80000000 : 0xb1000000)
 
 #define BNXT_GRCPF_REG_CHIMP_COMM		0x0
 #define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
@@ -1515,53 +1762,73 @@ do {									\
 		attr = FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K;	\
 } while (0)
 
+struct bnxt_ctx_mem_type {
+	u16	type;
+	u16	entry_size;
+	u32	flags;
+#define BNXT_CTX_MEM_TYPE_VALID FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID
+	u32	instance_bmap;
+	u8	init_value;
+	u8	entry_multiple;
+	u16	init_offset;
+#define	BNXT_CTX_INIT_INVALID_OFFSET	0xffff
+	u32	max_entries;
+	u32	min_entries;
+	u8	last:1;
+	u8	split_entry_cnt;
+#define BNXT_MAX_SPLIT_ENTRY	4
+	union {
+		struct {
+			u32	qp_l2_entries;
+			u32	qp_qp1_entries;
+			u32	qp_fast_qpmd_entries;
+		};
+		u32	srq_l2_entries;
+		u32	cq_l2_entries;
+		u32	vnic_entries;
+		struct {
+			u32	mrav_av_entries;
+			u32	mrav_num_entries_units;
+		};
+		u32	split[BNXT_MAX_SPLIT_ENTRY];
+	};
+	struct bnxt_ctx_pg_info	*pg_info;
+};
+
+#define BNXT_CTX_MRAV_AV_SPLIT_ENTRY	0
+
+#define BNXT_CTX_QP	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP
+#define BNXT_CTX_SRQ	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ
+#define BNXT_CTX_CQ	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ
+#define BNXT_CTX_VNIC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC
+#define BNXT_CTX_STAT	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT
+#define BNXT_CTX_STQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING
+#define BNXT_CTX_FTQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING
+#define BNXT_CTX_MRAV	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV
+#define BNXT_CTX_TIM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM
+#define BNXT_CTX_TKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC
+#define BNXT_CTX_RKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC
+#define BNXT_CTX_MTQM	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING
+#define BNXT_CTX_SQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW
+#define BNXT_CTX_RQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW
+#define BNXT_CTX_SRQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW
+#define BNXT_CTX_CQDBS	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW
+#define BNXT_CTX_QTKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_TKC
+#define BNXT_CTX_QRKC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_RKC
+#define BNXT_CTX_TBLSC	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE
+#define BNXT_CTX_XPAR	FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION
+
+#define BNXT_CTX_MAX	(BNXT_CTX_TIM + 1)
+#define BNXT_CTX_L2_MAX	(BNXT_CTX_FTQM + 1)
+#define BNXT_CTX_V2_MAX	(BNXT_CTX_XPAR + 1)
+#define BNXT_CTX_INV	((u16)-1)
+
 struct bnxt_ctx_mem_info {
-	u32	qp_max_entries;
-	u16	qp_min_qp1_entries;
-	u16	qp_max_l2_entries;
-	u16	qp_entry_size;
-	u16	srq_max_l2_entries;
-	u32	srq_max_entries;
-	u16	srq_entry_size;
-	u16	cq_max_l2_entries;
-	u32	cq_max_entries;
-	u16	cq_entry_size;
-	u16	vnic_max_vnic_entries;
-	u16	vnic_max_ring_table_entries;
-	u16	vnic_entry_size;
-	u32	stat_max_entries;
-	u16	stat_entry_size;
-	u16	tqm_entry_size;
-	u32	tqm_min_entries_per_ring;
-	u32	tqm_max_entries_per_ring;
-	u32	mrav_max_entries;
-	u16	mrav_entry_size;
-	u16	tim_entry_size;
-	u32	tim_max_entries;
-	u16	mrav_num_entries_units;
-	u8	tqm_entries_multiple;
 	u8	tqm_fp_rings_count;
 
 	u32	flags;
 	#define BNXT_CTX_FLAG_INITED	0x01
-
-	struct bnxt_ctx_pg_info qp_mem;
-	struct bnxt_ctx_pg_info srq_mem;
-	struct bnxt_ctx_pg_info cq_mem;
-	struct bnxt_ctx_pg_info vnic_mem;
-	struct bnxt_ctx_pg_info stat_mem;
-	struct bnxt_ctx_pg_info mrav_mem;
-	struct bnxt_ctx_pg_info tim_mem;
-	struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TQM_RINGS];
-
-#define BNXT_CTX_MEM_INIT_QP	0
-#define BNXT_CTX_MEM_INIT_SRQ	1
-#define BNXT_CTX_MEM_INIT_CQ	2
-#define BNXT_CTX_MEM_INIT_VNIC	3
-#define BNXT_CTX_MEM_INIT_STAT	4
-#define BNXT_CTX_MEM_INIT_MRAV	5
-#define BNXT_CTX_MEM_INIT_MAX	6
-	struct bnxt_mem_init	mem_init[BNXT_CTX_MEM_INIT_MAX];
+	struct bnxt_ctx_mem_type	ctx_arr[BNXT_CTX_V2_MAX];
 };
 
 enum bnxt_health_severity {
@@ -1697,6 +1964,10 @@ enum board_idx {
 	BCM57508_NPAR,
 	BCM57504_NPAR,
 	BCM57502_NPAR,
+	BCM57608,
+	BCM57604,
+	BCM57602,
+	BCM57601,
 	BCM58802,
 	BCM58804,
 	BCM58808,
@@ -1744,14 +2015,14 @@ struct bnxt {
 #define CHIP_NUM_57504		0x1751
 #define CHIP_NUM_57502		0x1752
 
+#define CHIP_NUM_57608		0x1760
+
 #define CHIP_NUM_58802		0xd802
 #define CHIP_NUM_58804		0xd804
 #define CHIP_NUM_58808		0xd808
 
 	u8			chip_rev;
 
-#define CHIP_NUM_58818		0xd818
-
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
 	((chip_num) >= CHIP_NUM_57301 &&	\
 	 (chip_num) <= CHIP_NUM_57304)
@@ -1801,7 +2072,7 @@ struct bnxt {
 	atomic_t		intr_sem;
 
 	u32			flags;
-	#define BNXT_FLAG_CHIP_P5	0x1
+	#define BNXT_FLAG_CHIP_P5_PLUS	0x1
 	#define BNXT_FLAG_VF		0x2
 	#define BNXT_FLAG_LRO		0x4
 #ifdef CONFIG_INET
@@ -1820,8 +2091,6 @@ struct bnxt {
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
-	#define BNXT_FLAG_UDP_RSS_CAP	0x800
-	#define BNXT_FLAG_NEW_RSS_CAP	0x2000
 	#define BNXT_FLAG_WOL_CAP	0x4000
 	#define BNXT_FLAG_ROCEV1_CAP	0x8000
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
@@ -1829,13 +2098,15 @@ struct bnxt {
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
-	#define BNXT_FLAG_CHIP_SR2	0x80000
+	#define BNXT_FLAG_CHIP_P7	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_DSN_VALID	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
+	#define BNXT_FLAG_UDP_GSO_CAP	0x800000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
+	#define BNXT_FLAG_TX_COAL_CMPL	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1855,21 +2126,21 @@ struct bnxt {
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
 #define BNXT_SUPPORTS_TPA(bp)	(!BNXT_CHIP_TYPE_NITRO_A0(bp) &&	\
-				 (!((bp)->flags & BNXT_FLAG_CHIP_P5) ||	\
+				 (!((bp)->flags & BNXT_FLAG_CHIP_P5_PLUS) ||\
 				  (bp)->max_tpa_v2) && !is_kdump_kernel())
 #define BNXT_RX_JUMBO_MODE(bp)	((bp)->flags & BNXT_FLAG_JUMBO)
 
-#define BNXT_CHIP_SR2(bp)			\
-	((bp)->chip_num == CHIP_NUM_58818)
+#define BNXT_CHIP_P7(bp)			\
+	((bp)->chip_num == CHIP_NUM_57608)
 
-#define BNXT_CHIP_P5_THOR(bp)			\
+#define BNXT_CHIP_P5(bp)			\
 	((bp)->chip_num == CHIP_NUM_57508 ||	\
 	 (bp)->chip_num == CHIP_NUM_57504 ||	\
 	 (bp)->chip_num == CHIP_NUM_57502)
 
 /* Chip class phase 5 */
-#define BNXT_CHIP_P5(bp)			\
-	(BNXT_CHIP_P5_THOR(bp) || BNXT_CHIP_SR2(bp))
+#define BNXT_CHIP_P5_PLUS(bp)			\
+	(BNXT_CHIP_P5(bp) || BNXT_CHIP_P7(bp))
 
 /* Chip class phase 4.x */
 #define BNXT_CHIP_P4(bp)			\
@@ -1880,7 +2151,7 @@ struct bnxt {
 	  !BNXT_CHIP_TYPE_NITRO_A0(bp)))
 
 #define BNXT_CHIP_P4_PLUS(bp)			\
-	(BNXT_CHIP_P4(bp) || BNXT_CHIP_P5(bp))
+	(BNXT_CHIP_P4(bp) || BNXT_CHIP_P5_PLUS(bp))
 
 	struct bnxt_aux_priv	*aux_priv;
 	struct bnxt_en_dev	*edev;
@@ -1941,6 +2212,11 @@ struct bnxt {
 	u16			rss_indir_tbl_entries;
 	u32			rss_hash_cfg;
 	u32			rss_hash_delta;
+	u32			rss_cap;
+#define BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA	BIT(0)
+#define BNXT_RSS_CAP_UDP_RSS_CAP		BIT(1)
+#define BNXT_RSS_CAP_NEW_RSS_CAP		BIT(2)
+#define BNXT_RSS_CAP_RSS_TCAM			BIT(3)
 
 	u16			max_mtu;
 	u8			max_tc;
@@ -1949,6 +2225,7 @@ struct bnxt {
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			num_tc;
 
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
@@ -2006,7 +2283,6 @@ struct bnxt {
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2	BIT_ULL(16)
 	#define BNXT_FW_CAP_PCIE_STATS_SUPPORTED	BIT_ULL(17)
 	#define BNXT_FW_CAP_EXT_STATS_SUPPORTED		BIT_ULL(18)
-	#define BNXT_FW_CAP_RSS_HASH_TYPE_DELTA		BIT_ULL(19)
 	#define BNXT_FW_CAP_ERR_RECOVER_RELOAD		BIT_ULL(20)
 	#define BNXT_FW_CAP_HOT_RESET			BIT_ULL(21)
 	#define BNXT_FW_CAP_PTP_RTC			BIT_ULL(22)
@@ -2023,6 +2299,8 @@ struct bnxt {
 	#define BNXT_FW_CAP_THRESHOLD_TEMP_SUPPORTED	BIT_ULL(33)
 	#define BNXT_FW_CAP_DFLT_VLAN_TPID_PCP		BIT_ULL(34)
 	#define BNXT_FW_CAP_PRE_RESV_VNICS		BIT_ULL(35)
+	#define BNXT_FW_CAP_BACKING_STORE_V2		BIT_ULL(36)
+	#define BNXT_FW_CAP_VNIC_TUNNEL_TPA		BIT_ULL(37)
 
 	u32			fw_dbg_cap;
 
