Merge tag 'net-next-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski: "Core & protocols: - Complete rework of garbage collection of AF_UNIX sockets. AF_UNIX is prone to forming reference count cycles due to fd passing functionality. New method based on Tarjan's Strongly Connected Components algorithm should be both faster and remove a lot of workarounds we accumulated over the years. - Add TCP fraglist GRO support, allowing chaining multiple TCP packets and forwarding them together. Useful for small switches / routers which lack basic checksum offload in some scenarios (e.g. PPPoE). - Support using SMP threads for handling packet backlog i.e. packet processing from software interfaces and old drivers which don't use NAPI. This helps move the processing out of the softirq jumble. - Continue work of converting from rtnl lock to RCU protection. Don't require rtnl lock when reading: IPv6 routing FIB, IPv6 address labels, netdev threaded NAPI sysfs files, bonding driver's sysfs files, MPLS devconf, IPv4 FIB rules, netns IDs, tcp metrics, TC Qdiscs, neighbor entries, ARP entries via ioctl(SIOCGARP), a lot of the link information available via rtnetlink. - Small optimizations from Eric to UDP wake up handling, memory accounting, RPS/RFS implementation, TCP packet sizing etc. - Allow direct page recycling in the bulk API used by XDP, for +2% PPS. - Support peek with an offset on TCP sockets. - Add MPTCP APIs for querying last time packets were received/sent/acked and whether MPTCP "upgrade" succeeded on a TCP socket. - Add intra-node communication shortcut to improve SMC performance. - Add IPv6 (and IPv{4,6}-over-IPv{4,6}) support to the GTP protocol driver. - Add HSR-SAN (RedBOX) mode of operation to the HSR protocol driver. - Add reset reasons for tracing what caused a TCP reset to be sent. - Introduce direction attribute for xfrm (IPSec) states. State can be used either for input or output packet processing. Things we sprinkled into general kernel code: - Add bitmap_{read,write}(), bitmap_size(), expose BYTES_TO_BITS(). This required touch-ups and renaming of a few existing users. - Add Endian-dependent __counted_by_{le,be} annotations. - Make building selftests "quieter" by printing summaries like "CC object.o" rather than full commands with all the arguments. Netfilter: - Use GFP_KERNEL to clone elements, to deal better with OOM situations and avoid failures in the .commit step. BPF: - Add eBPF JIT for ARCv2 CPUs. - Support attaching kprobe BPF programs through kprobe_multi link in a session mode, meaning, a BPF program is attached to both function entry and return, the entry program can decide if the return program gets executed and the entry program can share u64 cookie value with return program. "Session mode" is a common use-case for tetragon and bpftrace. - Add the ability to specify and retrieve BPF cookie for raw tracepoint programs in order to ease migration from classic to raw tracepoints. - Add an internal-only BPF per-CPU instruction for resolving per-CPU memory addresses and implement support in x86, ARM64 and RISC-V JITs. This allows inlining functions which need to access per-CPU state. - Optimize x86 BPF JIT's emit_mov_imm64, and add support for various atomics in bpf_arena which can be JITed as a single x86 instruction. Support BPF arena on ARM64. - Add a new bpf_wq API for deferring events and refactor process-context bpf_timer code to keep common code where possible. - Harden the BPF verifier's and/or/xor value tracking. - Introduce crypto kfuncs to let BPF programs call kernel crypto APIs. - Support bpf_tail_call_static() helper for BPF programs with GCC 13. - Add bpf_preempt_{disable,enable}() kfuncs in order to allow a BPF program to have code sections where preemption is disabled. Driver API: - Skip software TC processing completely if all installed rules are marked as HW-only, instead of checking the HW-only flag rule by rule. - Add support for configuring PoE (Power over Ethernet), similar to the already existing support for PoDL (Power over Data Line) config. - Initial bits of a queue control API, for now allowing a single queue to be reset without disturbing packet flow to other queues. - Common (ethtool) statistics for hardware timestamping. Tests and tooling: - Remove the need to create a config file to run the net forwarding tests so that a naive "make run_tests" can exercise them. - Define a method of writing tests which require an external endpoint to communicate with (to send/receive data towards the test machine). Add a few such tests. - Create a shared code library for writing Python tests. Expose the YAML Netlink library from tools/ to the tests for easy Netlink access. - Move netfilter tests under net/, extend them, separate performance tests from correctness tests, and iron out issues found by running them "on every commit". - Refactor BPF selftests to use common network helpers. - Further work filling in YAML definitions of Netlink messages for: nftables, team driver, bonding interfaces, vlan interfaces, VF info, TC u32 mark, TC police action. - Teach Python YAML Netlink to decode attribute policies. - Extend the definition of the "indexed array" construct in the specs to cover arrays of scalars rather than just nests. - Add hyperlinks between definitions in generated Netlink docs. Drivers: - Make sure unsupported flower control flags are rejected by drivers, and make more drivers report errors directly to the application rather than dmesg (large number of driver changes from Asbjørn Sloth Tønnesen). - Ethernet high-speed NICs: - Broadcom (bnxt): - support multiple RSS contexts and steering traffic to them - support XDP metadata - make page pool allocations more NUMA aware - Intel (100G, ice, idpf): - extract datapath code common among Intel drivers into a library - use fewer resources in switchdev by sharing queues with the PF - add PFCP filter support - add Ethernet filter support - use a spinlock instead of HW lock in PTP clock ops - support 5 layer Tx scheduler topology - nVidia/Mellanox: - 800G link modes and 100G SerDes speeds - per-queue IRQ coalescing configuration - Marvell Octeon: - support offloading TC packet mark action - Ethernet NICs consumer, embedded and virtual: - stop lying about skb->truesize in USB Ethernet drivers, it messes up TCP memory calculations - Google cloud vNIC: - support changing ring size via ethtool - support ring reset using the queue control API - VirtIO net: - expose flow hash from RSS to XDP - per-queue statistics - add selftests - Synopsys (stmmac): - support controllers which require an RX clock signal from the MII bus to perform their hardware initialization - TI: - icssg_prueth: support ICSSG-based Ethernet on AM65x SR1.0 devices - icssg_prueth: add SW TX / RX Coalescing based on hrtimers - cpsw: minimal XDP support - Renesas (ravb): - support describing the MDIO bus - Realtek (r8169): - add support for RTL8168M - Microchip Sparx5: - matchall and flower actions mirred and redirect - Ethernet switches: - nVidia/Mellanox: - improve events processing performance - Marvell: - add support for MV88E6250 family internal PHYs - Microchip: - add DCB and DSCP mapping support for KSZ switches - vsc73xx: convert to PHYLINK - Realtek: - rtl8226b/rtl8221b: add C45 instances and SerDes switching - Many driver changes related to PHYLIB and PHYLINK deprecated API cleanup - Ethernet PHYs: - Add a new driver for Airoha EN8811H 2.5 Gigabit PHY. - micrel: lan8814: add support for PPS out and external timestamp trigger - WiFi: - Disable Wireless Extensions (WEXT) in all Wi-Fi 7 devices drivers. Modern devices can only be configured using nl80211. - mac80211/cfg80211 - handle color change per link for WiFi 7 Multi-Link Operation - Intel (iwlwifi): - don't support puncturing in 5 GHz - support monitor mode on passive channels - BZ-W device support - P2P with HE/EHT support - re-add support for firmware API 90 - provide channel survey information for Automatic Channel Selection - MediaTek (mt76): - mt7921 LED control - mt7925 EHT radiotap support - mt7920e PCI support - Qualcomm (ath11k): - P2P support for QCA6390, WCN6855 and QCA2066 - support hibernation - ieee80211-freq-limit Device Tree property support - Qualcomm (ath12k): - refactoring in preparation of multi-link support - suspend and hibernation support - ACPI support - debugfs support, including dfs_simulate_radar support - RealTek: - rtw88: RTL8723CS SDIO device support - rtw89: RTL8922AE Wi-Fi 7 PCI device support - rtw89: complete features of new WiFi 7 chip 8922AE including BT-coexistence and Wake-on-WLAN - rtw89: use BIOS ACPI settings to set TX power and channels - rtl8xxxu: enable Management Frame Protection (MFP) support - Bluetooth: - support for Intel BlazarI and Filmore Peak2 (BE201) - support for MediaTek MT7921S SDIO - initial support for Intel PCIe BT driver - remove HCI_AMP support" * tag 'net-next-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1827 commits) selftests: netfilter: fix packetdrill conntrack testcase net: gro: fix napi_gro_cb zeroed alignment Bluetooth: btintel_pcie: Refactor and code cleanup Bluetooth: btintel_pcie: Fix warning reported by sparse Bluetooth: hci_core: Fix not handling hdev->le_num_of_adv_sets=1 Bluetooth: btintel: Fix compiler warning for multi_v7_defconfig config Bluetooth: btintel_pcie: Fix compiler warnings Bluetooth: btintel_pcie: Add *setup* function to download firmware Bluetooth: btintel_pcie: Add support for PCIe transport Bluetooth: btintel: Export few static functions Bluetooth: HCI: Remove HCI_AMP support Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() Bluetooth: qca: Fix error code in qca_read_fw_build_info() Bluetooth: hci_conn: Use __counted_by() and avoid -Wfamnae warning Bluetooth: btintel: Add support for Filmore Peak2 (BE201) Bluetooth: btintel: Add support for BlazarI LE Create Connection command timeout increased to 20 secs dt-bindings: net: bluetooth: Add MediaTek MT7921S SDIO Bluetooth Bluetooth: compute LE flow credits based on recvbuf space Bluetooth: hci_sync: Use cmd->num_cis instead of magic number ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2024-05-15 05:42:24 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2024-05-15 05:42:24 +0300
commit: 1b294a1f35616977caddaddf3e9d28e576a1adbc (patch)
tree: 723a406740083006b8f8724b5c5e532d4efa431d /drivers/net/ethernet
parent: b850dc206a57ae272c639e31ac202ec0c2f46960 (diff)
parent: 654de42f3fc6edc29d743c1dbcd1424f7793f63d (diff)
download: linux-1b294a1f35616977caddaddf3e9d28e576a1adbc.tar.xz
447 files changed, 14622 insertions, 9158 deletions
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index ba3e7aa1a28f..4725a8cfd695 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -31,9 +31,6 @@
    Setting to > 1512 effectively disables this feature. */
 static int rx_copybreak = 200;
 
-/* Allow setting MTU to a larger size, bypassing the normal ethernet setup. */
-static const int mtu = 1500;
-
 /* Maximum events (Rx packets, etc.) to handle at each interrupt. */
 static int max_interrupt_work = 20;
 
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index 5267e9dcd87e..be58dac0502a 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -502,7 +502,7 @@ static int el3_config(struct net_device *dev, struct ifmap *map)
 {
 	if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) {
 		if (map->port <= 3) {
-			dev->if_port = map->port;
+			WRITE_ONCE(dev->if_port, map->port);
 			netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
 			tc589_set_xcvr(dev, dev->if_port);
 		} else {
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 706bd59bf645..1fbab79e2be4 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -44,7 +44,7 @@ config 3C515
 
 config PCMCIA_3C574
 	tristate "3Com 3c574 PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	help
 	  Say Y here if you intend to attach a 3Com 3c574 or compatible PCMCIA
 	  (PC-card) Fast Ethernet card to your computer.
@@ -54,7 +54,7 @@ config PCMCIA_3C574
 
 config PCMCIA_3C589
 	tristate "3Com 3c589 PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	help
 	  Say Y here if you intend to attach a 3Com 3c589 or compatible PCMCIA
 	  (PC-card) Ethernet card to your computer.
diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig
index a4130e643342..345f250781c6 100644
--- a/drivers/net/ethernet/8390/Kconfig
+++ b/drivers/net/ethernet/8390/Kconfig
@@ -19,7 +19,7 @@ if NET_VENDOR_8390
 
 config PCMCIA_AXNET
 	tristate "Asix AX88190 PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	help
 	  Say Y here if you intend to attach an Asix AX88190-based PCMCIA
 	  (PC-card) Fast Ethernet card to your computer.  These cards are
@@ -117,7 +117,7 @@ config NE2000
 
 config NE2K_PCI
 	tristate "PCI NE2000 and clones support (see help)"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	select CRC32
 	help
 	  This driver is for NE2000 compatible PCI cards. It will not work
@@ -146,7 +146,7 @@ config APNE
 
 config PCMCIA_PCNET
 	tristate "NE2000 compatible PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	select CRC32
 	help
 	  Say Y here if you intend to attach an NE2000 compatible PCMCIA
diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c
index 05d39ecb97ff..e876fe52399a 100644
--- a/drivers/net/ethernet/8390/etherh.c
+++ b/drivers/net/ethernet/8390/etherh.c
@@ -258,7 +258,7 @@ static int etherh_set_config(struct net_device *dev, struct ifmap *map)
 		 * media type, turn off automedia detection.
 		 */
 		dev->flags &= ~IFF_AUTOMEDIA;
-		dev->if_port = map->port;
+		WRITE_ONCE(dev->if_port, map->port);
 		break;
 
 	default:
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 9bd5e991f1e5..780fb4afb6af 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -994,7 +994,7 @@ static int set_config(struct net_device *dev, struct ifmap *map)
 	    return -EOPNOTSUPP;
 	else if ((map->port < 1) || (map->port > 2))
 	    return -EINVAL;
-	dev->if_port = map->port;
+	WRITE_ONCE(dev->if_port, map->port);
 	netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
 	NS8390_init(dev, 1);
     }
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 8b4ef5121308..0713f1e2c7f3 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -11,10 +11,10 @@
 #include <linux/crc8.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/gpio/consumer.h>
 #include <linux/if_bridge.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
-#include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/mii.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 3d9220f9c9fe..b325e0cef120 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3852,7 +3852,7 @@ static int et131x_change_mtu(struct net_device *netdev, int new_mtu)
 
 	et131x_disable_txrx(netdev);
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	et131x_adapter_memory_free(adapter);
 
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index eafef84fe3be..3d8ac63132fb 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -2539,7 +2539,7 @@ static int ace_change_mtu(struct net_device *dev, int new_mtu)
 	struct ace_regs __iomem *regs = ap->regs;
 
 	writel(new_mtu + ETH_HLEN + 4, &regs->IfMtu);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (new_mtu > ACE_STD_MTU) {
 		if (!(ap->jumbo)) {
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 1c8763be0e4b..3c112c18ae6a 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -788,7 +788,7 @@ static int tse_change_mtu(struct net_device *dev, int new_mtu)
 		return -EBUSY;
 	}
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	netdev_update_features(dev);
 
 	return 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index fea57eb8e58b..924f03f5a6c7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -47,7 +47,7 @@
 /* ENA adaptive interrupt moderation settings */
 
 #define ENA_INTR_INITIAL_TX_INTERVAL_USECS 64
-#define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0
+#define ENA_INTR_INITIAL_RX_INTERVAL_USECS 20
 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1
 
 #define ENA_HASH_KEY_SIZE 40
@@ -305,6 +305,8 @@ struct ena_com_dev {
 	u16 stats_func; /* Selected function for extended statistic dump */
 	u16 stats_queue; /* Selected queue for extended statistic dump */
 
+	u32 ena_min_poll_delay_us;
+
 	struct ena_com_mmio_read mmio_read;
 
 	struct ena_rss rss;
@@ -325,8 +327,6 @@ struct ena_com_dev {
 	struct ena_intr_moder_entry *intr_moder_tbl;
 
 	struct ena_com_llq_info llq_info;
-
-	u32 ena_min_poll_delay_us;
 };
 
 struct ena_com_dev_get_features_ctx {
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 933e619b3a31..4c6e07aa4bbb 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -229,30 +229,43 @@ static struct ena_eth_io_rx_cdesc_base *
 		idx * io_cq->cdesc_entry_size_in_bytes);
 }
 
-static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
-					   u16 *first_cdesc_idx)
+static int ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
+				    u16 *first_cdesc_idx,
+				    u16 *num_descs)
 {
+	u16 count = io_cq->cur_rx_pkt_cdesc_count, head_masked;
 	struct ena_eth_io_rx_cdesc_base *cdesc;
-	u16 count = 0, head_masked;
 	u32 last = 0;
 
 	do {
+		u32 status;
+
 		cdesc = ena_com_get_next_rx_cdesc(io_cq);
 		if (!cdesc)
 			break;
+		status = READ_ONCE(cdesc->status);
 
 		ena_com_cq_inc_head(io_cq);
+		if (unlikely((status & ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK) >>
+		    ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT && count != 0)) {
+			struct ena_com_dev *dev = ena_com_io_cq_to_ena_dev(io_cq);
+
+			netdev_err(dev->net_device,
+				   "First bit is on in descriptor #%d on q_id: %d, req_id: %u\n",
+				   count, io_cq->qid, cdesc->req_id);
+			return -EFAULT;
+		}
 		count++;
-		last = (READ_ONCE(cdesc->status) & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >>
-		       ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT;
+		last = (status & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >>
+			ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT;
 	} while (!last);
 
 	if (last) {
 		*first_cdesc_idx = io_cq->cur_rx_pkt_cdesc_start_idx;
-		count += io_cq->cur_rx_pkt_cdesc_count;
 
 		head_masked = io_cq->head & (io_cq->q_depth - 1);
 
+		*num_descs = count;
 		io_cq->cur_rx_pkt_cdesc_count = 0;
 		io_cq->cur_rx_pkt_cdesc_start_idx = head_masked;
 
@@ -260,11 +273,11 @@ static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
 			   "ENA q_id: %d packets were completed. first desc idx %u descs# %d\n",
 			   io_cq->qid, *first_cdesc_idx, count);
 	} else {
-		io_cq->cur_rx_pkt_cdesc_count += count;
-		count = 0;
+		io_cq->cur_rx_pkt_cdesc_count = count;
+		*num_descs = 0;
 	}
 
-	return count;
+	return 0;
 }
 
 static int ena_com_create_meta(struct ena_com_io_sq *io_sq,
@@ -539,10 +552,14 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq,
 	u16 cdesc_idx = 0;
 	u16 nb_hw_desc;
 	u16 i = 0;
+	int rc;
 
 	WARN(io_cq->direction != ENA_COM_IO_QUEUE_DIRECTION_RX, "wrong Q type");
 
-	nb_hw_desc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx);
+	rc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx, &nb_hw_desc);
+	if (unlikely(rc != 0))
+		return -EFAULT;
+
 	if (nb_hw_desc == 0) {
 		ena_rx_ctx->descs = nb_hw_desc;
 		return 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index 72b019758caa..449bc4960ccc 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -47,7 +47,7 @@ struct ena_com_rx_ctx {
 	bool frag;
 	u32 hash;
 	u16 descs;
-	int max_bufs;
+	u16 max_bufs;
 	u8 pkt_offset;
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 0cb6cc1cef56..b24cc3f05248 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -49,6 +49,7 @@ static const struct ena_stats ena_stats_global_strings[] = {
 	ENA_STAT_GLOBAL_ENTRY(interface_up),
 	ENA_STAT_GLOBAL_ENTRY(interface_down),
 	ENA_STAT_GLOBAL_ENTRY(admin_q_pause),
+	ENA_STAT_GLOBAL_ENTRY(reset_fail),
 };
 
 static const struct ena_stats ena_stats_eni_strings[] = {
@@ -459,10 +460,18 @@ static void ena_get_drvinfo(struct net_device *dev,
 			    struct ethtool_drvinfo *info)
 {
 	struct ena_adapter *adapter = netdev_priv(dev);
-
-	strscpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
-	strscpy(info->bus_info, pci_name(adapter->pdev),
-		sizeof(info->bus_info));
+	ssize_t ret = 0;
+
+	ret = strscpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	if (ret < 0)
+		netif_dbg(adapter, drv, dev,
+			  "module name will be truncated, status = %zd\n", ret);
+
+	ret = strscpy(info->bus_info, pci_name(adapter->pdev),
+		      sizeof(info->bus_info));
+	if (ret < 0)
+		netif_dbg(adapter, drv, dev,
+			  "bus info will be truncated, status = %zd\n", ret);
 }
 
 static void ena_get_ringparam(struct net_device *netdev,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index be5acfa41ee0..184b6e6cbed4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -42,7 +42,7 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl);
 
 static int ena_rss_init_default(struct ena_adapter *adapter);
 static void check_for_admin_com_state(struct ena_adapter *adapter);
-static void ena_destroy_device(struct ena_adapter *adapter, bool graceful);
+static int ena_destroy_device(struct ena_adapter *adapter, bool graceful);
 static int ena_restore_device(struct ena_adapter *adapter);
 
 static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -104,7 +104,7 @@ static int ena_change_mtu(struct net_device *dev, int new_mtu)
 	if (!ret) {
 		netif_dbg(adapter, drv, dev, "Set MTU to %d\n", new_mtu);
 		update_rx_ring_mtu(adapter, new_mtu);
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 	} else {
 		netif_err(adapter, drv, dev, "Failed to set MTU to %d\n",
 			  new_mtu);
@@ -1347,6 +1347,8 @@ error:
 	if (rc == -ENOSPC) {
 		ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, &rx_ring->syncp);
 		ena_reset_device(adapter, ENA_REGS_RESET_TOO_MANY_RX_DESCS);
+	} else if (rc == -EFAULT) {
+		ena_reset_device(adapter, ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED);
 	} else {
 		ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1,
 				  &rx_ring->syncp);
@@ -2701,6 +2703,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd
 {
 	struct device *dev = &pdev->dev;
 	struct ena_admin_host_info *host_info;
+	ssize_t ret;
 	int rc;
 
 	/* Allocate only the host info */
@@ -2715,11 +2718,19 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd
 	host_info->bdf = pci_dev_id(pdev);
 	host_info->os_type = ENA_ADMIN_OS_LINUX;
 	host_info->kernel_ver = LINUX_VERSION_CODE;
-	strscpy(host_info->kernel_ver_str, utsname()->version,
-		sizeof(host_info->kernel_ver_str) - 1);
+	ret = strscpy(host_info->kernel_ver_str, utsname()->version,
+		      sizeof(host_info->kernel_ver_str));
+	if (ret < 0)
+		dev_dbg(dev,
+			"kernel version string will be truncated, status = %zd\n", ret);
+
 	host_info->os_dist = 0;
-	strscpy(host_info->os_dist_str, utsname()->release,
-		sizeof(host_info->os_dist_str));
+	ret = strscpy(host_info->os_dist_str, utsname()->release,
+		      sizeof(host_info->os_dist_str));
+	if (ret < 0)
+		dev_dbg(dev,
+			"OS distribution string will be truncated, status = %zd\n", ret);
+
 	host_info->driver_version =
 		(DRV_MODULE_GEN_MAJOR) |
 		(DRV_MODULE_GEN_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) |
@@ -3235,14 +3246,15 @@ err_disable_msix:
 	return rc;
 }
 
-static void ena_destroy_device(struct ena_adapter *adapter, bool graceful)
+static int ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	bool dev_up;
+	int rc = 0;
 
 	if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
-		return;
+		return 0;
 
 	netif_carrier_off(netdev);
 
@@ -3260,7 +3272,7 @@ static void ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 	 *  and device is up, ena_down() already reset the device.
 	 */
 	if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up))
-		ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason);
+		rc = ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason);
 
 	ena_free_mgmnt_irq(adapter);
 
@@ -3279,6 +3291,8 @@ static void ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 
 	clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 	clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	return rc;
 }
 
 static int ena_restore_device(struct ena_adapter *adapter)
@@ -3355,14 +3369,17 @@ err:
 
 static void ena_fw_reset_device(struct work_struct *work)
 {
+	int rc = 0;
+
 	struct ena_adapter *adapter =
 		container_of(work, struct ena_adapter, reset_task);
 
 	rtnl_lock();
 
 	if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
-		ena_destroy_device(adapter, false);
-		ena_restore_device(adapter);
+		rc |= ena_destroy_device(adapter, false);
+		rc |= ena_restore_device(adapter);
+		adapter->dev_stats.reset_fail += !!rc;
 
 		dev_err(&adapter->pdev->dev, "Device reset completed successfully\n");
 	}
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 6d2cc20210cc..d59509747d1a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -290,6 +290,7 @@ struct ena_stats_dev {
 	u64 admin_q_pause;
 	u64 rx_drops;
 	u64 tx_drops;
+	u64 reset_fail;
 };
 
 enum ena_flags_t {
diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index 2c3d6a77ea79..a2efebafd686 100644
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -22,6 +22,7 @@ enum ena_regs_reset_reason_types {
 	ENA_REGS_RESET_GENERIC                      = 13,
 	ENA_REGS_RESET_MISS_INTERRUPT               = 14,
 	ENA_REGS_RESET_SUSPECTED_POLL_STARVATION    = 15,
+	ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED	    = 16,
 };
 
 /* ena_registers offsets */
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index f8cc8925161c..b39c6f3e1eda 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -56,7 +56,7 @@ config LANCE
 
 config PCNET32
 	tristate "AMD PCnet32 PCI support"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	select CRC32
 	select MII
 	help
@@ -122,7 +122,7 @@ config MVME147_NET
 
 config PCMCIA_NMCLAN
 	tristate "New Media PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	help
 	  Say Y here if you intend to attach a New Media Ethernet or LiveWire
 	  PCMCIA (PC-card) Ethernet card to your computer.
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index ea6cfc2095e1..f64f96fa17cf 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1520,9 +1520,9 @@ static int amd8111e_change_mtu(struct net_device *dev, int new_mtu)
 
 	if (!netif_running(dev)) {
 		/* new_mtu will be used
-		 * when device starts netxt time
+		 * when device starts next time
 		 */
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		return 0;
 	}
 
@@ -1531,7 +1531,7 @@ static int amd8111e_change_mtu(struct net_device *dev, int new_mtu)
 	/* stop the chip */
 	writel(RUN, lp->mmio + CMD0);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	err = amd8111e_restart(dev);
 	spin_unlock_irq(&lp->lock);
@@ -1796,7 +1796,6 @@ static int amd8111e_probe_one(struct pci_dev *pdev,
 	lp = netdev_priv(dev);
 	lp->pci_dev = pdev;
 	lp->amd8111e_net_dev = dev;
-	lp->pm_cap = pdev->pm_cap;
 
 	spin_lock_init(&lp->lock);
 
diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h
index 9d570adb295b..305232f5476d 100644
--- a/drivers/net/ethernet/amd/amd8111e.h
+++ b/drivers/net/ethernet/amd/amd8111e.h
@@ -764,7 +764,6 @@ struct amd8111e_priv{
 	u32 ext_phy_id;
 
 	struct amd8111e_link_config link_config;
-	int pm_cap;
 
 	struct net_device *next;
 	int mii;
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 0dd391c84c13..37054a670407 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -760,7 +760,7 @@ static int mace_config(struct net_device *dev, struct ifmap *map)
 {
   if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) {
     if (map->port <= 2) {
-      dev->if_port = map->port;
+      WRITE_ONCE(dev->if_port, map->port);
       netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
     } else
       return -EINVAL;
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index a3e17a0c187a..14522d6d5f86 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -256,7 +256,8 @@ int pdsc_dl_flash_update(struct devlink *dl,
 int pdsc_dl_enable_get(struct devlink *dl, u32 id,
 		       struct devlink_param_gset_ctx *ctx);
 int pdsc_dl_enable_set(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx);
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack);
 int pdsc_dl_enable_validate(struct devlink *dl, u32 id,
 			    union devlink_param_value val,
 			    struct netlink_ext_ack *extack);
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 54864f27c87a..2681889162a2 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -37,7 +37,8 @@ int pdsc_dl_enable_get(struct devlink *dl, u32 id,
 }
 
 int pdsc_dl_enable_set(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx)
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack)
 {
 	struct pdsc *pdsc = devlink_priv(dl);
 	struct pdsc_viftype *vt_entry;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 6b73648b3779..c4a4e316683f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2070,7 +2070,7 @@ static int xgbe_change_mtu(struct net_device *netdev, int mtu)
 		return ret;
 
 	pdata->rx_buf_size = ret;
-	netdev->mtu = mtu;
+	WRITE_ONCE(netdev->mtu, mtu);
 
 	xgbe_restart_dev(pdata);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
index 9131020d06af..7912b3b45148 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
@@ -538,7 +538,6 @@ static const struct xgbe_version_data xgbe_v1 = {
 	.tx_tstamp_workaround		= 1,
 };
 
-#ifdef CONFIG_ACPI
 static const struct acpi_device_id xgbe_acpi_match[] = {
 	{ .id = "AMDI8001",
 	  .driver_data = (kernel_ulong_t)&xgbe_v1 },
@@ -546,9 +545,7 @@ static const struct acpi_device_id xgbe_acpi_match[] = {
 };
 
 MODULE_DEVICE_TABLE(acpi, xgbe_acpi_match);
-#endif
 
-#ifdef CONFIG_OF
 static const struct of_device_id xgbe_of_match[] = {
 	{ .compatible = "amd,xgbe-seattle-v1a",
 	  .data = &xgbe_v1 },
@@ -556,7 +553,6 @@ static const struct of_device_id xgbe_of_match[] = {
 };
 
 MODULE_DEVICE_TABLE(of, xgbe_of_match);
-#endif
 
 static SIMPLE_DEV_PM_OPS(xgbe_platform_pm_ops,
 			 xgbe_platform_suspend, xgbe_platform_resume);
@@ -564,12 +560,8 @@ static SIMPLE_DEV_PM_OPS(xgbe_platform_pm_ops,
 static struct platform_driver xgbe_driver = {
 	.driver = {
 		.name = XGBE_DRV_NAME,
-#ifdef CONFIG_ACPI
 		.acpi_match_table = xgbe_acpi_match,
-#endif
-#ifdef CONFIG_OF
 		.of_match_table = xgbe_of_match,
-#endif
 		.pm = &xgbe_platform_pm_ops,
 	},
 	.probe = xgbe_platform_probe,
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 44900026d11b..4af9d89d5f88 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1530,7 +1530,7 @@ static int xgene_change_mtu(struct net_device *ndev, int new_mtu)
 	frame_size = (new_mtu > ETH_DATA_LEN) ? (new_mtu + 18) : 0x600;
 
 	xgene_enet_close(ndev);
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 	pdata->mac_ops->set_framesize(pdata, frame_size);
 	xgene_enet_open(ndev);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 0b2a52199914..c1d1673c5749 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -146,7 +146,7 @@ static int aq_ndev_change_mtu(struct net_device *ndev, int new_mtu)
 
 	if (err < 0)
 		goto err_exit;
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 err_exit:
 	return err;
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 0f2f400b5bc4..a38be924cdaa 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1788,7 +1788,7 @@ static int ag71xx_change_mtu(struct net_device *ndev, int new_mtu)
 {
 	struct ag71xx *ag = netdev_priv(ndev);
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 	ag71xx_wr(ag, AG71XX_REG_MAC_MFL,
 		  ag71xx_max_frame_len(ndev->mtu));
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 49bb9a8f00e6..3d28654e5df7 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1176,7 +1176,7 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
 
-	netdev->mtu = mtu;
+	WRITE_ONCE(netdev->mtu, mtu);
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
 	netdev_update_features(netdev);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 46cdc32b4e31..c571614b1d50 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -561,7 +561,7 @@ static int atl1c_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev)) {
 		while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
 			msleep(1);
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		adapter->hw.max_frame_size = new_mtu;
 		atl1c_set_rxbufsize(adapter, netdev);
 		atl1c_down(adapter);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 5f2a6fcba967..9b778b34b67e 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -428,7 +428,7 @@ static int atl1e_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev)) {
 		while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
 			msleep(1);
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		adapter->hw.max_frame_size = new_mtu;
 		adapter->hw.rx_jumbo_th = (max_frame + 7) >> 3;
 		atl1e_down(adapter);
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index a9014d7932db..3afd3627ce48 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2687,7 +2687,7 @@ static int atl1_change_mtu(struct net_device *netdev, int new_mtu)
 	adapter->rx_buffer_len = (max_frame + 7) & ~7;
 	adapter->hw.rx_jumbo_th = adapter->rx_buffer_len / 8;
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	if (netif_running(netdev)) {
 		atl1_down(adapter);
 		atl1_up(adapter);
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index bcfc9488125b..fa9a4919f25d 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -905,7 +905,7 @@ static int atl2_change_mtu(struct net_device *netdev, int new_mtu)
 	struct atl2_hw *hw = &adapter->hw;
 
 	/* set MTU */
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	hw->max_frame_size = new_mtu;
 	ATL2_WRITE_REG(hw, REG_MTU, new_mtu + ETH_HLEN +
 		       VLAN_HLEN + ETH_FCS_LEN);
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 1be6d14030bc..e5809ad5eb82 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1042,13 +1042,13 @@ static int b44_change_mtu(struct net_device *dev, int new_mtu)
 		/* We'll just catch it later when the
 		 * device is up'd.
 		 */
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		return 0;
 	}
 
 	spin_lock_irq(&bp->lock);
 	b44_halt(bp);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	b44_init_rings(bp);
 	b44_init_hw(bp, B44_FULL_RESET);
 	spin_unlock_irq(&bp->lock);
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 3196c4dea076..3c0e3b9828be 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1652,7 +1652,7 @@ static int bcm_enet_change_mtu(struct net_device *dev, int new_mtu)
 	priv->rx_frag_size = SKB_DATA_ALIGN(priv->rx_buf_offset + priv->rx_buf_size) +
 					    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index b65b8592ad75..6ec773e61182 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -7912,7 +7912,7 @@ bnx2_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return bnx2_change_ring_size(bp, bp->rx_ring_size, bp->tx_ring_size,
 				     false);
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index c9b6acd8c892..a8e07e51418f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4902,7 +4902,7 @@ int bnx2x_change_mtu(struct net_device *dev, int new_mtu)
 	 * because the actual alloc size is
 	 * only updated as part of load
 	 */
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (!bnx2x_mtu_allows_gro(new_mtu))
 		dev->features &= ~NETIF_F_GRO_HW;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2c2ee79c4d77..c437ca1c0fd3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -76,7 +76,7 @@
 				 NETIF_MSG_TX_ERR)
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Broadcom BCM573xx network driver");
+MODULE_DESCRIPTION("Broadcom NetXtreme network driver");
 
 #define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN)
 #define BNXT_RX_DMA_OFFSET NET_SKB_PAD
@@ -137,6 +137,7 @@ static const struct {
 	[NETXTREME_E_VF_HV] = { "Broadcom NetXtreme-E Virtual Function for Hyper-V" },
 	[NETXTREME_E_P5_VF] = { "Broadcom BCM5750X NetXtreme-E Ethernet Virtual Function" },
 	[NETXTREME_E_P5_VF_HV] = { "Broadcom BCM5750X NetXtreme-E Virtual Function for Hyper-V" },
+	[NETXTREME_E_P7_VF] = { "Broadcom BCM5760X Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
@@ -211,6 +212,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x1807), .driver_data = NETXTREME_E_P5_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x1808), .driver_data = NETXTREME_E_P5_VF_HV },
 	{ PCI_VDEVICE(BROADCOM, 0x1809), .driver_data = NETXTREME_E_P5_VF_HV },
+	{ PCI_VDEVICE(BROADCOM, 0x1819), .driver_data = NETXTREME_E_P7_VF },
 	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
@@ -294,7 +296,7 @@ static bool bnxt_vf_pciid(enum board_idx idx)
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
 		idx == NETXTREME_S_VF || idx == NETXTREME_C_VF_HV ||
 		idx == NETXTREME_E_VF_HV || idx == NETXTREME_E_P5_VF ||
-		idx == NETXTREME_E_P5_VF_HV);
+		idx == NETXTREME_E_P5_VF_HV || idx == NETXTREME_E_P7_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -1296,9 +1298,9 @@ static int bnxt_agg_bufs_valid(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	return RX_AGG_CMP_VALID(agg, *raw_cons);
 }
 
-static inline struct sk_buff *bnxt_copy_skb(struct bnxt_napi *bnapi, u8 *data,
-					    unsigned int len,
-					    dma_addr_t mapping)
+static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data,
+				      unsigned int len,
+				      dma_addr_t mapping)
 {
 	struct bnxt *bp = bnapi->bp;
 	struct pci_dev *pdev = bp->pdev;
@@ -1318,6 +1320,39 @@ static inline struct sk_buff *bnxt_copy_skb(struct bnxt_napi *bnapi, u8 *data,
 				   bp->rx_dir);
 
 	skb_put(skb, len);
+
+	return skb;
+}
+
+static struct sk_buff *bnxt_copy_skb(struct bnxt_napi *bnapi, u8 *data,
+				     unsigned int len,
+				     dma_addr_t mapping)
+{
+	return bnxt_copy_data(bnapi, data, len, mapping);
+}
+
+static struct sk_buff *bnxt_copy_xdp(struct bnxt_napi *bnapi,
+				     struct xdp_buff *xdp,
+				     unsigned int len,
+				     dma_addr_t mapping)
+{
+	unsigned int metasize = 0;
+	u8 *data = xdp->data;
+	struct sk_buff *skb;
+
+	len = xdp->data_end - xdp->data_meta;
+	metasize = xdp->data - xdp->data_meta;
+	data = xdp->data_meta;
+
+	skb = bnxt_copy_data(bnapi, data, len, mapping);
+	if (!skb)
+		return skb;
+
+	if (metasize) {
+		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
+
 	return skb;
 }
 
@@ -1778,7 +1813,7 @@ 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->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+			cpr->sw_stats->rx.rx_oom_discards += 1;
 			return NULL;
 		}
 	} else {
@@ -1788,7 +1823,7 @@ 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->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+			cpr->sw_stats->rx.rx_oom_discards += 1;
 			return NULL;
 		}
 
@@ -1804,7 +1839,7 @@ 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->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+			cpr->sw_stats->rx.rx_oom_discards += 1;
 			return NULL;
 		}
 		skb_reserve(skb, bp->rx_offset);
@@ -1815,7 +1850,7 @@ 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->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+			cpr->sw_stats->rx.rx_oom_discards += 1;
 			return NULL;
 		}
 	}
@@ -2073,7 +2108,7 @@ 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++;
+			bnapi->cp_ring.sw_stats->rx.rx_buf_errors++;
 			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",
@@ -2101,14 +2136,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	if (xdp_active) {
-		if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &data_ptr, &len, event)) {
+		if (bnxt_rx_xdp(bp, rxr, cons, &xdp, data, &data_ptr, &len, event)) {
 			rc = 1;
 			goto next_rx;
 		}
 	}
 
 	if (len <= bp->rx_copy_thresh) {
-		skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
+		if (!xdp_active)
+			skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
+		else
+			skb = bnxt_copy_xdp(bnapi, &xdp, len, dma_addr);
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (!skb) {
 			if (agg_bufs) {
@@ -2186,7 +2224,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	} else {
 		if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L4_CS_ERR_BITS) {
 			if (dev->features & NETIF_F_RXCSUM)
-				bnapi->cp_ring.sw_stats.rx.rx_l4_csum_errors++;
+				bnapi->cp_ring.sw_stats->rx.rx_l4_csum_errors++;
 		}
 	}
 
@@ -2223,7 +2261,7 @@ next_rx_no_prod_no_len:
 	return rc;
 
 oom_next_rx:
-	cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+	cpr->sw_stats->rx.rx_oom_discards += 1;
 	rc = -ENOMEM;
 	goto next_rx;
 }
@@ -2272,7 +2310,7 @@ static int bnxt_force_rx_discard(struct bnxt *bp,
 	}
 	rc = bnxt_rx_pkt(bp, cpr, raw_cons, event);
 	if (rc && rc != -EBUSY)
-		cpr->bnapi->cp_ring.sw_stats.rx.rx_netpoll_discards += 1;
+		cpr->sw_stats->rx.rx_netpoll_discards += 1;
 	return rc;
 }
 
@@ -2481,6 +2519,9 @@ static bool bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2)
 		}
 		return false;
 	}
+	case ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED:
+		netdev_warn(bp->dev, "Speed change not supported with dual rate transceivers on this board\n");
+		break;
 	default:
 		netdev_err(bp->dev, "FW reported unknown error type %u\n",
 			   err_type);
@@ -3551,14 +3592,15 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 }
 
 static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
-				   struct bnxt_rx_ring_info *rxr)
+				   struct bnxt_rx_ring_info *rxr,
+				   int numa_node)
 {
 	struct page_pool_params pp = { 0 };
 
 	pp.pool_size = bp->rx_agg_ring_size;
 	if (BNXT_RX_PAGE_MODE(bp))
 		pp.pool_size += bp->rx_ring_size;
-	pp.nid = dev_to_node(&bp->pdev->dev);
+	pp.nid = numa_node;
 	pp.napi = &rxr->bnapi->napi;
 	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
@@ -3578,7 +3620,8 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 
 static int bnxt_alloc_rx_rings(struct bnxt *bp)
 {
-	int i, rc = 0, agg_rings = 0;
+	int numa_node = dev_to_node(&bp->pdev->dev);
+	int i, rc = 0, agg_rings = 0, cpu;
 
 	if (!bp->rx_ring)
 		return -ENOMEM;
@@ -3589,10 +3632,15 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring;
+		int cpu_node;
 
 		ring = &rxr->rx_ring_struct;
 
-		rc = bnxt_alloc_rx_page_pool(bp, rxr);
+		cpu = cpumask_local_spread(i, numa_node);
+		cpu_node = cpu_to_node(cpu);
+		netdev_dbg(bp->dev, "Allocating page pool for rx_ring[%d] on numa_node: %d\n",
+			   i, cpu_node);
+		rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node);
 		if (rc)
 			return rc;
 
@@ -3851,13 +3899,12 @@ static int bnxt_alloc_cp_sub_ring(struct bnxt *bp,
 static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
-	int i, j, rc, ulp_base_vec, ulp_msix;
+	int i, j, rc, 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, j = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr, *cpr2;
@@ -3876,10 +3923,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		if (rc)
 			return rc;
 
-		if (ulp_msix && i >= ulp_base_vec)
-			ring->map_idx = i + ulp_msix;
-		else
-			ring->map_idx = i;
+		ring->map_idx = ulp_msix + i;
 
 		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			continue;
@@ -3909,6 +3953,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 			if (rc)
 				return rc;
 			cpr2->bnapi = bnapi;
+			cpr2->sw_stats = cpr->sw_stats;
 			cpr2->cp_idx = k;
 			if (!k && rx) {
 				bp->rx_ring[i].rx_cpr = cpr2;
@@ -4233,6 +4278,7 @@ static void bnxt_init_vnics(struct bnxt *bp)
 		int j;
 
 		vnic->fw_vnic_id = INVALID_HW_RING_ID;
+		vnic->vnic_id = i;
 		for (j = 0; j < BNXT_MAX_CTX_PER_VNIC; j++)
 			vnic->fw_rss_cos_lb_ctx[j] = INVALID_HW_RING_ID;
 
@@ -4749,6 +4795,9 @@ static void bnxt_free_ring_stats(struct bnxt *bp)
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 
 		bnxt_free_stats_mem(bp, &cpr->stats);
+
+		kfree(cpr->sw_stats);
+		cpr->sw_stats = NULL;
 	}
 }
 
@@ -4763,6 +4812,10 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 
+		cpr->sw_stats = kzalloc(sizeof(*cpr->sw_stats), GFP_KERNEL);
+		if (!cpr->sw_stats)
+			return -ENOMEM;
+
 		cpr->stats.len = size;
 		rc = bnxt_alloc_stats_mem(bp, &cpr->stats, !i);
 		if (rc)
@@ -5780,8 +5833,22 @@ void bnxt_fill_ipv6_mask(__be32 mask[4])
 static void
 bnxt_cfg_rfs_ring_tbl_idx(struct bnxt *bp,
 			  struct hwrm_cfa_ntuple_filter_alloc_input *req,
-			  u16 rxq)
+			  struct bnxt_ntuple_filter *fltr)
 {
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+	u16 rxq = fltr->base.rxq;
+
+	if (fltr->base.flags & BNXT_ACT_RSS_CTX) {
+		list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list) {
+			if (rss_ctx->index == fltr->base.fw_vnic_id) {
+				struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+				req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
+				break;
+			}
+		}
+		return;
+	}
 	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
 		struct bnxt_vnic_info *vnic;
 		u32 enables;
@@ -5822,7 +5889,7 @@ int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 		req->flags =
 			cpu_to_le32(CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP);
 	} else if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
-		bnxt_cfg_rfs_ring_tbl_idx(bp, req, fltr->base.rxq);
+		bnxt_cfg_rfs_ring_tbl_idx(bp, req, fltr);
 	} else {
 		vnic = &bp->vnic_info[fltr->base.rxq + 1];
 		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
@@ -5930,9 +5997,9 @@ static void bnxt_hwrm_vnic_update_tunl_tpa(struct bnxt *bp,
 	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)
+int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			   u32 tpa_flags)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	u16 max_aggs = VNIC_TPA_CFG_REQ_MAX_AGGS_MAX;
 	struct hwrm_vnic_tpa_cfg_input *req;
 	int rc;
@@ -6017,9 +6084,10 @@ static u16 bnxt_cp_ring_for_tx(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 		return bnxt_cp_ring_from_grp(bp, &txr->tx_ring_struct);
 }
 
-static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
+int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx)
 {
 	int entries;
+	u16 *tbl;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		entries = BNXT_MAX_RSS_TABLE_ENTRIES_P5;
@@ -6027,16 +6095,22 @@ static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
 		entries = HW_HASH_INDEX_SIZE;
 
 	bp->rss_indir_tbl_entries = entries;
-	bp->rss_indir_tbl = kmalloc_array(entries, sizeof(*bp->rss_indir_tbl),
-					  GFP_KERNEL);
-	if (!bp->rss_indir_tbl)
+	tbl = kmalloc_array(entries, sizeof(*bp->rss_indir_tbl), GFP_KERNEL);
+	if (!tbl)
 		return -ENOMEM;
+
+	if (rss_ctx)
+		rss_ctx->rss_indir_tbl = tbl;
+	else
+		bp->rss_indir_tbl = tbl;
+
 	return 0;
 }
 
-static void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp)
+void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx)
 {
 	u16 max_rings, max_entries, pad, i;
+	u16 *rss_indir_tbl;
 
 	if (!bp->rx_nr_rings)
 		return;
@@ -6047,13 +6121,17 @@ static void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp)
 		max_rings = bp->rx_nr_rings;
 
 	max_entries = bnxt_get_rxfh_indir_size(bp->dev);
+	if (rss_ctx)
+		rss_indir_tbl = &rss_ctx->rss_indir_tbl[0];
+	else
+		rss_indir_tbl = &bp->rss_indir_tbl[0];
 
 	for (i = 0; i < max_entries; i++)
-		bp->rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, max_rings);
+		rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, max_rings);
 
 	pad = bp->rss_indir_tbl_entries - max_entries;
 	if (pad)
-		memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
+		memset(&rss_indir_tbl[i], 0, pad * sizeof(u16));
 }
 
 static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
@@ -6109,6 +6187,8 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
 
 		if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
 			j = ethtool_rxfh_indir_default(i, bp->rx_nr_rings);
+		else if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			j = vnic->rss_ctx->rss_indir_tbl[i];
 		else
 			j = bp->rss_indir_tbl[i];
 		rxr = &bp->rx_ring[j];
@@ -6146,9 +6226,9 @@ __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
 	req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr);
 }
 
-static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
+static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  bool set_rss)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_rss_cfg_input *req;
 	int rc;
 
@@ -6166,9 +6246,9 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	return hwrm_req_send(bp, req);
 }
 
-static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss)
+static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp,
+				     struct bnxt_vnic_info *vnic, bool set_rss)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_rss_cfg_input *req;
 	dma_addr_t ring_tbl_map;
 	u32 i, nr_ctxs;
@@ -6221,9 +6301,8 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp)
 	hwrm_req_drop(bp, req);
 }
 
-static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
+static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_plcmodes_cfg_input *req;
 	int rc;
 
@@ -6248,7 +6327,8 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
 	return hwrm_req_send(bp, req);
 }
 
-static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id,
+static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp,
+					struct bnxt_vnic_info *vnic,
 					u16 ctx_idx)
 {
 	struct hwrm_vnic_rss_cos_lb_ctx_free_input *req;
@@ -6257,10 +6337,10 @@ static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id,
 		return;
 
 	req->rss_cos_lb_ctx_id =
-		cpu_to_le16(bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx]);
+		cpu_to_le16(vnic->fw_rss_cos_lb_ctx[ctx_idx]);
 
 	hwrm_req_send(bp, req);
-	bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
+	vnic->fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
 }
 
 static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp)
@@ -6272,13 +6352,14 @@ static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp)
 
 		for (j = 0; j < BNXT_MAX_CTX_PER_VNIC; j++) {
 			if (vnic->fw_rss_cos_lb_ctx[j] != INVALID_HW_RING_ID)
-				bnxt_hwrm_vnic_ctx_free_one(bp, i, j);
+				bnxt_hwrm_vnic_ctx_free_one(bp, vnic, j);
 		}
 	}
 	bp->rsscos_nr_ctxs = 0;
 }
 
-static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
+static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp,
+				    struct bnxt_vnic_info *vnic, u16 ctx_idx)
 {
 	struct hwrm_vnic_rss_cos_lb_ctx_alloc_output *resp;
 	struct hwrm_vnic_rss_cos_lb_ctx_alloc_input *req;
@@ -6291,7 +6372,7 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
 	if (!rc)
-		bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] =
+		vnic->fw_rss_cos_lb_ctx[ctx_idx] =
 			le16_to_cpu(resp->rss_cos_lb_ctx_id);
 	hwrm_req_drop(bp, req);
 
@@ -6305,10 +6386,9 @@ static u32 bnxt_get_roce_vnic_mode(struct bnxt *bp)
 	return VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE;
 }
 
-int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
+int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	struct bnxt_vnic_info *vnic0 = &bp->vnic_info[BNXT_VNIC_DEFAULT];
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_cfg_input *req;
 	unsigned int ring = 0, grp_idx;
 	u16 def_vlan = 0;
@@ -6356,8 +6436,8 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	if (vnic->flags & BNXT_VNIC_RSS_FLAG)
 		ring = 0;
 	else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
-		ring = vnic_id - 1;
-	else if ((vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
+		ring = vnic->vnic_id - 1;
+	else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
 		ring = bp->rx_nr_rings - 1;
 
 	grp_idx = bp->rx_ring[ring].bnapi->index;
@@ -6373,25 +6453,25 @@ vnic_mru:
 #endif
 	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
 		req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
-	if (!vnic_id && bnxt_ulp_registered(bp->edev))
+	if (vnic->vnic_id == BNXT_VNIC_DEFAULT && bnxt_ulp_registered(bp->edev))
 		req->flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp));
 
 	return hwrm_req_send(bp, req);
 }
 
-static void bnxt_hwrm_vnic_free_one(struct bnxt *bp, u16 vnic_id)
+static void bnxt_hwrm_vnic_free_one(struct bnxt *bp,
+				    struct bnxt_vnic_info *vnic)
 {
-	if (bp->vnic_info[vnic_id].fw_vnic_id != INVALID_HW_RING_ID) {
+	if (vnic->fw_vnic_id != INVALID_HW_RING_ID) {
 		struct hwrm_vnic_free_input *req;
 
 		if (hwrm_req_init(bp, req, HWRM_VNIC_FREE))
 			return;
 
-		req->vnic_id =
-			cpu_to_le32(bp->vnic_info[vnic_id].fw_vnic_id);
+		req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
 
 		hwrm_req_send(bp, req);
-		bp->vnic_info[vnic_id].fw_vnic_id = INVALID_HW_RING_ID;
+		vnic->fw_vnic_id = INVALID_HW_RING_ID;
 	}
 }
 
@@ -6400,15 +6480,14 @@ static void bnxt_hwrm_vnic_free(struct bnxt *bp)
 	u16 i;
 
 	for (i = 0; i < bp->nr_vnics; i++)
-		bnxt_hwrm_vnic_free_one(bp, i);
+		bnxt_hwrm_vnic_free_one(bp, &bp->vnic_info[i]);
 }
 
-static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
-				unsigned int start_rx_ring_idx,
-				unsigned int nr_rings)
+int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			 unsigned int start_rx_ring_idx,
+			 unsigned int nr_rings)
 {
 	unsigned int i, j, grp_idx, end_idx = start_rx_ring_idx + nr_rings;
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_alloc_output *resp;
 	struct hwrm_vnic_alloc_input *req;
 	int rc;
@@ -6434,7 +6513,7 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 vnic_no_ring_grps:
 	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++)
 		vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
-	if (vnic_id == BNXT_VNIC_DEFAULT)
+	if (vnic->vnic_id == BNXT_VNIC_DEFAULT)
 		req->flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT);
 
 	resp = hwrm_req_hold(bp, req);
@@ -7266,17 +7345,7 @@ static int bnxt_hwrm_reserve_rings(struct bnxt *bp, struct bnxt_hw_rings *hwr)
 
 int bnxt_nq_rings_in_use(struct bnxt *bp)
 {
-	int cp = bp->cp_nr_rings;
-	int ulp_msix, ulp_base;
-
-	ulp_msix = bnxt_get_ulp_msix_num(bp);
-	if (ulp_msix) {
-		ulp_base = bnxt_get_ulp_msix_base(bp);
-		cp += ulp_msix;
-		if ((ulp_base + ulp_msix) > cp)
-			cp = ulp_base + ulp_msix;
-	}
-	return cp;
+	return bp->cp_nr_rings + bnxt_get_ulp_msix_num(bp);
 }
 
 static int bnxt_cp_rings_in_use(struct bnxt *bp)
@@ -7292,16 +7361,7 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 
 static int bnxt_get_func_stat_ctxs(struct bnxt *bp)
 {
-	int ulp_stat = bnxt_get_ulp_stat_ctxs(bp);
-	int cp = bp->cp_nr_rings;
-
-	if (!ulp_stat)
-		return cp;
-
-	if (bnxt_nq_rings_in_use(bp) > cp + bnxt_get_ulp_msix_num(bp))
-		return bnxt_get_ulp_msix_base(bp) + ulp_stat;
-
-	return cp + ulp_stat;
+	return bp->cp_nr_rings + bnxt_get_ulp_stat_ctxs(bp);
 }
 
 static int bnxt_get_total_rss_ctxs(struct bnxt *bp, struct bnxt_hw_rings *hwr)
@@ -7333,7 +7393,7 @@ static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp)
 	if (hw_resc->resv_rx_rings != bp->rx_nr_rings) {
 		hw_resc->resv_rx_rings = bp->rx_nr_rings;
 		if (!netif_is_rxfh_configured(bp->dev))
-			bnxt_set_dflt_rss_indir_tbl(bp);
+			bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 	}
 }
 
@@ -7341,7 +7401,7 @@ static int bnxt_get_total_vnics(struct bnxt *bp, int rx_rings)
 {
 	if (bp->flags & BNXT_FLAG_RFS) {
 		if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
-			return 2;
+			return 2 + bp->num_rss_ctx;
 		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			return rx_rings + 1;
 	}
@@ -7409,17 +7469,32 @@ static bool bnxt_rings_ok(struct bnxt *bp, struct bnxt_hw_rings *hwr)
 	       hwr->stat && (hwr->cp_p5 || !(bp->flags & BNXT_FLAG_CHIP_P5_PLUS));
 }
 
+static int bnxt_get_avail_msix(struct bnxt *bp, int num);
+
 static int __bnxt_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_rings hwr = {0};
+	int cp = bp->cp_nr_rings;
 	int rx_rings, rc;
+	int ulp_msix = 0;
 	bool sh = false;
 	int tx_cp;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
-	hwr.cp = bnxt_nq_rings_in_use(bp);
+	if (BNXT_NEW_RM(bp) && !bnxt_ulp_registered(bp->edev)) {
+		ulp_msix = bnxt_get_avail_msix(bp, bp->ulp_num_msix_want);
+		if (!ulp_msix)
+			bnxt_set_ulp_stat_ctxs(bp, 0);
+
+		if (ulp_msix > bp->ulp_num_msix_want)
+			ulp_msix = bp->ulp_num_msix_want;
+		hwr.cp = cp + ulp_msix;
+	} else {
+		hwr.cp = bnxt_nq_rings_in_use(bp);
+	}
+
 	hwr.tx = bp->tx_nr_rings;
 	hwr.rx = bp->rx_nr_rings;
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -7489,7 +7564,20 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		return -ENOMEM;
 
 	if (!netif_is_rxfh_configured(bp->dev))
-		bnxt_set_dflt_rss_indir_tbl(bp);
+		bnxt_set_dflt_rss_indir_tbl(bp, NULL);
+
+	if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {
+		int resv_msix, resv_ctx, ulp_ctxs;
+		struct bnxt_hw_resc *hw_resc;
+
+		hw_resc = &bp->hw_resc;
+		resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings;
+		ulp_msix = min_t(int, resv_msix, ulp_msix);
+		bnxt_set_ulp_msix_num(bp, ulp_msix);
+		resv_ctx = hw_resc->resv_stat_ctxs  - bp->cp_nr_rings;
+		ulp_ctxs = min(resv_ctx, bnxt_get_ulp_stat_ctxs(bp));
+		bnxt_set_ulp_stat_ctxs(bp, ulp_ctxs);
+	}
 
 	return rc;
 }
@@ -9668,7 +9756,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
-		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
+		rc = bnxt_hwrm_vnic_set_tpa(bp, &bp->vnic_info[i], tpa_flags);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
 				   i, rc);
@@ -9683,7 +9771,7 @@ static void bnxt_hwrm_clear_vnic_rss(struct bnxt *bp)
 	int i;
 
 	for (i = 0; i < bp->nr_vnics; i++)
-		bnxt_hwrm_vnic_set_rss(bp, i, false);
+		bnxt_hwrm_vnic_set_rss(bp, &bp->vnic_info[i], false);
 }
 
 static void bnxt_clear_vnic(struct bnxt *bp)
@@ -9761,28 +9849,27 @@ static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size)
 	return hwrm_req_send(bp, req);
 }
 
-static int __bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
+static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	int rc;
 
 	if (vnic->flags & BNXT_VNIC_RFS_NEW_RSS_FLAG)
 		goto skip_rss_ctx;
 
 	/* allocate context for vnic */
-	rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 0);
+	rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, 0);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 	bp->rsscos_nr_ctxs++;
 
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
-		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 1);
+		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, 1);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d cos ctx alloc failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 			goto vnic_setup_err;
 		}
 		bp->rsscos_nr_ctxs++;
@@ -9790,26 +9877,26 @@ static int __bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 
 skip_rss_ctx:
 	/* configure default vnic, ring grp */
-	rc = bnxt_hwrm_vnic_cfg(bp, vnic_id);
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 
 	/* Enable RSS hashing on vnic */
-	rc = bnxt_hwrm_vnic_set_rss(bp, vnic_id, true);
+	rc = bnxt_hwrm_vnic_set_rss(bp, vnic, true);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 
 	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
-		rc = bnxt_hwrm_vnic_set_hds(bp, vnic_id);
+		rc = bnxt_hwrm_vnic_set_hds(bp, vnic);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d set hds failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 		}
 	}
 
@@ -9817,16 +9904,33 @@ vnic_setup_err:
 	return rc;
 }
 
-static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
+int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic)
+{
+	int rc;
+
+	rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+	if (rc) {
+		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+			   vnic->vnic_id, rc);
+		return rc;
+	}
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
+	if (rc)
+		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
+			   vnic->vnic_id, rc);
+	return rc;
+}
+
+int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	int rc, i, nr_ctxs;
 
 	nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings);
 	for (i = 0; i < nr_ctxs; i++) {
-		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, i);
+		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, i);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d ctx %d alloc failure rc: %x\n",
-				   vnic_id, i, rc);
+				   vnic->vnic_id, i, rc);
 			break;
 		}
 		bp->rsscos_nr_ctxs++;
@@ -9834,63 +9938,57 @@ static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
 	if (i < nr_ctxs)
 		return -ENOMEM;
 
-	rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic_id, true);
-	if (rc) {
-		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-			   vnic_id, rc);
-		return rc;
-	}
-	rc = bnxt_hwrm_vnic_cfg(bp, vnic_id);
-	if (rc) {
-		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
-			   vnic_id, rc);
+	rc = bnxt_hwrm_vnic_rss_cfg_p5(bp, vnic);
+	if (rc)
 		return rc;
-	}
+
 	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
-		rc = bnxt_hwrm_vnic_set_hds(bp, vnic_id);
+		rc = bnxt_hwrm_vnic_set_hds(bp, vnic);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d set hds failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 		}
 	}
 	return rc;
 }
 
-static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
+static int bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return __bnxt_setup_vnic_p5(bp, vnic_id);
+		return __bnxt_setup_vnic_p5(bp, vnic);
 	else
-		return __bnxt_setup_vnic(bp, vnic_id);
+		return __bnxt_setup_vnic(bp, vnic);
 }
 
-static int bnxt_alloc_and_setup_vnic(struct bnxt *bp, u16 vnic_id,
+static int bnxt_alloc_and_setup_vnic(struct bnxt *bp,
+				     struct bnxt_vnic_info *vnic,
 				     u16 start_rx_ring_idx, int rx_rings)
 {
 	int rc;
 
-	rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, start_rx_ring_idx, rx_rings);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, start_rx_ring_idx, rx_rings);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		return rc;
 	}
-	return bnxt_setup_vnic(bp, vnic_id);
+	return bnxt_setup_vnic(bp, vnic);
 }
 
 static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 {
+	struct bnxt_vnic_info *vnic;
 	int i, rc = 0;
 
-	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
-		return bnxt_alloc_and_setup_vnic(bp, BNXT_VNIC_NTUPLE, 0,
-						 bp->rx_nr_rings);
+	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
+		vnic = &bp->vnic_info[BNXT_VNIC_NTUPLE];
+		return bnxt_alloc_and_setup_vnic(bp, vnic, 0, bp->rx_nr_rings);
+	}
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
-		struct bnxt_vnic_info *vnic;
 		u16 vnic_id = i + 1;
 		u16 ring_id = i;
 
@@ -9901,12 +9999,104 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 		vnic->flags |= BNXT_VNIC_RFS_FLAG;
 		if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 			vnic->flags |= BNXT_VNIC_RFS_NEW_RSS_FLAG;
-		if (bnxt_alloc_and_setup_vnic(bp, vnic_id, ring_id, 1))
+		if (bnxt_alloc_and_setup_vnic(bp, &bp->vnic_info[vnic_id], ring_id, 1))
 			break;
 	}
 	return rc;
 }
 
+void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			  bool all)
+{
+	struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+	struct bnxt_filter_base *usr_fltr, *tmp;
+	struct bnxt_ntuple_filter *ntp_fltr;
+	int i;
+
+	bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
+	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
+		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
+			bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
+	}
+	if (!all)
+		return;
+
+	list_for_each_entry_safe(usr_fltr, tmp, &bp->usr_fltr_list, list) {
+		if ((usr_fltr->flags & BNXT_ACT_RSS_CTX) &&
+		    usr_fltr->fw_vnic_id == rss_ctx->index) {
+			ntp_fltr = container_of(usr_fltr,
+						struct bnxt_ntuple_filter,
+						base);
+			bnxt_hwrm_cfa_ntuple_filter_free(bp, ntp_fltr);
+			bnxt_del_ntp_filter(bp, ntp_fltr);
+			bnxt_del_one_usr_fltr(bp, usr_fltr);
+		}
+	}
+
+	if (vnic->rss_table)
+		dma_free_coherent(&bp->pdev->dev, vnic->rss_table_size,
+				  vnic->rss_table,
+				  vnic->rss_table_dma_addr);
+	kfree(rss_ctx->rss_indir_tbl);
+	list_del(&rss_ctx->list);
+	bp->num_rss_ctx--;
+	clear_bit(rss_ctx->index, bp->rss_ctx_bmap);
+	kfree(rss_ctx);
+}
+
+static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
+{
+	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list) {
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		if (bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings) ||
+		    bnxt_hwrm_vnic_set_tpa(bp, vnic, set_tpa) ||
+		    __bnxt_setup_vnic_p5(bp, vnic)) {
+			netdev_err(bp->dev, "Failed to restore RSS ctx %d\n",
+				   rss_ctx->index);
+			bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+		}
+	}
+}
+
+struct bnxt_rss_ctx *bnxt_alloc_rss_ctx(struct bnxt *bp)
+{
+	struct bnxt_rss_ctx *rss_ctx = NULL;
+
+	rss_ctx = kzalloc(sizeof(*rss_ctx), GFP_KERNEL);
+	if (rss_ctx) {
+		rss_ctx->vnic.rss_ctx = rss_ctx;
+		list_add_tail(&rss_ctx->list, &bp->rss_ctx_list);
+		bp->num_rss_ctx++;
+	}
+	return rss_ctx;
+}
+
+void bnxt_clear_rss_ctxs(struct bnxt *bp, bool all)
+{
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list)
+		bnxt_del_one_rss_ctx(bp, rss_ctx, all);
+
+	if (all)
+		bitmap_free(bp->rss_ctx_bmap);
+}
+
+static void bnxt_init_multi_rss_ctx(struct bnxt *bp)
+{
+	bp->rss_ctx_bmap = bitmap_zalloc(BNXT_RSS_CTX_BMAP_LEN, GFP_KERNEL);
+	if (bp->rss_ctx_bmap) {
+		/* burn index 0 since we cannot have context 0 */
+		__set_bit(0, bp->rss_ctx_bmap);
+		INIT_LIST_HEAD(&bp->rss_ctx_list);
+		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
+	}
+}
+
 /* Allow PF, trusted VFs and VFs with default VLAN to be in promiscuous mode */
 static bool bnxt_promisc_ok(struct bnxt *bp)
 {
@@ -9919,16 +10109,17 @@ static bool bnxt_promisc_ok(struct bnxt *bp)
 
 static int bnxt_setup_nitroa0_vnic(struct bnxt *bp)
 {
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[1];
 	unsigned int rc = 0;
 
-	rc = bnxt_hwrm_vnic_alloc(bp, 1, bp->rx_nr_rings - 1, 1);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, bp->rx_nr_rings - 1, 1);
 	if (rc) {
 		netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
 			   rc);
 		return rc;
 	}
 
-	rc = bnxt_hwrm_vnic_cfg(bp, 1);
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
 		netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
 			   rc);
@@ -9971,7 +10162,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 		rx_nr_rings--;
 
 	/* default vnic 0 */
-	rc = bnxt_hwrm_vnic_alloc(bp, BNXT_VNIC_DEFAULT, 0, rx_nr_rings);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, rx_nr_rings);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic alloc failure rc: %x\n", rc);
 		goto err_out;
@@ -9980,7 +10171,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	if (BNXT_VF(bp))
 		bnxt_hwrm_func_qcfg(bp);
 
-	rc = bnxt_setup_vnic(bp, BNXT_VNIC_DEFAULT);
+	rc = bnxt_setup_vnic(bp, vnic);
 	if (rc)
 		goto err_out;
 	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
@@ -10295,19 +10486,10 @@ unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp)
 	return bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_func_stat_ctxs(bp);
 }
 
-int bnxt_get_avail_msix(struct bnxt *bp, int num)
+static int bnxt_get_avail_msix(struct bnxt *bp, int num)
 {
-	int max_cp = bnxt_get_max_func_cp_rings(bp);
 	int max_irq = bnxt_get_max_func_irqs(bp);
 	int total_req = bp->cp_nr_rings + num;
-	int max_idx, avail_msix;
-
-	max_idx = bp->total_irqs;
-	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)
-		return avail_msix;
 
 	if (max_irq < total_req) {
 		num = max_irq - bp->cp_nr_rings;
@@ -10434,13 +10616,23 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
 	bool irq_cleared = false;
 	int tcs = bp->num_tc;
+	int irqs_required;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
-	if (irq_re_init && BNXT_NEW_RM(bp) &&
-	    bnxt_get_num_msix(bp) != bp->total_irqs) {
+	if (BNXT_NEW_RM(bp) && !bnxt_ulp_registered(bp->edev)) {
+		int ulp_msix = bnxt_get_avail_msix(bp, bp->ulp_num_msix_want);
+
+		if (ulp_msix > bp->ulp_num_msix_want)
+			ulp_msix = bp->ulp_num_msix_want;
+		irqs_required = ulp_msix + bp->cp_nr_rings;
+	} else {
+		irqs_required = bnxt_get_num_msix(bp);
+	}
+
+	if (irq_re_init && BNXT_NEW_RM(bp) && irqs_required != bp->total_irqs) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
 		irq_cleared = true;
@@ -10622,9 +10814,9 @@ static void bnxt_disable_napi(struct bnxt *bp)
 
 		cpr = &bnapi->cp_ring;
 		if (bnapi->tx_fault)
-			cpr->sw_stats.tx.tx_resets++;
+			cpr->sw_stats->tx.tx_resets++;
 		if (bnapi->in_reset)
-			cpr->sw_stats.rx.rx_resets++;
+			cpr->sw_stats->rx.rx_resets++;
 		napi_disable(&bnapi->napi);
 		if (bnapi->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
@@ -11359,7 +11551,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		if (fw_reset) {
 			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
-				bnxt_ulp_stop(bp);
+				bnxt_ulp_irq_stop(bp);
 			bnxt_free_ctx_mem(bp);
 			bnxt_dcb_free(bp);
 			rc = bnxt_fw_init_one(bp);
@@ -11666,6 +11858,46 @@ static void bnxt_cfg_usr_fltrs(struct bnxt *bp)
 		bnxt_cfg_one_usr_fltr(bp, usr_fltr);
 }
 
+static int bnxt_set_xps_mapping(struct bnxt *bp)
+{
+	int numa_node = dev_to_node(&bp->pdev->dev);
+	unsigned int q_idx, map_idx, cpu, i;
+	const struct cpumask *cpu_mask_ptr;
+	int nr_cpus = num_online_cpus();
+	cpumask_t *q_map;
+	int rc = 0;
+
+	q_map = kcalloc(bp->tx_nr_rings_per_tc, sizeof(*q_map), GFP_KERNEL);
+	if (!q_map)
+		return -ENOMEM;
+
+	/* Create CPU mask for all TX queues across MQPRIO traffic classes.
+	 * Each TC has the same number of TX queues. The nth TX queue for each
+	 * TC will have the same CPU mask.
+	 */
+	for (i = 0; i < nr_cpus; i++) {
+		map_idx = i % bp->tx_nr_rings_per_tc;
+		cpu = cpumask_local_spread(i, numa_node);
+		cpu_mask_ptr = get_cpu_mask(cpu);
+		cpumask_or(&q_map[map_idx], &q_map[map_idx], cpu_mask_ptr);
+	}
+
+	/* Register CPU mask for each TX queue except the ones marked for XDP */
+	for (q_idx = 0; q_idx < bp->dev->real_num_tx_queues; q_idx++) {
+		map_idx = q_idx % bp->tx_nr_rings_per_tc;
+		rc = netif_set_xps_queue(bp->dev, &q_map[map_idx], q_idx);
+		if (rc) {
+			netdev_warn(bp->dev, "Error setting XPS for q:%d\n",
+				    q_idx);
+			break;
+		}
+	}
+
+	kfree(q_map);
+
+	return rc;
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -11728,8 +11960,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		}
 	}
 
-	if (irq_re_init)
+	if (irq_re_init) {
 		udp_tunnel_nic_reset_ntf(bp->dev);
+		rc = bnxt_set_xps_mapping(bp);
+		if (rc)
+			netdev_warn(bp->dev, "failed to set xps mapping\n");
+	}
 
 	if (bp->tx_nr_rings_xdp < num_possible_cpus()) {
 		if (!static_key_enabled(&bnxt_xdp_locking_key))
@@ -11754,6 +11990,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_hwrm_realloc_rss_ctx_vnic(bp);
 	bnxt_cfg_usr_fltrs(bp);
 	return 0;
 
@@ -11868,10 +12106,9 @@ static int bnxt_open(struct net_device *dev)
 		bnxt_hwrm_if_change(bp, false);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
-			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
-				bnxt_ulp_start(bp, 0);
-				bnxt_reenable_sriov(bp);
-			}
+			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+				bnxt_queue_sp_work(bp,
+						   BNXT_RESTART_ULP_SP_EVENT);
 		}
 	}
 
@@ -11902,6 +12139,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	while (bnxt_drv_busy(bp))
 		msleep(20);
 
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, false);
 	/* Flush rings and disable interrupts */
 	bnxt_shutdown_nic(bp, irq_re_init);
 
@@ -12101,8 +12340,8 @@ static void bnxt_get_ring_stats(struct bnxt *bp,
 		stats->tx_dropped += BNXT_GET_RING_STATS64(sw, tx_error_pkts);
 
 		stats->rx_dropped +=
-			cpr->sw_stats.rx.rx_netpoll_discards +
-			cpr->sw_stats.rx.rx_oom_discards;
+			cpr->sw_stats->rx.rx_netpoll_discards +
+			cpr->sw_stats->rx.rx_oom_discards;
 	}
 }
 
@@ -12169,7 +12408,7 @@ static void bnxt_get_one_ring_err_stats(struct bnxt *bp,
 					struct bnxt_total_ring_err_stats *stats,
 					struct bnxt_cp_ring_info *cpr)
 {
-	struct bnxt_sw_stats *sw_stats = &cpr->sw_stats;
+	struct bnxt_sw_stats *sw_stats = cpr->sw_stats;
 	u64 *hw_stats = cpr->stats.sw_stats;
 
 	stats->rx_total_l4_csum_errors += sw_stats->rx.rx_l4_csum_errors;
@@ -12399,33 +12638,26 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 }
 
 /* If runtime conditions support RFS */
-static bool bnxt_rfs_capable(struct bnxt *bp)
+bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx)
 {
 	struct bnxt_hw_rings hwr = {0};
 	int max_vnics, max_rss_ctxs;
 
-	hwr.rss_ctx = 1;
-	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
-		/* 2 VNICS: default + Ntuple */
-		hwr.vnic = 2;
-		hwr.rss_ctx = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
-			      hwr.vnic;
-		goto check_reserve_vnic;
-	}
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
+	    !BNXT_SUPPORTS_NTUPLE_VNIC(bp))
 		return bnxt_rfs_supported(bp);
+
 	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
 		return false;
 
-	hwr.vnic = 1 + bp->rx_nr_rings;
-check_reserve_vnic:
+	hwr.grp = bp->rx_nr_rings;
+	hwr.vnic = bnxt_get_total_vnics(bp, bp->rx_nr_rings);
+	if (new_rss_ctx)
+		hwr.vnic++;
+	hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	max_vnics = bnxt_get_max_func_vnics(bp);
 	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
-	    !(bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP))
-		hwr.rss_ctx = hwr.vnic;
-
 	if (hwr.vnic > max_vnics || hwr.rss_ctx > max_rss_ctxs) {
 		if (bp->rx_nr_rings > 1)
 			netdev_warn(bp->dev,
@@ -12459,7 +12691,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	netdev_features_t vlan_features;
 
-	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
+	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp, false))
 		features &= ~NETIF_F_NTUPLE;
 
 	if ((bp->flags & BNXT_FLAG_NO_AGG_RINGS) || bp->xdp_prog)
@@ -12851,17 +13083,8 @@ static void bnxt_reset_task(struct bnxt *bp, bool silent)
 	if (!silent)
 		bnxt_dbg_dump_states(bp);
 	if (netif_running(bp->dev)) {
-		int rc;
-
-		if (silent) {
-			bnxt_close_nic(bp, false, false);
-			bnxt_open_nic(bp, false, false);
-		} else {
-			bnxt_ulp_stop(bp);
-			bnxt_close_nic(bp, true, false);
-			rc = bnxt_open_nic(bp, true, false);
-			bnxt_ulp_start(bp, rc);
-		}
+		bnxt_close_nic(bp, !silent, false);
+		bnxt_open_nic(bp, !silent, false);
 	}
 }
 
@@ -13019,7 +13242,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 		rxr->bnapi->in_reset = false;
 		bnxt_alloc_one_rx_ring(bp, i);
 		cpr = &rxr->bnapi->cp_ring;
-		cpr->sw_stats.rx.rx_resets++;
+		cpr->sw_stats->rx.rx_resets++;
 		if (bp->flags & BNXT_FLAG_AGG_RINGS)
 			bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 		bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
@@ -13041,7 +13264,6 @@ static void bnxt_fw_fatal_close(struct bnxt *bp)
 
 static void bnxt_fw_reset_close(struct bnxt *bp)
 {
-	bnxt_ulp_stop(bp);
 	/* When firmware is in fatal state, quiesce device and disable
 	 * bus master to prevent any potential bad DMAs before freeing
 	 * kernel memory.
@@ -13122,6 +13344,7 @@ void bnxt_fw_exception(struct bnxt *bp)
 {
 	netdev_warn(bp->dev, "Detected firmware fatal condition, initiating reset\n");
 	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
+	bnxt_ulp_stop(bp);
 	bnxt_rtnl_lock_sp(bp);
 	bnxt_force_fw_reset(bp);
 	bnxt_rtnl_unlock_sp(bp);
@@ -13153,6 +13376,7 @@ static int bnxt_get_registered_vfs(struct bnxt *bp)
 
 void bnxt_fw_reset(struct bnxt *bp)
 {
+	bnxt_ulp_stop(bp);
 	bnxt_rtnl_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
 	    !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -13231,7 +13455,7 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 			bnxt_dbg_hwrm_ring_info_get(bp,
 				DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL,
 				fw_ring_id, &val[0], &val[1]);
-			cpr->sw_stats.cmn.missed_irqs++;
+			cpr->sw_stats->cmn.missed_irqs++;
 		}
 	}
 }
@@ -13277,6 +13501,12 @@ static void bnxt_fw_echo_reply(struct bnxt *bp)
 	hwrm_req_send(bp, req);
 }
 
+static void bnxt_ulp_restart(struct bnxt *bp)
+{
+	bnxt_ulp_stop(bp);
+	bnxt_ulp_start(bp, 0);
+}
+
 static void bnxt_sp_task(struct work_struct *work)
 {
 	struct bnxt *bp = container_of(work, struct bnxt, sp_task);
@@ -13288,6 +13518,11 @@ static void bnxt_sp_task(struct work_struct *work)
 		return;
 	}
 
+	if (test_and_clear_bit(BNXT_RESTART_ULP_SP_EVENT, &bp->sp_event)) {
+		bnxt_ulp_restart(bp);
+		bnxt_reenable_sriov(bp);
+	}
+
 	if (test_and_clear_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event))
 		bnxt_cfg_rx_mode(bp);
 
@@ -13416,8 +13651,8 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		return -ENOMEM;
 	hwr.stat = hwr.cp;
 	if (BNXT_NEW_RM(bp)) {
-		hwr.cp += bnxt_get_ulp_msix_num(bp);
-		hwr.stat += bnxt_get_ulp_stat_ctxs(bp);
+		hwr.cp += bnxt_get_ulp_msix_num_in_use(bp);
+		hwr.stat += bnxt_get_ulp_stat_ctxs_in_use(bp);
 		hwr.grp = rx;
 		hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	}
@@ -13600,7 +13835,7 @@ static void bnxt_set_dflt_rfs(struct bnxt *bp)
 	bp->flags &= ~BNXT_FLAG_RFS;
 	if (bnxt_rfs_supported(bp)) {
 		dev->hw_features |= NETIF_F_NTUPLE;
-		if (bnxt_rfs_capable(bp)) {
+		if (bnxt_rfs_capable(bp, false)) {
 			bp->flags |= BNXT_FLAG_RFS;
 			dev->features |= NETIF_F_NTUPLE;
 		}
@@ -13744,10 +13979,8 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp)
 static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
 {
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) {
-		bnxt_ulp_start(bp, rc);
+	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
 		bnxt_dl_health_fw_status_update(bp, false);
-	}
 	bp->fw_reset_state = 0;
 	dev_close(bp->dev);
 }
@@ -13778,7 +14011,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 				bp->fw_reset_state = 0;
 				netdev_err(bp->dev, "Firmware reset aborted, bnxt_get_registered_vfs() returns %d\n",
 					   n);
-				return;
+				goto ulp_start;
 			}
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
@@ -13788,7 +14021,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
 			bnxt_fw_reset_abort(bp, rc);
 			rtnl_unlock();
-			return;
+			goto ulp_start;
 		}
 		bnxt_fw_reset_close(bp);
 		if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) {
@@ -13881,7 +14114,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
 			rtnl_unlock();
-			return;
+			goto ulp_start;
 		}
 
 		if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) &&
@@ -13893,10 +14126,6 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		/* Make sure fw_reset_state is 0 before clearing the flag */
 		smp_mb__before_atomic();
 		clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-		bnxt_ulp_start(bp, 0);
-		bnxt_reenable_sriov(bp);
-		bnxt_vf_reps_alloc(bp);
-		bnxt_vf_reps_open(bp);
 		bnxt_ptp_reapply_pps(bp);
 		clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
 		if (test_and_clear_bit(BNXT_STATE_RECOVER, &bp->state)) {
@@ -13904,6 +14133,12 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
 		rtnl_unlock();
+		bnxt_ulp_start(bp, 0);
+		bnxt_reenable_sriov(bp);
+		rtnl_lock();
+		bnxt_vf_reps_alloc(bp);
+		bnxt_vf_reps_open(bp);
+		rtnl_unlock();
 		break;
 	}
 	return;
@@ -13919,6 +14154,8 @@ fw_reset_abort:
 	rtnl_lock();
 	bnxt_fw_reset_abort(bp, rc);
 	rtnl_unlock();
+ulp_start:
+	bnxt_ulp_start(bp, rc);
 }
 
 static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
@@ -14043,7 +14280,7 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	if (netif_running(dev))
 		bnxt_close_nic(bp, true, false);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
@@ -14453,12 +14690,9 @@ static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
 		u16 mode;
 
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-
 		mode = nla_get_u16(attr);
 		if (mode == bp->br_mode)
 			break;
@@ -14542,7 +14776,7 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
 	stats->bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes);
 	stats->bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes);
 
-	stats->alloc_fail = cpr->sw_stats.rx.rx_oom_discards;
+	stats->alloc_fail = cpr->sw_stats->rx.rx_oom_discards;
 }
 
 static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
@@ -14594,12 +14828,17 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
 
-	bnxt_rdma_aux_device_uninit(bp);
+	bnxt_rdma_aux_device_del(bp);
 
 	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+
+	bnxt_rdma_aux_device_uninit(bp);
+
 	bnxt_free_l2_filters(bp, true);
 	bnxt_free_ntp_fltrs(bp, true);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, true);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	/* Flush any pending tasks */
 	cancel_work_sync(&bp->sp_task);
@@ -14688,8 +14927,9 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	*max_rx = hw_resc->max_rx_rings;
 	*max_cp = bnxt_get_max_func_cp_rings_for_en(bp);
 	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));
+			bnxt_get_ulp_msix_num_in_use(bp),
+			hw_resc->max_stat_ctxs -
+			bnxt_get_ulp_stat_ctxs_in_use(bp));
 	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;
@@ -14785,6 +15025,7 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp)
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 {
 	int dflt_rings, max_rx_rings, max_tx_rings, rc;
+	int avail_msix;
 
 	if (!bnxt_can_reserve_rings(bp))
 		return 0;
@@ -14812,6 +15053,14 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 
+	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
+	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
+		int ulp_num_msix = min(avail_msix, bp->ulp_num_msix_want);
+
+		bnxt_set_ulp_msix_num(bp, ulp_num_msix);
+		bnxt_set_dflt_ulp_stat_ctxs(bp);
+	}
+
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
@@ -15058,7 +15307,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			bp->flags |= BNXT_FLAG_CHIP_P7;
 	}
 
-	rc = bnxt_alloc_rss_indir_tbl(bp);
+	rc = bnxt_alloc_rss_indir_tbl(bp, NULL);
 	if (rc)
 		goto init_err_pci_clean;
 
@@ -15161,6 +15410,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
+	bnxt_rdma_aux_device_init(bp);
 	rc = bnxt_set_dflt_rings(bp, true);
 	if (rc) {
 		if (BNXT_VF(bp) && rc == -ENODEV) {
@@ -15211,13 +15461,17 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_LIST_HEAD(&bp->usr_fltr_list);
 
+	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
+		bnxt_init_multi_rss_ctx(bp);
+
+
 	rc = register_netdev(dev);
 	if (rc)
 		goto init_err_cleanup;
 
 	bnxt_dl_fw_reporters_create(bp);
 
-	bnxt_rdma_aux_device_init(bp);
+	bnxt_rdma_aux_device_add(bp);
 
 	bnxt_print_device_info(bp);
 
@@ -15225,12 +15479,15 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 init_err_cleanup:
+	bnxt_rdma_aux_device_uninit(bp);
 	bnxt_dl_unregister(bp);
 init_err_dl:
 	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, true);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_hwmon_uninit(bp);
@@ -15285,8 +15542,9 @@ static int bnxt_suspend(struct device *device)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	rtnl_lock();
 	bnxt_ulp_stop(bp);
+
+	rtnl_lock();
 	if (netif_running(dev)) {
 		netif_device_detach(dev);
 		rc = bnxt_close(dev);
@@ -15341,10 +15599,10 @@ static int bnxt_resume(struct device *device)
 	}
 
 resume_exit:
+	rtnl_unlock();
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
 		bnxt_reenable_sriov(bp);
-	rtnl_unlock();
 	return rc;
 }
 
@@ -15374,11 +15632,11 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 
 	netdev_info(netdev, "PCI I/O error detected\n");
 
+	bnxt_ulp_stop(bp);
+
 	rtnl_lock();
 	netif_device_detach(netdev);
 
-	bnxt_ulp_stop(bp);
-
 	if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		netdev_err(bp->dev, "Firmware reset already in progress\n");
 		abort = true;
@@ -15430,6 +15688,10 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 
 	netdev_info(bp->dev, "PCI Slot Reset\n");
 
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
+	    test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state))
+		msleep(900);
+
 	rtnl_lock();
 
 	if (pci_enable_device(pdev)) {
@@ -15510,13 +15772,13 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	if (!err && netif_running(netdev))
 		err = bnxt_open(netdev);
 
-	bnxt_ulp_start(bp, err);
-	if (!err) {
-		bnxt_reenable_sriov(bp);
+	if (!err)
 		netif_device_attach(netdev);
-	}
 
 	rtnl_unlock();
+	bnxt_ulp_start(bp, err);
+	if (!err)
+		bnxt_reenable_sriov(bp);
 }
 
 static const struct pci_error_handlers bnxt_err_handler = {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index dd849e715c9b..656ab81c0272 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1152,7 +1152,7 @@ struct bnxt_cp_ring_info {
 	struct bnxt_stats_mem	stats;
 	u32			hw_stats_ctx_id;
 
-	struct bnxt_sw_stats	sw_stats;
+	struct bnxt_sw_stats	*sw_stats;
 
 	struct bnxt_ring_struct	cp_ring_struct;
 
@@ -1256,8 +1256,22 @@ struct bnxt_vnic_info {
 #define BNXT_VNIC_UCAST_FLAG	8
 #define BNXT_VNIC_RFS_NEW_RSS_FLAG	0x10
 #define BNXT_VNIC_NTUPLE_FLAG		0x20
+#define BNXT_VNIC_RSSCTX_FLAG		0x40
+	struct bnxt_rss_ctx	*rss_ctx;
+	u32		vnic_id;
 };
 
+struct bnxt_rss_ctx {
+	struct list_head list;
+	struct bnxt_vnic_info vnic;
+	u16	*rss_indir_tbl;
+	u8	index;
+};
+
+#define BNXT_MAX_ETH_RSS_CTX	32
+#define BNXT_RSS_CTX_BMAP_LEN	(BNXT_MAX_ETH_RSS_CTX + 1)
+#define BNXT_VNIC_ID_INVALID	0xffffffff
+
 struct bnxt_hw_rings {
 	int tx;
 	int rx;
@@ -1360,6 +1374,7 @@ struct bnxt_filter_base {
 #define BNXT_ACT_RING_DST	2
 #define BNXT_ACT_FUNC_DST	4
 #define BNXT_ACT_NO_AGING	8
+#define BNXT_ACT_RSS_CTX	0x10
 	u16			sw_id;
 	u16			rxq;
 	u16			fw_vnic_id;
@@ -1998,6 +2013,7 @@ enum board_idx {
 	NETXTREME_E_VF_HV,
 	NETXTREME_E_P5_VF,
 	NETXTREME_E_P5_VF_HV,
+	NETXTREME_E_P7_VF,
 };
 
 struct bnxt {
@@ -2227,6 +2243,9 @@ struct bnxt {
 	/* grp_info indexed by completion ring index */
 	struct bnxt_ring_grp_info	*grp_info;
 	struct bnxt_vnic_info	*vnic_info;
+	struct list_head	rss_ctx_list;
+	unsigned long		*rss_ctx_bmap;
+	u32			num_rss_ctx;
 	int			nr_vnics;
 	u16			*rss_indir_tbl;
 	u16			rss_indir_tbl_entries;
@@ -2241,6 +2260,7 @@ struct bnxt {
 #define BNXT_RSS_CAP_AH_V6_RSS_CAP		BIT(5)
 #define BNXT_RSS_CAP_ESP_V4_RSS_CAP		BIT(6)
 #define BNXT_RSS_CAP_ESP_V6_RSS_CAP		BIT(7)
+#define BNXT_RSS_CAP_MULTI_RSS_CTX		BIT(8)
 
 	u8			rss_hash_key[HW_HASH_KEY_SIZE];
 	u8			rss_hash_key_valid:1;
@@ -2284,6 +2304,7 @@ struct bnxt {
 
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
+	int			ulp_num_msix_want;
 	u8			mac_addr[ETH_ALEN];
 
 #ifdef CONFIG_BNXT_DCB
@@ -2340,6 +2361,10 @@ struct bnxt {
 #define BNXT_SUPPORTS_NTUPLE_VNIC(bp)	\
 	(BNXT_PF(bp) && ((bp)->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3))
 
+#define BNXT_SUPPORTS_MULTI_RSS_CTX(bp)				\
+	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
+	 ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX))
+
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
 	u16                     hwrm_cmd_kong_seq;
@@ -2416,6 +2441,7 @@ struct bnxt {
 #define BNXT_LINK_CFG_CHANGE_SP_EVENT	21
 #define BNXT_THERMAL_THRESHOLD_SP_EVENT	22
 #define BNXT_FW_ECHO_REQUEST_SP_EVENT	23
+#define BNXT_RESTART_ULP_SP_EVENT	24
 
 	struct delayed_work	fw_reset_task;
 	int			fw_reset_state;
@@ -2693,9 +2719,16 @@ 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);
+int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			   u32 tpa_flags);
 void bnxt_fill_ipv6_mask(__be32 mask[4]);
+int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
+void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
 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_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			 unsigned int start_rx_ring_idx,
+			 unsigned int nr_rings);
 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 *);
@@ -2705,7 +2738,6 @@ 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);
 unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
-int bnxt_get_avail_msix(struct bnxt *bp, int num);
 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);
@@ -2721,6 +2753,12 @@ int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all);
 int bnxt_hwrm_func_qcaps(struct bnxt *bp);
 int bnxt_hwrm_fw_set_time(struct bnxt *);
+int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			  bool all);
+struct bnxt_rss_ctx *bnxt_alloc_rss_ctx(struct bnxt *bp);
+void bnxt_clear_rss_ctxs(struct bnxt *bp, bool all);
 int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
@@ -2728,6 +2766,7 @@ void bnxt_reenable_sriov(struct bnxt *bp);
 void bnxt_close_nic(struct bnxt *, bool, bool);
 void bnxt_get_ring_err_stats(struct bnxt *bp,
 			     struct bnxt_total_ring_err_stats *stats);
+bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 			 u32 *reg_buf);
 void bnxt_fw_exception(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ae4529c043f0..4cb0fabf977e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -437,18 +437,20 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
+		bnxt_ulp_stop(bp);
 		rtnl_lock();
 		if (bnxt_sriov_cfg(bp)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "reload is unsupported while VFs are allocated or being configured");
 			rtnl_unlock();
+			bnxt_ulp_start(bp, 0);
 			return -EOPNOTSUPP;
 		}
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
 			rtnl_unlock();
+			bnxt_ulp_start(bp, 0);
 			return -ENODEV;
 		}
-		bnxt_ulp_stop(bp);
 		if (netif_running(bp->dev))
 			bnxt_close_nic(bp, true, true);
 		bnxt_vf_reps_free(bp);
@@ -516,7 +518,6 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		bnxt_vf_reps_alloc(bp);
 		if (netif_running(bp->dev))
 			rc = bnxt_open_nic(bp, true, true);
-		bnxt_ulp_start(bp, rc);
 		if (!rc) {
 			bnxt_reenable_sriov(bp);
 			bnxt_ptp_reapply_pps(bp);
@@ -570,6 +571,8 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		dev_close(bp->dev);
 	}
 	rtnl_unlock();
+	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
+		bnxt_ulp_start(bp, rc);
 	return rc;
 }
 
@@ -1096,7 +1099,8 @@ static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 }
 
 static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	struct hwrm_nvm_set_variable_input *req;
@@ -1145,7 +1149,8 @@ static int bnxt_remote_dev_reset_get(struct devlink *dl, u32 id,
 }
 
 static int bnxt_remote_dev_reset_set(struct devlink *dl, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1d240a27455a..8763f8a01457 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -631,13 +631,13 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 			buf[j] = sw_stats[k];
 
 skip_tpa_ring_stats:
-		sw = (u64 *)&cpr->sw_stats.rx;
+		sw = (u64 *)&cpr->sw_stats->rx;
 		if (is_rx_ring(bp, i)) {
 			for (k = 0; k < NUM_RING_RX_SW_STATS; j++, k++)
 				buf[j] = sw[k];
 		}
 
-		sw = (u64 *)&cpr->sw_stats.cmn;
+		sw = (u64 *)&cpr->sw_stats->cmn;
 		for (k = 0; k < NUM_RING_CMN_SW_STATS; j++, k++)
 			buf[j] = sw[k];
 	}
@@ -969,6 +969,8 @@ static int bnxt_set_channels(struct net_device *dev,
 	}
 
 	bnxt_clear_usr_fltrs(bp, true);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, false);
 	if (netif_running(dev)) {
 		if (BNXT_PF(bp)) {
 			/* TODO CHIMP_FW: Send message to all VF's
@@ -1205,6 +1207,36 @@ fltr_err:
 	return rc;
 }
 
+static struct bnxt_rss_ctx *bnxt_get_rss_ctx_from_index(struct bnxt *bp,
+							u32 index)
+{
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list)
+		if (rss_ctx->index == index)
+			return rss_ctx;
+	return NULL;
+}
+
+static int bnxt_alloc_rss_ctx_rss_table(struct bnxt *bp,
+					struct bnxt_rss_ctx *rss_ctx)
+{
+	int size = L1_CACHE_ALIGN(BNXT_MAX_RSS_TABLE_SIZE_P5);
+	struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+	vnic->rss_table_size = size + HW_HASH_KEY_SIZE;
+	vnic->rss_table = dma_alloc_coherent(&bp->pdev->dev,
+					     vnic->rss_table_size,
+					     &vnic->rss_table_dma_addr,
+					     GFP_KERNEL);
+	if (!vnic->rss_table)
+		return -ENOMEM;
+
+	vnic->rss_hash_key = ((void *)vnic->rss_table) + size;
+	vnic->rss_hash_key_dma_addr = vnic->rss_table_dma_addr + size;
+	return 0;
+}
+
 static int bnxt_add_l2_cls_rule(struct bnxt *bp,
 				struct ethtool_rx_flow_spec *fs)
 {
@@ -1280,22 +1312,24 @@ static bool bnxt_verify_ntuple_ip6_flow(struct ethtool_usrip6_spec *ip_spec,
 }
 
 static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
-				    struct ethtool_rx_flow_spec *fs)
+				    struct ethtool_rxnfc *cmd)
 {
-	u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
-	u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
 	struct bnxt_ntuple_filter *new_fltr, *fltr;
+	u32 flow_type = fs->flow_type & 0xff;
 	struct bnxt_l2_filter *l2_fltr;
 	struct bnxt_flow_masks *fmasks;
-	u32 flow_type = fs->flow_type;
 	struct flow_keys *fkeys;
-	u32 idx;
+	u32 idx, ring;
 	int rc;
+	u8 vf;
 
 	if (!bp->vnic_info)
 		return -EAGAIN;
 
-	if ((flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
+	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	if ((fs->flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
 		return -EOPNOTSUPP;
 
 	if (flow_type == IP_USER_FLOW) {
@@ -1403,6 +1437,19 @@ static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
 	rcu_read_unlock();
 
 	new_fltr->base.flags = BNXT_ACT_NO_AGING;
+	if (fs->flow_type & FLOW_RSS) {
+		struct bnxt_rss_ctx *rss_ctx;
+
+		new_fltr->base.fw_vnic_id = 0;
+		new_fltr->base.flags |= BNXT_ACT_RSS_CTX;
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, cmd->rss_context);
+		if (rss_ctx) {
+			new_fltr->base.fw_vnic_id = rss_ctx->index;
+		} else {
+			rc = -EINVAL;
+			goto ntuple_err;
+		}
+	}
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC)
 		new_fltr->base.flags |= BNXT_ACT_DROP;
 	else
@@ -1444,12 +1491,12 @@ static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	     flow_type == IPV6_USER_FLOW) &&
 	    !(bp->fw_cap & BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO))
 		return -EOPNOTSUPP;
-	if (flow_type & (FLOW_MAC_EXT | FLOW_RSS))
+	if (flow_type & FLOW_MAC_EXT)
 		return -EINVAL;
 	flow_type &= ~FLOW_EXT;
 
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC && flow_type != ETHER_FLOW)
-		return bnxt_add_ntuple_cls_rule(bp, fs);
+		return bnxt_add_ntuple_cls_rule(bp, cmd);
 
 	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
 	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
@@ -1463,7 +1510,7 @@ static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	if (flow_type == ETHER_FLOW)
 		rc = bnxt_add_l2_cls_rule(bp, fs);
 	else
-		rc = bnxt_add_ntuple_cls_rule(bp, fs);
+		rc = bnxt_add_ntuple_cls_rule(bp, cmd);
 	return rc;
 }
 
@@ -1754,7 +1801,10 @@ static u32 bnxt_get_rxfh_key_size(struct net_device *dev)
 static int bnxt_get_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh)
 {
+	u32 rss_context = rxfh->rss_context;
+	struct bnxt_rss_ctx *rss_ctx = NULL;
 	struct bnxt *bp = netdev_priv(dev);
+	u16 *indir_tbl = bp->rss_indir_tbl;
 	struct bnxt_vnic_info *vnic;
 	u32 i, tbl_size;
 
@@ -1764,10 +1814,18 @@ static int bnxt_get_rxfh(struct net_device *dev,
 		return 0;
 
 	vnic = &bp->vnic_info[BNXT_VNIC_DEFAULT];
-	if (rxfh->indir && bp->rss_indir_tbl) {
+	if (rxfh->rss_context) {
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, rss_context);
+		if (!rss_ctx)
+			return -EINVAL;
+		indir_tbl = rss_ctx->rss_indir_tbl;
+		vnic = &rss_ctx->vnic;
+	}
+
+	if (rxfh->indir && indir_tbl) {
 		tbl_size = bnxt_get_rxfh_indir_size(dev);
 		for (i = 0; i < tbl_size; i++)
-			rxfh->indir[i] = bp->rss_indir_tbl[i];
+			rxfh->indir[i] = indir_tbl[i];
 	}
 
 	if (rxfh->key && vnic->rss_hash_key)
@@ -1776,6 +1834,136 @@ static int bnxt_get_rxfh(struct net_device *dev,
 	return 0;
 }
 
+static void bnxt_modify_rss(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			    struct ethtool_rxfh_param *rxfh)
+{
+	if (rxfh->key) {
+		if (rss_ctx) {
+			memcpy(rss_ctx->vnic.rss_hash_key, rxfh->key,
+			       HW_HASH_KEY_SIZE);
+		} else {
+			memcpy(bp->rss_hash_key, rxfh->key, HW_HASH_KEY_SIZE);
+			bp->rss_hash_key_updated = true;
+		}
+	}
+	if (rxfh->indir) {
+		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+		u16 *indir_tbl = bp->rss_indir_tbl;
+
+		if (rss_ctx)
+			indir_tbl = rss_ctx->rss_indir_tbl;
+		for (i = 0; i < tbl_size; i++)
+			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));
+	}
+}
+
+static int bnxt_set_rxfh_context(struct bnxt *bp,
+				 struct ethtool_rxfh_param *rxfh,
+				 struct netlink_ext_ack *extack)
+{
+	u32 *rss_context = &rxfh->rss_context;
+	struct bnxt_rss_ctx *rss_ctx;
+	struct bnxt_vnic_info *vnic;
+	bool modify = false;
+	int bit_id;
+	int rc;
+
+	if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!netif_running(bp->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to set RSS contexts when interface is down");
+		return -EAGAIN;
+	}
+
+	if (*rss_context != ETH_RXFH_CONTEXT_ALLOC) {
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, *rss_context);
+		if (!rss_ctx) {
+			NL_SET_ERR_MSG_FMT_MOD(extack, "RSS context %u not found",
+					       *rss_context);
+			return -EINVAL;
+		}
+		if (*rss_context && rxfh->rss_delete) {
+			bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+			return 0;
+		}
+		modify = true;
+		vnic = &rss_ctx->vnic;
+		goto modify_context;
+	}
+
+	if (bp->num_rss_ctx >= BNXT_MAX_ETH_RSS_CTX) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Out of RSS contexts, maximum %u",
+				       BNXT_MAX_ETH_RSS_CTX);
+		return -EINVAL;
+	}
+
+	if (!bnxt_rfs_capable(bp, true)) {
+		NL_SET_ERR_MSG_MOD(extack, "Out hardware resources");
+		return -ENOMEM;
+	}
+
+	rss_ctx = bnxt_alloc_rss_ctx(bp);
+	if (!rss_ctx)
+		return -ENOMEM;
+
+	vnic = &rss_ctx->vnic;
+	vnic->flags |= BNXT_VNIC_RSSCTX_FLAG;
+	vnic->vnic_id = BNXT_VNIC_ID_INVALID;
+	rc = bnxt_alloc_rss_ctx_rss_table(bp, rss_ctx);
+	if (rc)
+		goto out;
+
+	rc = bnxt_alloc_rss_indir_tbl(bp, rss_ctx);
+	if (rc)
+		goto out;
+
+	bnxt_set_dflt_rss_indir_tbl(bp, rss_ctx);
+	memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE);
+
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate VNIC");
+		goto out;
+	}
+
+	rc = bnxt_hwrm_vnic_set_tpa(bp, vnic, bp->flags & BNXT_FLAG_TPA);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to setup TPA");
+		goto out;
+	}
+modify_context:
+	bnxt_modify_rss(bp, rss_ctx, rxfh);
+
+	if (modify)
+		return bnxt_hwrm_vnic_rss_cfg_p5(bp, vnic);
+
+	rc = __bnxt_setup_vnic_p5(bp, vnic);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to setup TPA");
+		goto out;
+	}
+
+	bit_id = bitmap_find_free_region(bp->rss_ctx_bmap,
+					 BNXT_RSS_CTX_BMAP_LEN, 0);
+	if (bit_id < 0) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	rss_ctx->index = (u16)bit_id;
+	*rss_context = rss_ctx->index;
+
+	return 0;
+out:
+	bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+	return rc;
+}
+
 static int bnxt_set_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh,
 			 struct netlink_ext_ack *extack)
@@ -1786,20 +1974,11 @@ static int bnxt_set_rxfh(struct net_device *dev,
 	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (rxfh->key) {
-		memcpy(bp->rss_hash_key, rxfh->key, HW_HASH_KEY_SIZE);
-		bp->rss_hash_key_updated = true;
-	}
+	if (rxfh->rss_context)
+		return bnxt_set_rxfh_context(bp, rxfh, extack);
 
-	if (rxfh->indir) {
-		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev);
+	bnxt_modify_rss(bp, NULL, rxfh);
 
-		for (i = 0; i < tbl_size; 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));
-	}
 	bnxt_clear_usr_fltrs(bp, false);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
@@ -4641,6 +4820,14 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 
 	if (!bp->num_tests || !BNXT_PF(bp))
 		return;
+
+	if (etest->flags & ETH_TEST_FL_OFFLINE &&
+	    bnxt_ulp_registered(bp->edev)) {
+		etest->flags |= ETH_TEST_FL_FAILED;
+		netdev_warn(dev, "Offline tests cannot be run with RoCE driver loaded\n");
+		return;
+	}
+
 	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (!netif_running(dev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
@@ -4671,7 +4858,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	if (!offline) {
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 	} else {
-		bnxt_ulp_stop(bp);
 		bnxt_close_nic(bp, true, false);
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 
@@ -4682,7 +4868,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		if (rc) {
 			bnxt_hwrm_mac_loopback(bp, false);
 			etest->flags |= ETH_TEST_FL_FAILED;
-			bnxt_ulp_start(bp, rc);
 			return;
 		}
 		if (bnxt_run_loopback(bp))
@@ -4709,7 +4894,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		bnxt_hwrm_phy_loopback(bp, false, false);
 		bnxt_half_close_nic(bp);
 		rc = bnxt_open_nic(bp, true, true);
-		bnxt_ulp_start(bp, rc);
 	}
 	if (rc || bnxt_test_irq(bp)) {
 		buf[BNXT_IRQ_TEST_IDX] = 1;
@@ -5071,6 +5255,7 @@ void bnxt_ethtool_free(struct bnxt *bp)
 
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
+	.cap_rss_ctx_supported		= 1,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USECS_IRQ |
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index e957abd704db..06ea86c80be1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -468,6 +468,10 @@ struct cmd_nums {
 	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
 	#define HWRM_TF_IF_TBL_SET                        0x2feUL
 	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
+	#define HWRM_TF_RESC_USAGE_SET                    0x300UL
+	#define HWRM_TF_RESC_USAGE_QUERY                  0x301UL
+	#define HWRM_TF_TBL_TYPE_ALLOC                    0x302UL
+	#define HWRM_TF_TBL_TYPE_FREE                     0x303UL
 	#define HWRM_TFC_TBL_SCOPE_QCAPS                  0x380UL
 	#define HWRM_TFC_TBL_SCOPE_ID_ALLOC               0x381UL
 	#define HWRM_TFC_TBL_SCOPE_CONFIG                 0x382UL
@@ -495,6 +499,7 @@ struct cmd_nums {
 	#define HWRM_TFC_IF_TBL_SET                       0x398UL
 	#define HWRM_TFC_IF_TBL_GET                       0x399UL
 	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
+	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
 	#define HWRM_SV                                   0x400UL
 	#define HWRM_DBG_READ_DIRECT                      0xff10UL
 	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
@@ -604,8 +609,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 15
-#define HWRM_VERSION_STR "1.10.3.15"
+#define HWRM_VERSION_RSVD 39
+#define HWRM_VERSION_STR "1.10.3.39"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -1328,8 +1333,9 @@ struct hwrm_async_event_cmpl_error_report_base {
 	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL           0x2UL
 	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM                      0x3UL
 	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD  0x4UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD        0x5UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                    ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD             0x5UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
 };
 
 /* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */
@@ -1478,6 +1484,30 @@ struct hwrm_async_event_cmpl_error_report_thermal {
 	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING
 };
 
+/* hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_SFT                         0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
+};
+
 /* hwrm_func_reset_input (size:192b/24B) */
 struct hwrm_func_reset_input {
 	__le16	req_type;
@@ -1781,6 +1811,9 @@ struct hwrm_func_qcaps_output {
 	#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
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED      0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED         0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED                  0x2000000UL
 	__le16	tunnel_disable_flag;
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
@@ -1791,10 +1824,8 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
 	__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
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_TX_CK     0x1UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK     0x2UL
 	u8	device_serial_number[8];
 	__le16	ctxs_per_partition;
 	u8	unused_2[2];
@@ -1844,6 +1875,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED           0x1000UL
 	#define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT                   0x2000UL
 	#define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV            0x4000UL
+	#define FUNC_QCFG_RESP_FLAGS_ROCE_VNIC_ID_VALID           0x8000UL
 	u8	mac_address[6];
 	__le16	pci_id;
 	__le16	alloc_rsscos_ctx;
@@ -1955,7 +1987,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB   0x9UL
 	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB   0xaUL
 	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB
-	u8	unused_2[2];
+	__le16	roce_vnic_id;
 	__le32	partition_min_bw;
 	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
 	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT              0
@@ -2003,6 +2035,8 @@ struct hwrm_func_qcfg_output {
 	__le32	roce_max_srq_per_vf;
 	__le32	roce_max_gid_per_vf;
 	__le16	xid_partition_cfg;
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
 	u8	unused_7;
 	u8	valid;
 };
@@ -2229,10 +2263,8 @@ struct hwrm_func_cfg_input {
 	__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
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK     0x2UL
 	__le16	unused_2;
 };
 
@@ -2416,6 +2448,7 @@ struct hwrm_func_drv_rgtr_input {
 	#define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT     0x100UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT                 0x200UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT           0x400UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE         0x800UL
 	__le32	enables;
 	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
 	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
@@ -3636,19 +3669,22 @@ struct hwrm_func_backing_store_cfg_v2_input {
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RKC           0x14UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING   0x15UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW  0x16UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW  0x17UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW  0x19UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QUIC_RKC      0x1bUL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE     0x1cUL
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST         FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE       0x1eUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE      0x1fUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE       0x20UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE      0x21UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE     0x22UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE   0x23UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID         0xffffUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST           FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
 	__le16	instance;
 	__le32	flags;
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
@@ -3707,17 +3743,22 @@ struct hwrm_func_backing_store_qcfg_v2_input {
 	#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_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RX_CK               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_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
 	#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;
@@ -3740,15 +3781,18 @@ struct hwrm_func_backing_store_qcfg_v2_output {
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING   0x6UL
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV          0xeUL
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM           0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TKC           0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RKC           0x14UL
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING   0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QUIC_RKC      0x1bUL
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE     0x1cUL
 	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST         FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE       0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE      0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE       0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE      0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE     0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE   0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID         0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST           FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
 	__le16	instance;
 	__le32	flags;
 	__le64	page_dir;
@@ -3841,19 +3885,22 @@ 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_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
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW  0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QUIC_RKC      0x1bUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE     0x1cUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST         FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE       0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE      0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE       0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE      0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE     0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE   0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID         0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST           FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
 	u8	rsvd[6];
 };
 
@@ -3873,19 +3920,22 @@ 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_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
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW  0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QUIC_TKC      0x1aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QUIC_RKC      0x1bUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE     0x1cUL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID       0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST         FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE       0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE      0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE       0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE      0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE     0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE   0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID         0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST           FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
 	__le16	entry_size;
 	__le32	flags;
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
@@ -3990,6 +4040,7 @@ struct hwrm_func_drv_if_change_output {
 	__le32	flags;
 	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
 	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE           0x4UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -4472,7 +4523,11 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPDD    (0x18UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP112   (0x1eUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFPDD     (0x1fUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP      (0x20UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP
 	__le16	fec_cfg;
 	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
 	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
@@ -7380,7 +7435,7 @@ struct hwrm_cfa_l2_filter_free_output {
 	u8	valid;
 };
 
-/* hwrm_cfa_l2_filter_cfg_input (size:320b/40B) */
+/* hwrm_cfa_l2_filter_cfg_input (size:384b/48B) */
 struct hwrm_cfa_l2_filter_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -7399,12 +7454,22 @@ struct hwrm_cfa_l2_filter_cfg_input {
 	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 2)
 	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 2)
 	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK       0x30UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT        4
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE    (0x0UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP  (0x1UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP  (0x2UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST        CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP
 	__le32	enables;
 	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
 	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_PROF_FUNC              0x4UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_L2_CONTEXT_ID          0x8UL
 	__le64	l2_filter_id;
 	__le32	dst_id;
 	__le32	new_mirror_vnic_id;
+	__le32	prof_func;
+	__le32	l2_context_id;
 };
 
 /* hwrm_cfa_l2_filter_cfg_output (size:128b/16B) */
@@ -8466,7 +8531,15 @@ struct hwrm_tunnel_dst_port_query_input {
 	#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_GRE          0x11UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
 	u8	tunnel_next_proto;
 	u8	unused_0[6];
 };
@@ -8514,7 +8587,15 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	#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_GRE          0x11UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
 	u8	tunnel_next_proto;
 	__be16	tunnel_dst_port_val;
 	u8	unused_0[4];
@@ -8565,7 +8646,15 @@ struct hwrm_tunnel_dst_port_free_input {
 	#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_GRE          0x11UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
 	u8	tunnel_next_proto;
 	__le16	tunnel_dst_port_id;
 	u8	unused_0[4];
@@ -8860,7 +8949,7 @@ struct hwrm_stat_generic_qstats_output {
 	u8	valid;
 };
 
-/* generic_sw_hw_stats (size:1408b/176B) */
+/* generic_sw_hw_stats (size:1472b/184B) */
 struct generic_sw_hw_stats {
 	__le64	pcie_statistics_tx_tlp;
 	__le64	pcie_statistics_rx_tlp;
@@ -8884,6 +8973,7 @@ struct generic_sw_hw_stats {
 	__le64	hw_db_recov_dbs_dropped;
 	__le64	hw_db_recov_drops_serviced;
 	__le64	hw_db_recov_dbs_recovered;
+	__le64	hw_db_recov_oo_drop_count;
 };
 
 /* hwrm_fw_reset_input (size:192b/24B) */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index cc07660330f5..e661ab154d6b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -109,7 +109,8 @@ static void bnxt_ptp_get_current_time(struct bnxt *bp)
 	spin_unlock_bh(&ptp->ptp_lock);
 }
 
-static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
+static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts,
+				   u32 txts_tmo)
 {
 	struct hwrm_port_ts_query_output *resp;
 	struct hwrm_port_ts_query_input *req;
@@ -122,10 +123,15 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
 	req->flags = cpu_to_le32(flags);
 	if ((flags & PORT_TS_QUERY_REQ_FLAGS_PATH) ==
 	    PORT_TS_QUERY_REQ_FLAGS_PATH_TX) {
+		u32 tmo_us = txts_tmo * 1000;
+
 		req->enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES);
 		req->ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid);
 		req->ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off);
-		req->ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT);
+		if (!tmo_us)
+			tmo_us = BNXT_PTP_QTS_TIMEOUT;
+		tmo_us = min(tmo_us, BNXT_PTP_QTS_MAX_TMO_US);
+		req->ts_req_timeout = cpu_to_le16(tmo_us);
 	}
 	resp = hwrm_req_hold(bp, req);
 
@@ -672,10 +678,17 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct skb_shared_hwtstamps timestamp;
+	unsigned long now = jiffies;
 	u64 ts = 0, ns = 0;
+	u32 tmo = 0;
 	int rc;
 
-	rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_PATH_TX, &ts);
+	if (!ptp->txts_pending)
+		ptp->abs_txts_tmo = now + msecs_to_jiffies(ptp->txts_tmo);
+	if (!time_after_eq(now, ptp->abs_txts_tmo))
+		tmo = jiffies_to_msecs(ptp->abs_txts_tmo - now);
+	rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_PATH_TX, &ts,
+				     tmo);
 	if (!rc) {
 		memset(&timestamp, 0, sizeof(timestamp));
 		spin_lock_bh(&ptp->ptp_lock);
@@ -684,6 +697,10 @@ 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 {
+		if (!time_after_eq(jiffies, ptp->abs_txts_tmo)) {
+			ptp->txts_pending = true;
+			return;
+		}
 		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
@@ -691,6 +708,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 	dev_kfree_skb_any(ptp->tx_skb);
 	ptp->tx_skb = NULL;
 	atomic_inc(&ptp->tx_avail);
+	ptp->txts_pending = false;
 }
 
 static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
@@ -714,6 +732,8 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
 		spin_unlock_bh(&ptp->ptp_lock);
 		ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
 	}
+	if (ptp->txts_pending)
+		return 0;
 	return HZ;
 }
 
@@ -891,7 +911,8 @@ int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
 		if (rc)
 			return rc;
 	} else {
-		rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME, &ns);
+		rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME,
+					     &ns, 0);
 		if (rc)
 			return rc;
 	}
@@ -965,6 +986,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 		spin_unlock_bh(&ptp->ptp_lock);
 		ptp_schedule_worker(ptp->ptp_clock, 0);
 	}
+	ptp->txts_tmo = BNXT_PTP_DFLT_TX_TMO;
 	return 0;
 
 out:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index fce8dc39a7d0..2c3415c8fc03 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -22,7 +22,9 @@
 #define BNXT_LO_TIMER_MASK	0x0000ffffffffUL
 #define BNXT_HI_TIMER_MASK	0xffff00000000UL
 
+#define BNXT_PTP_DFLT_TX_TMO	1000 /* ms */
 #define BNXT_PTP_QTS_TIMEOUT	1000
+#define BNXT_PTP_QTS_MAX_TMO_US	65535U
 #define BNXT_PTP_QTS_TX_ENABLES	(PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID |	\
 				 PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT | \
 				 PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET)
@@ -115,11 +117,14 @@ struct bnxt_ptp_cfg {
 					 BNXT_PTP_MSG_PDELAY_REQ |	\
 					 BNXT_PTP_MSG_PDELAY_RESP)
 	u8			tx_tstamp_en:1;
+	u8			txts_pending:1;
 	int			rx_filter;
 	u32			tstamp_filters;
 
 	u32			refclk_regs[2];
 	u32			refclk_mapped_regs[2];
+	u32			txts_tmo;
+	unsigned long		abs_txts_tmo;
 };
 
 #if BITS_PER_LONG == 32
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 273c9ba48f09..d2ca90407cce 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -370,6 +370,7 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 			      struct bnxt_tc_flow *flow)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(tc_flow_cmd);
+	struct netlink_ext_ack *extack = tc_flow_cmd->common.extack;
 	struct flow_dissector *dissector = rule->match.dissector;
 
 	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
@@ -380,6 +381,9 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 195c02dc0683..ba3fa1c2e5d9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -31,21 +31,74 @@ static DEFINE_IDA(bnxt_aux_dev_ids);
 static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent)
 {
 	struct bnxt_en_dev *edev = bp->edev;
-	int num_msix, idx, i;
+	int num_msix, i;
 
 	if (!edev->ulp_tbl->msix_requested) {
 		netdev_warn(bp->dev, "Requested MSI-X vectors insufficient\n");
 		return;
 	}
 	num_msix = edev->ulp_tbl->msix_requested;
-	idx = edev->ulp_tbl->msix_base;
 	for (i = 0; i < num_msix; i++) {
-		ent[i].vector = bp->irq_tbl[idx + i].vector;
-		ent[i].ring_idx = idx + i;
+		ent[i].vector = bp->irq_tbl[i].vector;
+		ent[i].ring_idx = i;
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 			ent[i].db_offset = bp->db_offset;
 		else
-			ent[i].db_offset = (idx + i) * 0x80;
+			ent[i].db_offset = i * 0x80;
+	}
+}
+
+int bnxt_get_ulp_msix_num(struct bnxt *bp)
+{
+	if (bp->edev)
+		return bp->edev->ulp_num_msix_vec;
+	return 0;
+}
+
+void bnxt_set_ulp_msix_num(struct bnxt *bp, int num)
+{
+	if (bp->edev)
+		bp->edev->ulp_num_msix_vec = num;
+}
+
+int bnxt_get_ulp_msix_num_in_use(struct bnxt *bp)
+{
+	if (bnxt_ulp_registered(bp->edev))
+		return bp->edev->ulp_num_msix_vec;
+	return 0;
+}
+
+int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
+{
+	if (bp->edev)
+		return bp->edev->ulp_num_ctxs;
+	return 0;
+}
+
+void bnxt_set_ulp_stat_ctxs(struct bnxt *bp, int num_ulp_ctx)
+{
+	if (bp->edev)
+		bp->edev->ulp_num_ctxs = num_ulp_ctx;
+}
+
+int bnxt_get_ulp_stat_ctxs_in_use(struct bnxt *bp)
+{
+	if (bnxt_ulp_registered(bp->edev))
+		return bp->edev->ulp_num_ctxs;
+	return 0;
+}
+
+void bnxt_set_dflt_ulp_stat_ctxs(struct bnxt *bp)
+{
+	if (bp->edev) {
+		bp->edev->ulp_num_ctxs = BNXT_MIN_ROCE_STAT_CTXS;
+		/* Reserve one additional stat_ctx for PF0 (except
+		 * on 1-port NICs) as it also creates one stat_ctx
+		 * for PF1 in case of RoCE bonding.
+		 */
+		if (BNXT_PF(bp) && !bp->pf.port_id &&
+		    bp->port_count > 1)
+			bp->edev->ulp_num_ctxs++;
 	}
 }
 
@@ -57,25 +110,36 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	struct bnxt *bp = netdev_priv(dev);
 	unsigned int max_stat_ctxs;
 	struct bnxt_ulp *ulp;
+	int rc = 0;
 
+	rtnl_lock();
+	mutex_lock(&edev->en_dev_lock);
+	if (!bp->irq_tbl) {
+		rc = -ENODEV;
+		goto exit;
+	}
 	max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
 	if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
-	    bp->cp_nr_rings == max_stat_ctxs)
-		return -ENOMEM;
+	    bp->cp_nr_rings == max_stat_ctxs) {
+		rc = -ENOMEM;
+		goto exit;
+	}
 
 	ulp = edev->ulp_tbl;
-	if (!ulp)
-		return -ENOMEM;
-
 	ulp->handle = handle;
 	rcu_assign_pointer(ulp->ulp_ops, ulp_ops);
 
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
-		bnxt_hwrm_vnic_cfg(bp, 0);
+		bnxt_hwrm_vnic_cfg(bp, &bp->vnic_info[BNXT_VNIC_DEFAULT]);
+
+	edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp);
 
 	bnxt_fill_msix_vecs(bp, bp->edev->msix_entries);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
-	return 0;
+exit:
+	mutex_unlock(&edev->en_dev_lock);
+	rtnl_unlock();
+	return rc;
 }
 EXPORT_SYMBOL(bnxt_register_dev);
 
@@ -87,8 +151,11 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	int i = 0;
 
 	ulp = edev->ulp_tbl;
+	rtnl_lock();
+	mutex_lock(&edev->en_dev_lock);
 	if (ulp->msix_requested)
 		edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
+	edev->ulp_tbl->msix_requested = 0;
 
 	if (ulp->max_async_event_id)
 		bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true);
@@ -101,11 +168,13 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 		msleep(100);
 		i++;
 	}
+	mutex_unlock(&edev->en_dev_lock);
+	rtnl_unlock();
 	return;
 }
 EXPORT_SYMBOL(bnxt_unregister_dev);
 
-int bnxt_get_ulp_msix_num(struct bnxt *bp)
+static int bnxt_set_dflt_ulp_msix(struct bnxt *bp)
 {
 	u32 roce_msix = BNXT_VF(bp) ?
 			BNXT_MAX_VF_ROCE_MSIX : BNXT_MAX_ROCE_MSIX;
@@ -114,29 +183,6 @@ int bnxt_get_ulp_msix_num(struct bnxt *bp)
 		min_t(u32, roce_msix, num_online_cpus()) : 0);
 }
 
-int bnxt_get_ulp_msix_base(struct bnxt *bp)
-{
-	if (bnxt_ulp_registered(bp->edev)) {
-		struct bnxt_en_dev *edev = bp->edev;
-
-		if (edev->ulp_tbl->msix_requested)
-			return edev->ulp_tbl->msix_base;
-	}
-	return 0;
-}
-
-int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
-{
-	if (bnxt_ulp_registered(bp->edev)) {
-		struct bnxt_en_dev *edev = bp->edev;
-
-		if (edev->ulp_tbl->msix_requested)
-			return BNXT_MIN_ROCE_STAT_CTXS;
-	}
-
-	return 0;
-}
-
 int bnxt_send_msg(struct bnxt_en_dev *edev,
 			 struct bnxt_fw_msg *fw_msg)
 {
@@ -181,6 +227,12 @@ void bnxt_ulp_stop(struct bnxt *bp)
 	if (!edev)
 		return;
 
+	mutex_lock(&edev->en_dev_lock);
+	if (!bnxt_ulp_registered(edev)) {
+		mutex_unlock(&edev->en_dev_lock);
+		return;
+	}
+
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
 		struct auxiliary_device *adev;
@@ -195,6 +247,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 			adrv->suspend(adev, pm);
 		}
 	}
+	mutex_unlock(&edev->en_dev_lock);
 }
 
 void bnxt_ulp_start(struct bnxt *bp, int err)
@@ -210,6 +263,12 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	if (err)
 		return;
 
+	mutex_lock(&edev->en_dev_lock);
+	if (!bnxt_ulp_registered(edev)) {
+		mutex_unlock(&edev->en_dev_lock);
+		return;
+	}
+
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
 
@@ -225,7 +284,7 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 			adrv->resume(adev);
 		}
 	}
-
+	mutex_unlock(&edev->en_dev_lock);
 }
 
 void bnxt_ulp_irq_stop(struct bnxt *bp)
@@ -309,7 +368,6 @@ void bnxt_rdma_aux_device_uninit(struct bnxt *bp)
 
 	aux_priv = bp->aux_priv;
 	adev = &aux_priv->aux_dev;
-	auxiliary_device_delete(adev);
 	auxiliary_device_uninit(adev);
 }
 
@@ -327,6 +385,14 @@ static void bnxt_aux_dev_release(struct device *dev)
 	bp->aux_priv = NULL;
 }
 
+void bnxt_rdma_aux_device_del(struct bnxt *bp)
+{
+	if (!bp->edev)
+		return;
+
+	auxiliary_device_delete(&bp->aux_priv->aux_dev);
+}
+
 static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 {
 	edev->net = bp->dev;
@@ -334,6 +400,7 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 	edev->l2_db_size = bp->db_size;
 	edev->l2_db_size_nc = bp->db_size;
 	edev->l2_db_offset = bp->db_offset;
+	mutex_init(&edev->en_dev_lock);
 
 	if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
 		edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
@@ -347,7 +414,23 @@ static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
 	edev->pf_port_id = bp->pf.port_id;
 	edev->en_state = bp->state;
 	edev->bar0 = bp->bar0;
-	edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp);
+}
+
+void bnxt_rdma_aux_device_add(struct bnxt *bp)
+{
+	struct auxiliary_device *aux_dev;
+	int rc;
+
+	if (!bp->edev)
+		return;
+
+	aux_dev = &bp->aux_priv->aux_dev;
+	rc = auxiliary_device_add(aux_dev);
+	if (rc) {
+		netdev_warn(bp->dev, "Failed to add auxiliary device for ROCE\n");
+		auxiliary_device_uninit(aux_dev);
+		bp->flags &= ~BNXT_FLAG_ROCE_CAP;
+	}
 }
 
 void bnxt_rdma_aux_device_init(struct bnxt *bp)
@@ -404,13 +487,7 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp)
 	edev->ulp_tbl = ulp;
 	bp->edev = edev;
 	bnxt_set_edev_info(edev, bp);
-
-	rc = auxiliary_device_add(aux_dev);
-	if (rc) {
-		netdev_warn(bp->dev,
-			    "Failed to add auxiliary device for ROCE\n");
-		goto aux_dev_uninit;
-	}
+	bp->ulp_num_msix_want = bnxt_set_dflt_ulp_msix(bp);
 
 	return;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index b9e73de14b57..4eafe6ec0abf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -46,7 +46,6 @@ struct bnxt_ulp {
 	unsigned long	*async_events_bmap;
 	u16		max_async_event_id;
 	u16		msix_requested;
-	u16		msix_base;
 	atomic_t	ref_count;
 };
 
@@ -86,18 +85,28 @@ struct bnxt_en_dev {
 							 * updated in resume.
 							 */
 	void __iomem                    *bar0;
+
+	u16				ulp_num_msix_vec;
+	u16				ulp_num_ctxs;
+
+					/* serialize ulp operations */
+	struct mutex			en_dev_lock;
 };
 
 static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev)
 {
-	if (edev && edev->ulp_tbl)
+	if (edev && rcu_access_pointer(edev->ulp_tbl->ulp_ops))
 		return true;
 	return false;
 }
 
 int bnxt_get_ulp_msix_num(struct bnxt *bp);
-int bnxt_get_ulp_msix_base(struct bnxt *bp);
+int bnxt_get_ulp_msix_num_in_use(struct bnxt *bp);
+void bnxt_set_ulp_msix_num(struct bnxt *bp, int num);
 int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
+void bnxt_set_ulp_stat_ctxs(struct bnxt *bp, int num_ctxs);
+int bnxt_get_ulp_stat_ctxs_in_use(struct bnxt *bp);
+void bnxt_set_dflt_ulp_stat_ctxs(struct bnxt *bp);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp, int err);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
@@ -105,6 +114,8 @@ void bnxt_ulp_irq_stop(struct bnxt *bp);
 void bnxt_ulp_irq_restart(struct bnxt *bp, int err);
 void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl);
 void bnxt_rdma_aux_device_uninit(struct bnxt *bp);
+void bnxt_rdma_aux_device_del(struct bnxt *bp);
+void bnxt_rdma_aux_device_add(struct bnxt *bp);
 void bnxt_rdma_aux_device_init(struct bnxt *bp);
 int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops,
 		      void *handle);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 4079538bc310..345681d5007e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -197,7 +197,7 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
 
 	xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
-	xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
+	xdp_prepare_buff(xdp, data_ptr - offset, offset, len, true);
 }
 
 void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
@@ -222,7 +222,7 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
  * false   - packet should be passed to the stack.
  */
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+		 struct xdp_buff *xdp, struct page *page, u8 **data_ptr,
 		 unsigned int *len, u8 *event)
 {
 	struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
@@ -244,9 +244,9 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 	txr = rxr->bnapi->tx_ring[0];
 	/* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
-	orig_data = xdp.data;
+	orig_data = xdp->data;
 
-	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	tx_avail = bnxt_tx_avail(bp, txr);
 	/* If the tx ring is not full, we must not update the rx producer yet
@@ -255,10 +255,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	if (tx_avail != bp->tx_ring_size)
 		*event &= ~BNXT_RX_EVENT;
 
-	*len = xdp.data_end - xdp.data;
-	if (orig_data != xdp.data) {
-		offset = xdp.data - xdp.data_hard_start;
-		*data_ptr = xdp.data_hard_start + offset;
+	*len = xdp->data_end - xdp->data;
+	if (orig_data != xdp->data) {
+		offset = xdp->data - xdp->data_hard_start;
+		*data_ptr = xdp->data_hard_start + offset;
 	}
 
 	switch (act) {
@@ -270,8 +270,8 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		mapping = rx_buf->mapping - bp->rx_dma_offset;
 		*event &= BNXT_TX_CMP_EVENT;
 
-		if (unlikely(xdp_buff_has_frags(&xdp))) {
-			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(&xdp);
+		if (unlikely(xdp_buff_has_frags(xdp))) {
+			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 			tx_needed += sinfo->nr_frags;
 			*event = BNXT_AGG_EVENT;
@@ -279,7 +279,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 		if (tx_avail < tx_needed) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
-			bnxt_xdp_buff_frags_free(rxr, &xdp);
+			bnxt_xdp_buff_frags_free(rxr, xdp);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
 		}
@@ -289,7 +289,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 		*event |= BNXT_TX_EVENT;
 		__bnxt_xmit_xdp(bp, txr, mapping + offset, *len,
-				NEXT_RX(rxr->rx_prod), &xdp);
+				NEXT_RX(rxr->rx_prod), xdp);
 		bnxt_reuse_rx_data(rxr, cons, page);
 		return true;
 	case XDP_REDIRECT:
@@ -306,12 +306,12 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		/* if we are unable to allocate a new buffer, abort and reuse */
 		if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
-			bnxt_xdp_buff_frags_free(rxr, &xdp);
+			bnxt_xdp_buff_frags_free(rxr, xdp);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
 		}
 
-		if (xdp_do_redirect(bp->dev, &xdp, xdp_prog)) {
+		if (xdp_do_redirect(bp->dev, xdp, xdp_prog)) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
 			page_pool_recycle_direct(rxr->page_pool, page);
 			return true;
@@ -326,7 +326,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		trace_xdp_exception(bp->dev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
-		bnxt_xdp_buff_frags_free(rxr, &xdp);
+		bnxt_xdp_buff_frags_free(rxr, xdp);
 		bnxt_reuse_rx_data(rxr, cons, page);
 		break;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 5e412c5655ba..0122782400b8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -18,7 +18,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 				   struct xdp_buff *xdp);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+		 struct xdp_buff *xdp, struct page *page, u8 **data_ptr,
 		 unsigned int *len, u8 *event);
 int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 3d63177e7e52..c2b4188a1ef1 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -3682,7 +3682,8 @@ static int cnic_get_v4_route(struct sockaddr_in *dst_addr,
 #if defined(CONFIG_INET)
 	struct rtable *rt;
 
-	rt = ip_route_output(&init_net, dst_addr->sin_addr.s_addr, 0, 0, 0);
+	rt = ip_route_output(&init_net, dst_addr->sin_addr.s_addr, 0, 0, 0,
+			     RT_SCOPE_UNIVERSE);
 	if (!IS_ERR(rt)) {
 		*dst = &rt->dst;
 		return 0;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 62ff4381ac83..1589a49b876c 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -4019,7 +4019,7 @@ static int tg3_power_up(struct tg3 *tp)
 
 static int tg3_setup_phy(struct tg3 *, bool);
 
-static int tg3_power_down_prepare(struct tg3 *tp)
+static void tg3_power_down_prepare(struct tg3 *tp)
 {
 	u32 misc_host_ctrl;
 	bool device_should_wake, do_low_power;
@@ -4263,7 +4263,7 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 
 	tg3_ape_driver_state_change(tp, RESET_KIND_SHUTDOWN);
 
-	return 0;
+	return;
 }
 
 static void tg3_power_down(struct tg3 *tp)
@@ -14295,7 +14295,7 @@ static void tg3_set_rx_mode(struct net_device *dev)
 static inline void tg3_set_mtu(struct net_device *dev, struct tg3 *tp,
 			       int new_mtu)
 {
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (new_mtu > ETH_DATA_LEN) {
 		if (tg3_flag(tp, 5780_CLASS)) {
@@ -18084,7 +18084,6 @@ static int tg3_suspend(struct device *device)
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct tg3 *tp = netdev_priv(dev);
-	int err = 0;
 
 	rtnl_lock();
 
@@ -18108,32 +18107,11 @@ static int tg3_suspend(struct device *device)
 	tg3_flag_clear(tp, INIT_COMPLETE);
 	tg3_full_unlock(tp);
 
-	err = tg3_power_down_prepare(tp);
-	if (err) {
-		int err2;
-
-		tg3_full_lock(tp, 0);
-
-		tg3_flag_set(tp, INIT_COMPLETE);
-		err2 = tg3_restart_hw(tp, true);
-		if (err2)
-			goto out;
-
-		tg3_timer_start(tp);
-
-		netif_device_attach(dev);
-		tg3_netif_start(tp);
-
-out:
-		tg3_full_unlock(tp);
-
-		if (!err2)
-			tg3_phy_start(tp);
-	}
+	tg3_power_down_prepare(tp);
 
 unlock:
 	rtnl_unlock();
-	return err;
+	return 0;
 }
 
 static int tg3_resume(struct device *device)
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index c32174484a96..fe121d36112d 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3276,7 +3276,7 @@ bnad_change_mtu(struct net_device *netdev, int new_mtu)
 	mutex_lock(&bnad->conf_mutex);
 
 	mtu = netdev->mtu;
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	frame = BNAD_FRAME_SIZE(mtu);
 	new_frame = BNAD_FRAME_SIZE(new_mtu);
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 898debfd4db3..241ce9a2fa99 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3022,7 +3022,7 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu)
 	if (netif_running(dev))
 		return -EBUSY;
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 5e97f1e4e38e..a71b320fd030 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -1358,7 +1358,7 @@ static int xgmac_change_mtu(struct net_device *dev, int new_mtu)
 
 	/* Bring interface down, change mtu and bring interface back up */
 	xgmac_stop(dev);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return xgmac_open(dev);
 }
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index f38d31bfab1b..674c54831875 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -1262,7 +1262,7 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EINVAL;
 	}
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	lio->mtu = new_mtu;
 
 	WRITE_ONCE(sc->caller_is_done, true);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index aa6c0dfb6f1c..96c6ea12279f 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -218,7 +218,7 @@ lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu)
 		return -EIO;
 	}
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 007d4b06819e..744f2434f7fa 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -649,7 +649,7 @@ static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu)
 	struct octeon_mgmt *p = netdev_priv(netdev);
 	int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	/* HW lifts the limit if the frame is VLAN tagged
 	 * (+4 bytes per each tag, up to two tags)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index eff350e0bc2a..aebb9fef3f6e 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1589,7 +1589,7 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EINVAL;
 	}
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (!netif_running(netdev))
 		return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index d2286adf09fe..7d7d3e0098df 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -844,7 +844,7 @@ static int t1_change_mtu(struct net_device *dev, int new_mtu)
 		return -EOPNOTSUPP;
 	if ((ret = mac->ops->set_mtu(mac, new_mtu)))
 		return ret;
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 2236f1d35f2b..f92a3550e480 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2559,7 +2559,7 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 
 	if ((ret = t3_mac_set_mtu(&pi->mac, new_mtu)))
 		return ret;
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	init_port_mtus(adapter);
 	if (adapter->params.rev == 0 && offload_running(adapter))
 		t3_load_mtus(adapter, adapter->params.mtus,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 2eb33a727bba..2418645c8823 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3180,7 +3180,7 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 	ret = t4_set_rxmode(pi->adapter, pi->adapter->mbox, pi->viid,
 			    pi->viid_mirror, new_mtu, -1, -1, -1, -1, true);
 	if (!ret)
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 72ac4a34424b..69d045d769c4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -305,7 +305,7 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 	fs->mask.iport = ~0;
 }
 
-static int cxgb4_validate_flow_match(struct net_device *dev,
+static int cxgb4_validate_flow_match(struct netlink_ext_ack *extack,
 				     struct flow_rule *rule)
 {
 	struct flow_dissector *dissector = rule->match.dissector;
@@ -321,11 +321,15 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IP))) {
-		netdev_warn(dev, "Unsupported key used: 0x%llx\n",
-			    dissector->used_keys);
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Unsupported key used: 0x%llx",
+				       dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
 
@@ -339,13 +343,15 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
 		struct flow_match_ip match;
 
 		if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) {
-			netdev_err(dev, "IP Key supported only with IPv4/v6");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "IP Key supported only with IPv4/v6");
 			return -EINVAL;
 		}
 
 		flow_rule_match_ip(rule, &match);
 		if (match.mask->ttl) {
-			netdev_warn(dev, "ttl match unsupported for offload");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "ttl match unsupported for offload");
 			return -EOPNOTSUPP;
 		}
 	}
@@ -576,7 +582,7 @@ static bool valid_l4_mask(u32 mask)
 	return hi && lo ? false : true;
 }
 
-static bool valid_pedit_action(struct net_device *dev,
+static bool valid_pedit_action(struct netlink_ext_ack *extack,
 			       const struct flow_action_entry *act,
 			       u8 *natmode_flags)
 {
@@ -595,8 +601,7 @@ static bool valid_pedit_action(struct net_device *dev,
 		case PEDIT_ETH_SMAC_47_16:
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit field\n",
-				   __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit field");
 			return false;
 		}
 		break;
@@ -609,8 +614,7 @@ static bool valid_pedit_action(struct net_device *dev,
 			*natmode_flags |= CXGB4_ACTION_NATMODE_DIP;
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit field\n",
-				   __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit field");
 			return false;
 		}
 		break;
@@ -629,8 +633,7 @@ static bool valid_pedit_action(struct net_device *dev,
 			*natmode_flags |= CXGB4_ACTION_NATMODE_DIP;
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit field\n",
-				   __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit field");
 			return false;
 		}
 		break;
@@ -638,8 +641,8 @@ static bool valid_pedit_action(struct net_device *dev,
 		switch (offset) {
 		case PEDIT_TCP_SPORT_DPORT:
 			if (!valid_l4_mask(~mask)) {
-				netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
-					   __func__);
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported mask for TCP L4 ports");
 				return false;
 			}
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -648,8 +651,7 @@ static bool valid_pedit_action(struct net_device *dev,
 				*natmode_flags |= CXGB4_ACTION_NATMODE_DPORT;
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit field\n",
-				   __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit field");
 			return false;
 		}
 		break;
@@ -657,8 +659,8 @@ static bool valid_pedit_action(struct net_device *dev,
 		switch (offset) {
 		case PEDIT_UDP_SPORT_DPORT:
 			if (!valid_l4_mask(~mask)) {
-				netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
-					   __func__);
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported mask for UDP L4 ports");
 				return false;
 			}
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -667,13 +669,12 @@ static bool valid_pedit_action(struct net_device *dev,
 				*natmode_flags |= CXGB4_ACTION_NATMODE_DPORT;
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit field\n",
-				   __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit field");
 			return false;
 		}
 		break;
 	default:
-		netdev_err(dev, "%s: Unsupported pedit type\n", __func__);
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit type");
 		return false;
 	}
 	return true;
@@ -727,8 +728,7 @@ int cxgb4_validate_flow_actions(struct net_device *dev,
 			 * the provided output port is not valid
 			 */
 			if (!found) {
-				netdev_err(dev, "%s: Out port invalid\n",
-					   __func__);
+				NL_SET_ERR_MSG_MOD(extack, "Out port invalid");
 				return -EINVAL;
 			}
 			act_redir = true;
@@ -745,21 +745,21 @@ int cxgb4_validate_flow_actions(struct net_device *dev,
 			case FLOW_ACTION_VLAN_PUSH:
 			case FLOW_ACTION_VLAN_MANGLE:
 				if (proto != ETH_P_8021Q) {
-					netdev_err(dev, "%s: Unsupported vlan proto\n",
-						   __func__);
+					NL_SET_ERR_MSG_MOD(extack,
+							   "Unsupported vlan proto");
 					return -EOPNOTSUPP;
 				}
 				break;
 			default:
-				netdev_err(dev, "%s: Unsupported vlan action\n",
-					   __func__);
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Unsupported vlan action");
 				return -EOPNOTSUPP;
 			}
 			act_vlan = true;
 			}
 			break;
 		case FLOW_ACTION_MANGLE: {
-			bool pedit_valid = valid_pedit_action(dev, act,
+			bool pedit_valid = valid_pedit_action(extack, act,
 							      &natmode_flags);
 
 			if (!pedit_valid)
@@ -771,14 +771,14 @@ int cxgb4_validate_flow_actions(struct net_device *dev,
 			/* Do nothing. cxgb4_set_filter will validate */
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported action\n", __func__);
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
 			return -EOPNOTSUPP;
 		}
 	}
 
 	if ((act_pedit || act_vlan) && !act_redir) {
-		netdev_err(dev, "%s: pedit/vlan rewrite invalid without egress redirect\n",
-			   __func__);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "pedit/vlan rewrite invalid without egress redirect");
 		return -EINVAL;
 	}
 
@@ -864,7 +864,7 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule,
 	if (cxgb4_validate_flow_actions(dev, &rule->action, extack, 0))
 		return -EOPNOTSUPP;
 
-	if (cxgb4_validate_flow_match(dev, rule))
+	if (cxgb4_validate_flow_match(extack, rule))
 		return -EOPNOTSUPP;
 
 	cxgb4_process_flow_match(dev, rule, fs);
@@ -901,8 +901,7 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule,
 	init_completion(&ctx.completion);
 	ret = __cxgb4_set_filter(dev, fidx, fs, &ctx);
 	if (ret) {
-		netdev_err(dev, "%s: filter creation err %d\n",
-			   __func__, ret);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "filter creation err %d", ret);
 		return ret;
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 17faac715882..5c13bcb4550d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -406,7 +406,7 @@ free_sge_txq_uld(struct adapter *adap, struct sge_uld_txq_info *txq_info)
 	for (i = 0; i < nq; i++) {
 		struct sge_uld_txq *txq = &txq_info->uldtxq[i];
 
-		if (txq && txq->q.desc) {
+		if (txq->q.desc) {
 			tasklet_kill(&txq->qresume_tsk);
 			t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0,
 					txq->q.cntxt_id);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 9ba0864592e8..2fbe0f059a0b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1169,7 +1169,7 @@ static int cxgb4vf_change_mtu(struct net_device *dev, int new_mtu)
 	ret = t4vf_set_rxmode(pi->adapter, pi->viid, new_mtu,
 			      -1, -1, -1, -1, true);
 	if (!ret)
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 6482728794dd..e8e460a92e0e 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -10,6 +10,7 @@
 #include <net/ipv6.h>
 #include <linux/netdevice.h>
 #include <crypto/aes.h>
+#include <linux/skbuff_ref.h>
 #include "chcr_ktls.h"
 
 static LIST_HEAD(uld_ctx_list);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index d266a87297a5..f604119efc80 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2027,7 +2027,7 @@ static int _enic_change_mtu(struct net_device *netdev, int new_mtu)
 			return err;
 	}
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (running) {
 		err = enic_open(netdev);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 12a83fa1302d..9f6089e81608 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -146,23 +146,19 @@ EXPORT_SYMBOL(vnic_dev_get_res);
 static unsigned int vnic_dev_desc_ring_size(struct vnic_dev_ring *ring,
 	unsigned int desc_count, unsigned int desc_size)
 {
-	/* The base address of the desc rings must be 512 byte aligned.
-	 * Descriptor count is aligned to groups of 32 descriptors.  A
-	 * count of 0 means the maximum 4096 descriptors.  Descriptor
-	 * size is aligned to 16 bytes.
-	 */
-
-	unsigned int count_align = 32;
-	unsigned int desc_align = 16;
 
-	ring->base_align = 512;
+	/* Descriptor ring base address alignment in bytes*/
+	ring->base_align = VNIC_DESC_BASE_ALIGN;
 
+	/* A count of 0 means the maximum descriptors */
 	if (desc_count == 0)
-		desc_count = 4096;
+		desc_count = VNIC_DESC_MAX_COUNT;
 
-	ring->desc_count = ALIGN(desc_count, count_align);
+	/* Descriptor count aligned in groups of VNIC_DESC_COUNT_ALIGN descriptors */
+	ring->desc_count = ALIGN(desc_count, VNIC_DESC_COUNT_ALIGN);
 
-	ring->desc_size = ALIGN(desc_size, desc_align);
+	/* Descriptor size alignment in bytes */
+	ring->desc_size = ALIGN(desc_size, VNIC_DESC_SIZE_ALIGN);
 
 	ring->size = ring->desc_count * ring->desc_size;
 	ring->size_unaligned = ring->size + ring->base_align;
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.h b/drivers/net/ethernet/cisco/enic/vnic_dev.h
index 6273794b923b..7fdd8c661c99 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.h
@@ -31,6 +31,11 @@ static inline void writeq(u64 val, void __iomem *reg)
 #undef pr_fmt
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#define VNIC_DESC_SIZE_ALIGN	16
+#define VNIC_DESC_COUNT_ALIGN	32
+#define VNIC_DESC_BASE_ALIGN	512
+#define VNIC_DESC_MAX_COUNT	4096
+
 enum vnic_dev_intr_mode {
 	VNIC_DEV_INTR_MODE_UNKNOWN,
 	VNIC_DEV_INTR_MODE_INTX,
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 705c3eb19cd3..5f0c9e1771db 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1107,10 +1107,13 @@ static void gmac_tx_irq_enable(struct net_device *netdev,
 {
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 	struct gemini_ethernet *geth = port->geth;
+	unsigned long flags;
 	u32 val, mask;
 
 	netdev_dbg(netdev, "%s device %d\n", __func__, netdev->dev_id);
 
+	spin_lock_irqsave(&geth->irq_lock, flags);
+
 	mask = GMAC0_IRQ0_TXQ0_INTS << (6 * netdev->dev_id + txq);
 
 	if (en)
@@ -1119,6 +1122,8 @@ static void gmac_tx_irq_enable(struct net_device *netdev,
 	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
 	val = en ? val | mask : val & ~mask;
 	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
 }
 
 static void gmac_tx_irq(struct net_device *netdev, unsigned int txq_num)
@@ -1415,15 +1420,19 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget)
 	union gmac_rxdesc_3 word3;
 	struct page *page = NULL;
 	unsigned int page_offs;
+	unsigned long flags;
 	unsigned short r, w;
 	union dma_rwptr rw;
 	dma_addr_t mapping;
 	int frag_nr = 0;
 
+	spin_lock_irqsave(&geth->irq_lock, flags);
 	rw.bits32 = readl(ptr_reg);
 	/* Reset interrupt as all packages until here are taken into account */
 	writel(DEFAULT_Q0_INT_BIT << netdev->dev_id,
 	       geth->base + GLOBAL_INTERRUPT_STATUS_1_REG);
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+
 	r = rw.bits.rptr;
 	w = rw.bits.wptr;
 
@@ -1726,10 +1735,9 @@ static irqreturn_t gmac_irq(int irq, void *data)
 		gmac_update_hw_stats(netdev);
 
 	if (val & (GMAC0_RX_OVERRUN_INT_BIT << (netdev->dev_id * 8))) {
+		spin_lock(&geth->irq_lock);
 		writel(GMAC0_RXDERR_INT_BIT << (netdev->dev_id * 8),
 		       geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
-
-		spin_lock(&geth->irq_lock);
 		u64_stats_update_begin(&port->ir_stats_syncp);
 		++port->stats.rx_fifo_errors;
 		u64_stats_update_end(&port->ir_stats_syncp);
@@ -1978,7 +1986,7 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu)
 
 	gmac_disable_tx_rx(netdev);
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	gmac_update_config0_reg(netdev, max_len << CONFIG0_MAXLEN_SHIFT,
 				CONFIG0_MAXLEN_MASK);
 
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index aaf0eda96292..8af5ecec7d61 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -708,7 +708,7 @@ static int change_mtu(struct net_device *dev, int new_mtu)
 {
 	if (netif_running(dev))
 		return -EBUSY;
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index ad862ed7888a..a8596ebcdfd6 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4982,10 +4982,7 @@ static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
 		mode = nla_get_u16(attr);
 		if (BE3_chip(adapter) && mode == BRIDGE_MODE_VEPA)
 			return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 003bc9a45c65..1047c805054e 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1092,7 +1092,7 @@ static int ftmac100_change_mtu(struct net_device *netdev, int mtu)
 	}
 	iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR);
 
-	netdev->mtu = mtu;
+	WRITE_ONCE(netdev->mtu, mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index dcbc598b11c6..baa0b3c2ce6f 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2995,7 +2995,7 @@ static int dpaa_change_mtu(struct net_device *net_dev, int new_mtu)
 	if (priv->xdp_prog && !xdp_validate_mtu(priv, new_mtu))
 		return -EINVAL;
 
-	net_dev->mtu = new_mtu;
+	WRITE_ONCE(net_dev->mtu, new_mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 888509cf1f21..6866807973da 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2698,7 +2698,7 @@ static int dpaa2_eth_change_mtu(struct net_device *dev, int new_mtu)
 		return err;
 
 out:
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 
@@ -2896,11 +2896,14 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 static int update_xps(struct dpaa2_eth_priv *priv)
 {
 	struct net_device *net_dev = priv->net_dev;
-	struct cpumask xps_mask;
-	struct dpaa2_eth_fq *fq;
 	int i, num_queues, netdev_queues;
+	struct dpaa2_eth_fq *fq;
+	cpumask_var_t xps_mask;
 	int err = 0;
 
+	if (!alloc_cpumask_var(&xps_mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	num_queues = dpaa2_eth_queue_count(priv);
 	netdev_queues = (net_dev->num_tc ? : 1) * num_queues;
 
@@ -2910,16 +2913,17 @@ static int update_xps(struct dpaa2_eth_priv *priv)
 	for (i = 0; i < netdev_queues; i++) {
 		fq = &priv->fq[i % num_queues];
 
-		cpumask_clear(&xps_mask);
-		cpumask_set_cpu(fq->target_cpu, &xps_mask);
+		cpumask_clear(xps_mask);
+		cpumask_set_cpu(fq->target_cpu, xps_mask);
 
-		err = netif_set_xps_queue(net_dev, &xps_mask, i);
+		err = netif_set_xps_queue(net_dev, xps_mask, i);
 		if (err) {
 			netdev_warn_once(net_dev, "Error setting XPS queue\n");
 			break;
 		}
 	}
 
+	free_cpumask_var(xps_mask);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index b6a534a3e0b1..701a87370737 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -33,6 +33,9 @@ static int dpaa2_switch_flower_parse_key(struct flow_cls_offload *cls,
 	acl_h = &acl_key->match;
 	acl_m = &acl_key->mask;
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
 
@@ -548,6 +551,9 @@ static int dpaa2_switch_flower_parse_mirror_key(struct flow_cls_offload *cls,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
 		struct flow_match_vlan match;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index f3543a2df68d..a71f848adc05 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -590,7 +590,7 @@ static int dpaa2_switch_port_change_mtu(struct net_device *netdev, int mtu)
 		return err;
 	}
 