@@ -2067,8 +2345,10 @@ struct bnxt {
 
 	u16			vxlan_fw_dst_port_id;
 	u16			nge_fw_dst_port_id;
+	u16			vxlan_gpe_fw_dst_port_id;
 	__be16			vxlan_port;
 	__be16			nge_port;
+	__be16			vxlan_gpe_port;
 	u8			port_partition_type;
 	u8			port_count;
 	u16			br_mode;
@@ -2136,9 +2416,11 @@ struct bnxt {
 	/* ensure atomic 64-bit doorbell writes on 32-bit systems. */
 	spinlock_t		db_lock;
 #endif
+	int			db_offset;	/* db_offset within db_size */
 	int			db_size;
 
 #define BNXT_NTP_FLTR_MAX_FLTR	4096
+#define BNXT_MAX_FLTR		(BNXT_NTP_FLTR_MAX_FLTR + BNXT_L2_FLTR_MAX_FLTR)
 #define BNXT_NTP_FLTR_HASH_SIZE	512
 #define BNXT_NTP_FLTR_HASH_MASK	(BNXT_NTP_FLTR_HASH_SIZE - 1)
 	struct hlist_head	ntp_fltr_hash_tbl[BNXT_NTP_FLTR_HASH_SIZE];
@@ -2147,6 +2429,14 @@ struct bnxt {
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+#define BNXT_L2_FLTR_MAX_FLTR	1024
+#define BNXT_L2_FLTR_HASH_SIZE	32
+#define BNXT_L2_FLTR_HASH_MASK	(BNXT_L2_FLTR_HASH_SIZE - 1)
+	struct hlist_head	l2_fltr_hash_tbl[BNXT_L2_FLTR_HASH_SIZE];
+
+	u32			hash_seed;
+	u64			toeplitz_prefix;
+
 	/* To protect link related settings during link changes and
 	 * ethtool settings changes.
 	 */
@@ -2169,6 +2459,7 @@ struct bnxt {
 #define BNXT_PHY_FL_NO_PAUSE		(PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED << 8)
 #define BNXT_PHY_FL_NO_PFC		(PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED << 8)
 #define BNXT_PHY_FL_BANK_SEL		(PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED << 8)
+#define BNXT_PHY_FL_SPEEDS2		(PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED << 8)
 
 	u8			num_tests;
 	struct bnxt_test_info	*test_info;
@@ -2212,15 +2503,15 @@ struct bnxt {
 #define BNXT_NUM_TX_RING_STATS			8
 #define BNXT_NUM_TPA_RING_STATS			4
 #define BNXT_NUM_TPA_RING_STATS_P5		5
-#define BNXT_NUM_TPA_RING_STATS_P5_SR2		6
+#define BNXT_NUM_TPA_RING_STATS_P7		6
 
 #define BNXT_RING_STATS_SIZE_P5					\
 	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
 	  BNXT_NUM_TPA_RING_STATS_P5) * 8)
 
-#define BNXT_RING_STATS_SIZE_P5_SR2				\
+#define BNXT_RING_STATS_SIZE_P7					\
 	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
-	  BNXT_NUM_TPA_RING_STATS_P5_SR2) * 8)
+	  BNXT_NUM_TPA_RING_STATS_P7) * 8)
 
 #define BNXT_GET_RING_STATS64(sw, counter)		\
 	(*((sw) + offsetof(struct ctx_hw_stats, counter) / 8))
@@ -2303,10 +2594,11 @@ static inline void bnxt_writeq_relaxed(struct bnxt *bp, u64 val,
 static inline void bnxt_db_write_relaxed(struct bnxt *bp,
 					 struct bnxt_db_info *db, u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_writeq_relaxed(bp, db->db_key64 | idx, db->doorbell);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		bnxt_writeq_relaxed(bp, db->db_key64 | DB_RING_IDX(db, idx),
+				    db->doorbell);
 	} else {
-		u32 db_val = db->db_key32 | idx;
+		u32 db_val = db->db_key32 | DB_RING_IDX(db, idx);
 
 		writel_relaxed(db_val, db->doorbell);
 		if (bp->flags & BNXT_FLAG_DOUBLE_DB)
@@ -2318,10 +2610,11 @@ static inline void bnxt_db_write_relaxed(struct bnxt *bp,
 static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 				 u32 idx)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		bnxt_writeq(bp, db->db_key64 | idx, db->doorbell);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		bnxt_writeq(bp, db->db_key64 | DB_RING_IDX(db, idx),
+			    db->doorbell);
 	} else {
-		u32 db_val = db->db_key32 | idx;
+		u32 db_val = db->db_key32 | DB_RING_IDX(db, idx);
 
 		writel(db_val, db->doorbell);
 		if (bp->flags & BNXT_FLAG_DOUBLE_DB)
@@ -2351,12 +2644,21 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
 			    int bmap_size, bool async_only);
 int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp);
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+				     struct bnxt_ntuple_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+				      struct bnxt_ntuple_filter *fltr);
+void bnxt_fill_ipv6_mask(__be32 mask[4]);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
 int bnxt_nq_rings_in_use(struct bnxt *bp);
 int bnxt_hwrm_set_coal(struct bnxt *);
 void bnxt_free_ctx_mem(struct bnxt *bp);
+int bnxt_num_tx_to_cp(struct bnxt *bp, int tx);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
@@ -2366,7 +2668,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  int idx);
+			  u16 curr);
 void bnxt_report_link(struct bnxt *bp);
 int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
@@ -2393,6 +2695,13 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 int bnxt_fw_init_one(struct bnxt *bp);
 bool bnxt_hwrm_reset_permitted(struct bnxt *bp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
+struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx);
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb);
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx);
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 int bnxt_restore_pf_fw_resources(struct bnxt *bp);
 int bnxt_get_port_parent_id(struct net_device *dev,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 63e0670383..0dbb880a7a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -228,7 +228,7 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
 		}
 	}
 	if (bp->ieee_ets) {
-		int tc = netdev_get_num_tc(bp->dev);
+		int tc = bp->num_tc;
 
 		if (!tc)
 			tc = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 89809f1b12..ae4529c043 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -462,8 +462,6 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		}
 		bnxt_cancel_reservations(bp, false);
 		bnxt_free_ctx_mem(bp);
-		kfree(bp->ctx);
-		bp->ctx = NULL;
 		break;
 	}
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: {
@@ -734,7 +732,7 @@ static int bnxt_hwrm_get_nvm_cfg_ver(struct bnxt *bp, u32 *nvm_cfg_ver)
 	}
 
 	/* earlier devices present as an array of raw bytes */
-	if (!BNXT_CHIP_P5(bp)) {
+	if (!BNXT_CHIP_P5_PLUS(bp)) {
 		dim = 0;
 		i = 0;
 		bits *= 3;  /* array of 3 version components */
@@ -754,7 +752,7 @@ static int bnxt_hwrm_get_nvm_cfg_ver(struct bnxt *bp, u32 *nvm_cfg_ver)
 			goto exit;
 		bnxt_copy_from_nvm_data(&ver, data, bits, bytes);
 
-		if (BNXT_CHIP_P5(bp)) {
+		if (BNXT_CHIP_P5_PLUS(bp)) {
 			*nvm_cfg_ver <<= 8;
 			*nvm_cfg_ver |= ver.vu8;
 		} else {
@@ -774,7 +772,7 @@ static int bnxt_dl_info_put(struct bnxt *bp, struct devlink_info_req *req,
 	if (!strlen(buf))
 		return 0;
 
-	if ((bp->flags & BNXT_FLAG_CHIP_P5) &&
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
 	    (!strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_NCSI) ||
 	     !strcmp(key, DEVLINK_INFO_VERSION_GENERIC_FW_ROCE)))
 		return 0;
@@ -1000,7 +998,7 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (rc)
 		return rc;
 
-	if (BNXT_CHIP_P5(bp)) {
+	if (BNXT_CHIP_P5_PLUS(bp)) {
 		rc = bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_SRT_PATCH);
 		if (rc)
 			return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 5f67a7f94e..dc4ca706b0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -460,6 +460,7 @@ static const struct {
 	BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES,
 	BNXT_RX_STATS_EXT_ENTRY(rx_fec_corrected_blocks),
 	BNXT_RX_STATS_EXT_ENTRY(rx_fec_uncorrectable_blocks),
+	BNXT_RX_STATS_EXT_ENTRY(rx_filter_miss),
 };
 
 static const struct {
@@ -510,9 +511,9 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 {
 	if (BNXT_SUPPORTS_TPA(bp)) {
 		if (bp->max_tpa_v2) {
-			if (BNXT_CHIP_P5_THOR(bp))
+			if (BNXT_CHIP_P5(bp))
 				return BNXT_NUM_TPA_RING_STATS_P5;
-			return BNXT_NUM_TPA_RING_STATS_P5_SR2;
+			return BNXT_NUM_TPA_RING_STATS_P7;
 		}
 		return BNXT_NUM_TPA_RING_STATS;
 	}
@@ -527,7 +528,8 @@ static int bnxt_get_num_ring_stats(struct bnxt *bp)
 	     bnxt_get_num_tpa_ring_stats(bp);
 	tx = NUM_RING_TX_HW_STATS;
 	cmn = NUM_RING_CMN_SW_STATS;
-	return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings +
+	return rx * bp->rx_nr_rings +
+	       tx * (bp->tx_nr_rings_xdp + bp->tx_nr_rings_per_tc) +
 	       cmn * bp->cp_nr_rings;
 }
 
@@ -882,7 +884,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	tx_grps = max(tcs, 1);
 	if (bp->tx_nr_rings_xdp)
 		tx_grps++;
@@ -922,6 +924,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	bool sh = false;
 	int tx_xdp = 0;
 	int rc = 0;
+	int tx_cp;
 
 	if (channel->other_count)
 		return -EINVAL;
@@ -941,7 +944,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (channel->combined_count)
 		sh = true;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 
 	req_tx_rings = sh ? channel->combined_count : channel->tx_count;
 	req_rx_rings = sh ? channel->combined_count : channel->rx_count;
@@ -988,8 +991,9 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (tcs > 1)
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs + tx_xdp;
 