-	netdev->mtu = mtu;
+	WRITE_ONCE(netdev->mtu, mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 9f07f4947b63..5c45f42232d3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2769,7 +2769,7 @@ static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog,
 	if (priv->min_num_stack_tx_queues + num_xdp_tx_queues >
 	    priv->num_tx_rings) {
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)",
+				       "Reserving %d XDP TXQs leaves under %d for stack (total %d)",
 				       num_xdp_tx_queues,
 				       priv->min_num_stack_tx_queues,
 				       priv->num_tx_rings);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8bd213da8fb6..a72d8a2eb0b3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3674,29 +3674,6 @@ fec_set_mac_address(struct net_device *ndev, void *p)
 	return 0;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/**
- * fec_poll_controller - FEC Poll controller function
- * @dev: The FEC network adapter
- *
- * Polled functionality used by netconsole and others in non interrupt mode
- *
- */
-static void fec_poll_controller(struct net_device *dev)
-{
-	int i;
-	struct fec_enet_private *fep = netdev_priv(dev);
-
-	for (i = 0; i < FEC_IRQ_NUM; i++) {
-		if (fep->irq[i] > 0) {
-			disable_irq(fep->irq[i]);
-			fec_enet_interrupt(fep->irq[i], dev);
-			enable_irq(fep->irq[i]);
-		}
-	}
-}
-#endif
-
 static inline void fec_enet_set_netdev_features(struct net_device *netdev,
 	netdev_features_t features)
 {
@@ -4003,9 +3980,6 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_tx_timeout		= fec_timeout,
 	.ndo_set_mac_address	= fec_set_mac_address,
 	.ndo_eth_ioctl		= phy_do_ioctl_running,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= fec_poll_controller,
-#endif
 	.ndo_set_features	= fec_set_features,
 	.ndo_bpf		= fec_enet_bpf,
 	.ndo_xdp_xmit		= fec_enet_xdp_xmit,
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 758535adc9ff..92b8f4ab26f1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -267,7 +267,6 @@ struct memac_cfg {
 	bool reset_on_init;
 	bool pause_ignore;
 	bool promiscuous_mode_enable;
-	struct fixed_phy_status *fixed_link;
 	u16 max_frame_length;
 	u16 pause_quanta;
 	u32 tx_ipg_length;
diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.c b/drivers/net/ethernet/freescale/fman/fman_muram.c
index f557d68e5b76..1ed245a2ee01 100644
--- a/drivers/net/ethernet/freescale/fman/fman_muram.c
+++ b/drivers/net/ethernet/freescale/fman/fman_muram.c
@@ -12,7 +12,6 @@
 struct muram_info {
 	struct gen_pool *pool;
 	void __iomem *vbase;
-	size_t size;
 	phys_addr_t pbase;
 };
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index a811238c018d..2baef59f741d 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2026,7 +2026,7 @@ static int gfar_change_mtu(struct net_device *dev, int new_mtu)
 	if (dev->flags & IFF_UP)
 		stop_gfar(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (dev->flags & IFF_UP)
 		startup_gfar(dev);
diff --git a/drivers/net/ethernet/fujitsu/Kconfig b/drivers/net/ethernet/fujitsu/Kconfig
index 0a1400cb410a..06a28bce5d27 100644
--- a/drivers/net/ethernet/fujitsu/Kconfig
+++ b/drivers/net/ethernet/fujitsu/Kconfig
@@ -18,7 +18,7 @@ if NET_VENDOR_FUJITSU
 
 config PCMCIA_FMVJ18X
 	tristate "Fujitsu FMV-J18x PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	select CRC32
 	help
 	  Say Y here if you intend to attach a Fujitsu FMV-J18x or compatible
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c
index df86770731ad..ac86179a0a81 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_main.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c
@@ -927,7 +927,7 @@ static int fun_change_mtu(struct net_device *netdev, int new_mtu)
 
 	rc = fun_port_write_cmd(fp, FUN_ADMIN_PORT_KEY_MTU, new_mtu);
 	if (!rc)
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 4814c96d5fe7..ae1e21c9b0a5 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -50,6 +50,10 @@
 /* PTYPEs are always 10 bits. */
 #define GVE_NUM_PTYPES	1024
 
+/* Default minimum ring size */
+#define GVE_DEFAULT_MIN_TX_RING_SIZE 256
+#define GVE_DEFAULT_MIN_RX_RING_SIZE 512
+
 #define GVE_DEFAULT_RX_BUFFER_SIZE 2048
 
 #define GVE_MAX_RX_BUFFER_SIZE 4096
@@ -63,7 +67,6 @@
 #define GVE_DEFAULT_HEADER_BUFFER_SIZE 128
 
 #define DQO_QPL_DEFAULT_TX_PAGES 512
-#define DQO_QPL_DEFAULT_RX_PAGES 2048
 
 /* Maximum TSO size supported on DQO */
 #define GVE_DQO_TX_MAX	0x3FFFF
@@ -607,6 +610,7 @@ struct gve_notify_block {
 	struct gve_priv *priv;
 	struct gve_tx_ring *tx; /* tx rings on this block */
 	struct gve_rx_ring *rx; /* rx rings on this block */
+	u32 irq;
 };
 
 /* Tracks allowed and current queue settings */
@@ -621,11 +625,6 @@ struct gve_qpl_config {
 	unsigned long *qpl_id_map; /* bitmap of used qpl ids */
 };
 
-struct gve_options_dqo_rda {
-	u16 tx_comp_ring_entries; /* number of tx_comp descriptors */
-	u16 rx_buff_ring_entries; /* number of rx_buff descriptors */
-};
-
 struct gve_irq_db {
 	__be32 index;
 } ____cacheline_aligned;
@@ -639,28 +638,10 @@ struct gve_ptype_lut {
 	struct gve_ptype ptypes[GVE_NUM_PTYPES];
 };
 
-/* Parameters for allocating queue page lists */
-struct gve_qpls_alloc_cfg {
-	struct gve_qpl_config *qpl_cfg;
-	struct gve_queue_config *tx_cfg;
-	struct gve_queue_config *rx_cfg;
-
-	u16 num_xdp_queues;
-	bool raw_addressing;
-	bool is_gqi;
-
-	/* Allocated resources are returned here */
-	struct gve_queue_page_list *qpls;
-};
-
 /* Parameters for allocating resources for tx queues */
 struct gve_tx_alloc_rings_cfg {
 	struct gve_queue_config *qcfg;
 
-	/* qpls and qpl_cfg must already be allocated */
-	struct gve_queue_page_list *qpls;
-	struct gve_qpl_config *qpl_cfg;
-
 	u16 ring_size;
 	u16 start_idx;
 	u16 num_rings;
@@ -676,10 +657,6 @@ struct gve_rx_alloc_rings_cfg {
 	struct gve_queue_config *qcfg;
 	struct gve_queue_config *qcfg_tx;
 
-	/* qpls and qpl_cfg must already be allocated */
-	struct gve_queue_page_list *qpls;
-	struct gve_qpl_config *qpl_cfg;
-
 	u16 ring_size;
 	u16 packet_buffer_size;
 	bool raw_addressing;
@@ -705,7 +682,6 @@ struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
 	struct gve_rx_ring *rx; /* array of rx_cfg.num_queues */
-	struct gve_queue_page_list *qpls; /* array of num qpls */
 	struct gve_notify_block *ntfy_blocks; /* array of num_ntfy_blks */
 	struct gve_irq_db *irq_db_indices; /* array of num_ntfy_blks */
 	dma_addr_t irq_db_indices_bus;
@@ -718,9 +694,13 @@ struct gve_priv {
 	u16 num_event_counters;
 	u16 tx_desc_cnt; /* num desc per ring */
 	u16 rx_desc_cnt; /* num desc per ring */
+	u16 max_tx_desc_cnt;
+	u16 max_rx_desc_cnt;
+	u16 min_tx_desc_cnt;
+	u16 min_rx_desc_cnt;
+	bool modify_ring_size_enabled;
+	bool default_min_ring_size;
 	u16 tx_pages_per_qpl; /* Suggested number of pages per qpl for TX queues by NIC */
-	u16 rx_pages_per_qpl; /* Suggested number of pages per qpl for RX queues by NIC */
-	u16 rx_data_slot_cnt; /* rx buffer length */
 	u64 max_registered_pages;
 	u64 num_registered_pages; /* num pages registered with NIC */
 	struct bpf_prog *xdp_prog; /* XDP BPF program */
@@ -730,7 +710,6 @@ struct gve_priv {
 	u16 num_xdp_queues;
 	struct gve_queue_config tx_cfg;
 	struct gve_queue_config rx_cfg;
-	struct gve_qpl_config qpl_cfg; /* map used QPL ids */
 	u32 num_ntfy_blks; /* spilt between TX and RX so must be even */
 
 	struct gve_registers __iomem *reg_bar0; /* see gve_register.h */
@@ -792,7 +771,6 @@ struct gve_priv {
 	u64 link_speed;
 	bool up_before_suspend; /* True if dev was up before suspend */
 
-	struct gve_options_dqo_rda options_dqo_rda;
 	struct gve_ptype_lut *ptype_lut_dqo;
 
 	/* Must be a power of two. */
@@ -1027,7 +1005,6 @@ static inline u32 gve_rx_qpl_id(struct gve_priv *priv, int rx_qid)
 	return priv->tx_cfg.max_queues + rx_qid;
 }
 
-/* Returns the index into priv->qpls where a certain rx queue's QPL resides */
 static inline u32 gve_get_rx_qpl_id(const struct gve_queue_config *tx_cfg, int rx_qid)
 {
 	return tx_cfg->max_queues + rx_qid;
@@ -1038,41 +1015,17 @@ static inline u32 gve_tx_start_qpl_id(struct gve_priv *priv)
 	return gve_tx_qpl_id(priv, 0);
 }
 
-/* Returns the index into priv->qpls where the first rx queue's QPL resides */
 static inline u32 gve_rx_start_qpl_id(const struct gve_queue_config *tx_cfg)
 {
 	return gve_get_rx_qpl_id(tx_cfg, 0);
 }
 
-/* Returns a pointer to the next available tx qpl in the list of qpls */
-static inline
-struct gve_queue_page_list *gve_assign_tx_qpl(struct gve_tx_alloc_rings_cfg *cfg,
-					      int tx_qid)
-{
-	/* QPL already in use */
-	if (test_bit(tx_qid, cfg->qpl_cfg->qpl_id_map))
-		return NULL;
-	set_bit(tx_qid, cfg->qpl_cfg->qpl_id_map);
-	return &cfg->qpls[tx_qid];
-}
-
-/* Returns a pointer to the next available rx qpl in the list of qpls */
-static inline
-struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_rx_alloc_rings_cfg *cfg,
-					      int rx_qid)
+static inline u32 gve_get_rx_pages_per_qpl_dqo(u32 rx_desc_cnt)
 {
-	int id = gve_get_rx_qpl_id(cfg->qcfg_tx, rx_qid);
-	/* QPL already in use */
-	if (test_bit(id, cfg->qpl_cfg->qpl_id_map))
-		return NULL;
-	set_bit(id, cfg->qpl_cfg->qpl_id_map);
-	return &cfg->qpls[id];
-}
-
-/* Unassigns the qpl with the given id */
-static inline void gve_unassign_qpl(struct gve_qpl_config *qpl_cfg, int id)
-{
-	clear_bit(id, qpl_cfg->qpl_id_map);
+	/* For DQO, page count should be more than ring size for
+	 * out-of-order completions. Set it to two times of ring size.
+	 */
+	return 2 * rx_desc_cnt;
 }
 
 /* Returns the correct dma direction for tx and rx qpls */
@@ -1115,6 +1068,12 @@ int gve_alloc_page(struct gve_priv *priv, struct device *dev,
 		   enum dma_data_direction, gfp_t gfp_flags);
 void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
 		   enum dma_data_direction);
+/* qpls */
+struct gve_queue_page_list *gve_alloc_queue_page_list(struct gve_priv *priv,
+						      u32 id, int pages);
+void gve_free_queue_page_list(struct gve_priv *priv,
+			      struct gve_queue_page_list *qpl,
+			      u32 id);
 /* tx handling */
 netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev);
 int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
@@ -1137,6 +1096,12 @@ bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx);
 void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx);
 int gve_rx_poll(struct gve_notify_block *block, int budget);
 bool gve_rx_work_pending(struct gve_rx_ring *rx);
+int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
+			  struct gve_rx_alloc_rings_cfg *cfg,
+			  struct gve_rx_ring *rx,
+			  int idx);
+void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
+			  struct gve_rx_alloc_rings_cfg *cfg);
 int gve_rx_alloc_rings(struct gve_priv *priv);
 int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_rx_alloc_rings_cfg *cfg);
@@ -1150,6 +1115,12 @@ int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split);
 /* Reset */
 void gve_schedule_reset(struct gve_priv *priv);
 int gve_reset(struct gve_priv *priv, bool attempt_teardown);
+void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
+			     struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+			     struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
+int gve_adjust_config(struct gve_priv *priv,
+		      struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 int gve_adjust_queues(struct gve_priv *priv,
 		      struct gve_queue_config new_rx_config,
 		      struct gve_queue_config new_tx_config);
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index ae12ac38e18b..8ca0def176ef 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -32,6 +32,8 @@ struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *desc
 	return option_end > descriptor_end ? NULL : (struct gve_device_option *)option_end;
 }
 
+#define GVE_DEVICE_OPTION_NO_MIN_RING_SIZE	8
+
 static
 void gve_parse_device_option(struct gve_priv *priv,
 			     struct gve_device_descriptor *device_descriptor,
@@ -41,7 +43,8 @@ void gve_parse_device_option(struct gve_priv *priv,
 			     struct gve_device_option_dqo_rda **dev_op_dqo_rda,
 			     struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
 			     struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
-			     struct gve_device_option_buffer_sizes **dev_op_buffer_sizes)
+			     struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
+			     struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	u32 req_feat_mask = be32_to_cpu(option->required_features_mask);
 	u16 option_length = be16_to_cpu(option->option_length);
@@ -165,6 +168,27 @@ void gve_parse_device_option(struct gve_priv *priv,
 				 "Buffer Sizes");
 		*dev_op_buffer_sizes = (void *)(option + 1);
 		break;
+	case GVE_DEV_OPT_ID_MODIFY_RING:
+		if (option_length < GVE_DEVICE_OPTION_NO_MIN_RING_SIZE ||
+		    req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING) {
+			dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
+				 "Modify Ring", (int)sizeof(**dev_op_modify_ring),
+				 GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING,
+				 option_length, req_feat_mask);
+			break;
+		}
+
+		if (option_length > sizeof(**dev_op_modify_ring)) {
+			dev_warn(&priv->pdev->dev,
+				 GVE_DEVICE_OPTION_TOO_BIG_FMT, "Modify Ring");
+		}
+
+		*dev_op_modify_ring = (void *)(option + 1);
+
+		/* device has not provided min ring size */
+		if (option_length == GVE_DEVICE_OPTION_NO_MIN_RING_SIZE)
+			priv->default_min_ring_size = true;
+		break;
 	default:
 		/* If we don't recognize the option just continue
 		 * without doing anything.
@@ -183,7 +207,8 @@ gve_process_device_options(struct gve_priv *priv,
 			   struct gve_device_option_dqo_rda **dev_op_dqo_rda,
 			   struct gve_device_option_jumbo_frames **dev_op_jumbo_frames,
 			   struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
-			   struct gve_device_option_buffer_sizes **dev_op_buffer_sizes)
+			   struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
+			   struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	const int num_options = be16_to_cpu(descriptor->num_device_options);
 	struct gve_device_option *dev_opt;
@@ -204,7 +229,8 @@ gve_process_device_options(struct gve_priv *priv,
 		gve_parse_device_option(priv, descriptor, dev_opt,
 					dev_op_gqi_rda, dev_op_gqi_qpl,
 					dev_op_dqo_rda, dev_op_jumbo_frames,
-					dev_op_dqo_qpl, dev_op_buffer_sizes);
+					dev_op_dqo_qpl, dev_op_buffer_sizes,
+					dev_op_modify_ring);
 		dev_opt = next_opt;
 	}
 
@@ -565,6 +591,7 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
 			cpu_to_be64(tx->q_resources_bus),
 		.tx_ring_addr = cpu_to_be64(tx->bus),
 		.ntfy_id = cpu_to_be32(tx->ntfy_id),
+		.tx_ring_size = cpu_to_be16(priv->tx_desc_cnt),
 	};
 
 	if (gve_is_gqi(priv)) {
@@ -573,24 +600,17 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
 
 		cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
 	} else {
-		u16 comp_ring_size;
 		u32 qpl_id = 0;
 
-		if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+		if (priv->queue_format == GVE_DQO_RDA_FORMAT)
 			qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
-			comp_ring_size =
-				priv->options_dqo_rda.tx_comp_ring_entries;
-		} else {
+		else
 			qpl_id = tx->dqo.qpl->id;
-			comp_ring_size = priv->tx_desc_cnt;
-		}
 		cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd.create_tx_queue.tx_ring_size =
-			cpu_to_be16(priv->tx_desc_cnt);
 		cmd.create_tx_queue.tx_comp_ring_addr =
 			cpu_to_be64(tx->complq_bus_dqo);
 		cmd.create_tx_queue.tx_comp_ring_size =
-			cpu_to_be16(comp_ring_size);
+			cpu_to_be16(priv->tx_desc_cnt);
 	}
 
 	return gve_adminq_issue_cmd(priv, &cmd);
@@ -610,63 +630,73 @@ int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_que
 	return gve_adminq_kick_and_wait(priv);
 }
 
-static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
+static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
+					       union gve_adminq_command *cmd,
+					       u32 queue_index)
 {
 	struct gve_rx_ring *rx = &priv->rx[queue_index];
-	union gve_adminq_command cmd;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
-	cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) {
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
+	cmd->create_rx_queue = (struct gve_adminq_create_rx_queue) {
 		.queue_id = cpu_to_be32(queue_index),
 		.ntfy_id = cpu_to_be32(rx->ntfy_id),
 		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
+		.rx_ring_size = cpu_to_be16(priv->rx_desc_cnt),
 	};
 
 	if (gve_is_gqi(priv)) {
 		u32 qpl_id = priv->queue_format == GVE_GQI_RDA_FORMAT ?
 			GVE_RAW_ADDRESSING_QPL_ID : rx->data.qpl->id;
 
-		cmd.create_rx_queue.rx_desc_ring_addr =
-			cpu_to_be64(rx->desc.bus),
-		cmd.create_rx_queue.rx_data_ring_addr =
-			cpu_to_be64(rx->data.data_bus),
-		cmd.create_rx_queue.index = cpu_to_be32(queue_index);
-		cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd.create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
+		cmd->create_rx_queue.rx_desc_ring_addr =
+			cpu_to_be64(rx->desc.bus);
+		cmd->create_rx_queue.rx_data_ring_addr =
+			cpu_to_be64(rx->data.data_bus);
+		cmd->create_rx_queue.index = cpu_to_be32(queue_index);
+		cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
+		cmd->create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
 	} else {
-		u16 rx_buff_ring_entries;
 		u32 qpl_id = 0;
 
-		if (priv->queue_format == GVE_DQO_RDA_FORMAT) {
+		if (priv->queue_format == GVE_DQO_RDA_FORMAT)
 			qpl_id = GVE_RAW_ADDRESSING_QPL_ID;
-			rx_buff_ring_entries =
-				priv->options_dqo_rda.rx_buff_ring_entries;
-		} else {
+		else
 			qpl_id = rx->dqo.qpl->id;
-			rx_buff_ring_entries = priv->rx_desc_cnt;
-		}
-		cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd.create_rx_queue.rx_ring_size =
-			cpu_to_be16(priv->rx_desc_cnt);
-		cmd.create_rx_queue.rx_desc_ring_addr =
+		cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
+		cmd->create_rx_queue.rx_desc_ring_addr =
 			cpu_to_be64(rx->dqo.complq.bus);
-		cmd.create_rx_queue.rx_data_ring_addr =
+		cmd->create_rx_queue.rx_data_ring_addr =
 			cpu_to_be64(rx->dqo.bufq.bus);
-		cmd.create_rx_queue.packet_buffer_size =
+		cmd->create_rx_queue.packet_buffer_size =
 			cpu_to_be16(priv->data_buffer_size_dqo);
-		cmd.create_rx_queue.rx_buff_ring_size =
-			cpu_to_be16(rx_buff_ring_entries);
-		cmd.create_rx_queue.enable_rsc =
+		cmd->create_rx_queue.rx_buff_ring_size =
+			cpu_to_be16(priv->rx_desc_cnt);
+		cmd->create_rx_queue.enable_rsc =
 			!!(priv->dev->features & NETIF_F_LRO);
 		if (priv->header_split_enabled)
-			cmd.create_rx_queue.header_buffer_size =
+			cmd->create_rx_queue.header_buffer_size =
 				cpu_to_be16(priv->header_buf_size);
 	}
+}
+
+static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	union gve_adminq_command cmd;
 
+	gve_adminq_get_create_rx_queue_cmd(priv, &cmd, queue_index);
 	return gve_adminq_issue_cmd(priv, &cmd);
 }
 
+/* Unlike gve_adminq_create_rx_queue, this actually rings the doorbell */
+int gve_adminq_create_single_rx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	union gve_adminq_command cmd;
+
+	gve_adminq_get_create_rx_queue_cmd(priv, &cmd, queue_index);
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
 int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues)
 {
 	int err;
@@ -713,22 +743,31 @@ int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_qu
 	return gve_adminq_kick_and_wait(priv);
 }
 
+static void gve_adminq_make_destroy_rx_queue_cmd(union gve_adminq_command *cmd,
+						 u32 queue_index)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
+	cmd->destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
+		.queue_id = cpu_to_be32(queue_index),
+	};
+}
+
 static int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index)
 {
 	union gve_adminq_command cmd;
-	int err;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
-	cmd.destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
-		.queue_id = cpu_to_be32(queue_index),
-	};
+	gve_adminq_make_destroy_rx_queue_cmd(&cmd, queue_index);
+	return gve_adminq_issue_cmd(priv, &cmd);
+}
 
-	err = gve_adminq_issue_cmd(priv, &cmd);
-	if (err)
-		return err;
+/* Unlike gve_adminq_destroy_rx_queue, this actually rings the doorbell */
+int gve_adminq_destroy_single_rx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	union gve_adminq_command cmd;
 
-	return 0;
+	gve_adminq_make_destroy_rx_queue_cmd(&cmd, queue_index);
+	return gve_adminq_execute_cmd(priv, &cmd);
 }
 
 int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues)
@@ -745,31 +784,17 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues)
 	return gve_adminq_kick_and_wait(priv);
 }
 
-static int gve_set_desc_cnt(struct gve_priv *priv,
-			    struct gve_device_descriptor *descriptor)
-{
-	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
-	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
-	return 0;
-}
-
-static int
-gve_set_desc_cnt_dqo(struct gve_priv *priv,
-		     const struct gve_device_descriptor *descriptor,
-		     const struct gve_device_option_dqo_rda *dev_op_dqo_rda)
+static void gve_set_default_desc_cnt(struct gve_priv *priv,
+			const struct gve_device_descriptor *descriptor)
 {
 	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
 	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
 
-	if (priv->queue_format == GVE_DQO_QPL_FORMAT)
-		return 0;
-
-	priv->options_dqo_rda.tx_comp_ring_entries =
-		be16_to_cpu(dev_op_dqo_rda->tx_comp_ring_entries);
-	priv->options_dqo_rda.rx_buff_ring_entries =
-		be16_to_cpu(dev_op_dqo_rda->rx_buff_ring_entries);
-
-	return 0;
+	/* set default ranges */
+	priv->max_tx_desc_cnt = priv->tx_desc_cnt;
+	priv->max_rx_desc_cnt = priv->rx_desc_cnt;
+	priv->min_tx_desc_cnt = priv->tx_desc_cnt;
+	priv->min_rx_desc_cnt = priv->rx_desc_cnt;
 }
 
 static void gve_enable_supported_features(struct gve_priv *priv,
@@ -779,7 +804,9 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 					  const struct gve_device_option_dqo_qpl
 					  *dev_op_dqo_qpl,
 					  const struct gve_device_option_buffer_sizes
-					  *dev_op_buffer_sizes)
+					  *dev_op_buffer_sizes,
+					  const struct gve_device_option_modify_ring
+					  *dev_op_modify_ring)
 {
 	/* Before control reaches this point, the page-size-capped max MTU from
 	 * the gve_device_descriptor field has already been stored in
@@ -796,12 +823,8 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 	if (dev_op_dqo_qpl) {
 		priv->tx_pages_per_qpl =
 			be16_to_cpu(dev_op_dqo_qpl->tx_pages_per_qpl);
-		priv->rx_pages_per_qpl =
-			be16_to_cpu(dev_op_dqo_qpl->rx_pages_per_qpl);
 		if (priv->tx_pages_per_qpl == 0)
 			priv->tx_pages_per_qpl = DQO_QPL_DEFAULT_TX_PAGES;
-		if (priv->rx_pages_per_qpl == 0)
-			priv->rx_pages_per_qpl = DQO_QPL_DEFAULT_RX_PAGES;
 	}
 
 	if (dev_op_buffer_sizes &&
@@ -814,12 +837,33 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 			 "BUFFER SIZES device option enabled with max_rx_buffer_size of %u, header_buf_size of %u.\n",
 			 priv->max_rx_buffer_size, priv->header_buf_size);
 	}
+
+	/* Read and store ring size ranges given by device */
+	if (dev_op_modify_ring &&
+	    (supported_features_mask & GVE_SUP_MODIFY_RING_MASK)) {
+		priv->modify_ring_size_enabled = true;
+
+		/* max ring size for DQO QPL should not be overwritten because of device limit */
+		if (priv->queue_format != GVE_DQO_QPL_FORMAT) {
+			priv->max_rx_desc_cnt = be16_to_cpu(dev_op_modify_ring->max_rx_ring_size);
+			priv->max_tx_desc_cnt = be16_to_cpu(dev_op_modify_ring->max_tx_ring_size);
+		}
+		if (priv->default_min_ring_size) {
+			/* If device hasn't provided minimums, use default minimums */
+			priv->min_tx_desc_cnt = GVE_DEFAULT_MIN_TX_RING_SIZE;
+			priv->min_rx_desc_cnt = GVE_DEFAULT_MIN_RX_RING_SIZE;
+		} else {
+			priv->min_rx_desc_cnt = be16_to_cpu(dev_op_modify_ring->min_rx_ring_size);
+			priv->min_tx_desc_cnt = be16_to_cpu(dev_op_modify_ring->min_tx_ring_size);
+		}
+	}
 }
 
 int gve_adminq_describe_device(struct gve_priv *priv)
 {
 	struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL;
 	struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL;
+	struct gve_device_option_modify_ring *dev_op_modify_ring = NULL;
 	struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL;
 	struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL;
 	struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL;
@@ -851,9 +895,9 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 
 	err = gve_process_device_options(priv, descriptor, &dev_op_gqi_rda,
 					 &dev_op_gqi_qpl, &dev_op_dqo_rda,
-					 &dev_op_jumbo_frames,
-					 &dev_op_dqo_qpl,
-					 &dev_op_buffer_sizes);
+					 &dev_op_jumbo_frames, &dev_op_dqo_qpl,
+					 &dev_op_buffer_sizes,
+					 &dev_op_modify_ring);
 	if (err)
 		goto free_device_descriptor;
 
@@ -888,15 +932,13 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 		dev_info(&priv->pdev->dev,
 			 "Driver is running with GQI QPL queue format.\n");
 	}
-	if (gve_is_gqi(priv)) {
-		err = gve_set_desc_cnt(priv, descriptor);
-	} else {
-		/* DQO supports LRO. */
+
+	/* set default descriptor counts */
+	gve_set_default_desc_cnt(priv, descriptor);
+
+	/* DQO supports LRO. */
+	if (!gve_is_gqi(priv))
 		priv->dev->hw_features |= NETIF_F_LRO;
-		err = gve_set_desc_cnt_dqo(priv, descriptor, dev_op_dqo_rda);
-	}
-	if (err)
-		goto free_device_descriptor;
 
 	priv->max_registered_pages =
 				be64_to_cpu(descriptor->max_registered_pages);
@@ -912,18 +954,11 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	mac = descriptor->mac;
 	dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac);
 	priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl);
-	priv->rx_data_slot_cnt = be16_to_cpu(descriptor->rx_pages_per_qpl);
-
-	if (gve_is_gqi(priv) && priv->rx_data_slot_cnt < priv->rx_desc_cnt) {
-		dev_err(&priv->pdev->dev, "rx_data_slot_cnt cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n",
-			priv->rx_data_slot_cnt);
-		priv->rx_desc_cnt = priv->rx_data_slot_cnt;
-	}
 	priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
 
 	gve_enable_supported_features(priv, supported_features_mask,
 				      dev_op_jumbo_frames, dev_op_dqo_qpl,
-				      dev_op_buffer_sizes);
+				      dev_op_buffer_sizes, dev_op_modify_ring);
 
 free_device_descriptor:
 	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 5ac972e45ff8..e64f0dbe744d 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -103,8 +103,7 @@ static_assert(sizeof(struct gve_device_option_gqi_qpl) == 4);
 
 struct gve_device_option_dqo_rda {
 	__be32 supported_features_mask;
-	__be16 tx_comp_ring_entries;
-	__be16 rx_buff_ring_entries;
+	__be32 reserved;
 };
 
 static_assert(sizeof(struct gve_device_option_dqo_rda) == 8);
@@ -134,6 +133,16 @@ struct gve_device_option_buffer_sizes {
 
 static_assert(sizeof(struct gve_device_option_buffer_sizes) == 8);
 
+struct gve_device_option_modify_ring {
+	__be32 supported_featured_mask;
+	__be16 max_rx_ring_size;
+	__be16 max_tx_ring_size;
+	__be16 min_rx_ring_size;
+	__be16 min_tx_ring_size;
+};
+
+static_assert(sizeof(struct gve_device_option_modify_ring) == 12);
+
 /* Terminology:
  *
  * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA
@@ -143,28 +152,31 @@ static_assert(sizeof(struct gve_device_option_buffer_sizes) == 8);
  *       the device for read/write and data is copied from/to SKBs.
  */
 enum gve_dev_opt_id {
-	GVE_DEV_OPT_ID_GQI_RAW_ADDRESSING = 0x1,
-	GVE_DEV_OPT_ID_GQI_RDA = 0x2,
-	GVE_DEV_OPT_ID_GQI_QPL = 0x3,
-	GVE_DEV_OPT_ID_DQO_RDA = 0x4,
-	GVE_DEV_OPT_ID_DQO_QPL = 0x7,
-	GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8,
-	GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa,
+	GVE_DEV_OPT_ID_GQI_RAW_ADDRESSING	= 0x1,
+	GVE_DEV_OPT_ID_GQI_RDA			= 0x2,
+	GVE_DEV_OPT_ID_GQI_QPL			= 0x3,
+	GVE_DEV_OPT_ID_DQO_RDA			= 0x4,
+	GVE_DEV_OPT_ID_MODIFY_RING		= 0x6,
+	GVE_DEV_OPT_ID_DQO_QPL			= 0x7,
+	GVE_DEV_OPT_ID_JUMBO_FRAMES		= 0x8,
+	GVE_DEV_OPT_ID_BUFFER_SIZES		= 0xa,
 };
 
 enum gve_dev_opt_req_feat_mask {
-	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL = 0x0,
-	GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES = 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING	= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING		= 0x0,
 };
 
 enum gve_sup_feature_mask {
-	GVE_SUP_JUMBO_FRAMES_MASK = 1 << 2,
-	GVE_SUP_BUFFER_SIZES_MASK = 1 << 4,
+	GVE_SUP_MODIFY_RING_MASK	= 1 << 0,
+	GVE_SUP_JUMBO_FRAMES_MASK	= 1 << 2,
+	GVE_SUP_BUFFER_SIZES_MASK	= 1 << 4,
 };
 
 #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0
@@ -439,7 +451,9 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv,
 int gve_adminq_deconfigure_device_resources(struct gve_priv *priv);
 int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues);
 int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues);
+int gve_adminq_create_single_rx_queue(struct gve_priv *priv, u32 queue_index);
 int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues);
+int gve_adminq_destroy_single_rx_queue(struct gve_priv *priv, u32 queue_index);
 int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id);
 int gve_adminq_register_page_list(struct gve_priv *priv,
 				  struct gve_queue_page_list *qpl);
diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h
index b81584829c40..e83773fb891f 100644
--- a/drivers/net/ethernet/google/gve/gve_dqo.h
+++ b/drivers/net/ethernet/google/gve/gve_dqo.h
@@ -44,6 +44,12 @@ void gve_tx_free_rings_dqo(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg);
 void gve_tx_start_ring_dqo(struct gve_priv *priv, int idx);
 void gve_tx_stop_ring_dqo(struct gve_priv *priv, int idx);
+int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
+			  struct gve_rx_alloc_rings_cfg *cfg,
+			  struct gve_rx_ring *rx,
+			  int idx);
+void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			  struct gve_rx_alloc_rings_cfg *cfg);
 int gve_rx_alloc_rings_dqo(struct gve_priv *priv,
 			   struct gve_rx_alloc_rings_cfg *cfg);
 void gve_rx_free_rings_dqo(struct gve_priv *priv,
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 9aebfb843d9d..fe1741d482b4 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -8,6 +8,7 @@
 #include "gve.h"
 #include "gve_adminq.h"
 #include "gve_dqo.h"
+#include "gve_utils.h"
 
 static void gve_get_drvinfo(struct net_device *netdev,
 			    struct ethtool_drvinfo *info)
@@ -73,7 +74,7 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
 	"adminq_create_tx_queue_cnt", "adminq_create_rx_queue_cnt",
 	"adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt",
 	"adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt",
-	"adminq_report_stats_cnt", "adminq_report_link_speed_cnt"
+	"adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt"
 };
 
 static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = {
@@ -89,42 +90,34 @@ static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = {
 static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
-	char *s = (char *)data;
+	u8 *s = (char *)data;
 	int num_tx_queues;
 	int i, j;
 
 	num_tx_queues = gve_num_tx_queues(priv);
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(s, *gve_gstrings_main_stats,
-		       sizeof(gve_gstrings_main_stats));
-		s += sizeof(gve_gstrings_main_stats);
-
-		for (i = 0; i < priv->rx_cfg.num_queues; i++) {
-			for (j = 0; j < NUM_GVE_RX_CNTS; j++) {
-				snprintf(s, ETH_GSTRING_LEN,
-					 gve_gstrings_rx_stats[j], i);
-				s += ETH_GSTRING_LEN;
-			}
-		}
+		for (i = 0; i < ARRAY_SIZE(gve_gstrings_main_stats); i++)
+			ethtool_puts(&s, gve_gstrings_main_stats[i]);
 
-		for (i = 0; i < num_tx_queues; i++) {
-			for (j = 0; j < NUM_GVE_TX_CNTS; j++) {
-				snprintf(s, ETH_GSTRING_LEN,
-					 gve_gstrings_tx_stats[j], i);
-				s += ETH_GSTRING_LEN;
-			}
-		}
+		for (i = 0; i < priv->rx_cfg.num_queues; i++)
+			for (j = 0; j < NUM_GVE_RX_CNTS; j++)
+				ethtool_sprintf(&s, gve_gstrings_rx_stats[j],
+						i);
+
+		for (i = 0; i < num_tx_queues; i++)
+			for (j = 0; j < NUM_GVE_TX_CNTS; j++)
+				ethtool_sprintf(&s, gve_gstrings_tx_stats[j],
+						i);
+
+		for (i = 0; i < ARRAY_SIZE(gve_gstrings_adminq_stats); i++)
+			ethtool_puts(&s, gve_gstrings_adminq_stats[i]);
 
-		memcpy(s, *gve_gstrings_adminq_stats,
-		       sizeof(gve_gstrings_adminq_stats));
-		s += sizeof(gve_gstrings_adminq_stats);
 		break;
 
 	case ETH_SS_PRIV_FLAGS:
-		memcpy(s, *gve_gstrings_priv_flags,
-		       sizeof(gve_gstrings_priv_flags));
-		s += sizeof(gve_gstrings_priv_flags);
+		for (i = 0; i < ARRAY_SIZE(gve_gstrings_priv_flags); i++)
+			ethtool_puts(&s, gve_gstrings_priv_flags[i]);
 		break;
 
 	default:
@@ -165,6 +158,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	struct stats *report_stats;
 	int *rx_qid_to_stats_idx;
 	int *tx_qid_to_stats_idx;
+	int num_stopped_rxqs = 0;
+	int num_stopped_txqs = 0;
 	struct gve_priv *priv;
 	bool skip_nic_stats;
 	unsigned int start;
@@ -181,12 +176,23 @@ gve_get_ethtool_stats(struct net_device *netdev,
 					    sizeof(int), GFP_KERNEL);
 	if (!rx_qid_to_stats_idx)
 		return;
+	for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
+		rx_qid_to_stats_idx[ring] = -1;
+		if (!gve_rx_was_added_to_block(priv, ring))
+			num_stopped_rxqs++;
+	}
 	tx_qid_to_stats_idx = kmalloc_array(num_tx_queues,
 					    sizeof(int), GFP_KERNEL);
 	if (!tx_qid_to_stats_idx) {
 		kfree(rx_qid_to_stats_idx);
 		return;
 	}
+	for (ring = 0; ring < num_tx_queues; ring++) {
+		tx_qid_to_stats_idx[ring] = -1;
+		if (!gve_tx_was_added_to_block(priv, ring))
+			num_stopped_txqs++;
+	}
+
 	for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0,
 	     rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0,
 	     rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0,
@@ -260,7 +266,13 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	/* For rx cross-reporting stats, start from nic rx stats in report */
 	base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues +
 		GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues;
-	max_stats_idx = NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues +
+	/* The boundary between driver stats and NIC stats shifts if there are
+	 * stopped queues.
+	 */
+	base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs +
+		NIC_TX_STATS_REPORT_NUM * num_stopped_txqs;
+	max_stats_idx = NIC_RX_STATS_REPORT_NUM *
+		(priv->rx_cfg.num_queues - num_stopped_rxqs) +
 		base_stats_idx;
 	/* Preprocess the stats report for rx, map queue id to start index */
 	skip_nic_stats = false;
@@ -274,6 +286,10 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			skip_nic_stats = true;
 			break;
 		}
+		if (queue_id < 0 || queue_id >= priv->rx_cfg.num_queues) {
+			net_err_ratelimited("Invalid rxq id in NIC stats\n");
+			continue;
+		}
 		rx_qid_to_stats_idx[queue_id] = stats_idx;
 	}
 	/* walk RX rings */
@@ -308,11 +324,11 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = rx->rx_copybreak_pkt;
 			data[i++] = rx->rx_copied_pkt;
 			/* stats from NIC */
-			if (skip_nic_stats) {
+			stats_idx = rx_qid_to_stats_idx[ring];
+			if (skip_nic_stats || stats_idx < 0) {
 				/* skip NIC rx stats */
 				i += NIC_RX_STATS_REPORT_NUM;
 			} else {
-				stats_idx = rx_qid_to_stats_idx[ring];
 				for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) {
 					u64 value =
 						be64_to_cpu(report_stats[stats_idx + j].value);
@@ -338,7 +354,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
 
 	/* For tx cross-reporting stats, start from nic tx stats in report */
 	base_stats_idx = max_stats_idx;
-	max_stats_idx = NIC_TX_STATS_REPORT_NUM * num_tx_queues +
+	max_stats_idx = NIC_TX_STATS_REPORT_NUM *
+		(num_tx_queues - num_stopped_txqs) +
 		max_stats_idx;
 	/* Preprocess the stats report for tx, map queue id to start index */
 	skip_nic_stats = false;
@@ -352,6 +369,10 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			skip_nic_stats = true;
 			break;
 		}
+		if (queue_id < 0 || queue_id >= num_tx_queues) {
+			net_err_ratelimited("Invalid txq id in NIC stats\n");
+			continue;
+		}
 		tx_qid_to_stats_idx[queue_id] = stats_idx;
 	}
 	/* walk TX rings */
@@ -383,11 +404,11 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = gve_tx_load_event_counter(priv, tx);
 			data[i++] = tx->dma_mapping_error;
 			/* stats from NIC */
-			if (skip_nic_stats) {
+			stats_idx = tx_qid_to_stats_idx[ring];
+			if (skip_nic_stats || stats_idx < 0) {
 				/* skip NIC tx stats */
 				i += NIC_TX_STATS_REPORT_NUM;
 			} else {
-				stats_idx = tx_qid_to_stats_idx[ring];
 				for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) {
 					u64 value =
 						be64_to_cpu(report_stats[stats_idx + j].value);
@@ -428,6 +449,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = priv->adminq_set_driver_parameter_cnt;
 	data[i++] = priv->adminq_report_stats_cnt;
 	data[i++] = priv->adminq_report_link_speed_cnt;
+	data[i++] = priv->adminq_get_ptype_map_cnt;
 }
 
 static void gve_get_channels(struct net_device *netdev,
@@ -489,8 +511,8 @@ static void gve_get_ringparam(struct net_device *netdev,
 {
 	struct gve_priv *priv = netdev_priv(netdev);
 
-	cmd->rx_max_pending = priv->rx_desc_cnt;
-	cmd->tx_max_pending = priv->tx_desc_cnt;
+	cmd->rx_max_pending = priv->max_rx_desc_cnt;
+	cmd->tx_max_pending = priv->max_tx_desc_cnt;
 	cmd->rx_pending = priv->rx_desc_cnt;
 	cmd->tx_pending = priv->tx_desc_cnt;
 
@@ -502,20 +524,81 @@ static void gve_get_ringparam(struct net_device *netdev,
 		kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED;
 }
 
+static int gve_adjust_ring_sizes(struct gve_priv *priv,
+				 u16 new_tx_desc_cnt,
+				 u16 new_rx_desc_cnt)
+{
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
+	int err;
+
+	/* get current queue configuration */
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+
+	/* copy over the new ring_size from ethtool */
+	tx_alloc_cfg.ring_size = new_tx_desc_cnt;
+	rx_alloc_cfg.ring_size = new_rx_desc_cnt;
+
+	if (netif_running(priv->dev)) {
+		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+		if (err)
+			return err;
+	}
+
+	/* Set new ring_size for the next up */
+	priv->tx_desc_cnt = new_tx_desc_cnt;
+	priv->rx_desc_cnt = new_rx_desc_cnt;
+
+	return 0;
+}
+
+static int gve_validate_req_ring_size(struct gve_priv *priv, u16 new_tx_desc_cnt,
+				      u16 new_rx_desc_cnt)
+{
+	/* check for valid range */
+	if (new_tx_desc_cnt < priv->min_tx_desc_cnt ||
+	    new_tx_desc_cnt > priv->max_tx_desc_cnt ||
+	    new_rx_desc_cnt < priv->min_rx_desc_cnt ||
+	    new_rx_desc_cnt > priv->max_rx_desc_cnt) {
+		dev_err(&priv->pdev->dev, "Requested descriptor count out of range\n");
+		return -EINVAL;
+	}
+
+	if (!is_power_of_2(new_tx_desc_cnt) || !is_power_of_2(new_rx_desc_cnt)) {
+		dev_err(&priv->pdev->dev, "Requested descriptor count has to be a power of 2\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int gve_set_ringparam(struct net_device *netdev,
 			     struct ethtool_ringparam *cmd,
 			     struct kernel_ethtool_ringparam *kernel_cmd,
 			     struct netlink_ext_ack *extack)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
+	u16 new_tx_cnt, new_rx_cnt;
+	int err;
 
-	if (priv->tx_desc_cnt != cmd->tx_pending ||
-	    priv->rx_desc_cnt != cmd->rx_pending) {
-		dev_info(&priv->pdev->dev, "Modify ring size is not supported.\n");
+	err = gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split);
+	if (err)
+		return err;
+
+	if (cmd->tx_pending == priv->tx_desc_cnt && cmd->rx_pending == priv->rx_desc_cnt)
+		return 0;
+
+	if (!priv->modify_ring_size_enabled) {
+		dev_err(&priv->pdev->dev, "Modify ring size is not supported.\n");
 		return -EOPNOTSUPP;
 	}
 
-	return gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split);
+	new_tx_cnt = cmd->tx_pending;
+	new_rx_cnt = cmd->rx_pending;
+
+	if (gve_validate_req_ring_size(priv, new_tx_cnt, new_rx_cnt))
+		return -EINVAL;
+
+	return gve_adjust_ring_sizes(priv, new_tx_cnt, new_rx_cnt);
 }
 
 static int gve_user_reset(struct net_device *netdev, u32 *flags)
@@ -710,5 +793,6 @@ const struct ethtool_ops gve_ethtool_ops = {
 	.set_tunable = gve_set_tunable,
 	.get_priv_flags = gve_get_priv_flags,
 	.set_priv_flags = gve_set_priv_flags,
-	.get_link_ksettings = gve_get_link_ksettings
+	.get_link_ksettings = gve_get_link_ksettings,
+	.get_ts_info = ethtool_op_get_ts_info,
 };
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 166bd827a6d7..cabf7d4bcecb 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -9,6 +9,7 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/sched.h>
@@ -16,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/utsname.h>
 #include <linux/version.h>
+#include <net/netdev_queues.h>
 #include <net/sch_generic.h>
 #include <net/xdp_sock_drv.h>
 #include "gve.h"
@@ -253,6 +255,18 @@ static irqreturn_t gve_intr_dqo(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+static int gve_is_napi_on_home_cpu(struct gve_priv *priv, u32 irq)
+{
+	int cpu_curr = smp_processor_id();
+	const struct cpumask *aff_mask;
+
+	aff_mask = irq_get_effective_affinity_mask(irq);
+	if (unlikely(!aff_mask))
+		return 1;
+
+	return cpumask_test_cpu(cpu_curr, aff_mask);
+}
+
 int gve_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct gve_notify_block *block;
@@ -322,8 +336,21 @@ int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 		reschedule |= work_done == budget;
 	}
 
-	if (reschedule)
-		return budget;
+	if (reschedule) {
+		/* Reschedule by returning budget only if already on the correct
+		 * cpu.
+		 */
+		if (likely(gve_is_napi_on_home_cpu(priv, block->irq)))
+			return budget;
+
+		/* If not on the cpu with which this queue's irq has affinity
+		 * with, we avoid rescheduling napi and arm the irq instead so
+		 * that napi gets rescheduled back eventually onto the right
+		 * cpu.
+		 */
+		if (work_done == budget)
+			work_done--;
+	}
 
 	if (likely(napi_complete_done(napi, work_done))) {
 		/* Enable interrupts again.
@@ -428,6 +455,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv)
 				"Failed to receive msix vector %d\n", i);
 			goto abort_with_some_ntfy_blocks;
 		}
+		block->irq = priv->msix_vectors[msix_idx].vector;
 		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
 				      get_cpu_mask(i % active_cpus));
 		block->irq_db_index = &priv->irq_db_indices[i].index;
@@ -441,6 +469,7 @@ abort_with_some_ntfy_blocks:
 		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
 				      NULL);
 		free_irq(priv->msix_vectors[msix_idx].vector, block);
+		block->irq = 0;
 	}
 	kvfree(priv->ntfy_blocks);
 	priv->ntfy_blocks = NULL;
@@ -474,6 +503,7 @@ static void gve_free_notify_blocks(struct gve_priv *priv)
 		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
 				      NULL);
 		free_irq(priv->msix_vectors[msix_idx].vector, block);
+		block->irq = 0;
 	}
 	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
 	kvfree(priv->ntfy_blocks);
@@ -582,37 +612,36 @@ static void gve_teardown_device_resources(struct gve_priv *priv)
 	gve_clear_device_resources_ok(priv);
 }
 
-static int gve_unregister_qpl(struct gve_priv *priv, u32 i)
+static int gve_unregister_qpl(struct gve_priv *priv,
+			      struct gve_queue_page_list *qpl)
 {
 	int err;
 
-	err = gve_adminq_unregister_page_list(priv, priv->qpls[i].id);
+	if (!qpl)
+		return 0;
+
+	err = gve_adminq_unregister_page_list(priv, qpl->id);
 	if (err) {
 		netif_err(priv, drv, priv->dev,
 			  "Failed to unregister queue page list %d\n",
-			  priv->qpls[i].id);
+			  qpl->id);
 		return err;
 	}
 
-	priv->num_registered_pages -= priv->qpls[i].num_entries;
+	priv->num_registered_pages -= qpl->num_entries;
 	return 0;
 }
 
-static int gve_register_qpl(struct gve_priv *priv, u32 i)
+static int gve_register_qpl(struct gve_priv *priv,
+			    struct gve_queue_page_list *qpl)
 {
-	int num_rx_qpls;
 	int pages;
 	int err;
 
-	/* Rx QPLs succeed Tx QPLs in the priv->qpls array. */
-	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
-	if (i >= gve_rx_start_qpl_id(&priv->tx_cfg) + num_rx_qpls) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot register nonexisting QPL at index %d\n", i);
-		return -EINVAL;
-	}
+	if (!qpl)
+		return 0;
 
-	pages = priv->qpls[i].num_entries;
+	pages = qpl->num_entries;
 
 	if (pages + priv->num_registered_pages > priv->max_registered_pages) {
 		netif_err(priv, drv, priv->dev,
@@ -622,14 +651,11 @@ static int gve_register_qpl(struct gve_priv *priv, u32 i)
 		return -EINVAL;
 	}
 
-	err = gve_adminq_register_page_list(priv, &priv->qpls[i]);
+	err = gve_adminq_register_page_list(priv, qpl);
 	if (err) {
 		netif_err(priv, drv, priv->dev,
 			  "failed to register queue page list %d\n",
-			  priv->qpls[i].id);
-		/* This failure will trigger a reset - no need to clean
-		 * up
-		 */
+			  qpl->id);
 		return err;
 	}
 
@@ -637,6 +663,26 @@ static int gve_register_qpl(struct gve_priv *priv, u32 i)
 	return 0;
 }
 
+static struct gve_queue_page_list *gve_tx_get_qpl(struct gve_priv *priv, int idx)
+{
+	struct gve_tx_ring *tx = &priv->tx[idx];
+
+	if (gve_is_gqi(priv))
+		return tx->tx_fifo.qpl;
+	else
+		return tx->dqo.qpl;
+}
+
+static struct gve_queue_page_list *gve_rx_get_qpl(struct gve_priv *priv, int idx)
+{
+	struct gve_rx_ring *rx = &priv->rx[idx];
+
+	if (gve_is_gqi(priv))
+		return rx->data.qpl;
+	else
+		return rx->dqo.qpl;
+}
+
 static int gve_register_xdp_qpls(struct gve_priv *priv)
 {
 	int start_id;
@@ -645,7 +691,7 @@ static int gve_register_xdp_qpls(struct gve_priv *priv)
 
 	start_id = gve_xdp_tx_start_queue_id(priv);
 	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_register_qpl(priv, i);
+		err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i));
 		/* This failure will trigger a reset - no need to clean up */
 		if (err)
 			return err;
@@ -656,7 +702,6 @@ static int gve_register_xdp_qpls(struct gve_priv *priv)
 static int gve_register_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
-	int start_id;
 	int err;
 	int i;
 
@@ -665,15 +710,13 @@ static int gve_register_qpls(struct gve_priv *priv)
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
-		err = gve_register_qpl(priv, i);
+		err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i));
 		if (err)
 			return err;
 	}
 
-	/* there might be a gap between the tx and rx qpl ids */
-	start_id = gve_rx_start_qpl_id(&priv->tx_cfg);
 	for (i = 0; i < num_rx_qpls; i++) {
-		err = gve_register_qpl(priv, start_id + i);
+		err = gve_register_qpl(priv, gve_rx_get_qpl(priv, i));
 		if (err)
 			return err;
 	}
@@ -689,7 +732,7 @@ static int gve_unregister_xdp_qpls(struct gve_priv *priv)
 
 	start_id = gve_xdp_tx_start_queue_id(priv);
 	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_unregister_qpl(priv, i);
+		err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i));
 		/* This failure will trigger a reset - no need to clean */
 		if (err)
 			return err;
@@ -700,7 +743,6 @@ static int gve_unregister_xdp_qpls(struct gve_priv *priv)
 static int gve_unregister_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
-	int start_id;
 	int err;
 	int i;
 
@@ -709,15 +751,14 @@ static int gve_unregister_qpls(struct gve_priv *priv)
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
-		err = gve_unregister_qpl(priv, i);
+		err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i));
 		/* This failure will trigger a reset - no need to clean */
 		if (err)
 			return err;
 	}
 
-	start_id = gve_rx_start_qpl_id(&priv->tx_cfg);
 	for (i = 0; i < num_rx_qpls; i++) {
-		err = gve_unregister_qpl(priv, start_id + i);
+		err = gve_unregister_qpl(priv, gve_rx_get_qpl(priv, i));
 		/* This failure will trigger a reset - no need to clean */
 		if (err)
 			return err;
@@ -828,8 +869,6 @@ static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv,
 {
 	cfg->qcfg = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
-	cfg->qpls = priv->qpls;
-	cfg->qpl_cfg = &priv->qpl_cfg;
 	cfg->ring_size = priv->tx_desc_cnt;
 	cfg->start_idx = 0;
 	cfg->num_rings = gve_num_tx_queues(priv);
@@ -886,9 +925,9 @@ static int gve_alloc_xdp_rings(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_alloc_rings(struct gve_priv *priv,
-			   struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
-			   struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+static int gve_queues_mem_alloc(struct gve_priv *priv,
+				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
 	int err;
 
@@ -974,9 +1013,9 @@ static void gve_free_xdp_rings(struct gve_priv *priv)
 	}
 }
 
-static void gve_free_rings(struct gve_priv *priv,
-			   struct gve_tx_alloc_rings_cfg *tx_cfg,
-			   struct gve_rx_alloc_rings_cfg *rx_cfg)
+static void gve_queues_mem_free(struct gve_priv *priv,
+				struct gve_tx_alloc_rings_cfg *tx_cfg,
+				struct gve_rx_alloc_rings_cfg *rx_cfg)
 {
 	if (gve_is_gqi(priv)) {
 		gve_tx_free_rings_gqi(priv, tx_cfg);
@@ -1005,35 +1044,41 @@ int gve_alloc_page(struct gve_priv *priv, struct device *dev,
 	return 0;
 }
 
-static int gve_alloc_queue_page_list(struct gve_priv *priv,
-				     struct gve_queue_page_list *qpl,
-				     u32 id, int pages)
+struct gve_queue_page_list *gve_alloc_queue_page_list(struct gve_priv *priv,
+						      u32 id, int pages)
 {
+	struct gve_queue_page_list *qpl;
 	int err;
 	int i;
 
+	qpl = kvzalloc(sizeof(*qpl), GFP_KERNEL);
+	if (!qpl)
+		return NULL;
+
 	qpl->id = id;
 	qpl->num_entries = 0;
 	qpl->pages = kvcalloc(pages, sizeof(*qpl->pages), GFP_KERNEL);
-	/* caller handles clean up */
 	if (!qpl->pages)
-		return -ENOMEM;
+		goto abort;
+
 	qpl->page_buses = kvcalloc(pages, sizeof(*qpl->page_buses), GFP_KERNEL);
-	/* caller handles clean up */
 	if (!qpl->page_buses)
-		return -ENOMEM;
+		goto abort;
 
 	for (i = 0; i < pages; i++) {
 		err = gve_alloc_page(priv, &priv->pdev->dev, &qpl->pages[i],
 				     &qpl->page_buses[i],
 				     gve_qpl_dma_dir(priv, id), GFP_KERNEL);
-		/* caller handles clean up */
 		if (err)
-			return -ENOMEM;
+			goto abort;
 		qpl->num_entries++;
 	}
 
-	return 0;
+	return qpl;
+
+abort:
+	gve_free_queue_page_list(priv, qpl, id);
+	return NULL;
 }
 
 void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
@@ -1045,14 +1090,16 @@ void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
 		put_page(page);
 }
 
-static void gve_free_queue_page_list(struct gve_priv *priv,
-				     struct gve_queue_page_list *qpl,
-				     int id)
+void gve_free_queue_page_list(struct gve_priv *priv,
+			      struct gve_queue_page_list *qpl,
+			      u32 id)
 {
 	int i;
 
-	if (!qpl->pages)
+	if (!qpl)
 		return;
+	if (!qpl->pages)
+		goto free_qpl;
 	if (!qpl->page_buses)
 		goto free_pages;
 
@@ -1065,120 +1112,8 @@ static void gve_free_queue_page_list(struct gve_priv *priv,
 free_pages:
 	kvfree(qpl->pages);
 	qpl->pages = NULL;
-}
-
-static void gve_free_n_qpls(struct gve_priv *priv,
-			    struct gve_queue_page_list *qpls,
-			    int start_id,
-			    int num_qpls)
-{
-	int i;
-
-	for (i = start_id; i < start_id + num_qpls; i++)
-		gve_free_queue_page_list(priv, &qpls[i], i);
-}
-
-static int gve_alloc_n_qpls(struct gve_priv *priv,
-			    struct gve_queue_page_list *qpls,
-			    int page_count,
-			    int start_id,
-			    int num_qpls)
-{
-	int err;
-	int i;
-
-	for (i = start_id; i < start_id + num_qpls; i++) {
-		err = gve_alloc_queue_page_list(priv, &qpls[i], i, page_count);
-		if (err)
-			goto free_qpls;
-	}
-
-	return 0;
-
-free_qpls:
-	/* Must include the failing QPL too for gve_alloc_queue_page_list fails
-	 * without cleaning up.
-	 */
-	gve_free_n_qpls(priv, qpls, start_id, i - start_id + 1);
-	return err;
-}
-
-static int gve_alloc_qpls(struct gve_priv *priv,
-			  struct gve_qpls_alloc_cfg *cfg)
-{
-	int max_queues = cfg->tx_cfg->max_queues + cfg->rx_cfg->max_queues;
-	int rx_start_id, tx_num_qpls, rx_num_qpls;
-	struct gve_queue_page_list *qpls;
-	int page_count;
-	int err;
-
-	if (cfg->raw_addressing)
-		return 0;
-
-	qpls = kvcalloc(max_queues, sizeof(*qpls), GFP_KERNEL);
-	if (!qpls)
-		return -ENOMEM;
-
-	cfg->qpl_cfg->qpl_map_size = BITS_TO_LONGS(max_queues) *
-		sizeof(unsigned long) * BITS_PER_BYTE;
-	cfg->qpl_cfg->qpl_id_map = kvcalloc(BITS_TO_LONGS(max_queues),
-					    sizeof(unsigned long), GFP_KERNEL);
-	if (!cfg->qpl_cfg->qpl_id_map) {
-		err = -ENOMEM;
-		goto free_qpl_array;
-	}
-
-	/* Allocate TX QPLs */
-	page_count = priv->tx_pages_per_qpl;
-	tx_num_qpls = gve_num_tx_qpls(cfg->tx_cfg, cfg->num_xdp_queues,
-				      gve_is_qpl(priv));
-	err = gve_alloc_n_qpls(priv, qpls, page_count, 0, tx_num_qpls);
-	if (err)
-		goto free_qpl_map;
-
-	/* Allocate RX QPLs */
-	rx_start_id = gve_rx_start_qpl_id(cfg->tx_cfg);
-	/* For GQI_QPL number of pages allocated have 1:1 relationship with
-	 * number of descriptors. For DQO, number of pages required are
-	 * more than descriptors (because of out of order completions).
-	 */
-	page_count = cfg->is_gqi ? priv->rx_data_slot_cnt : priv->rx_pages_per_qpl;
-	rx_num_qpls = gve_num_rx_qpls(cfg->rx_cfg, gve_is_qpl(priv));
-	err = gve_alloc_n_qpls(priv, qpls, page_count, rx_start_id, rx_num_qpls);
-	if (err)
-		goto free_tx_qpls;
-
-	cfg->qpls = qpls;
-	return 0;
-
-free_tx_qpls:
-	gve_free_n_qpls(priv, qpls, 0, tx_num_qpls);
-free_qpl_map:
-	kvfree(cfg->qpl_cfg->qpl_id_map);
-	cfg->qpl_cfg->qpl_id_map = NULL;
-free_qpl_array:
-	kvfree(qpls);
-	return err;
-}
-
-static void gve_free_qpls(struct gve_priv *priv,
-			  struct gve_qpls_alloc_cfg *cfg)
-{
-	int max_queues = cfg->tx_cfg->max_queues + cfg->rx_cfg->max_queues;
-	struct gve_queue_page_list *qpls = cfg->qpls;
-	int i;
-
-	if (!qpls)
-		return;
-
-	kvfree(cfg->qpl_cfg->qpl_id_map);
-	cfg->qpl_cfg->qpl_id_map = NULL;
-
-	for (i = 0; i < max_queues; i++)
-		gve_free_queue_page_list(priv, &qpls[i], i);
-
-	kvfree(qpls);
-	cfg->qpls = NULL;
+free_qpl:
+	kvfree(qpl);
 }
 
 /* Use this to schedule a reset when the device is capable of continuing
@@ -1282,18 +1217,6 @@ static void gve_drain_page_cache(struct gve_priv *priv)
 		page_frag_cache_drain(&priv->rx[i].page_cache);
 }
 
-static void gve_qpls_get_curr_alloc_cfg(struct gve_priv *priv,
-					struct gve_qpls_alloc_cfg *cfg)
-{
-	  cfg->raw_addressing = !gve_is_qpl(priv);
-	  cfg->is_gqi = gve_is_gqi(priv);
-	  cfg->num_xdp_queues = priv->num_xdp_queues;
-	  cfg->qpl_cfg = &priv->qpl_cfg;
-	  cfg->tx_cfg = &priv->tx_cfg;
-	  cfg->rx_cfg = &priv->rx_cfg;
-	  cfg->qpls = priv->qpls;
-}
-
 static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 				      struct gve_rx_alloc_rings_cfg *cfg)
 {
@@ -1301,8 +1224,6 @@ static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->qcfg_tx = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->enable_header_split = priv->header_split_enabled;
-	cfg->qpls = priv->qpls;
-	cfg->qpl_cfg = &priv->qpl_cfg;
 	cfg->ring_size = priv->rx_desc_cnt;
 	cfg->packet_buffer_size = gve_is_gqi(priv) ?
 				  GVE_DEFAULT_RX_BUFFER_SIZE :
@@ -1310,90 +1231,56 @@ static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->rx = priv->rx;
 }
 
-static void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
-				    struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
-				    struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
-				    struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
+			     struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+			     struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
-	gve_qpls_get_curr_alloc_cfg(priv, qpls_alloc_cfg);
 	gve_tx_get_curr_alloc_cfg(priv, tx_alloc_cfg);
 	gve_rx_get_curr_alloc_cfg(priv, rx_alloc_cfg);
 }
 
-static void gve_rx_start_rings(struct gve_priv *priv, int num_rings)
+static void gve_rx_start_ring(struct gve_priv *priv, int i)
 {
-	int i;
-
-	for (i = 0; i < num_rings; i++) {
-		if (gve_is_gqi(priv))
-			gve_rx_start_ring_gqi(priv, i);
-		else
-			gve_rx_start_ring_dqo(priv, i);
-	}
+	if (gve_is_gqi(priv))
+		gve_rx_start_ring_gqi(priv, i);
+	else
+		gve_rx_start_ring_dqo(priv, i);
 }
 
-static void gve_rx_stop_rings(struct gve_priv *priv, int num_rings)
+static void gve_rx_start_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
-	if (!priv->rx)
-		return;
-
-	for (i = 0; i < num_rings; i++) {
-		if (gve_is_gqi(priv))
-			gve_rx_stop_ring_gqi(priv, i);
-		else
-			gve_rx_stop_ring_dqo(priv, i);
-	}
+	for (i = 0; i < num_rings; i++)
+		gve_rx_start_ring(priv, i);
 }
 
-static void gve_queues_mem_free(struct gve_priv *priv,
-				struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
-				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
-				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+static void gve_rx_stop_ring(struct gve_priv *priv, int i)
 {
-	gve_free_rings(priv, tx_alloc_cfg, rx_alloc_cfg);
-	gve_free_qpls(priv, qpls_alloc_cfg);
+	if (gve_is_gqi(priv))
+		gve_rx_stop_ring_gqi(priv, i);
+	else
+		gve_rx_stop_ring_dqo(priv, i);
 }
 
-static int gve_queues_mem_alloc(struct gve_priv *priv,
-				struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
-				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
-				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+static void gve_rx_stop_rings(struct gve_priv *priv, int num_rings)
 {
-	int err;
-
-	err = gve_alloc_qpls(priv, qpls_alloc_cfg);
-	if (err) {
-		netif_err(priv, drv, priv->dev, "Failed to alloc QPLs\n");
-		return err;
-	}
-	tx_alloc_cfg->qpls = qpls_alloc_cfg->qpls;
-	rx_alloc_cfg->qpls = qpls_alloc_cfg->qpls;
-	err = gve_alloc_rings(priv, tx_alloc_cfg, rx_alloc_cfg);
-	if (err) {
-		netif_err(priv, drv, priv->dev, "Failed to alloc rings\n");
-		goto free_qpls;
-	}
+	int i;
 
-	return 0;
+	if (!priv->rx)
+		return;
 
-free_qpls:
-	gve_free_qpls(priv, qpls_alloc_cfg);
-	return err;
+	for (i = 0; i < num_rings; i++)
+		gve_rx_stop_ring(priv, i);
 }
 
 static void gve_queues_mem_remove(struct gve_priv *priv)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
 
-	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
-				&tx_alloc_cfg, &rx_alloc_cfg);
-	gve_queues_mem_free(priv, &qpls_alloc_cfg,
-			    &tx_alloc_cfg, &rx_alloc_cfg);
-	priv->qpls = NULL;
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+	gve_queues_mem_free(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 	priv->tx = NULL;
 	priv->rx = NULL;
 }
@@ -1402,7 +1289,6 @@ static void gve_queues_mem_remove(struct gve_priv *priv)
  * No memory is allocated. Passed-in memory is freed on errors.
  */
 static int gve_queues_start(struct gve_priv *priv,
-			    struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
 			    struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 			    struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
@@ -1410,12 +1296,10 @@ static int gve_queues_start(struct gve_priv *priv,
 	int err;
 
 	/* Record new resources into priv */
-	priv->qpls = qpls_alloc_cfg->qpls;
 	priv->tx = tx_alloc_cfg->tx;
 	priv->rx = rx_alloc_cfg->rx;
 
 	/* Record new configs into priv */
-	priv->qpl_cfg = *qpls_alloc_cfg->qpl_cfg;
 	priv->tx_cfg = *tx_alloc_cfg->qcfg;
 	priv->rx_cfg = *rx_alloc_cfg->qcfg;
 	priv->tx_desc_cnt = tx_alloc_cfg->ring_size;
@@ -1483,23 +1367,19 @@ static int gve_open(struct net_device *dev)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
 	struct gve_priv *priv = netdev_priv(dev);
 	int err;
 
-	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
-				&tx_alloc_cfg, &rx_alloc_cfg);
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 
-	err = gve_queues_mem_alloc(priv, &qpls_alloc_cfg,
-				   &tx_alloc_cfg, &rx_alloc_cfg);
+	err = gve_queues_mem_alloc(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 	if (err)
 		return err;
 
 	/* No need to free on error: ownership of resources is lost after
 	 * calling gve_queues_start.
 	 */
-	err = gve_queues_start(priv, &qpls_alloc_cfg,
-			       &tx_alloc_cfg, &rx_alloc_cfg);
+	err = gve_queues_start(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 	if (err)
 		return err;
 
@@ -1558,11 +1438,8 @@ static int gve_close(struct net_device *dev)
 
 static int gve_remove_xdp_queues(struct gve_priv *priv)
 {
-	int qpl_start_id;
 	int err;
 
-	qpl_start_id = gve_xdp_tx_start_queue_id(priv);
-
 	err = gve_destroy_xdp_rings(priv);
 	if (err)
 		return err;
@@ -1574,27 +1451,19 @@ static int gve_remove_xdp_queues(struct gve_priv *priv)
 	gve_unreg_xdp_info(priv);
 	gve_free_xdp_rings(priv);
 
-	gve_free_n_qpls(priv, priv->qpls, qpl_start_id, gve_num_xdp_qpls(priv));
 	priv->num_xdp_queues = 0;
 	return 0;
 }
 
 static int gve_add_xdp_queues(struct gve_priv *priv)
 {
-	int start_id;
 	int err;
 
 	priv->num_xdp_queues = priv->rx_cfg.num_queues;
 
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	err = gve_alloc_n_qpls(priv, priv->qpls, priv->tx_pages_per_qpl,
-			       start_id, gve_num_xdp_qpls(priv));
-	if (err)
-		goto err;
-
 	err = gve_alloc_xdp_rings(priv);
 	if (err)
-		goto free_xdp_qpls;
+		goto err;
 
 	err = gve_reg_xdp_info(priv, priv->dev);
 	if (err)
@@ -1612,8 +1481,6 @@ static int gve_add_xdp_queues(struct gve_priv *priv)
 
 free_xdp_rings:
 	gve_free_xdp_rings(priv);
-free_xdp_qpls:
-	gve_free_n_qpls(priv, priv->qpls, start_id, gve_num_xdp_qpls(priv));
 err:
 	priv->num_xdp_queues = 0;
 	return err;
@@ -1863,16 +1730,14 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-static int gve_adjust_config(struct gve_priv *priv,
-			     struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
-			     struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
-			     struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
+int gve_adjust_config(struct gve_priv *priv,
+		      struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
 	int err;
 
 	/* Allocate resources for the new confiugration */
-	err = gve_queues_mem_alloc(priv, qpls_alloc_cfg,
-				   tx_alloc_cfg, rx_alloc_cfg);
+	err = gve_queues_mem_alloc(priv, tx_alloc_cfg, rx_alloc_cfg);
 	if (err) {
 		netif_err(priv, drv, priv->dev,
 			  "Adjust config failed to alloc new queues");
@@ -1884,14 +1749,12 @@ static int gve_adjust_config(struct gve_priv *priv,
 	if (err) {
 		netif_err(priv, drv, priv->dev,
 			  "Adjust config failed to close old queues");
-		gve_queues_mem_free(priv, qpls_alloc_cfg,
-				    tx_alloc_cfg, rx_alloc_cfg);
+		gve_queues_mem_free(priv, tx_alloc_cfg, rx_alloc_cfg);
 		return err;
 	}
 
 	/* Bring the device back up again with the new resources. */
-	err = gve_queues_start(priv, qpls_alloc_cfg,
-			       tx_alloc_cfg, rx_alloc_cfg);
+	err = gve_queues_start(priv, tx_alloc_cfg, rx_alloc_cfg);
 	if (err) {
 		netif_err(priv, drv, priv->dev,
 			  "Adjust config failed to start new queues, !!! DISABLING ALL QUEUES !!!\n");
@@ -1911,32 +1774,18 @@ int gve_adjust_queues(struct gve_priv *priv,
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
-	struct gve_qpl_config new_qpl_cfg;
 	int err;
 
-	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
-				&tx_alloc_cfg, &rx_alloc_cfg);
-
-	/* qpl_cfg is not read-only, it contains a map that gets updated as
-	 * rings are allocated, which is why we cannot use the yet unreleased
-	 * one in priv.
-	 */
-	qpls_alloc_cfg.qpl_cfg = &new_qpl_cfg;
-	tx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
-	rx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 
 	/* Relay the new config from ethtool */
-	qpls_alloc_cfg.tx_cfg = &new_tx_config;
 	tx_alloc_cfg.qcfg = &new_tx_config;
 	rx_alloc_cfg.qcfg_tx = &new_tx_config;
-	qpls_alloc_cfg.rx_cfg = &new_rx_config;
 	rx_alloc_cfg.qcfg = &new_rx_config;
 	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
 
 	if (netif_carrier_ok(priv->dev)) {
-		err = gve_adjust_config(priv, &qpls_alloc_cfg,
-					&tx_alloc_cfg, &rx_alloc_cfg);
+		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 		return err;
 	}
 	/* Set the config for the next up. */
@@ -1961,12 +1810,16 @@ static void gve_turndown(struct gve_priv *priv)
 		int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx);
 		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
+		if (!gve_tx_was_added_to_block(priv, idx))
+			continue;
 		napi_disable(&block->napi);
 	}
 	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
 		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
 		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
+		if (!gve_rx_was_added_to_block(priv, idx))
+			continue;
 		napi_disable(&block->napi);
 	}
 
@@ -1989,6 +1842,9 @@ static void gve_turnup(struct gve_priv *priv)
 		int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx);
 		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
+		if (!gve_tx_was_added_to_block(priv, idx))
+			continue;
+
 		napi_enable(&block->napi);
 		if (gve_is_gqi(priv)) {
 			iowrite32be(0, gve_irq_doorbell(priv, block));
@@ -1996,11 +1852,21 @@ static void gve_turnup(struct gve_priv *priv)
 			gve_set_itr_coalesce_usecs_dqo(priv, block,
 						       priv->tx_coalesce_usecs);
 		}
+
+		/* Any descs written by the NIC before this barrier will be
+		 * handled by the one-off napi schedule below. Whereas any
+		 * descs after the barrier will generate interrupts.
+		 */
+		mb();
+		napi_schedule(&block->napi);
 	}
 	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
 		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
 		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
+		if (!gve_rx_was_added_to_block(priv, idx))
+			continue;
+
 		napi_enable(&block->napi);
 		if (gve_is_gqi(priv)) {
 			iowrite32be(0, gve_irq_doorbell(priv, block));
@@ -2008,11 +1874,27 @@ static void gve_turnup(struct gve_priv *priv)
 			gve_set_itr_coalesce_usecs_dqo(priv, block,
 						       priv->rx_coalesce_usecs);
 		}
+
+		/* Any descs written by the NIC before this barrier will be
+		 * handled by the one-off napi schedule below. Whereas any
+		 * descs after the barrier will generate interrupts.
+		 */
+		mb();
+		napi_schedule(&block->napi);
 	}
 
 	gve_set_napi_enabled(priv);
 }
 
+static void gve_turnup_and_check_status(struct gve_priv *priv)
+{
+	u32 status;
+
+	gve_turnup(priv);
+	status = ioread32be(&priv->reg_bar0->device_status);
+	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
+}
+
 static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct gve_notify_block *block;
@@ -2077,7 +1959,6 @@ int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
 	bool enable_hdr_split;
 	int err = 0;
 
@@ -2097,15 +1978,13 @@ int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split)
 	if (enable_hdr_split == priv->header_split_enabled)
 		return 0;
 
-	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
-				&tx_alloc_cfg, &rx_alloc_cfg);
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 
 	rx_alloc_cfg.enable_header_split = enable_hdr_split;
 	rx_alloc_cfg.packet_buffer_size = gve_get_pkt_buf_size(priv, enable_hdr_split);
 
 	if (netif_running(priv->dev))
-		err = gve_adjust_config(priv, &qpls_alloc_cfg,
-					&tx_alloc_cfg, &rx_alloc_cfg);
+		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 	return err;
 }
 
@@ -2115,26 +1994,15 @@ static int gve_set_features(struct net_device *netdev,
 	const netdev_features_t orig_features = netdev->features;
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
 	struct gve_priv *priv = netdev_priv(netdev);
-	struct gve_qpl_config new_qpl_cfg;
 	int err;
 
-	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
-				&tx_alloc_cfg, &rx_alloc_cfg);
-	/* qpl_cfg is not read-only, it contains a map that gets updated as
-	 * rings are allocated, which is why we cannot use the yet unreleased
-	 * one in priv.
-	 */
-	qpls_alloc_cfg.qpl_cfg = &new_qpl_cfg;
-	tx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
-	rx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 
 	if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) {
 		netdev->features ^= NETIF_F_LRO;
 		if (netif_carrier_ok(netdev)) {
-			err = gve_adjust_config(priv, &qpls_alloc_cfg,
-						&tx_alloc_cfg, &rx_alloc_cfg);
+			err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 			if (err) {
 				/* Revert the change on error. */
 				netdev->features = orig_features;
@@ -2473,6 +2341,140 @@ static void gve_write_version(u8 __iomem *driver_version_register)
 	writeb('\n', driver_version_register);
 }
 