-	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
-			       bp->tx_nr_rings + bp->rx_nr_rings;
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
 
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);
@@ -1007,29 +1011,60 @@ static int bnxt_set_channels(struct net_device *dev,
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
-static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
-			    u32 *rule_locs)
+static u32 bnxt_get_all_fltr_ids_rcu(struct bnxt *bp, struct hlist_head tbl[],
+				     int tbl_size, u32 *ids, u32 start,
+				     u32 id_cnt)
 {
-	int i, j = 0;
+	int i, j = start;
 
-	cmd->data = bp->ntp_fltr_count;
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
+	if (j >= id_cnt)
+		return j;
+	for (i = 0; i < tbl_size; i++) {
 		struct hlist_head *head;
-		struct bnxt_ntuple_filter *fltr;
+		struct bnxt_filter_base *fltr;
 
-		head = &bp->ntp_fltr_hash_tbl[i];
-		rcu_read_lock();
+		head = &tbl[i];
 		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (j == cmd->rule_cnt)
-				break;
-			rule_locs[j++] = fltr->sw_id;
+			if (!fltr->flags ||
+			    test_bit(BNXT_FLTR_FW_DELETED, &fltr->state))
+				continue;
+			ids[j++] = fltr->sw_id;
+			if (j == id_cnt)
+				return j;
+		}
+	}
+	return j;
+}
+
+static struct bnxt_filter_base *bnxt_get_one_fltr_rcu(struct bnxt *bp,
+						      struct hlist_head tbl[],
+						      int tbl_size, u32 id)
+{
+	int i;
+
+	for (i = 0; i < tbl_size; i++) {
+		struct hlist_head *head;
+		struct bnxt_filter_base *fltr;
+
+		head = &tbl[i];
+		hlist_for_each_entry_rcu(fltr, head, hash) {
+			if (fltr->flags && fltr->sw_id == id)
+				return fltr;
 		}
-		rcu_read_unlock();
-		if (j == cmd->rule_cnt)
-			break;
 	}
-	cmd->rule_cnt = j;
+	return NULL;
+}
+
+static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
+			    u32 *rule_locs)
+{
+	cmd->data = bp->ntp_fltr_count;
+	rcu_read_lock();
+	cmd->rule_cnt = bnxt_get_all_fltr_ids_rcu(bp, bp->ntp_fltr_hash_tbl,
+						  BNXT_NTP_FLTR_HASH_SIZE,
+						  rule_locs, 0, cmd->rule_cnt);
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -1037,27 +1072,24 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fs =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct bnxt_filter_base *fltr_base;
 	struct bnxt_ntuple_filter *fltr;
 	struct flow_keys *fkeys;
-	int i, rc = -EINVAL;
+	int rc = -EINVAL;
 
 	if (fs->location >= BNXT_NTP_FLTR_MAX_FLTR)
 		return rc;
 
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
-		struct hlist_head *head;
-
-		head = &bp->ntp_fltr_hash_tbl[i];
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (fltr->sw_id == fs->location)
-				goto fltr_found;
-		}
+	rcu_read_lock();
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (!fltr_base) {
 		rcu_read_unlock();
+		return rc;
 	}
-	return rc;
+	fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
 
-fltr_found:
 	fkeys = &fltr->fkeys;
 	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
@@ -1067,20 +1099,23 @@ fltr_found:
 		else
 			goto fltr_err;
 
-		fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
-		fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
-
-		fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
-		fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
-
-		fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
-		fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
-
-		fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
-		fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
+			fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
+			fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+			fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
+			fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+			fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
+			fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		}
 	} else {
-		int i;
-
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
 			fs->flow_type = TCP_V6_FLOW;
 		else if (fkeys->basic.ip_proto == IPPROTO_UDP)
@@ -1088,22 +1123,27 @@ fltr_found:
 		else
 			goto fltr_err;
 
-		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
-			fkeys->addrs.v6addrs.src;
-		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
-			fkeys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			fs->m_u.tcp_ip6_spec.ip6src[i] = cpu_to_be32(~0);
-			fs->m_u.tcp_ip6_spec.ip6dst[i] = cpu_to_be32(~0);
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
+			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
+				fkeys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6src);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
+			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
+				fkeys->addrs.v6addrs.dst;
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6dst);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
+			fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
+			fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
+			fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
+			fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
 		}
-		fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
-		fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
-
-		fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
-		fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
 	}
 
-	fs->ring_cookie = fltr->rxq;
+	fs->ring_cookie = fltr->base.rxq;
 	rc = 0;
 
 fltr_err:
@@ -1111,7 +1151,221 @@ fltr_err:
 
 	return rc;
 }
-#endif
+
+#define IPV4_ALL_MASK		((__force __be32)~0)
+#define L4_PORT_ALL_MASK	((__force __be16)~0)
+
+static bool ipv6_mask_is_full(__be32 mask[4])
+{
+	return (mask[0] & mask[1] & mask[2] & mask[3]) == IPV4_ALL_MASK;
+}
+
+static bool ipv6_mask_is_zero(__be32 mask[4])
+{
+	return !(mask[0] | mask[1] | mask[2] | mask[3]);
+}
+
+static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
+				    struct ethtool_rx_flow_spec *fs)
+{
+	u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	struct bnxt_ntuple_filter *new_fltr, *fltr;
+	struct bnxt_l2_filter *l2_fltr;
+	u32 flow_type = fs->flow_type;
+	struct flow_keys *fkeys;
+	u32 idx;
+	int rc;
+
+	if (!bp->vnic_info)
+		return -EAGAIN;
+
+	if ((flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
+		return -EOPNOTSUPP;
+
+	new_fltr = kzalloc(sizeof(*new_fltr), GFP_KERNEL);
+	if (!new_fltr)
+		return -ENOMEM;
+
+	l2_fltr = bp->vnic_info[0].l2_filters[0];
+	atomic_inc(&l2_fltr->refcnt);
+	new_fltr->l2_fltr = l2_fltr;
+	fkeys = &new_fltr->fkeys;
+
+	rc = -EOPNOTSUPP;
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW: {
+		struct ethtool_tcpip4_spec *ip_spec = &fs->h_u.tcp_ip4_spec;
+		struct ethtool_tcpip4_spec *ip_mask = &fs->m_u.tcp_ip4_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V4_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IP);
+
+		if (ip_mask->ip4src == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.src = ip_spec->ip4src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (ip_mask->ip4src) {
+			goto ntuple_err;
+		}
+		if (ip_mask->ip4dst == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.dst = ip_spec->ip4dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (ip_mask->ip4dst) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW: {
+		struct ethtool_tcpip6_spec *ip_spec = &fs->h_u.tcp_ip6_spec;
+		struct ethtool_tcpip6_spec *ip_mask = &fs->m_u.tcp_ip6_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V6_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IPV6);
+
+		if (ipv6_mask_is_full(ip_mask->ip6src)) {
+			fkeys->addrs.v6addrs.src =
+				*(struct in6_addr *)&ip_spec->ip6src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6src)) {
+			goto ntuple_err;
+		}
+		if (ipv6_mask_is_full(ip_mask->ip6dst)) {
+			fkeys->addrs.v6addrs.dst =
+				*(struct in6_addr *)&ip_spec->ip6dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6dst)) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	default:
+		rc = -EOPNOTSUPP;
+		goto ntuple_err;
+	}
+	if (!new_fltr->ntuple_flags)
+		goto ntuple_err;
+
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, NULL);
+	rcu_read_lock();
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
+		rcu_read_unlock();
+		rc = -EEXIST;
+		goto ntuple_err;
+	}
+	rcu_read_unlock();
+
+	new_fltr->base.rxq = ring;
+	new_fltr->base.flags = BNXT_ACT_NO_AGING;
+	__set_bit(BNXT_FLTR_VALID, &new_fltr->base.state);
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
+		rc = bnxt_hwrm_cfa_ntuple_filter_alloc(bp, new_fltr);
+		if (rc) {
+			bnxt_del_ntp_filter(bp, new_fltr);
+			return rc;
+		}
+		fs->location = new_fltr->base.sw_id;
+		return 0;
+	}
+
+ntuple_err:
+	atomic_dec(&l2_fltr->refcnt);
+	kfree(new_fltr);
+	return rc;
+}
+
+static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	u32 ring, flow_type;
+	int rc;
+	u8 vf;
+
+	if (!netif_running(bp->dev))
+		return -EAGAIN;
+	if (!(bp->flags & BNXT_FLAG_RFS))
+		return -EPERM;
+	if (fs->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+
+	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	if (BNXT_VF(bp) && vf)
+		return -EINVAL;
+	if (BNXT_PF(bp) && vf > bp->pf.active_vfs)
+		return -EINVAL;
+	if (!vf && ring >= bp->rx_nr_rings)
+		return -EINVAL;
+
+	flow_type = fs->flow_type;
+	if (flow_type & (FLOW_MAC_EXT | FLOW_RSS))
+		return -EINVAL;
+	flow_type &= ~FLOW_EXT;
+	if (flow_type == ETHER_FLOW)
+		rc = -EOPNOTSUPP;
+	else
+		rc = bnxt_add_ntuple_cls_rule(bp, fs);
+	return rc;
+}
+
+static int bnxt_srxclsrldel(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	struct bnxt_filter_base *fltr_base;
+	struct bnxt_ntuple_filter *fltr;
+
+	rcu_read_lock();
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (!fltr_base) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
+	if (!(fltr->base.flags & BNXT_ACT_NO_AGING)) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	rcu_read_unlock();
+	bnxt_hwrm_cfa_ntuple_filter_free(bp, fltr);
+	bnxt_del_ntp_filter(bp, fltr);
+	return 0;
+}
 
 static u64 get_ethtool_ipv4_rss(struct bnxt *bp)
 {
@@ -1194,7 +1448,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (tuple == 4)
 			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
 	} else if (cmd->flow_type == UDP_V4_FLOW) {
-		if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+		if (tuple == 4 && !(bp->rss_cap & BNXT_RSS_CAP_UDP_RSS_CAP))
 			return -EINVAL;
 		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
 		if (tuple == 4)
@@ -1204,7 +1458,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		if (tuple == 4)
 			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
 	} else if (cmd->flow_type == UDP_V6_FLOW) {
-		if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+		if (tuple == 4 && !(bp->rss_cap & BNXT_RSS_CAP_UDP_RSS_CAP))
 			return -EINVAL;
 		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
 		if (tuple == 4)
@@ -1244,7 +1498,7 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	if (bp->rss_hash_cfg == rss_hash_cfg)
 		return 0;
 
-	if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA)
+	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
 		bp->rss_hash_delta = bp->rss_hash_cfg ^ rss_hash_cfg;
 	bp->rss_hash_cfg = rss_hash_cfg;
 	if (netif_running(bp->dev)) {
@@ -1261,14 +1515,13 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int rc = 0;
 
 	switch (cmd->cmd) {
-#ifdef CONFIG_RFS_ACCEL
 	case ETHTOOL_GRXRINGS:
 		cmd->data = bp->rx_nr_rings;
 		break;
 
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = bp->ntp_fltr_count;
-		cmd->data = BNXT_NTP_FLTR_MAX_FLTR;
+		cmd->data = BNXT_NTP_FLTR_MAX_FLTR | RX_CLS_LOC_SPECIAL;
 		break;
 
 	case ETHTOOL_GRXCLSRLALL:
@@ -1278,7 +1531,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRULE:
 		rc = bnxt_grxclsrule(bp, cmd);
 		break;
-#endif
 
 	case ETHTOOL_GRXFH:
 		rc = bnxt_grxfh(bp, cmd);
@@ -1302,6 +1554,14 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 		rc = bnxt_srxfh(bp, cmd);
 		break;
 
+	case ETHTOOL_SRXCLSRLINS:
+		rc = bnxt_srxclsrlins(bp, cmd);
+		break;
+
+	case ETHTOOL_SRXCLSRLDEL:
+		rc = bnxt_srxclsrldel(bp, cmd);
+		break;
+
 	default:
 		rc = -EOPNOTSUPP;
 		break;
@@ -1313,8 +1573,9 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
+		       BNXT_RSS_TABLE_ENTRIES_P5;
 	return HW_HASH_INDEX_SIZE;
 }
 
@@ -1323,49 +1584,49 @@ static u32 bnxt_get_rxfh_key_size(struct net_device *dev)
 	return HW_HASH_KEY_SIZE;
 }
 
-static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int bnxt_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_vnic_info *vnic;
 	u32 i, tbl_size;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (!bp->vnic_info)
 		return 0;
 
 	vnic = &bp->vnic_info[0];
-	if (indir && bp->rss_indir_tbl) {
+	if (rxfh->indir && bp->rss_indir_tbl) {
 		tbl_size = bnxt_get_rxfh_indir_size(dev);
 		for (i = 0; i < tbl_size; i++)
-			indir[i] = bp->rss_indir_tbl[i];
+			rxfh->indir[i] = bp->rss_indir_tbl[i];
 	}
 
-	if (key && vnic->rss_hash_key)
-		memcpy(key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
+	if (rxfh->key && vnic->rss_hash_key)
+		memcpy(rxfh->key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
 
 	return 0;
 }
 
-static int bnxt_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int bnxt_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	if (hfunc && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev);
 
 		for (i = 0; i < tbl_size; i++)
-			bp->rss_indir_tbl[i] = indir[i];
+			bp->rss_indir_tbl[i] = rxfh->indir[i];
 		pad = bp->rss_indir_tbl_entries - tbl_size;
 		if (pad)
 			memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
@@ -1568,6 +1829,22 @@ static const enum bnxt_media_type bnxt_phy_types[] = {
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2] = BNXT_MEDIA_SR,
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2] = BNXT_MEDIA_LR_ER_FR,
 	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4] = BNXT_MEDIA_CR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4] = BNXT_MEDIA_SR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4] = BNXT_MEDIA_LR_ER_FR,
+	[PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4] = BNXT_MEDIA_LR_ER_FR,
 };
 
 static enum bnxt_media_type
@@ -1595,6 +1872,7 @@ enum bnxt_link_speed_indices {
 	BNXT_LINK_SPEED_50GB_IDX,
 	BNXT_LINK_SPEED_100GB_IDX,
 	BNXT_LINK_SPEED_200GB_IDX,
+	BNXT_LINK_SPEED_400GB_IDX,
 	__BNXT_LINK_SPEED_END
 };
 
@@ -1606,9 +1884,21 @@ static enum bnxt_link_speed_indices bnxt_fw_speed_idx(u16 speed)
 	case BNXT_LINK_SPEED_10GB: return BNXT_LINK_SPEED_10GB_IDX;
 	case BNXT_LINK_SPEED_25GB: return BNXT_LINK_SPEED_25GB_IDX;
 	case BNXT_LINK_SPEED_40GB: return BNXT_LINK_SPEED_40GB_IDX;
-	case BNXT_LINK_SPEED_50GB: return BNXT_LINK_SPEED_50GB_IDX;
-	case BNXT_LINK_SPEED_100GB: return BNXT_LINK_SPEED_100GB_IDX;
-	case BNXT_LINK_SPEED_200GB: return BNXT_LINK_SPEED_200GB_IDX;
+	case BNXT_LINK_SPEED_50GB:
+	case BNXT_LINK_SPEED_50GB_PAM4:
+		return BNXT_LINK_SPEED_50GB_IDX;
+	case BNXT_LINK_SPEED_100GB:
+	case BNXT_LINK_SPEED_100GB_PAM4:
+	case BNXT_LINK_SPEED_100GB_PAM4_112:
+		return BNXT_LINK_SPEED_100GB_IDX;
+	case BNXT_LINK_SPEED_200GB:
+	case BNXT_LINK_SPEED_200GB_PAM4:
+	case BNXT_LINK_SPEED_200GB_PAM4_112:
+		return BNXT_LINK_SPEED_200GB_IDX;
+	case BNXT_LINK_SPEED_400GB:
+	case BNXT_LINK_SPEED_400GB_PAM4:
+	case BNXT_LINK_SPEED_400GB_PAM4_112:
+		return BNXT_LINK_SPEED_400GB_IDX;
 	default: return BNXT_LINK_SPEED_UNKNOWN;
 	}
 }
@@ -1681,6 +1971,12 @@ bnxt_link_modes[__BNXT_LINK_SPEED_END][BNXT_SIG_MODE_MAX][__BNXT_MEDIA_END] = {
 			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
 			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
 		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT,
+		},
 	},
 	[BNXT_LINK_SPEED_200GB_IDX] = {
 		[BNXT_SIG_MODE_PAM4] = {
@@ -1689,6 +1985,26 @@ bnxt_link_modes[__BNXT_LINK_SPEED_END][BNXT_SIG_MODE_MAX][__BNXT_MEDIA_END] = {
 			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
 			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
 		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT,
+		},
+	},
+	[BNXT_LINK_SPEED_400GB_IDX] = {
+		[BNXT_SIG_MODE_PAM4] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT,
+		},
+		[BNXT_SIG_MODE_PAM4_112] = {
+			[BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT,
+			[BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT,
+			[BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT,
+			[BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
+		},
 	},
 };
 
@@ -1753,7 +2069,8 @@ static void bnxt_get_ethtool_modes(struct bnxt_link_info *link_info,
 				 lk_ksettings->link_modes.supported);
 	}
 
-	if (link_info->support_auto_speeds || link_info->support_pam4_auto_speeds)
+	if (link_info->support_auto_speeds || link_info->support_auto_speeds2 ||
+	    link_info->support_pam4_auto_speeds)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 lk_ksettings->link_modes.supported);
 
@@ -1789,22 +2106,60 @@ static const u16 bnxt_pam4_speed_masks[] = {
 	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_50GB,
 	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_100GB,
 	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_200GB,
+	[__BNXT_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */
+};
+
+static const u16 bnxt_nrz_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_1GB_IDX] = BNXT_LINK_SPEEDS2_MSK_1GB,
+	[BNXT_LINK_SPEED_10GB_IDX] = BNXT_LINK_SPEEDS2_MSK_10GB,
+	[BNXT_LINK_SPEED_25GB_IDX] = BNXT_LINK_SPEEDS2_MSK_25GB,
+	[BNXT_LINK_SPEED_40GB_IDX] = BNXT_LINK_SPEEDS2_MSK_40GB,
+	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_SPEEDS2_MSK_50GB,
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB,
+	[__BNXT_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */
+};
+
+static const u16 bnxt_pam4_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_SPEEDS2_MSK_50GB_PAM4,
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB_PAM4,
+	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_SPEEDS2_MSK_200GB_PAM4,
+	[BNXT_LINK_SPEED_400GB_IDX] = BNXT_LINK_SPEEDS2_MSK_400GB_PAM4,
+};
+
+static const u16 bnxt_pam4_112_speeds2_masks[] = {
+	[BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112,
+	[BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112,
+	[BNXT_LINK_SPEED_400GB_IDX] = BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112,
 };
 
 static enum bnxt_link_speed_indices
-bnxt_encoding_speed_idx(u8 sig_mode, u16 speed_msk)
+bnxt_encoding_speed_idx(u8 sig_mode, u16 phy_flags, u16 speed_msk)
 {
 	const u16 *speeds;
 	int idx, len;
 
 	switch (sig_mode) {
 	case BNXT_SIG_MODE_NRZ:
-		speeds = bnxt_nrz_speed_masks;
-		len = ARRAY_SIZE(bnxt_nrz_speed_masks);
+		if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			speeds = bnxt_nrz_speeds2_masks;
+			len = ARRAY_SIZE(bnxt_nrz_speeds2_masks);
+		} else {
+			speeds = bnxt_nrz_speed_masks;
+			len = ARRAY_SIZE(bnxt_nrz_speed_masks);
+		}
 		break;
 	case BNXT_SIG_MODE_PAM4:
-		speeds = bnxt_pam4_speed_masks;
-		len = ARRAY_SIZE(bnxt_pam4_speed_masks);
+		if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+			speeds = bnxt_pam4_speeds2_masks;
+			len = ARRAY_SIZE(bnxt_pam4_speeds2_masks);
+		} else {
+			speeds = bnxt_pam4_speed_masks;
+			len = ARRAY_SIZE(bnxt_pam4_speed_masks);
+		}
+		break;
+	case BNXT_SIG_MODE_PAM4_112:
+		speeds = bnxt_pam4_112_speeds2_masks;
+		len = ARRAY_SIZE(bnxt_pam4_112_speeds2_masks);
 		break;
 	default:
 		return BNXT_LINK_SPEED_UNKNOWN;
@@ -1822,14 +2177,14 @@ bnxt_encoding_speed_idx(u8 sig_mode, u16 speed_msk)
 
 static void
 __bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
-			  u8 sig_mode, unsigned long *et_mask)
+			  u8 sig_mode, u16 phy_flags, unsigned long *et_mask)
 {
 	enum ethtool_link_mode_bit_indices link_mode;
 	enum bnxt_link_speed_indices speed;
 	u8 bit;
 
 	for_each_set_bit(bit, &fw_mask, BNXT_FW_SPEED_MSK_BITS) {
-		speed = bnxt_encoding_speed_idx(sig_mode, 1 << bit);
+		speed = bnxt_encoding_speed_idx(sig_mode, phy_flags, 1 << bit);
 		if (!speed)
 			continue;
 