+static int gve_rx_queue_stop(struct net_device *dev, void *per_q_mem, int idx)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_rx_ring *gve_per_q_mem;
+	int err;
+
+	if (!priv->rx)
+		return -EAGAIN;
+
+	/* Destroying queue 0 while other queues exist is not supported in DQO */
+	if (!gve_is_gqi(priv) && idx == 0)
+		return -ERANGE;
+
+	/* Single-queue destruction requires quiescence on all queues */
+	gve_turndown(priv);
+
+	/* This failure will trigger a reset - no need to clean up */
+	err = gve_adminq_destroy_single_rx_queue(priv, idx);
+	if (err)
+		return err;
+
+	if (gve_is_qpl(priv)) {
+		/* This failure will trigger a reset - no need to clean up */
+		err = gve_unregister_qpl(priv, gve_rx_get_qpl(priv, idx));
+		if (err)
+			return err;
+	}
+
+	gve_rx_stop_ring(priv, idx);
+
+	/* Turn the unstopped queues back up */
+	gve_turnup_and_check_status(priv);
+
+	gve_per_q_mem = (struct gve_rx_ring *)per_q_mem;
+	*gve_per_q_mem = priv->rx[idx];
+	memset(&priv->rx[idx], 0, sizeof(priv->rx[idx]));
+	return 0;
+}
+
+static void gve_rx_queue_mem_free(struct net_device *dev, void *per_q_mem)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_rx_alloc_rings_cfg cfg = {0};
+	struct gve_rx_ring *gve_per_q_mem;
+
+	gve_per_q_mem = (struct gve_rx_ring *)per_q_mem;
+	gve_rx_get_curr_alloc_cfg(priv, &cfg);
+
+	if (gve_is_gqi(priv))
+		gve_rx_free_ring_gqi(priv, gve_per_q_mem, &cfg);
+	else
+		gve_rx_free_ring_dqo(priv, gve_per_q_mem, &cfg);
+}
+
+static int gve_rx_queue_mem_alloc(struct net_device *dev, void *per_q_mem,
+				  int idx)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_rx_alloc_rings_cfg cfg = {0};
+	struct gve_rx_ring *gve_per_q_mem;
+	int err;
+
+	if (!priv->rx)
+		return -EAGAIN;
+
+	gve_per_q_mem = (struct gve_rx_ring *)per_q_mem;
+	gve_rx_get_curr_alloc_cfg(priv, &cfg);
+
+	if (gve_is_gqi(priv))
+		err = gve_rx_alloc_ring_gqi(priv, &cfg, gve_per_q_mem, idx);
+	else
+		err = gve_rx_alloc_ring_dqo(priv, &cfg, gve_per_q_mem, idx);
+
+	return err;
+}
+
+static int gve_rx_queue_start(struct net_device *dev, void *per_q_mem, int idx)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_rx_ring *gve_per_q_mem;
+	int err;
+
+	if (!priv->rx)
+		return -EAGAIN;
+
+	gve_per_q_mem = (struct gve_rx_ring *)per_q_mem;
+	priv->rx[idx] = *gve_per_q_mem;
+
+	/* Single-queue creation requires quiescence on all queues */
+	gve_turndown(priv);
+
+	gve_rx_start_ring(priv, idx);
+
+	if (gve_is_qpl(priv)) {
+		/* This failure will trigger a reset - no need to clean up */
+		err = gve_register_qpl(priv, gve_rx_get_qpl(priv, idx));
+		if (err)
+			goto abort;
+	}
+
+	/* This failure will trigger a reset - no need to clean up */
+	err = gve_adminq_create_single_rx_queue(priv, idx);
+	if (err)
+		goto abort;
+
+	if (gve_is_gqi(priv))
+		gve_rx_write_doorbell(priv, &priv->rx[idx]);
+	else
+		gve_rx_post_buffers_dqo(&priv->rx[idx]);
+
+	/* Turn the unstopped queues back up */
+	gve_turnup_and_check_status(priv);
+	return 0;
+
+abort:
+	gve_rx_stop_ring(priv, idx);
+
+	/* All failures in this func result in a reset, by clearing the struct
+	 * at idx, we prevent a double free when that reset runs. The reset,
+	 * which needs the rtnl lock, will not run till this func returns and
+	 * its caller gives up the lock.
+	 */
+	memset(&priv->rx[idx], 0, sizeof(priv->rx[idx]));
+	return err;
+}
+
+static const struct netdev_queue_mgmt_ops gve_queue_mgmt_ops = {
+	.ndo_queue_mem_size	=	sizeof(struct gve_rx_ring),
+	.ndo_queue_mem_alloc	=	gve_rx_queue_mem_alloc,
+	.ndo_queue_mem_free	=	gve_rx_queue_mem_free,
+	.ndo_queue_start	=	gve_rx_queue_start,
+	.ndo_queue_stop		=	gve_rx_queue_stop,
+};
+
 static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int max_tx_queues, max_rx_queues;
@@ -2527,6 +2529,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, dev);
 	dev->ethtool_ops = &gve_ethtool_ops;
 	dev->netdev_ops = &gve_netdev_ops;
+	dev->queue_mgmt_ops = &gve_queue_mgmt_ops;
 
 	/* Set default and supported features.
 	 *
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 20f5a9e7fae9..acb73d4d0de6 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -30,6 +30,9 @@ static void gve_rx_unfill_pages(struct gve_priv *priv,
 	u32 slots = rx->mask + 1;
 	int i;
 
+	if (!rx->data.page_info)
+		return;
+
 	if (rx->data.raw_addressing) {
 		for (i = 0; i < slots; i++)
 			gve_rx_free_buffer(&priv->pdev->dev, &rx->data.page_info[i],
@@ -38,8 +41,6 @@ static void gve_rx_unfill_pages(struct gve_priv *priv,
 		for (i = 0; i < slots; i++)
 			page_ref_sub(rx->data.page_info[i].page,
 				     rx->data.page_info[i].pagecnt_bias - 1);
-		gve_unassign_qpl(cfg->qpl_cfg, rx->data.qpl->id);
-		rx->data.qpl = NULL;
 
 		for (i = 0; i < rx->qpl_copy_pool_mask + 1; i++) {
 			page_ref_sub(rx->qpl_copy_pool[i].page,
@@ -51,6 +52,41 @@ static void gve_rx_unfill_pages(struct gve_priv *priv,
 	rx->data.page_info = NULL;
 }
 
+static void gve_rx_ctx_clear(struct gve_rx_ctx *ctx)
+{
+	ctx->skb_head = NULL;
+	ctx->skb_tail = NULL;
+	ctx->total_size = 0;
+	ctx->frag_cnt = 0;
+	ctx->drop_pkt = false;
+}
+
+static void gve_rx_init_ring_state_gqi(struct gve_rx_ring *rx)
+{
+	rx->desc.seqno = 1;
+	rx->cnt = 0;
+	gve_rx_ctx_clear(&rx->ctx);
+}
+
+static void gve_rx_reset_ring_gqi(struct gve_priv *priv, int idx)
+{
+	struct gve_rx_ring *rx = &priv->rx[idx];
+	const u32 slots = priv->rx_desc_cnt;
+	size_t size;
+
+	/* Reset desc ring */
+	if (rx->desc.desc_ring) {
+		size = slots * sizeof(rx->desc.desc_ring[0]);
+		memset(rx->desc.desc_ring, 0, size);
+	}
+
+	/* Reset q_resources */
+	if (rx->q_resources)
+		memset(rx->q_resources, 0, sizeof(*rx->q_resources));
+
+	gve_rx_init_ring_state_gqi(rx);
+}
+
 void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -60,34 +96,48 @@ void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx)
 
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
+	gve_rx_reset_ring_gqi(priv, idx);
 }
 
-static void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
-				 struct gve_rx_alloc_rings_cfg *cfg)
+void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
+			  struct gve_rx_alloc_rings_cfg *cfg)
 {
 	struct device *dev = &priv->pdev->dev;
 	u32 slots = rx->mask + 1;
 	int idx = rx->q_num;
 	size_t bytes;
+	u32 qpl_id;
 
-	bytes = sizeof(struct gve_rx_desc) * cfg->ring_size;
-	dma_free_coherent(dev, bytes, rx->desc.desc_ring, rx->desc.bus);
-	rx->desc.desc_ring = NULL;
+	if (rx->desc.desc_ring) {
+		bytes = sizeof(struct gve_rx_desc) * cfg->ring_size;
+		dma_free_coherent(dev, bytes, rx->desc.desc_ring, rx->desc.bus);
+		rx->desc.desc_ring = NULL;
+	}
 
-	dma_free_coherent(dev, sizeof(*rx->q_resources),
-			  rx->q_resources, rx->q_resources_bus);
-	rx->q_resources = NULL;
+	if (rx->q_resources) {
+		dma_free_coherent(dev, sizeof(*rx->q_resources),
+				  rx->q_resources, rx->q_resources_bus);
+		rx->q_resources = NULL;
+	}
 
 	gve_rx_unfill_pages(priv, rx, cfg);
 
-	bytes = sizeof(*rx->data.data_ring) * slots;
-	dma_free_coherent(dev, bytes, rx->data.data_ring,
-			  rx->data.data_bus);
-	rx->data.data_ring = NULL;
+	if (rx->data.data_ring) {
+		bytes = sizeof(*rx->data.data_ring) * slots;
+		dma_free_coherent(dev, bytes, rx->data.data_ring,
+				  rx->data.data_bus);
+		rx->data.data_ring = NULL;
+	}
 
 	kvfree(rx->qpl_copy_pool);
 	rx->qpl_copy_pool = NULL;
 
+	if (rx->data.qpl) {
+		qpl_id = gve_get_rx_qpl_id(cfg->qcfg_tx, idx);
+		gve_free_queue_page_list(priv, rx->data.qpl, qpl_id);
+		rx->data.qpl = NULL;
+	}
+
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
 }
 
@@ -144,14 +194,6 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 	if (!rx->data.page_info)
 		return -ENOMEM;
 
-	if (!rx->data.raw_addressing) {
-		rx->data.qpl = gve_assign_rx_qpl(cfg, rx->q_num);
-		if (!rx->data.qpl) {
-			kvfree(rx->data.page_info);
-			rx->data.page_info = NULL;
-			return -ENOMEM;
-		}
-	}
 	for (i = 0; i < slots; i++) {
 		if (!rx->data.raw_addressing) {
 			struct page *page = rx->data.qpl->pages[i];
@@ -204,9 +246,6 @@ alloc_err_qpl:
 		page_ref_sub(rx->data.page_info[i].page,
 			     rx->data.page_info[i].pagecnt_bias - 1);
 
-	gve_unassign_qpl(cfg->qpl_cfg, rx->data.qpl->id);
-	rx->data.qpl = NULL;
-
 	return err;
 
 alloc_err_rda:
@@ -217,15 +256,6 @@ alloc_err_rda:
 	return err;
 }
 
-static void gve_rx_ctx_clear(struct gve_rx_ctx *ctx)
-{
-	ctx->skb_head = NULL;
-	ctx->skb_tail = NULL;
-	ctx->total_size = 0;
-	ctx->frag_cnt = 0;
-	ctx->drop_pkt = false;
-}
-
 void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -234,14 +264,16 @@ void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx)
 	gve_add_napi(priv, ntfy_idx, gve_napi_poll);
 }
 
-static int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
-				 struct gve_rx_alloc_rings_cfg *cfg,
-				 struct gve_rx_ring *rx,
-				 int idx)
+int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
+			  struct gve_rx_alloc_rings_cfg *cfg,
+			  struct gve_rx_ring *rx,
+			  int idx)
 {
 	struct device *hdev = &priv->pdev->dev;
-	u32 slots = priv->rx_data_slot_cnt;
+	u32 slots = cfg->ring_size;
 	int filled_pages;
+	int qpl_page_cnt;
+	u32 qpl_id = 0;
 	size_t bytes;
 	int err;
 
@@ -274,10 +306,22 @@ static int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 		goto abort_with_slots;
 	}
 
+	if (!rx->data.raw_addressing) {
+		qpl_id = gve_get_rx_qpl_id(cfg->qcfg_tx, rx->q_num);
+		qpl_page_cnt = cfg->ring_size;
+
+		rx->data.qpl = gve_alloc_queue_page_list(priv, qpl_id,
+							 qpl_page_cnt);
+		if (!rx->data.qpl) {
+			err = -ENOMEM;
+			goto abort_with_copy_pool;
+		}
+	}
+
 	filled_pages = gve_rx_prefill_pages(rx, cfg);
 	if (filled_pages < 0) {
 		err = -ENOMEM;
-		goto abort_with_copy_pool;
+		goto abort_with_qpl;
 	}
 	rx->fill_cnt = filled_pages;
 	/* Ensure data ring slots (packet buffers) are visible. */
@@ -304,9 +348,8 @@ static int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 		err = -ENOMEM;
 		goto abort_with_q_resources;
 	}
-	rx->cnt = 0;
 	rx->db_threshold = slots / 2;
-	rx->desc.seqno = 1;
+	gve_rx_init_ring_state_gqi(rx);
 
 	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	gve_rx_ctx_clear(&rx->ctx);
@@ -319,6 +362,11 @@ abort_with_q_resources:
 	rx->q_resources = NULL;
 abort_filled:
 	gve_rx_unfill_pages(priv, rx, cfg);
+abort_with_qpl:
+	if (!rx->data.raw_addressing) {
+		gve_free_queue_page_list(priv, rx->data.qpl, qpl_id);
+		rx->data.qpl = NULL;
+	}
 abort_with_copy_pool:
 	kvfree(rx->qpl_copy_pool);
 	rx->qpl_copy_pool = NULL;
@@ -337,12 +385,6 @@ int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	if (!cfg->raw_addressing && !cfg->qpls) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc QPL ring before allocing QPLs\n");
-		return -EINVAL;
-	}
-
 	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8e8071308aeb..c1c912de59c7 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -178,7 +178,7 @@ static int gve_alloc_page_dqo(struct gve_rx_ring *rx,
 			return err;
 	} else {
 		idx = rx->dqo.next_qpl_page_idx;
-		if (idx >= priv->rx_pages_per_qpl) {
+		if (idx >= gve_get_rx_pages_per_qpl_dqo(priv->rx_desc_cnt)) {
 			net_err_ratelimited("%s: Out of QPL pages\n",
 					    priv->dev->name);
 			return -ENOMEM;
@@ -211,6 +211,82 @@ static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx)
 	}
 }
 
+static void gve_rx_init_ring_state_dqo(struct gve_rx_ring *rx,
+				       const u32 buffer_queue_slots,
+				       const u32 completion_queue_slots)
+{
+	int i;
+
+	/* Set buffer queue state */
+	rx->dqo.bufq.mask = buffer_queue_slots - 1;
+	rx->dqo.bufq.head = 0;
+	rx->dqo.bufq.tail = 0;
+
+	/* Set completion queue state */
+	rx->dqo.complq.num_free_slots = completion_queue_slots;
+	rx->dqo.complq.mask = completion_queue_slots - 1;
+	rx->dqo.complq.cur_gen_bit = 0;
+	rx->dqo.complq.head = 0;
+
+	/* Set RX SKB context */
+	rx->ctx.skb_head = NULL;
+	rx->ctx.skb_tail = NULL;
+
+	/* Set up linked list of buffer IDs */
+	if (rx->dqo.buf_states) {
+		for (i = 0; i < rx->dqo.num_buf_states - 1; i++)
+			rx->dqo.buf_states[i].next = i + 1;
+		rx->dqo.buf_states[rx->dqo.num_buf_states - 1].next = -1;
+	}
+
+	rx->dqo.free_buf_states = 0;
+	rx->dqo.recycled_buf_states.head = -1;
+	rx->dqo.recycled_buf_states.tail = -1;
+	rx->dqo.used_buf_states.head = -1;
+	rx->dqo.used_buf_states.tail = -1;
+}
+
+static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
+{
+	struct gve_rx_ring *rx = &priv->rx[idx];
+	size_t size;
+	int i;
+
+	const u32 buffer_queue_slots = priv->rx_desc_cnt;
+	const u32 completion_queue_slots = priv->rx_desc_cnt;
+
+	/* Reset buffer queue */
+	if (rx->dqo.bufq.desc_ring) {
+		size = sizeof(rx->dqo.bufq.desc_ring[0]) *
+			buffer_queue_slots;
+		memset(rx->dqo.bufq.desc_ring, 0, size);
+	}
+
+	/* Reset completion queue */
+	if (rx->dqo.complq.desc_ring) {
+		size = sizeof(rx->dqo.complq.desc_ring[0]) *
+			completion_queue_slots;
+		memset(rx->dqo.complq.desc_ring, 0, size);
+	}
+
+	/* Reset q_resources */
+	if (rx->q_resources)
+		memset(rx->q_resources, 0, sizeof(*rx->q_resources));
+
+	/* Reset buf states */
+	if (rx->dqo.buf_states) {
+		for (i = 0; i < rx->dqo.num_buf_states; i++) {
+			struct gve_rx_buf_state_dqo *bs = &rx->dqo.buf_states[i];
+
+			if (bs->page_info.page)
+				gve_free_page_dqo(priv, bs, !rx->dqo.qpl);
+		}
+	}
+
+	gve_rx_init_ring_state_dqo(rx, buffer_queue_slots,
+				   completion_queue_slots);
+}
+
 void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -220,16 +296,18 @@ void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
+	gve_rx_reset_ring_dqo(priv, idx);
 }
 
-static void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
-				 struct gve_rx_alloc_rings_cfg *cfg)
+void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			  struct gve_rx_alloc_rings_cfg *cfg)
 {
 	struct device *hdev = &priv->pdev->dev;
 	size_t completion_queue_slots;
 	size_t buffer_queue_slots;
 	int idx = rx->q_num;
 	size_t size;
+	u32 qpl_id;
 	int i;
 
 	completion_queue_slots = rx->dqo.complq.mask + 1;
@@ -247,8 +325,10 @@ static void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
 		if (bs->page_info.page)
 			gve_free_page_dqo(priv, bs, !rx->dqo.qpl);
 	}
+
 	if (rx->dqo.qpl) {
-		gve_unassign_qpl(cfg->qpl_cfg, rx->dqo.qpl->id);
+		qpl_id = gve_get_rx_qpl_id(cfg->qcfg_tx, rx->q_num);
+		gve_free_queue_page_list(priv, rx->dqo.qpl, qpl_id);
 		rx->dqo.qpl = NULL;
 	}
 
@@ -275,10 +355,10 @@ static void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
 }
 
-static int gve_rx_alloc_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx)
+static int gve_rx_alloc_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx,
+				 const u32 buf_count)
 {
 	struct device *hdev = &priv->pdev->dev;
-	int buf_count = rx->dqo.bufq.mask + 1;
 
 	rx->dqo.hdr_bufs.data = dma_alloc_coherent(hdev, priv->header_buf_size * buf_count,
 						   &rx->dqo.hdr_bufs.addr, GFP_KERNEL);
@@ -296,17 +376,17 @@ void gve_rx_start_ring_dqo(struct gve_priv *priv, int idx)
 	gve_add_napi(priv, ntfy_idx, gve_napi_poll_dqo);
 }
 
-static int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
-				 struct gve_rx_alloc_rings_cfg *cfg,
-				 struct gve_rx_ring *rx,
-				 int idx)
+int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
+			  struct gve_rx_alloc_rings_cfg *cfg,
+			  struct gve_rx_ring *rx,
+			  int idx)
 {
 	struct device *hdev = &priv->pdev->dev;
+	int qpl_page_cnt;
 	size_t size;
-	int i;
+	u32 qpl_id;
 
-	const u32 buffer_queue_slots = cfg->raw_addressing ?
-		priv->options_dqo_rda.rx_buff_ring_entries : cfg->ring_size;
+	const u32 buffer_queue_slots = cfg->ring_size;
 	const u32 completion_queue_slots = cfg->ring_size;
 
 	netif_dbg(priv, drv, priv->dev, "allocating rx ring DQO\n");
@@ -314,15 +394,10 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	memset(rx, 0, sizeof(*rx));
 	rx->gve = priv;
 	rx->q_num = idx;
-	rx->dqo.bufq.mask = buffer_queue_slots - 1;
-	rx->dqo.complq.num_free_slots = completion_queue_slots;
-	rx->dqo.complq.mask = completion_queue_slots - 1;
-	rx->ctx.skb_head = NULL;
-	rx->ctx.skb_tail = NULL;
 
 	rx->dqo.num_buf_states = cfg->raw_addressing ?
 		min_t(s16, S16_MAX, buffer_queue_slots * 4) :
-		priv->rx_pages_per_qpl;
+		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
 	rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states,
 				      sizeof(rx->dqo.buf_states[0]),
 				      GFP_KERNEL);
@@ -331,19 +406,9 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 
 	/* Allocate header buffers for header-split */
 	if (cfg->enable_header_split)
-		if (gve_rx_alloc_hdr_bufs(priv, rx))
+		if (gve_rx_alloc_hdr_bufs(priv, rx, buffer_queue_slots))
 			goto err;
 
-	/* Set up linked list of buffer IDs */
-	for (i = 0; i < rx->dqo.num_buf_states - 1; i++)
-		rx->dqo.buf_states[i].next = i + 1;
-
-	rx->dqo.buf_states[rx->dqo.num_buf_states - 1].next = -1;
-	rx->dqo.recycled_buf_states.head = -1;
-	rx->dqo.recycled_buf_states.tail = -1;
-	rx->dqo.used_buf_states.head = -1;
-	rx->dqo.used_buf_states.tail = -1;
-
 	/* Allocate RX completion queue */
 	size = sizeof(rx->dqo.complq.desc_ring[0]) *
 		completion_queue_slots;
@@ -360,7 +425,11 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 		goto err;
 
 	if (!cfg->raw_addressing) {
-		rx->dqo.qpl = gve_assign_rx_qpl(cfg, rx->q_num);
+		qpl_id = gve_get_rx_qpl_id(cfg->qcfg_tx, rx->q_num);
+		qpl_page_cnt = gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
+
+		rx->dqo.qpl = gve_alloc_queue_page_list(priv, qpl_id,
+							qpl_page_cnt);
 		if (!rx->dqo.qpl)
 			goto err;
 		rx->dqo.next_qpl_page_idx = 0;
@@ -371,6 +440,9 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	if (!rx->q_resources)
 		goto err;
 
+	gve_rx_init_ring_state_dqo(rx, buffer_queue_slots,
+				   completion_queue_slots);
+
 	return 0;
 
 err:
@@ -393,12 +465,6 @@ int gve_rx_alloc_rings_dqo(struct gve_priv *priv,
 	int err;
 	int i;
 
-	if (!cfg->raw_addressing && !cfg->qpls) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc QPL ring before allocing QPLs\n");
-		return -EINVAL;
-	}
-
 	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 4b9853adc113..24a64ec1073e 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -216,6 +216,7 @@ static void gve_tx_free_ring_gqi(struct gve_priv *priv, struct gve_tx_ring *tx,
 	struct device *hdev = &priv->pdev->dev;
 	int idx = tx->q_num;
 	size_t bytes;
+	u32 qpl_id;
 	u32 slots;
 
 	slots = tx->mask + 1;
@@ -223,9 +224,12 @@ static void gve_tx_free_ring_gqi(struct gve_priv *priv, struct gve_tx_ring *tx,
 			  tx->q_resources, tx->q_resources_bus);
 	tx->q_resources = NULL;
 
-	if (!tx->raw_addressing) {
-		gve_tx_fifo_release(priv, &tx->tx_fifo);
-		gve_unassign_qpl(cfg->qpl_cfg, tx->tx_fifo.qpl->id);
+	if (tx->tx_fifo.qpl) {
+		if (tx->tx_fifo.base)
+			gve_tx_fifo_release(priv, &tx->tx_fifo);
+
+		qpl_id = gve_tx_qpl_id(priv, tx->q_num);
+		gve_free_queue_page_list(priv, tx->tx_fifo.qpl, qpl_id);
 		tx->tx_fifo.qpl = NULL;
 	}
 
@@ -256,6 +260,8 @@ static int gve_tx_alloc_ring_gqi(struct gve_priv *priv,
 				 int idx)
 {
 	struct device *hdev = &priv->pdev->dev;
+	int qpl_page_cnt;
+	u32 qpl_id = 0;
 	size_t bytes;
 
 	/* Make sure everything is zeroed to start */
@@ -280,9 +286,14 @@ static int gve_tx_alloc_ring_gqi(struct gve_priv *priv,
 	tx->raw_addressing = cfg->raw_addressing;
 	tx->dev = hdev;
 	if (!tx->raw_addressing) {
-		tx->tx_fifo.qpl = gve_assign_tx_qpl(cfg, idx);
+		qpl_id = gve_tx_qpl_id(priv, tx->q_num);
+		qpl_page_cnt = priv->tx_pages_per_qpl;
+
+		tx->tx_fifo.qpl = gve_alloc_queue_page_list(priv, qpl_id,
+							    qpl_page_cnt);
 		if (!tx->tx_fifo.qpl)
 			goto abort_with_desc;
+
 		/* map Tx FIFO */
 		if (gve_tx_fifo_init(priv, &tx->tx_fifo))
 			goto abort_with_qpl;
@@ -302,8 +313,10 @@ abort_with_fifo:
 	if (!tx->raw_addressing)
 		gve_tx_fifo_release(priv, &tx->tx_fifo);
 abort_with_qpl:
-	if (!tx->raw_addressing)
-		gve_unassign_qpl(cfg->qpl_cfg, tx->tx_fifo.qpl->id);
+	if (!tx->raw_addressing) {
+		gve_free_queue_page_list(priv, tx->tx_fifo.qpl, qpl_id);
+		tx->tx_fifo.qpl = NULL;
+	}
 abort_with_desc:
 	dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
 	tx->desc = NULL;
@@ -320,12 +333,6 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	if (!cfg->raw_addressing && !cfg->qpls) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc QPL ring before allocing QPLs\n");
-		return -EINVAL;
-	}
-
 	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index bc34b6cd3a3e..fe1b26a4d736 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -209,6 +209,7 @@ static void gve_tx_free_ring_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
 	struct device *hdev = &priv->pdev->dev;
 	int idx = tx->q_num;
 	size_t bytes;
+	u32 qpl_id;
 
 	if (tx->q_resources) {
 		dma_free_coherent(hdev, sizeof(*tx->q_resources),
@@ -237,7 +238,8 @@ static void gve_tx_free_ring_dqo(struct gve_priv *priv, struct gve_tx_ring *tx,
 	tx->dqo.tx_qpl_buf_next = NULL;
 
 	if (tx->dqo.qpl) {
-		gve_unassign_qpl(cfg->qpl_cfg, tx->dqo.qpl->id);
+		qpl_id = gve_tx_qpl_id(priv, tx->q_num);
+		gve_free_queue_page_list(priv, tx->dqo.qpl, qpl_id);
 		tx->dqo.qpl = NULL;
 	}
 
@@ -285,7 +287,9 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv,
 {
 	struct device *hdev = &priv->pdev->dev;
 	int num_pending_packets;
+	int qpl_page_cnt;
 	size_t bytes;
+	u32 qpl_id;
 	int i;
 
 	memset(tx, 0, sizeof(*tx));
@@ -295,9 +299,7 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv,
 
 	/* Queue sizes must be a power of 2 */
 	tx->mask = cfg->ring_size - 1;
-	tx->dqo.complq_mask = priv->queue_format == GVE_DQO_RDA_FORMAT ?
-		priv->options_dqo_rda.tx_comp_ring_entries - 1 :
-		tx->mask;
+	tx->dqo.complq_mask = tx->mask;
 
 	/* The max number of pending packets determines the maximum number of
 	 * descriptors which maybe written to the completion queue.
@@ -354,7 +356,11 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv,
 		goto err;
 
 	if (!cfg->raw_addressing) {
-		tx->dqo.qpl = gve_assign_tx_qpl(cfg, idx);
+		qpl_id = gve_tx_qpl_id(priv, tx->q_num);
+		qpl_page_cnt = priv->tx_pages_per_qpl;
+
+		tx->dqo.qpl = gve_alloc_queue_page_list(priv, qpl_id,
+							qpl_page_cnt);
 		if (!tx->dqo.qpl)
 			goto err;
 
@@ -376,12 +382,6 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	if (!cfg->raw_addressing && !cfg->qpls) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc QPL ring before allocing QPLs\n");
-		return -EINVAL;
-	}
-
 	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 8a713eed4465..fd32e15cadcb 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1777,7 +1777,7 @@ static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu)
 	}
 
 	/* finally, set new mtu to netdevice */
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 out:
 	if (if_running) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 133c94646c21..7cebb08bd320 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -104,6 +104,7 @@ enum HNAE3_DEV_CAP_BITS {
 	HNAE3_DEV_SUPPORT_WOL_B,
 	HNAE3_DEV_SUPPORT_TM_FLUSH_B,
 	HNAE3_DEV_SUPPORT_VF_FAULT_B,
+	HNAE3_DEV_SUPPORT_ERR_MOD_GEN_REG_B,
 };
 
 #define hnae3_ae_dev_fd_supported(ae_dev) \
@@ -181,6 +182,9 @@ enum HNAE3_DEV_CAP_BITS {
 #define hnae3_ae_dev_vf_fault_supported(ae_dev) \
 	test_bit(HNAE3_DEV_SUPPORT_VF_FAULT_B, (ae_dev)->caps)
 
+#define hnae3_ae_dev_gen_reg_dfx_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_ERR_MOD_GEN_REG_B, (hdev)->ae_dev->caps)
+
 enum HNAE3_PF_CAP_BITS {
 	HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0,
 };
@@ -362,6 +366,15 @@ struct hnae3_vector_info {
 #define HNAE3_FW_VERSION_BYTE0_SHIFT	0
 #define HNAE3_FW_VERSION_BYTE0_MASK	GENMASK(7, 0)
 
+#define HNAE3_SCC_VERSION_BYTE3_SHIFT	24
+#define HNAE3_SCC_VERSION_BYTE3_MASK	GENMASK(31, 24)
+#define HNAE3_SCC_VERSION_BYTE2_SHIFT	16
+#define HNAE3_SCC_VERSION_BYTE2_MASK	GENMASK(23, 16)
+#define HNAE3_SCC_VERSION_BYTE1_SHIFT	8
+#define HNAE3_SCC_VERSION_BYTE1_MASK	GENMASK(15, 8)
+#define HNAE3_SCC_VERSION_BYTE0_SHIFT	0
+#define HNAE3_SCC_VERSION_BYTE0_MASK	GENMASK(7, 0)
+
 struct hnae3_ring_chain_node {
 	struct hnae3_ring_chain_node *next;
 	u32 tqp_index;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
index 652d71326231..ea40b594dbac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
@@ -158,6 +158,7 @@ static const struct hclge_comm_caps_bit_map hclge_pf_cmd_caps[] = {
 	{HCLGE_COMM_CAP_WOL_B, HNAE3_DEV_SUPPORT_WOL_B},
 	{HCLGE_COMM_CAP_TM_FLUSH_B, HNAE3_DEV_SUPPORT_TM_FLUSH_B},
 	{HCLGE_COMM_CAP_VF_FAULT_B, HNAE3_DEV_SUPPORT_VF_FAULT_B},
+	{HCLGE_COMM_CAP_ERR_MOD_GEN_REG_B, HNAE3_DEV_SUPPORT_ERR_MOD_GEN_REG_B},
 };
 
 static const struct hclge_comm_caps_bit_map hclge_vf_cmd_caps[] = {
@@ -470,10 +471,14 @@ static int hclge_comm_cmd_check_result(struct hclge_comm_hw *hw,
 int hclge_comm_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
 			int num)
 {
+	bool is_special = hclge_comm_is_special_opcode(le16_to_cpu(desc->opcode));
 	struct hclge_comm_cmq_ring *csq = &hw->cmq.csq;
 	int ret;
 	int ntc;
 
+	if (hw->cmq.ops.trace_cmd_send)
+		hw->cmq.ops.trace_cmd_send(hw, desc, num, is_special);
+
 	spin_lock_bh(&hw->cmq.csq.lock);
 
 	if (test_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hw->comm_state)) {
@@ -507,6 +512,9 @@ int hclge_comm_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
 
 	spin_unlock_bh(&hw->cmq.csq.lock);
 
+	if (hw->cmq.ops.trace_cmd_get)
+		hw->cmq.ops.trace_cmd_get(hw, desc, num, is_special);
+
 	return ret;
 }
 
@@ -584,6 +592,17 @@ err_csq:
 	return ret;
 }
 
+void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
+			     const struct hclge_comm_cmq_ops *ops)
+{
+	struct hclge_comm_cmq *cmdq = &hw->cmq;
+
+	if (ops) {
+		cmdq->ops.trace_cmd_send = ops->trace_cmd_send;
+		cmdq->ops.trace_cmd_get = ops->trace_cmd_get;
+	}
+}
+
 int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw,
 			u32 *fw_version, bool is_pf,
 			unsigned long reset_pending)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
index 552396518e08..2c2a2f1e0d7a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h
@@ -91,6 +91,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_DFX_RCB_REG		= 0x004D,
 	HCLGE_OPC_DFX_TQP_REG		= 0x004E,
 	HCLGE_OPC_DFX_SSU_REG_2		= 0x004F,
+	HCLGE_OPC_DFX_GEN_REG		= 0x7038,
 
 	HCLGE_OPC_QUERY_DEV_SPECS	= 0x0050,
 	HCLGE_OPC_GET_QUEUE_ERR_VF      = 0x0067,
@@ -246,6 +247,9 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QCN_AJUST_INIT	= 0x1A07,
 	HCLGE_OPC_QCN_DFX_CNT_STATUS    = 0x1A08,
 
+	/* SCC commands */
+	HCLGE_OPC_QUERY_SCC_VER		= 0x1A84,
+
 	/* Mailbox command */
 	HCLGEVF_OPC_MBX_PF_TO_VF	= 0x2000,
 	HCLGEVF_OPC_MBX_VF_TO_PF	= 0x2001,
@@ -353,6 +357,7 @@ enum HCLGE_COMM_CAP_BITS {
 	HCLGE_COMM_CAP_LANE_NUM_B = 27,
 	HCLGE_COMM_CAP_WOL_B = 28,
 	HCLGE_COMM_CAP_TM_FLUSH_B = 31,
+	HCLGE_COMM_CAP_ERR_MOD_GEN_REG_B = 32,
 };
 
 enum HCLGE_COMM_API_CAP_BITS {
@@ -392,6 +397,11 @@ struct hclge_comm_query_version_cmd {
 	__le32 caps[HCLGE_COMM_QUERY_CAP_LENGTH]; /* capabilities of device */
 };
 
+struct hclge_comm_query_scc_cmd {
+	__le32 scc_version;
+	u8 rsv[20];
+};
+
 #define HCLGE_DESC_DATA_LEN		6
 struct hclge_desc {
 	__le16 opcode;
@@ -423,11 +433,22 @@ enum hclge_comm_cmd_status {
 	HCLGE_COMM_ERR_CSQ_ERROR	= -3,
 };
 
+struct hclge_comm_hw;
+struct hclge_comm_cmq_ops {
+	void (*trace_cmd_send)(struct hclge_comm_hw *hw,
+			       struct hclge_desc *desc,
+			       int num, bool is_special);
+	void (*trace_cmd_get)(struct hclge_comm_hw *hw,
+			      struct hclge_desc *desc,
+			      int num, bool is_special);
+};
+
 struct hclge_comm_cmq {
 	struct hclge_comm_cmq_ring csq;
 	struct hclge_comm_cmq_ring crq;
 	u16 tx_timeout;
 	enum hclge_comm_cmd_status last_status;
+	struct hclge_comm_cmq_ops ops;
 };
 
 struct hclge_comm_hw {
@@ -474,5 +495,6 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw);
 int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw,
 			u32 *fw_version, bool is_pf,
 			unsigned long reset_pending);
-
+void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
+			     const struct hclge_comm_cmq_ops *ops);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 19668a8d22f7..dfdc0e032c07 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2761,7 +2761,7 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 		netdev_err(netdev, "failed to change MTU in hardware %d\n",
 			   ret);
 	else
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 9ec471ced3d6..debf143e9940 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -18,6 +18,646 @@ static const char * const hclge_mac_state_str[] = {
 
 static const char * const tc_map_mode_str[] = { "PRIO", "DSCP" };
 
+static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
+	{false, "Reserved"},
+	{true,	"BP_CPU_STATE"},
+	{true,	"DFX_MSIX_INFO_NIC_0"},
+	{true,	"DFX_MSIX_INFO_NIC_1"},
+	{true,	"DFX_MSIX_INFO_NIC_2"},
+	{true,	"DFX_MSIX_INFO_NIC_3"},
+
+	{true,	"DFX_MSIX_INFO_ROC_0"},
+	{true,	"DFX_MSIX_INFO_ROC_1"},
+	{true,	"DFX_MSIX_INFO_ROC_2"},
+	{true,	"DFX_MSIX_INFO_ROC_3"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
+	{false, "Reserved"},
+	{true,	"SSU_ETS_PORT_STATUS"},
+	{true,	"SSU_ETS_TCG_STATUS"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{true,	"SSU_BP_STATUS_0"},
+
+	{true,	"SSU_BP_STATUS_1"},
+	{true,	"SSU_BP_STATUS_2"},
+	{true,	"SSU_BP_STATUS_3"},
+	{true,	"SSU_BP_STATUS_4"},
+	{true,	"SSU_BP_STATUS_5"},
+	{true,	"SSU_MAC_TX_PFC_IND"},
+
+	{true,	"MAC_SSU_RX_PFC_IND"},
+	{true,	"BTMP_AGEING_ST_B0"},
+	{true,	"BTMP_AGEING_ST_B1"},
+	{true,	"BTMP_AGEING_ST_B2"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"FULL_DROP_NUM"},
+	{true,	"PART_DROP_NUM"},
+	{true,	"PPP_KEY_DROP_NUM"},
+	{true,	"PPP_RLT_DROP_NUM"},
+	{true,	"LO_PRI_UNICAST_RLT_DROP_NUM"},
+	{true,	"HI_PRI_MULTICAST_RLT_DROP_NUM"},
+
+	{true,	"LO_PRI_MULTICAST_RLT_DROP_NUM"},
+	{true,	"NCSI_PACKET_CURR_BUFFER_CNT"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK0"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK1"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK2"},
+	{true,	"SSU_MB_RD_RLT_DROP_CNT"},
+
+	{true,	"SSU_PPP_MAC_KEY_NUM_L"},
+	{true,	"SSU_PPP_MAC_KEY_NUM_H"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_L"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_H"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_L"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_H"},
+
+	{true,	"PPP_SSU_HOST_RLT_NUM_L"},
+	{true,	"PPP_SSU_HOST_RLT_NUM_H"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_L"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_H"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_L"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"SSU_KEY_DROP_NUM"},
+	{true,	"MB_UNCOPY_NUM"},
+	{true,	"RX_OQ_DROP_PKT_CNT"},
+	{true,	"TX_OQ_DROP_PKT_CNT"},
+	{true,	"BANK_UNBALANCE_DROP_CNT"},
+	{true,	"BANK_UNBALANCE_RX_DROP_CNT"},
+
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"RX_OQ_GLB_DROP_PKT_CNT"},
+	{false, "Reserved"},
+
+	{true,	"LO_PRI_UNICAST_CUR_CNT"},
+	{true,	"HI_PRI_MULTICAST_CUR_CNT"},
+	{true,	"LO_PRI_MULTICAST_CUR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
+	{true,	"prt_id"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_0"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_1"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_2"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_3"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_4"},
+
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_5"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_6"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_7"},
+	{true,	"PACKET_CURR_BUFFER_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"RX_PACKET_IN_CNT_L"},
+	{true,	"RX_PACKET_IN_CNT_H"},
+	{true,	"RX_PACKET_OUT_CNT_L"},
+	{true,	"RX_PACKET_OUT_CNT_H"},
+	{true,	"TX_PACKET_IN_CNT_L"},
+	{true,	"TX_PACKET_IN_CNT_H"},
+
+	{true,	"TX_PACKET_OUT_CNT_L"},
+	{true,	"TX_PACKET_OUT_CNT_H"},
+	{true,	"ROC_RX_PACKET_IN_CNT_L"},
+	{true,	"ROC_RX_PACKET_IN_CNT_H"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_L"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_7_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_2_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_5_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_0_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_3_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_6_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
+	{true,	"OQ_INDEX"},
+	{true,	"QUEUE_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
+	{true,	"prt_id"},
+	{true,	"IGU_RX_ERR_PKT"},
+	{true,	"IGU_RX_NO_SOF_PKT"},
+	{true,	"EGU_TX_1588_SHORT_PKT"},
+	{true,	"EGU_TX_1588_PKT"},
+	{true,	"EGU_TX_ERR_PKT"},
+
+	{true,	"IGU_RX_OUT_L2_PKT"},
+	{true,	"IGU_RX_OUT_L3_PKT"},
+	{true,	"IGU_RX_OUT_L4_PKT"},
+	{true,	"IGU_RX_IN_L2_PKT"},
+	{true,	"IGU_RX_IN_L3_PKT"},
+	{true,	"IGU_RX_IN_L4_PKT"},
+
+	{true,	"IGU_RX_EL3E_PKT"},
+	{true,	"IGU_RX_EL4E_PKT"},
+	{true,	"IGU_RX_L3E_PKT"},
+	{true,	"IGU_RX_L4E_PKT"},
+	{true,	"IGU_RX_ROCEE_PKT"},
+	{true,	"IGU_RX_OUT_UDP0_PKT"},
+
+	{true,	"IGU_RX_IN_UDP0_PKT"},
+	{true,	"IGU_MC_CAR_DROP_PKT_L"},
+	{true,	"IGU_MC_CAR_DROP_PKT_H"},
+	{true,	"IGU_BC_CAR_DROP_PKT_L"},
+	{true,	"IGU_BC_CAR_DROP_PKT_H"},
+	{false, "Reserved"},
+
+	{true,	"IGU_RX_OVERSIZE_PKT_L"},
+	{true,	"IGU_RX_OVERSIZE_PKT_H"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_L"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_H"},
+	{true,	"IGU_RX_OUT_ALL_PKT_L"},
+	{true,	"IGU_RX_OUT_ALL_PKT_H"},
+
+	{true,	"IGU_TX_OUT_ALL_PKT_L"},
+	{true,	"IGU_TX_OUT_ALL_PKT_H"},
+	{true,	"IGU_RX_UNI_PKT_L"},
+	{true,	"IGU_RX_UNI_PKT_H"},
+	{true,	"IGU_RX_MULTI_PKT_L"},
+	{true,	"IGU_RX_MULTI_PKT_H"},
+
+	{true,	"IGU_RX_BROAD_PKT_L"},
+	{true,	"IGU_RX_BROAD_PKT_H"},
+	{true,	"EGU_TX_OUT_ALL_PKT_L"},
+	{true,	"EGU_TX_OUT_ALL_PKT_H"},
+	{true,	"EGU_TX_UNI_PKT_L"},
+	{true,	"EGU_TX_UNI_PKT_H"},
+
+	{true,	"EGU_TX_MULTI_PKT_L"},
+	{true,	"EGU_TX_MULTI_PKT_H"},
+	{true,	"EGU_TX_BROAD_PKT_L"},
+	{true,	"EGU_TX_BROAD_PKT_H"},
+	{true,	"IGU_TX_KEY_NUM_L"},
+	{true,	"IGU_TX_KEY_NUM_H"},
+
+	{true,	"IGU_RX_NON_TUN_PKT_L"},
+	{true,	"IGU_RX_NON_TUN_PKT_H"},
+	{true,	"IGU_RX_TUN_PKT_L"},
+	{true,	"IGU_RX_TUN_PKT_H"},
+	{false,	"Reserved"},
+	{false,	"Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
+	{true, "tc_queue_num"},
+	{true, "FSM_DFX_ST0"},
+	{true, "FSM_DFX_ST1"},
+	{true, "RPU_RX_PKT_DROP_CNT"},
+	{true, "BUF_WAIT_TIMEOUT"},
+	{true, "BUF_WAIT_TIMEOUT_QID"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
+	{false, "Reserved"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+
+	{true,	"FIFO_DFX_ST5"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
+	{false, "Reserved"},
+	{true,	"NCSI_EGU_TX_FIFO_STS"},
+	{true,	"NCSI_PAUSE_STATUS"},
+	{true,	"NCSI_RX_CTRL_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_CKS_ERR_CNT"},
+
+	{true,	"NCSI_RX_CTRL_PKT_CNT"},
+	{true,	"NCSI_RX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_PKT_CNT"},
+	{true,	"NCSI_RX_FCS_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_DMAC_ERR_CNT"},
+
+	{true,	"NCSI_TX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_CNT"},
+	{true,	"NCSI_TX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_PKT_CNT"},
+	{true,	"NCSI_TX_PT_PKT_TRUNC_CNT"},
+
+	{true,	"NCSI_TX_PT_PKT_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_TRUNC_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_CFLIT_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_OK"},
+	{true,	"NCSI_MAC_RX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_RX_UC_PKTS"},
+	{true,	"NCSI_MAC_RX_MC_PKTS"},
+	{true,	"NCSI_MAC_RX_BC_PKTS"},
+	{true,	"NCSI_MAC_RX_PKTS_64OCTETS"},
+
+	{true,	"NCSI_MAC_RX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_255TO511OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1024TO1518OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1519TOMAXOCTETS"},
+
+	{true,	"NCSI_MAC_RX_FCS_ERRORS"},
+	{true,	"NCSI_MAC_RX_LONG_ERRORS"},
+	{true,	"NCSI_MAC_RX_JABBER_ERRORS"},
+	{true,	"NCSI_MAC_RX_RUNT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_SHORT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_FILT_PKT_CNT"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_TOTAL_FILT"},
+	{true,	"NCSI_MAC_TX_OCTETS_OK"},
+	{true,	"NCSI_MAC_TX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_TX_UC_PKTS"},
+	{true,	"NCSI_MAC_TX_MC_PKTS"},
+	{true,	"NCSI_MAC_TX_BC_PKTS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_64OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_256TO511OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_1024TO1518OCTETS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_1519TOMAXOCTETS"},
+	{true,	"NCSI_MAC_TX_UNDERRUN"},
+	{true,	"NCSI_MAC_TX_CRC_ERROR"},
+	{true,	"NCSI_MAC_TX_PAUSE_FRAMES"},
+	{true,	"NCSI_MAC_RX_PAD_PKTS"},
+	{true,	"NCSI_MAC_RX_PAUSE_FRAMES"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
+	{false, "Reserved"},
+	{true,	"LGE_IGU_AFIFO_DFX_0"},
+	{true,	"LGE_IGU_AFIFO_DFX_1"},
+	{true,	"LGE_IGU_AFIFO_DFX_2"},
+	{true,	"LGE_IGU_AFIFO_DFX_3"},
+	{true,	"LGE_IGU_AFIFO_DFX_4"},
+
+	{true,	"LGE_IGU_AFIFO_DFX_5"},
+	{true,	"LGE_IGU_AFIFO_DFX_6"},
+	{true,	"LGE_IGU_AFIFO_DFX_7"},
+	{true,	"LGE_EGU_AFIFO_DFX_0"},
+	{true,	"LGE_EGU_AFIFO_DFX_1"},
+	{true,	"LGE_EGU_AFIFO_DFX_2"},
+
+	{true,	"LGE_EGU_AFIFO_DFX_3"},
+	{true,	"LGE_EGU_AFIFO_DFX_4"},
+	{true,	"LGE_EGU_AFIFO_DFX_5"},
+	{true,	"LGE_EGU_AFIFO_DFX_6"},
+	{true,	"LGE_EGU_AFIFO_DFX_7"},
+	{true,	"CGE_IGU_AFIFO_DFX_0"},
+
+	{true,	"CGE_IGU_AFIFO_DFX_1"},
+	{true,	"CGE_EGU_AFIFO_DFX_0"},
+	{true,	"CGE_EGU_AFIFO_DFX_1"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
+	{false, "Reserved"},
+	{true,	"DROP_FROM_PRT_PKT_CNT"},
+	{true,	"DROP_FROM_HOST_PKT_CNT"},
+	{true,	"DROP_TX_VLAN_PROC_CNT"},
+	{true,	"DROP_MNG_CNT"},
+	{true,	"DROP_FD_CNT"},
+
+	{true,	"DROP_NO_DST_CNT"},
+	{true,	"DROP_MC_MBID_FULL_CNT"},
+	{true,	"DROP_SC_FILTERED"},
+	{true,	"PPP_MC_DROP_PKT_CNT"},
+	{true,	"DROP_PT_CNT"},
+	{true,	"DROP_MAC_ANTI_SPOOF_CNT"},
+
+	{true,	"DROP_IG_VFV_CNT"},
+	{true,	"DROP_IG_PRTV_CNT"},
+	{true,	"DROP_CNM_PFC_PAUSE_CNT"},
+	{true,	"DROP_TORUS_TC_CNT"},
+	{true,	"DROP_TORUS_LPBK_CNT"},
+	{true,	"PPP_HFS_STS"},
+
+	{true,	"PPP_MC_RSLT_STS"},
+	{true,	"PPP_P3U_STS"},
+	{true,	"PPP_RSLT_DESCR_STS"},
+	{true,	"PPP_UMV_STS_0"},
+	{true,	"PPP_UMV_STS_1"},
+	{true,	"PPP_VFV_STS"},
+
+	{true,	"PPP_GRO_KEY_CNT"},
+	{true,	"PPP_GRO_INFO_CNT"},
+	{true,	"PPP_GRO_DROP_CNT"},
+	{true,	"PPP_GRO_OUT_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_DATA_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_TCAM_CNT"},
+
+	{true,	"PPP_GRO_INFO_MATCH_CNT"},
+	{true,	"PPP_GRO_FREE_ENTRY_CNT"},
+	{true,	"PPP_GRO_INNER_DFX_SIGNAL"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"GET_RX_PKT_CNT_L"},
+	{true,	"GET_RX_PKT_CNT_H"},
+	{true,	"GET_TX_PKT_CNT_L"},
+	{true,	"GET_TX_PKT_CNT_H"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_H"},
+
+	{true,	"SEND_MC_FROM_PRT_CNT_L"},
+	{true,	"SEND_MC_FROM_PRT_CNT_H"},
+	{true,	"SEND_MC_FROM_HOST_CNT_L"},
+	{true,	"SEND_MC_FROM_HOST_CNT_H"},
+	{true,	"SSU_MC_RD_CNT_L"},
+	{true,	"SSU_MC_RD_CNT_H"},
+
+	{true,	"SSU_MC_DROP_CNT_L"},
+	{true,	"SSU_MC_DROP_CNT_H"},
+	{true,	"SSU_MC_RD_PKT_CNT_L"},
+	{true,	"SSU_MC_RD_PKT_CNT_H"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_L"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_H"},
+
+	{true,	"PPP_MC_2PRT_PKT_CNT_L"},
+	{true,	"PPP_MC_2PRT_PKT_CNT_H"},
+	{true,	"NTSNOS_PKT_CNT_L"},
+	{true,	"NTSNOS_PKT_CNT_H"},
+	{true,	"NTUP_PKT_CNT_L"},
+	{true,	"NTUP_PKT_CNT_H"},
+
+	{true,	"NTLCL_PKT_CNT_L"},
+	{true,	"NTLCL_PKT_CNT_H"},
+	{true,	"NTTGT_PKT_CNT_L"},
+	{true,	"NTTGT_PKT_CNT_H"},
+	{true,	"RTNS_PKT_CNT_L"},
+	{true,	"RTNS_PKT_CNT_H"},
+
+	{true,	"RTLPBK_PKT_CNT_L"},
+	{true,	"RTLPBK_PKT_CNT_H"},
+	{true,	"NR_PKT_CNT_L"},
+	{true,	"NR_PKT_CNT_H"},
+	{true,	"RR_PKT_CNT_L"},
+	{true,	"RR_PKT_CNT_H"},
+
+	{true,	"MNG_TBL_HIT_CNT_L"},
+	{true,	"MNG_TBL_HIT_CNT_H"},
+	{true,	"FD_TBL_HIT_CNT_L"},
+	{true,	"FD_TBL_HIT_CNT_H"},
+	{true,	"FD_LKUP_CNT_L"},
+	{true,	"FD_LKUP_CNT_H"},
+
+	{true,	"BC_HIT_CNT_L"},
+	{true,	"BC_HIT_CNT_H"},
+	{true,	"UM_TBL_UC_HIT_CNT_L"},
+	{true,	"UM_TBL_UC_HIT_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_CNT_H"},
+
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_L"},
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_H"},
+	{true,	"MTA_TBL_HIT_CNT_L"},
+	{true,	"MTA_TBL_HIT_CNT_H"},
+	{true,	"FWD_BONDING_HIT_CNT_L"},
+	{true,	"FWD_BONDING_HIT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_CNT_H"},
+	{true,	"GET_TUNL_PKT_CNT_L"},
+	{true,	"GET_TUNL_PKT_CNT_H"},
+	{true,	"GET_BMC_PKT_CNT_L"},
+	{true,	"GET_BMC_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_H"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_L"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_H"},
+	{true,	"VLAN_MIRR_CNT_L"},
+	{true,	"VLAN_MIRR_CNT_H"},
+
+	{true,	"IG_MIRR_CNT_L"},
+	{true,	"IG_MIRR_CNT_H"},
+	{true,	"EG_MIRR_CNT_L"},
+	{true,	"EG_MIRR_CNT_H"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_L"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_H"},
+
+	{true,	"LAN_PAIR_CNT_L"},
+	{true,	"LAN_PAIR_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_H"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_L"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
+	{false, "Reserved"},
+	{true,	"FSM_DFX_ST0"},
+	{true,	"FSM_DFX_ST1"},
+	{true,	"FSM_DFX_ST2"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+	{true,	"FIFO_DFX_ST5"},
+	{true,	"FIFO_DFX_ST6"},
+	{true,	"FIFO_DFX_ST7"},
+
+	{true,	"FIFO_DFX_ST8"},
+	{true,	"FIFO_DFX_ST9"},
+	{true,	"FIFO_DFX_ST10"},
+	{true,	"FIFO_DFX_ST11"},
+	{true,	"Q_CREDIT_VLD_0"},
+	{true,	"Q_CREDIT_VLD_1"},
+
+	{true,	"Q_CREDIT_VLD_2"},
+	{true,	"Q_CREDIT_VLD_3"},
+	{true,	"Q_CREDIT_VLD_4"},
+	{true,	"Q_CREDIT_VLD_5"},
+	{true,	"Q_CREDIT_VLD_6"},
+	{true,	"Q_CREDIT_VLD_7"},
+
+	{true,	"Q_CREDIT_VLD_8"},
+	{true,	"Q_CREDIT_VLD_9"},
+	{true,	"Q_CREDIT_VLD_10"},
+	{true,	"Q_CREDIT_VLD_11"},
+	{true,	"Q_CREDIT_VLD_12"},
+	{true,	"Q_CREDIT_VLD_13"},
+
+	{true,	"Q_CREDIT_VLD_14"},
+	{true,	"Q_CREDIT_VLD_15"},
+	{true,	"Q_CREDIT_VLD_16"},
+	{true,	"Q_CREDIT_VLD_17"},
+	{true,	"Q_CREDIT_VLD_18"},
+	{true,	"Q_CREDIT_VLD_19"},
+
+	{true,	"Q_CREDIT_VLD_20"},
+	{true,	"Q_CREDIT_VLD_21"},
+	{true,	"Q_CREDIT_VLD_22"},
+	{true,	"Q_CREDIT_VLD_23"},
+	{true,	"Q_CREDIT_VLD_24"},
+	{true,	"Q_CREDIT_VLD_25"},
+
+	{true,	"Q_CREDIT_VLD_26"},
+	{true,	"Q_CREDIT_VLD_27"},
+	{true,	"Q_CREDIT_VLD_28"},
+	{true,	"Q_CREDIT_VLD_29"},
+	{true,	"Q_CREDIT_VLD_30"},
+	{true,	"Q_CREDIT_VLD_31"},
+
+	{true,	"GRO_BD_SERR_CNT"},
+	{true,	"GRO_CONTEXT_SERR_CNT"},
+	{true,	"RX_STASH_CFG_SERR_CNT"},
+	{true,	"AXI_RD_FBD_SERR_CNT"},
+	{true,	"GRO_BD_MERR_CNT"},
+	{true,	"GRO_CONTEXT_MERR_CNT"},
+
+	{true,	"RX_STASH_CFG_MERR_CNT"},
+	{true,	"AXI_RD_FBD_MERR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static const struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
+	{true, "q_num"},
+	{true, "RCB_CFG_RX_RING_TAIL"},
+	{true, "RCB_CFG_RX_RING_HEAD"},
+	{true, "RCB_CFG_RX_RING_FBDNUM"},
+	{true, "RCB_CFG_RX_RING_OFFSET"},
+	{true, "RCB_CFG_RX_RING_FBDOFFSET"},
+
+	{true, "RCB_CFG_RX_RING_PKTNUM_RECORD"},
+	{true, "RCB_CFG_TX_RING_TAIL"},
+	{true, "RCB_CFG_TX_RING_HEAD"},
+	{true, "RCB_CFG_TX_RING_FBDNUM"},
+	{true, "RCB_CFG_TX_RING_OFFSET"},
+	{true, "RCB_CFG_TX_RING_EBDNUM"},
+};
+
 static const struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
 	{ .cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
 	  .dfx_msg = &hclge_dbg_bios_common_reg[0],
@@ -161,10 +801,8 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset,
 	return 0;
 }
 
-static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
-			      struct hclge_desc *desc_src,
-			      int index, int bd_num,
-			      enum hclge_opcode_type cmd)
+int hclge_dbg_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc_src,
+		       int index, int bd_num, enum hclge_opcode_type cmd)
 {
 	struct hclge_desc *desc = desc_src;
 	int ret, i;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 724052928b88..2b998cbed826 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -99,646 +99,6 @@ struct hclge_dbg_status_dfx_info {
 	char message[HCLGE_DBG_MAX_DFX_MSG_LEN];
 };
 
-static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
-	{false, "Reserved"},
-	{true,	"BP_CPU_STATE"},
-	{true,	"DFX_MSIX_INFO_NIC_0"},
-	{true,	"DFX_MSIX_INFO_NIC_1"},
-	{true,	"DFX_MSIX_INFO_NIC_2"},
-	{true,	"DFX_MSIX_INFO_NIC_3"},
-
-	{true,	"DFX_MSIX_INFO_ROC_0"},
-	{true,	"DFX_MSIX_INFO_ROC_1"},
-	{true,	"DFX_MSIX_INFO_ROC_2"},
-	{true,	"DFX_MSIX_INFO_ROC_3"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
-	{false, "Reserved"},
-	{true,	"SSU_ETS_PORT_STATUS"},
-	{true,	"SSU_ETS_TCG_STATUS"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{true,	"SSU_BP_STATUS_0"},
-
-	{true,	"SSU_BP_STATUS_1"},
-	{true,	"SSU_BP_STATUS_2"},
-	{true,	"SSU_BP_STATUS_3"},
-	{true,	"SSU_BP_STATUS_4"},
-	{true,	"SSU_BP_STATUS_5"},
-	{true,	"SSU_MAC_TX_PFC_IND"},
-
-	{true,	"MAC_SSU_RX_PFC_IND"},
-	{true,	"BTMP_AGEING_ST_B0"},
-	{true,	"BTMP_AGEING_ST_B1"},
-	{true,	"BTMP_AGEING_ST_B2"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-
-	{true,	"FULL_DROP_NUM"},
-	{true,	"PART_DROP_NUM"},
-	{true,	"PPP_KEY_DROP_NUM"},
-	{true,	"PPP_RLT_DROP_NUM"},
-	{true,	"LO_PRI_UNICAST_RLT_DROP_NUM"},
-	{true,	"HI_PRI_MULTICAST_RLT_DROP_NUM"},
-
-	{true,	"LO_PRI_MULTICAST_RLT_DROP_NUM"},
-	{true,	"NCSI_PACKET_CURR_BUFFER_CNT"},
-	{true,	"BTMP_AGEING_RLS_CNT_BANK0"},
-	{true,	"BTMP_AGEING_RLS_CNT_BANK1"},
-	{true,	"BTMP_AGEING_RLS_CNT_BANK2"},
-	{true,	"SSU_MB_RD_RLT_DROP_CNT"},
-
-	{true,	"SSU_PPP_MAC_KEY_NUM_L"},
-	{true,	"SSU_PPP_MAC_KEY_NUM_H"},
-	{true,	"SSU_PPP_HOST_KEY_NUM_L"},
-	{true,	"SSU_PPP_HOST_KEY_NUM_H"},
-	{true,	"PPP_SSU_MAC_RLT_NUM_L"},
-	{true,	"PPP_SSU_MAC_RLT_NUM_H"},
-
-	{true,	"PPP_SSU_HOST_RLT_NUM_L"},
-	{true,	"PPP_SSU_HOST_RLT_NUM_H"},
-	{true,	"NCSI_RX_PACKET_IN_CNT_L"},
-	{true,	"NCSI_RX_PACKET_IN_CNT_H"},
-	{true,	"NCSI_TX_PACKET_OUT_CNT_L"},
-	{true,	"NCSI_TX_PACKET_OUT_CNT_H"},
-
-	{true,	"SSU_KEY_DROP_NUM"},
-	{true,	"MB_UNCOPY_NUM"},
-	{true,	"RX_OQ_DROP_PKT_CNT"},
-	{true,	"TX_OQ_DROP_PKT_CNT"},
-	{true,	"BANK_UNBALANCE_DROP_CNT"},
-	{true,	"BANK_UNBALANCE_RX_DROP_CNT"},
-
-	{true,	"NIC_L2_ERR_DROP_PKT_CNT"},
-	{true,	"ROC_L2_ERR_DROP_PKT_CNT"},
-	{true,	"NIC_L2_ERR_DROP_PKT_CNT_RX"},
-	{true,	"ROC_L2_ERR_DROP_PKT_CNT_RX"},
-	{true,	"RX_OQ_GLB_DROP_PKT_CNT"},
-	{false, "Reserved"},
-
-	{true,	"LO_PRI_UNICAST_CUR_CNT"},
-	{true,	"HI_PRI_MULTICAST_CUR_CNT"},
-	{true,	"LO_PRI_MULTICAST_CUR_CNT"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
-	{true,	"prt_id"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_0"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_1"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_2"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_3"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_4"},
-
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_5"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_6"},
-	{true,	"PACKET_TC_CURR_BUFFER_CNT_7"},
-	{true,	"PACKET_CURR_BUFFER_CNT"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-
-	{true,	"RX_PACKET_IN_CNT_L"},
-	{true,	"RX_PACKET_IN_CNT_H"},
-	{true,	"RX_PACKET_OUT_CNT_L"},
-	{true,	"RX_PACKET_OUT_CNT_H"},
-	{true,	"TX_PACKET_IN_CNT_L"},
-	{true,	"TX_PACKET_IN_CNT_H"},
-
-	{true,	"TX_PACKET_OUT_CNT_L"},
-	{true,	"TX_PACKET_OUT_CNT_H"},
-	{true,	"ROC_RX_PACKET_IN_CNT_L"},
-	{true,	"ROC_RX_PACKET_IN_CNT_H"},
-	{true,	"ROC_TX_PACKET_OUT_CNT_L"},
-	{true,	"ROC_TX_PACKET_OUT_CNT_H"},
-
-	{true,	"RX_PACKET_TC_IN_CNT_0_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_0_H"},
-	{true,	"RX_PACKET_TC_IN_CNT_1_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_1_H"},
-	{true,	"RX_PACKET_TC_IN_CNT_2_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_2_H"},
-
-	{true,	"RX_PACKET_TC_IN_CNT_3_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_3_H"},
-	{true,	"RX_PACKET_TC_IN_CNT_4_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_4_H"},
-	{true,	"RX_PACKET_TC_IN_CNT_5_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_5_H"},
-
-	{true,	"RX_PACKET_TC_IN_CNT_6_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_6_H"},
-	{true,	"RX_PACKET_TC_IN_CNT_7_L"},
-	{true,	"RX_PACKET_TC_IN_CNT_7_H"},
-	{true,	"RX_PACKET_TC_OUT_CNT_0_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_0_H"},
-
-	{true,	"RX_PACKET_TC_OUT_CNT_1_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_1_H"},
-	{true,	"RX_PACKET_TC_OUT_CNT_2_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_2_H"},
-	{true,	"RX_PACKET_TC_OUT_CNT_3_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_3_H"},
-
-	{true,	"RX_PACKET_TC_OUT_CNT_4_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_4_H"},
-	{true,	"RX_PACKET_TC_OUT_CNT_5_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_5_H"},
-	{true,	"RX_PACKET_TC_OUT_CNT_6_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_6_H"},
-
-	{true,	"RX_PACKET_TC_OUT_CNT_7_L"},
-	{true,	"RX_PACKET_TC_OUT_CNT_7_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_0_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_0_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_1_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_1_H"},
-
-	{true,	"TX_PACKET_TC_IN_CNT_2_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_2_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_3_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_3_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_4_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_4_H"},
-
-	{true,	"TX_PACKET_TC_IN_CNT_5_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_5_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_6_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_6_H"},
-	{true,	"TX_PACKET_TC_IN_CNT_7_L"},
-	{true,	"TX_PACKET_TC_IN_CNT_7_H"},
-
-	{true,	"TX_PACKET_TC_OUT_CNT_0_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_0_H"},
-	{true,	"TX_PACKET_TC_OUT_CNT_1_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_1_H"},
-	{true,	"TX_PACKET_TC_OUT_CNT_2_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_2_H"},
-
-	{true,	"TX_PACKET_TC_OUT_CNT_3_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_3_H"},
-	{true,	"TX_PACKET_TC_OUT_CNT_4_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_4_H"},
-	{true,	"TX_PACKET_TC_OUT_CNT_5_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_5_H"},
-
-	{true,	"TX_PACKET_TC_OUT_CNT_6_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_6_H"},
-	{true,	"TX_PACKET_TC_OUT_CNT_7_L"},
-	{true,	"TX_PACKET_TC_OUT_CNT_7_H"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
-	{true,	"OQ_INDEX"},
-	{true,	"QUEUE_CNT"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
-	{true,	"prt_id"},
-	{true,	"IGU_RX_ERR_PKT"},
-	{true,	"IGU_RX_NO_SOF_PKT"},
-	{true,	"EGU_TX_1588_SHORT_PKT"},
-	{true,	"EGU_TX_1588_PKT"},
-	{true,	"EGU_TX_ERR_PKT"},
-
-	{true,	"IGU_RX_OUT_L2_PKT"},
-	{true,	"IGU_RX_OUT_L3_PKT"},
-	{true,	"IGU_RX_OUT_L4_PKT"},
-	{true,	"IGU_RX_IN_L2_PKT"},
-	{true,	"IGU_RX_IN_L3_PKT"},
-	{true,	"IGU_RX_IN_L4_PKT"},
-
-	{true,	"IGU_RX_EL3E_PKT"},
-	{true,	"IGU_RX_EL4E_PKT"},
-	{true,	"IGU_RX_L3E_PKT"},
-	{true,	"IGU_RX_L4E_PKT"},
-	{true,	"IGU_RX_ROCEE_PKT"},
-	{true,	"IGU_RX_OUT_UDP0_PKT"},
-
-	{true,	"IGU_RX_IN_UDP0_PKT"},
-	{true,	"IGU_MC_CAR_DROP_PKT_L"},
-	{true,	"IGU_MC_CAR_DROP_PKT_H"},
-	{true,	"IGU_BC_CAR_DROP_PKT_L"},
-	{true,	"IGU_BC_CAR_DROP_PKT_H"},
-	{false, "Reserved"},
-
-	{true,	"IGU_RX_OVERSIZE_PKT_L"},
-	{true,	"IGU_RX_OVERSIZE_PKT_H"},
-	{true,	"IGU_RX_UNDERSIZE_PKT_L"},
-	{true,	"IGU_RX_UNDERSIZE_PKT_H"},
-	{true,	"IGU_RX_OUT_ALL_PKT_L"},
-	{true,	"IGU_RX_OUT_ALL_PKT_H"},
-
-	{true,	"IGU_TX_OUT_ALL_PKT_L"},
-	{true,	"IGU_TX_OUT_ALL_PKT_H"},
-	{true,	"IGU_RX_UNI_PKT_L"},
-	{true,	"IGU_RX_UNI_PKT_H"},
-	{true,	"IGU_RX_MULTI_PKT_L"},
-	{true,	"IGU_RX_MULTI_PKT_H"},
-
-	{true,	"IGU_RX_BROAD_PKT_L"},
-	{true,	"IGU_RX_BROAD_PKT_H"},
-	{true,	"EGU_TX_OUT_ALL_PKT_L"},
-	{true,	"EGU_TX_OUT_ALL_PKT_H"},
-	{true,	"EGU_TX_UNI_PKT_L"},
-	{true,	"EGU_TX_UNI_PKT_H"},
-
-	{true,	"EGU_TX_MULTI_PKT_L"},
-	{true,	"EGU_TX_MULTI_PKT_H"},
-	{true,	"EGU_TX_BROAD_PKT_L"},
-	{true,	"EGU_TX_BROAD_PKT_H"},
-	{true,	"IGU_TX_KEY_NUM_L"},
-	{true,	"IGU_TX_KEY_NUM_H"},
-
-	{true,	"IGU_RX_NON_TUN_PKT_L"},
-	{true,	"IGU_RX_NON_TUN_PKT_H"},
-	{true,	"IGU_RX_TUN_PKT_L"},
-	{true,	"IGU_RX_TUN_PKT_H"},
-	{false,	"Reserved"},
-	{false,	"Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
-	{true, "tc_queue_num"},
-	{true, "FSM_DFX_ST0"},
-	{true, "FSM_DFX_ST1"},
-	{true, "RPU_RX_PKT_DROP_CNT"},
-	{true, "BUF_WAIT_TIMEOUT"},
-	{true, "BUF_WAIT_TIMEOUT_QID"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
-	{false, "Reserved"},
-	{true,	"FIFO_DFX_ST0"},
-	{true,	"FIFO_DFX_ST1"},
-	{true,	"FIFO_DFX_ST2"},
-	{true,	"FIFO_DFX_ST3"},
-	{true,	"FIFO_DFX_ST4"},
-
-	{true,	"FIFO_DFX_ST5"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
-	{false, "Reserved"},
-	{true,	"NCSI_EGU_TX_FIFO_STS"},
-	{true,	"NCSI_PAUSE_STATUS"},
-	{true,	"NCSI_RX_CTRL_DMAC_ERR_CNT"},
-	{true,	"NCSI_RX_CTRL_SMAC_ERR_CNT"},
-	{true,	"NCSI_RX_CTRL_CKS_ERR_CNT"},
-
-	{true,	"NCSI_RX_CTRL_PKT_CNT"},
-	{true,	"NCSI_RX_PT_DMAC_ERR_CNT"},
-	{true,	"NCSI_RX_PT_SMAC_ERR_CNT"},
-	{true,	"NCSI_RX_PT_PKT_CNT"},
-	{true,	"NCSI_RX_FCS_ERR_CNT"},
-	{true,	"NCSI_TX_CTRL_DMAC_ERR_CNT"},
-
-	{true,	"NCSI_TX_CTRL_SMAC_ERR_CNT"},
-	{true,	"NCSI_TX_CTRL_PKT_CNT"},
-	{true,	"NCSI_TX_PT_DMAC_ERR_CNT"},
-	{true,	"NCSI_TX_PT_SMAC_ERR_CNT"},
-	{true,	"NCSI_TX_PT_PKT_CNT"},
-	{true,	"NCSI_TX_PT_PKT_TRUNC_CNT"},
-
-	{true,	"NCSI_TX_PT_PKT_ERR_CNT"},
-	{true,	"NCSI_TX_CTRL_PKT_ERR_CNT"},
-	{true,	"NCSI_RX_CTRL_PKT_TRUNC_CNT"},
-	{true,	"NCSI_RX_CTRL_PKT_CFLIT_CNT"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-
-	{true,	"NCSI_MAC_RX_OCTETS_OK"},
-	{true,	"NCSI_MAC_RX_OCTETS_BAD"},
-	{true,	"NCSI_MAC_RX_UC_PKTS"},
-	{true,	"NCSI_MAC_RX_MC_PKTS"},
-	{true,	"NCSI_MAC_RX_BC_PKTS"},
-	{true,	"NCSI_MAC_RX_PKTS_64OCTETS"},
-
-	{true,	"NCSI_MAC_RX_PKTS_65TO127OCTETS"},
-	{true,	"NCSI_MAC_RX_PKTS_128TO255OCTETS"},
-	{true,	"NCSI_MAC_RX_PKTS_255TO511OCTETS"},
-	{true,	"NCSI_MAC_RX_PKTS_512TO1023OCTETS"},
-	{true,	"NCSI_MAC_RX_PKTS_1024TO1518OCTETS"},
-	{true,	"NCSI_MAC_RX_PKTS_1519TOMAXOCTETS"},
-
-	{true,	"NCSI_MAC_RX_FCS_ERRORS"},
-	{true,	"NCSI_MAC_RX_LONG_ERRORS"},
-	{true,	"NCSI_MAC_RX_JABBER_ERRORS"},
-	{true,	"NCSI_MAC_RX_RUNT_ERR_CNT"},
-	{true,	"NCSI_MAC_RX_SHORT_ERR_CNT"},
-	{true,	"NCSI_MAC_RX_FILT_PKT_CNT"},
-
-	{true,	"NCSI_MAC_RX_OCTETS_TOTAL_FILT"},
-	{true,	"NCSI_MAC_TX_OCTETS_OK"},
-	{true,	"NCSI_MAC_TX_OCTETS_BAD"},
-	{true,	"NCSI_MAC_TX_UC_PKTS"},
-	{true,	"NCSI_MAC_TX_MC_PKTS"},
-	{true,	"NCSI_MAC_TX_BC_PKTS"},
-
-	{true,	"NCSI_MAC_TX_PKTS_64OCTETS"},
-	{true,	"NCSI_MAC_TX_PKTS_65TO127OCTETS"},
-	{true,	"NCSI_MAC_TX_PKTS_128TO255OCTETS"},
-	{true,	"NCSI_MAC_TX_PKTS_256TO511OCTETS"},
-	{true,	"NCSI_MAC_TX_PKTS_512TO1023OCTETS"},
-	{true,	"NCSI_MAC_TX_PKTS_1024TO1518OCTETS"},
-
-	{true,	"NCSI_MAC_TX_PKTS_1519TOMAXOCTETS"},
-	{true,	"NCSI_MAC_TX_UNDERRUN"},
-	{true,	"NCSI_MAC_TX_CRC_ERROR"},
-	{true,	"NCSI_MAC_TX_PAUSE_FRAMES"},
-	{true,	"NCSI_MAC_RX_PAD_PKTS"},
-	{true,	"NCSI_MAC_RX_PAUSE_FRAMES"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
-	{false, "Reserved"},
-	{true,	"LGE_IGU_AFIFO_DFX_0"},
-	{true,	"LGE_IGU_AFIFO_DFX_1"},
-	{true,	"LGE_IGU_AFIFO_DFX_2"},
-	{true,	"LGE_IGU_AFIFO_DFX_3"},
-	{true,	"LGE_IGU_AFIFO_DFX_4"},
-
-	{true,	"LGE_IGU_AFIFO_DFX_5"},
-	{true,	"LGE_IGU_AFIFO_DFX_6"},
-	{true,	"LGE_IGU_AFIFO_DFX_7"},
-	{true,	"LGE_EGU_AFIFO_DFX_0"},
-	{true,	"LGE_EGU_AFIFO_DFX_1"},
-	{true,	"LGE_EGU_AFIFO_DFX_2"},
-
-	{true,	"LGE_EGU_AFIFO_DFX_3"},
-	{true,	"LGE_EGU_AFIFO_DFX_4"},
-	{true,	"LGE_EGU_AFIFO_DFX_5"},
-	{true,	"LGE_EGU_AFIFO_DFX_6"},
-	{true,	"LGE_EGU_AFIFO_DFX_7"},
-	{true,	"CGE_IGU_AFIFO_DFX_0"},
-
-	{true,	"CGE_IGU_AFIFO_DFX_1"},
-	{true,	"CGE_EGU_AFIFO_DFX_0"},
-	{true,	"CGE_EGU_AFIFO_DFX_1"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
-	{false, "Reserved"},
-	{true,	"DROP_FROM_PRT_PKT_CNT"},
-	{true,	"DROP_FROM_HOST_PKT_CNT"},
-	{true,	"DROP_TX_VLAN_PROC_CNT"},
-	{true,	"DROP_MNG_CNT"},
-	{true,	"DROP_FD_CNT"},
-
-	{true,	"DROP_NO_DST_CNT"},
-	{true,	"DROP_MC_MBID_FULL_CNT"},
-	{true,	"DROP_SC_FILTERED"},
-	{true,	"PPP_MC_DROP_PKT_CNT"},
-	{true,	"DROP_PT_CNT"},
-	{true,	"DROP_MAC_ANTI_SPOOF_CNT"},
-
-	{true,	"DROP_IG_VFV_CNT"},
-	{true,	"DROP_IG_PRTV_CNT"},
-	{true,	"DROP_CNM_PFC_PAUSE_CNT"},
-	{true,	"DROP_TORUS_TC_CNT"},
-	{true,	"DROP_TORUS_LPBK_CNT"},
-	{true,	"PPP_HFS_STS"},
-
-	{true,	"PPP_MC_RSLT_STS"},
-	{true,	"PPP_P3U_STS"},
-	{true,	"PPP_RSLT_DESCR_STS"},
-	{true,	"PPP_UMV_STS_0"},
-	{true,	"PPP_UMV_STS_1"},
-	{true,	"PPP_VFV_STS"},
-
-	{true,	"PPP_GRO_KEY_CNT"},
-	{true,	"PPP_GRO_INFO_CNT"},
-	{true,	"PPP_GRO_DROP_CNT"},
-	{true,	"PPP_GRO_OUT_CNT"},
-	{true,	"PPP_GRO_KEY_MATCH_DATA_CNT"},
-	{true,	"PPP_GRO_KEY_MATCH_TCAM_CNT"},
-
-	{true,	"PPP_GRO_INFO_MATCH_CNT"},
-	{true,	"PPP_GRO_FREE_ENTRY_CNT"},
-	{true,	"PPP_GRO_INNER_DFX_SIGNAL"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-
-	{true,	"GET_RX_PKT_CNT_L"},
-	{true,	"GET_RX_PKT_CNT_H"},
-	{true,	"GET_TX_PKT_CNT_L"},
-	{true,	"GET_TX_PKT_CNT_H"},
-	{true,	"SEND_UC_PRT2HOST_PKT_CNT_L"},
-	{true,	"SEND_UC_PRT2HOST_PKT_CNT_H"},
-
-	{true,	"SEND_UC_PRT2PRT_PKT_CNT_L"},
-	{true,	"SEND_UC_PRT2PRT_PKT_CNT_H"},
-	{true,	"SEND_UC_HOST2HOST_PKT_CNT_L"},
-	{true,	"SEND_UC_HOST2HOST_PKT_CNT_H"},
-	{true,	"SEND_UC_HOST2PRT_PKT_CNT_L"},
-	{true,	"SEND_UC_HOST2PRT_PKT_CNT_H"},
-
-	{true,	"SEND_MC_FROM_PRT_CNT_L"},
-	{true,	"SEND_MC_FROM_PRT_CNT_H"},
-	{true,	"SEND_MC_FROM_HOST_CNT_L"},
-	{true,	"SEND_MC_FROM_HOST_CNT_H"},
-	{true,	"SSU_MC_RD_CNT_L"},
-	{true,	"SSU_MC_RD_CNT_H"},
-
-	{true,	"SSU_MC_DROP_CNT_L"},
-	{true,	"SSU_MC_DROP_CNT_H"},
-	{true,	"SSU_MC_RD_PKT_CNT_L"},
-	{true,	"SSU_MC_RD_PKT_CNT_H"},
-	{true,	"PPP_MC_2HOST_PKT_CNT_L"},
-	{true,	"PPP_MC_2HOST_PKT_CNT_H"},
-
-	{true,	"PPP_MC_2PRT_PKT_CNT_L"},
-	{true,	"PPP_MC_2PRT_PKT_CNT_H"},
-	{true,	"NTSNOS_PKT_CNT_L"},
-	{true,	"NTSNOS_PKT_CNT_H"},
-	{true,	"NTUP_PKT_CNT_L"},
-	{true,	"NTUP_PKT_CNT_H"},
-
-	{true,	"NTLCL_PKT_CNT_L"},
-	{true,	"NTLCL_PKT_CNT_H"},
-	{true,	"NTTGT_PKT_CNT_L"},
-	{true,	"NTTGT_PKT_CNT_H"},
-	{true,	"RTNS_PKT_CNT_L"},
-	{true,	"RTNS_PKT_CNT_H"},
-
-	{true,	"RTLPBK_PKT_CNT_L"},
-	{true,	"RTLPBK_PKT_CNT_H"},
-	{true,	"NR_PKT_CNT_L"},
-	{true,	"NR_PKT_CNT_H"},
-	{true,	"RR_PKT_CNT_L"},
-	{true,	"RR_PKT_CNT_H"},
-
-	{true,	"MNG_TBL_HIT_CNT_L"},
-	{true,	"MNG_TBL_HIT_CNT_H"},
-	{true,	"FD_TBL_HIT_CNT_L"},
-	{true,	"FD_TBL_HIT_CNT_H"},
-	{true,	"FD_LKUP_CNT_L"},
-	{true,	"FD_LKUP_CNT_H"},
-
-	{true,	"BC_HIT_CNT_L"},
-	{true,	"BC_HIT_CNT_H"},
-	{true,	"UM_TBL_UC_HIT_CNT_L"},
-	{true,	"UM_TBL_UC_HIT_CNT_H"},
-	{true,	"UM_TBL_MC_HIT_CNT_L"},
-	{true,	"UM_TBL_MC_HIT_CNT_H"},
-
-	{true,	"UM_TBL_VMDQ1_HIT_CNT_L"},
-	{true,	"UM_TBL_VMDQ1_HIT_CNT_H"},
-	{true,	"MTA_TBL_HIT_CNT_L"},
-	{true,	"MTA_TBL_HIT_CNT_H"},
-	{true,	"FWD_BONDING_HIT_CNT_L"},
-	{true,	"FWD_BONDING_HIT_CNT_H"},
-
-	{true,	"PROMIS_TBL_HIT_CNT_L"},
-	{true,	"PROMIS_TBL_HIT_CNT_H"},
-	{true,	"GET_TUNL_PKT_CNT_L"},
-	{true,	"GET_TUNL_PKT_CNT_H"},
-	{true,	"GET_BMC_PKT_CNT_L"},
-	{true,	"GET_BMC_PKT_CNT_H"},
-
-	{true,	"SEND_UC_PRT2BMC_PKT_CNT_L"},
-	{true,	"SEND_UC_PRT2BMC_PKT_CNT_H"},
-	{true,	"SEND_UC_HOST2BMC_PKT_CNT_L"},
-	{true,	"SEND_UC_HOST2BMC_PKT_CNT_H"},
-	{true,	"SEND_UC_BMC2HOST_PKT_CNT_L"},
-	{true,	"SEND_UC_BMC2HOST_PKT_CNT_H"},
-
-	{true,	"SEND_UC_BMC2PRT_PKT_CNT_L"},
-	{true,	"SEND_UC_BMC2PRT_PKT_CNT_H"},
-	{true,	"PPP_MC_2BMC_PKT_CNT_L"},
-	{true,	"PPP_MC_2BMC_PKT_CNT_H"},
-	{true,	"VLAN_MIRR_CNT_L"},
-	{true,	"VLAN_MIRR_CNT_H"},
-
-	{true,	"IG_MIRR_CNT_L"},
-	{true,	"IG_MIRR_CNT_H"},
-	{true,	"EG_MIRR_CNT_L"},
-	{true,	"EG_MIRR_CNT_H"},
-	{true,	"RX_DEFAULT_HOST_HIT_CNT_L"},
-	{true,	"RX_DEFAULT_HOST_HIT_CNT_H"},
-
-	{true,	"LAN_PAIR_CNT_L"},
-	{true,	"LAN_PAIR_CNT_H"},
-	{true,	"UM_TBL_MC_HIT_PKT_CNT_L"},
-	{true,	"UM_TBL_MC_HIT_PKT_CNT_H"},
-	{true,	"MTA_TBL_HIT_PKT_CNT_L"},
-	{true,	"MTA_TBL_HIT_PKT_CNT_H"},
-
-	{true,	"PROMIS_TBL_HIT_PKT_CNT_L"},
-	{true,	"PROMIS_TBL_HIT_PKT_CNT_H"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
-	{false, "Reserved"},
-	{true,	"FSM_DFX_ST0"},
-	{true,	"FSM_DFX_ST1"},
-	{true,	"FSM_DFX_ST2"},
-	{true,	"FIFO_DFX_ST0"},
-	{true,	"FIFO_DFX_ST1"},
-
-	{true,	"FIFO_DFX_ST2"},
-	{true,	"FIFO_DFX_ST3"},
-	{true,	"FIFO_DFX_ST4"},
-	{true,	"FIFO_DFX_ST5"},
-	{true,	"FIFO_DFX_ST6"},
-	{true,	"FIFO_DFX_ST7"},
-
-	{true,	"FIFO_DFX_ST8"},
-	{true,	"FIFO_DFX_ST9"},
-	{true,	"FIFO_DFX_ST10"},
-	{true,	"FIFO_DFX_ST11"},
-	{true,	"Q_CREDIT_VLD_0"},
-	{true,	"Q_CREDIT_VLD_1"},
-
-	{true,	"Q_CREDIT_VLD_2"},
-	{true,	"Q_CREDIT_VLD_3"},
-	{true,	"Q_CREDIT_VLD_4"},
-	{true,	"Q_CREDIT_VLD_5"},
-	{true,	"Q_CREDIT_VLD_6"},
-	{true,	"Q_CREDIT_VLD_7"},
-
-	{true,	"Q_CREDIT_VLD_8"},
-	{true,	"Q_CREDIT_VLD_9"},
-	{true,	"Q_CREDIT_VLD_10"},
-	{true,	"Q_CREDIT_VLD_11"},
-	{true,	"Q_CREDIT_VLD_12"},
-	{true,	"Q_CREDIT_VLD_13"},
-
-	{true,	"Q_CREDIT_VLD_14"},
-	{true,	"Q_CREDIT_VLD_15"},
-	{true,	"Q_CREDIT_VLD_16"},
-	{true,	"Q_CREDIT_VLD_17"},
-	{true,	"Q_CREDIT_VLD_18"},
-	{true,	"Q_CREDIT_VLD_19"},
-
-	{true,	"Q_CREDIT_VLD_20"},
-	{true,	"Q_CREDIT_VLD_21"},
-	{true,	"Q_CREDIT_VLD_22"},
-	{true,	"Q_CREDIT_VLD_23"},
-	{true,	"Q_CREDIT_VLD_24"},
-	{true,	"Q_CREDIT_VLD_25"},
-
-	{true,	"Q_CREDIT_VLD_26"},
-	{true,	"Q_CREDIT_VLD_27"},
-	{true,	"Q_CREDIT_VLD_28"},
-	{true,	"Q_CREDIT_VLD_29"},
-	{true,	"Q_CREDIT_VLD_30"},
-	{true,	"Q_CREDIT_VLD_31"},
-
-	{true,	"GRO_BD_SERR_CNT"},
-	{true,	"GRO_CONTEXT_SERR_CNT"},
-	{true,	"RX_STASH_CFG_SERR_CNT"},
-	{true,	"AXI_RD_FBD_SERR_CNT"},
-	{true,	"GRO_BD_MERR_CNT"},
-	{true,	"GRO_CONTEXT_MERR_CNT"},
-
-	{true,	"RX_STASH_CFG_MERR_CNT"},
-	{true,	"AXI_RD_FBD_MERR_CNT"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-	{false, "Reserved"},
-};
-
-static const struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
-	{true, "q_num"},
-	{true, "RCB_CFG_RX_RING_TAIL"},
-	{true, "RCB_CFG_RX_RING_HEAD"},
-	{true, "RCB_CFG_RX_RING_FBDNUM"},
-	{true, "RCB_CFG_RX_RING_OFFSET"},
-	{true, "RCB_CFG_RX_RING_FBDOFFSET"},
-
-	{true, "RCB_CFG_RX_RING_PKTNUM_RECORD"},
-	{true, "RCB_CFG_TX_RING_TAIL"},
-	{true, "RCB_CFG_TX_RING_HEAD"},
-	{true, "RCB_CFG_TX_RING_FBDNUM"},
-	{true, "RCB_CFG_TX_RING_OFFSET"},
-	{true, "RCB_CFG_TX_RING_EBDNUM"},
-};
-
 #define HCLGE_DBG_INFO_LEN			256
 #define HCLGE_DBG_VLAN_FLTR_INFO_LEN		256
 #define HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN		512
@@ -771,4 +131,7 @@ struct hclge_dbg_vlan_cfg {
 	u8 pri_only2;
 };
 