@@ -1843,16 +2198,83 @@ __bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
 
 static void
 bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media,
-			u8 sig_mode, unsigned long *et_mask)
+			u8 sig_mode, u16 phy_flags, unsigned long *et_mask)
 {
 	if (media) {
-		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask);
+		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags,
+					  et_mask);
 		return;
 	}
 
 	/* list speeds for all media if unknown */
 	for (media = 1; media < __BNXT_MEDIA_END; media++)
-		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask);
+		__bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags,
+					  et_mask);
+}
+
+static void
+bnxt_get_all_ethtool_support_speeds(struct bnxt_link_info *link_info,
+				    enum bnxt_media_type media,
+				    struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 sp_nrz, sp_pam4, sp_pam4_112 = 0;
+	u16 phy_flags = bp->phy_flags;
+
+	if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		sp_nrz = link_info->support_speeds2;
+		sp_pam4 = link_info->support_speeds2;
+		sp_pam4_112 = link_info->support_speeds2;
+	} else {
+		sp_nrz = link_info->support_speeds;
+		sp_pam4 = link_info->support_pam4_speeds;
+	}
+	bnxt_get_ethtool_speeds(sp_nrz, media, BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.supported);
+	bnxt_get_ethtool_speeds(sp_pam4, media, BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.supported);
+	bnxt_get_ethtool_speeds(sp_pam4_112, media, BNXT_SIG_MODE_PAM4_112,
+				phy_flags, lk_ksettings->link_modes.supported);
+}
+
+static void
+bnxt_get_all_ethtool_adv_speeds(struct bnxt_link_info *link_info,
+				enum bnxt_media_type media,
+				struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 sp_nrz, sp_pam4, sp_pam4_112 = 0;
+	u16 phy_flags = bp->phy_flags;
+
+	sp_nrz = link_info->advertising;
+	if (phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		sp_pam4 = link_info->advertising;
+		sp_pam4_112 = link_info->advertising;
+	} else {
+		sp_pam4 = link_info->advertising_pam4;
+	}
+	bnxt_get_ethtool_speeds(sp_nrz, media, BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.advertising);
+	bnxt_get_ethtool_speeds(sp_pam4, media, BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.advertising);
+	bnxt_get_ethtool_speeds(sp_pam4_112, media, BNXT_SIG_MODE_PAM4_112,
+				phy_flags, lk_ksettings->link_modes.advertising);
+}
+
+static void
+bnxt_get_all_ethtool_lp_speeds(struct bnxt_link_info *link_info,
+			       enum bnxt_media_type media,
+			       struct ethtool_link_ksettings *lk_ksettings)
+{
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 phy_flags = bp->phy_flags;
+
+	bnxt_get_ethtool_speeds(link_info->lp_auto_link_speeds, media,
+				BNXT_SIG_MODE_NRZ, phy_flags,
+				lk_ksettings->link_modes.lp_advertising);
+	bnxt_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds, media,
+				BNXT_SIG_MODE_PAM4, phy_flags,
+				lk_ksettings->link_modes.lp_advertising);
 }
 
 static void bnxt_update_speed(u32 *delta, bool installed_media, u16 *speeds,
@@ -1881,22 +2303,42 @@ static void bnxt_update_speed(u32 *delta, bool installed_media, u16 *speeds,
 static void bnxt_set_ethtool_speeds(struct bnxt_link_info *link_info,
 				    const unsigned long *et_mask)
 {
+	struct bnxt *bp = container_of(link_info, struct bnxt, link_info);
+	u16 const *sp_msks, *sp_pam4_msks, *sp_pam4_112_msks;
 	enum bnxt_media_type media = bnxt_get_media(link_info);
+	u16 *adv, *adv_pam4, *adv_pam4_112 = NULL;
+	u32 delta_pam4_112 = 0;
 	u32 delta_pam4 = 0;
 	u32 delta_nrz = 0;
 	int i, m;
 
+	adv = &link_info->advertising;
+	if (bp->phy_flags & BNXT_PHY_FL_SPEEDS2) {
+		adv_pam4 = &link_info->advertising;
+		adv_pam4_112 = &link_info->advertising;
+		sp_msks = bnxt_nrz_speeds2_masks;
+		sp_pam4_msks = bnxt_pam4_speeds2_masks;
+		sp_pam4_112_msks = bnxt_pam4_112_speeds2_masks;
+	} else {
+		adv_pam4 = &link_info->advertising_pam4;
+		sp_msks = bnxt_nrz_speed_masks;
+		sp_pam4_msks = bnxt_pam4_speed_masks;
+	}
 	for (i = 1; i < __BNXT_LINK_SPEED_END; i++) {
 		/* accept any legal media from user */
 		for (m = 1; m < __BNXT_MEDIA_END; m++) {
 			bnxt_update_speed(&delta_nrz, m == media,
-					  &link_info->advertising,
-					  bnxt_nrz_speed_masks[i], et_mask,
+					  adv, sp_msks[i], et_mask,
 					  bnxt_link_modes[i][BNXT_SIG_MODE_NRZ][m]);
 			bnxt_update_speed(&delta_pam4, m == media,
-					  &link_info->advertising_pam4,
-					  bnxt_pam4_speed_masks[i], et_mask,
+					  adv_pam4, sp_pam4_msks[i], et_mask,
 					  bnxt_link_modes[i][BNXT_SIG_MODE_PAM4][m]);
+			if (!adv_pam4_112)
+				continue;
+
+			bnxt_update_speed(&delta_pam4_112, m == media,
+					  adv_pam4_112, sp_pam4_112_msks[i], et_mask,
+					  bnxt_link_modes[i][BNXT_SIG_MODE_PAM4_112][m]);
 		}
 	}
 }
@@ -1961,11 +2403,20 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
 	case BNXT_LINK_SPEED_40GB:
 		return SPEED_40000;
 	case BNXT_LINK_SPEED_50GB:
+	case BNXT_LINK_SPEED_50GB_PAM4:
 		return SPEED_50000;
 	case BNXT_LINK_SPEED_100GB:
+	case BNXT_LINK_SPEED_100GB_PAM4:
+	case BNXT_LINK_SPEED_100GB_PAM4_112:
 		return SPEED_100000;
 	case BNXT_LINK_SPEED_200GB:
+	case BNXT_LINK_SPEED_200GB_PAM4:
+	case BNXT_LINK_SPEED_200GB_PAM4_112:
 		return SPEED_200000;
+	case BNXT_LINK_SPEED_400GB:
+	case BNXT_LINK_SPEED_400GB_PAM4:
+	case BNXT_LINK_SPEED_400GB_PAM4_112:
+		return SPEED_400000;
 	default:
 		return SPEED_UNKNOWN;
 	}
@@ -1981,6 +2432,7 @@ static void bnxt_get_default_speeds(struct ethtool_link_ksettings *lk_ksettings,
 		base->duplex = DUPLEX_HALF;
 		if (link_info->duplex & BNXT_LINK_DUPLEX_FULL)
 			base->duplex = DUPLEX_FULL;
+		lk_ksettings->lanes = link_info->active_lanes;
 	} else if (!link_info->autoneg) {
 		base->speed = bnxt_fw_to_ethtool_speed(link_info->req_link_speed);
 		base->duplex = DUPLEX_HALF;
@@ -2008,12 +2460,7 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	mutex_lock(&bp->link_lock);
 	bnxt_get_ethtool_modes(link_info, lk_ksettings);
 	media = bnxt_get_media(link_info);
-	bnxt_get_ethtool_speeds(link_info->support_speeds,
-				media, BNXT_SIG_MODE_NRZ,
-				lk_ksettings->link_modes.supported);
-	bnxt_get_ethtool_speeds(link_info->support_pam4_speeds,
-				media, BNXT_SIG_MODE_PAM4,
-				lk_ksettings->link_modes.supported);
+	bnxt_get_all_ethtool_support_speeds(link_info, media, lk_ksettings);
 	bnxt_fw_to_ethtool_support_fec(link_info, lk_ksettings);
 	link_mode = bnxt_get_link_mode(link_info);
 	if (link_mode != BNXT_LINK_MODE_UNKNOWN)
@@ -2026,20 +2473,10 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 lk_ksettings->link_modes.advertising);
 		base->autoneg = AUTONEG_ENABLE;
-		bnxt_get_ethtool_speeds(link_info->advertising,
-					media, BNXT_SIG_MODE_NRZ,
-					lk_ksettings->link_modes.advertising);
-		bnxt_get_ethtool_speeds(link_info->advertising_pam4,
-					media, BNXT_SIG_MODE_PAM4,
-					lk_ksettings->link_modes.advertising);
-		if (link_info->phy_link_status == BNXT_LINK_LINK) {
-			bnxt_get_ethtool_speeds(link_info->lp_auto_link_speeds,
-						media, BNXT_SIG_MODE_NRZ,
-						lk_ksettings->link_modes.lp_advertising);
-			bnxt_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds,
-						media, BNXT_SIG_MODE_PAM4,
-						lk_ksettings->link_modes.lp_advertising);
-		}
+		bnxt_get_all_ethtool_adv_speeds(link_info, media, lk_ksettings);
+		if (link_info->phy_link_status == BNXT_LINK_LINK)
+			bnxt_get_all_ethtool_lp_speeds(link_info, media,
+						       lk_ksettings);
 	} else {
 		base->autoneg = AUTONEG_DISABLE;
 	}
@@ -2074,6 +2511,7 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
 	u16 support_pam4_spds = link_info->support_pam4_speeds;
+	u16 support_spds2 = link_info->support_speeds2;
 	u16 support_spds = link_info->support_speeds;
 	u8 sig_mode = BNXT_SIG_MODE_NRZ;
 	u32 lanes_needed = 1;
@@ -2085,7 +2523,8 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB;
 		break;
 	case SPEED_1000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_1GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_1GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_1GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 		break;
 	case SPEED_2500:
@@ -2093,7 +2532,8 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB;
 		break;
 	case SPEED_10000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_10GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_10GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_10GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
 		break;
 	case SPEED_20000:
@@ -2103,26 +2543,34 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 		}
 		break;
 	case SPEED_25000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_25GB)
+		if ((support_spds & BNXT_LINK_SPEED_MSK_25GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_25GB))
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
 		break;
 	case SPEED_40000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_40GB) {
+		if ((support_spds & BNXT_LINK_SPEED_MSK_40GB) ||
+		    (support_spds2 & BNXT_LINK_SPEEDS2_MSK_40GB)) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
 			lanes_needed = 4;
 		}
 		break;
 	case SPEED_50000:
-		if ((support_spds & BNXT_LINK_SPEED_MSK_50GB) && lanes != 1) {
+		if (((support_spds & BNXT_LINK_SPEED_MSK_50GB) ||
+		     (support_spds2 & BNXT_LINK_SPEEDS2_MSK_50GB)) &&
+		    lanes != 1) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
 			lanes_needed = 2;
 		} else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_50GB) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_50GB_PAM4) {
+			fw_speed = BNXT_LINK_SPEED_50GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
 		}
 		break;
 	case SPEED_100000:
-		if ((support_spds & BNXT_LINK_SPEED_MSK_100GB) &&
+		if (((support_spds & BNXT_LINK_SPEED_MSK_100GB) ||
+		     (support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB)) &&
 		    lanes != 2 && lanes != 1) {
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB;
 			lanes_needed = 4;
@@ -2130,6 +2578,14 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
 			lanes_needed = 2;
+		} else if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB_PAM4) &&
+			   lanes != 1) {
+			fw_speed = BNXT_LINK_SPEED_100GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 2;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_100GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_100GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
 		}
 		break;
 	case SPEED_200000:
@@ -2137,6 +2593,27 @@ bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes)
 			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB;
 			sig_mode = BNXT_SIG_MODE_PAM4;
 			lanes_needed = 4;
+		} else if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_200GB_PAM4) &&
+			   lanes != 2) {
+			fw_speed = BNXT_LINK_SPEED_200GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 4;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_200GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_200GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
+			lanes_needed = 2;
+		}
+		break;
+	case SPEED_400000:
+		if ((support_spds2 & BNXT_LINK_SPEEDS2_MSK_400GB_PAM4) &&
+		    lanes != 4) {
+			fw_speed = BNXT_LINK_SPEED_400GB_PAM4;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+			lanes_needed = 8;
+		} else if (support_spds2 & BNXT_LINK_SPEEDS2_MSK_400GB_PAM4_112) {
+			fw_speed = BNXT_LINK_SPEED_400GB_PAM4_112;
+			sig_mode = BNXT_SIG_MODE_PAM4_112;
+			lanes_needed = 4;
 		}
 		break;
 	}
@@ -3910,7 +4387,8 @@ static int bnxt_poll_loopback(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		 * reading any further.
 		 */
 		dma_rmb();
-		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) {
+		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP ||
+		    TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_V3_CMP) {
 			rc = bnxt_rx_loopback(bp, cpr, raw_cons, pkt_size);
 			raw_cons = NEXT_RAW_CMP(raw_cons);
 			raw_cons = NEXT_RAW_CMP(raw_cons);
@@ -3934,8 +4412,8 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	int rc;
 
 	cpr = &rxr->bnapi->cp_ring;
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		cpr = cpr->cp_ring_arr[BNXT_RX_HDL];
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		cpr = rxr->rx_cpr;
 	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
 	skb = netdev_alloc_skb(bp->dev, pkt_size);
 	if (!skb)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index d5fad5a3cd..e957abd704 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -40,6 +40,8 @@ struct hwrm_resp_hdr {
 #define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
 #define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
 #define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
 #define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
 #define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
 #define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
@@ -196,6 +198,9 @@ struct cmd_nums {
 	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
 	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
 	#define HWRM_QUEUE_QCAPS                          0x8cUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
 	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
 	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
 	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
@@ -214,6 +219,7 @@ struct cmd_nums {
 	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
 	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
 	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
 	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
 	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
 	#define HWRM_STAT_CTX_FREE                        0xb1UL
@@ -261,6 +267,7 @@ struct cmd_nums {
 	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
 	#define HWRM_PORT_CFG                             0xdcUL
 	#define HWRM_PORT_QCFG                            0xddUL
+	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
 	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
 	#define HWRM_REG_POWER_QUERY                      0xe1UL
 	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
@@ -392,6 +399,10 @@ struct cmd_nums {
 	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
 	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
 	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
+	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
+	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
+	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
+	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -406,9 +417,9 @@ struct cmd_nums {
 	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
 	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
 	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
-	#define HWRM_MFG_PARAM_SEEPROM_SYNC               0x20eUL
-	#define HWRM_MFG_PARAM_SEEPROM_READ               0x20fUL
-	#define HWRM_MFG_PARAM_SEEPROM_HEALTH             0x210UL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
 	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
 	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
 	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
@@ -418,6 +429,16 @@ struct cmd_nums {
 	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
 	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
 	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
+	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
+	#define HWRM_UDCC_QCAPS                           0x258UL
+	#define HWRM_UDCC_CFG                             0x259UL
+	#define HWRM_UDCC_QCFG                            0x25aUL
+	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
+	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
+	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
+	#define HWRM_UDCC_COMP_CFG                        0x25eUL
+	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
+	#define HWRM_UDCC_COMP_QUERY                      0x260UL
 	#define HWRM_TF                                   0x2bcUL
 	#define HWRM_TF_VERSION_GET                       0x2bdUL
 	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
@@ -582,9 +603,9 @@ struct hwrm_err_output {
 #define HWRM_TARGET_ID_TOOLS 0xFFFD
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
-#define HWRM_VERSION_UPDATE 2
-#define HWRM_VERSION_RSVD 171
-#define HWRM_VERSION_STR "1.10.2.171"
+#define HWRM_VERSION_UPDATE 3
+#define HWRM_VERSION_RSVD 15
+#define HWRM_VERSION_STR "1.10.3.15"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -816,7 +837,8 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x4cUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
@@ -1632,7 +1654,7 @@ struct hwrm_func_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcaps_output (size:896b/112B) */
+/* hwrm_func_qcaps_output (size:1088b/136B) */
 struct hwrm_func_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1736,21 +1758,29 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
 	__le16	max_key_ctxs_alloc;
 	__le32	flags_ext2;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED     0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                       0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                      0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED             0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED       0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED              0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                    0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                      0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED              0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED             0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                     0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED               0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED          0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED          0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
 	__le16	tunnel_disable_flag;
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
@@ -1760,15 +1790,21 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
-	u8	key_xid_partition_cap;
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_TKC          0x1UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_RKC          0x2UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_QUIC_TKC     0x4UL
-	#define FUNC_QCAPS_RESP_KEY_XID_PARTITION_CAP_QUIC_RKC     0x8UL
-	u8	unused_1;
+	__le16	xid_partition_cap;
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_KTLS_TKC     0x1UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_KTLS_RKC     0x2UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_QUIC_TKC     0x4UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_QUIC_RKC     0x8UL
 	u8	device_serial_number[8];
 	__le16	ctxs_per_partition;
-	u8	unused_2[5];
+	u8	unused_2[2];
+	__le32	roce_vf_max_av;
+	__le32	roce_vf_max_cq;
+	__le32	roce_vf_max_mrw;
+	__le32	roce_vf_max_qp;
+	__le32	roce_vf_max_srq;
+	__le32	roce_vf_max_gid;
+	u8	unused_3[3];
 	u8	valid;
 };
 
@@ -1783,7 +1819,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:1024b/128B) */
+/* hwrm_func_qcfg_output (size:1280b/160B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1892,7 +1928,7 @@ struct hwrm_func_qcfg_output {
 	__le16	alloc_msix;
 	__le16	registered_vfs;
 	__le16	l2_doorbell_bar_size_kb;
-	u8	unused_1;
+	u8	active_endpoints;
 	u8	always_1;
 	__le32	reset_addr_poll;
 	__le16	legacy_l2_db_size_kb;
@@ -1952,15 +1988,26 @@ struct hwrm_func_qcfg_output {
 	u8	kdnet_pcie_function;
 	__le16	port_kdnet_fid;
 	u8	unused_5[2];
-	__le32	alloc_tx_key_ctxs;
-	__le32	alloc_rx_key_ctxs;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
 	u8	lag_id;
 	u8	parif;
-	u8	unused_6[5];
+	u8	fw_lag_id;
+	u8	unused_6;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	u8	unused_7;
 	u8	valid;
 };
 
-/* hwrm_func_cfg_input (size:1088b/136B) */
+/* hwrm_func_cfg_input (size:1280b/160B) */
 struct hwrm_func_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -1996,7 +2043,6 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
 	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
 	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
-	#define FUNC_CFG_REQ_FLAGS_KEY_CTX_ASSETS_TEST            0x80000000UL
 	__le32	enables;
 	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
@@ -2028,8 +2074,8 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
 	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
 	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
-	#define FUNC_CFG_REQ_ENABLES_TX_KEY_CTXS              0x40000000UL
-	#define FUNC_CFG_REQ_ENABLES_RX_KEY_CTXS              0x80000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
 	__le16	admin_mtu;
 	__le16	mru;
 	__le16	num_rsscos_ctxs;
@@ -2139,10 +2185,21 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
 	__be16	tpid;
 	__le16	host_mtu;
-	u8	unused_0[4];
+	__le32	flags2;
+	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
+	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
 	__le32	enables2;
-	#define FUNC_CFG_REQ_ENABLES2_KDNET            0x1UL
-	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE     0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_KDNET                   0x1UL
+	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE            0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS        0x4UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS        0x8UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF      0x10UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF      0x20UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF     0x40UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF      0x80UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF     0x100UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF     0x200UL
+	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG       0x400UL
 	u8	port_kdnet_mode;
 	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
 	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
@@ -2165,7 +2222,18 @@ struct hwrm_func_cfg_input {
 	__le32	num_ktls_rx_key_ctxs;
 	__le32	num_quic_tx_key_ctxs;
 	__le32	num_quic_rx_key_ctxs;
-	__le32	unused_2;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_KTLS_TKC     0x1UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_KTLS_RKC     0x2UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_QUIC_TKC     0x4UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_QUIC_RKC     0x8UL
+	__le16	unused_2;
 };
 