+int hclge_dbg_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc_src,
+		       int index, int bd_num, enum hclge_opcode_type cmd);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c
index 9a939c0b217f..a1571c108678 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c
@@ -5,6 +5,34 @@
 
 #include "hclge_devlink.h"
 
+static int hclge_devlink_scc_info_get(struct devlink *devlink,
+				      struct devlink_info_req *req)
+{
+	struct hclge_devlink_priv *priv = devlink_priv(devlink);
+	char scc_version[HCLGE_DEVLINK_FW_SCC_LEN];
+	struct hclge_dev *hdev = priv->hdev;
+	u32 scc_version_tmp;
+	int ret;
+
+	ret = hclge_query_scc_version(hdev, &scc_version_tmp);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get scc version, ret = %d\n", ret);
+		return ret;
+	}
+
+	snprintf(scc_version, sizeof(scc_version), "%lu.%lu.%lu.%lu",
+		 hnae3_get_field(scc_version_tmp, HNAE3_SCC_VERSION_BYTE3_MASK,
+				 HNAE3_FW_VERSION_BYTE3_SHIFT),
+		 hnae3_get_field(scc_version_tmp, HNAE3_SCC_VERSION_BYTE2_MASK,
+				 HNAE3_FW_VERSION_BYTE2_SHIFT),
+		 hnae3_get_field(scc_version_tmp, HNAE3_SCC_VERSION_BYTE1_MASK,
+				 HNAE3_FW_VERSION_BYTE1_SHIFT),
+		 hnae3_get_field(scc_version_tmp, HNAE3_SCC_VERSION_BYTE0_MASK,
+				 HNAE3_FW_VERSION_BYTE0_SHIFT));
+	return devlink_info_version_running_put(req, "fw.scc", scc_version);
+}
+
 static int hclge_devlink_info_get(struct devlink *devlink,
 				  struct devlink_info_req *req,
 				  struct netlink_ext_ack *extack)
@@ -13,6 +41,7 @@ static int hclge_devlink_info_get(struct devlink *devlink,
 	struct hclge_devlink_priv *priv = devlink_priv(devlink);
 	char version_str[HCLGE_DEVLINK_FW_STRING_LEN];
 	struct hclge_dev *hdev = priv->hdev;
+	int ret;
 
 	snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu",
 		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK,
@@ -24,9 +53,18 @@ static int hclge_devlink_info_get(struct devlink *devlink,
 		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK,
 				 HNAE3_FW_VERSION_BYTE0_SHIFT));
 
-	return devlink_info_version_running_put(req,
-						DEVLINK_INFO_VERSION_GENERIC_FW,
-						version_str);
+	ret = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW,
+					       version_str);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "failed to set running version of fw\n");
+		return ret;
+	}
+
+	if (hdev->pdev->revision > HNAE3_DEVICE_VERSION_V2)
+		ret = hclge_devlink_scc_info_get(devlink, req);
+
+	return ret;
 }
 
 static int hclge_devlink_reload_down(struct devlink *devlink, bool netns_change,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h
index 918be04507a5..148effa5ea89 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.h
@@ -6,6 +6,8 @@
 
 #include "hclge_main.h"
 
+#define	HCLGE_DEVLINK_FW_SCC_LEN	32
+
 struct hclge_devlink_priv {
 	struct hclge_dev *hdev;
 };
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index d63e114f93d0..e132c2f09560 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -1198,6 +1198,425 @@ static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
 	}
 };
 
+static const struct hclge_mod_reg_info hclge_ssu_reg_0_info[] = {
+	{
+		.reg_name = "SSU_BP_STATUS_0~5",
+		.reg_offset_group = { 5, 6, 7, 8, 9, 10},
+		.group_size = 6
+	}, {
+		.reg_name = "LO_PRI_UNICAST_CUR_CNT",
+		.reg_offset_group = {54},
+		.group_size = 1
+	}, {
+		.reg_name = "HI/LO_PRI_MULTICAST_CUR_CNT",
+		.reg_offset_group = {55, 56},
+		.group_size = 2
+	}, {
+		.reg_name = "SSU_MB_RD_RLT_DROP_CNT",
+		.reg_offset_group = {29},
+		.group_size = 1
+	}, {
+		.reg_name = "SSU_PPP_MAC_KEY_NUM",
+		.reg_offset_group = {31, 30},
+		.group_size = 2
+	}, {
+		.reg_name = "SSU_PPP_HOST_KEY_NUM",
+		.reg_offset_group = {33, 32},
+		.group_size = 2
+	}, {
+		.reg_name = "PPP_SSU_MAC/HOST_RLT_NUM",
+		.reg_offset_group = {35, 34, 37, 36},
+		.group_size = 4
+	}, {
+		.reg_name = "FULL/PART_DROP_NUM",
+		.reg_offset_group = {18, 19},
+		.group_size = 2
+	}, {
+		.reg_name = "PPP_KEY/RLT_DROP_NUM",
+		.reg_offset_group = {20, 21},
+		.group_size = 2
+	}, {
+		.reg_name = "NIC/ROC_L2_ERR_DROP_PKT_CNT",
+		.reg_offset_group = {48, 49},
+		.group_size = 2
+	}, {
+		.reg_name = "NIC/ROC_L2_ERR_DROP_PKT_CNT_RX",
+		.reg_offset_group = {50, 51},
+		.group_size = 2
+	},
+};
+
+static const struct hclge_mod_reg_info hclge_ssu_reg_1_info[] = {
+	{
+		.reg_name = "RX_PACKET_IN/OUT_CNT",
+		.reg_offset_group = {13, 12, 15, 14},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_IN/OUT_CNT",
+		.reg_offset_group = {17, 16, 19, 18},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC0_IN/OUT_CNT",
+		.reg_offset_group = {25, 24, 41, 40},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC1_IN/OUT_CNT",
+		.reg_offset_group = {27, 26, 43, 42},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC2_IN/OUT_CNT",
+		.reg_offset_group = {29, 28, 45, 44},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC3_IN/OUT_CNT",
+		.reg_offset_group = {31, 30, 47, 46},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC4_IN/OUT_CNT",
+		.reg_offset_group = {33, 32, 49, 48},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC5_IN/OUT_CNT",
+		.reg_offset_group = {35, 34, 51, 50},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC6_IN/OUT_CNT",
+		.reg_offset_group = {37, 36, 53, 52},
+		.group_size = 4
+	}, {
+		.reg_name = "RX_PACKET_TC7_IN/OUT_CNT",
+		.reg_offset_group = {39, 38, 55, 54},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC0_IN/OUT_CNT",
+		.reg_offset_group = {57, 56, 73, 72},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC1_IN/OUT_CNT",
+		.reg_offset_group = {59, 58, 75, 74},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC2_IN/OUT_CNT",
+		.reg_offset_group = {61, 60, 77, 76},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC3_IN/OUT_CNT",
+		.reg_offset_group = {63, 62, 79, 78},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC4_IN/OUT_CNT",
+		.reg_offset_group = {65, 64, 81, 80},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC5_IN/OUT_CNT",
+		.reg_offset_group = {67, 66, 83, 82},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC6_IN/OUT_CNT",
+		.reg_offset_group = {69, 68, 85, 84},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PACKET_TC7_IN/OUT_CNT",
+		.reg_offset_group = {71, 70, 87, 86},
+		.group_size = 4
+	}, {
+		.reg_name = "PACKET_TC0~3_CURR_BUFFER_CNT",
+		.reg_offset_group = {1, 2, 3, 4},
+		.group_size = 4
+	}, {
+		.reg_name = "PACKET_TC4~7_CURR_BUFFER_CNT",
+		.reg_offset_group = {5, 6, 7, 8},
+		.group_size = 4
+	}, {
+		.reg_name = "ROC_RX_PACKET_IN_CNT",
+		.reg_offset_group = {21, 20},
+		.group_size = 2
+	}, {
+		.reg_name = "ROC_TX_PACKET_OUT_CNT",
+		.reg_offset_group = {23, 22},
+		.group_size = 2
+	}
+};
+
+static const struct hclge_mod_reg_info hclge_rpu_reg_0_info[] = {
+	{
+		.reg_name = "RPU_FSM_DFX_ST0/ST1_TNL",
+		.has_suffix = true,
+		.reg_offset_group = {1, 2},
+		.group_size = 2
+	}, {
+		.reg_name = "RPU_RX_PKT_DROP_CNT_TNL",
+		.has_suffix = true,
+		.reg_offset_group = {3},
+		.group_size = 1
+	}
+};
+
+static const struct hclge_mod_reg_info hclge_rpu_reg_1_info[] = {
+	{
+		.reg_name = "FIFO_DFX_ST0_1_2_4",
+		.reg_offset_group = {1, 2, 3, 5},
+		.group_size = 4
+	}
+};
+
+static const struct hclge_mod_reg_info hclge_igu_egu_reg_info[] = {
+	{
+		.reg_name = "IGU_RX_ERR_PKT",
+		.reg_offset_group = {1},
+		.group_size = 1
+	}, {
+		.reg_name = "IGU_RX_OUT_ALL_PKT",
+		.reg_offset_group = {29, 28},
+		.group_size = 2
+	}, {
+		.reg_name = "EGU_TX_OUT_ALL_PKT",
+		.reg_offset_group = {39, 38},
+		.group_size = 2
+	}, {
+		.reg_name = "EGU_TX_ERR_PKT",
+		.reg_offset_group = {5},
+		.group_size = 1
+	}
+};
+
+static const struct hclge_mod_reg_info hclge_gen_reg_info_tnl[] = {
+	{
+		.reg_name = "SSU2RPU_TNL_WR_PKT_CNT_TNL",
+		.has_suffix = true,
+		.reg_offset_group = {1},
+		.group_size = 1
+	}, {
+		.reg_name = "RPU2HST_TNL_WR_PKT_CNT_TNL",
+		.has_suffix = true,
+		.reg_offset_group = {12},
+		.group_size = 1
+	}
+};
+
+static const struct hclge_mod_reg_info hclge_gen_reg_info[] = {
+	{
+		.reg_name = "SSU_OVERSIZE_DROP_CNT",
+		.reg_offset_group = {12},
+		.group_size = 1
+	}, {
+		.reg_name = "ROCE_RX_BYPASS_5NS_DROP_NUM",
+		.reg_offset_group = {13},
+		.group_size = 1
+	}, {
+		.reg_name = "RX_PKT_IN/OUT_ERR_CNT",
+		.reg_offset_group = {15, 14, 19, 18},
+		.group_size = 4
+	}, {
+		.reg_name = "TX_PKT_IN/OUT_ERR_CNT",
+		.reg_offset_group = {17, 16, 21, 20},
+		.group_size = 4
+	}, {
+		.reg_name = "ETS_TC_READY",
+		.reg_offset_group = {22},
+		.group_size = 1
+	}, {
+		.reg_name = "MIB_TX/RX_BAD_PKTS",
+		.reg_offset_group = {19, 18, 29, 28},
+		.group_size = 4
+	}, {
+		.reg_name = "MIB_TX/RX_GOOD_PKTS",
+		.reg_offset_group = {21, 20, 31, 30},
+		.group_size = 4
+	}, {
+		.reg_name = "MIB_TX/RX_TOTAL_PKTS",
+		.reg_offset_group = {23, 22, 33, 32},
+		.group_size = 4
+	}, {
+		.reg_name = "MIB_TX/RX_PAUSE_PKTS",
+		.reg_offset_group = {25, 24, 35, 34},
+		.group_size = 4
+	}, {
+		.reg_name = "MIB_TX_ERR_ALL_PKTS",
+		.reg_offset_group = {27, 26},
+		.group_size = 2
+	}, {
+		.reg_name = "MIB_RX_FCS_ERR_PKTS",
+		.reg_offset_group = {37, 36},
+		.group_size = 2
+	}, {
+		.reg_name = "IGU_EGU_AUTO_GATE_EN",
+		.reg_offset_group = {42},
+		.group_size = 1
+	}, {
+		.reg_name = "IGU_EGU_INT_SRC",
+		.reg_offset_group = {43},
+		.group_size = 1
+	}, {
+		.reg_name = "EGU_READY_NUM_CFG",
+		.reg_offset_group = {44},
+		.group_size = 1
+	}, {
+		.reg_name = "IGU_EGU_TNL_DFX",
+		.reg_offset_group = {45},
+		.group_size = 1
+	}, {
+		.reg_name = "TX_TNL_NOTE_PKT",
+		.reg_offset_group = {46},
+		.group_size = 1
+	}
+};
+
+static const struct hclge_mod_reg_common_msg hclge_ssu_reg_common_msg[] = {
+	{
+		.cmd = HCLGE_OPC_DFX_SSU_REG_0,
+		.result_regs = hclge_ssu_reg_0_info,
+		.bd_num = HCLGE_BD_NUM_SSU_REG_0,
+		.result_regs_size = ARRAY_SIZE(hclge_ssu_reg_0_info)
+	}, {
+		.cmd = HCLGE_OPC_DFX_SSU_REG_1,
+		.result_regs = hclge_ssu_reg_1_info,
+		.bd_num = HCLGE_BD_NUM_SSU_REG_1,
+		.result_regs_size = ARRAY_SIZE(hclge_ssu_reg_1_info)
+	}, {
+		.cmd = HCLGE_OPC_DFX_RPU_REG_0,
+		.result_regs = hclge_rpu_reg_0_info,
+		.bd_num = HCLGE_BD_NUM_RPU_REG_0,
+		.result_regs_size = ARRAY_SIZE(hclge_rpu_reg_0_info),
+		.need_para = true
+	}, {
+		.cmd = HCLGE_OPC_DFX_RPU_REG_1,
+		.result_regs = hclge_rpu_reg_1_info,
+		.bd_num = HCLGE_BD_NUM_RPU_REG_1,
+		.result_regs_size = ARRAY_SIZE(hclge_rpu_reg_1_info)
+	}, {
+		.cmd = HCLGE_OPC_DFX_IGU_EGU_REG,
+		.result_regs = hclge_igu_egu_reg_info,
+		.bd_num = HCLGE_BD_NUM_IGU_EGU_REG,
+		.result_regs_size = ARRAY_SIZE(hclge_igu_egu_reg_info)
+	}, {
+		.cmd = HCLGE_OPC_DFX_GEN_REG,
+		.result_regs = hclge_gen_reg_info_tnl,
+		.bd_num = HCLGE_BD_NUM_GEN_REG,
+		.result_regs_size = ARRAY_SIZE(hclge_gen_reg_info_tnl),
+		.need_para = true
+	}, {
+		.cmd = HCLGE_OPC_DFX_GEN_REG,
+		.result_regs = hclge_gen_reg_info,
+		.bd_num = HCLGE_BD_NUM_GEN_REG,
+		.result_regs_size = ARRAY_SIZE(hclge_gen_reg_info)
+	}
+};
+
+static int
+hclge_print_mod_reg_info(struct device *dev, struct hclge_desc *desc,
+			 const struct hclge_mod_reg_info *reg_info, int size)
+{
+	int i, j, pos, actual_len;
+	u8 offset, bd_idx, index;
+	char *buf;
+
+	buf = kzalloc(HCLGE_MOD_REG_INFO_LEN_MAX, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		actual_len = strlen(reg_info[i].reg_name) +
+			     HCLGE_MOD_REG_EXTRA_LEN +
+			     HCLGE_MOD_REG_VALUE_LEN * reg_info[i].group_size;
+		if (actual_len > HCLGE_MOD_REG_INFO_LEN_MAX) {
+			dev_info(dev, "length of reg(%s) is invalid, len=%d\n",
+				 reg_info[i].reg_name, actual_len);
+			continue;
+		}
+
+		pos = scnprintf(buf, HCLGE_MOD_REG_INFO_LEN_MAX, "%s",
+				reg_info[i].reg_name);
+		if (reg_info[i].has_suffix)
+			pos += scnprintf(buf + pos,
+					 HCLGE_MOD_REG_INFO_LEN_MAX - pos, "%u",
+					 le32_to_cpu(desc->data[0]));
+		pos += scnprintf(buf + pos,
+				 HCLGE_MOD_REG_INFO_LEN_MAX - pos,
+				 ":");
+		for (j = 0; j < reg_info[i].group_size; j++) {
+			offset = reg_info[i].reg_offset_group[j];
+			index = offset % HCLGE_DESC_DATA_LEN;
+			bd_idx = offset / HCLGE_DESC_DATA_LEN;
+			pos += scnprintf(buf + pos,
+					 HCLGE_MOD_REG_INFO_LEN_MAX - pos,
+					 " %08x",
+					 le32_to_cpu(desc[bd_idx].data[index]));
+		}
+		dev_info(dev, "%s\n", buf);
+	}
+
+	kfree(buf);
+	return 0;
+}
+
+static bool hclge_err_mod_check_support_cmd(enum hclge_opcode_type opcode,
+					    struct hclge_dev *hdev)
+{
+	if (opcode == HCLGE_OPC_DFX_GEN_REG &&
+	    !hnae3_ae_dev_gen_reg_dfx_supported(hdev))
+		return false;
+	return true;
+}
+
+/* For each common msg, send cmdq to IMP and print result reg info.
+ * If there is a parameter, loop it and request.
+ */
+static void
+hclge_query_reg_info(struct hclge_dev *hdev,
+		     struct hclge_mod_reg_common_msg *msg, u32 loop_time,
+		     u32 *loop_para)
+{
+	int desc_len, i, ret;
+
+	desc_len = msg->bd_num * sizeof(struct hclge_desc);
+	msg->desc = kzalloc(desc_len, GFP_KERNEL);
+	if (!msg->desc) {
+		dev_err(&hdev->pdev->dev, "failed to query reg info, ret=%d",
+			-ENOMEM);
+		return;
+	}
+
+	for (i = 0; i < loop_time; i++) {
+		ret = hclge_dbg_cmd_send(hdev, msg->desc, *loop_para,
+					 msg->bd_num, msg->cmd);
+		loop_para++;
+		if (ret)
+			continue;
+		ret = hclge_print_mod_reg_info(&hdev->pdev->dev, msg->desc,
+					       msg->result_regs,
+					       msg->result_regs_size);
+		if (ret)
+			dev_err(&hdev->pdev->dev, "failed to print mod reg info, ret=%d\n",
+				ret);
+	}
+
+	kfree(msg->desc);
+}
+
+static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev)
+{
+	u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0};
+	struct hclge_mod_reg_common_msg msg;
+	u8 i, j, num;
+	u32 loop_time;
+
+	num = ARRAY_SIZE(hclge_ssu_reg_common_msg);
+	for (i = 0; i < num; i++) {
+		msg = hclge_ssu_reg_common_msg[i];
+		if (!hclge_err_mod_check_support_cmd(msg.cmd, hdev))
+			continue;
+		loop_time = 1;
+		loop_para[0] = 0;
+		if (msg.need_para) {
+			loop_time = hdev->ae_dev->dev_specs.tnl_num;
+			for (j = 0; j < loop_time; j++)
+				loop_para[j] = j + 1;
+		}
+		hclge_query_reg_info(hdev, &msg, loop_time, loop_para);
+	}
+}
+
 static const struct hclge_hw_module_id hclge_hw_module_id_st[] = {
 	{
 		.module_id = MODULE_NONE,
@@ -1210,7 +1629,8 @@ static const struct hclge_hw_module_id hclge_hw_module_id_st[] = {
 		.msg = "MODULE_GE"
 	}, {
 		.module_id = MODULE_IGU_EGU,
-		.msg = "MODULE_IGU_EGU"
+		.msg = "MODULE_IGU_EGU",
+		.query_reg_info = hclge_query_reg_info_of_ssu
 	}, {
 		.module_id = MODULE_LGE,
 		.msg = "MODULE_LGE"
@@ -1231,7 +1651,8 @@ static const struct hclge_hw_module_id hclge_hw_module_id_st[] = {
 		.msg = "MODULE_RTC"
 	}, {
 		.module_id = MODULE_SSU,
-		.msg = "MODULE_SSU"
+		.msg = "MODULE_SSU",
+		.query_reg_info = hclge_query_reg_info_of_ssu
 	}, {
 		.module_id = MODULE_TM,
 		.msg = "MODULE_TM"
@@ -2762,7 +3183,7 @@ void hclge_handle_occurred_error(struct hclge_dev *hdev)
 }
 
 static bool
-hclge_handle_error_type_reg_log(struct device *dev,
+hclge_handle_error_type_reg_log(struct hclge_dev *hdev,
 				struct hclge_mod_err_info *mod_info,
 				struct hclge_type_reg_err_info *type_reg_info)
 {
@@ -2770,6 +3191,7 @@ hclge_handle_error_type_reg_log(struct device *dev,
 #define HCLGE_ERR_TYPE_IS_RAS_OFFSET 7
 
 	u8 mod_id, total_module, type_id, total_type, i, is_ras;
+	struct device *dev = &hdev->pdev->dev;
 	u8 index_module = MODULE_NONE;
 	u8 index_type = NONE_ERROR;
 	bool cause_by_vf = false;
@@ -2810,6 +3232,9 @@ hclge_handle_error_type_reg_log(struct device *dev,
 	for (i = 0; i < type_reg_info->reg_num; i++)
 		dev_err(dev, "0x%08x\n", type_reg_info->hclge_reg[i]);
 
+	if (hclge_hw_module_id_st[index_module].query_reg_info)
+		hclge_hw_module_id_st[index_module].query_reg_info(hdev);
+
 	return cause_by_vf;
 }
 
@@ -2850,7 +3275,7 @@ static void hclge_handle_error_module_log(struct hnae3_ae_dev *ae_dev,
 
 			type_reg_info = (struct hclge_type_reg_err_info *)
 					    &buf[offset++];
-			if (hclge_handle_error_type_reg_log(dev, mod_info,
+			if (hclge_handle_error_type_reg_log(hdev, mod_info,
 							    type_reg_info))
 				cause_by_vf = true;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 68b738affa66..45a783a50643 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -5,6 +5,7 @@
 #define __HCLGE_ERR_H
 
 #include "hclge_main.h"
+#include "hclge_debugfs.h"
 #include "hnae3.h"
 
 #define HCLGE_MPF_RAS_INT_MIN_BD_NUM	10
@@ -115,6 +116,18 @@
 #define HCLGE_REG_NUM_MAX			256
 #define HCLGE_DESC_NO_DATA_LEN			8
 
+#define HCLGE_BD_NUM_SSU_REG_0		10
+#define HCLGE_BD_NUM_SSU_REG_1		15
+#define HCLGE_BD_NUM_RPU_REG_0		1
+#define HCLGE_BD_NUM_RPU_REG_1		2
+#define HCLGE_BD_NUM_IGU_EGU_REG	9
+#define HCLGE_BD_NUM_GEN_REG		8
+#define HCLGE_MOD_REG_INFO_LEN_MAX	256
+#define HCLGE_MOD_REG_EXTRA_LEN		11
+#define HCLGE_MOD_REG_VALUE_LEN		9
+#define HCLGE_MOD_REG_GROUP_MAX_SIZE	6
+#define HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE	8
+
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
@@ -191,6 +204,7 @@ struct hclge_hw_error {
 struct hclge_hw_module_id {
 	enum hclge_mod_name_list module_id;
 	const char *msg;
+	void (*query_reg_info)(struct hclge_dev *hdev);
 };
 
 struct hclge_hw_type_id {
@@ -218,6 +232,28 @@ struct hclge_type_reg_err_info {
 	u32 hclge_reg[HCLGE_REG_NUM_MAX];
 };
 
+struct hclge_mod_reg_info {
+	const char *reg_name;
+	bool has_suffix; /* add suffix for register name */
+	/* the positions of reg values in hclge_desc.data */
+	u8 reg_offset_group[HCLGE_MOD_REG_GROUP_MAX_SIZE];
+	u8 group_size;
+};
+
+/* This structure defines cmdq used to query the hardware module debug
+ * regisgers.
+ */
+struct hclge_mod_reg_common_msg {
+	enum hclge_opcode_type cmd;
+	struct hclge_desc *desc;
+	u8 bd_num; /* the bd number of hclge_desc used */
+	bool need_para; /* whether this cmdq needs to add para */
+
+	/* the regs need to print */
+	const struct hclge_mod_reg_info *result_regs;
+	u16 result_regs_size;
+};
+
 int hclge_config_mac_tnl_int(struct hclge_dev *hdev, bool en);
 int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state);
 int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ce60332d83c3..43cc6ee4d87d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -27,6 +27,8 @@
 #include "hclge_devlink.h"
 #include "hclge_comm_cmd.h"
 
+#include "hclge_trace.h"
+
 #define HCLGE_NAME			"hclge"
 
 #define HCLGE_BUF_SIZE_UNIT	256U
@@ -391,6 +393,48 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	return hclge_comm_cmd_send(&hw->hw, desc, num);
 }
 
+static void hclge_trace_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
+				 int num, bool is_special)
+{
+	int i;
+
+	trace_hclge_pf_cmd_send(hw, desc, 0, num);
+
+	if (!is_special) {
+		for (i = 1; i < num; i++)
+			trace_hclge_pf_cmd_send(hw, &desc[i], i, num);
+	} else {
+		for (i = 1; i < num; i++)
+			trace_hclge_pf_special_cmd_send(hw, (__le32 *)&desc[i],
+							i, num);
+	}
+}
+
+static void hclge_trace_cmd_get(struct hclge_comm_hw *hw, struct hclge_desc *desc,
+				int num, bool is_special)
+{
+	int i;
+
+	if (!HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag)))
+		return;
+
+	trace_hclge_pf_cmd_get(hw, desc, 0, num);
+
+	if (!is_special) {
+		for (i = 1; i < num; i++)
+			trace_hclge_pf_cmd_get(hw, &desc[i], i, num);
+	} else {
+		for (i = 1; i < num; i++)
+			trace_hclge_pf_special_cmd_get(hw, (__le32 *)&desc[i],
+						       i, num);
+	}
+}
+
+static const struct hclge_comm_cmq_ops hclge_cmq_ops = {
+	.trace_cmd_send = hclge_trace_cmd_send,
+	.trace_cmd_get = hclge_trace_cmd_get,
+};
+
 static int hclge_mac_update_stats_defective(struct hclge_dev *hdev)
 {
 #define HCLGE_MAC_CMD_NUM 21
@@ -7183,8 +7227,9 @@ static void hclge_get_cls_key_vlan(const struct flow_rule *flow,
 	}
 }
 
-static void hclge_get_cls_key_ip(const struct flow_rule *flow,
-				 struct hclge_fd_rule *rule)
+static int hclge_get_cls_key_ip(const struct flow_rule *flow,
+				struct hclge_fd_rule *rule,
+				struct netlink_ext_ack *extack)
 {
 	u16 addr_type = 0;
 
@@ -7193,6 +7238,9 @@ static void hclge_get_cls_key_ip(const struct flow_rule *flow,
 
 		flow_rule_match_control(flow, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags, extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
@@ -7221,6 +7269,8 @@ static void hclge_get_cls_key_ip(const struct flow_rule *flow,
 		rule->unused_tuple |= BIT(INNER_SRC_IP);
 		rule->unused_tuple |= BIT(INNER_DST_IP);
 	}
+
+	return 0;
 }
 
 static void hclge_get_cls_key_port(const struct flow_rule *flow,
@@ -7246,7 +7296,9 @@ static int hclge_parse_cls_flower(struct hclge_dev *hdev,
 				  struct hclge_fd_rule *rule)
 {
 	struct flow_rule *flow = flow_cls_offload_flow_rule(cls_flower);
+	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct flow_dissector *dissector = flow->match.dissector;
+	int ret;
 
 	if (dissector->used_keys &
 	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
@@ -7264,7 +7316,11 @@ static int hclge_parse_cls_flower(struct hclge_dev *hdev,
 	hclge_get_cls_key_basic(flow, rule);
 	hclge_get_cls_key_mac(flow, rule);
 	hclge_get_cls_key_vlan(flow, rule);
-	hclge_get_cls_key_ip(flow, rule);
+
+	ret = hclge_get_cls_key_ip(flow, rule, extack);
+	if (ret)
+		return ret;
+
 	hclge_get_cls_key_port(flow, rule);
 
 	return 0;
@@ -10848,6 +10904,24 @@ static u32 hclge_get_fw_version(struct hnae3_handle *handle)
 	return hdev->fw_version;
 }
 
+int hclge_query_scc_version(struct hclge_dev *hdev, u32 *scc_version)
+{
+	struct hclge_comm_query_scc_cmd *resp;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_SCC_VER, 1);
+	resp = (struct hclge_comm_query_scc_cmd *)desc.data;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		return ret;
+
+	*scc_version = le32_to_cpu(resp->scc_version);
+
+	return 0;
+}
+
 static void hclge_set_flowctrl_adv(struct hclge_dev *hdev, u32 rx_en, u32 tx_en)
 {
 	struct phy_device *phydev = hdev->hw.mac.phydev;
@@ -11637,6 +11711,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_pci_uninit;
 
 	/* Firmware command initialize */
+	hclge_comm_cmd_init_ops(&hdev->hw.hw, &hclge_cmq_ops);
 	ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw, &hdev->fw_version,
 				  true, hdev->reset_pending);
 	if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 3a9186457ad8..b5178b0f88b3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1172,4 +1172,5 @@ int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en);
 int hclge_mac_update_stats(struct hclge_dev *hdev);
 struct hclge_vport *hclge_get_vf_vport(struct hclge_dev *hdev, int vf);
 int hclge_inform_vf_reset(struct hclge_vport *vport, u16 reset_type);
+int hclge_query_scc_version(struct hclge_dev *hdev, u32 *scc_version);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
index f3cd5a376eca..7e47f0c21d88 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
@@ -10,6 +10,7 @@
 
 #include <linux/tracepoint.h>
 
+#define PF_DESC_LEN	(sizeof(struct hclge_desc) / sizeof(u32))
 #define PF_GET_MBX_LEN	(sizeof(struct hclge_mbx_vf_to_pf_cmd) / sizeof(u32))
 #define PF_SEND_MBX_LEN	(sizeof(struct hclge_mbx_pf_to_vf_cmd) / sizeof(u32))
 
@@ -77,6 +78,99 @@ TRACE_EVENT(hclge_pf_mbx_send,
 	)
 );
 
+DECLARE_EVENT_CLASS(hclge_pf_cmd_template,
+		    TP_PROTO(struct hclge_comm_hw *hw,
+			     struct hclge_desc *desc,
+			     int index,
+			     int num),
+		    TP_ARGS(hw, desc, index, num),
+
+		    TP_STRUCT__entry(__field(u16, opcode)
+			__field(u16, flag)
+			__field(u16, retval)
+			__field(u16, rsv)
+			__field(int, index)
+			__field(int, num)
+			__string(pciname, pci_name(hw->cmq.csq.pdev))
+			__array(u32, data, HCLGE_DESC_DATA_LEN)),
+
+		    TP_fast_assign(int i;
+			__entry->opcode = le16_to_cpu(desc->opcode);
+			__entry->flag = le16_to_cpu(desc->flag);
+			__entry->retval = le16_to_cpu(desc->retval);
+			__entry->rsv = le16_to_cpu(desc->rsv);
+			__entry->index = index;
+			__entry->num = num;
+			__assign_str(pciname, pci_name(hw->cmq.csq.pdev));
+			for (i = 0; i < HCLGE_DESC_DATA_LEN; i++)
+				__entry->data[i] = le32_to_cpu(desc->data[i]);),
+
+		    TP_printk("%s opcode:0x%04x %d-%d flag:0x%04x retval:0x%04x rsv:0x%04x data:%s",
+			      __get_str(pciname), __entry->opcode,
+			      __entry->index, __entry->num,
+			      __entry->flag, __entry->retval, __entry->rsv,
+			      __print_array(__entry->data,
+					    HCLGE_DESC_DATA_LEN, sizeof(u32)))
+);
+
+DEFINE_EVENT(hclge_pf_cmd_template, hclge_pf_cmd_send,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      struct hclge_desc *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num)
+);
+
+DEFINE_EVENT(hclge_pf_cmd_template, hclge_pf_cmd_get,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      struct hclge_desc *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num)
+);
+
+DECLARE_EVENT_CLASS(hclge_pf_special_cmd_template,
+		    TP_PROTO(struct hclge_comm_hw *hw,
+			     __le32 *data,
+			     int index,
+			     int num),
+		    TP_ARGS(hw, data, index, num),
+
+		    TP_STRUCT__entry(__field(int, index)
+			__field(int, num)
+			__string(pciname, pci_name(hw->cmq.csq.pdev))
+			__array(u32, data, PF_DESC_LEN)),
+
+		    TP_fast_assign(int i;
+			__entry->index = index;
+			__entry->num = num;
+			__assign_str(pciname, pci_name(hw->cmq.csq.pdev));
+			for (i = 0; i < PF_DESC_LEN; i++)
+				__entry->data[i] = le32_to_cpu(data[i]);
+		),
+
+		    TP_printk("%s %d-%d data:%s",
+			      __get_str(pciname),
+			      __entry->index, __entry->num,
+			      __print_array(__entry->data,
+					    PF_DESC_LEN, sizeof(u32)))
+);
+
+DEFINE_EVENT(hclge_pf_special_cmd_template, hclge_pf_special_cmd_send,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      __le32 *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num));
+
+DEFINE_EVENT(hclge_pf_special_cmd_template, hclge_pf_special_cmd_get,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      __le32 *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num)
+);
+
 #endif /* _HCLGE_TRACE_H_ */
 
 /* This must be outside ifdef _HCLGE_TRACE_H */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 43ee20eb03d1..3735d2fed11f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -11,6 +11,7 @@
 #include "hnae3.h"
 #include "hclgevf_devlink.h"
 #include "hclge_comm_rss.h"
+#include "hclgevf_trace.h"
 
 #define HCLGEVF_NAME	"hclgevf"
 
@@ -47,6 +48,42 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclge_desc *desc, int num)
 	return hclge_comm_cmd_send(&hw->hw, desc, num);
 }
 
+static void hclgevf_trace_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
+				   int num, bool is_special)
+{
+	int i;
+
+	trace_hclge_vf_cmd_send(hw, desc, 0, num);
+
+	if (is_special)
+		return;
+
+	for (i = 1; i < num; i++)
+		trace_hclge_vf_cmd_send(hw, &desc[i], i, num);
+}
+
+static void hclgevf_trace_cmd_get(struct hclge_comm_hw *hw, struct hclge_desc *desc,
+				  int num, bool is_special)
+{
+	int i;
+
+	if (!HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag)))
+		return;
+
+	trace_hclge_vf_cmd_get(hw, desc, 0, num);
+
+	if (is_special)
+		return;
+
+	for (i = 1; i < num; i++)
+		trace_hclge_vf_cmd_get(hw, &desc[i], i, num);
+}
+
+static const struct hclge_comm_cmq_ops hclgevf_cmq_ops = {
+	.trace_cmd_send = hclgevf_trace_cmd_send,
+	.trace_cmd_get = hclgevf_trace_cmd_get,
+};
+
 void hclgevf_arq_init(struct hclgevf_dev *hdev)
 {
 	struct hclge_comm_cmq *cmdq = &hdev->hw.hw.cmq;
@@ -2796,6 +2833,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 	}
 
 	hclgevf_arq_init(hdev);
+
 	ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw,
 				  &hdev->fw_version, false,
 				  hdev->reset_pending);
@@ -2850,6 +2888,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_cmd_queue_init;
 
 	hclgevf_arq_init(hdev);
+
+	hclge_comm_cmd_init_ops(&hdev->hw.hw, &hclgevf_cmq_ops);
 	ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw,
 				  &hdev->fw_version, false,
 				  hdev->reset_pending);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h
index b259e95dd53c..e2e3a2602b6a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h
@@ -77,6 +77,56 @@ TRACE_EVENT(hclge_vf_mbx_send,
 	)
 );
 
+DECLARE_EVENT_CLASS(hclge_vf_cmd_template,
+		    TP_PROTO(struct hclge_comm_hw *hw,
+			     struct hclge_desc *desc,
+			     int index,
+			     int num),
+
+		    TP_ARGS(hw, desc, index, num),
+
+		    TP_STRUCT__entry(__field(u16, opcode)
+			__field(u16, flag)
+			__field(u16, retval)
+			__field(u16, rsv)
+			__field(int, index)
+			__field(int, num)
+			__string(pciname, pci_name(hw->cmq.csq.pdev))
+			__array(u32, data, HCLGE_DESC_DATA_LEN)),
+
+		    TP_fast_assign(int i;
+			__entry->opcode = le16_to_cpu(desc->opcode);
+			__entry->flag = le16_to_cpu(desc->flag);
+			__entry->retval = le16_to_cpu(desc->retval);
+			__entry->rsv = le16_to_cpu(desc->rsv);
+			__entry->index = index;
+			__entry->num = num;
+			__assign_str(pciname, pci_name(hw->cmq.csq.pdev));
+			for (i = 0; i < HCLGE_DESC_DATA_LEN; i++)
+				__entry->data[i] = le32_to_cpu(desc->data[i]);),
+
+		    TP_printk("%s opcode:0x%04x %d-%d flag:0x%04x retval:0x%04x rsv:0x%04x data:%s",
+			      __get_str(pciname), __entry->opcode,
+			      __entry->index, __entry->num,
+			      __entry->flag, __entry->retval, __entry->rsv,
+			      __print_array(__entry->data,
+					    HCLGE_DESC_DATA_LEN, sizeof(u32)))
+);
+
+DEFINE_EVENT(hclge_vf_cmd_template, hclge_vf_cmd_send,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      struct hclge_desc *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num));
+
+DEFINE_EVENT(hclge_vf_cmd_template, hclge_vf_cmd_get,
+	     TP_PROTO(struct hclge_comm_hw *hw,
+		      struct hclge_desc *desc,
+		      int index,
+		      int num),
+	     TP_ARGS(hw, desc, index, num));
+
 #endif /* _HCLGEVF_TRACE_H_ */
 
 /* This must be outside ifdef _HCLGEVF_TRACE_H */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 499c657d37a9..890f213da8d1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -581,7 +581,7 @@ static int hinic_change_mtu(struct net_device *netdev, int new_mtu)
 	if (err)
 		netif_err(nic_dev, drv, netdev, "Failed to set port mtu\n");
 	else
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index e6e47b1842ea..a19d098f2e2b 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1098,7 +1098,7 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 		/* This is to prevent starting RX channel in emac_rx_enable() */
 		set_bit(MAL_COMMAC_RX_STOPPED, &dev->commac.flags);
 
-		dev->ndev->mtu = new_mtu;
+		WRITE_ONCE(dev->ndev->mtu, new_mtu);
 		emac_full_tx_reset(dev);
 	}
 
@@ -1130,7 +1130,7 @@ static int emac_change_mtu(struct net_device *ndev, int new_mtu)
 	}
 
 	if (!ret) {
-		ndev->mtu = new_mtu;
+		WRITE_ONCE(ndev->mtu, new_mtu);
 		dev->rx_skb_size = emac_rx_skb_size(new_mtu);
 		dev->rx_sync_size = emac_rx_sync_size(new_mtu);
 	}
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index 2439f7e96e05..d92dd9c83031 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -605,9 +605,13 @@ static int mal_probe(struct platform_device *ofdev)
 	INIT_LIST_HEAD(&mal->list);
 	spin_lock_init(&mal->lock);
 
-	init_dummy_netdev(&mal->dummy_dev);
+	mal->dummy_dev = alloc_netdev_dummy(0);
+	if (!mal->dummy_dev) {
+		err = -ENOMEM;
+		goto fail_unmap;
+	}
 
-	netif_napi_add_weight(&mal->dummy_dev, &mal->napi, mal_poll,
+	netif_napi_add_weight(mal->dummy_dev, &mal->napi, mal_poll,
 			      CONFIG_IBM_EMAC_POLL_WEIGHT);
 
 	/* Load power-on reset defaults */
@@ -637,7 +641,7 @@ static int mal_probe(struct platform_device *ofdev)
 					  GFP_KERNEL);
 	if (mal->bd_virt == NULL) {
 		err = -ENOMEM;
-		goto fail_unmap;
+		goto fail_dummy;
 	}
 
 	for (i = 0; i < mal->num_tx_chans; ++i)
@@ -703,6 +707,8 @@ static int mal_probe(struct platform_device *ofdev)
 	free_irq(mal->serr_irq, mal);
  fail2:
 	dma_free_coherent(&ofdev->dev, bd_size, mal->bd_virt, mal->bd_dma);
+ fail_dummy:
+	free_netdev(mal->dummy_dev);
  fail_unmap:
 	dcr_unmap(mal->dcr_host, 0x100);
  fail:
@@ -734,6 +740,8 @@ static void mal_remove(struct platform_device *ofdev)
 
 	mal_reset(mal);
 
+	free_netdev(mal->dummy_dev);
+
 	dma_free_coherent(&ofdev->dev,
 			  sizeof(struct mal_descriptor) *
 			  (NUM_TX_BUFF * mal->num_tx_chans +
diff --git a/drivers/net/ethernet/ibm/emac/mal.h b/drivers/net/ethernet/ibm/emac/mal.h
index d212373a72e7..e0ddc41186a2 100644
--- a/drivers/net/ethernet/ibm/emac/mal.h
+++ b/drivers/net/ethernet/ibm/emac/mal.h
@@ -205,7 +205,7 @@ struct mal_instance {
 	int			index;
 	spinlock_t		lock;
 
-	struct net_device	dummy_dev;
+	struct net_device	*dummy_dev;
 
 	unsigned int features;
 };
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b5aef0b29efe..4c9d9badd698 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1537,7 +1537,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
 		adapter->rx_buff_pool[i].active = 1;
 
 		if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) {
-			dev->mtu = new_mtu;
+			WRITE_ONCE(dev->mtu, new_mtu);
 			vio_cmo_set_dev_desired(viodev,
 						ibmveth_get_desired_dma
 						(viodev));
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 30c47b8470ad..5e9a93bdb518 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2371,7 +2371,7 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
 		ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
 	else
 		ind_bufp->index = 0;
-	return 0;
+	return rc;
 }
 
 static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
@@ -2424,7 +2424,9 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_dropped++;
 		tx_send_failed++;
 		ret = NETDEV_TX_OK;
-		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
 		goto out;
 	}
 
@@ -2439,8 +2441,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		dev_kfree_skb_any(skb);
 		tx_send_failed++;
 		tx_dropped++;
-		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		ret = NETDEV_TX_OK;
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 639fbb12bd35..e0287fbd501d 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -16,6 +16,9 @@ config NET_VENDOR_INTEL
 
 if NET_VENDOR_INTEL
 
+source "drivers/net/ethernet/intel/libeth/Kconfig"
+source "drivers/net/ethernet/intel/libie/Kconfig"
+
 config E100
 	tristate "Intel(R) PRO/100+ support"
 	depends on PCI
@@ -41,7 +44,7 @@ config E100
 
 config E1000
 	tristate "Intel(R) PRO/1000 Gigabit Ethernet support"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	help
 	  This driver supports Intel(R) PRO/1000 gigabit ethernet family of
 	  adapters.  For more information on how to identify your adapter, go
@@ -225,6 +228,7 @@ config I40E
 	depends on PTP_1588_CLOCK_OPTIONAL
 	depends on PCI
 	select AUXILIARY_BUS
+	select LIBIE
 	select NET_DEVLINK
 	help
 	  This driver supports Intel(R) Ethernet Controller XL710 Family of
@@ -253,6 +257,8 @@ config I40E_DCB
 # so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF
 config IAVF
 	tristate
+	select LIBIE
+
 config I40EVF
 	tristate "Intel(R) Ethernet Adaptive Virtual Function support"
 	select IAVF
@@ -283,6 +289,7 @@ config ICE
 	depends on GNSS || GNSS = n
 	select AUXILIARY_BUS
 	select DIMLIB
+	select LIBIE
 	select NET_DEVLINK
 	select PLDMFW
 	select DPLL
diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile
index dacb481ee5b1..04c844ef4964 100644
--- a/drivers/net/ethernet/intel/Makefile
+++ b/drivers/net/ethernet/intel/Makefile
@@ -3,6 +3,9 @@
 # Makefile for the Intel network device drivers.
 #
 
+obj-$(CONFIG_LIBETH) += libeth/
+obj-$(CONFIG_LIBIE) += libie/
+
 obj-$(CONFIG_E100) += e100.o
 obj-$(CONFIG_E1000) += e1000/
 obj-$(CONFIG_E1000E) += e1000e/
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 3fcb8daaa243..9b068d40778d 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3037,7 +3037,7 @@ static int __e100_power_off(struct pci_dev *pdev, bool wake)
 	return 0;
 }
 
-static int __maybe_unused e100_suspend(struct device *dev_d)
+static int e100_suspend(struct device *dev_d)
 {
 	bool wake;
 
@@ -3046,7 +3046,7 @@ static int __maybe_unused e100_suspend(struct device *dev_d)
 	return 0;
 }
 
-static int __maybe_unused e100_resume(struct device *dev_d)
+static int e100_resume(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct nic *nic = netdev_priv(netdev);
@@ -3163,7 +3163,7 @@ static const struct pci_error_handlers e100_err_handler = {
 	.resume = e100_io_resume,
 };
 
-static SIMPLE_DEV_PM_OPS(e100_pm_ops, e100_suspend, e100_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(e100_pm_ops, e100_suspend, e100_resume);
 
 static struct pci_driver e100_driver = {
 	.name =         DRV_NAME,
@@ -3172,7 +3172,7 @@ static struct pci_driver e100_driver = {
 	.remove =       e100_remove,
 
 	/* Power Management hooks */
-	.driver.pm =	&e100_pm_ops,
+	.driver.pm =	pm_sleep_ptr(&e100_pm_ops),
 
 	.shutdown =     e100_shutdown,
 	.err_handler = &e100_err_handler,
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 1d1e93686af2..60fff9a6c53e 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -149,8 +149,8 @@ static int e1000_vlan_rx_kill_vid(struct net_device *netdev,
 				  __be16 proto, u16 vid);
 static void e1000_restore_vlan(struct e1000_adapter *adapter);
 
-static int __maybe_unused e1000_suspend(struct device *dev);
-static int __maybe_unused e1000_resume(struct device *dev);
+static int e1000_suspend(struct device *dev);
+static int e1000_resume(struct device *dev);
 static void e1000_shutdown(struct pci_dev *pdev);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -175,16 +175,14 @@ static const struct pci_error_handlers e1000_err_handler = {
 	.resume = e1000_io_resume,
 };
 
-static SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume);
 
 static struct pci_driver e1000_driver = {
 	.name     = e1000_driver_name,
 	.id_table = e1000_pci_tbl,
 	.probe    = e1000_probe,
 	.remove   = e1000_remove,
-	.driver = {
-		.pm = &e1000_pm_ops,
-	},
+	.driver.pm = pm_sleep_ptr(&e1000_pm_ops),
 	.shutdown = e1000_shutdown,
 	.err_handler = &e1000_err_handler
 };
@@ -3571,7 +3569,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		e1000_up(adapter);
@@ -5135,7 +5133,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	return 0;
 }
 
-static int __maybe_unused e1000_suspend(struct device *dev)
+static int e1000_suspend(struct device *dev)
 {
 	int retval;
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -5147,7 +5145,7 @@ static int __maybe_unused e1000_suspend(struct device *dev)
 	return retval;
 }
 
-static int __maybe_unused e1000_resume(struct device *dev)
+static int e1000_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 23a58cada43a..5e2cfa73f889 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -679,8 +679,6 @@
 /* PCI/PCI-X/PCI-EX Config space */
 #define PCI_HEADER_TYPE_REGISTER     0x0E
 
-#define PCI_HEADER_TYPE_MULTIFUNC    0x80
-
 #define PHY_REVISION_MASK      0xFFFFFFF0
 #define MAX_PHY_REG_ADDRESS    0x1F  /* 5 bit address bus (0-0x1F) */
 #define MAX_PHY_MULTI_PAGE_REG 0xF
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index dc553c51d79a..85da20778e0f 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -156,7 +156,7 @@ static int e1000_get_link_ksettings(struct net_device *netdev,
 			speed = adapter->link_speed;
 			cmd->base.duplex = adapter->link_duplex - 1;
 		}
-	} else if (!pm_runtime_suspended(netdev->dev.parent)) {
+	} else {
 		u32 status = er32(STATUS);
 
 		if (status & E1000_STATUS_LU) {
@@ -274,16 +274,13 @@ static int e1000_set_link_ksettings(struct net_device *netdev,
 	ethtool_convert_link_mode_to_legacy_u32(&advertising,
 						cmd->link_modes.advertising);
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	/* When SoL/IDER sessions are active, autoneg/speed/duplex
 	 * cannot be changed
 	 */
 	if (hw->phy.ops.check_reset_block &&
 	    hw->phy.ops.check_reset_block(hw)) {
 		e_err("Cannot change link characteristics when SoL/IDER is active.\n");
-		ret_val = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	/* MDI setting is only allowed when autoneg enabled because
@@ -291,16 +288,13 @@ static int e1000_set_link_ksettings(struct net_device *netdev,
 	 * duplex is forced.
 	 */
 	if (cmd->base.eth_tp_mdix_ctrl) {
-		if (hw->phy.media_type != e1000_media_type_copper) {
-			ret_val = -EOPNOTSUPP;
-			goto out;
-		}
+		if (hw->phy.media_type != e1000_media_type_copper)
+			return -EOPNOTSUPP;
 
 		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
 		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
-			ret_val = -EINVAL;
-			goto out;
+			return -EINVAL;
 		}
 	}
 
@@ -347,7 +341,6 @@ static int e1000_set_link_ksettings(struct net_device *netdev,
 	}
 
 out:
-	pm_runtime_put_sync(netdev->dev.parent);
 	clear_bit(__E1000_RESETTING, &adapter->state);
 	return ret_val;
 }
@@ -383,8 +376,6 @@ static int e1000_set_pauseparam(struct net_device *netdev,
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	if (adapter->fc_autoneg == AUTONEG_ENABLE) {
 		hw->fc.requested_mode = e1000_fc_default;
 		if (netif_running(adapter->netdev)) {
@@ -417,7 +408,6 @@ static int e1000_set_pauseparam(struct net_device *netdev,
 	}
 
 out:
-	pm_runtime_put_sync(netdev->dev.parent);
 	clear_bit(__E1000_RESETTING, &adapter->state);
 	return retval;
 }
@@ -448,8 +438,6 @@ static void e1000_get_regs(struct net_device *netdev,
 	u32 *regs_buff = p;
 	u16 phy_data;
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	memset(p, 0, E1000_REGS_LEN * sizeof(u32));
 
 	regs->version = (1u << 24) |
@@ -495,8 +483,6 @@ static void e1000_get_regs(struct net_device *netdev,
 	e1e_rphy(hw, MII_STAT1000, &phy_data);
 	regs_buff[24] = (u32)phy_data;	/* phy local receiver status */
 	regs_buff[25] = regs_buff[24];	/* phy remote receiver status */
-
-	pm_runtime_put_sync(netdev->dev.parent);
 }
 
 static int e1000_get_eeprom_len(struct net_device *netdev)
@@ -529,8 +515,6 @@ static int e1000_get_eeprom(struct net_device *netdev,
 	if (!eeprom_buff)
 		return -ENOMEM;
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	if (hw->nvm.type == e1000_nvm_eeprom_spi) {
 		ret_val = e1000_read_nvm(hw, first_word,
 					 last_word - first_word + 1,
@@ -544,8 +528,6 @@ static int e1000_get_eeprom(struct net_device *netdev,
 		}
 	}
 
-	pm_runtime_put_sync(netdev->dev.parent);
-
 	if (ret_val) {
 		/* a read error occurred, throw away the result */
 		memset(eeprom_buff, 0xff, sizeof(u16) *
@@ -595,8 +577,6 @@ static int e1000_set_eeprom(struct net_device *netdev,
 
 	ptr = (void *)eeprom_buff;
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	if (eeprom->offset & 1) {
 		/* need read/modify/write of first changed EEPROM word */
 		/* only the second byte of the word is being modified */
@@ -637,7 +617,6 @@ static int e1000_set_eeprom(struct net_device *netdev,
 		ret_val = e1000e_update_nvm_checksum(hw);
 
 out:
-	pm_runtime_put_sync(netdev->dev.parent);
 	kfree(eeprom_buff);
 	return ret_val;
 }
@@ -733,8 +712,6 @@ static int e1000_set_ringparam(struct net_device *netdev,
 		}
 	}
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	e1000e_down(adapter, true);
 
 	/* We can't just free everything and then setup again, because the
@@ -773,7 +750,6 @@ err_setup_rx:
 		e1000e_free_tx_resources(temp_tx);
 err_setup:
 	e1000e_up(adapter);
-	pm_runtime_put_sync(netdev->dev.parent);
 free_temp:
 	vfree(temp_tx);
 	vfree(temp_rx);
@@ -1816,8 +1792,6 @@ static void e1000_diag_test(struct net_device *netdev,
 	u8 autoneg;
 	bool if_running = netif_running(netdev);
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	set_bit(__E1000_TESTING, &adapter->state);
 
 	if (!if_running) {
@@ -1903,8 +1877,6 @@ static void e1000_diag_test(struct net_device *netdev,
 	}
 
 	msleep_interruptible(4 * 1000);
-
-	pm_runtime_put_sync(netdev->dev.parent);
 }
 
 static void e1000_get_wol(struct net_device *netdev,
@@ -2046,15 +2018,11 @@ static int e1000_set_coalesce(struct net_device *netdev,
 		adapter->itr_setting = adapter->itr & ~3;
 	}
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	if (adapter->itr_setting != 0)
 		e1000e_write_itr(adapter, adapter->itr);
 	else
 		e1000e_write_itr(adapter, 0);
 
-	pm_runtime_put_sync(netdev->dev.parent);
-
 	return 0;
 }
 
@@ -2068,9 +2036,7 @@ static int e1000_nway_reset(struct net_device *netdev)
 	if (!adapter->hw.mac.autoneg)
 		return -EINVAL;
 
-	pm_runtime_get_sync(netdev->dev.parent);
 	e1000e_reinit_locked(adapter);
-	pm_runtime_put_sync(netdev->dev.parent);
 
 	return 0;
 }
@@ -2084,12 +2050,8 @@ static void e1000_get_ethtool_stats(struct net_device *netdev,
 	int i;
 	char *p = NULL;
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	dev_get_stats(netdev, &net_stats);
 
-	pm_runtime_put_sync(netdev->dev.parent);
-
 	for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) {
 		switch (e1000_gstrings_stats[i].type) {
 		case NETDEV_STATS:
@@ -2146,9 +2108,7 @@ static int e1000_get_rxnfc(struct net_device *netdev,
 		struct e1000_hw *hw = &adapter->hw;
 		u32 mrqc;
 
-		pm_runtime_get_sync(netdev->dev.parent);
 		mrqc = er32(MRQC);
-		pm_runtime_put_sync(netdev->dev.parent);
 
 		if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK))
 			return 0;
@@ -2211,13 +2171,9 @@ static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 		return -EOPNOTSUPP;
 	}
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	ret_val = hw->phy.ops.acquire(hw);
-	if (ret_val) {
-		pm_runtime_put_sync(netdev->dev.parent);
+	if (ret_val)
 		return -EBUSY;
-	}
 
 	/* EEE Capability */
 	ret_val = e1000_read_emi_reg_locked(hw, cap_addr, &phy_data);
@@ -2257,8 +2213,6 @@ release:
 	if (ret_val)
 		ret_val = -ENODATA;
 
-	pm_runtime_put_sync(netdev->dev.parent);
-
 	return ret_val;
 }
 
@@ -2299,16 +2253,12 @@ static int e1000e_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 
 	hw->dev_spec.ich8lan.eee_disable = !edata->eee_enabled;
 
-	pm_runtime_get_sync(netdev->dev.parent);
-
 	/* reset the link */
 	if (netif_running(netdev))
 		e1000e_reinit_locked(adapter);
 	else
 		e1000e_reset(adapter);
 
-	pm_runtime_put_sync(netdev->dev.parent);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 3692fce20195..220d62fca55d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6038,7 +6038,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	adapter->max_frame_size = max_frame;
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	pm_runtime_get_sync(netdev->dev.parent);
 
@@ -6968,13 +6968,13 @@ static int __e1000_resume(struct pci_dev *pdev)
 	return 0;
 }
 
-static __maybe_unused int e1000e_pm_prepare(struct device *dev)
+static int e1000e_pm_prepare(struct device *dev)
 {
 	return pm_runtime_suspended(dev) &&
 		pm_suspend_via_firmware();
 }
 
-static __maybe_unused int e1000e_pm_suspend(struct device *dev)
+static int e1000e_pm_suspend(struct device *dev)
 {
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
@@ -6997,7 +6997,7 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev)
 	return rc;
 }
 
-static __maybe_unused int e1000e_pm_resume(struct device *dev)
+static int e1000e_pm_resume(struct device *dev)
 {
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
@@ -7031,7 +7031,7 @@ static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev)
 	return -EBUSY;
 }
 
-static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev)
+static int e1000e_pm_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7050,7 +7050,7 @@ static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev)
 	return rc;
 }
 
-static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev)
+static int e1000e_pm_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7937,8 +7937,7 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
 
-static const struct dev_pm_ops e1000_pm_ops = {
-#ifdef CONFIG_PM_SLEEP
+static const struct dev_pm_ops e1000e_pm_ops = {
 	.prepare	= e1000e_pm_prepare,
 	.suspend	= e1000e_pm_suspend,
 	.resume		= e1000e_pm_resume,
@@ -7946,9 +7945,8 @@ static const struct dev_pm_ops e1000_pm_ops = {
 	.thaw		= e1000e_pm_thaw,
 	.poweroff	= e1000e_pm_suspend,
 	.restore	= e1000e_pm_resume,
-#endif
-	SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume,
-			   e1000e_pm_runtime_idle)
+	RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume,
+		       e1000e_pm_runtime_idle)
 };
 
 /* PCI Device API Driver */
@@ -7957,9 +7955,7 @@ static struct pci_driver e1000_driver = {
 	.id_table = e1000_pci_tbl,
 	.probe    = e1000_probe,
 	.remove   = e1000_remove,
-	.driver   = {
-		.pm = &e1000_pm_ops,
-	},
+	.driver.pm = pm_ptr(&e1000e_pm_ops),
 	.shutdown = e1000_shutdown,
 	.err_handler = &e1000_err_handler
 };
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index d748b98274e7..92de609b7218 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -2342,7 +2342,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
  * suspend or hibernation. This function does not need to handle lower PCIe
  * device state as the stack takes care of that for us.
  **/
-static int __maybe_unused fm10k_resume(struct device *dev)
+static int fm10k_resume(struct device *dev)
 {
 	struct fm10k_intfc *interface = dev_get_drvdata(dev);
 	struct net_device *netdev = interface->netdev;
@@ -2369,7 +2369,7 @@ static int __maybe_unused fm10k_resume(struct device *dev)
  * system suspend or hibernation. This function does not need to handle lower
  * PCIe device state as the stack takes care of that for us.
  **/
-static int __maybe_unused fm10k_suspend(struct device *dev)
+static int fm10k_suspend(struct device *dev)
 {
 	struct fm10k_intfc *interface = dev_get_drvdata(dev);
 	struct net_device *netdev = interface->netdev;
@@ -2502,16 +2502,14 @@ static const struct pci_error_handlers fm10k_err_handler = {
 	.reset_done = fm10k_io_reset_done,
 };
 
-static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume);
 
 static struct pci_driver fm10k_driver = {
 	.name			= fm10k_driver_name,
 	.id_table		= fm10k_pci_tbl,
 	.probe			= fm10k_probe,
 	.remove			= fm10k_remove,
-	.driver = {
-		.pm		= &fm10k_pm_ops,
-	},
+	.driver.pm		= pm_sleep_ptr(&fm10k_pm_ops),
 	.sriov_configure	= fm10k_iov_configure,
 	.err_handler		= &fm10k_err_handler
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 2fbabcdb5bb5..bca2084cc54b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -788,7 +788,6 @@ struct i40e_veb {
 	u16 stats_idx;		/* index of VEB parent */
 	u8  enabled_tc;
 	u16 bridge_mode;	/* Bridge Mode (VEB/VEPA) */
-	u16 flags;
 	u16 bw_limit;
 	u8  bw_max_quanta;
 	bool is_abs_credits;
@@ -1213,7 +1212,7 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi);
 void i40e_vsi_stop_rings_no_wait(struct  i40e_vsi *vsi);
 int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi);
 int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count);
-struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid,
+struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 uplink_seid,
 				u16 downlink_seid, u8 enabled_tc);
 void i40e_veb_release(struct i40e_veb *veb);
 
@@ -1237,8 +1236,8 @@ static inline void i40e_dbg_exit(void) {}
 int i40e_lan_add_device(struct i40e_pf *pf);
 int i40e_lan_del_device(struct i40e_pf *pf);
 void i40e_client_subtask(struct i40e_pf *pf);
-void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi);
-void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset);
+void i40e_notify_client_of_l2_param_changes(struct i40e_pf *pf);
+void i40e_notify_client_of_netdev_close(struct i40e_pf *pf, bool reset);
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs);
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id);
 void i40e_client_update_msix_info(struct i40e_pf *pf);
@@ -1374,6 +1373,17 @@ i40e_pf_get_vsi_by_seid(struct i40e_pf *pf, u16 seid)
 }
 
 /**
+ * i40e_pf_get_main_vsi - get pointer to main VSI
+ * @pf: pointer to a PF
+ *
+ * Return: pointer to main VSI or NULL if it does not exist
+ **/
+static inline struct i40e_vsi *i40e_pf_get_main_vsi(struct i40e_pf *pf)
+{
+	return (pf->lan_vsi != I40E_NO_VSI) ? pf->vsi[pf->lan_vsi] : NULL;
+}
+
+/**
  * i40e_pf_get_veb_by_seid - find VEB by SEID
  * @pf: pointer to a PF
  * @seid: SEID of the VSI
@@ -1391,4 +1401,15 @@ i40e_pf_get_veb_by_seid(struct i40e_pf *pf, u16 seid)
 	return NULL;
 }
 
+/**
+ * i40e_pf_get_main_veb - get pointer to main VEB
+ * @pf: pointer to a PF
+ *
+ * Return: pointer to main VEB or NULL if it does not exist
+ **/
+static inline struct i40e_veb *i40e_pf_get_main_veb(struct i40e_pf *pf)
+{
+	return (pf->lan_veb != I40E_NO_VEB) ? pf->veb[pf->lan_veb] : NULL;
+}
+
 #endif /* _I40E_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index b32071ee84af..59263551c383 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -101,25 +101,26 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
 
 /**
  * i40e_notify_client_of_l2_param_changes - call the client notify callback
- * @vsi: the VSI with l2 param changes
+ * @pf: PF device pointer
  *
- * If there is a client to this VSI, call the client
+ * If there is a client, call its callback
  **/
-void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi)
+void i40e_notify_client_of_l2_param_changes(struct i40e_pf *pf)
 {
-	struct i40e_pf *pf = vsi->back;
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_client_instance *cdev = pf->cinst;
 	struct i40e_params params;
 
 	if (!cdev || !cdev->client)
 		return;
 	if (!cdev->client->ops || !cdev->client->ops->l2_param_change) {
-		dev_dbg(&vsi->back->pdev->dev,
+		dev_dbg(&pf->pdev->dev,
 			"Cannot locate client instance l2_param_change routine\n");
 		return;
 	}
 	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
-		dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
+		dev_dbg(&pf->pdev->dev,
+			"Client is not open, abort l2 param change\n");
 		return;
 	}
 	memset(&params, 0, sizeof(params));
@@ -157,20 +158,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev)
 
 /**
  * i40e_notify_client_of_netdev_close - call the client close callback
- * @vsi: the VSI with netdev closed
+ * @pf: PF device pointer
  * @reset: true when close called due to a reset pending
  *
  * If there is a client to this netdev, call the client with close
  **/
-void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
+void i40e_notify_client_of_netdev_close(struct i40e_pf *pf, bool reset)
 {
-	struct i40e_pf *pf = vsi->back;
 	struct i40e_client_instance *cdev = pf->cinst;
 
 	if (!cdev || !cdev->client)
 		return;
 	if (!cdev->client->ops || !cdev->client->ops->close) {
-		dev_dbg(&vsi->back->pdev->dev,
+		dev_dbg(&pf->pdev->dev,
 			"Cannot locate client instance close routine\n");
 		return;
 	}
@@ -333,9 +333,9 @@ static int i40e_register_auxiliary_dev(struct i40e_info *ldev, const char *name)
  **/
 static void i40e_client_add_instance(struct i40e_pf *pf)
 {
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_client_instance *cdev = NULL;
 	struct netdev_hw_addr *mac = NULL;
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 
 	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
 	if (!cdev)
@@ -399,9 +399,9 @@ void i40e_client_del_instance(struct i40e_pf *pf)
  **/
 void i40e_client_subtask(struct i40e_pf *pf)
 {
-	struct i40e_client *client;
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_client_instance *cdev;
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_client *client;
 	int ret = 0;
 
 	if (!test_and_clear_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state))
@@ -665,8 +665,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 				       bool is_vf, u32 vf_id,
 				       u32 flag, u32 valid_flag)
 {
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(ldev->pf);
 	struct i40e_pf *pf = ldev->pf;
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_vsi_context ctxt;
 	bool update = true;
 	int err;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index de6ca6295742..e8031f1a9b4f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -381,259 +381,6 @@ int i40e_aq_set_rss_key(struct i40e_hw *hw,
 	return i40e_aq_get_set_rss_key(hw, vsi_id, key, true);
 }
 