 /* hwrm_func_cfg_output (size:128b/16B) */
@@ -2604,7 +2672,7 @@ struct hwrm_func_vf_resource_cfg_input {
 	__le32	max_quic_rx_key_ctxs;
 };
 
-/* hwrm_func_vf_resource_cfg_output (size:320b/40B) */
+/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
 struct hwrm_func_vf_resource_cfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -2618,8 +2686,10 @@ struct hwrm_func_vf_resource_cfg_output {
 	__le16	reserved_vnics;
 	__le16	reserved_stat_ctx;
 	__le16	reserved_hw_ring_grps;
-	__le32	reserved_tx_key_ctxs;
-	__le32	reserved_rx_key_ctxs;
+	__le32	reserved_ktls_tx_key_ctxs;
+	__le32	reserved_ktls_rx_key_ctxs;
+	__le32	reserved_quic_tx_key_ctxs;
+	__le32	reserved_quic_rx_key_ctxs;
 	u8	unused_0[7];
 	u8	valid;
 };
@@ -3441,7 +3511,8 @@ struct hwrm_func_ptp_cfg_input {
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
 	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
 	u8	unused_0[3];
 	__le32	ptp_freq_adj_ext_period;
 	__le32	ptp_freq_adj_ext_up;
@@ -3627,28 +3698,28 @@ struct hwrm_func_backing_store_qcfg_v2_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP            0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ           0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ            0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC          0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT          0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING   0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING   0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV          0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC           0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING   0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW  0x16UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW  0x17UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW  0x19UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_RKC      0x1bUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE     0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST         FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC                 0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC                 0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_TKC            0x1aUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QUIC_RKC            0x1bUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
 	__le16	instance;
 	u8	rsvd[4];
 };
@@ -3744,6 +3815,15 @@ struct mrav_split_entries {
 	__le32	rsvd2[2];
 };
 
+/* ts_split_entries (size:128b/16B) */
+struct ts_split_entries {
+	__le32	region_num_entries;
+	u8	tsid;
+	u8	lkup_static_bkt_cnt_exp[2];
+	u8	rsvd;
+	__le32	rsvd2[2];
+};
+
 /* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
 struct hwrm_func_backing_store_qcaps_v2_input {
 	__le16	req_type;
@@ -3761,8 +3841,8 @@ struct hwrm_func_backing_store_qcaps_v2_input {
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC           0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_KTLS_TKC      0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_KTLS_RKC      0x14UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING   0x15UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW  0x16UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW  0x17UL
@@ -3793,8 +3873,8 @@ struct hwrm_func_backing_store_qcaps_v2_output {
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RKC           0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_KTLS_TKC      0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_KTLS_RKC      0x14UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING   0x15UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW  0x16UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW  0x17UL
@@ -3838,56 +3918,55 @@ struct hwrm_func_backing_store_qcaps_v2_output {
 
 /* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
 struct hwrm_func_dbr_pacing_qcfg_input {
-	__le16  req_type;
-	__le16  cmpl_ring;
-	__le16  seq_id;
-	__le16  target_id;
-	__le64  resp_addr;
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
 };
 
 /* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
 struct hwrm_func_dbr_pacing_qcfg_output {
-	__le16  error_code;
-	__le16  req_type;
-	__le16  seq_id;
-	__le16  resp_len;
-	u8      flags;
-#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
-	u8      unused_0[7];
-	__le32  dbr_stat_db_fifo_reg;
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     \
-		FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
-	__le32  dbr_stat_db_fifo_reg_watermark_mask;
-	u8      dbr_stat_db_fifo_reg_watermark_shift;
-	u8      unused_1[3];
-	__le32  dbr_stat_db_fifo_reg_fifo_room_mask;
-	u8      dbr_stat_db_fifo_reg_fifo_room_shift;
-	u8      unused_2[3];
-	__le32  dbr_throttling_aeq_arm_reg;
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST	\
-		FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
-#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
-	u8      dbr_throttling_aeq_arm_reg_val;
-	u8      unused_3[7];
-	__le32  primary_nq_id;
-	__le32  pacing_threshold;
-	u8      unused_4[7];
-	u8      valid;
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
+	u8	unused_0[7];
+	__le32	dbr_stat_db_fifo_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
+	__le32	dbr_stat_db_fifo_reg_watermark_mask;
+	u8	dbr_stat_db_fifo_reg_watermark_shift;
+	u8	unused_1[3];
+	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
+	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
+	u8	unused_2[3];
+	__le32	dbr_throttling_aeq_arm_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
+	u8	dbr_throttling_aeq_arm_reg_val;
+	u8	unused_3[3];
+	__le32	dbr_stat_db_max_fifo_depth;
+	__le32	primary_nq_id;
+	__le32	pacing_threshold;
+	u8	unused_4[7];
+	u8	valid;
 };
 
 /* hwrm_func_drv_if_change_input (size:192b/24B) */
@@ -3915,7 +3994,7 @@ struct hwrm_func_drv_if_change_output {
 	u8	valid;
 };
 
-/* hwrm_port_phy_cfg_input (size:448b/56B) */
+/* hwrm_port_phy_cfg_input (size:512b/64B) */
 struct hwrm_port_phy_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -3960,6 +4039,8 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
 	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
 	__le16	port_id;
 	__le16	force_link_speed;
 	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
@@ -3990,7 +4071,9 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
 	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	u8	unused_0;
+	u8	mgmt_flag;
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
 	__le16	auto_link_speed;
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
@@ -4054,7 +4137,36 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
 	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
-	u8	unused_2[2];
+	__le16	force_link_speeds2;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112
+	__le16	auto_link_speeds2_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
+	u8	unused_2[6];
 };
 
 /* hwrm_port_phy_cfg_output (size:128b/16B) */
@@ -4104,7 +4216,8 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
 	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
 	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
@@ -4127,6 +4240,7 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
 	u8	duplex_cfg;
@@ -4270,7 +4384,23 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
 	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4
 	u8	media_type;
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL
 	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP      0x1UL
@@ -4366,6 +4496,7 @@ struct hwrm_port_phy_qcfg_output {
 	u8	option_flags;
 	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
 	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
 	char	phy_vendor_name[16];
 	char	phy_vendor_partnumber[16];
 	__le16	support_pam4_speeds;
@@ -4387,7 +4518,53 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
 	u8	link_down_reason;
 	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF     0x1UL
-	u8	unused_0[7];
+	__le16	support_speeds2;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
+	u8	active_lanes;
 	u8	valid;
 };
 
@@ -4426,6 +4603,7 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
 	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
 	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
 	__le16	port_id;
 	u8	ipg;
 	u8	lpbk;
@@ -4459,7 +4637,12 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
 	u8	unused_0[3];
 	__le32	ptp_freq_adj_ppb;
-	u8	unused_1[4];
+	u8	unused_1[3];
+	u8	ptp_load_control;
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
 	__le64	ptp_adj_phase;
 };
 
@@ -4504,6 +4687,7 @@ struct hwrm_port_mac_ptp_qcfg_output {
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
 	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
 	u8	unused_0[3];
 	__le32	rx_ts_reg_off_lower;
 	__le32	rx_ts_reg_off_upper;
@@ -4968,7 +5152,7 @@ struct hwrm_port_phy_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_port_phy_qcaps_output (size:256b/32B) */
+/* hwrm_port_phy_qcaps_output (size:320b/40B) */
 struct hwrm_port_phy_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -5051,7 +5235,40 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED       0x1UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED         0x2UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED     0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED       0x8UL
 	u8	internal_port_cnt;
+	u8	unused_0;
+	__le16	supported_speeds2_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
+	__le16	supported_speeds2_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -5472,6 +5689,30 @@ struct hwrm_port_led_qcaps_output {
 	u8	valid;
 };
 
+/* hwrm_port_mac_qcaps_input (size:192b/24B) */
+struct hwrm_port_mac_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_qcaps_output (size:128b/16B) */
+struct hwrm_port_mac_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
+	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
 /* hwrm_queue_qportcfg_input (size:192b/24B) */
 struct hwrm_queue_qportcfg_input {
 	__le16	req_type;
@@ -7488,7 +7729,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
 	__le16	dst_id;
-	__le16	mirror_vnic_id;
+	__le16	rfs_ring_tbl_idx;
 	u8	tunnel_type;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
@@ -8201,6 +8442,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
 	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -8223,7 +8465,8 @@ struct hwrm_tunnel_dst_port_query_input {
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	u8	unused_0[6];
 };
@@ -8245,7 +8488,10 @@ struct hwrm_tunnel_dst_port_query_output {
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
 	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	unused_0[2];
+	u8	status;
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
+	u8	unused_0;
 	u8	valid;
 };
 
@@ -8267,7 +8513,8 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	__be16	tunnel_dst_port_val;
 	u8	unused_0[4];
@@ -8284,7 +8531,8 @@ struct hwrm_tunnel_dst_port_alloc_output {
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
 	u8	upar_in_use;
 	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
@@ -8316,7 +8564,8 @@ struct hwrm_tunnel_dst_port_free_input {
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI        0xeUL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6         0xfUL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE          0x11UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE
 	u8	tunnel_next_proto;
 	__le16	tunnel_dst_port_id;
 	u8	unused_0[4];
@@ -9717,7 +9966,7 @@ struct hwrm_nvm_get_dev_info_input {
 	__le64	resp_addr;
 };
 
-/* hwrm_nvm_get_dev_info_output (size:640b/80B) */
+/* hwrm_nvm_get_dev_info_output (size:704b/88B) */
 struct hwrm_nvm_get_dev_info_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -9747,6 +9996,10 @@ struct hwrm_nvm_get_dev_info_output {
 	__le16	roce_fw_minor;
 	__le16	roce_fw_build;
 	__le16	roce_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
 	u8	unused_0[7];
 	u8	valid;
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 6e3da3362b..cc07660330 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -129,7 +129,7 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
 	}
 	resp = hwrm_req_hold(bp, req);
 
-	rc = hwrm_req_send(bp, req);
+	rc = hwrm_req_send_silent(bp, req);
 	if (!rc)
 		*ts = le64_to_cpu(resp->ptp_msg_ts);
 	hwrm_req_drop(bp, req);
@@ -319,15 +319,17 @@ static int bnxt_ptp_cfg_event(struct bnxt *bp, u8 event)
 	return hwrm_req_send(bp, req);
 }
 
-void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
+int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct hwrm_port_mac_cfg_input *req;
+	int rc;
 
 	if (!ptp || !ptp->tstamp_filters)
-		return;
+		return -EIO;
 