-/* The i40e_ptype_lookup table is used to convert from the 8-bit ptype in the
- * hardware to a bit-field that can be used by SW to more easily determine the
- * packet type.
- *
- * Macros are used to shorten the table lines and make this table human
- * readable.
- *
- * We store the PTYPE in the top byte of the bit field - this is just so that
- * we can check that the table doesn't have a row missing, as the index into
- * the table should be the PTYPE.
- *
- * Typical work flow:
- *
- * IF NOT i40e_ptype_lookup[ptype].known
- * THEN
- *      Packet is unknown
- * ELSE IF i40e_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP
- *      Use the rest of the fields to look at the tunnels, inner protocols, etc
- * ELSE
- *      Use the enum i40e_rx_l2_ptype to decode the packet type
- * ENDIF
- */
-
-/* macro to make the table lines short, use explicit indexing with [PTYPE] */
-#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	[PTYPE] = { \
-		1, \
-		I40E_RX_PTYPE_OUTER_##OUTER_IP, \
-		I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \
-		I40E_RX_PTYPE_##OUTER_FRAG, \
-		I40E_RX_PTYPE_TUNNEL_##T, \
-		I40E_RX_PTYPE_TUNNEL_END_##TE, \
-		I40E_RX_PTYPE_##TEF, \
-		I40E_RX_PTYPE_INNER_PROT_##I, \
-		I40E_RX_PTYPE_PAYLOAD_LAYER_##PL }
-
-#define I40E_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-
-/* shorter macros makes the table fit but are terse */
-#define I40E_RX_PTYPE_NOF		I40E_RX_PTYPE_NOT_FRAG
-#define I40E_RX_PTYPE_FRG		I40E_RX_PTYPE_FRAG
-#define I40E_RX_PTYPE_INNER_PROT_TS	I40E_RX_PTYPE_INNER_PROT_TIMESYNC
-
-/* Lookup table mapping in the 8-bit HW PTYPE to the bit field for decoding */
-struct i40e_rx_ptype_decoded i40e_ptype_lookup[BIT(8)] = {
-	/* L2 Packet types */
-	I40E_PTT_UNUSED_ENTRY(0),
-	I40E_PTT(1,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	I40E_PTT(2,  L2, NONE, NOF, NONE, NONE, NOF, TS,   PAY2),
-	I40E_PTT(3,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	I40E_PTT_UNUSED_ENTRY(4),
-	I40E_PTT_UNUSED_ENTRY(5),
-	I40E_PTT(6,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	I40E_PTT(7,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	I40E_PTT_UNUSED_ENTRY(8),
-	I40E_PTT_UNUSED_ENTRY(9),
-	I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-
-	/* Non Tunneled IPv4 */
-	I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(25),
-	I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(32),
-	I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(39),
-	I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(47),
-	I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(54),
-	I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(62),
-	I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(69),
-	I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(77),
-	I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(84),
-	I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(91),
-	I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	I40E_PTT(95,  IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(96,  IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(97,  IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(98),
-	I40E_PTT(99,  IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(105),
-	I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(113),
-	I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(120),
-	I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(128),
-	I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(135),
-	I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(143),
-	I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	I40E_PTT_UNUSED_ENTRY(150),
-	I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* unused entries */
-	[154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-};
-
 /**
  * i40e_init_shared_code - Initialize the shared code
  * @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
index 2f53f0f53bc3..daa9f2c42f70 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -407,8 +407,9 @@ static int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
  **/
 static int i40e_ddp_restore(struct i40e_pf *pf)
 {
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
+	struct net_device *netdev = vsi->netdev;
 	struct i40e_ddp_old_profile_list *entry;
-	struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev;
 	int status = 0;
 
 	if (!list_empty(&pf->ddp_old_prof)) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index f9ba45f596c9..abf624d770e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -53,6 +53,7 @@ static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer,
 				     size_t count, loff_t *ppos)
 {
 	struct i40e_pf *pf = filp->private_data;
+	struct i40e_vsi *main_vsi;
 	int bytes_not_copied;
 	int buf_size = 256;
 	char *buf;
@@ -68,8 +69,8 @@ static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer,
 	if (!buf)
 		return -ENOSPC;
 
-	len = snprintf(buf, buf_size, "%s: %s\n",
-		       pf->vsi[pf->lan_vsi]->netdev->name,
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
 		       i40e_dbg_command_buf);
 
 	bytes_not_copied = copy_to_user(buffer, buf, len);
@@ -128,7 +129,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 		dev_info(&pf->pdev->dev,
 			 "    state[%d] = %08lx\n",
 			 i, vsi->state[i]);
-	if (vsi == pf->vsi[pf->lan_vsi])
+	if (vsi->type == I40E_VSI_MAIN)
 		dev_info(&pf->pdev->dev, "    MAC address: %pM Port MAC: %pM\n",
 			 pf->hw.mac.addr,
 			 pf->hw.mac.port_addr);
@@ -786,7 +787,8 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		cnt = sscanf(&cmd_buf[7], "%i", &vsi_seid);
 		if (cnt == 0) {
 			/* default to PF VSI */
-			vsi_seid = pf->vsi[pf->lan_vsi]->seid;
+			vsi = i40e_pf_get_main_vsi(pf);
+			vsi_seid = vsi->seid;
 		} else if (vsi_seid < 0) {
 			dev_info(&pf->pdev->dev, "add VSI %d: bad vsi seid\n",
 				 vsi_seid);
@@ -867,7 +869,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			goto command_write_done;
 		}
 
-		veb = i40e_veb_setup(pf, 0, uplink_seid, vsi_seid, enabled_tc);
+		veb = i40e_veb_setup(pf, uplink_seid, vsi_seid, enabled_tc);
 		if (veb)
 			dev_info(&pf->pdev->dev, "added relay %d\n", veb->seid);
 		else
@@ -1030,7 +1032,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 				goto command_write_done;
 			}
 
-			vsi = pf->vsi[pf->lan_vsi];
+			vsi = i40e_pf_get_main_vsi(pf);
 			switch_id =
 				le16_to_cpu(vsi->info.switch_id) &
 					    I40E_AQ_VSI_SW_ID_MASK;
@@ -1380,6 +1382,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		dev_info(&pf->pdev->dev, "FD current total filter count for this interface: %d\n",
 			 i40e_get_current_fd_count(pf));
 	} else if (strncmp(cmd_buf, "lldp", 4) == 0) {
+		/* Get main VSI */
+		struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
+
 		if (strncmp(&cmd_buf[5], "stop", 4) == 0) {
 			int ret;
 
@@ -1391,10 +1396,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 				goto command_write_done;
 			}
 			ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
-						pf->hw.mac.addr,
-						ETH_P_LLDP, 0,
-						pf->vsi[pf->lan_vsi]->seid,
-						0, true, NULL, NULL);
+						pf->hw.mac.addr, ETH_P_LLDP, 0,
+						main_vsi->seid, 0, true, NULL,
+						NULL);
 			if (ret) {
 				dev_info(&pf->pdev->dev,
 					"%s: Add Control Packet Filter AQ command failed =0x%x\n",
@@ -1409,10 +1413,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			int ret;
 
 			ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
-						pf->hw.mac.addr,
-						ETH_P_LLDP, 0,
-						pf->vsi[pf->lan_vsi]->seid,
-						0, false, NULL, NULL);
+						pf->hw.mac.addr, ETH_P_LLDP, 0,
+						main_vsi->seid, 0, false, NULL,
+						NULL);
 			if (ret) {
 				dev_info(&pf->pdev->dev,
 					"%s: Remove Control Packet Filter AQ command failed =0x%x\n",
@@ -1639,6 +1642,7 @@ static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
 					size_t count, loff_t *ppos)
 {
 	struct i40e_pf *pf = filp->private_data;
+	struct i40e_vsi *main_vsi;
 	int bytes_not_copied;
 	int buf_size = 256;
 	char *buf;
@@ -1654,8 +1658,8 @@ static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
 	if (!buf)
 		return -ENOSPC;
 
-	len = snprintf(buf, buf_size, "%s: %s\n",
-		       pf->vsi[pf->lan_vsi]->netdev->name,
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
 		       i40e_dbg_netdev_ops_buf);
 
 	bytes_not_copied = copy_to_user(buffer, buf, len);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 42e7e6cdaa6d..4e28785c9fb2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1241,7 +1241,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 		i40e_partition_setting_complaint(pf);
 		return -EOPNOTSUPP;
 	}
-	if (vsi != pf->vsi[pf->lan_vsi])
+	if (vsi->type != I40E_VSI_MAIN)
 		return -EOPNOTSUPP;
 	if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET &&
 	    hw->phy.media_type != I40E_MEDIA_TYPE_FIBER &&
@@ -1710,7 +1710,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
-	if (vsi != pf->vsi[pf->lan_vsi])
+	if (vsi->type != I40E_VSI_MAIN)
 		return -EOPNOTSUPP;
 
 	is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED;
@@ -2029,7 +2029,7 @@ static void i40e_get_ringparam(struct net_device *netdev,
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 
 	ring->rx_max_pending = i40e_get_max_num_descriptors(pf);
 	ring->tx_max_pending = i40e_get_max_num_descriptors(pf);
@@ -2292,7 +2292,7 @@ static int i40e_get_stats_count(struct net_device *netdev)
 	struct i40e_pf *pf = vsi->back;
 	int stats_len;
 
-	if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1)
+	if (vsi->type == I40E_VSI_MAIN && pf->hw.partition_id == 1)
 		stats_len = I40E_PF_STATS_LEN;
 	else
 		stats_len = I40E_VSI_STATS_LEN;
@@ -2422,17 +2422,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	}
 	rcu_read_unlock();
 
-	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
+	if (vsi->type != I40E_VSI_MAIN || pf->hw.partition_id != 1)
 		goto check_data_pointer;
 
-	veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
-		     (pf->lan_veb < I40E_MAX_VEB) &&
-		     test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags));
+	veb = i40e_pf_get_main_veb(pf);
+	veb_stats = veb && test_bit(I40E_FLAG_VEB_STATS_ENA, pf->flags);
 
-	if (veb_stats) {
-		veb = pf->veb[pf->lan_veb];
+	if (veb_stats)
 		i40e_update_veb_stats(veb);
-	}
 
 	/* If veb stats aren't enabled, pass NULL instead of the veb so that
 	 * we initialize stats to zero and update the data pointer
@@ -2495,7 +2492,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 				      "rx", i);
 	}
 
-	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
+	if (vsi->type != I40E_VSI_MAIN || pf->hw.partition_id != 1)
 		goto check_data_pointer;
 
 	i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
@@ -2792,7 +2789,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 	}
 
-	if (vsi != pf->vsi[pf->lan_vsi])
+	if (vsi->type != I40E_VSI_MAIN)
 		return -EOPNOTSUPP;
 
 	/* NVM bit on means WoL disabled for the port */
@@ -3370,6 +3367,7 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 	struct i40e_rx_flow_userdef userdef = {0};
 	struct i40e_fdir_filter *rule = NULL;
 	struct hlist_node *node2;
+	struct i40e_vsi *vsi;
 	u64 input_set;
 	u16 index;
 
@@ -3493,9 +3491,8 @@ no_input_set:
 		fsp->flow_type |= FLOW_EXT;
 	}
 
-	if (rule->dest_vsi != pf->vsi[pf->lan_vsi]->id) {
-		struct i40e_vsi *vsi;
-
+	vsi = i40e_pf_get_main_vsi(pf);
+	if (rule->dest_vsi != vsi->id) {
 		vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi);
 		if (vsi && vsi->type == I40E_VSI_SRIOV) {
 			/* VFs are zero-indexed by the driver, but ethtool
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ffb9f9f15c52..1f188c052828 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -100,6 +100,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX
 
 MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
+MODULE_IMPORT_NS(LIBIE);
 MODULE_LICENSE("GPL v2");
 
 static struct workqueue_struct *i40e_wq;
@@ -989,7 +990,7 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	ns->tx_dropped = es->tx_discards;
 
 	/* pull in a couple PF stats if this is the main vsi */
-	if (vsi == pf->vsi[pf->lan_vsi]) {
+	if (vsi->type == I40E_VSI_MAIN) {
 		ns->rx_crc_errors = pf->stats.crc_errors;
 		ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes;
 		ns->rx_length_errors = pf->stats.rx_length_errors;
@@ -1234,7 +1235,7 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
 
-	if (vsi == pf->vsi[pf->lan_vsi])
+	if (vsi->type == I40E_VSI_MAIN)
 		i40e_update_pf_stats(pf);
 
 	i40e_update_vsi_stats(vsi);
@@ -2475,12 +2476,12 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name,
  **/
 static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_hw *hw = &pf->hw;
 	int aq_ret;
 
 	if (vsi->type == I40E_VSI_MAIN &&
-	    pf->lan_veb != I40E_NO_VEB &&
+	    i40e_pf_get_main_veb(pf) &&
 	    !test_bit(I40E_FLAG_MFP_ENA, pf->flags)) {
 		/* set defport ON for Main VSI instead of true promisc
 		 * this way we will get all unicast/multicast and VLAN
@@ -2960,7 +2961,7 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	if (netif_running(netdev))
 		i40e_vsi_reinit_locked(vsi);
 	set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
@@ -4322,7 +4323,7 @@ static irqreturn_t i40e_intr(int irq, void *data)
 
 	/* only q0 is used in MSI/Legacy mode, and none are used in MSIX */
 	if (icr0 & I40E_PFINT_ICR0_QUEUE_0_MASK) {
-		struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+		struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 		struct i40e_q_vector *q_vector = vsi->q_vectors[0];
 
 		/* We do not have a way to disarm Queue causes while leaving
@@ -5472,7 +5473,7 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg)
  **/
 static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	u8 num_tc = vsi->mqprio_qopt.qopt.num_tc;
 	u8 enabled_tc = 1, i;
 
@@ -5489,13 +5490,14 @@ static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf)
  **/
 static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 {
-	struct i40e_hw *hw = &pf->hw;
 	u8 i, enabled_tc = 1;
 	u8 num_tc = 0;
-	struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
 
-	if (i40e_is_tc_mqprio_enabled(pf))
-		return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc;
+	if (i40e_is_tc_mqprio_enabled(pf)) {
+		struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
+
+		return vsi->mqprio_qopt.qopt.num_tc;
+	}
 
 	/* If neither MQPRIO nor DCB is enabled, then always use single TC */
 	if (!test_bit(I40E_FLAG_DCB_ENA, pf->flags))
@@ -5503,7 +5505,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 
 	/* SFP mode will be enabled for all TCs on port */
 	if (!test_bit(I40E_FLAG_MFP_ENA, pf->flags))
-		return i40e_dcb_get_num_tc(dcbcfg);
+		return i40e_dcb_get_num_tc(&pf->hw.local_dcbx_config);
 
 	/* MFP mode return count of enabled TCs for this PF */
 	if (pf->hw.func_caps.iscsi)
@@ -5916,6 +5918,28 @@ out:
 }
 
 /**
+ * i40e_vsi_reconfig_tc - Reconfigure VSI Tx Scheduler for stored TC map
+ * @vsi: VSI to be reconfigured
+ *
+ * This reconfigures a particular VSI for TCs that are mapped to the
+ * TC bitmap stored previously for the VSI.
+ *
+ * Context: It is expected that the VSI queues have been quisced before
+ *          calling this function.
+ *
+ * Return: 0 on success, negative value on failure
+ **/
+static int i40e_vsi_reconfig_tc(struct i40e_vsi *vsi)
+{
+	u8 enabled_tc;
+
+	enabled_tc = vsi->tc_config.enabled_tc;
+	vsi->tc_config.enabled_tc = 0;
+
+	return i40e_vsi_config_tc(vsi, enabled_tc);
+}
+
+/**
  * i40e_get_link_speed - Returns link speed for the interface
  * @vsi: VSI to be configured
  *
@@ -6477,6 +6501,7 @@ static inline int i40e_setup_hw_channel(struct i40e_pf *pf,
 static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi,
 			       struct i40e_channel *ch)
 {
+	struct i40e_vsi *main_vsi;
 	u8 vsi_type;
 	u16 seid;
 	int ret;
@@ -6490,7 +6515,8 @@ static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi,
 	}
 
 	/* underlying switching element */
-	seid = pf->vsi[pf->lan_vsi]->uplink_seid;
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	seid = main_vsi->uplink_seid;
 
 	/* create channel (VSI), configure TX rings */
 	ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type);
@@ -6808,7 +6834,7 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 		/* - Enable all TCs for the LAN VSI
 		 * - For all others keep them at TC0 for now
 		 */
-		if (v == pf->lan_vsi)
+		if (vsi->type == I40E_VSI_MAIN)
 			tc_map = i40e_pf_get_tc_map(pf);
 		else
 			tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
@@ -7047,7 +7073,9 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg)
 
 	/* Configure Rx Packet Buffers in HW */
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-		mfs_tc[i] = pf->vsi[pf->lan_vsi]->netdev->mtu;
+		struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
+
+		mfs_tc[i] = main_vsi->netdev->mtu;
 		mfs_tc[i] += I40E_PACKET_HDR_PAD;
 	}
 
@@ -8643,6 +8671,10 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 
 		flow_rule_match_control(rule, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
@@ -9113,7 +9145,7 @@ err_setup_rx:
 	i40e_vsi_free_rx_resources(vsi);
 err_setup_tx:
 	i40e_vsi_free_tx_resources(vsi);
-	if (vsi == pf->vsi[pf->lan_vsi])
+	if (vsi->type == I40E_VSI_MAIN)
 		i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
 
 	return err;
@@ -9804,7 +9836,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 		dev_warn(&pf->pdev->dev, "FD table did not flush, needs more time\n");
 	} else {
 		/* replay sideband filters */
-		i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
+		i40e_fdir_filter_restore(i40e_pf_get_main_vsi(pf));
 		if (!disable_atr && !pf->fd_tcp4_filter_cnt)
 			clear_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state);
 		clear_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
@@ -9902,7 +9934,8 @@ static void i40e_veb_link_event(struct i40e_veb *veb, bool link_up)
  **/
 static void i40e_link_event(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
+	struct i40e_veb *veb = i40e_pf_get_main_veb(pf);
 	u8 new_link_speed, old_link_speed;
 	bool new_link, old_link;
 	int status;
@@ -9942,8 +9975,8 @@ static void i40e_link_event(struct i40e_pf *pf)
 	/* Notify the base of the switch tree connected to
 	 * the link.  Floating VEBs are not notified.
 	 */
-	if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
-		i40e_veb_link_event(pf->veb[pf->lan_veb], new_link);
+	if (veb)
+		i40e_veb_link_event(veb, new_link);
 	else
 		i40e_vsi_link_event(vsi, new_link);
 
@@ -10273,7 +10306,7 @@ static void i40e_verify_eeprom(struct i40e_pf *pf)
  **/
 static void i40e_enable_pf_switch_lb(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_vsi_context ctxt;
 	int ret;
 
@@ -10309,7 +10342,7 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf)
  **/
 static void i40e_disable_pf_switch_lb(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_vsi_context ctxt;
 	int ret;
 
@@ -10385,7 +10418,7 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 
 	if (veb->uplink_seid == pf->mac_seid) {
 		/* Check that the LAN VSI has VEB owning flag set */
-		ctl_vsi = pf->vsi[pf->lan_vsi];
+		ctl_vsi = i40e_pf_get_main_vsi(pf);
 
 		if (WARN_ON(ctl_vsi->veb_idx != veb->idx ||
 			    !(ctl_vsi->flags & I40E_VSI_FLAG_VEB_OWNER))) {
@@ -10528,7 +10561,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi);
  **/
 static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi;
+	struct i40e_vsi *main_vsi, *vsi;
 
 	/* quick workaround for an NVM issue that leaves a critical register
 	 * uninitialized
@@ -10553,8 +10586,8 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 
 	/* create a new VSI if none exists */
 	if (!vsi) {
-		vsi = i40e_vsi_setup(pf, I40E_VSI_FDIR,
-				     pf->vsi[pf->lan_vsi]->seid, 0);
+		main_vsi = i40e_pf_get_main_vsi(pf);
+		vsi = i40e_vsi_setup(pf, I40E_VSI_FDIR, main_vsi->seid, 0);
 		if (!vsi) {
 			dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
 			clear_bit(I40E_FLAG_FD_SB_ENA, pf->flags);
@@ -10833,7 +10866,7 @@ static int i40e_reset(struct i40e_pf *pf)
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
 	const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf);
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_veb *veb;
 	int ret;
@@ -10842,7 +10875,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 
 	if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
 	    is_recovery_mode_reported)
-		i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
+		i40e_set_ethtool_ops(vsi->netdev);
 
 	if (test_bit(__I40E_DOWN, pf->state) &&
 	    !test_bit(__I40E_RECOVERY_MODE, pf->state))
@@ -11266,7 +11299,7 @@ static void i40e_service_task(struct work_struct *work)
 		return;
 
 	if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) {
-		i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
+		i40e_detect_recover_hung(pf);
 		i40e_sync_filters_subtask(pf);
 		i40e_reset_subtask(pf);
 		i40e_handle_mdd_event(pf);
@@ -11275,14 +11308,12 @@ static void i40e_service_task(struct work_struct *work)
 		i40e_fdir_reinit_subtask(pf);
 		if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
 			/* Client subtask will reopen next time through. */
-			i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi],
-							   true);
+			i40e_notify_client_of_netdev_close(pf, true);
 		} else {
 			i40e_client_subtask(pf);
 			if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
 					       pf->state))
-				i40e_notify_client_of_l2_param_changes(
-								pf->vsi[pf->lan_vsi]);
+				i40e_notify_client_of_l2_param_changes(pf);
 		}
 		i40e_sync_filters_subtask(pf);
 	} else {
@@ -11990,7 +12021,7 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
 	/* if not MSIX, give the one vector only to the LAN VSI */
 	if (test_bit(I40E_FLAG_MSIX_ENA, pf->flags))
 		num_q_vectors = vsi->num_q_vectors;
-	else if (vsi == pf->vsi[pf->lan_vsi])
+	else if (vsi->type == I40E_VSI_MAIN)
 		num_q_vectors = 1;
 	else
 		return -EINVAL;
@@ -12396,7 +12427,7 @@ void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut,
  **/
 static int i40e_pf_config_rss(struct i40e_pf *pf)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	u8 seed[I40E_HKEY_ARRAY_SIZE];
 	u8 *lut;
 	struct i40e_hw *hw = &pf->hw;
@@ -12468,7 +12499,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
  **/
 int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 {
-	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	int new_rss_size;
 
 	if (!test_bit(I40E_FLAG_RSS_ENA, pf->flags))
@@ -13107,7 +13138,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 	int rem;
 
 	/* Only for PF VSI for now */
-	if (vsi->seid != pf->vsi[pf->lan_vsi]->seid)
+	if (vsi->type != I40E_VSI_MAIN)
 		return -EOPNOTSUPP;
 
 	/* Find the HW bridge for PF VSI */
@@ -13117,20 +13148,16 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		__u16 mode;
-
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
+		__u16 mode = nla_get_u16(attr);
 
-		mode = nla_get_u16(attr);
 		if ((mode != BRIDGE_MODE_VEPA) &&
 		    (mode != BRIDGE_MODE_VEB))
 			return -EINVAL;
 
 		/* Insert a new HW bridge */
 		if (!veb) {
-			veb = i40e_veb_setup(pf, 0, vsi->uplink_seid, vsi->seid,
+			veb = i40e_veb_setup(pf, vsi->uplink_seid, vsi->seid,
 					     vsi->tc_config.enabled_tc);
 			if (veb) {
 				veb->bridge_mode = mode;
@@ -13179,7 +13206,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	struct i40e_veb *veb;
 
 	/* Only for PF VSI for now */
-	if (vsi->seid != pf->vsi[pf->lan_vsi]->seid)
+	if (vsi->type != I40E_VSI_MAIN)
 		return -EOPNOTSUPP;
 
 	/* Find the HW bridge for the PF VSI */
@@ -13761,9 +13788,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 		 * the end, which is 4 bytes long, so force truncation of the
 		 * original name by IFNAMSIZ - 4
 		 */
-		snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d",
-			 IFNAMSIZ - 4,
-			 pf->vsi[pf->lan_vsi]->netdev->name);
+		struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
+
+		snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d", IFNAMSIZ - 4,
+			 main_vsi->netdev->name);
 		eth_random_addr(mac_addr);
 
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -14130,8 +14158,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 			 vsi->seid, vsi->uplink_seid);
 		return -ENODEV;
 	}
-	if (vsi == pf->vsi[pf->lan_vsi] &&
-	    !test_bit(__I40E_DOWN, pf->state)) {
+	if (vsi->type == I40E_VSI_MAIN && !test_bit(__I40E_DOWN, pf->state)) {
 		dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
 		return -ENODEV;
 	}
@@ -14275,9 +14302,9 @@ vector_setup_out:
  **/
 static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 {
+	struct i40e_vsi *main_vsi;
 	u16 alloc_queue_pairs;
 	struct i40e_pf *pf;
-	u8 enabled_tc;
 	int ret;
 
 	if (!vsi)
@@ -14309,10 +14336,10 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 	/* Update the FW view of the VSI. Force a reset of TC and queue
 	 * layout configurations.
 	 */
-	enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc;
-	pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
-	pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
-	i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	main_vsi->seid = pf->main_vsi_seid;
+	i40e_vsi_reconfig_tc(main_vsi);
+
 	if (vsi->type == I40E_VSI_MAIN)
 		i40e_rm_default_mac_filter(vsi, pf->hw.mac.perm_addr);
 
@@ -14386,13 +14413,13 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 		}
 
 		if (vsi->uplink_seid == pf->mac_seid)
-			veb = i40e_veb_setup(pf, 0, pf->mac_seid, vsi->seid,
+			veb = i40e_veb_setup(pf, pf->mac_seid, vsi->seid,
 					     vsi->tc_config.enabled_tc);
 		else if ((vsi->flags & I40E_VSI_FLAG_VEB_OWNER) == 0)
-			veb = i40e_veb_setup(pf, 0, vsi->uplink_seid, vsi->seid,
+			veb = i40e_veb_setup(pf, vsi->uplink_seid, vsi->seid,
 					     vsi->tc_config.enabled_tc);
 		if (veb) {
-			if (vsi->seid != pf->vsi[pf->lan_vsi]->seid) {
+			if (vsi->type != I40E_VSI_MAIN) {
 				dev_info(&vsi->back->pdev->dev,
 					 "New VSI creation error, uplink seid of LAN VSI expected.\n");
 				return NULL;
@@ -14783,7 +14810,6 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
 /**
  * i40e_veb_setup - Set up a VEB
  * @pf: board private structure
- * @flags: VEB setup flags
  * @uplink_seid: the switch element to link to
  * @vsi_seid: the initial VSI seid
  * @enabled_tc: Enabled TC bit-map
@@ -14796,9 +14822,8 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi)
  * Returns pointer to the successfully allocated VEB sw struct on
  * success, otherwise returns NULL on failure.
  **/
-struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags,
-				u16 uplink_seid, u16 vsi_seid,
-				u8 enabled_tc)
+struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 uplink_seid,
+				u16 vsi_seid, u8 enabled_tc)
 {
 	struct i40e_vsi *vsi = NULL;
 	struct i40e_veb *veb;
@@ -14829,7 +14854,6 @@ struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags,
 	if (veb_idx < 0)
 		goto err_alloc;
 	veb = pf->veb[veb_idx];
-	veb->flags = flags;
 	veb->uplink_seid = uplink_seid;
 	veb->enabled_tc = (enabled_tc ? enabled_tc : 0x1);
 
@@ -14881,7 +14905,8 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
 		/* Main VEB? */
 		if (uplink_seid != pf->mac_seid)
 			break;
-		if (pf->lan_veb >= I40E_MAX_VEB) {
+		veb = i40e_pf_get_main_veb(pf);
+		if (!veb) {
 			int v;
 
 			/* find existing or else empty VEB */
@@ -14895,12 +14920,15 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
 				pf->lan_veb = v;
 			}
 		}
-		if (pf->lan_veb >= I40E_MAX_VEB)
+
+		/* Try to get again main VEB as pf->lan_veb may have changed */
+		veb = i40e_pf_get_main_veb(pf);
+		if (!veb)
 			break;
 
-		pf->veb[pf->lan_veb]->seid = seid;
-		pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid;
-		pf->veb[pf->lan_veb]->pf = pf;
+		veb->seid = seid;
+		veb->uplink_seid = pf->mac_seid;
+		veb->pf = pf;
 		break;
 	case I40E_SWITCH_ELEMENT_TYPE_VSI:
 		if (num_reported != 1)
@@ -14998,6 +15026,7 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig)
  **/
 static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
+	struct i40e_vsi *main_vsi;
 	u16 flags = 0;
 	int ret;
 
@@ -15042,22 +15071,25 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 	}
 
 	/* first time setup */
-	if (pf->lan_vsi == I40E_NO_VSI || reinit) {
-		struct i40e_vsi *vsi = NULL;
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	if (!main_vsi || reinit) {
+		struct i40e_veb *veb;
 		u16 uplink_seid;
 
 		/* Set up the PF VSI associated with the PF's main VSI
 		 * that is already in the HW switch
 		 */
-		if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
-			uplink_seid = pf->veb[pf->lan_veb]->seid;
+		veb = i40e_pf_get_main_veb(pf);
+		if (veb)
+			uplink_seid = veb->seid;
 		else
 			uplink_seid = pf->mac_seid;
-		if (pf->lan_vsi == I40E_NO_VSI)
-			vsi = i40e_vsi_setup(pf, I40E_VSI_MAIN, uplink_seid, 0);
+		if (!main_vsi)
+			main_vsi = i40e_vsi_setup(pf, I40E_VSI_MAIN,
+						  uplink_seid, 0);
 		else if (reinit)
-			vsi = i40e_vsi_reinit_setup(pf->vsi[pf->lan_vsi]);
-		if (!vsi) {
+			main_vsi = i40e_vsi_reinit_setup(main_vsi);
+		if (!main_vsi) {
 			dev_info(&pf->pdev->dev, "setup of MAIN VSI failed\n");
 			i40e_cloud_filter_exit(pf);
 			i40e_fdir_teardown(pf);
@@ -15065,13 +15097,10 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 		}
 	} else {
 		/* force a reset of TC and queue layout configurations */
-		u8 enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc;
-
-		pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
-		pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
-		i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
+		main_vsi->seid = pf->main_vsi_seid;
+		i40e_vsi_reconfig_tc(main_vsi);
 	}
-	i40e_vlan_stripping_disable(pf->vsi[pf->lan_vsi]);
+	i40e_vlan_stripping_disable(main_vsi);
 
 	i40e_fdir_sb_setup(pf);
 
@@ -15098,7 +15127,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 		rtnl_lock();
 
 	/* repopulate tunnel port filters */
-	udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev);
+	udp_tunnel_nic_reset_ntf(main_vsi->netdev);
 
 	if (!lock_acquired)
 		rtnl_unlock();
@@ -15242,6 +15271,7 @@ static int i40e_setup_pf_filter_control(struct i40e_pf *pf)
 #define REMAIN(__x) (INFO_STRING_LEN - (__x))
 static void i40e_print_features(struct i40e_pf *pf)
 {
+	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_hw *hw = &pf->hw;
 	char *buf;
 	int i;
@@ -15255,8 +15285,7 @@ static void i40e_print_features(struct i40e_pf *pf)
 	i += scnprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs);
 #endif
 	i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
-		      pf->hw.func_caps.num_vsis,
-		      pf->vsi[pf->lan_vsi]->num_queue_pairs);
+		       pf->hw.func_caps.num_vsis, main_vsi->num_queue_pairs);
 	if (test_bit(I40E_FLAG_RSS_ENA, pf->flags))
 		i += scnprintf(&buf[i], REMAIN(i), " RSS");
 	if (test_bit(I40E_FLAG_FD_ATR_ENA, pf->flags))
@@ -15920,7 +15949,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
 		goto err_vsis;
 	}
-	INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list);
+
+	vsi = i40e_pf_get_main_vsi(pf);
+	INIT_LIST_HEAD(&vsi->ch_list);
 
 	/* if FDIR VSI was set up, start it now */
 	vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR);
@@ -16223,7 +16254,7 @@ static void i40e_remove(struct pci_dev *pdev)
 	/* Client close must be called explicitly here because the timer
 	 * has been stopped.
 	 */
-	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+	i40e_notify_client_of_netdev_close(pf, false);
 
 	i40e_fdir_teardown(pf);
 
@@ -16422,15 +16453,15 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
  **/
 static void i40e_enable_mc_magic_wake(struct i40e_pf *pf)
 {
+	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_hw *hw = &pf->hw;
 	u8 mac_addr[6];
 	u16 flags = 0;
 	int ret;
 
 	/* Get current MAC address in case it's an LAA */
-	if (pf->vsi[pf->lan_vsi] && pf->vsi[pf->lan_vsi]->netdev) {
-		ether_addr_copy(mac_addr,
-				pf->vsi[pf->lan_vsi]->netdev->dev_addr);
+	if (main_vsi && main_vsi->netdev) {
+		ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr);
 	} else {
 		dev_err(&pf->pdev->dev,
 			"Failed to retrieve MAC address; using default\n");
@@ -16482,7 +16513,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	/* Client close must be called explicitly here because the timer
 	 * has been stopped.
 	 */
-	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+	i40e_notify_client_of_netdev_close(pf, false);
 
 	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
 	    pf->wol_en)
@@ -16518,7 +16549,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
  * i40e_suspend - PM callback for moving to D3
  * @dev: generic device information structure
  **/
-static int __maybe_unused i40e_suspend(struct device *dev)
+static int i40e_suspend(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
 	struct i40e_hw *hw = &pf->hw;
@@ -16536,7 +16567,7 @@ static int __maybe_unused i40e_suspend(struct device *dev)
 	/* Client close must be called explicitly here because the timer
 	 * has been stopped.
 	 */
-	i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+	i40e_notify_client_of_netdev_close(pf, false);
 
 	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
 	    pf->wol_en)
@@ -16569,7 +16600,7 @@ static int __maybe_unused i40e_suspend(struct device *dev)
  * i40e_resume - PM callback for waking up from D3
  * @dev: generic device information structure
  **/
-static int __maybe_unused i40e_resume(struct device *dev)
+static int i40e_resume(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
 	int err;
@@ -16615,16 +16646,14 @@ static const struct pci_error_handlers i40e_err_handler = {
 	.resume = i40e_pci_error_resume,
 };
 
-static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume);
 
 static struct pci_driver i40e_driver = {
 	.name     = i40e_driver_name,
 	.id_table = i40e_pci_tbl,
 	.probe    = i40e_probe,
 	.remove   = i40e_remove,
-	.driver   = {
-		.pm = &i40e_pm_ops,
-	},
+	.driver.pm = pm_sleep_ptr(&i40e_pm_ops),
 	.shutdown = i40e_shutdown,
 	.err_handler = &i40e_err_handler,
 	.sriov_configure = i40e_pci_sriov_configure,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 605fd82f5d20..7f0936f4e05e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -734,37 +734,7 @@ int i40e_validate_nvm_checksum(struct i40e_hw *hw,
 	return ret_code;
 }
 
-static int i40e_nvmupd_state_init(struct i40e_hw *hw,
-				  struct i40e_nvm_access *cmd,
-				  u8 *bytes, int *perrno);
-static int i40e_nvmupd_state_reading(struct i40e_hw *hw,
-				     struct i40e_nvm_access *cmd,
-				     u8 *bytes, int *perrno);
-static int i40e_nvmupd_state_writing(struct i40e_hw *hw,
-				     struct i40e_nvm_access *cmd,
-				     u8 *bytes, int *errno);
-static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw,
-						struct i40e_nvm_access *cmd,
-						int *perrno);
-static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw,
-				 struct i40e_nvm_access *cmd,
-				 int *perrno);
-static int i40e_nvmupd_nvm_write(struct i40e_hw *hw,
-				 struct i40e_nvm_access *cmd,
-				 u8 *bytes, int *perrno);
-static int i40e_nvmupd_nvm_read(struct i40e_hw *hw,
-				struct i40e_nvm_access *cmd,
-				u8 *bytes, int *perrno);
-static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
-			       struct i40e_nvm_access *cmd,
-			       u8 *bytes, int *perrno);
-static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
-				     struct i40e_nvm_access *cmd,
-				     u8 *bytes, int *perrno);
-static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw,
-				    struct i40e_nvm_access *cmd,
-				    u8 *bytes, int *perrno);
-static inline u8 i40e_nvmupd_get_module(u32 val)
+static u8 i40e_nvmupd_get_module(u32 val)
 {
 	return (u8)(val & I40E_NVM_MOD_PNT_MASK);
 }
@@ -799,121 +769,408 @@ static const char * const i40e_nvm_update_state_str[] = {
 };
 
 /**
- * i40e_nvmupd_command - Process an NVM update command
+ * i40e_nvmupd_validate_command - Validate given command
  * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command
- * @bytes: pointer to the data buffer
+ * @cmd: pointer to nvm update command buffer
  * @perrno: pointer to return error code
  *
- * Dispatches command depending on what update state is current
+ * Return one of the valid command types or I40E_NVMUPD_INVALID
  **/
-int i40e_nvmupd_command(struct i40e_hw *hw,
-			struct i40e_nvm_access *cmd,
-			u8 *bytes, int *perrno)
+static enum i40e_nvmupd_cmd
+i40e_nvmupd_validate_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd,
+			     int *perrno)
 {
 	enum i40e_nvmupd_cmd upd_cmd;
-	int status;
-
-	/* assume success */
-	*perrno = 0;
+	u8 module, transaction;
 
-	/* early check for status command and debug msgs */
-	upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno);
+	/* anything that doesn't match a recognized case is an error */
+	upd_cmd = I40E_NVMUPD_INVALID;
 
-	i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d opc 0x%04x cmd 0x%08x config 0x%08x offset 0x%08x data_size 0x%08x\n",
-		   i40e_nvm_update_state_str[upd_cmd],
-		   hw->nvmupd_state,
-		   hw->nvm_release_on_done, hw->nvm_wait_opcode,
-		   cmd->command, cmd->config, cmd->offset, cmd->data_size);
+	transaction = i40e_nvmupd_get_transaction(cmd->config);
+	module = i40e_nvmupd_get_module(cmd->config);
 
-	if (upd_cmd == I40E_NVMUPD_INVALID) {
-		*perrno = -EFAULT;
+	/* limits on data size */
+	if (cmd->data_size < 1 || cmd->data_size > I40E_NVMUPD_MAX_DATA) {
 		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_validate_command returns %d errno %d\n",
-			   upd_cmd, *perrno);
+			   "%s data_size %d\n", __func__, cmd->data_size);
+		*perrno = -EFAULT;
+		return I40E_NVMUPD_INVALID;
 	}
 
-	/* a status request returns immediately rather than
-	 * going into the state machine
-	 */
-	if (upd_cmd == I40E_NVMUPD_STATUS) {
-		if (!cmd->data_size) {
-			*perrno = -EFAULT;
-			return -EINVAL;
+	switch (cmd->command) {
+	case I40E_NVM_READ:
+		switch (transaction) {
+		case I40E_NVM_CON:
+			upd_cmd = I40E_NVMUPD_READ_CON;
+			break;
+		case I40E_NVM_SNT:
+			upd_cmd = I40E_NVMUPD_READ_SNT;
+			break;
+		case I40E_NVM_LCB:
+			upd_cmd = I40E_NVMUPD_READ_LCB;
+			break;
+		case I40E_NVM_SA:
+			upd_cmd = I40E_NVMUPD_READ_SA;
+			break;
+		case I40E_NVM_EXEC:
+			if (module == 0xf)
+				upd_cmd = I40E_NVMUPD_STATUS;
+			else if (module == 0)
+				upd_cmd = I40E_NVMUPD_GET_AQ_RESULT;
+			break;
+		case I40E_NVM_AQE:
+			upd_cmd = I40E_NVMUPD_GET_AQ_EVENT;
+			break;
 		}
+		break;
 
-		bytes[0] = hw->nvmupd_state;
-
-		if (cmd->data_size >= 4) {
-			bytes[1] = 0;
-			*((u16 *)&bytes[2]) = hw->nvm_wait_opcode;
+	case I40E_NVM_WRITE:
+		switch (transaction) {
+		case I40E_NVM_CON:
+			upd_cmd = I40E_NVMUPD_WRITE_CON;
+			break;
+		case I40E_NVM_SNT:
+			upd_cmd = I40E_NVMUPD_WRITE_SNT;
+			break;
+		case I40E_NVM_LCB:
+			upd_cmd = I40E_NVMUPD_WRITE_LCB;
+			break;
+		case I40E_NVM_SA:
+			upd_cmd = I40E_NVMUPD_WRITE_SA;
+			break;
+		case I40E_NVM_ERA:
+			upd_cmd = I40E_NVMUPD_WRITE_ERA;
+			break;
+		case I40E_NVM_CSUM:
+			upd_cmd = I40E_NVMUPD_CSUM_CON;
+			break;
+		case (I40E_NVM_CSUM | I40E_NVM_SA):
+			upd_cmd = I40E_NVMUPD_CSUM_SA;
+			break;
+		case (I40E_NVM_CSUM | I40E_NVM_LCB):
+			upd_cmd = I40E_NVMUPD_CSUM_LCB;
+			break;
+		case I40E_NVM_EXEC:
+			if (module == 0)
+				upd_cmd = I40E_NVMUPD_EXEC_AQ;
+			break;
 		}
+		break;
+	}
 
-		/* Clear error status on read */
-		if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR)
-			hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+	return upd_cmd;
+}
 
-		return 0;
+/**
+ * i40e_nvmupd_nvm_erase - Erase an NVM module
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @perrno: pointer to return error code
+ *
+ * module, offset, data_size and data are in cmd structure
+ **/
+static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw,
+				 struct i40e_nvm_access *cmd,
+				 int *perrno)
+{
+	struct i40e_asq_cmd_details cmd_details;
+	u8 module, transaction;
+	int status = 0;
+	bool last;
+
+	transaction = i40e_nvmupd_get_transaction(cmd->config);
+	module = i40e_nvmupd_get_module(cmd->config);
+	last = (transaction & I40E_NVM_LCB);
+
+	memset(&cmd_details, 0, sizeof(cmd_details));
+	cmd_details.wb_desc = &hw->nvm_wb_desc;
+
+	status = i40e_aq_erase_nvm(hw, module, cmd->offset, (u16)cmd->data_size,
+				   last, &cmd_details);
+	if (status) {
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s mod 0x%x  off 0x%x len 0x%x\n",
+			   __func__, module, cmd->offset, cmd->data_size);
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s status %d aq %d\n",
+			   __func__, status, hw->aq.asq_last_status);
+		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
 	}
 
-	/* Clear status even it is not read and log */
-	if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) {
+	return status;
+}
+
+/**
+ * i40e_nvmupd_nvm_write - Write NVM
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @bytes: pointer to the data buffer
+ * @perrno: pointer to return error code
+ *
+ * module, offset, data_size and data are in cmd structure
+ **/
+static int i40e_nvmupd_nvm_write(struct i40e_hw *hw,
+				 struct i40e_nvm_access *cmd,
+				 u8 *bytes, int *perrno)
+{
+	struct i40e_asq_cmd_details cmd_details;
+	u8 module, transaction;
+	u8 preservation_flags;
+	int status = 0;
+	bool last;
+
+	transaction = i40e_nvmupd_get_transaction(cmd->config);
+	module = i40e_nvmupd_get_module(cmd->config);
+	last = (transaction & I40E_NVM_LCB);
+	preservation_flags = i40e_nvmupd_get_preservation_flags(cmd->config);
+
+	memset(&cmd_details, 0, sizeof(cmd_details));
+	cmd_details.wb_desc = &hw->nvm_wb_desc;
+
+	status = i40e_aq_update_nvm(hw, module, cmd->offset,
+				    (u16)cmd->data_size, bytes, last,
+				    preservation_flags, &cmd_details);
+	if (status) {
 		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n");
-		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+			   "%s mod 0x%x off 0x%x len 0x%x\n",
+			   __func__, module, cmd->offset, cmd->data_size);
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s status %d aq %d\n",
+			   __func__, status, hw->aq.asq_last_status);
+		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
 	}
 
-	/* Acquire lock to prevent race condition where adminq_task
-	 * can execute after i40e_nvmupd_nvm_read/write but before state
-	 * variables (nvm_wait_opcode, nvm_release_on_done) are updated.
-	 *
-	 * During NVMUpdate, it is observed that lock could be held for
-	 * ~5ms for most commands. However lock is held for ~60ms for
-	 * NVMUPD_CSUM_LCB command.
-	 */
-	mutex_lock(&hw->aq.arq_mutex);
-	switch (hw->nvmupd_state) {
-	case I40E_NVMUPD_STATE_INIT:
-		status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno);
-		break;
+	return status;
+}
 
-	case I40E_NVMUPD_STATE_READING:
-		status = i40e_nvmupd_state_reading(hw, cmd, bytes, perrno);
-		break;
+/**
+ * i40e_nvmupd_nvm_read - Read NVM
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @bytes: pointer to the data buffer
+ * @perrno: pointer to return error code
+ *
+ * cmd structure contains identifiers and data buffer
+ **/
+static int i40e_nvmupd_nvm_read(struct i40e_hw *hw,
+				struct i40e_nvm_access *cmd,
+				u8 *bytes, int *perrno)
+{
+	struct i40e_asq_cmd_details cmd_details;
+	u8 module, transaction;
+	int status;
+	bool last;
 
-	case I40E_NVMUPD_STATE_WRITING:
-		status = i40e_nvmupd_state_writing(hw, cmd, bytes, perrno);
-		break;
+	transaction = i40e_nvmupd_get_transaction(cmd->config);
+	module = i40e_nvmupd_get_module(cmd->config);
+	last = (transaction == I40E_NVM_LCB) || (transaction == I40E_NVM_SA);
 
-	case I40E_NVMUPD_STATE_INIT_WAIT:
-	case I40E_NVMUPD_STATE_WRITE_WAIT:
-		/* if we need to stop waiting for an event, clear
-		 * the wait info and return before doing anything else
-		 */
-		if (cmd->offset == 0xffff) {
-			i40e_nvmupd_clear_wait_state(hw);
-			status = 0;
-			break;
+	memset(&cmd_details, 0, sizeof(cmd_details));
+	cmd_details.wb_desc = &hw->nvm_wb_desc;
+
+	status = i40e_aq_read_nvm(hw, module, cmd->offset, (u16)cmd->data_size,
+				  bytes, last, &cmd_details);
+	if (status) {
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s mod 0x%x  off 0x%x  len 0x%x\n",
+			   __func__, module, cmd->offset, cmd->data_size);
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s status %d aq %d\n",
+			   __func__, status, hw->aq.asq_last_status);
+		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
+	}
+
+	return status;
+}
+
+/**
+ * i40e_nvmupd_exec_aq - Run an AQ command
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @bytes: pointer to the data buffer
+ * @perrno: pointer to return error code
+ *
+ * cmd structure contains identifiers and data buffer
+ **/
+static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
+			       struct i40e_nvm_access *cmd,
+			       u8 *bytes, int *perrno)
+{
+	struct i40e_asq_cmd_details cmd_details;
+	struct i40e_aq_desc *aq_desc;
+	u32 buff_size = 0;
+	u8 *buff = NULL;
+	u32 aq_desc_len;
+	u32 aq_data_len;
+	int status;
+
+	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
+	if (cmd->offset == 0xffff)
+		return 0;
+
+	memset(&cmd_details, 0, sizeof(cmd_details));
+	cmd_details.wb_desc = &hw->nvm_wb_desc;
+
+	aq_desc_len = sizeof(struct i40e_aq_desc);
+	memset(&hw->nvm_wb_desc, 0, aq_desc_len);
+
+	/* get the aq descriptor */
+	if (cmd->data_size < aq_desc_len) {
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n",
+			   cmd->data_size, aq_desc_len);
+		*perrno = -EINVAL;
+		return -EINVAL;
+	}
+	aq_desc = (struct i40e_aq_desc *)bytes;
+
+	/* if data buffer needed, make sure it's ready */
+	aq_data_len = cmd->data_size - aq_desc_len;
+	buff_size = max_t(u32, aq_data_len, le16_to_cpu(aq_desc->datalen));
+	if (buff_size) {
+		if (!hw->nvm_buff.va) {
+			status = i40e_allocate_virt_mem(hw, &hw->nvm_buff,
+							hw->aq.asq_buf_size);
+			if (status)
+				i40e_debug(hw, I40E_DEBUG_NVM,
+					   "NVMUPD: i40e_allocate_virt_mem for exec buff failed, %d\n",
+					   status);
 		}
 
-		status = -EBUSY;
-		*perrno = -EBUSY;
-		break;
+		if (hw->nvm_buff.va) {
+			buff = hw->nvm_buff.va;
+			memcpy(buff, &bytes[aq_desc_len], aq_data_len);
+		}
+	}
 
-	default:
-		/* invalid state, should never happen */
+	if (cmd->offset)
+		memset(&hw->nvm_aq_event_desc, 0, aq_desc_len);
+
+	/* and away we go! */
+	status = i40e_asq_send_command(hw, aq_desc, buff,
+				       buff_size, &cmd_details);
+	if (status) {
 		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "NVMUPD: no such state %d\n", hw->nvmupd_state);
-		status = -EOPNOTSUPP;
-		*perrno = -ESRCH;
-		break;
+			   "%s err %pe aq_err %s\n",
+			   __func__, ERR_PTR(status),
+			   i40e_aq_str(hw, hw->aq.asq_last_status));
+		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
+		return status;
+	}
+
+	/* should we wait for a followup event? */
+	if (cmd->offset) {
+		hw->nvm_wait_opcode = cmd->offset;
+		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT;
 	}
 
-	mutex_unlock(&hw->aq.arq_mutex);
 	return status;
 }
 
 /**
+ * i40e_nvmupd_get_aq_result - Get the results from the previous exec_aq
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @bytes: pointer to the data buffer
+ * @perrno: pointer to return error code
+ *
+ * cmd structure contains identifiers and data buffer
+ **/
+static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
+				     struct i40e_nvm_access *cmd,
+				     u8 *bytes, int *perrno)
+{
+	u32 aq_total_len;
+	u32 aq_desc_len;
+	int remainder;
+	u8 *buff;
+
+	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
+
+	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen);
+
+	/* check offset range */
+	if (cmd->offset > aq_total_len) {
+		i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n",
+			   __func__, cmd->offset, aq_total_len);
+		*perrno = -EINVAL;
+		return -EINVAL;
+	}
+
+	/* check copylength range */
+	if (cmd->data_size > (aq_total_len - cmd->offset)) {
+		int new_len = aq_total_len - cmd->offset;
+
+		i40e_debug(hw, I40E_DEBUG_NVM, "%s: copy length %d too big, trimming to %d\n",
+			   __func__, cmd->data_size, new_len);
+		cmd->data_size = new_len;
+	}
+
+	remainder = cmd->data_size;
+	if (cmd->offset < aq_desc_len) {
+		u32 len = aq_desc_len - cmd->offset;
+
+		len = min(len, cmd->data_size);
+		i40e_debug(hw, I40E_DEBUG_NVM, "%s: aq_desc bytes %d to %d\n",
+			   __func__, cmd->offset, cmd->offset + len);
+
+		buff = ((u8 *)&hw->nvm_wb_desc) + cmd->offset;
+		memcpy(bytes, buff, len);
+
+		bytes += len;
+		remainder -= len;
+		buff = hw->nvm_buff.va;
+	} else {
+		buff = hw->nvm_buff.va + (cmd->offset - aq_desc_len);
+	}
+
+	if (remainder > 0) {
+		int start_byte = buff - (u8 *)hw->nvm_buff.va;
+
+		i40e_debug(hw, I40E_DEBUG_NVM, "%s: databuf bytes %d to %d\n",
+			   __func__, start_byte, start_byte + remainder);
+		memcpy(bytes, buff, remainder);
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_nvmupd_get_aq_event - Get the Admin Queue event from previous exec_aq
+ * @hw: pointer to hardware structure
+ * @cmd: pointer to nvm update command buffer
+ * @bytes: pointer to the data buffer
+ * @perrno: pointer to return error code
+ *
+ * cmd structure contains identifiers and data buffer
+ **/
+static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw,
+				    struct i40e_nvm_access *cmd,
+				    u8 *bytes, int *perrno)
+{
+	u32 aq_total_len;
+	u32 aq_desc_len;
+
+	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
+
+	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen);
+
+	/* check copylength range */
+	if (cmd->data_size > aq_total_len) {
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "%s: copy length %d too big, trimming to %d\n",
+			   __func__, cmd->data_size, aq_total_len);
+		cmd->data_size = aq_total_len;
+	}
+
+	memcpy(bytes, &hw->nvm_aq_event_desc, cmd->data_size);
+
+	return 0;
+}
+
+/**
  * i40e_nvmupd_state_init - Handle NVM update state Init
  * @hw: pointer to hardware structure
  * @cmd: pointer to nvm update command buffer
@@ -937,7 +1194,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno);
 			i40e_release_nvm(hw);
@@ -948,7 +1205,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno);
 			if (status)
@@ -962,7 +1219,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_nvmupd_nvm_erase(hw, cmd, perrno);
 			if (status) {
@@ -979,7 +1236,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno);
 			if (status) {
@@ -996,7 +1253,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno);
 			if (status) {
@@ -1012,7 +1269,7 @@ static int i40e_nvmupd_state_init(struct i40e_hw *hw,
 		status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE);
 		if (status) {
 			*perrno = i40e_aq_rc_to_posix(status,
-						     hw->aq.asq_last_status);
+						      hw->aq.asq_last_status);
 		} else {
 			status = i40e_update_nvm_checksum(hw);
 			if (status) {
@@ -1185,7 +1442,7 @@ retry:
 	 * so here we try to reacquire the semaphore then retry the write.
 	 * We only do one retry, then give up.
 	 */
-	if (status && (hw->aq.asq_last_status == I40E_AQ_RC_EBUSY) &&
+	if (status && hw->aq.asq_last_status == I40E_AQ_RC_EBUSY &&
 	    !retry_attempt) {
 		u32 old_asq_status = hw->aq.asq_last_status;
 		int old_status = status;
@@ -1215,457 +1472,168 @@ retry:
 }
 
 /**
- * i40e_nvmupd_clear_wait_state - clear wait state on hw
- * @hw: pointer to the hardware structure
- **/
-void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw)
-{
-	i40e_debug(hw, I40E_DEBUG_NVM,
-		   "NVMUPD: clearing wait on opcode 0x%04x\n",
-		   hw->nvm_wait_opcode);
-
-	if (hw->nvm_release_on_done) {
-		i40e_release_nvm(hw);
-		hw->nvm_release_on_done = false;
-	}
-	hw->nvm_wait_opcode = 0;
-
-	if (hw->aq.arq_last_status) {
-		hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR;
-		return;
-	}
-
-	switch (hw->nvmupd_state) {
-	case I40E_NVMUPD_STATE_INIT_WAIT:
-		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
-		break;
-
-	case I40E_NVMUPD_STATE_WRITE_WAIT:
-		hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING;
-		break;
-
-	default:
-		break;
-	}
-}
-
-/**
- * i40e_nvmupd_check_wait_event - handle NVM update operation events
- * @hw: pointer to the hardware structure
- * @opcode: the event that just happened
- * @desc: AdminQ descriptor
- **/
-void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
-				  struct i40e_aq_desc *desc)
-{
-	u32 aq_desc_len = sizeof(struct i40e_aq_desc);
-
-	if (opcode == hw->nvm_wait_opcode) {
-		memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len);
-		i40e_nvmupd_clear_wait_state(hw);
-	}
-}
-
-/**
- * i40e_nvmupd_validate_command - Validate given command
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @perrno: pointer to return error code
- *
- * Return one of the valid command types or I40E_NVMUPD_INVALID
- **/
-static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw,
-						 struct i40e_nvm_access *cmd,
-						 int *perrno)
-{
-	enum i40e_nvmupd_cmd upd_cmd;
-	u8 module, transaction;
-
-	/* anything that doesn't match a recognized case is an error */
-	upd_cmd = I40E_NVMUPD_INVALID;
-
-	transaction = i40e_nvmupd_get_transaction(cmd->config);
-	module = i40e_nvmupd_get_module(cmd->config);
-
-	/* limits on data size */
-	if ((cmd->data_size < 1) ||
-	    (cmd->data_size > I40E_NVMUPD_MAX_DATA)) {
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_validate_command data_size %d\n",
-			   cmd->data_size);
-		*perrno = -EFAULT;
-		return I40E_NVMUPD_INVALID;
-	}
-
-	switch (cmd->command) {
-	case I40E_NVM_READ:
-		switch (transaction) {
-		case I40E_NVM_CON:
-			upd_cmd = I40E_NVMUPD_READ_CON;
-			break;
-		case I40E_NVM_SNT:
-			upd_cmd = I40E_NVMUPD_READ_SNT;
-			break;
-		case I40E_NVM_LCB:
-			upd_cmd = I40E_NVMUPD_READ_LCB;
-			break;
-		case I40E_NVM_SA:
-			upd_cmd = I40E_NVMUPD_READ_SA;
-			break;
-		case I40E_NVM_EXEC:
-			if (module == 0xf)
-				upd_cmd = I40E_NVMUPD_STATUS;
-			else if (module == 0)
-				upd_cmd = I40E_NVMUPD_GET_AQ_RESULT;
-			break;
-		case I40E_NVM_AQE:
-			upd_cmd = I40E_NVMUPD_GET_AQ_EVENT;
-			break;
-		}
-		break;
-
-	case I40E_NVM_WRITE:
-		switch (transaction) {
-		case I40E_NVM_CON:
-			upd_cmd = I40E_NVMUPD_WRITE_CON;
-			break;
-		case I40E_NVM_SNT:
-			upd_cmd = I40E_NVMUPD_WRITE_SNT;
-			break;
-		case I40E_NVM_LCB:
-			upd_cmd = I40E_NVMUPD_WRITE_LCB;
-			break;
-		case I40E_NVM_SA:
-			upd_cmd = I40E_NVMUPD_WRITE_SA;
-			break;
-		case I40E_NVM_ERA:
-			upd_cmd = I40E_NVMUPD_WRITE_ERA;
-			break;
-		case I40E_NVM_CSUM:
-			upd_cmd = I40E_NVMUPD_CSUM_CON;
-			break;
-		case (I40E_NVM_CSUM|I40E_NVM_SA):
-			upd_cmd = I40E_NVMUPD_CSUM_SA;
-			break;
-		case (I40E_NVM_CSUM|I40E_NVM_LCB):
-			upd_cmd = I40E_NVMUPD_CSUM_LCB;
-			break;
-		case I40E_NVM_EXEC:
-			if (module == 0)
-				upd_cmd = I40E_NVMUPD_EXEC_AQ;
-			break;
-		}
-		break;
-	}
-
-	return upd_cmd;
-}
-
-/**
- * i40e_nvmupd_exec_aq - Run an AQ command
+ * i40e_nvmupd_command - Process an NVM update command
  * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
+ * @cmd: pointer to nvm update command
  * @bytes: pointer to the data buffer
  * @perrno: pointer to return error code
  *
- * cmd structure contains identifiers and data buffer
+ * Dispatches command depending on what update state is current
  **/
-static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
-			       struct i40e_nvm_access *cmd,
-			       u8 *bytes, int *perrno)
+int i40e_nvmupd_command(struct i40e_hw *hw,
+			struct i40e_nvm_access *cmd,
+			u8 *bytes, int *perrno)
 {
-	struct i40e_asq_cmd_details cmd_details;
-	struct i40e_aq_desc *aq_desc;
-	u32 buff_size = 0;
-	u8 *buff = NULL;
-	u32 aq_desc_len;
-	u32 aq_data_len;
+	enum i40e_nvmupd_cmd upd_cmd;
 	int status;
 
-	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
-	if (cmd->offset == 0xffff)
-		return 0;
+	/* assume success */
+	*perrno = 0;
 
-	memset(&cmd_details, 0, sizeof(cmd_details));
-	cmd_details.wb_desc = &hw->nvm_wb_desc;
+	/* early check for status command and debug msgs */
+	upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno);
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
-	memset(&hw->nvm_wb_desc, 0, aq_desc_len);
+	i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d opc 0x%04x cmd 0x%08x config 0x%08x offset 0x%08x data_size 0x%08x\n",
+		   i40e_nvm_update_state_str[upd_cmd],
+		   hw->nvmupd_state,
+		   hw->nvm_release_on_done, hw->nvm_wait_opcode,
+		   cmd->command, cmd->config, cmd->offset, cmd->data_size);
 
-	/* get the aq descriptor */
-	if (cmd->data_size < aq_desc_len) {
+	if (upd_cmd == I40E_NVMUPD_INVALID) {
+		*perrno = -EFAULT;
 		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n",
-			   cmd->data_size, aq_desc_len);
-		*perrno = -EINVAL;
-		return -EINVAL;
+			   "i40e_nvmupd_validate_command returns %d errno %d\n",
+			   upd_cmd, *perrno);
 	}
-	aq_desc = (struct i40e_aq_desc *)bytes;
 
-	/* if data buffer needed, make sure it's ready */
-	aq_data_len = cmd->data_size - aq_desc_len;
-	buff_size = max_t(u32, aq_data_len, le16_to_cpu(aq_desc->datalen));
-	if (buff_size) {
-		if (!hw->nvm_buff.va) {
-			status = i40e_allocate_virt_mem(hw, &hw->nvm_buff,
-							hw->aq.asq_buf_size);
-			if (status)
-				i40e_debug(hw, I40E_DEBUG_NVM,
-					   "NVMUPD: i40e_allocate_virt_mem for exec buff failed, %d\n",
-					   status);
-		}
-
-		if (hw->nvm_buff.va) {
-			buff = hw->nvm_buff.va;
-			memcpy(buff, &bytes[aq_desc_len], aq_data_len);
+	/* a status request returns immediately rather than
+	 * going into the state machine
+	 */
+	if (upd_cmd == I40E_NVMUPD_STATUS) {
+		if (!cmd->data_size) {
+			*perrno = -EFAULT;
+			return -EINVAL;
 		}
-	}
-
-	if (cmd->offset)
-		memset(&hw->nvm_aq_event_desc, 0, aq_desc_len);
-
-	/* and away we go! */
-	status = i40e_asq_send_command(hw, aq_desc, buff,
-				       buff_size, &cmd_details);
-	if (status) {
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "%s err %pe aq_err %s\n",
-			   __func__, ERR_PTR(status),
-			   i40e_aq_str(hw, hw->aq.asq_last_status));
-		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
-		return status;
-	}
-
-	/* should we wait for a followup event? */
-	if (cmd->offset) {
-		hw->nvm_wait_opcode = cmd->offset;
-		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT;
-	}
-
-	return status;
-}
 
-/**
- * i40e_nvmupd_get_aq_result - Get the results from the previous exec_aq
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @bytes: pointer to the data buffer
- * @perrno: pointer to return error code
- *
- * cmd structure contains identifiers and data buffer
- **/
-static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
-				     struct i40e_nvm_access *cmd,
-				     u8 *bytes, int *perrno)
-{
-	u32 aq_total_len;
-	u32 aq_desc_len;
-	int remainder;
-	u8 *buff;
-
-	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
-
-	aq_desc_len = sizeof(struct i40e_aq_desc);
-	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen);
+		bytes[0] = hw->nvmupd_state;
 
-	/* check offset range */
-	if (cmd->offset > aq_total_len) {
-		i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n",
-			   __func__, cmd->offset, aq_total_len);
-		*perrno = -EINVAL;
-		return -EINVAL;
-	}
+		if (cmd->data_size >= 4) {
+			bytes[1] = 0;
+			*((u16 *)&bytes[2]) = hw->nvm_wait_opcode;
+		}
 
-	/* check copylength range */
-	if (cmd->data_size > (aq_total_len - cmd->offset)) {
-		int new_len = aq_total_len - cmd->offset;
+		/* Clear error status on read */
+		if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR)
+			hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
 
-		i40e_debug(hw, I40E_DEBUG_NVM, "%s: copy length %d too big, trimming to %d\n",
-			   __func__, cmd->data_size, new_len);
-		cmd->data_size = new_len;
+		return 0;
 	}
 
-	remainder = cmd->data_size;
-	if (cmd->offset < aq_desc_len) {
-		u32 len = aq_desc_len - cmd->offset;
-
-		len = min(len, cmd->data_size);
-		i40e_debug(hw, I40E_DEBUG_NVM, "%s: aq_desc bytes %d to %d\n",
-			   __func__, cmd->offset, cmd->offset + len);
-
-		buff = ((u8 *)&hw->nvm_wb_desc) + cmd->offset;
-		memcpy(bytes, buff, len);
-
-		bytes += len;
-		remainder -= len;
-		buff = hw->nvm_buff.va;
-	} else {
-		buff = hw->nvm_buff.va + (cmd->offset - aq_desc_len);
+	/* Clear status even it is not read and log */
+	if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) {
+		i40e_debug(hw, I40E_DEBUG_NVM,
+			   "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n");
+		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
 	}
 
-	if (remainder > 0) {
-		int start_byte = buff - (u8 *)hw->nvm_buff.va;
-
-		i40e_debug(hw, I40E_DEBUG_NVM, "%s: databuf bytes %d to %d\n",
-			   __func__, start_byte, start_byte + remainder);
-		memcpy(bytes, buff, remainder);
-	}
+	/* Acquire lock to prevent race condition where adminq_task
+	 * can execute after i40e_nvmupd_nvm_read/write but before state
+	 * variables (nvm_wait_opcode, nvm_release_on_done) are updated.
+	 *
+	 * During NVMUpdate, it is observed that lock could be held for
+	 * ~5ms for most commands. However lock is held for ~60ms for
+	 * NVMUPD_CSUM_LCB command.
+	 */
+	mutex_lock(&hw->aq.arq_mutex);
+	switch (hw->nvmupd_state) {
+	case I40E_NVMUPD_STATE_INIT:
+		status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno);
+		break;
 
-	return 0;
-}
+	case I40E_NVMUPD_STATE_READING:
+		status = i40e_nvmupd_state_reading(hw, cmd, bytes, perrno);
+		break;
 
-/**
- * i40e_nvmupd_get_aq_event - Get the Admin Queue event from previous exec_aq
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @bytes: pointer to the data buffer
- * @perrno: pointer to return error code
- *
- * cmd structure contains identifiers and data buffer
- **/
-static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw,
-				    struct i40e_nvm_access *cmd,
-				    u8 *bytes, int *perrno)
-{
-	u32 aq_total_len;
-	u32 aq_desc_len;
+	case I40E_NVMUPD_STATE_WRITING:
+		status = i40e_nvmupd_state_writing(hw, cmd, bytes, perrno);
+		break;
 
-	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
+	case I40E_NVMUPD_STATE_INIT_WAIT:
+	case I40E_NVMUPD_STATE_WRITE_WAIT:
+		/* if we need to stop waiting for an event, clear
+		 * the wait info and return before doing anything else
+		 */
+		if (cmd->offset == 0xffff) {
+			i40e_nvmupd_clear_wait_state(hw);
+			status = 0;
+			break;
+		}
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
-	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen);
+		status = -EBUSY;
+		*perrno = -EBUSY;
+		break;
 
-	/* check copylength range */
-	if (cmd->data_size > aq_total_len) {
+	default:
+		/* invalid state, should never happen */
 		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "%s: copy length %d too big, trimming to %d\n",
-			   __func__, cmd->data_size, aq_total_len);
-		cmd->data_size = aq_total_len;
+			   "NVMUPD: no such state %d\n", hw->nvmupd_state);
+		status = -EOPNOTSUPP;
+		*perrno = -ESRCH;
+		break;
 	}
 
-	memcpy(bytes, &hw->nvm_aq_event_desc, cmd->data_size);
-
-	return 0;
+	mutex_unlock(&hw->aq.arq_mutex);
+	return status;
 }
 
 /**
- * i40e_nvmupd_nvm_read - Read NVM
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @bytes: pointer to the data buffer
- * @perrno: pointer to return error code
- *
- * cmd structure contains identifiers and data buffer
+ * i40e_nvmupd_clear_wait_state - clear wait state on hw
+ * @hw: pointer to the hardware structure
  **/
-static int i40e_nvmupd_nvm_read(struct i40e_hw *hw,
-				struct i40e_nvm_access *cmd,
-				u8 *bytes, int *perrno)
+void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw)
 {
-	struct i40e_asq_cmd_details cmd_details;
-	u8 module, transaction;
-	int status;
-	bool last;
-
-	transaction = i40e_nvmupd_get_transaction(cmd->config);
-	module = i40e_nvmupd_get_module(cmd->config);
-	last = (transaction == I40E_NVM_LCB) || (transaction == I40E_NVM_SA);
-
-	memset(&cmd_details, 0, sizeof(cmd_details));
-	cmd_details.wb_desc = &hw->nvm_wb_desc;
+	i40e_debug(hw, I40E_DEBUG_NVM,
+		   "NVMUPD: clearing wait on opcode 0x%04x\n",
+		   hw->nvm_wait_opcode);
 
-	status = i40e_aq_read_nvm(hw, module, cmd->offset, (u16)cmd->data_size,
-				  bytes, last, &cmd_details);
-	if (status) {
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_read mod 0x%x  off 0x%x  len 0x%x\n",
-			   module, cmd->offset, cmd->data_size);
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_read status %d aq %d\n",
-			   status, hw->aq.asq_last_status);
-		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
+	if (hw->nvm_release_on_done) {
+		i40e_release_nvm(hw);
+		hw->nvm_release_on_done = false;
 	}
+	hw->nvm_wait_opcode = 0;
 
-	return status;
-}
-
-/**
- * i40e_nvmupd_nvm_erase - Erase an NVM module
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @perrno: pointer to return error code
- *
- * module, offset, data_size and data are in cmd structure
- **/
-static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw,
-				 struct i40e_nvm_access *cmd,
-				 int *perrno)
-{
-	struct i40e_asq_cmd_details cmd_details;
-	u8 module, transaction;
-	int status = 0;
-	bool last;
+	if (hw->aq.arq_last_status) {
+		hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR;
+		return;
+	}
 
-	transaction = i40e_nvmupd_get_transaction(cmd->config);
-	module = i40e_nvmupd_get_module(cmd->config);
-	last = (transaction & I40E_NVM_LCB);
+	switch (hw->nvmupd_state) {
+	case I40E_NVMUPD_STATE_INIT_WAIT:
+		hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+		break;
 
-	memset(&cmd_details, 0, sizeof(cmd_details));
-	cmd_details.wb_desc = &hw->nvm_wb_desc;
+	case I40E_NVMUPD_STATE_WRITE_WAIT:
+		hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING;
+		break;
 
-	status = i40e_aq_erase_nvm(hw, module, cmd->offset, (u16)cmd->data_size,
-				   last, &cmd_details);
-	if (status) {
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_erase mod 0x%x  off 0x%x len 0x%x\n",
-			   module, cmd->offset, cmd->data_size);
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_erase status %d aq %d\n",
-			   status, hw->aq.asq_last_status);
-		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
+	default:
+		break;
 	}
-
-	return status;
 }
 
 /**
- * i40e_nvmupd_nvm_write - Write NVM
- * @hw: pointer to hardware structure
- * @cmd: pointer to nvm update command buffer
- * @bytes: pointer to the data buffer
- * @perrno: pointer to return error code
- *
- * module, offset, data_size and data are in cmd structure
+ * i40e_nvmupd_check_wait_event - handle NVM update operation events
+ * @hw: pointer to the hardware structure
+ * @opcode: the event that just happened
+ * @desc: AdminQ descriptor
  **/
-static int i40e_nvmupd_nvm_write(struct i40e_hw *hw,
-				 struct i40e_nvm_access *cmd,
-				 u8 *bytes, int *perrno)
+void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
+				  struct i40e_aq_desc *desc)
 {
-	struct i40e_asq_cmd_details cmd_details;
-	u8 module, transaction;
-	u8 preservation_flags;
-	int status = 0;
-	bool last;
-
-	transaction = i40e_nvmupd_get_transaction(cmd->config);
-	module = i40e_nvmupd_get_module(cmd->config);
-	last = (transaction & I40E_NVM_LCB);
-	preservation_flags = i40e_nvmupd_get_preservation_flags(cmd->config);
-
-	memset(&cmd_details, 0, sizeof(cmd_details));
-	cmd_details.wb_desc = &hw->nvm_wb_desc;
+	u32 aq_desc_len = sizeof(struct i40e_aq_desc);
 
-	status = i40e_aq_update_nvm(hw, module, cmd->offset,
-				    (u16)cmd->data_size, bytes, last,
-				    preservation_flags, &cmd_details);
-	if (status) {
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_write mod 0x%x off 0x%x len 0x%x\n",
-			   module, cmd->offset, cmd->data_size);
-		i40e_debug(hw, I40E_DEBUG_NVM,
-			   "i40e_nvmupd_nvm_write status %d aq %d\n",
-			   status, hw->aq.asq_last_status);
-		*perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status);
+	if (opcode == hw->nvm_wait_opcode) {
+		memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len);
+		i40e_nvmupd_clear_wait_state(hw);
 	}
-
-	return status;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index ce1f11b8ad65..5a0699ca7ce5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -371,13 +371,6 @@ void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);
 
 int i40e_set_mac_type(struct i40e_hw *hw);
 
-extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[];
-
-static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
-{
-	return i40e_ptype_lookup[ptype];
-}
-
 /**
  * i40e_virtchnl_link_speed - Convert AdminQ link_speed to virtchnl definition
  * @link_speed: the speed to convert
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index e7ebcb09f23c..b72a4b5d76b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -1472,7 +1472,8 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf)
  **/
 void i40e_ptp_init(struct i40e_pf *pf)
 {
-	struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev;
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
+	struct net_device *netdev = vsi->netdev;
 	struct i40e_hw *hw = &pf->hw;
 	u32 pf_id;
 	long err;
@@ -1536,6 +1537,7 @@ void i40e_ptp_init(struct i40e_pf *pf)
  **/
 void i40e_ptp_stop(struct i40e_pf *pf)
 {
+	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_hw *hw = &pf->hw;
 	u32 regval;
 
@@ -1555,7 +1557,7 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 		ptp_clock_unregister(pf->ptp_clock);
 		pf->ptp_clock = NULL;
 		dev_info(&pf->pdev->dev, "%s: removed PHC on %s\n", __func__,
-			 pf->vsi[pf->lan_vsi]->netdev->name);
+			 main_vsi->netdev->name);
 	}
 
 	if (i40e_is_ptp_pin_dev(&pf->hw)) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1a12b732818e..c006f716a3bd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/net/intel/libie/rx.h>
 #include <linux/prefetch.h>
 #include <linux/sctp.h>
 #include <net/mpls.h>
@@ -23,7 +24,7 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 {
 	struct i40e_filter_program_desc *fdir_desc;
 	struct i40e_pf *pf = tx_ring->vsi->back;
-	u32 flex_ptype, dtype_cmd;
+	u32 flex_ptype, dtype_cmd, vsi_id;
 	u16 i;
 
 	/* grab the next descriptor */
@@ -41,8 +42,8 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_PCTYPE_MASK, fdata->pctype);
 
 	/* Use LAN VSI Id if not programmed by user */
-	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK,
-				 fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id);
+	vsi_id = fdata->dest_vsi ? : i40e_pf_get_main_vsi(pf)->id;
+	flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK, vsi_id);
 
 	dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG;
 
@@ -860,13 +861,15 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 
 /**
  * i40e_detect_recover_hung - Function to detect and recover hung_queues
- * @vsi:  pointer to vsi struct with tx queues
+ * @pf: pointer to PF struct
  *
- * VSI has netdev and netdev has TX queues. This function is to check each of
- * those TX queues if they are hung, trigger recovery by issuing SW interrupt.
+ * LAN VSI has netdev and netdev has TX queues. This function is to check
+ * each of those TX queues if they are hung, trigger recovery by issuing
+ * SW interrupt.
  **/
-void i40e_detect_recover_hung(struct i40e_vsi *vsi)
+void i40e_detect_recover_hung(struct i40e_pf *pf)
 {
+	struct i40e_vsi *vsi = i40e_pf_get_main_vsi(pf);
 	struct i40e_ring *tx_ring = NULL;
 	struct net_device *netdev;
 	unsigned int i;
@@ -1741,38 +1744,30 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
 				    union i40e_rx_desc *rx_desc)
 {
-	struct i40e_rx_ptype_decoded decoded;
+	struct libeth_rx_pt decoded;
 	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword);
-	rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword);
-	decoded = decode_rx_desc_ptype(ptype);
-
 	skb->ip_summed = CHECKSUM_NONE;
 
-	skb_checksum_none_assert(skb);
+	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+	ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword);
 
-	/* Rx csum enabled and ip headers found? */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+	decoded = libie_rx_pt_parse(ptype);
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
 		return;
 
+	rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword);
+	rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword);
+
 	/* did the hardware decode the packet and checksum? */
 	if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
 		return;
 
-	/* both known and outer_ip must be set for the below code to work */
-	if (!(decoded.known && decoded.outer_ip))
-		return;
-
-	ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4);
-	ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6);
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
 
 	if (ipv4 &&
 	    (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) |
@@ -1800,20 +1795,10 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	 * we need to bump the checksum level by 1 to reflect the fact that
 	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
+	if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT)
 		skb->csum_level = 1;
 
-	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
-	switch (decoded.inner_prot) {
-	case I40E_RX_PTYPE_INNER_PROT_TCP:
-	case I40E_RX_PTYPE_INNER_PROT_UDP:
-	case I40E_RX_PTYPE_INNER_PROT_SCTP:
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		fallthrough;
-	default:
-		break;
-	}
-
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	return;
 
 checksum_fail:
@@ -1821,29 +1806,6 @@ checksum_fail:
 }
 
 /**
- * i40e_ptype_to_htype - get a hash type
- * @ptype: the ptype value from the descriptor
- *
- * Returns a hash type to be used by skb_set_hash
- **/
-static inline int i40e_ptype_to_htype(u8 ptype)
-{
-	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
-
-	if (!decoded.known)
-		return PKT_HASH_TYPE_NONE;
-
-	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-	    decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4)
-		return PKT_HASH_TYPE_L4;
-	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
-		 decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3)
-		return PKT_HASH_TYPE_L3;
-	else
-		return PKT_HASH_TYPE_L2;
-}
-
-/**
  * i40e_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
  * @rx_desc: specific descriptor
@@ -1855,17 +1817,19 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
 				struct sk_buff *skb,
 				u8 rx_ptype)
 {
+	struct libeth_rx_pt decoded;
 	u32 hash;
 	const __le64 rss_mask =
 		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
 			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
-	if (!(ring->netdev->features & NETIF_F_RXHASH))
+	decoded = libie_rx_pt_parse(rx_ptype);
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
 		return;
 
 	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
 		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-		skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+		libeth_rx_pt_set_hash(skb, hash, decoded);
 	}
 }
 
@@ -2144,9 +2108,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	 */
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       I40E_RX_HDR_SIZE,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, I40E_RX_HDR_SIZE);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 2cdc7de6301c..7c26c9a2bf65 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -470,7 +470,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring);
 int i40e_napi_poll(struct napi_struct *napi, int budget);
 void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
 u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
-void i40e_detect_recover_hung(struct i40e_vsi *vsi);
+void i40e_detect_recover_hung(struct i40e_pf *pf);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
 int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index d9031499697e..28568e126850 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -745,94 +745,6 @@ enum i40e_rx_desc_error_l3l4e_fcoe_masks {
 #define I40E_RXD_QW1_PTYPE_SHIFT	30
 #define I40E_RXD_QW1_PTYPE_MASK		(0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT)
 
-/* Packet type non-ip values */
-enum i40e_rx_l2_ptype {
-	I40E_RX_PTYPE_L2_RESERVED			= 0,
-	I40E_RX_PTYPE_L2_MAC_PAY2			= 1,
-	I40E_RX_PTYPE_L2_TIMESYNC_PAY2			= 2,
-	I40E_RX_PTYPE_L2_FIP_PAY2			= 3,
-	I40E_RX_PTYPE_L2_OUI_PAY2			= 4,
-	I40E_RX_PTYPE_L2_MACCNTRL_PAY2			= 5,
-	I40E_RX_PTYPE_L2_LLDP_PAY2			= 6,
-	I40E_RX_PTYPE_L2_ECP_PAY2			= 7,
-	I40E_RX_PTYPE_L2_EVB_PAY2			= 8,
-	I40E_RX_PTYPE_L2_QCN_PAY2			= 9,
-	I40E_RX_PTYPE_L2_EAPOL_PAY2			= 10,
-	I40E_RX_PTYPE_L2_ARP				= 11,
-	I40E_RX_PTYPE_L2_FCOE_PAY3			= 12,
-	I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3		= 13,
-	I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3		= 14,
-	I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3		= 15,
-	I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA		= 16,
-	I40E_RX_PTYPE_L2_FCOE_VFT_PAY3			= 17,
-	I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA		= 18,
-	I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY			= 19,
-	I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP			= 20,
-	I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER		= 21,
-	I40E_RX_PTYPE_GRENAT4_MAC_PAY3			= 58,
-	I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4	= 87,
-	I40E_RX_PTYPE_GRENAT6_MAC_PAY3			= 124,
-	I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4	= 153
-};
-
-struct i40e_rx_ptype_decoded {
-	u32 known:1;
-	u32 outer_ip:1;
-	u32 outer_ip_ver:1;
-	u32 outer_frag:1;
-	u32 tunnel_type:3;
-	u32 tunnel_end_prot:2;
-	u32 tunnel_end_frag:1;
-	u32 inner_prot:4;
-	u32 payload_layer:3;
-};
-
-enum i40e_rx_ptype_outer_ip {
-	I40E_RX_PTYPE_OUTER_L2	= 0,
-	I40E_RX_PTYPE_OUTER_IP	= 1
-};
-
-enum i40e_rx_ptype_outer_ip_ver {
-	I40E_RX_PTYPE_OUTER_NONE	= 0,
-	I40E_RX_PTYPE_OUTER_IPV4	= 0,
-	I40E_RX_PTYPE_OUTER_IPV6	= 1
-};
-
-enum i40e_rx_ptype_outer_fragmented {
-	I40E_RX_PTYPE_NOT_FRAG	= 0,
-	I40E_RX_PTYPE_FRAG	= 1
-};
-
-enum i40e_rx_ptype_tunnel_type {
-	I40E_RX_PTYPE_TUNNEL_NONE		= 0,
-	I40E_RX_PTYPE_TUNNEL_IP_IP		= 1,
-	I40E_RX_PTYPE_TUNNEL_IP_GRENAT		= 2,
-	I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC	= 3,
-	I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN	= 4,
-};
-
-enum i40e_rx_ptype_tunnel_end_prot {
-	I40E_RX_PTYPE_TUNNEL_END_NONE	= 0,
-	I40E_RX_PTYPE_TUNNEL_END_IPV4	= 1,
-	I40E_RX_PTYPE_TUNNEL_END_IPV6	= 2,
-};
-
-enum i40e_rx_ptype_inner_prot {
-	I40E_RX_PTYPE_INNER_PROT_NONE		= 0,
-	I40E_RX_PTYPE_INNER_PROT_UDP		= 1,
-	I40E_RX_PTYPE_INNER_PROT_TCP		= 2,
-	I40E_RX_PTYPE_INNER_PROT_SCTP		= 3,
-	I40E_RX_PTYPE_INNER_PROT_ICMP		= 4,
-	I40E_RX_PTYPE_INNER_PROT_TIMESYNC	= 5
-};
-
-enum i40e_rx_ptype_payload_layer {
-	I40E_RX_PTYPE_PAYLOAD_LAYER_NONE	= 0,
-	I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2	= 1,
-	I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3	= 2,
-	I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4	= 3,
-};
-
 #define I40E_RXD_QW1_LENGTH_PBUF_SHIFT	38
 #define I40E_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
 					 I40E_RXD_QW1_LENGTH_PBUF_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 232b65b9c8ea..662622f01e31 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -795,13 +795,13 @@ error_param:
 static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx)
 {
 	struct i40e_mac_filter *f = NULL;
+	struct i40e_vsi *main_vsi, *vsi;
 	struct i40e_pf *pf = vf->pf;
-	struct i40e_vsi *vsi;
 	u64 max_tx_rate = 0;
 	int ret = 0;
 
-	vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, pf->vsi[pf->lan_vsi]->seid,
-			     vf->vf_id);
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, main_vsi->seid, vf->vf_id);
 
 	if (!vsi) {
 		dev_err(&pf->pdev->dev,
@@ -3322,8 +3322,9 @@ error_param:
 static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 {
 	struct i40e_pf *pf = vf->pf;
-	int abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id;
+	struct i40e_vsi *main_vsi;
 	int aq_ret = 0;
+	int abs_vf_id;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
 	    !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) {
@@ -3331,8 +3332,9 @@ static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 		goto error_param;
 	}
 
-	i40e_notify_client_of_vf_msg(pf->vsi[pf->lan_vsi], abs_vf_id,
-				     msg, msglen);
+	main_vsi = i40e_pf_get_main_vsi(pf);
+	abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id;
+	i40e_notify_client_of_vf_msg(main_vsi, abs_vf_id, msg, msglen);
 
 error_param:
 	/* send the response to the VF */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 11500003af0d..a85b425794df 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -301,8 +301,7 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 	net_prefetch(xdp->data_meta);
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
 	if (unlikely(!skb))
 		goto out;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index db8188c7ac4b..23a6557fc3db 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -287,7 +287,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_RESET_PENDING		BIT(4)
 #define IAVF_FLAG_RESET_NEEDED		BIT(5)
 #define IAVF_FLAG_WB_ON_ITR_CAPABLE		BIT(6)
-#define IAVF_FLAG_LEGACY_RX			BIT(15)
+/* BIT(15) is free, was IAVF_FLAG_LEGACY_RX */
 #define IAVF_FLAG_REINIT_ITR_NEEDED		BIT(16)
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index 5a25233a89d5..aa751ce3425b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -432,259 +432,6 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
 	return iavf_aq_get_set_rss_key(hw, vsi_id, key, true);
 }
 
-/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the
- * hardware to a bit-field that can be used by SW to more easily determine the
- * packet type.
- *
- * Macros are used to shorten the table lines and make this table human
- * readable.
- *
- * We store the PTYPE in the top byte of the bit field - this is just so that
- * we can check that the table doesn't have a row missing, as the index into
- * the table should be the PTYPE.
- *
- * Typical work flow:
- *
- * IF NOT iavf_ptype_lookup[ptype].known
- * THEN
- *      Packet is unknown
- * ELSE IF iavf_ptype_lookup[ptype].outer_ip == IAVF_RX_PTYPE_OUTER_IP
- *      Use the rest of the fields to look at the tunnels, inner protocols, etc
- * ELSE
- *      Use the enum iavf_rx_l2_ptype to decode the packet type
- * ENDIF
- */
-
-/* macro to make the table lines short, use explicit indexing with [PTYPE] */
-#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	[PTYPE] = { \
-		1, \
-		IAVF_RX_PTYPE_OUTER_##OUTER_IP, \
-		IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \
-		IAVF_RX_PTYPE_##OUTER_FRAG, \
-		IAVF_RX_PTYPE_TUNNEL_##T, \
-		IAVF_RX_PTYPE_TUNNEL_END_##TE, \
-		IAVF_RX_PTYPE_##TEF, \
-		IAVF_RX_PTYPE_INNER_PROT_##I, \
-		IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL }
-
-#define IAVF_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-
-/* shorter macros makes the table fit but are terse */
-#define IAVF_RX_PTYPE_NOF		IAVF_RX_PTYPE_NOT_FRAG
-#define IAVF_RX_PTYPE_FRG		IAVF_RX_PTYPE_FRAG
-#define IAVF_RX_PTYPE_INNER_PROT_TS	IAVF_RX_PTYPE_INNER_PROT_TIMESYNC
-
-/* Lookup table mapping the 8-bit HW PTYPE to the bit field for decoding */
-struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = {
-	/* L2 Packet types */
-	IAVF_PTT_UNUSED_ENTRY(0),
-	IAVF_PTT(1,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	IAVF_PTT(2,  L2, NONE, NOF, NONE, NONE, NOF, TS,   PAY2),
-	IAVF_PTT(3,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	IAVF_PTT_UNUSED_ENTRY(4),
-	IAVF_PTT_UNUSED_ENTRY(5),
-	IAVF_PTT(6,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	IAVF_PTT(7,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	IAVF_PTT_UNUSED_ENTRY(8),
-	IAVF_PTT_UNUSED_ENTRY(9),
-	IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
-
-	/* Non Tunneled IPv4 */
-	IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(25),
-	IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(32),
-	IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(39),
-	IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(47),
-	IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(54),
-	IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(62),
-	IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(69),
-	IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(77),
-	IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(84),
-	IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(91),
-	IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	IAVF_PTT(95,  IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(96,  IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(97,  IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(98),
-	IAVF_PTT(99,  IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(105),
-	IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(113),
-	IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(120),
-	IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(128),
-	IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(135),
-	IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(143),
-	IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	IAVF_PTT_UNUSED_ENTRY(150),
-	IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* unused entries */
-	[154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-};
-
 /**
  * iavf_aq_send_msg_to_pf
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 378c3e9ddf9d..52273f7eab2c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -240,29 +240,6 @@ static const struct iavf_stats iavf_gstrings_stats[] = {
 
 #define IAVF_QUEUE_STATS_LEN	ARRAY_SIZE(iavf_gstrings_queue_stats)
 
-/* For now we have one and only one private flag and it is only defined
- * when we have support for the SKIP_CPU_SYNC DMA attribute.  Instead
- * of leaving all this code sitting around empty we will strip it unless
- * our one private flag is actually available.
- */
-struct iavf_priv_flags {
-	char flag_string[ETH_GSTRING_LEN];
-	u32 flag;
-	bool read_only;
-};
-
-#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \
-	.flag_string = _name, \
-	.flag = _flag, \
-	.read_only = _read_only, \
-}
-
-static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = {
-	IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0),
-};
-
-#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags)
-
 /**
  * iavf_get_link_ksettings - Get Link Speed and Duplex settings
  * @netdev: network interface device structure
@@ -342,8 +319,6 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset)
 		return IAVF_STATS_LEN +
 			(IAVF_QUEUE_STATS_LEN * 2 *
 			 netdev->real_num_tx_queues);
-	else if (sset == ETH_SS_PRIV_FLAGS)
-		return IAVF_PRIV_FLAGS_STR_LEN;
 	else
 		return -EINVAL;
 }
@@ -386,21 +361,6 @@ static void iavf_get_ethtool_stats(struct net_device *netdev,
 }
 
 /**
- * iavf_get_priv_flag_strings - Get private flag strings
- * @netdev: network interface device structure
- * @data: buffer for string data
- *
- * Builds the private flags string table
- **/
-static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data)
-{
-	unsigned int i;
-
-	for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++)
-		ethtool_puts(&data, iavf_gstrings_priv_flags[i].flag_string);
-}
-
-/**
  * iavf_get_stat_strings - Get stat strings
  * @netdev: network interface device structure
  * @data: buffer for string data
@@ -438,109 +398,12 @@ static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 	case ETH_SS_STATS:
 		iavf_get_stat_strings(netdev, data);
 		break;
-	case ETH_SS_PRIV_FLAGS:
-		iavf_get_priv_flag_strings(netdev, data);
-		break;
 	default:
 		break;
 	}
 }
 
 /**
- * iavf_get_priv_flags - report device private flags
- * @netdev: network interface device structure
- *
- * The get string set count and the string set should be matched for each
- * flag returned.  Add new strings for each flag to the iavf_gstrings_priv_flags
- * array.
- *
- * Returns a u32 bitmap of flags.
- **/
-static u32 iavf_get_priv_flags(struct net_device *netdev)
-{
-	struct iavf_adapter *adapter = netdev_priv(netdev);
-	u32 i, ret_flags = 0;
-
-	for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) {
-		const struct iavf_priv_flags *priv_flags;
-
-		priv_flags = &iavf_gstrings_priv_flags[i];
-
-		if (priv_flags->flag & adapter->flags)
-			ret_flags |= BIT(i);
-	}
-
-	return ret_flags;
-}
-
-/**
- * iavf_set_priv_flags - set private flags
- * @netdev: network interface device structure
- * @flags: bit flags to be set
- **/
-static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
-{
-	struct iavf_adapter *adapter = netdev_priv(netdev);
-	u32 orig_flags, new_flags, changed_flags;
-	int ret = 0;
-	u32 i;
-
-	orig_flags = READ_ONCE(adapter->flags);
-	new_flags = orig_flags;
-
-	for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) {
-		const struct iavf_priv_flags *priv_flags;
-
-		priv_flags = &iavf_gstrings_priv_flags[i];
-
-		if (flags & BIT(i))
-			new_flags |= priv_flags->flag;
-		else
-			new_flags &= ~(priv_flags->flag);
-
-		if (priv_flags->read_only &&
-		    ((orig_flags ^ new_flags) & ~BIT(i)))
-			return -EOPNOTSUPP;
-	}
-
-	/* Before we finalize any flag changes, any checks which we need to
-	 * perform to determine if the new flags will be supported should go
-	 * here...
-	 */
-
-	/* Compare and exchange the new flags into place. If we failed, that
-	 * is if cmpxchg returns anything but the old value, this means
-	 * something else must have modified the flags variable since we
-	 * copied it. We'll just punt with an error and log something in the
-	 * message buffer.
-	 */
-	if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) {
-		dev_warn(&adapter->pdev->dev,
-			 "Unable to update adapter->flags as it was modified by another thread...\n");
-		return -EAGAIN;
-	}
-
-	changed_flags = orig_flags ^ new_flags;
-
-	/* Process any additional changes needed as a result of flag changes.
-	 * The changed_flags value reflects the list of bits that were changed
-	 * in the code above.
-	 */
-
-	/* issue a reset to force legacy-rx change to take effect */
-	if (changed_flags & IAVF_FLAG_LEGACY_RX) {
-		if (netif_running(netdev)) {
-			iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
-			ret = iavf_wait_for_reset(adapter);
-			if (ret)
-				netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset");
-		}
-	}
-
-	return ret;
-}
-
-/**
  * iavf_get_msglevel - Get debug message level
  * @netdev: network interface device structure
  *
@@ -585,7 +448,6 @@ static void iavf_get_drvinfo(struct net_device *netdev,
 	strscpy(drvinfo->driver, iavf_driver_name, 32);
 	strscpy(drvinfo->fw_version, "N/A", 4);
 	strscpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
-	drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN;
 }
 
 /**
@@ -1995,8 +1857,6 @@ static const struct ethtool_ops iavf_ethtool_ops = {
 	.get_strings		= iavf_get_strings,
 	.get_ethtool_stats	= iavf_get_ethtool_stats,
 	.get_sset_count		= iavf_get_sset_count,
-	.get_priv_flags		= iavf_get_priv_flags,
-	.set_priv_flags		= iavf_set_priv_flags,
 	.get_msglevel		= iavf_get_msglevel,
 	.set_msglevel		= iavf_set_msglevel,
 	.get_coalesce		= iavf_get_coalesce,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 166832a4213a..c6dff0963053 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/net/intel/libie/rx.h>
+
 #include "iavf.h"
 #include "iavf_prototype.h"
 /* All iavf tracepoints are defined by the include below, which must
@@ -45,6 +47,8 @@ MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);
 MODULE_ALIAS("i40evf");
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
 MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver");
+MODULE_IMPORT_NS(LIBETH);
+MODULE_IMPORT_NS(LIBIE);
 MODULE_LICENSE("GPL v2");
 
 static const struct net_device_ops iavf_netdev_ops;
@@ -714,40 +718,10 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)
  **/
 static void iavf_configure_rx(struct iavf_adapter *adapter)
 {
-	unsigned int rx_buf_len = IAVF_RXBUFFER_2048;
 	struct iavf_hw *hw = &adapter->hw;
-	int i;
-
-	/* Legacy Rx will always default to a 2048 buffer size. */
-#if (PAGE_SIZE < 8192)
-	if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) {
-		struct net_device *netdev = adapter->netdev;
-
-		/* For jumbo frames on systems with 4K pages we have to use
-		 * an order 1 page, so we might as well increase the size
-		 * of our Rx buffer to make better use of the available space
-		 */
-		rx_buf_len = IAVF_RXBUFFER_3072;
-
-		/* We use a 1536 buffer size for configurations with
-		 * standard Ethernet mtu.  On x86 this gives us enough room
-		 * for shared info and 192 bytes of padding.
-		 */
-		if (!IAVF_2K_TOO_SMALL_WITH_PADDING &&
-		    (netdev->mtu <= ETH_DATA_LEN))
-			rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN;
-	}
-#endif
 
-	for (i = 0; i < adapter->num_active_queues; i++) {
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
 		adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
-		adapter->rx_rings[i].rx_buf_len = rx_buf_len;
-
-		if (adapter->flags & IAVF_FLAG_LEGACY_RX)
-			clear_ring_build_skb_enabled(&adapter->rx_rings[i]);
-		else
-			set_ring_build_skb_enabled(&adapter->rx_rings[i]);
-	}
 }
 
 /**
@@ -1615,7 +1589,6 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter)
 		rx_ring = &adapter->rx_rings[i];
 		rx_ring->queue_index = i;
 		rx_ring->netdev = adapter->netdev;
-		rx_ring->dev = &adapter->pdev->dev;
 		rx_ring->count = adapter->rx_desc_count;
 		rx_ring->itr_setting = IAVF_ITR_RX_DEF;
 	}
@@ -2642,9 +2615,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	iavf_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
-	/* MTU range: 68 - 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD;
+	netdev->max_mtu = LIBIE_MAX_MTU;
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
@@ -3785,6 +3757,10 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 
 		flow_rule_match_control(rule, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
@@ -4324,7 +4300,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev)) {
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
@@ -5051,7 +5027,7 @@ err_dma:
  *
  * Called when the system (VM) is entering sleep/suspend.
  **/
-static int __maybe_unused iavf_suspend(struct device *dev_d)
+static int iavf_suspend(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct iavf_adapter *adapter = netdev_priv(netdev);
@@ -5079,7 +5055,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d)
  *
  * Called when the system (VM) is resumed from sleep/suspend.
  **/
-static int __maybe_unused iavf_resume(struct device *dev_d)
+static int iavf_resume(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct iavf_adapter *adapter;
@@ -5266,14 +5242,14 @@ static void iavf_shutdown(struct pci_dev *pdev)
 		pci_set_power_state(pdev, PCI_D3hot);
 }
 
-static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
 
 static struct pci_driver iavf_driver = {
 	.name      = iavf_driver_name,
 	.id_table  = iavf_pci_tbl,
 	.probe     = iavf_probe,
 	.remove    = iavf_remove,
-	.driver.pm = &iavf_pm_ops,
+	.driver.pm = pm_sleep_ptr(&iavf_pm_ops),
 	.shutdown  = iavf_shutdown,
 };
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
index 4a48e6171405..48c3901381b4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
@@ -45,13 +45,6 @@ enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,
 enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid,
 				     struct iavf_aqc_get_set_rss_key_data *key);
 
-extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[];
-
-static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
-{
-	return iavf_ptype_lookup[ptype];
-}
-
 void iavf_vf_parse_hw_config(struct iavf_hw *hw,
 			     struct virtchnl_vf_resource *msg);
 enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index b71484c87a84..26b424fd6718 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/bitfield.h>
+#include <linux/net/intel/libie/rx.h>
 #include <linux/prefetch.h>
 
 #include "iavf.h"
@@ -184,7 +185,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)
 			 * pending work.
 			 */
 			packets = tx_ring->stats.packets & INT_MAX;
-			if (tx_ring->tx_stats.prev_pkt_ctr == packets) {
+			if (tx_ring->prev_pkt_ctr == packets) {
 				iavf_force_wb(vsi, tx_ring->q_vector);
 				continue;
 			}
@@ -193,7 +194,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)
 			 * to iavf_get_tx_pending()
 			 */
 			smp_rmb();
-			tx_ring->tx_stats.prev_pkt_ctr =
+			tx_ring->prev_pkt_ctr =
 			  iavf_get_tx_pending(tx_ring, true) ? packets : -1;
 		}
 	}
@@ -319,7 +320,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi,
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
 		    !test_bit(__IAVF_VSI_DOWN, vsi->state) &&
 		    (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count))
-			tx_ring->arm_wb = true;
+			tx_ring->flags |= IAVF_TXR_FLAGS_ARM_WB;
 	}
 
 	/* notify netdev of completed buffers */
@@ -674,7 +675,7 @@ int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring)
 
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
-	tx_ring->tx_stats.prev_pkt_ctr = -1;
+	tx_ring->prev_pkt_ctr = -1;
 	return 0;
 
 err:
@@ -689,11 +690,8 @@ err:
  **/
 static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
 {
-	unsigned long bi_size;
-	u16 i;
-
 	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_bi)
+	if (!rx_ring->rx_fqes)
 		return;
 
 	if (rx_ring->skb) {
@@ -701,41 +699,16 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
 		rx_ring->skb = NULL;
 	}
 
-	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+	/* Free all the Rx ring buffers */
+	for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) {
+		const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i];
 
-		if (!rx_bi->page)
-			continue;
+		page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false);
 
-		/* Invalidate cache lines that may have been written to by
-		 * device so that we avoid corrupting memory.
-		 */
-		dma_sync_single_range_for_cpu(rx_ring->dev,
-					      rx_bi->dma,
-					      rx_bi->page_offset,
-					      rx_ring->rx_buf_len,
-					      DMA_FROM_DEVICE);
-
-		/* free resources associated with mapping */
-		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
-				     iavf_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE,
-				     IAVF_RX_DMA_ATTR);
-
-		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
-
-		rx_bi->page = NULL;
-		rx_bi->page_offset = 0;
+		if (unlikely(++i == rx_ring->count))
+			i = 0;
 	}
 
-	bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_bi, 0, bi_size);
-
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
-	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 }
@@ -748,15 +721,22 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
  **/
 void iavf_free_rx_resources(struct iavf_ring *rx_ring)
 {
+	struct libeth_fq fq = {
+		.fqes	= rx_ring->rx_fqes,
+		.pp	= rx_ring->pp,
+	};
+
 	iavf_clean_rx_ring(rx_ring);
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
 
 	if (rx_ring->desc) {
-		dma_free_coherent(rx_ring->dev, rx_ring->size,
+		dma_free_coherent(rx_ring->pp->p.dev, rx_ring->size,
 				  rx_ring->desc, rx_ring->dma);
 		rx_ring->desc = NULL;
 	}
+
+	libeth_rx_fq_destroy(&fq);
+	rx_ring->rx_fqes = NULL;
+	rx_ring->pp = NULL;
 }
 
 /**
@@ -767,38 +747,46 @@ void iavf_free_rx_resources(struct iavf_ring *rx_ring)
  **/
 int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
-	int bi_size;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_bi);
-	bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
-	rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
-	if (!rx_ring->rx_bi)
-		goto err;
+	struct libeth_fq fq = {
+		.count		= rx_ring->count,
+		.buf_len	= LIBIE_MAX_RX_BUF_LEN,
+		.nid		= NUMA_NO_NODE,
+	};
+	int ret;
+
+	ret = libeth_rx_fq_create(&fq, &rx_ring->q_vector->napi);
+	if (ret)
+		return ret;
+
+	rx_ring->pp = fq.pp;
+	rx_ring->rx_fqes = fq.fqes;
+	rx_ring->truesize = fq.truesize;
+	rx_ring->rx_buf_len = fq.buf_len;
 
 	u64_stats_init(&rx_ring->syncp);
 
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
-	rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
+	rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
 
 	if (!rx_ring->desc) {
-		dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
+		dev_info(fq.pp->p.dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			 rx_ring->size);
 		goto err;
 	}
 
-	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 
 	return 0;
+
 err:
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
+	libeth_rx_fq_destroy(&fq);
+	rx_ring->rx_fqes = NULL;
+	rx_ring->pp = NULL;
+
 	return -ENOMEM;
 }
 
@@ -811,9 +799,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val)
 {
 	rx_ring->next_to_use = val;
 
-	/* update next to alloc since we have filled the ring */
-	rx_ring->next_to_alloc = val;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -824,69 +809,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val)
 }
 
 /**
- * iavf_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int iavf_rx_offset(struct iavf_ring *rx_ring)
-{
-	return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0;
-}
-
-/**
- * iavf_alloc_mapped_page - recycle or make a new page
- * @rx_ring: ring to use
- * @bi: rx_buffer struct to modify
- *
- * Returns true if the page was successfully allocated or
- * reused.
- **/
-static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring,
-				   struct iavf_rx_buffer *bi)
-{
-	struct page *page = bi->page;
-	dma_addr_t dma;
-
-	/* since we are recycling buffers we should seldom need to alloc */
-	if (likely(page)) {
-		rx_ring->rx_stats.page_reuse_count++;
-		return true;
-	}
-
-	/* alloc new page for storage */
-	page = dev_alloc_pages(iavf_rx_pg_order(rx_ring));
-	if (unlikely(!page)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
-				 iavf_rx_pg_size(rx_ring),
-				 DMA_FROM_DEVICE,
-				 IAVF_RX_DMA_ATTR);
-
-	/* if mapping failed free memory back to system since
-	 * there isn't much point in holding memory we can't use
-	 */
-	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, iavf_rx_pg_order(rx_ring));
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	bi->dma = dma;
-	bi->page = page;
-	bi->page_offset = iavf_rx_offset(rx_ring);
-
-	/* initialize pagecnt_bias to 1 representing we fully own page */
-	bi->pagecnt_bias = 1;
-
-	return true;
-}
-
-/**
  * iavf_receive_skb - Send a completed packet up the stack
  * @rx_ring:  rx ring in play
  * @skb: packet to send up
@@ -916,38 +838,37 @@ static void iavf_receive_skb(struct iavf_ring *rx_ring,
  **/
 bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 {
+	const struct libeth_fq_fp fq = {
+		.pp		= rx_ring->pp,
+		.fqes		= rx_ring->rx_fqes,
+		.truesize	= rx_ring->truesize,
+		.count		= rx_ring->count,
+	};
 	u16 ntu = rx_ring->next_to_use;
 	union iavf_rx_desc *rx_desc;
-	struct iavf_rx_buffer *bi;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
 		return false;
 
 	rx_desc = IAVF_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_bi[ntu];
 
 	do {
-		if (!iavf_alloc_mapped_page(rx_ring, bi))
-			goto no_buffers;
+		dma_addr_t addr;
 
-		/* sync the buffer for use by the device */
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 rx_ring->rx_buf_len,
-						 DMA_FROM_DEVICE);
+		addr = libeth_rx_alloc(&fq, ntu);
+		if (addr == DMA_MAPPING_ERROR)
+			goto no_buffers;
 
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+		rx_desc->read.pkt_addr = cpu_to_le64(addr);
 
 		rx_desc++;
-		bi++;
 		ntu++;
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = IAVF_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_bi;
 			ntu = 0;
 		}
 
@@ -966,6 +887,8 @@ no_buffers:
 	if (rx_ring->next_to_use != ntu)
 		iavf_release_rx_desc(rx_ring, ntu);
 
+	rx_ring->rx_stats.alloc_page_failed++;
+
 	/* make sure to come back via polling to try again after
 	 * allocation failure
 	 */
@@ -982,38 +905,30 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi,
 			     struct sk_buff *skb,
 			     union iavf_rx_desc *rx_desc)
 {
-	struct iavf_rx_ptype_decoded decoded;
+	struct libeth_rx_pt decoded;
 	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-	decoded = decode_rx_desc_ptype(ptype);
-
 	skb->ip_summed = CHECKSUM_NONE;
 
-	skb_checksum_none_assert(skb);
+	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
 
-	/* Rx csum enabled and ip headers found? */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+	decoded = libie_rx_pt_parse(ptype);
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
 		return;
 
+	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
+	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
+
 	/* did the hardware decode the packet and checksum? */
 	if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
 		return;
 
-	/* both known and outer_ip must be set for the below code to work */
-	if (!(decoded.known && decoded.outer_ip))
-		return;
-
-	ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4);
-	ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6);
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
 
 	if (ipv4 &&
 	    (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
@@ -1037,17 +952,7 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi,
 	if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
-	switch (decoded.inner_prot) {
-	case IAVF_RX_PTYPE_INNER_PROT_TCP:
-	case IAVF_RX_PTYPE_INNER_PROT_UDP:
-	case IAVF_RX_PTYPE_INNER_PROT_SCTP:
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		fallthrough;
-	default:
-		break;
-	}
-
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	return;
 
 checksum_fail:
@@ -1055,29 +960,6 @@ checksum_fail:
 }
 
 /**
- * iavf_ptype_to_htype - get a hash type
- * @ptype: the ptype value from the descriptor
- *
- * Returns a hash type to be used by skb_set_hash
- **/
-static int iavf_ptype_to_htype(u8 ptype)
-{
-	struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
-
-	if (!decoded.known)
-		return PKT_HASH_TYPE_NONE;
-
-	if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP &&
-	    decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4)
-		return PKT_HASH_TYPE_L4;
-	else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP &&
-		 decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3)
-		return PKT_HASH_TYPE_L3;
-	else
-		return PKT_HASH_TYPE_L2;
-}
-
-/**
  * iavf_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
  * @rx_desc: specific descriptor
@@ -1089,17 +971,19 @@ static void iavf_rx_hash(struct iavf_ring *ring,
 			 struct sk_buff *skb,
 			 u8 rx_ptype)
 {
+	struct libeth_rx_pt decoded;
 	u32 hash;
 	const __le64 rss_mask =
 		cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
 			    IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
-	if (!(ring->netdev->features & NETIF_F_RXHASH))
+	decoded = libie_rx_pt_parse(rx_ptype);
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
 		return;
 
 	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
 		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-		skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype));
+		libeth_rx_pt_set_hash(skb, hash, decoded);
 	}
 }
 
@@ -1152,95 +1036,9 @@ static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb)
 }
 
 /**
- * iavf_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
- * @old_buff: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- **/
-static void iavf_reuse_rx_page(struct iavf_ring *rx_ring,
-			       struct iavf_rx_buffer *old_buff)
-{
-	struct iavf_rx_buffer *new_buff;
-	u16 nta = rx_ring->next_to_alloc;
-
-	new_buff = &rx_ring->rx_bi[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_buff->dma		= old_buff->dma;
-	new_buff->page		= old_buff->page;
-	new_buff->page_offset	= old_buff->page_offset;
-	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
-}
-
-/**
- * iavf_can_reuse_rx_page - Determine if this page can be reused by
- * the adapter for another receive
- *
- * @rx_buffer: buffer containing the page
- *
- * If page is reusable, rx_buffer->page_offset is adjusted to point to
- * an unused region in the page.
- *
- * For small pages, @truesize will be a constant value, half the size
- * of the memory at page.  We'll attempt to alternate between high and
- * low halves of the page, with one half ready for use by the hardware
- * and the other half being consumed by the stack.  We use the page
- * ref count to determine whether the stack has finished consuming the
- * portion of this page that was passed up with a previous packet.  If
- * the page ref count is >1, we'll assume the "other" half page is
- * still busy, and this page cannot be reused.
- *
- * For larger pages, @truesize will be the actual space used by the
- * received packet (adjusted upward to an even multiple of the cache
- * line size).  This will advance through the page by the amount
- * actually consumed by the received packets while there is still
- * space for a buffer.  Each region of larger pages will be used at
- * most once, after which the page will not be reused.
- *
- * In either case, if the page is reusable its refcount is increased.
- **/
-static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer)
-{
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
-	struct page *page = rx_buffer->page;
-
-	/* Is any reuse possible? */
-	if (!dev_page_is_reusable(page))
-		return false;
-
-#if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely((page_count(page) - pagecnt_bias) > 1))
-		return false;
-#else
-#define IAVF_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048)
-	if (rx_buffer->page_offset > IAVF_LAST_OFFSET)
-		return false;
-#endif
-
-	/* If we have drained the page fragment pool we need to update
-	 * the pagecnt_bias and page count so that we fully restock the
-	 * number of references the driver holds.
-	 */
-	if (unlikely(!pagecnt_bias)) {
-		page_ref_add(page, USHRT_MAX);
-		rx_buffer->pagecnt_bias = USHRT_MAX;
-	}
-
-	return true;
-}
-
-/**
  * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_buffer: buffer containing page to add
  * @skb: sk_buff to place the data into
+ * @rx_buffer: buffer containing page to add
  * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
@@ -1248,206 +1046,50 @@ static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer)
  *
  * The function will then update the page offset.
  **/
-static void iavf_add_rx_frag(struct iavf_ring *rx_ring,
-			     struct iavf_rx_buffer *rx_buffer,
-			     struct sk_buff *skb,
+static void iavf_add_rx_frag(struct sk_buff *skb,
+			     const struct libeth_fqe *rx_buffer,
 			     unsigned int size)
 {
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
-#else
-	unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring));
-#endif
-
-	if (!size)
-		return;
+	u32 hr = rx_buffer->page->pp->p.offset;
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
-			rx_buffer->page_offset, size, truesize);
-
-	/* page is being used so we must update the page offset */
-#if (PAGE_SIZE < 8192)
-	rx_buffer->page_offset ^= truesize;
-#else
-	rx_buffer->page_offset += truesize;
-#endif
-}
-
-/**
- * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use
- * @rx_ring: rx descriptor ring to transact packets on
- * @size: size of buffer to add to skb
- *
- * This function will pull an Rx buffer from the ring and synchronize it
- * for use by the CPU.
- */
-static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring,
-						 const unsigned int size)
-{
-	struct iavf_rx_buffer *rx_buffer;
-
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	prefetchw(rx_buffer->page);
-	if (!size)
-		return rx_buffer;
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
-
-	/* We have pulled a buffer for use, so decrement pagecnt_bias */
-	rx_buffer->pagecnt_bias--;
-
-	return rx_buffer;
-}
-
-/**
- * iavf_construct_skb - Allocate skb and populate it
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_buffer: rx buffer to pull data from
- * @size: size of buffer to add to skb
- *
- * This function allocates an skb.  It then populates it with the page
- * data from the current receive descriptor, taking care to set up the
- * skb correctly.
- */
-static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
-					  struct iavf_rx_buffer *rx_buffer,
-					  unsigned int size)
-{
-	void *va;
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
-#else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
-#endif
-	unsigned int headlen;
-	struct sk_buff *skb;
-
-	if (!rx_buffer)
-		return NULL;
-	/* prefetch first cache line of first page */
-	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
-	net_prefetch(va);
-
-	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       IAVF_RX_HDR_SIZE,
-			       GFP_ATOMIC | __GFP_NOWARN);
-	if (unlikely(!skb))
-		return NULL;
-
-	/* Determine available headroom for copy */
-	headlen = size;
-	if (headlen > IAVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
-
-	/* update all of the pointers */
-	size -= headlen;
-	if (size) {
-		skb_add_rx_frag(skb, 0, rx_buffer->page,
-				rx_buffer->page_offset + headlen,
-				size, truesize);
-
-		/* buffer is used by skb, update page_offset */
-#if (PAGE_SIZE < 8192)
-		rx_buffer->page_offset ^= truesize;
-#else
-		rx_buffer->page_offset += truesize;
-#endif
-	} else {
-		/* buffer is unused, reset bias back to rx_buffer */
-		rx_buffer->pagecnt_bias++;
-	}
-
-	return skb;
+			rx_buffer->offset + hr, size, rx_buffer->truesize);
 }
 
 /**
  * iavf_build_skb - Build skb around an existing buffer
- * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_buffer: Rx buffer to pull data from
  * @size: size of buffer to add to skb
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
-static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
-				      struct iavf_rx_buffer *rx_buffer,
+static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 				      unsigned int size)
 {
-	void *va;
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
-#else
-	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(IAVF_SKB_PAD + size);
-#endif
+	u32 hr = rx_buffer->page->pp->p.offset;
 	struct sk_buff *skb;
+	void *va;
 
-	if (!rx_buffer || !size)
-		return NULL;
 	/* prefetch first cache line of first page */
-	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
-	net_prefetch(va);
+	va = page_address(rx_buffer->page) + rx_buffer->offset;
+	net_prefetch(va + hr);
 
 	/* build an skb around the page buffer */
-	skb = napi_build_skb(va - IAVF_SKB_PAD, truesize);
+	skb = napi_build_skb(va, rx_buffer->truesize);
 	if (unlikely(!skb))
 		return NULL;
 
+	skb_mark_for_recycle(skb);
+
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, IAVF_SKB_PAD);
+	skb_reserve(skb, hr);
 	__skb_put(skb, size);
 
-	/* buffer is used by skb, update page_offset */
-#if (PAGE_SIZE < 8192)
-	rx_buffer->page_offset ^= truesize;
-#else
-	rx_buffer->page_offset += truesize;
-#endif
-
 	return skb;
 }
 
 /**
- * iavf_put_rx_buffer - Clean up used buffer and either recycle or free
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_buffer: rx buffer to pull data from
- *
- * This function will clean up the contents of the rx_buffer.  It will
- * either recycle the buffer or unmap it and free the associated resources.
- */
-static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
-			       struct iavf_rx_buffer *rx_buffer)
-{
-	if (!rx_buffer)
-		return;
-
-	if (iavf_can_reuse_rx_page(rx_buffer)) {
-		/* hand second half of page back to the ring */
-		iavf_reuse_rx_page(rx_ring, rx_buffer);
-		rx_ring->rx_stats.page_reuse_count++;
-	} else {
-		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
-				     iavf_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR);
-		__page_frag_cache_drain(rx_buffer->page,
-					rx_buffer->pagecnt_bias);
-	}
-
-	/* clear contents of buffer_info */
-	rx_buffer->page = NULL;
-}
-
-/**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
  * @rx_desc: Rx descriptor for current buffer
@@ -1500,7 +1142,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
-		struct iavf_rx_buffer *rx_buffer;
+		struct libeth_fqe *rx_buffer;
 		union iavf_rx_desc *rx_desc;
 		unsigned int size;
 		u16 vlan_tag = 0;
@@ -1535,28 +1177,27 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
-		rx_buffer = iavf_get_rx_buffer(rx_ring, size);
+
+		rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
+		if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+			goto skip_data;
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(rx_ring, rx_buffer, skb, size);
-		else if (ring_uses_build_skb(rx_ring))
-			skb = iavf_build_skb(rx_ring, rx_buffer, size);
+			iavf_add_rx_frag(skb, rx_buffer, size);
 		else
-			skb = iavf_construct_skb(rx_ring, rx_buffer, size);
+			skb = iavf_build_skb(rx_buffer, size);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
-			if (rx_buffer && size)
-				rx_buffer->pagecnt_bias++;
 			break;
 		}
 
-		iavf_put_rx_buffer(rx_ring, rx_buffer);
+skip_data:
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb))
+		if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
 			continue;
 
 		/* ERR_MASK will only have valid bits if EOP set, and
@@ -1743,8 +1384,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget)
 			clean_complete = false;
 			continue;
 		}
-		arm_wb |= ring->arm_wb;
-		ring->arm_wb = false;
+		arm_wb |= !!(ring->flags & IAVF_TXR_FLAGS_ARM_WB);
+		ring->flags &= ~IAVF_TXR_FLAGS_ARM_WB;
 	}
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 10ba36602c0c..d7b5587aeb8e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -80,79 +80,8 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-/* Supported Rx Buffer Sizes (a multiple of 128) */
-#define IAVF_RXBUFFER_256   256
-#define IAVF_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
-#define IAVF_RXBUFFER_2048  2048
-#define IAVF_RXBUFFER_3072  3072  /* Used for large frames w/ padding */
-#define IAVF_MAX_RXBUFFER   9728  /* largest size for single descriptor */
-
-/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
- * reserve 2 more, and skb_shared_info adds an additional 384 bytes more,
- * this adds up to 512 bytes of extra data meaning the smallest allocation
- * we could have is 1K.
- * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab)
- * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
- */
-#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256
-#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
 #define iavf_rx_desc iavf_32byte_rx_desc
 
-#define IAVF_RX_DMA_ATTR \
-	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
-
-/* Attempt to maximize the headroom available for incoming frames.  We
- * use a 2K buffer for receives and need 1536/1534 to store the data for
- * the frame.  This leaves us with 512 bytes of room.  From that we need
- * to deduct the space needed for the shared info and the padding needed
- * to IP align the frame.
- *
- * Note: For cache line sizes 256 or larger this value is going to end
- *	 up negative.  In these cases we should fall back to the legacy
- *	 receive path.
- */
-#if (PAGE_SIZE < 8192)
-#define IAVF_2K_TOO_SMALL_WITH_PADDING \
-((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048))
-
-static inline int iavf_compute_pad(int rx_buf_len)
-{
-	int page_size, pad_size;
-
-	page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
-	pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
-
-	return pad_size;
-}
-
-static inline int iavf_skb_pad(void)
-{
-	int rx_buf_len;
-
-	/* If a 2K buffer cannot handle a standard Ethernet frame then
-	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
-	 *
-	 * For a 3K buffer we need to add enough padding to allow for
-	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
-	 * cache-line alignment.
-	 */
-	if (IAVF_2K_TOO_SMALL_WITH_PADDING)
-		rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
-	else
-		rx_buf_len = IAVF_RXBUFFER_1536;
-
-	/* if needed make room for NET_IP_ALIGN */
-	rx_buf_len -= NET_IP_ALIGN;
-
-	return iavf_compute_pad(rx_buf_len);
-}
-
-#define IAVF_SKB_PAD iavf_skb_pad()
-#else
-#define IAVF_2K_TOO_SMALL_WITH_PADDING false
-#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#endif
-
 /**
  * iavf_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -271,17 +200,6 @@ struct iavf_tx_buffer {
 	u32 tx_flags;
 };
 
-struct iavf_rx_buffer {
-	dma_addr_t dma;
-	struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
-	__u32 page_offset;
-#else
-	__u16 page_offset;
-#endif
-	__u16 pagecnt_bias;
-};
-
 struct iavf_queue_stats {
 	u64 packets;
 	u64 bytes;
@@ -293,7 +211,6 @@ struct iavf_tx_queue_stats {
 	u64 tx_done_old;
 	u64 tx_linearize;
 	u64 tx_force_wb;
-	int prev_pkt_ctr;
 	u64 tx_lost_interrupt;
 };
 
@@ -301,14 +218,6 @@ struct iavf_rx_queue_stats {
 	u64 non_eop_descs;
 	u64 alloc_page_failed;
 	u64 alloc_buff_failed;
-	u64 page_reuse_count;
-	u64 realloc_count;
-};
-
-enum iavf_ring_state_t {
-	__IAVF_TX_FDIR_INIT_DONE,
-	__IAVF_TX_XPS_INIT_DONE,
-	__IAVF_RING_STATE_NBITS /* must be last */
 };
 
 /* some useful defines for virtchannel interface, which
@@ -326,16 +235,19 @@ enum iavf_ring_state_t {
 struct iavf_ring {
 	struct iavf_ring *next;		/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
-	struct device *dev;		/* Used for DMA mapping */
+	union {
+		struct page_pool *pp;	/* Used on Rx for buffer management */
+		struct device *dev;	/* Used on Tx for DMA mapping */
+	};
 	struct net_device *netdev;	/* netdev ring maps to */
 	union {
+		struct libeth_fqe *rx_fqes;
 		struct iavf_tx_buffer *tx_bi;
-		struct iavf_rx_buffer *rx_bi;
 	};
-	DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS);
-	u16 queue_index;		/* Queue number of ring */
-	u8 dcb_tc;			/* Traffic class of ring */
 	u8 __iomem *tail;
+	u32 truesize;
+
+	u16 queue_index;		/* Queue number of ring */
 
 	/* high bit set means dynamic, use accessors routines to read/write.
 	 * hardware only supports 2us resolution for the ITR registers.
@@ -345,23 +257,15 @@ struct iavf_ring {
 	u16 itr_setting;
 
 	u16 count;			/* Number of descriptors */
-	u16 reg_idx;			/* HW register index of the ring */
-	u16 rx_buf_len;
 
 	/* used in interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
 
-	u8 atr_sample_rate;
-	u8 atr_count;
-
-	bool ring_active;		/* is ring online or not */
-	bool arm_wb;		/* do something to arm write back */
-	u8 packet_stride;
-
 	u16 flags;
 #define IAVF_TXR_FLAGS_WB_ON_ITR		BIT(0)
-#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED	BIT(1)
+#define IAVF_TXR_FLAGS_ARM_WB			BIT(1)
+/* BIT(2) is free */
 #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1	BIT(3)
 #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2	BIT(4)
 #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2	BIT(5)
@@ -374,6 +278,7 @@ struct iavf_ring {
 		struct iavf_rx_queue_stats rx_stats;
 	};
 
+	int prev_pkt_ctr;		/* For Tx stall detection */
 	unsigned int size;		/* length of descriptor ring in bytes */
 	dma_addr_t dma;			/* physical address of ring */
 
@@ -381,7 +286,6 @@ struct iavf_ring {
 	struct iavf_q_vector *q_vector;	/* Backreference to associated vector */
 
 	struct rcu_head rcu;		/* to avoid race on free */
-	u16 next_to_alloc;
 	struct sk_buff *skb;		/* When iavf_clean_rx_ring_irq() must
 					 * return before it sees the EOP for
 					 * the current packet, we save that skb
@@ -390,22 +294,9 @@ struct iavf_ring {
 					 * iavf_clean_rx_ring_irq() is called
 					 * for this ring.
 					 */
-} ____cacheline_internodealigned_in_smp;
-
-static inline bool ring_uses_build_skb(struct iavf_ring *ring)
-{
-	return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED);
-}
 
-static inline void set_ring_build_skb_enabled(struct iavf_ring *ring)
-{
-	ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED;
-}
-
-static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring)
-{
-	ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED;
-}
+	u32 rx_buf_len;
+} ____cacheline_internodealigned_in_smp;
 
 #define IAVF_ITR_ADAPTIVE_MIN_INC	0x0002
 #define IAVF_ITR_ADAPTIVE_MIN_USECS	0x0002
@@ -428,17 +319,6 @@ struct iavf_ring_container {
 #define iavf_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
-static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring)
-{
-#if (PAGE_SIZE < 8192)
-	if (ring->rx_buf_len > (PAGE_SIZE / 2))
-		return 1;
-#endif
-	return 0;
-}
-
-#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring))
-
 bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count);
 netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
 int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index 2b6a207fa441..f6b09e57abce 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -10,8 +10,6 @@
 #include "iavf_adminq.h"
 #include "iavf_devids.h"
 
-#define IAVF_RXQ_CTX_DBUFF_SHIFT 7
-
 /* IAVF_MASK is a macro used on 32 bit registers */
 #define IAVF_MASK(mask, shift) ((u32)(mask) << (shift))
 
@@ -327,94 +325,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 #define IAVF_RXD_QW1_PTYPE_SHIFT	30
 #define IAVF_RXD_QW1_PTYPE_MASK		(0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
 
-/* Packet type non-ip values */
-enum iavf_rx_l2_ptype {
-	IAVF_RX_PTYPE_L2_RESERVED			= 0,
-	IAVF_RX_PTYPE_L2_MAC_PAY2			= 1,
-	IAVF_RX_PTYPE_L2_TIMESYNC_PAY2			= 2,
-	IAVF_RX_PTYPE_L2_FIP_PAY2			= 3,
-	IAVF_RX_PTYPE_L2_OUI_PAY2			= 4,
-	IAVF_RX_PTYPE_L2_MACCNTRL_PAY2			= 5,
-	IAVF_RX_PTYPE_L2_LLDP_PAY2			= 6,
-	IAVF_RX_PTYPE_L2_ECP_PAY2			= 7,
-	IAVF_RX_PTYPE_L2_EVB_PAY2			= 8,
-	IAVF_RX_PTYPE_L2_QCN_PAY2			= 9,
-	IAVF_RX_PTYPE_L2_EAPOL_PAY2			= 10,
-	IAVF_RX_PTYPE_L2_ARP				= 11,
-	IAVF_RX_PTYPE_L2_FCOE_PAY3			= 12,
-	IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3		= 13,
-	IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3		= 14,
-	IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3		= 15,
-	IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA		= 16,
-	IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3			= 17,
-	IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA		= 18,
-	IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY			= 19,
-	IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP			= 20,
-	IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER		= 21,
-	IAVF_RX_PTYPE_GRENAT4_MAC_PAY3			= 58,
-	IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4	= 87,
-	IAVF_RX_PTYPE_GRENAT6_MAC_PAY3			= 124,
-	IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4	= 153
-};
-
-struct iavf_rx_ptype_decoded {
-	u32 known:1;
-	u32 outer_ip:1;
-	u32 outer_ip_ver:1;
-	u32 outer_frag:1;
-	u32 tunnel_type:3;
-	u32 tunnel_end_prot:2;
-	u32 tunnel_end_frag:1;
-	u32 inner_prot:4;
-	u32 payload_layer:3;
-};
-
-enum iavf_rx_ptype_outer_ip {
-	IAVF_RX_PTYPE_OUTER_L2	= 0,
-	IAVF_RX_PTYPE_OUTER_IP	= 1
-};
-
-enum iavf_rx_ptype_outer_ip_ver {
-	IAVF_RX_PTYPE_OUTER_NONE	= 0,
-	IAVF_RX_PTYPE_OUTER_IPV4	= 0,
-	IAVF_RX_PTYPE_OUTER_IPV6	= 1
-};
-
-enum iavf_rx_ptype_outer_fragmented {
-	IAVF_RX_PTYPE_NOT_FRAG	= 0,
-	IAVF_RX_PTYPE_FRAG	= 1
-};
-
-enum iavf_rx_ptype_tunnel_type {
-	IAVF_RX_PTYPE_TUNNEL_NONE		= 0,
-	IAVF_RX_PTYPE_TUNNEL_IP_IP		= 1,
-	IAVF_RX_PTYPE_TUNNEL_IP_GRENAT		= 2,
-	IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC	= 3,
-	IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN	= 4,
-};
-
-enum iavf_rx_ptype_tunnel_end_prot {
-	IAVF_RX_PTYPE_TUNNEL_END_NONE	= 0,
-	IAVF_RX_PTYPE_TUNNEL_END_IPV4	= 1,
-	IAVF_RX_PTYPE_TUNNEL_END_IPV6	= 2,
-};
-
-enum iavf_rx_ptype_inner_prot {
-	IAVF_RX_PTYPE_INNER_PROT_NONE		= 0,
-	IAVF_RX_PTYPE_INNER_PROT_UDP		= 1,
-	IAVF_RX_PTYPE_INNER_PROT_TCP		= 2,
-	IAVF_RX_PTYPE_INNER_PROT_SCTP		= 3,
-	IAVF_RX_PTYPE_INNER_PROT_ICMP		= 4,
-	IAVF_RX_PTYPE_INNER_PROT_TIMESYNC	= 5
-};
-
-enum iavf_rx_ptype_payload_layer {
-	IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE	= 0,
-	IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2	= 1,
-	IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3	= 2,
-	IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4	= 3,
-};
-
 #define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT	38
 #define IAVF_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
 					 IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 22f2df7c460b..1e543f6a7c30 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/net/intel/libie/rx.h>
+
 #include "iavf.h"
 #include "iavf_prototype.h"
 
@@ -268,13 +270,13 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 void iavf_configure_queues(struct iavf_adapter *adapter)
 {
 	struct virtchnl_vsi_queue_config_info *vqci;
-	int i, max_frame = adapter->vf_res->max_mtu;
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
+	u32 i, max_frame;
 	size_t len;
 
-	if (max_frame > IAVF_MAX_RXBUFFER || !max_frame)
-		max_frame = IAVF_MAX_RXBUFFER;
+	max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
+	max_frame = min_not_zero(adapter->vf_res->max_mtu, max_frame);
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -288,11 +290,6 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	if (!vqci)
 		return;
 
-	/* Limit maximum frame size when jumbo frames is not enabled */
-	if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) &&
-	    (adapter->netdev->mtu <= ETH_DATA_LEN))
-		max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN;
-
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -309,9 +306,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		vqpi->rxq.ring_len = adapter->rx_rings[i].count;
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
 		vqpi->rxq.max_pkt_size = max_frame;
-		vqpi->rxq.databuffer_size =
-			ALIGN(adapter->rx_rings[i].rx_buf_len,
-			      BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT));
+		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index cddd82d4ca0f..03500e28ac99 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -5,6 +5,7 @@
 # Makefile for the Intel(R) Ethernet Connection E800 Series Linux Driver
 #
 
+subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_ICE) += ice.o
 
 ice-y := ice_main.o	\
@@ -28,7 +29,8 @@ ice-y := ice_main.o	\
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
 	 ice_idc.o	\
-	 ice_devlink.o	\
+	 devlink/devlink.o	\
+	 devlink/devlink_port.o \
 	 ice_ddp.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
@@ -36,7 +38,8 @@ ice-y := ice_main.o	\
 	 ice_repr.o	\
 	 ice_tc_lib.o	\
 	 ice_fwlog.o	\
-	 ice_debugfs.o
+	 ice_debugfs.o  \
+	 ice_adapter.o
 ice-$(CONFIG_PCI_IOV) +=	\
 	ice_sriov.o		\
 	ice_virtchnl.o		\
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index b516e42b41f0..c4b69655cdf5 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -5,13 +5,11 @@
 
 #include "ice.h"
 #include "ice_lib.h"
-#include "ice_devlink.h"
+#include "devlink.h"
 #include "ice_eswitch.h"
 #include "ice_fw_update.h"
 #include "ice_dcb_lib.h"
 
-static int ice_active_port_option = -1;
-
 /* context for devlink info version reporting */
 struct ice_info_ctx {
 	char buf[128];
@@ -478,17 +476,17 @@ ice_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
 		if (ice_is_eswitch_mode_switchdev(pf)) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Go to legacy mode before doing reinit\n");
+					   "Go to legacy mode before doing reinit");
 			return -EOPNOTSUPP;
 		}
 		if (ice_is_adq_active(pf)) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Turn off ADQ before doing reinit\n");
+					   "Turn off ADQ before doing reinit");
 			return -EOPNOTSUPP;
 		}
 		if (ice_has_vfs(pf)) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Remove all VFs before doing reinit\n");
+					   "Remove all VFs before doing reinit");
 			return -EOPNOTSUPP;
 		}
 		ice_devlink_reinit_down(pf);
@@ -526,248 +524,153 @@ ice_devlink_reload_empr_finish(struct ice_pf *pf,
 }
 
 /**
- * ice_devlink_port_opt_speed_str - convert speed to a string
- * @speed: speed value
- */
-static const char *ice_devlink_port_opt_speed_str(u8 speed)
-{
-	switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) {
-	case ICE_AQC_PORT_OPT_MAX_LANE_100M:
-		return "0.1";
-	case ICE_AQC_PORT_OPT_MAX_LANE_1G:
-		return "1";
-	case ICE_AQC_PORT_OPT_MAX_LANE_2500M:
-		return "2.5";
-	case ICE_AQC_PORT_OPT_MAX_LANE_5G:
-		return "5";
-	case ICE_AQC_PORT_OPT_MAX_LANE_10G:
-		return "10";
-	case ICE_AQC_PORT_OPT_MAX_LANE_25G:
-		return "25";
-	case ICE_AQC_PORT_OPT_MAX_LANE_50G:
-		return "50";
-	case ICE_AQC_PORT_OPT_MAX_LANE_100G:
-		return "100";
-	}
-
-	return "-";
-}
-
-#define ICE_PORT_OPT_DESC_LEN	50
-/**
- * ice_devlink_port_options_print - Print available port split options
- * @pf: the PF to print split port options
+ * ice_get_tx_topo_user_sel - Read user's choice from flash
+ * @pf: pointer to pf structure
+ * @layers: value read from flash will be saved here
  *
- * Prints a table with available port split options and max port speeds
+ * Reads user's preference for Tx Scheduler Topology Tree from PFA TLV.
+ *
+ * Return: zero when read was successful, negative values otherwise.
  */
-static void ice_devlink_port_options_print(struct ice_pf *pf)
+static int ice_get_tx_topo_user_sel(struct ice_pf *pf, uint8_t *layers)
 {
-	u8 i, j, options_count, cnt, speed, pending_idx, active_idx;
-	struct ice_aqc_get_port_options_elem *options, *opt;
-	struct device *dev = ice_pf_to_dev(pf);
-	bool active_valid, pending_valid;
-	char desc[ICE_PORT_OPT_DESC_LEN];
-	const char *str;
-	int status;
+	struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {};
+	struct ice_hw *hw = &pf->hw;
+	int err;
 
-	options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV,
-			  sizeof(*options), GFP_KERNEL);
-	if (!options)
-		return;
+	err = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (err)
+		return err;
 
-	for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) {
-		opt = options + i * ICE_AQC_PORT_OPT_MAX;
-		options_count = ICE_AQC_PORT_OPT_MAX;
-		active_valid = 0;
+	err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0,
+			      sizeof(usr_sel), &usr_sel, true, true, NULL);
+	if (err)
+		goto exit_release_res;
 
-		status = ice_aq_get_port_options(&pf->hw, opt, &options_count,
-						 i, true, &active_idx,
-						 &active_valid, &pending_idx,
-						 &pending_valid);
-		if (status) {
-			dev_dbg(dev, "Couldn't read port option for port %d, err %d\n",
-				i, status);
-			goto err;
-		}
-	}
+	if (usr_sel.data & ICE_AQC_NVM_TX_TOPO_USER_SEL)
+		*layers = ICE_SCHED_5_LAYERS;
+	else
+		*layers = ICE_SCHED_9_LAYERS;
 
-	dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n");
-	dev_dbg(dev, "Status  Split      Quad 0          Quad 1\n");
-	dev_dbg(dev, "        count  L0  L1  L2  L3  L4  L5  L6  L7\n");
+exit_release_res:
+	ice_release_nvm(hw);
 
-	for (i = 0; i < options_count; i++) {
-		cnt = 0;
+	return err;
+}
 
-		if (i == ice_active_port_option)
-			str = "Active";
-		else if ((i == pending_idx) && pending_valid)
-			str = "Pending";
-		else
-			str = "";
+/**
+ * ice_update_tx_topo_user_sel - Save user's preference in flash
+ * @pf: pointer to pf structure
+ * @layers: value to be saved in flash
+ *
+ * Variable "layers" defines user's preference about number of layers in Tx
+ * Scheduler Topology Tree. This choice should be stored in PFA TLV field
+ * and be picked up by driver, next time during init.
+ *
+ * Return: zero when save was successful, negative values otherwise.
+ */
+static int ice_update_tx_topo_user_sel(struct ice_pf *pf, int layers)
+{
+	struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {};
+	struct ice_hw *hw = &pf->hw;
+	int err;
 
-		cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
-				"%-8s", str);
+	err = ice_acquire_nvm(hw, ICE_RES_WRITE);
+	if (err)
+		return err;
 
-		cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
-				"%-6u", options[i].pmd);
+	err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0,
+			      sizeof(usr_sel), &usr_sel, true, true, NULL);
+	if (err)
+		goto exit_release_res;
 
-		for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) {
-			speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed;
-			str = ice_devlink_port_opt_speed_str(speed);
-			cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
-					"%3s ", str);
-		}
+	if (layers == ICE_SCHED_5_LAYERS)
+		usr_sel.data |= ICE_AQC_NVM_TX_TOPO_USER_SEL;
+	else
+		usr_sel.data &= ~ICE_AQC_NVM_TX_TOPO_USER_SEL;
 
-		dev_dbg(dev, "%s\n", desc);
-	}
+	err = ice_write_one_nvm_block(pf, ICE_AQC_NVM_TX_TOPO_MOD_ID, 2,
+				      sizeof(usr_sel.data), &usr_sel.data,
+				      true, NULL, NULL);
+exit_release_res:
+	ice_release_nvm(hw);
 
-err:
-	kfree(options);
+	return err;
 }
 
 /**
- * ice_devlink_aq_set_port_option - Send set port option admin queue command
- * @pf: the PF to print split port options
- * @option_idx: selected port option
- * @extack: extended netdev ack structure
+ * ice_devlink_tx_sched_layers_get - Get tx_scheduling_layers parameter
+ * @devlink: pointer to the devlink instance
+ * @id: the parameter ID to set
+ * @ctx: context to store the parameter value
  *
- * Sends set port option admin queue command with selected port option and
- * calls NVM write activate.
+ * Return: zero on success and negative value on failure.
  */
-static int
-ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx,
-			       struct netlink_ext_ack *extack)
+static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id,
+					   struct devlink_param_gset_ctx *ctx)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	int status;
-
-	status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx);
-	if (status) {
-		dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n",
-			status, pf->hw.adminq.sq_last_status);
-		NL_SET_ERR_MSG_MOD(extack, "Port split request failed");
-		return -EIO;
-	}
-
-	status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE);
-	if (status) {
-		dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
-			status, pf->hw.adminq.sq_last_status);
-		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
-		return -EIO;
-	}
-
-	status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL);
-	if (status) {
-		dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n",
-			status, pf->hw.adminq.sq_last_status);
-		NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data");
-		ice_release_nvm(&pf->hw);
-		return -EIO;
-	}
+	struct ice_pf *pf = devlink_priv(devlink);
+	int err;
 
-	ice_release_nvm(&pf->hw);
+	err = ice_get_tx_topo_user_sel(pf, &ctx->val.vu8);
+	if (err)
+		return err;
 
-	NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split");
 	return 0;
 }
 
 /**
- * ice_devlink_port_split - .port_split devlink handler
- * @devlink: devlink instance structure
- * @port: devlink port structure
- * @count: number of ports to split to
- * @extack: extended netdev ack structure
- *
- * Callback for the devlink .port_split operation.
- *
- * Unfortunately, the devlink expression of available options is limited
- * to just a number, so search for an FW port option which supports
- * the specified number. As there could be multiple FW port options with
- * the same port split count, allow switching between them. When the same
- * port split count request is issued again, switch to the next FW port
- * option with the same port split count.
+ * ice_devlink_tx_sched_layers_set - Set tx_scheduling_layers parameter
+ * @devlink: pointer to the devlink instance
+ * @id: the parameter ID to set
+ * @ctx: context to get the parameter value
+ * @extack: netlink extended ACK structure
  *
- * Return: zero on success or an error code on failure.
+ * Return: zero on success and negative value on failure.
  */
-static int
-ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port,
-		       unsigned int count, struct netlink_ext_ack *extack)
+static int ice_devlink_tx_sched_layers_set(struct devlink *devlink, u32 id,
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
-	struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX];
-	u8 i, j, active_idx, pending_idx, new_option;
 	struct ice_pf *pf = devlink_priv(devlink);
-	u8 option_count = ICE_AQC_PORT_OPT_MAX;
-	struct device *dev = ice_pf_to_dev(pf);
-	bool active_valid, pending_valid;
-	int status;
-
-	status = ice_aq_get_port_options(&pf->hw, options, &option_count,
-					 0, true, &active_idx, &active_valid,
-					 &pending_idx, &pending_valid);
-	if (status) {
-		dev_dbg(dev, "Couldn't read port split options, err = %d\n",
-			status);
-		NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options");
-		return -EIO;
-	}
-
-	new_option = ICE_AQC_PORT_OPT_MAX;
-	active_idx = pending_valid ? pending_idx : active_idx;
-	for (i = 1; i <= option_count; i++) {
-		/* In order to allow switching between FW port options with
-		 * the same port split count, search for a new option starting
-		 * from the active/pending option (with array wrap around).
-		 */
-		j = (active_idx + i) % option_count;
-
-		if (count == options[j].pmd) {
-			new_option = j;
-			break;
-		}
-	}
-
-	if (new_option == active_idx) {
-		dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n",
-			count);
-		NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set");
-		ice_devlink_port_options_print(pf);
-		return -EINVAL;
-	}
-
-	if (new_option == ICE_AQC_PORT_OPT_MAX) {
-		dev_dbg(dev, "request to split: count: %u not found\n", count);
-		NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config");
-		ice_devlink_port_options_print(pf);
-		return -EINVAL;
-	}
+	int err;
 
-	status = ice_devlink_aq_set_port_option(pf, new_option, extack);
-	if (status)
-		return status;
+	err = ice_update_tx_topo_user_sel(pf, ctx->val.vu8);
+	if (err)
+		return err;
 
-	ice_devlink_port_options_print(pf);
+	NL_SET_ERR_MSG_MOD(extack,
+			   "Tx scheduling layers have been changed on this device. You must do the PCI slot powercycle for the change to take effect.");
 
 	return 0;
 }
 
 /**
- * ice_devlink_port_unsplit - .port_unsplit devlink handler
- * @devlink: devlink instance structure
- * @port: devlink port structure
- * @extack: extended netdev ack structure
+ * ice_devlink_tx_sched_layers_validate - Validate passed tx_scheduling_layers
+ *                                        parameter value
+ * @devlink: unused pointer to devlink instance
+ * @id: the parameter ID to validate
+ * @val: value to validate
+ * @extack: netlink extended ACK structure
  *
- * Callback for the devlink .port_unsplit operation.
- * Calls ice_devlink_port_split with split count set to 1.
- * There could be no FW option available with split count 1.
+ * Supported values are:
+ * - 5 - five layers Tx Scheduler Topology Tree
+ * - 9 - nine layers Tx Scheduler Topology Tree
  *
- * Return: zero on success or an error code on failure.
+ * Return: zero when passed parameter value is supported. Negative value on
+ * error.
  */
-static int
-ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port,
-			 struct netlink_ext_ack *extack)
+static int ice_devlink_tx_sched_layers_validate(struct devlink *devlink, u32 id,
+						union devlink_param_value val,
+						struct netlink_ext_ack *extack)
 {
-	return ice_devlink_port_split(devlink, port, 1, extack);
+	if (val.vu8 != ICE_SCHED_5_LAYERS && val.vu8 != ICE_SCHED_9_LAYERS) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Wrong number of tx scheduler layers provided.");
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 /**
@@ -1290,18 +1193,16 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 static int ice_devlink_reinit_up(struct ice_pf *pf)
 {
 	struct ice_vsi *vsi = ice_get_main_vsi(pf);
-	struct ice_vsi_cfg_params params;
 	int err;
 
 	err = ice_init_dev(pf);
 	if (err)
 		return err;
 
-	params = ice_vsi_to_params(vsi);
-	params.flags = ICE_VSI_FLAG_INIT;
+	vsi->flags = ICE_VSI_FLAG_INIT;
 
 	rtnl_lock();
-	err = ice_vsi_cfg(vsi, &params);
+	err = ice_vsi_cfg(vsi);
 	rtnl_unlock();
 	if (err)
 		goto err_vsi_cfg;
@@ -1391,9 +1292,9 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 	return 0;
 }
 
-static int
-ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	bool roce_ena = ctx->val.vbool;
@@ -1442,9 +1343,9 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 	return 0;
 }
 
-static int
-ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
-			  struct devlink_param_gset_ctx *ctx)
+static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	bool iw_ena = ctx->val.vbool;
@@ -1482,6 +1383,11 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+enum ice_param_id {
+	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
+};
+
 static const struct devlink_param ice_devlink_params[] = {
 	DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			      ice_devlink_enable_roce_get,
@@ -1491,7 +1397,13 @@ static const struct devlink_param ice_devlink_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
-
+	DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
+			     "tx_scheduling_layers",
+			     DEVLINK_PARAM_TYPE_U8,
+			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			     ice_devlink_tx_sched_layers_get,
+			     ice_devlink_tx_sched_layers_set,
+			     ice_devlink_tx_sched_layers_validate),
 };
 
 static void ice_devlink_free(void *devlink_ptr)
@@ -1534,7 +1446,7 @@ void ice_devlink_register(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
 
-	devlink_register(devlink);
+	devl_register(devlink);
 }
 
 /**
@@ -1545,197 +1457,28 @@ void ice_devlink_register(struct ice_pf *pf)
  */
 void ice_devlink_unregister(struct ice_pf *pf)
 {
-	devlink_unregister(priv_to_devlink(pf));
-}
-
-/**
- * ice_devlink_set_switch_id - Set unique switch id based on pci dsn
- * @pf: the PF to create a devlink port for
- * @ppid: struct with switch id information
- */
-static void
-ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid)
-{
-	struct pci_dev *pdev = pf->pdev;
-	u64 id;
-
-	id = pci_get_dsn(pdev);
-
-	ppid->id_len = sizeof(id);
-	put_unaligned_be64(id, &ppid->id);
+	devl_unregister(priv_to_devlink(pf));
 }
 
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_hw *hw = &pf->hw;
+	size_t params_size;
 
-	return devlink_params_register(devlink, ice_devlink_params,
-				       ARRAY_SIZE(ice_devlink_params));
-}
-
-void ice_devlink_unregister_params(struct ice_pf *pf)
-{
-	devlink_params_unregister(priv_to_devlink(pf), ice_devlink_params,
-				  ARRAY_SIZE(ice_devlink_params));
-}
-
-/**
- * ice_devlink_set_port_split_options - Set port split options
- * @pf: the PF to set port split options
- * @attrs: devlink attributes
- *
- * Sets devlink port split options based on available FW port options
- */
-static void
-ice_devlink_set_port_split_options(struct ice_pf *pf,
-				   struct devlink_port_attrs *attrs)
-{
-	struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX];
-	u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX;
-	bool active_valid, pending_valid;
-	int status;
-
-	status = ice_aq_get_port_options(&pf->hw, options, &option_count,
-					 0, true, &active_idx, &active_valid,
-					 &pending_idx, &pending_valid);
-	if (status) {
-		dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n",
-			status);
-		return;
-	}
-
-	/* find the biggest available port split count */
-	for (i = 0; i < option_count; i++)
-		attrs->lanes = max_t(int, attrs->lanes, options[i].pmd);
-
-	attrs->splittable = attrs->lanes ? 1 : 0;
-	ice_active_port_option = active_idx;
-}
-
-static const struct devlink_port_ops ice_devlink_port_ops = {
-	.port_split = ice_devlink_port_split,
-	.port_unsplit = ice_devlink_port_unsplit,
-};
-
-/**
- * ice_devlink_create_pf_port - Create a devlink port for this PF
- * @pf: the PF to create a devlink port for
- *
- * Create and register a devlink_port for this PF.
- * This function has to be called under devl_lock.
- *
- * Return: zero on success or an error code on failure.
- */
-int ice_devlink_create_pf_port(struct ice_pf *pf)
-{
-	struct devlink_port_attrs attrs = {};
-	struct devlink_port *devlink_port;
-	struct devlink *devlink;
-	struct ice_vsi *vsi;
-	struct device *dev;
-	int err;
-
-	devlink = priv_to_devlink(pf);
-
-	dev = ice_pf_to_dev(pf);
-
-	devlink_port = &pf->devlink_port;
-
-	vsi = ice_get_main_vsi(pf);
-	if (!vsi)
-		return -EIO;
-
-	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-	attrs.phys.port_number = pf->hw.bus.func;
-
-	/* As FW supports only port split options for whole device,
-	 * set port split options only for first PF.
-	 */
-	if (pf->hw.pf_id == 0)
-		ice_devlink_set_port_split_options(pf, &attrs);
-
-	ice_devlink_set_switch_id(pf, &attrs.switch_id);
-
-	devlink_port_attrs_set(devlink_port, &attrs);
-
-	err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx,
-					  &ice_devlink_port_ops);
-	if (err) {
-		dev_err(dev, "Failed to create devlink port for PF %d, error %d\n",
-			pf->hw.pf_id, err);
-		return err;
-	}
-
-	return 0;
-}
-
-/**
- * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF
- * @pf: the PF to cleanup
- *
- * Unregisters the devlink_port structure associated with this PF.
- * This function has to be called under devl_lock.
- */
-void ice_devlink_destroy_pf_port(struct ice_pf *pf)
-{
-	devl_port_unregister(&pf->devlink_port);
-}
-
-/**
- * ice_devlink_create_vf_port - Create a devlink port for this VF
- * @vf: the VF to create a port for
- *
- * Create and register a devlink_port for this VF.
- *
- * Return: zero on success or an error code on failure.
- */
-int ice_devlink_create_vf_port(struct ice_vf *vf)
-{
-	struct devlink_port_attrs attrs = {};
-	struct devlink_port *devlink_port;
-	struct devlink *devlink;
-	struct ice_vsi *vsi;
-	struct device *dev;
-	struct ice_pf *pf;
-	int err;
-
-	pf = vf->pf;
-	dev = ice_pf_to_dev(pf);
-	devlink_port = &vf->devlink_port;
-
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi)
-		return -EINVAL;
-
-	attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
-	attrs.pci_vf.pf = pf->hw.bus.func;
-	attrs.pci_vf.vf = vf->vf_id;
-
-	ice_devlink_set_switch_id(pf, &attrs.switch_id);
-
-	devlink_port_attrs_set(devlink_port, &attrs);
-	devlink = priv_to_devlink(pf);
+	params_size =  ARRAY_SIZE(ice_devlink_params);
 
-	err = devlink_port_register(devlink, devlink_port, vsi->idx);
-	if (err) {
-		dev_err(dev, "Failed to create devlink port for VF %d, error %d\n",
-			vf->vf_id, err);
-		return err;
-	}
+	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		params_size--;
 