-	if (hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG))
+	rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG);
+	if (rc)
 		goto out;
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_RX_ALL_PKT_TS) && (ptp->tstamp_filters &
@@ -342,15 +344,17 @@ void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
 	req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE);
 	req->rx_ts_capture_ptp_msg_type = cpu_to_le16(ptp->rxctl);
 
-	if (!hwrm_req_send(bp, req)) {
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
 		bp->ptp_all_rx_tstamp = !!(ptp->tstamp_filters &
 					   PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE);
-		return;
+		return 0;
 	}
 	ptp->tstamp_filters = 0;
 out:
 	bp->ptp_all_rx_tstamp = 0;
 	netdev_warn(bp->dev, "Failed to configure HW packet timestamp filters\n");
+	return rc;
 }
 
 void bnxt_ptp_reapply_pps(struct bnxt *bp)
@@ -494,7 +498,6 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	u32 flags = 0;
-	int rc = 0;
 
 	switch (ptp->rx_filter) {
 	case HWTSTAMP_FILTER_ALL:
@@ -519,18 +522,7 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 
 	ptp->tstamp_filters = flags;
 
-	if (netif_running(bp->dev)) {
-		if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) {
-			bnxt_close_nic(bp, false, false);
-			rc = bnxt_open_nic(bp, false, false);
-		} else {
-			bnxt_ptp_cfg_tstamp_filters(bp);
-		}
-		if (!rc && !ptp->tstamp_filters)
-			rc = -EIO;
-	}
-
-	return rc;
+	return bnxt_ptp_cfg_tstamp_filters(bp);
 }
 
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -649,7 +641,7 @@ static int bnxt_map_ptp_regs(struct bnxt *bp)
 	int rc, i;
 
 	reg_arr = ptp->refclk_regs;
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (BNXT_CHIP_P5(bp)) {
 		rc = bnxt_map_regs(bp, reg_arr, 2, BNXT_PTP_GRC_WIN);
 		if (rc)
 			return rc;
@@ -692,8 +684,8 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_err(bp->dev, "TS query for TX timer failed rc = %x\n",
-			   rc);
+		netdev_warn_once(bp->dev,
+				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 
 	dev_kfree_skb_any(ptp->tx_skb);
@@ -966,7 +958,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 		rc = err;
 		goto out;
 	}
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (BNXT_CHIP_P5(bp)) {
 		spin_lock_bh(&ptp->ptp_lock);
 		bnxt_refclk_read(bp, NULL, &ptp->current_time);
 		WRITE_ONCE(ptp->old_time, ptp->current_time);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 34162e07a1..fce8dc39a7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -137,7 +137,7 @@ do {						\
 int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off);
 void bnxt_ptp_update_current_time(struct bnxt *bp);
 void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2);
-void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
+int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index c722b3b417..175192ebaa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -536,7 +536,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	if (rc)
 		return rc;
 
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 		vf_msix = hw_resc->max_nqs - bnxt_nq_rings_in_use(bp);
 		vf_ring_grps = 0;
 	} else {
@@ -565,7 +565,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		req->min_l2_ctxs = cpu_to_le16(min);
 		req->min_vnics = cpu_to_le16(min);
 		req->min_stat_ctx = cpu_to_le16(min);
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			req->min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
@@ -602,7 +602,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 	req->max_stat_ctx = cpu_to_le16(vf_stat_ctx);
 	req->max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
 	req->max_rsscos_ctx = cpu_to_le16(vf_rss);
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		req->max_msix = cpu_to_le16(vf_msix / num_vfs);
 
 	hwrm_req_hold(bp, req);
@@ -630,7 +630,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 			le16_to_cpu(req->min_rsscos_ctx) * n;
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 6ba2b93986..195c02dc06 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -42,13 +42,10 @@ static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent)
 	for (i = 0; i < num_msix; i++) {
 		ent[i].vector = bp->irq_tbl[idx + i].vector;
 		ent[i].ring_idx = idx + i;
-		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			ent[i].db_offset = DB_PF_OFFSET_P5;
-			if (BNXT_VF(bp))
-				ent[i].db_offset = DB_VF_OFFSET_P5;
-		} else {
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+			ent[i].db_offset = bp->db_offset;
+		else
 			ent[i].db_offset = (idx + i) * 0x80;
-		}
 	}
 }
 
@@ -213,6 +210,9 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	if (err)
 		return;
 
+	if (edev->ulp_tbl->msix_requested)
+		bnxt_fill_msix_vecs(bp, edev->msix_entries);
+
 	if (aux_priv) {
 		struct auxiliary_device *adev;
 
@@ -333,6 +333,7 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 	edev->pdev = bp->pdev;
 	edev->l2_db_size = bp->db_size;
 	edev->l2_db_size_nc = bp->db_size;
+	edev->l2_db_offset = bp->db_offset;
 
 	if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
 		edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
@@ -394,12 +395,13 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp)
 	if (!edev)
 		goto aux_dev_uninit;
 
+	aux_priv->edev = edev;
+
 	ulp = kzalloc(sizeof(*ulp), GFP_KERNEL);
 	if (!ulp)
 		goto aux_dev_uninit;
 
 	edev->ulp_tbl = ulp;
-	aux_priv->edev = edev;
 	bp->edev = edev;
 	bnxt_set_edev_info(edev, bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 6ff77f082e..b9e73de14b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -73,6 +73,10 @@ struct bnxt_en_dev {
 							 * bytes mapped as non-
 							 * cacheable.
 							 */
+	int				l2_db_offset;	/* Doorbell offset in
+							 * bytes within
+							 * l2_db_size_nc.
+							 */
 	u16				chip_num;
 	u16				hw_ring_stats_size;
 	u16				pf_port_id;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 8cb9a99154..4079538bc3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -42,17 +42,17 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 
 	/* fill up the first buffer */
 	prod = txr->tx_prod;
-	tx_buf = &txr->tx_buf_ring[prod];
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 	tx_buf->nr_frags = num_frags;
 	if (xdp)
 		tx_buf->page = virt_to_head_page(xdp->data);
 
-	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+	txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 	flags = (len << TX_BD_LEN_SHIFT) |
 		((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT) |
 		bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
-	txbd->tx_bd_opaque = prod;
+	txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod, 1 + num_frags);
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
 	/* now let us fill up the frags into the next buffers */
@@ -66,10 +66,10 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 		WRITE_ONCE(txr->tx_prod, prod);
 
 		/* first fill up the first buffer */
-		frag_tx_buf = &txr->tx_buf_ring[prod];
+		frag_tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		frag_tx_buf->page = skb_frag_page(frag);
 
-		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
 		frag_len = skb_frag_size(frag);
 		flags = frag_len << TX_BD_LEN_SHIFT;
@@ -120,20 +120,20 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 {
-	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
+	struct bnxt_tx_ring_info *txr = bnapi->tx_ring[0];
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	u16 tx_hw_cons = txr->tx_hw_cons;
 	bool rx_doorbell_needed = false;
-	int nr_pkts = bnapi->tx_pkts;
 	struct bnxt_sw_tx_bd *tx_buf;
 	u16 tx_cons = txr->tx_cons;
 	u16 last_tx_cons = tx_cons;
-	int i, j, frags;
+	int j, frags;
 
 	if (!budget)
 		return;
 
-	for (i = 0; i < nr_pkts; i++) {
-		tx_buf = &txr->tx_buf_ring[tx_cons];
+	while (RING_TX(bp, tx_cons) != tx_hw_cons) {
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, tx_cons)];
 
 		if (tx_buf->action == XDP_REDIRECT) {
 			struct pci_dev *pdev = bp->pdev;
@@ -153,20 +153,20 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 			frags = tx_buf->nr_frags;
 			for (j = 0; j < frags; j++) {
 				tx_cons = NEXT_TX(tx_cons);
-				tx_buf = &txr->tx_buf_ring[tx_cons];
+				tx_buf = &txr->tx_buf_ring[RING_TX(bp, tx_cons)];
 				page_pool_recycle_direct(rxr->page_pool, tx_buf->page);
 			}
 		} else {
-			bnxt_sched_reset_txr(bp, txr, i);
+			bnxt_sched_reset_txr(bp, txr, tx_cons);
 			return;
 		}
 		tx_cons = NEXT_TX(tx_cons);
 	}
 
-	bnapi->tx_pkts = 0;
+	bnapi->events &= ~BNXT_TX_CMP_EVENT;
 	WRITE_ONCE(txr->tx_cons, tx_cons);
 	if (rx_doorbell_needed) {
-		tx_buf = &txr->tx_buf_ring[last_tx_cons];
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, last_tx_cons)];
 		bnxt_db_write(bp, &rxr->rx_db, tx_buf->rx_prod);
 
 	}
@@ -242,7 +242,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	pdev = bp->pdev;
 	offset = bp->rx_offset;
 
-	txr = rxr->bnapi->tx_ring;
+	txr = rxr->bnapi->tx_ring[0];
 	/* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
 	orig_data = xdp.data;
 
@@ -268,7 +268,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	case XDP_TX:
 		rx_buf = &rxr->rx_buf_ring[cons];
 		mapping = rx_buf->mapping - bp->rx_dma_offset;
-		*event = 0;
+		*event &= BNXT_TX_CMP_EVENT;
 
 		if (unlikely(xdp_buff_has_frags(&xdp))) {
 			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(&xdp);
@@ -391,7 +391,7 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
-	int tx_xdp = 0, rc, tc;
+	int tx_xdp = 0, tx_cp, rc, tc;
 	struct bpf_prog *old;
 
 	if (prog && !prog->aux->xdp_has_frags &&
@@ -407,7 +407,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	if (prog)
 		tx_xdp = bp->rx_nr_rings;
 
-	tc = netdev_get_num_tc(dev);
+	tc = bp->num_tc;
 	if (!tc)
 		tc = 1;
 	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
@@ -439,7 +439,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
-	bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings);
+	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+	bp->cp_nr_rings = max_t(int, tx_cp, bp->rx_nr_rings);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f52830dfb2..04964bbe08 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12745,24 +12745,23 @@ static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
 	return size;
 }
 
-static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int tg3_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		indir[i] = tp->rss_ind_tbl[i];
+		rxfh->indir[i] = tp->rss_ind_tbl[i];
 
 	return 0;
 }
 
-static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
-			const u8 hfunc)
+static int tg3_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	size_t i;
@@ -12770,15 +12769,16 @@ static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		tp->rss_ind_tbl[i] = indir[i];
+		tp->rss_ind_tbl[i] = rxfh->indir[i];
 
 	if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
 		return 0;