-	return 0;
+	return devl_params_register(devlink, ice_devlink_params,
+				    params_size);
 }
 
-/**
- * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF
- * @vf: the VF to cleanup
- *
- * Unregisters the devlink_port structure associated with this VF.
- */
-void ice_devlink_destroy_vf_port(struct ice_vf *vf)
+void ice_devlink_unregister_params(struct ice_pf *pf)
 {
-	devl_rate_leaf_destroy(&vf->devlink_port);
-	devlink_port_unregister(&vf->devlink_port);
+	devl_params_unregister(priv_to_devlink(pf), ice_devlink_params,
+			       ARRAY_SIZE(ice_devlink_params));
 }
 
 #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
@@ -1976,8 +1719,8 @@ void ice_devlink_init_regions(struct ice_pf *pf)
 	u64 nvm_size, sram_size;
 
 	nvm_size = pf->hw.flash.flash_size;
-	pf->nvm_region = devlink_region_create(devlink, &ice_nvm_region_ops, 1,
-					       nvm_size);
+	pf->nvm_region = devl_region_create(devlink, &ice_nvm_region_ops, 1,
+					    nvm_size);
 	if (IS_ERR(pf->nvm_region)) {
 		dev_err(dev, "failed to create NVM devlink region, err %ld\n",
 			PTR_ERR(pf->nvm_region));
@@ -1985,17 +1728,17 @@ void ice_devlink_init_regions(struct ice_pf *pf)
 	}
 
 	sram_size = pf->hw.flash.sr_words * 2u;
-	pf->sram_region = devlink_region_create(devlink, &ice_sram_region_ops,
-						1, sram_size);
+	pf->sram_region = devl_region_create(devlink, &ice_sram_region_ops,
+					     1, sram_size);
 	if (IS_ERR(pf->sram_region)) {
 		dev_err(dev, "failed to create shadow-ram devlink region, err %ld\n",
 			PTR_ERR(pf->sram_region));
 		pf->sram_region = NULL;
 	}
 
-	pf->devcaps_region = devlink_region_create(devlink,
-						   &ice_devcaps_region_ops, 10,
-						   ICE_AQ_MAX_BUF_LEN);
+	pf->devcaps_region = devl_region_create(devlink,
+						&ice_devcaps_region_ops, 10,
+						ICE_AQ_MAX_BUF_LEN);
 	if (IS_ERR(pf->devcaps_region)) {
 		dev_err(dev, "failed to create device-caps devlink region, err %ld\n",
 			PTR_ERR(pf->devcaps_region));
@@ -2012,11 +1755,11 @@ void ice_devlink_init_regions(struct ice_pf *pf)
 void ice_devlink_destroy_regions(struct ice_pf *pf)
 {
 	if (pf->nvm_region)
-		devlink_region_destroy(pf->nvm_region);
+		devl_region_destroy(pf->nvm_region);
 
 	if (pf->sram_region)
-		devlink_region_destroy(pf->sram_region);
+		devl_region_destroy(pf->sram_region);
 
 	if (pf->devcaps_region)
-		devlink_region_destroy(pf->devcaps_region);
+		devl_region_destroy(pf->devcaps_region);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/devlink/devlink.h
index d291c0e2e17b..d291c0e2e17b 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.h
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
new file mode 100644
index 000000000000..13e6790d3cae
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -0,0 +1,430 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Intel Corporation. */
+
+#include <linux/vmalloc.h>
+
+#include "ice.h"
+#include "devlink.h"
+
+static int ice_active_port_option = -1;
+
+/**
+ * ice_devlink_port_opt_speed_str - convert speed to a string
+ * @speed: speed value
+ */
+static const char *ice_devlink_port_opt_speed_str(u8 speed)
+{
+	switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) {
+	case ICE_AQC_PORT_OPT_MAX_LANE_100M:
+		return "0.1";
+	case ICE_AQC_PORT_OPT_MAX_LANE_1G:
+		return "1";
+	case ICE_AQC_PORT_OPT_MAX_LANE_2500M:
+		return "2.5";
+	case ICE_AQC_PORT_OPT_MAX_LANE_5G:
+		return "5";
+	case ICE_AQC_PORT_OPT_MAX_LANE_10G:
+		return "10";
+	case ICE_AQC_PORT_OPT_MAX_LANE_25G:
+		return "25";
+	case ICE_AQC_PORT_OPT_MAX_LANE_50G:
+		return "50";
+	case ICE_AQC_PORT_OPT_MAX_LANE_100G:
+		return "100";
+	}
+
+	return "-";
+}
+
+#define ICE_PORT_OPT_DESC_LEN	50
+/**
+ * ice_devlink_port_options_print - Print available port split options
+ * @pf: the PF to print split port options
+ *
+ * Prints a table with available port split options and max port speeds
+ */
+static void ice_devlink_port_options_print(struct ice_pf *pf)
+{
+	u8 i, j, options_count, cnt, speed, pending_idx, active_idx;
+	struct ice_aqc_get_port_options_elem *options, *opt;
+	struct device *dev = ice_pf_to_dev(pf);
+	bool active_valid, pending_valid;
+	char desc[ICE_PORT_OPT_DESC_LEN];
+	const char *str;
+	int status;
+
+	options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV,
+			  sizeof(*options), GFP_KERNEL);
+	if (!options)
+		return;
+
+	for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) {
+		opt = options + i * ICE_AQC_PORT_OPT_MAX;
+		options_count = ICE_AQC_PORT_OPT_MAX;
+		active_valid = 0;
+
+		status = ice_aq_get_port_options(&pf->hw, opt, &options_count,
+						 i, true, &active_idx,
+						 &active_valid, &pending_idx,
+						 &pending_valid);
+		if (status) {
+			dev_dbg(dev, "Couldn't read port option for port %d, err %d\n",
+				i, status);
+			goto err;
+		}
+	}
+
+	dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n");
+	dev_dbg(dev, "Status  Split      Quad 0          Quad 1\n");
+	dev_dbg(dev, "        count  L0  L1  L2  L3  L4  L5  L6  L7\n");
+
+	for (i = 0; i < options_count; i++) {
+		cnt = 0;
+
+		if (i == ice_active_port_option)
+			str = "Active";
+		else if ((i == pending_idx) && pending_valid)
+			str = "Pending";
+		else
+			str = "";
+
+		cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
+				"%-8s", str);
+
+		cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
+				"%-6u", options[i].pmd);
+
+		for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) {
+			speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed;
+			str = ice_devlink_port_opt_speed_str(speed);
+			cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt,
+					"%3s ", str);
+		}
+
+		dev_dbg(dev, "%s\n", desc);
+	}
+
+err:
+	kfree(options);
+}
+
+/**
+ * ice_devlink_aq_set_port_option - Send set port option admin queue command
+ * @pf: the PF to print split port options
+ * @option_idx: selected port option
+ * @extack: extended netdev ack structure
+ *
+ * Sends set port option admin queue command with selected port option and
+ * calls NVM write activate.
+ */
+static int
+ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx,
+			       struct netlink_ext_ack *extack)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int status;
+
+	status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx);
+	if (status) {
+		dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n",
+			status, pf->hw.adminq.sq_last_status);
+		NL_SET_ERR_MSG_MOD(extack, "Port split request failed");
+		return -EIO;
+	}
+
+	status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE);
+	if (status) {
+		dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
+			status, pf->hw.adminq.sq_last_status);
+		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
+		return -EIO;
+	}
+
+	status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL);
+	if (status) {
+		dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n",
+			status, pf->hw.adminq.sq_last_status);
+		NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data");
+		ice_release_nvm(&pf->hw);
+		return -EIO;
+	}
+
+	ice_release_nvm(&pf->hw);
+
+	NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split");
+	return 0;
+}
+
+/**
+ * ice_devlink_port_split - .port_split devlink handler
+ * @devlink: devlink instance structure
+ * @port: devlink port structure
+ * @count: number of ports to split to
+ * @extack: extended netdev ack structure
+ *
+ * Callback for the devlink .port_split operation.
+ *
+ * Unfortunately, the devlink expression of available options is limited
+ * to just a number, so search for an FW port option which supports
+ * the specified number. As there could be multiple FW port options with
+ * the same port split count, allow switching between them. When the same
+ * port split count request is issued again, switch to the next FW port
+ * option with the same port split count.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port,
+		       unsigned int count, struct netlink_ext_ack *extack)
+{
+	struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX];
+	u8 i, j, active_idx, pending_idx, new_option;
+	struct ice_pf *pf = devlink_priv(devlink);
+	u8 option_count = ICE_AQC_PORT_OPT_MAX;
+	struct device *dev = ice_pf_to_dev(pf);
+	bool active_valid, pending_valid;
+	int status;
+
+	status = ice_aq_get_port_options(&pf->hw, options, &option_count,
+					 0, true, &active_idx, &active_valid,
+					 &pending_idx, &pending_valid);
+	if (status) {
+		dev_dbg(dev, "Couldn't read port split options, err = %d\n",
+			status);
+		NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options");
+		return -EIO;
+	}
+
+	new_option = ICE_AQC_PORT_OPT_MAX;
+	active_idx = pending_valid ? pending_idx : active_idx;
+	for (i = 1; i <= option_count; i++) {
+		/* In order to allow switching between FW port options with
+		 * the same port split count, search for a new option starting
+		 * from the active/pending option (with array wrap around).
+		 */
+		j = (active_idx + i) % option_count;
+
+		if (count == options[j].pmd) {
+			new_option = j;
+			break;
+		}
+	}
+
+	if (new_option == active_idx) {
+		dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n",
+			count);
+		NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set");
+		ice_devlink_port_options_print(pf);
+		return -EINVAL;
+	}
+
+	if (new_option == ICE_AQC_PORT_OPT_MAX) {
+		dev_dbg(dev, "request to split: count: %u not found\n", count);
+		NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config");
+		ice_devlink_port_options_print(pf);
+		return -EINVAL;
+	}
+
+	status = ice_devlink_aq_set_port_option(pf, new_option, extack);
+	if (status)
+		return status;
+
+	ice_devlink_port_options_print(pf);
+
+	return 0;
+}
+
+/**
+ * ice_devlink_port_unsplit - .port_unsplit devlink handler
+ * @devlink: devlink instance structure
+ * @port: devlink port structure
+ * @extack: extended netdev ack structure
+ *
+ * Callback for the devlink .port_unsplit operation.
+ * Calls ice_devlink_port_split with split count set to 1.
+ * There could be no FW option available with split count 1.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port,
+			 struct netlink_ext_ack *extack)
+{
+	return ice_devlink_port_split(devlink, port, 1, extack);
+}
+
+/**
+ * ice_devlink_set_port_split_options - Set port split options
+ * @pf: the PF to set port split options
+ * @attrs: devlink attributes
+ *
+ * Sets devlink port split options based on available FW port options
+ */
+static void
+ice_devlink_set_port_split_options(struct ice_pf *pf,
+				   struct devlink_port_attrs *attrs)
+{
+	struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX];
+	u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX;
+	bool active_valid, pending_valid;
+	int status;
+
+	status = ice_aq_get_port_options(&pf->hw, options, &option_count,
+					 0, true, &active_idx, &active_valid,
+					 &pending_idx, &pending_valid);
+	if (status) {
+		dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n",
+			status);
+		return;
+	}
+
+	/* find the biggest available port split count */
+	for (i = 0; i < option_count; i++)
+		attrs->lanes = max_t(int, attrs->lanes, options[i].pmd);
+
+	attrs->splittable = attrs->lanes ? 1 : 0;
+	ice_active_port_option = active_idx;
+}
+
+static const struct devlink_port_ops ice_devlink_port_ops = {
+	.port_split = ice_devlink_port_split,
+	.port_unsplit = ice_devlink_port_unsplit,
+};
+
+/**
+ * ice_devlink_set_switch_id - Set unique switch id based on pci dsn
+ * @pf: the PF to create a devlink port for
+ * @ppid: struct with switch id information
+ */
+static void
+ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid)
+{
+	struct pci_dev *pdev = pf->pdev;
+	u64 id;
+
+	id = pci_get_dsn(pdev);
+
+	ppid->id_len = sizeof(id);
+	put_unaligned_be64(id, &ppid->id);
+}
+
+/**
+ * ice_devlink_create_pf_port - Create a devlink port for this PF
+ * @pf: the PF to create a devlink port for
+ *
+ * Create and register a devlink_port for this PF.
+ * This function has to be called under devl_lock.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_devlink_create_pf_port(struct ice_pf *pf)
+{
+	struct devlink_port_attrs attrs = {};
+	struct devlink_port *devlink_port;
+	struct devlink *devlink;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	int err;
+
+	devlink = priv_to_devlink(pf);
+
+	dev = ice_pf_to_dev(pf);
+
+	devlink_port = &pf->devlink_port;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return -EIO;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	attrs.phys.port_number = pf->hw.bus.func;
+
+	/* As FW supports only port split options for whole device,
+	 * set port split options only for first PF.
+	 */
+	if (pf->hw.pf_id == 0)
+		ice_devlink_set_port_split_options(pf, &attrs);
+
+	ice_devlink_set_switch_id(pf, &attrs.switch_id);
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+
+	err = devl_port_register_with_ops(devlink, devlink_port, vsi->idx,
+					  &ice_devlink_port_ops);
+	if (err) {
+		dev_err(dev, "Failed to create devlink port for PF %d, error %d\n",
+			pf->hw.pf_id, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF
+ * @pf: the PF to cleanup
+ *
+ * Unregisters the devlink_port structure associated with this PF.
+ * This function has to be called under devl_lock.
+ */
+void ice_devlink_destroy_pf_port(struct ice_pf *pf)
+{
+	devl_port_unregister(&pf->devlink_port);
+}
+
+/**
+ * ice_devlink_create_vf_port - Create a devlink port for this VF
+ * @vf: the VF to create a port for
+ *
+ * Create and register a devlink_port for this VF.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_devlink_create_vf_port(struct ice_vf *vf)
+{
+	struct devlink_port_attrs attrs = {};
+	struct devlink_port *devlink_port;
+	struct devlink *devlink;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	struct ice_pf *pf;
+	int err;
+
+	pf = vf->pf;
+	dev = ice_pf_to_dev(pf);
+	devlink_port = &vf->devlink_port;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -EINVAL;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
+	attrs.pci_vf.pf = pf->hw.bus.func;
+	attrs.pci_vf.vf = vf->vf_id;
+
+	ice_devlink_set_switch_id(pf, &attrs.switch_id);
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+	devlink = priv_to_devlink(pf);
+
+	err = devlink_port_register(devlink, devlink_port, vsi->idx);
+	if (err) {
+		dev_err(dev, "Failed to create devlink port for VF %d, error %d\n",
+			vf->vf_id, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF
+ * @vf: the VF to cleanup
+ *
+ * Unregisters the devlink_port structure associated with this VF.
+ */
+void ice_devlink_destroy_vf_port(struct ice_vf *vf)
+{
+	devl_rate_leaf_destroy(&vf->devlink_port);
+	devlink_port_unregister(&vf->devlink_port);
+}
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
new file mode 100644
index 000000000000..9223bcdb6444
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024, Intel Corporation. */
+
+#ifndef _DEVLINK_PORT_H_
+#define _DEVLINK_PORT_H_
+
+int ice_devlink_create_pf_port(struct ice_pf *pf);
+void ice_devlink_destroy_pf_port(struct ice_pf *pf);
+int ice_devlink_create_vf_port(struct ice_vf *vf);
+void ice_devlink_destroy_vf_port(struct ice_vf *vf);
+
+#endif /* _DEVLINK_PORT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 365c03d1c462..6ad8002b22e1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -77,6 +77,7 @@
 #include "ice_gnss.h"
 #include "ice_irq.h"
 #include "ice_dpll.h"
+#include "ice_adapter.h"
 
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
@@ -330,7 +331,6 @@ struct ice_vsi {
 	struct net_device *netdev;
 	struct ice_sw *vsw;		 /* switch this VSI is on */
 	struct ice_pf *back;		 /* back pointer to PF */
-	struct ice_port_info *port_info; /* back pointer to port_info */
 	struct ice_rx_ring **rx_rings;	 /* Rx ring array */
 	struct ice_tx_ring **tx_rings;	 /* Tx ring array */
 	struct ice_q_vector **q_vectors; /* q_vector array */
@@ -348,12 +348,9 @@ struct ice_vsi {
 	/* tell if only dynamic irq allocation is allowed */
 	bool irq_dyn_alloc;
 
-	enum ice_vsi_type type;
 	u16 vsi_num;			/* HW (absolute) index of this VSI */
 	u16 idx;			/* software index in pf->vsi[] */
 
-	struct ice_vf *vf;		/* VF associated with this VSI */
-
 	u16 num_gfltr;
 	u16 num_bfltr;
 
@@ -445,12 +442,18 @@ struct ice_vsi {
 	u8 old_numtc;
 	u16 old_ena_tc;
 
-	struct ice_channel *ch;
-
 	/* setup back reference, to which aggregator node this VSI
 	 * corresponds to
 	 */
 	struct ice_agg_node *agg_node;
+
+	struct_group_tagged(ice_vsi_cfg_params, params,
+		struct ice_port_info *port_info; /* back pointer to port_info */
+		struct ice_channel *ch; /* VSI's channel structure, may be NULL */
+		struct ice_vf *vf; /* VF associated with this VSI, may be NULL */
+		u32 flags; /* VSI flags used for rebuild and configuration */
+		enum ice_vsi_type type; /* the type of the VSI */
+	);
 } ____cacheline_internodealigned_in_smp;
 
 /* struct that defines an interrupt vector */
@@ -458,7 +461,7 @@ struct ice_q_vector {
 	struct ice_vsi *vsi;
 
 	u16 v_idx;			/* index in the vsi->q_vector array. */
-	u16 reg_idx;
+	u16 reg_idx;			/* PF relative register index */
 	u8 num_ring_rx;			/* total number of Rx rings in vector */
 	u8 num_ring_tx;			/* total number of Tx rings in vector */
 	u8 wb_on_itr:1;			/* if true, WB on ITR is enabled */
@@ -480,6 +483,7 @@ struct ice_q_vector {
 	char name[ICE_INT_NAME_STR_LEN];
 
 	u16 total_events;	/* net_dim(): number of interrupts processed */
+	u16 vf_reg_idx;		/* VF relative register index */
 	struct msi_map irq;
 } ____cacheline_internodealigned_in_smp;
 
@@ -522,17 +526,10 @@ enum ice_misc_thread_tasks {
 };
 
 struct ice_eswitch {
-	struct ice_vsi *control_vsi;
 	struct ice_vsi *uplink_vsi;
 	struct ice_esw_br_offloads *br_offloads;
 	struct xarray reprs;
 	bool is_running;
-	/* struct to allow cp queues management optimization */
-	struct {
-		int to_reach;
-		int value;
-		bool is_reaching;
-	} qs;
 };
 
 struct ice_agg_node {
@@ -544,6 +541,7 @@ struct ice_agg_node {
 
 struct ice_pf {
 	struct pci_dev *pdev;
+	struct ice_adapter *adapter;
 
 	struct devlink_region *nvm_region;
 	struct devlink_region *sram_region;
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
new file mode 100644
index 000000000000..52d15ef7f4b1
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-FileCopyrightText: Copyright Red Hat
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+#include "ice_adapter.h"
+
+static DEFINE_XARRAY(ice_adapters);
+
+/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
+#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
+#define INDEX_FIELD_BUS    GENMASK(12, 5)
+#define INDEX_FIELD_SLOT   GENMASK(4, 0)
+
+static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+{
+	unsigned int domain = pci_domain_nr(pdev->bus);
+
+	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
+
+	return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
+	       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
+	       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
+}
+
+static struct ice_adapter *ice_adapter_new(void)
+{
+	struct ice_adapter *adapter;
+
+	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+	if (!adapter)
+		return NULL;
+
+	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
+	refcount_set(&adapter->refcount, 1);
+
+	return adapter;
+}
+
+static void ice_adapter_free(struct ice_adapter *adapter)
+{
+	kfree(adapter);
+}
+
+DEFINE_FREE(ice_adapter_free, struct ice_adapter*, if (_T) ice_adapter_free(_T))
+
+/**
+ * ice_adapter_get - Get a shared ice_adapter structure.
+ * @pdev: Pointer to the pci_dev whose driver is getting the ice_adapter.
+ *
+ * Gets a pointer to a shared ice_adapter structure. Physical functions (PFs)
+ * of the same multi-function PCI device share one ice_adapter structure.
+ * The ice_adapter is reference-counted. The PF driver must use ice_adapter_put
+ * to release its reference.
+ *
+ * Context: Process, may sleep.
+ * Return:  Pointer to ice_adapter on success.
+ *          ERR_PTR() on error. -ENOMEM is the only possible error.
+ */
+struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+{
+	struct ice_adapter *ret, __free(ice_adapter_free) *adapter = NULL;
+	unsigned long index = ice_adapter_index(pdev);
+
+	adapter = ice_adapter_new();
+	if (!adapter)
+		return ERR_PTR(-ENOMEM);
+
+	xa_lock(&ice_adapters);
+	ret = __xa_cmpxchg(&ice_adapters, index, NULL, adapter, GFP_KERNEL);
+	if (xa_is_err(ret)) {
+		ret = ERR_PTR(xa_err(ret));
+		goto unlock;
+	}
+	if (ret) {
+		refcount_inc(&ret->refcount);
+		goto unlock;
+	}
+	ret = no_free_ptr(adapter);
+unlock:
+	xa_unlock(&ice_adapters);
+	return ret;
+}
+
+/**
+ * ice_adapter_put - Release a reference to the shared ice_adapter structure.
+ * @pdev: Pointer to the pci_dev whose driver is releasing the ice_adapter.
+ *
+ * Releases the reference to ice_adapter previously obtained with
+ * ice_adapter_get.
+ *
+ * Context: Any.
+ */
+void ice_adapter_put(const struct pci_dev *pdev)
+{
+	unsigned long index = ice_adapter_index(pdev);
+	struct ice_adapter *adapter;
+
+	xa_lock(&ice_adapters);
+	adapter = xa_load(&ice_adapters, index);
+	if (WARN_ON(!adapter))
+		goto unlock;
+
+	if (!refcount_dec_and_test(&adapter->refcount))
+		goto unlock;
+
+	WARN_ON(__xa_erase(&ice_adapters, index) != adapter);
+	ice_adapter_free(adapter);
+unlock:
+	xa_unlock(&ice_adapters);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
new file mode 100644
index 000000000000..9d11014ec02f
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-FileCopyrightText: Copyright Red Hat */
+
+#ifndef _ICE_ADAPTER_H_
+#define _ICE_ADAPTER_H_
+
+#include <linux/spinlock_types.h>
+#include <linux/refcount_types.h>
+
+struct pci_dev;
+
+/**
+ * struct ice_adapter - PCI adapter resources shared across PFs
+ * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME
+ *                        register of the PTP clock.
+ * @refcount: Reference count. struct ice_pf objects hold the references.
+ */
+struct ice_adapter {
+	/* For access to the GLTSYN_TIME register */
+	spinlock_t ptp_gltsyn_time_lock;
+
+	refcount_t refcount;
+};
+
+struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
+void ice_adapter_put(const struct pci_dev *pdev);
+
+#endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 1f3e7a6903e5..e76c388b9905 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -121,6 +121,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
+#define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
 #define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
 #define ICE_AQC_BIT_ROCEV2_LAG				0x01
 #define ICE_AQC_BIT_SRIOV_LAG				0x02
@@ -264,6 +265,8 @@ struct ice_aqc_set_port_params {
 #define ICE_AQC_RES_TYPE_FLAG_SHARED			BIT(7)
 #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM		BIT(12)
 #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX		BIT(13)
+#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED		BIT(14)
+#define ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL		BIT(15)
 
 #define ICE_AQC_RES_TYPE_FLAG_DEDICATED			0x00
 
@@ -808,6 +811,23 @@ struct ice_aqc_get_topo {
 	__le32 addr_low;
 };
 
+/* Get/Set Tx Topology (indirect 0x0418/0x0417) */
+struct ice_aqc_get_set_tx_topo {
+	u8 set_flags;
+#define ICE_AQC_TX_TOPO_FLAGS_CORRER		BIT(0)
+#define ICE_AQC_TX_TOPO_FLAGS_SRC_RAM		BIT(1)
+#define ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW		BIT(4)
+#define ICE_AQC_TX_TOPO_FLAGS_ISSUED		BIT(5)
+
+	u8 get_flags;
+#define ICE_AQC_TX_TOPO_GET_RAM		2
+
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
 /* Update TSE (indirect 0x0403)
  * Get TSE (indirect 0x0404)
  * Add TSE (indirect 0x0401)
@@ -1664,6 +1684,15 @@ struct ice_aqc_nvm {
 
 #define ICE_AQC_NVM_START_POINT			0
 
+#define ICE_AQC_NVM_TX_TOPO_MOD_ID		0x14B
+
+struct ice_aqc_nvm_tx_topo_user_sel {
+	__le16 length;
+	u8 data;
+#define ICE_AQC_NVM_TX_TOPO_USER_SEL	BIT(4)
+	u8 reserved;
+};
+
 /* NVM Checksum Command (direct, 0x0706) */
 struct ice_aqc_nvm_checksum {
 	u8 flags;
@@ -2536,6 +2565,7 @@ struct ice_aq_desc {
 		struct ice_aqc_get_link_topo get_link_topo;
 		struct ice_aqc_i2c read_write_i2c;
 		struct ice_aqc_read_i2c_resp read_i2c_resp;
+		struct ice_aqc_get_set_tx_topo get_set_tx_topo;
 	} params;
 };
 
@@ -2642,6 +2672,10 @@ enum ice_adminq_opc {
 	ice_aqc_opc_query_sched_res			= 0x0412,
 	ice_aqc_opc_remove_rl_profiles			= 0x0415,
 
+	/* tx topology commands */
+	ice_aqc_opc_set_tx_topo				= 0x0417,
+	ice_aqc_opc_get_tx_topo				= 0x0418,
+
 	/* PHY commands */
 	ice_aqc_opc_get_phy_caps			= 0x0600,
 	ice_aqc_opc_set_phy_cfg				= 0x0601,
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index a545a7917e4f..687f6cb2b917 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -121,7 +121,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 	q_vector->irq.index = -ENOENT;
 
 	if (vsi->type == ICE_VSI_VF) {
-		q_vector->reg_idx = ice_calc_vf_reg_idx(vsi->vf, q_vector);
+		ice_calc_vf_reg_idx(vsi->vf, q_vector);
 		goto out;
 	} else if (vsi->type == ICE_VSI_CTRL && vsi->vf) {
 		struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi);
@@ -145,6 +145,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 
 skip_alloc:
 	q_vector->reg_idx = q_vector->irq.index;
+	q_vector->vf_reg_idx = q_vector->irq.index;
 
 	/* only set affinity_mask if the CPU is online */
 	if (cpu_online(v_idx))
@@ -264,30 +265,6 @@ static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8
 }
 
 /**
- * ice_eswitch_calc_txq_handle
- * @ring: pointer to ring which unique index is needed
- *
- * To correctly work with many netdevs ring->q_index of Tx rings on switchdev
- * VSI can repeat. Hardware ring setup requires unique q_index. Calculate it
- * here by finding index in vsi->tx_rings of this ring.
- *
- * Return ICE_INVAL_Q_INDEX when index wasn't found. Should never happen,
- * because VSI is get from ring->vsi, so it has to be present in this VSI.
- */
-static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring)
-{
-	const struct ice_vsi *vsi = ring->vsi;
-	int i;
-
-	ice_for_each_txq(vsi, i) {
-		if (vsi->tx_rings[i] == ring)
-			return i;
-	}
-
-	return ICE_INVAL_Q_INDEX;
-}
-
-/**
  * ice_cfg_xps_tx_ring - Configure XPS for a Tx ring
  * @ring: The Tx ring to configure
  *
@@ -353,9 +330,6 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 		tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id;
 		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
 		break;
-	case ICE_VSI_SWITCHDEV_CTRL:
-		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
-		break;
 	default:
 		return;
 	}
@@ -479,6 +453,14 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	/* Rx queue threshold in units of 64 */
 	rlan_ctx.lrxqthresh = 1;
 
+	/* PF acts as uplink for switchdev; set flex descriptor with src_vsi
+	 * metadata and flags to allow redirecting to PR netdev
+	 */
+	if (ice_is_eswitch_mode_switchdev(vsi->back)) {
+		ring->flags |= ICE_RX_FLAGS_MULTIDEV;
+		rxdid = ICE_RXDID_FLEX_NIC_2;
+	}
+
 	/* Enable Flexible Descriptors in the queue context which
 	 * allows this driver to select a specific receive descriptor format
 	 * increasing context priority to pick up profile ID; default is 0x01;
@@ -919,14 +901,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring,
 	/* Add unique software queue handle of the Tx queue per
 	 * TC into the VSI Tx ring
 	 */
-	if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) {
-		ring->q_handle = ice_eswitch_calc_txq_handle(ring);
-
-		if (ring->q_handle == ICE_INVAL_Q_INDEX)
-			return -ENODEV;
-	} else {
-		ring->q_handle = ice_calc_txq_handle(vsi, ring, tc);
-	}
+	ring->q_handle = ice_calc_txq_handle(vsi, ring, tc);
 
 	if (ch)
 		status = ice_ena_vsi_txq(vsi->port_info, ch->ch_vsi->idx, 0,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index d9f6cc71d900..5649b257e631 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -160,10 +160,16 @@ static int ice_set_mac_type(struct ice_hw *hw)
 	case ICE_DEV_ID_E825C_SGMII:
 		hw->mac_type = ICE_MAC_GENERIC_3K_E825;
 		break;
-	case ICE_DEV_ID_E830_BACKPLANE:
-	case ICE_DEV_ID_E830_QSFP56:
-	case ICE_DEV_ID_E830_SFP:
-	case ICE_DEV_ID_E830_SFP_DD:
+	case ICE_DEV_ID_E830CC_BACKPLANE:
+	case ICE_DEV_ID_E830CC_QSFP56:
+	case ICE_DEV_ID_E830CC_SFP:
+	case ICE_DEV_ID_E830CC_SFP_DD:
+	case ICE_DEV_ID_E830C_BACKPLANE:
+	case ICE_DEV_ID_E830_XXV_BACKPLANE:
+	case ICE_DEV_ID_E830C_QSFP:
+	case ICE_DEV_ID_E830_XXV_QSFP:
+	case ICE_DEV_ID_E830C_SFP:
+	case ICE_DEV_ID_E830_XXV_SFP:
 		hw->mac_type = ICE_MAC_E830;
 		break;
 	default:
@@ -1142,6 +1148,8 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
 	mutex_init(&hw->tnl_lock);
+	ice_init_chk_recipe_reuse_support(hw);
+
 	return 0;
 
 err_unroll_fltr_mgmt_struct:
@@ -1615,6 +1623,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
 	case ice_aqc_opc_set_port_params:
 	case ice_aqc_opc_get_vlan_mode_parameters:
 	case ice_aqc_opc_set_vlan_mode_parameters:
+	case ice_aqc_opc_set_tx_topo:
+	case ice_aqc_opc_get_tx_topo:
 	case ice_aqc_opc_add_recipe:
 	case ice_aqc_opc_recipe_to_profile:
 	case ice_aqc_opc_get_recipe:
@@ -2171,6 +2181,9 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n",
 			  prefix, caps->sriov_lag);
 		break;
+	case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
+		caps->tx_sched_topo_comp_mode_en = (number == 1);
+		break;
 	default:
 		/* Not one of the recognized common capabilities */
 		found = false;
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 6e20ee610022..a94e7072b570 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -3,7 +3,7 @@
 
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
 
 /**
  * ice_dcb_get_ena_tc - return bitmap of enabled TCs
@@ -291,7 +291,6 @@ static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked)
 
 		switch (vsi->type) {
 		case ICE_VSI_CHNL:
-		case ICE_VSI_SWITCHDEV_CTRL:
 		case ICE_VSI_PF:
 			if (ena)
 				ice_ena_vsi(vsi, locked);
@@ -776,8 +775,7 @@ void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
 		/* no need to proceed with remaining cfg if it is CHNL
 		 * or switchdev VSI
 		 */
-		if (vsi->type == ICE_VSI_CHNL ||
-		    vsi->type == ICE_VSI_SWITCHDEV_CTRL)
+		if (vsi->type == ICE_VSI_CHNL)
 			continue;
 
 		ice_vsi_map_rings_to_vectors(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index fc91c4d41186..ce5034ed2b24 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -4,6 +4,7 @@
 #include "ice_common.h"
 #include "ice.h"
 #include "ice_ddp.h"
+#include "ice_sched.h"
 
 /* For supporting double VLAN mode, it is necessary to enable or disable certain
  * boost tcam entries. The metadata labels names that match the following
@@ -721,6 +722,12 @@ static bool ice_is_gtp_c_profile(u16 prof_idx)
 	}
 }
 
+static bool ice_is_pfcp_profile(u16 prof_idx)
+{
+	return prof_idx >= ICE_PROFID_IPV4_PFCP_NODE &&
+	       prof_idx <= ICE_PROFID_IPV6_PFCP_SESSION;
+}
+
 /**
  * ice_get_sw_prof_type - determine switch profile type
  * @hw: pointer to the HW structure
@@ -738,6 +745,9 @@ static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw,
 	if (ice_is_gtp_u_profile(prof_idx))
 		return ICE_PROF_TUN_GTPU;
 
+	if (ice_is_pfcp_profile(prof_idx))
+		return ICE_PROF_TUN_PFCP;
+
 	for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) {
 		/* UDP tunnel will have UDP_OF protocol ID and VNI offset */
 		if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF &&
@@ -1424,14 +1434,14 @@ ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr,
 		goto exit;
 	}
 
-	conf_idx = le32_to_cpu(seg->signed_seg_idx);
-	start = le32_to_cpu(seg->signed_buf_start);
 	count = le32_to_cpu(seg->signed_buf_count);
-
 	state = ice_download_pkg_sig_seg(hw, seg);
-	if (state)
+	if (state || !count)
 		goto exit;
 
+	conf_idx = le32_to_cpu(seg->signed_seg_idx);
+	start = le32_to_cpu(seg->signed_buf_start);
+
 	state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start,
 					    count);
 
@@ -2263,3 +2273,211 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf,
 
 	return state;
 }
+
+/**
+ * ice_get_set_tx_topo - get or set Tx topology
+ * @hw: pointer to the HW struct
+ * @buf: pointer to Tx topology buffer
+ * @buf_size: buffer size
+ * @cd: pointer to command details structure or NULL
+ * @flags: pointer to descriptor flags
+ * @set: 0-get, 1-set topology
+ *
+ * The function will get or set Tx topology
+ *
+ * Return: zero when set was successful, negative values otherwise.
+ */
+static int
+ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
+		    struct ice_sq_cd *cd, u8 *flags, bool set)
+{
+	struct ice_aqc_get_set_tx_topo *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	cmd = &desc.params.get_set_tx_topo;
+	if (set) {
+		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo);
+		cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED;
+		/* requested to update a new topology, not a default topology */
+		if (buf)
+			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
+					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
+
+		if (ice_is_e825c(hw))
+			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	} else {
+		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
+		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
+	}
+
+	if (!ice_is_e825c(hw))
+		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+	if (status)
+		return status;
+	/* read the return flag values (first byte) for get operation */
+	if (!set && flags)
+		*flags = desc.params.get_set_tx_topo.set_flags;
+
+	return 0;
+}
+
+/**
+ * ice_cfg_tx_topo - Initialize new Tx topology if available
+ * @hw: pointer to the HW struct
+ * @buf: pointer to Tx topology buffer
+ * @len: buffer size
+ *
+ * The function will apply the new Tx topology from the package buffer
+ * if available.
+ *
+ * Return: zero when update was successful, negative values otherwise.
+ */
+int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len)
+{
+	u8 *current_topo, *new_topo = NULL;
+	struct ice_run_time_cfg_seg *seg;
+	struct ice_buf_hdr *section;
+	struct ice_pkg_hdr *pkg_hdr;
+	enum ice_ddp_state state;
+	u16 offset, size = 0;
+	u32 reg = 0;
+	int status;
+	u8 flags;
+
+	if (!buf || !len)
+		return -EINVAL;
+
+	/* Does FW support new Tx topology mode ? */
+	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) {
+		ice_debug(hw, ICE_DBG_INIT, "FW doesn't support compatibility mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	current_topo = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!current_topo)
+		return -ENOMEM;
+
+	/* Get the current Tx topology */
+	status = ice_get_set_tx_topo(hw, current_topo, ICE_AQ_MAX_BUF_LEN, NULL,
+				     &flags, false);
+
+	kfree(current_topo);
+
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n");
+		return status;
+	}
+
+	/* Is default topology already applied ? */
+	if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "Default topology already applied\n");
+		return -EEXIST;
+	}
+
+	/* Is new topology already applied ? */
+	if ((flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "New topology already applied\n");
+		return -EEXIST;
+	}
+
+	/* Setting topology already issued? */
+	if (flags & ICE_AQC_TX_TOPO_FLAGS_ISSUED) {
+		ice_debug(hw, ICE_DBG_INIT, "Update Tx topology was done by another PF\n");
+		/* Add a small delay before exiting */
+		msleep(2000);
+		return -EEXIST;
+	}
+
+	/* Change the topology from new to default (5 to 9) */
+	if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "Change topology from 5 to 9 layers\n");
+		goto update_topo;
+	}
+
+	pkg_hdr = (struct ice_pkg_hdr *)buf;
+	state = ice_verify_pkg(pkg_hdr, len);
+	if (state) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to verify pkg (err: %d)\n",
+			  state);
+		return -EIO;
+	}
+
+	/* Find runtime configuration segment */
+	seg = (struct ice_run_time_cfg_seg *)
+	      ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE_RUN_TIME_CFG, pkg_hdr);
+	if (!seg) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment is missing\n");
+		return -EIO;
+	}
+
+	if (le32_to_cpu(seg->buf_table.buf_count) < ICE_MIN_S_COUNT) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment count(%d) is wrong\n",
+			  seg->buf_table.buf_count);
+		return -EIO;
+	}
+
+	section = ice_pkg_val_buf(seg->buf_table.buf_array);
+	if (!section || le32_to_cpu(section->section_entry[0].type) !=
+		ICE_SID_TX_5_LAYER_TOPO) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology section type is wrong\n");
+		return -EIO;
+	}
+
+	size = le16_to_cpu(section->section_entry[0].size);
+	offset = le16_to_cpu(section->section_entry[0].offset);
+	if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology section size is wrong\n");
+		return -EIO;
+	}
+
+	/* Make sure the section fits in the buffer */
+	if (offset + size > ICE_PKG_BUF_SIZE) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology buffer > 4K\n");
+		return -EIO;
+	}
+
+	/* Get the new topology buffer */
+	new_topo = ((u8 *)section) + offset;
+
+update_topo:
+	/* Acquire global lock to make sure that set topology issued
+	 * by one PF.
+	 */
+	status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, ICE_RES_WRITE,
+				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n");
+		return status;
+	}
+
+	/* Check if reset was triggered already. */
+	reg = rd32(hw, GLGEN_RSTAT);
+	if (reg & GLGEN_RSTAT_DEVSTATE_M) {
+		/* Reset is in progress, re-init the HW again */
+		ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n");
+		ice_check_reset(hw);
+		return 0;
+	}
+
+	/* Set new topology */
+	status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true);
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n");
+		return status;
+	}
+
+	/* New topology is updated, delay 1 second before issuing the CORER */
+	msleep(1000);
+	ice_reset(hw, ICE_RESET_CORER);
+	/* CORER will clear the global lock, so no explicit call
+	 * required for release.
+	 */
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h
index ff66c2ffb1a2..622543f08b43 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.h
@@ -454,4 +454,6 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld);
 void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
 			   u32 sect_type);
 
+int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len);
+
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index 9dfae9bce758..34fd604132f5 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -16,14 +16,26 @@
 #define ICE_DEV_ID_E823L_1GBE		0x124F
 /* Intel(R) Ethernet Connection E823-L for QSFP */
 #define ICE_DEV_ID_E823L_QSFP		0x151D
+/* Intel(R) Ethernet Controller E830-CC for backplane */
+#define ICE_DEV_ID_E830CC_BACKPLANE	0x12D1
+/* Intel(R) Ethernet Controller E830-CC for QSFP */
+#define ICE_DEV_ID_E830CC_QSFP56	0x12D2
+/* Intel(R) Ethernet Controller E830-CC for SFP */
+#define ICE_DEV_ID_E830CC_SFP		0x12D3
+/* Intel(R) Ethernet Controller E830-CC for SFP-DD */
+#define ICE_DEV_ID_E830CC_SFP_DD	0x12D4
 /* Intel(R) Ethernet Controller E830-C for backplane */
-#define ICE_DEV_ID_E830_BACKPLANE	0x12D1
+#define ICE_DEV_ID_E830C_BACKPLANE	0x12D5
 /* Intel(R) Ethernet Controller E830-C for QSFP */
-#define ICE_DEV_ID_E830_QSFP56		0x12D2
+#define ICE_DEV_ID_E830C_QSFP		0x12D8
 /* Intel(R) Ethernet Controller E830-C for SFP */
-#define ICE_DEV_ID_E830_SFP		0x12D3
-/* Intel(R) Ethernet Controller E830-C for SFP-DD */
-#define ICE_DEV_ID_E830_SFP_DD		0x12D4
+#define ICE_DEV_ID_E830C_SFP		0x12DA
+/* Intel(R) Ethernet Controller E830-XXV for backplane */
+#define ICE_DEV_ID_E830_XXV_BACKPLANE	0x12DC
+/* Intel(R) Ethernet Controller E830-XXV for QSFP */
+#define ICE_DEV_ID_E830_XXV_QSFP	0x12DD
+/* Intel(R) Ethernet Controller E830-XXV for SFP */
+#define ICE_DEV_ID_E830_XXV_SFP		0x12DE
 /* Intel(R) Ethernet Controller E810-C for backplane */
 #define ICE_DEV_ID_E810C_BACKPLANE	0x1591
 /* Intel(R) Ethernet Controller E810-C for QSFP */
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 9069725c71b4..b102db8b829a 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -7,89 +7,10 @@
 #include "ice_eswitch_br.h"
 #include "ice_fltr.h"
 #include "ice_repr.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
 #include "ice_tc_lib.h"
 
 /**
- * ice_eswitch_del_sp_rules - delete adv rules added on PRs
- * @pf: pointer to the PF struct
- *
- * Delete all advanced rules that were used to forward packets with the
- * device's VSI index to the corresponding eswitch ctrl VSI queue.
- */
-static void ice_eswitch_del_sp_rules(struct ice_pf *pf)
-{
-	struct ice_repr *repr;
-	unsigned long id;
-
-	xa_for_each(&pf->eswitch.reprs, id, repr) {
-		if (repr->sp_rule.rid)
-			ice_rem_adv_rule_by_id(&pf->hw, &repr->sp_rule);
-	}
-}
-
-/**
- * ice_eswitch_add_sp_rule - add adv rule with device's VSI index
- * @pf: pointer to PF struct
- * @repr: pointer to the repr struct
- *
- * This function adds advanced rule that forwards packets with
- * device's VSI index to the corresponding eswitch ctrl VSI queue.
- */
-static int ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
-{
-	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
-	struct ice_adv_rule_info rule_info = { 0 };
-	struct ice_adv_lkup_elem *list;
-	struct ice_hw *hw = &pf->hw;
-	const u16 lkups_cnt = 1;
-	int err;
-
-	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
-	if (!list)
-		return -ENOMEM;
-
-	ice_rule_add_src_vsi_metadata(list);
-
-	rule_info.sw_act.flag = ICE_FLTR_TX;
-	rule_info.sw_act.vsi_handle = ctrl_vsi->idx;
-	rule_info.sw_act.fltr_act = ICE_FWD_TO_Q;
-	rule_info.sw_act.fwd_id.q_id = hw->func_caps.common_cap.rxq_first_id +
-				       ctrl_vsi->rxq_map[repr->q_id];
-	rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE;
-	rule_info.flags_info.act_valid = true;
-	rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN;
-	rule_info.src_vsi = repr->src_vsi->idx;
-
-	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info,
-			       &repr->sp_rule);
-	if (err)
-		dev_err(ice_pf_to_dev(pf), "Unable to add slow-path rule for eswitch for PR %d",
-			repr->id);
-
-	kfree(list);
-	return err;
-}
-
-static int
-ice_eswitch_add_sp_rules(struct ice_pf *pf)
-{
-	struct ice_repr *repr;
-	unsigned long id;
-	int err;
-
-	xa_for_each(&pf->eswitch.reprs, id, repr) {
-		err = ice_eswitch_add_sp_rule(pf, repr);
-		if (err) {
-			ice_eswitch_del_sp_rules(pf);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-/**
  * ice_eswitch_setup_env - configure eswitch HW filters
  * @pf: pointer to PF struct
  *
@@ -99,10 +20,13 @@ ice_eswitch_add_sp_rules(struct ice_pf *pf)
 static int ice_eswitch_setup_env(struct ice_pf *pf)
 {
 	struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
-	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 	struct net_device *netdev = uplink_vsi->netdev;
+	bool if_running = netif_running(netdev);
 	struct ice_vsi_vlan_ops *vlan_ops;
-	bool rule_added = false;
+
+	if (if_running && !test_and_set_bit(ICE_VSI_DOWN, uplink_vsi->state))
+		if (ice_down(uplink_vsi))
+			return -ENODEV;
 
 	ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
 
@@ -112,98 +36,53 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	netif_addr_unlock_bh(netdev);
 
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
+		goto err_vlan_zero;
+
+	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
+			     ICE_FLTR_RX))
 		goto err_def_rx;
 
-	if (!ice_is_dflt_vsi_in_use(uplink_vsi->port_info)) {
-		if (ice_set_dflt_vsi(uplink_vsi))
-			goto err_def_rx;
-		rule_added = true;
-	}
+	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
+			     ICE_FLTR_TX))
+		goto err_def_tx;
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 	if (vlan_ops->dis_rx_filtering(uplink_vsi))
-		goto err_dis_rx;
+		goto err_vlan_filtering;
 
 	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
 		goto err_override_uplink;
 
-	if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override))
-		goto err_override_control;
-
 	if (ice_vsi_update_local_lb(uplink_vsi, true))
 		goto err_override_local_lb;
 
+	if (if_running && ice_up(uplink_vsi))
+		goto err_up;
+
 	return 0;
 
+err_up:
+	ice_vsi_update_local_lb(uplink_vsi, false);
 err_override_local_lb:
-	ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override);
-err_override_control:
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 err_override_uplink:
 	vlan_ops->ena_rx_filtering(uplink_vsi);
-err_dis_rx:
-	if (rule_added)
-		ice_clear_dflt_vsi(uplink_vsi);
+err_vlan_filtering:
+	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
+			 ICE_FLTR_TX);
+err_def_tx:
+	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
+			 ICE_FLTR_RX);
 err_def_rx:
+	ice_vsi_del_vlan_zero(uplink_vsi);
+err_vlan_zero:
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
 				       ICE_FWD_TO_VSI);
-	return -ENODEV;
-}
-
-/**
- * ice_eswitch_remap_rings_to_vectors - reconfigure rings of eswitch ctrl VSI
- * @eswitch: pointer to eswitch struct
- *
- * In eswitch number of allocated Tx/Rx rings is equal.
- *
- * This function fills q_vectors structures associated with representor and
- * move each ring pairs to port representor netdevs. Each port representor
- * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to
- * number of VFs.
- */
-static void ice_eswitch_remap_rings_to_vectors(struct ice_eswitch *eswitch)
-{
-	struct ice_vsi *vsi = eswitch->control_vsi;
-	unsigned long repr_id = 0;
-	int q_id;
-
-	ice_for_each_txq(vsi, q_id) {
-		struct ice_q_vector *q_vector;
-		struct ice_tx_ring *tx_ring;
-		struct ice_rx_ring *rx_ring;
-		struct ice_repr *repr;
-
-		repr = xa_find(&eswitch->reprs, &repr_id, U32_MAX,
-			       XA_PRESENT);
-		if (!repr)
-			break;
-
-		repr_id += 1;
-		repr->q_id = q_id;
-		q_vector = repr->q_vector;
-		tx_ring = vsi->tx_rings[q_id];
-		rx_ring = vsi->rx_rings[q_id];
-
-		q_vector->vsi = vsi;
-		q_vector->reg_idx = vsi->q_vectors[0]->reg_idx;
-
-		q_vector->num_ring_tx = 1;
-		q_vector->tx.tx_ring = tx_ring;
-		tx_ring->q_vector = q_vector;
-		tx_ring->next = NULL;
-		tx_ring->netdev = repr->netdev;
-		/* In switchdev mode, from OS stack perspective, there is only
-		 * one queue for given netdev, so it needs to be indexed as 0.
-		 */
-		tx_ring->q_index = 0;
+	if (if_running)
+		ice_up(uplink_vsi);
 
-		q_vector->num_ring_rx = 1;
-		q_vector->rx.rx_ring = rx_ring;
-		rx_ring->q_vector = q_vector;
-		rx_ring->next = NULL;
-		rx_ring->netdev = repr->netdev;
-	}
+	return -ENODEV;
 }
 
 /**
@@ -225,8 +104,6 @@ ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr)
 	repr->dst = NULL;
 	ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
 				       ICE_FWD_TO_VSI);
-
-	netif_napi_del(&repr->q_vector->napi);
 }
 
 /**
@@ -236,7 +113,7 @@ ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr)
  */
 static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)
 {
-	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
+	struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
 	struct ice_vsi *vsi = repr->src_vsi;
 	struct metadata_dst *dst;
 
@@ -252,15 +129,11 @@ static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)
 	if (ice_vsi_add_vlan_zero(vsi))
 		goto err_update_security;
 
-	netif_napi_add(repr->netdev, &repr->q_vector->napi,
-		       ice_napi_poll);
-
-	netif_keep_dst(repr->netdev);
+	netif_keep_dst(uplink_vsi->netdev);
 
 	dst = repr->dst;
 	dst->u.port_info.port_id = vsi->vsi_num;
-	dst->u.port_info.lower_dev = repr->netdev;
-	ice_repr_set_traffic_vsi(repr, ctrl_vsi);
+	dst->u.port_info.lower_dev = uplink_vsi->netdev;
 
 	return 0;
 
@@ -318,27 +191,19 @@ void ice_eswitch_update_repr(unsigned long repr_id, struct ice_vsi *vsi)
 netdev_tx_t
 ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
-	struct ice_netdev_priv *np;
-	struct ice_repr *repr;
-	struct ice_vsi *vsi;
-
-	np = netdev_priv(netdev);
-	vsi = np->vsi;
-
-	if (!vsi || !ice_is_switchdev_running(vsi->back))
-		return NETDEV_TX_BUSY;
-
-	if (ice_is_reset_in_progress(vsi->back->state) ||
-	    test_bit(ICE_VF_DIS, vsi->back->state))
-		return NETDEV_TX_BUSY;
+	struct ice_repr *repr = ice_netdev_to_repr(netdev);
+	unsigned int len = skb->len;
+	int ret;
 
-	repr = ice_netdev_to_repr(netdev);
 	skb_dst_drop(skb);
 	dst_hold((struct dst_entry *)repr->dst);
 	skb_dst_set(skb, (struct dst_entry *)repr->dst);
-	skb->queue_mapping = repr->q_id;
+	skb->dev = repr->dst->u.port_info.lower_dev;
+
+	ret = dev_queue_xmit(skb);
+	ice_repr_inc_tx_stats(repr, len, ret);
 
-	return ice_start_xmit(skb, netdev);
+	return ret;
 }
 
 /**
@@ -374,71 +239,29 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb,
 static void ice_eswitch_release_env(struct ice_pf *pf)
 {
 	struct ice_vsi *uplink_vsi = pf->eswitch.uplink_vsi;
-	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 	struct ice_vsi_vlan_ops *vlan_ops;
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_local_lb(uplink_vsi, false);
-	ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override);
 	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
-	ice_clear_dflt_vsi(uplink_vsi);
+	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
+			 ICE_FLTR_TX);
+	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
+			 ICE_FLTR_RX);
 	ice_fltr_add_mac_and_broadcast(uplink_vsi,
 				       uplink_vsi->port_info->mac.perm_addr,
 				       ICE_FWD_TO_VSI);
 }
 
 /**
- * ice_eswitch_vsi_setup - configure eswitch control VSI
- * @pf: pointer to PF structure
- * @pi: pointer to port_info structure
- */
-static struct ice_vsi *
-ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
-{
-	struct ice_vsi_cfg_params params = {};
-
-	params.type = ICE_VSI_SWITCHDEV_CTRL;
-	params.pi = pi;
-	params.flags = ICE_VSI_FLAG_INIT;
-
-	return ice_vsi_setup(pf, &params);
-}
-
-/**
- * ice_eswitch_napi_enable - enable NAPI for all port representors
- * @reprs: xarray of reprs
- */
-static void ice_eswitch_napi_enable(struct xarray *reprs)
-{
-	struct ice_repr *repr;
-	unsigned long id;
-
-	xa_for_each(reprs, id, repr)
-		napi_enable(&repr->q_vector->napi);
-}
-
-/**
- * ice_eswitch_napi_disable - disable NAPI for all port representors
- * @reprs: xarray of reprs
- */
-static void ice_eswitch_napi_disable(struct xarray *reprs)
-{
-	struct ice_repr *repr;
-	unsigned long id;
-
-	xa_for_each(reprs, id, repr)
-		napi_disable(&repr->q_vector->napi);
-}
-
-/**
  * ice_eswitch_enable_switchdev - configure eswitch in switchdev mode
  * @pf: pointer to PF structure
  */
 static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 {
-	struct ice_vsi *ctrl_vsi, *uplink_vsi;
+	struct ice_vsi *uplink_vsi;
 
 	uplink_vsi = ice_get_main_vsi(pf);
 	if (!uplink_vsi)
@@ -450,17 +273,10 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 		return -EINVAL;
 	}
 
-	pf->eswitch.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info);
-	if (!pf->eswitch.control_vsi)
-		return -ENODEV;
-
-	ctrl_vsi = pf->eswitch.control_vsi;
-	/* cp VSI is createad with 1 queue as default */
-	pf->eswitch.qs.value = 1;
 	pf->eswitch.uplink_vsi = uplink_vsi;
 
 	if (ice_eswitch_setup_env(pf))
-		goto err_vsi;
+		return -ENODEV;
 
 	if (ice_eswitch_br_offloads_init(pf))
 		goto err_br_offloads;
@@ -471,8 +287,6 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 
 err_br_offloads:
 	ice_eswitch_release_env(pf);
-err_vsi:
-	ice_vsi_release(ctrl_vsi);
 	return -ENODEV;
 }
 
@@ -482,14 +296,10 @@ err_vsi:
  */
 static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
 {
-	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
-
 	ice_eswitch_br_offloads_deinit(pf);
 	ice_eswitch_release_env(pf);
-	ice_vsi_release(ctrl_vsi);
 
 	pf->eswitch.is_running = false;
-	pf->eswitch.qs.is_reaching = false;
 }
 
 /**
@@ -530,7 +340,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode,
 
 		dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev",
 			 pf->hw.pf_id);
-		xa_init_flags(&pf->eswitch.reprs, XA_FLAGS_ALLOC);
+		xa_init(&pf->eswitch.reprs);
 		NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev");
 		break;
 	}
@@ -602,56 +412,18 @@ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
 
 static void ice_eswitch_stop_reprs(struct ice_pf *pf)
 {
-	ice_eswitch_del_sp_rules(pf);
 	ice_eswitch_stop_all_tx_queues(pf);
-	ice_eswitch_napi_disable(&pf->eswitch.reprs);
 }
 
 static void ice_eswitch_start_reprs(struct ice_pf *pf)
 {
-	ice_eswitch_napi_enable(&pf->eswitch.reprs);
 	ice_eswitch_start_all_tx_queues(pf);
-	ice_eswitch_add_sp_rules(pf);
-}
-
-static void
-ice_eswitch_cp_change_queues(struct ice_eswitch *eswitch, int change)
-{
-	struct ice_vsi *cp = eswitch->control_vsi;
-	int queues = 0;
-
-	if (eswitch->qs.is_reaching) {
-		if (eswitch->qs.to_reach >= eswitch->qs.value + change) {
-			queues = eswitch->qs.to_reach;
-			eswitch->qs.is_reaching = false;
-		} else {
-			queues = 0;
-		}
-	} else if ((change > 0 && cp->alloc_txq <= eswitch->qs.value) ||
-		   change < 0) {
-		queues = cp->alloc_txq + change;
-	}
-
-	if (queues) {
-		cp->req_txq = queues;
-		cp->req_rxq = queues;
-		ice_vsi_close(cp);
-		ice_vsi_rebuild(cp, ICE_VSI_FLAG_NO_INIT);
-		ice_vsi_open(cp);
-	} else if (!change) {
-		/* change == 0 means that VSI wasn't open, open it here */
-		ice_vsi_open(cp);
-	}
-
-	eswitch->qs.value += change;
-	ice_eswitch_remap_rings_to_vectors(eswitch);
 }
 
 int
 ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 {
 	struct ice_repr *repr;
-	int change = 1;
 	int err;
 
 	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
@@ -661,9 +433,6 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 		err = ice_eswitch_enable_switchdev(pf);
 		if (err)
 			return err;
-		/* Control plane VSI is created with 1 queue as default */
-		pf->eswitch.qs.to_reach -= 1;
-		change = 0;
 	}
 
 	ice_eswitch_stop_reprs(pf);
@@ -678,14 +447,12 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 	if (err)
 		goto err_setup_repr;
 
-	err = xa_alloc(&pf->eswitch.reprs, &repr->id, repr,
-		       XA_LIMIT(1, INT_MAX), GFP_KERNEL);
+	err = xa_insert(&pf->eswitch.reprs, repr->id, repr, GFP_KERNEL);
 	if (err)
 		goto err_xa_alloc;
 
 	vf->repr_id = repr->id;
 
-	ice_eswitch_cp_change_queues(&pf->eswitch, change);
 	ice_eswitch_start_reprs(pf);
 
 	return 0;
@@ -715,8 +482,6 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
 
 	if (xa_empty(&pf->eswitch.reprs))
 		ice_eswitch_disable_switchdev(pf);
-	else
-		ice_eswitch_cp_change_queues(&pf->eswitch, -1);
 
 	ice_eswitch_release_repr(pf, repr);
 	ice_repr_rem_vf(repr);
@@ -738,37 +503,37 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
  * ice_eswitch_rebuild - rebuild eswitch
  * @pf: pointer to PF structure
  */
-int ice_eswitch_rebuild(struct ice_pf *pf)
+void ice_eswitch_rebuild(struct ice_pf *pf)
 {
 	struct ice_repr *repr;
 	unsigned long id;
-	int err;
 
 	if (!ice_is_switchdev_running(pf))
-		return 0;
-
-	err = ice_vsi_rebuild(pf->eswitch.control_vsi, ICE_VSI_FLAG_INIT);
-	if (err)
-		return err;
+		return;
 
 	xa_for_each(&pf->eswitch.reprs, id, repr)
 		ice_eswitch_detach(pf, repr->vf);
-
-	return 0;
 }
 
 /**
- * ice_eswitch_reserve_cp_queues - reserve control plane VSI queues
- * @pf: pointer to PF structure
- * @change: how many more (or less) queues is needed
+ * ice_eswitch_get_target - get netdev based on src_vsi from descriptor
+ * @rx_ring: ring used to receive the packet
+ * @rx_desc: descriptor used to get src_vsi value
  *
- * Remember to call ice_eswitch_attach/detach() the "change" times.
+ * Get src_vsi value from descriptor and load correct representor. If it isn't
+ * found return rx_ring->netdev.
  */
-void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change)
+struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring,
+					  union ice_32b_rx_flex_desc *rx_desc)
 {
-	if (pf->eswitch.qs.value + change < 0)
-		return;
+	struct ice_eswitch *eswitch = &rx_ring->vsi->back->eswitch;
+	struct ice_32b_rx_flex_desc_nic_2 *desc;
+	struct ice_repr *repr;
+
+	desc = (struct ice_32b_rx_flex_desc_nic_2 *)rx_desc;
+	repr = xa_load(&eswitch->reprs, le16_to_cpu(desc->src_vsi));
+	if (!repr)
+		return rx_ring->netdev;
 
-	pf->eswitch.qs.to_reach = pf->eswitch.qs.value + change;
-	pf->eswitch.qs.is_reaching = true;
+	return repr->netdev;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h
index 1a288a03a79a..e2e5c0c75e7d 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h
@@ -10,7 +10,7 @@
 void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf);
 int
 ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf);
-int ice_eswitch_rebuild(struct ice_pf *pf);
+void ice_eswitch_rebuild(struct ice_pf *pf);
 
 int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int
@@ -26,7 +26,8 @@ void ice_eswitch_set_target_vsi(struct sk_buff *skb,
 				struct ice_tx_offload_params *off);
 netdev_tx_t
 ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev);
-void ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change);
+struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring,
+					  union ice_32b_rx_flex_desc *rx_desc);
 #else /* CONFIG_ICE_SWITCHDEV */
 static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { }
 
@@ -78,7 +79,11 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_BUSY;
 }
 
-static inline void
-ice_eswitch_reserve_cp_queues(struct ice_pf *pf, int change) { }
+static inline struct net_device *
+ice_eswitch_get_target(struct ice_rx_ring *rx_ring,
+		       union ice_32b_rx_flex_desc *rx_desc)
+{
+	return rx_ring->netdev;
+}
 #endif /* CONFIG_ICE_SWITCHDEV */
 #endif /* _ICE_ESWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 9a1a04f5f146..e3cab8e98f52 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -41,6 +41,8 @@ static struct in6_addr zero_ipv6_addr_mask = {
 static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow)
 {
 	switch (flow) {
+	case ICE_FLTR_PTYPE_NONF_ETH:
+		return ETHER_FLOW;
 	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
 		return TCP_V4_FLOW;
 	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
@@ -72,6 +74,8 @@ static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow)
 static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth)
 {
 	switch (eth) {
+	case ETHER_FLOW:
+		return ICE_FLTR_PTYPE_NONF_ETH;
 	case TCP_V4_FLOW:
 		return ICE_FLTR_PTYPE_NONF_IPV4_TCP;
 	case UDP_V4_FLOW:
@@ -137,6 +141,10 @@ int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd)
 	memset(&fsp->m_ext, 0, sizeof(fsp->m_ext));
 
 	switch (fsp->flow_type) {
+	case ETHER_FLOW:
+		fsp->h_u.ether_spec = rule->eth;
+		fsp->m_u.ether_spec = rule->eth_mask;
+		break;
 	case IPV4_USER_FLOW:
 		fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
 		fsp->h_u.usr_ip4_spec.proto = 0;
@@ -1194,6 +1202,122 @@ ice_set_fdir_ip6_usr_seg(struct ice_flow_seg_info *seg,
 }
 
 /**
+ * ice_fdir_vlan_valid - validate VLAN data for Flow Director rule
+ * @dev: network interface device structure
+ * @fsp: pointer to ethtool Rx flow specification
+ *
+ * Return: true if vlan data is valid, false otherwise
+ */
+static bool ice_fdir_vlan_valid(struct device *dev,
+				struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->m_ext.vlan_etype && !eth_type_vlan(fsp->h_ext.vlan_etype))
+		return false;
+
+	if (fsp->m_ext.vlan_tci && ntohs(fsp->h_ext.vlan_tci) >= VLAN_N_VID)
+		return false;
+
+	/* proto and vlan must have vlan-etype defined */
+	if (fsp->m_u.ether_spec.h_proto && fsp->m_ext.vlan_tci &&
+	    !fsp->m_ext.vlan_etype) {
+		dev_warn(dev, "Filter with proto and vlan require also vlan-etype");
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ice_set_ether_flow_seg - set address and protocol segments for ether flow
+ * @dev: network interface device structure
+ * @seg: flow segment for programming
+ * @eth_spec: mask data from ethtool
+ *
+ * Return: 0 on success and errno in case of error.
+ */
+static int ice_set_ether_flow_seg(struct device *dev,
+				  struct ice_flow_seg_info *seg,
+				  struct ethhdr *eth_spec)
+{
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ETH);
+
+	/* empty rules are not valid */
+	if (is_zero_ether_addr(eth_spec->h_source) &&
+	    is_zero_ether_addr(eth_spec->h_dest) &&
+	    !eth_spec->h_proto)
+		return -EINVAL;
+
+	/* Ethertype */
+	if (eth_spec->h_proto == htons(0xFFFF)) {
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_TYPE,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	} else if (eth_spec->h_proto) {
+		dev_warn(dev, "Only 0x0000 or 0xffff proto mask is allowed for flow-type ether");
+		return -EOPNOTSUPP;
+	}
+
+	/* Source MAC address */
+	if (is_broadcast_ether_addr(eth_spec->h_source))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_SA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!is_zero_ether_addr(eth_spec->h_source))
+		goto err_mask;
+
+	/* Destination MAC address */
+	if (is_broadcast_ether_addr(eth_spec->h_dest))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_ETH_DA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!is_zero_ether_addr(eth_spec->h_dest))
+		goto err_mask;
+
+	return 0;
+
+err_mask:
+	dev_warn(dev, "Only 00:00:00:00:00:00 or ff:ff:ff:ff:ff:ff MAC address mask is allowed for flow-type ether");
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ice_set_fdir_vlan_seg - set vlan segments for ether flow
+ * @seg: flow segment for programming
+ * @ext_masks: masks for additional RX flow fields
+ *
+ * Return: 0 on success and errno in case of error.
+ */
+static int
+ice_set_fdir_vlan_seg(struct ice_flow_seg_info *seg,
+		      struct ethtool_flow_ext *ext_masks)
+{
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_VLAN);
+
+	if (ext_masks->vlan_etype) {
+		if (ext_masks->vlan_etype != htons(0xFFFF))
+			return -EOPNOTSUPP;
+
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_S_VLAN,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	}
+
+	if (ext_masks->vlan_tci) {
+		if (ext_masks->vlan_tci != htons(0xFFFF))
+			return -EOPNOTSUPP;
+
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_C_VLAN,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	}
+
+	return 0;
+}
+
+/**
  * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter
  * @pf: PF structure
  * @fsp: pointer to ethtool Rx flow specification
@@ -1209,7 +1333,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp,
 	struct device *dev = ice_pf_to_dev(pf);
 	enum ice_fltr_ptype fltr_idx;
 	struct ice_hw *hw = &pf->hw;
-	bool perfect_filter;
+	bool perfect_filter = false;
 	int ret;
 
 	seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL);
@@ -1262,6 +1386,16 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp,
 		ret = ice_set_fdir_ip6_usr_seg(seg, &fsp->m_u.usr_ip6_spec,
 					       &perfect_filter);
 		break;
+	case ETHER_FLOW:
+		ret = ice_set_ether_flow_seg(dev, seg, &fsp->m_u.ether_spec);
+		if (!ret && (fsp->m_ext.vlan_etype || fsp->m_ext.vlan_tci)) {
+			if (!ice_fdir_vlan_valid(dev, fsp)) {
+				ret = -EINVAL;
+				break;
+			}
+			ret = ice_set_fdir_vlan_seg(seg, &fsp->m_ext);
+		}
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -1823,6 +1957,10 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp,
 		input->mask.v6.tc = fsp->m_u.usr_ip6_spec.tclass;
 		input->mask.v6.proto = fsp->m_u.usr_ip6_spec.l4_proto;
 		break;
+	case ETHER_FLOW:
+		input->eth = fsp->h_u.ether_spec;
+		input->eth_mask = fsp->m_u.ether_spec;
+		break;
 	default:
 		/* not doing un-parsed flow types */
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 5840c3e04a5b..26b357c0ae15 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -4,6 +4,8 @@
 #include "ice_common.h"
 
 /* These are training packet headers used to program flow director filters. */
+static const u8 ice_fdir_eth_pkt[22];
+
 static const u8 ice_fdir_tcpv4_pkt[] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
@@ -417,6 +419,11 @@ static const u8 ice_fdir_ip6_tun_pkt[] = {
 /* Flow Director no-op training packet table */
 static const struct ice_fdir_base_pkt ice_fdir_pkt[] = {
 	{
+		ICE_FLTR_PTYPE_NONF_ETH,
+		sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt,
+		sizeof(ice_fdir_eth_pkt), ice_fdir_eth_pkt,
+	},
+	{
 		ICE_FLTR_PTYPE_NONF_IPV4_TCP,
 		sizeof(ice_fdir_tcpv4_pkt), ice_fdir_tcpv4_pkt,
 		sizeof(ice_fdir_tcp4_tun_pkt), ice_fdir_tcp4_tun_pkt,
@@ -914,6 +921,21 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 	 * perspective. The input from user is from Rx filter perspective.
 	 */
 	switch (flow) {
+	case ICE_FLTR_PTYPE_NONF_ETH:
+		ice_pkt_insert_mac_addr(loc, input->eth.h_dest);
+		ice_pkt_insert_mac_addr(loc + ETH_ALEN, input->eth.h_source);
+		if (input->ext_data.vlan_tag || input->ext_data.vlan_type) {
+			ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET,
+					   input->ext_data.vlan_type);
+			ice_pkt_insert_u16(loc, ICE_ETH_VLAN_TCI_OFFSET,
+					   input->ext_data.vlan_tag);
+			ice_pkt_insert_u16(loc, ICE_ETH_TYPE_VLAN_OFFSET,
+					   input->eth.h_proto);
+		} else {
+			ice_pkt_insert_u16(loc, ICE_ETH_TYPE_F_OFFSET,
+					   input->eth.h_proto);
+		}
+		break;
 	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
 		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
 				   input->ip.v4.src_ip);
@@ -1189,52 +1211,58 @@ static int ice_cmp_ipv6_addr(__be32 *a, __be32 *b)
  * ice_fdir_comp_rules - compare 2 filters
  * @a: a Flow Director filter data structure
  * @b: a Flow Director filter data structure
- * @v6: bool true if v6 filter
  *
  * Returns true if the filters match
  */
 static bool
-ice_fdir_comp_rules(struct ice_fdir_fltr *a,  struct ice_fdir_fltr *b, bool v6)
+ice_fdir_comp_rules(struct ice_fdir_fltr *a,  struct ice_fdir_fltr *b)
 {
 	enum ice_fltr_ptype flow_type = a->flow_type;
 
 	/* The calling function already checks that the two filters have the
 	 * same flow_type.
 	 */
-	if (!v6) {
-		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) {
-			if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
-			    a->ip.v4.src_ip == b->ip.v4.src_ip &&
-			    a->ip.v4.dst_port == b->ip.v4.dst_port &&
-			    a->ip.v4.src_port == b->ip.v4.src_port)
-				return true;
-		} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
-			if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
-			    a->ip.v4.src_ip == b->ip.v4.src_ip &&
-			    a->ip.v4.l4_header == b->ip.v4.l4_header &&
-			    a->ip.v4.proto == b->ip.v4.proto &&
-			    a->ip.v4.ip_ver == b->ip.v4.ip_ver &&
-			    a->ip.v4.tos == b->ip.v4.tos)
-				return true;
-		}
-	} else {
-		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_TCP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) {
-			if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
-			    a->ip.v6.src_port == b->ip.v6.src_port &&
-			    !ice_cmp_ipv6_addr(a->ip.v6.dst_ip,
-					       b->ip.v6.dst_ip) &&
-			    !ice_cmp_ipv6_addr(a->ip.v6.src_ip,
-					       b->ip.v6.src_ip))
-				return true;
-		} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) {
-			if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
-			    a->ip.v6.src_port == b->ip.v6.src_port)
-				return true;
-		}
+	switch (flow_type) {
+	case ICE_FLTR_PTYPE_NONF_ETH:
+		if (!memcmp(&a->eth, &b->eth, sizeof(a->eth)))
+			return true;
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
+	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
+	case ICE_FLTR_PTYPE_NONF_IPV4_SCTP:
+		if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
+		    a->ip.v4.src_ip == b->ip.v4.src_ip &&
+		    a->ip.v4.dst_port == b->ip.v4.dst_port &&
+		    a->ip.v4.src_port == b->ip.v4.src_port)
+			return true;
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_OTHER:
+		if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
+		    a->ip.v4.src_ip == b->ip.v4.src_ip &&
+		    a->ip.v4.l4_header == b->ip.v4.l4_header &&
+		    a->ip.v4.proto == b->ip.v4.proto &&
+		    a->ip.v4.ip_ver == b->ip.v4.ip_ver &&
+		    a->ip.v4.tos == b->ip.v4.tos)
+			return true;
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_UDP:
+	case ICE_FLTR_PTYPE_NONF_IPV6_TCP:
+	case ICE_FLTR_PTYPE_NONF_IPV6_SCTP:
+		if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
+		    a->ip.v6.src_port == b->ip.v6.src_port &&
+		    !ice_cmp_ipv6_addr(a->ip.v6.dst_ip,
+				       b->ip.v6.dst_ip) &&
+		    !ice_cmp_ipv6_addr(a->ip.v6.src_ip,
+				       b->ip.v6.src_ip))
+			return true;
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_OTHER:
+		if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
+		    a->ip.v6.src_port == b->ip.v6.src_port)
+			return true;
+		break;
+	default:
+		break;
 	}
 
 	return false;
@@ -1253,19 +1281,10 @@ bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input)
 	bool ret = false;
 
 	list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) {
-		enum ice_fltr_ptype flow_type;
-
 		if (rule->flow_type != input->flow_type)
 			continue;
 
-		flow_type = input->flow_type;
-		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP ||
-		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER)
-			ret = ice_fdir_comp_rules(rule, input, false);
-		else
-			ret = ice_fdir_comp_rules(rule, input, true);
+		ret = ice_fdir_comp_rules(rule, input);
 		if (ret) {
 			if (rule->fltr_id == input->fltr_id &&
 			    rule->q_index != input->q_index)
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 1b9b84490689..021ecbac7848 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -8,6 +8,9 @@
 #define ICE_FDIR_MAX_RAW_PKT_SIZE	(512 + ICE_FDIR_TUN_PKT_OFF)
 
 /* macros for offsets into packets for flow director programming */
+#define ICE_ETH_TYPE_F_OFFSET		12
+#define ICE_ETH_VLAN_TCI_OFFSET		14
+#define ICE_ETH_TYPE_VLAN_OFFSET	16
 #define ICE_IPV4_SRC_ADDR_OFFSET	26
 #define ICE_IPV4_DST_ADDR_OFFSET	30
 #define ICE_IPV4_TCP_SRC_PORT_OFFSET	34
@@ -159,6 +162,8 @@ struct ice_fdir_fltr {
 	struct list_head fltr_node;
 	enum ice_fltr_ptype flow_type;
 
+	struct ethhdr eth, eth_mask;
+
 	union {
 		struct ice_fdir_v4 v4;
 		struct ice_fdir_v6 v6;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index d427a79d001a..817beca591e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -93,6 +93,7 @@ enum ice_tunnel_type {
 	TNL_GRETAP,
 	TNL_GTPC,
 	TNL_GTPU,
+	TNL_PFCP,
 	__TNL_TYPE_CNT,
 	TNL_LAST = 0xFF,
 	TNL_ALL = 0xFF,
@@ -358,7 +359,8 @@ enum ice_prof_type {
 	ICE_PROF_TUN_GRE = 0x4,
 	ICE_PROF_TUN_GTPU = 0x8,
 	ICE_PROF_TUN_GTPC = 0x10,
-	ICE_PROF_TUN_ALL = 0x1E,
+	ICE_PROF_TUN_PFCP = 0x20,
+	ICE_PROF_TUN_ALL = 0x3E,
 	ICE_PROF_ALL = 0xFF,
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 319a2d6fe26c..f81db6c107c8 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -286,10 +286,9 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon
  *
  * Returns: zero on success, or a negative error code on failure.
  */
-static int
-ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
-			u16 block_size, u8 *block, bool last_cmd,
-			u8 *reset_level, struct netlink_ext_ack *extack)
+int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
+			    u16 block_size, u8 *block, bool last_cmd,
+			    u8 *reset_level, struct netlink_ext_ack *extack)
 {
 	u16 completion_module, completion_retval;
 	struct device *dev = ice_pf_to_dev(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h
index 750574885716..04b200462757 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.h
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h
@@ -9,5 +9,8 @@ int ice_devlink_flash_update(struct devlink *devlink,
 			     struct netlink_ext_ack *extack);
 int ice_get_pending_updates(struct ice_pf *pf, u8 *pending,
 			    struct netlink_ext_ack *extack);
+int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
+			    u16 block_size, u8 *block, bool last_cmd,
+			    u8 *reset_level, struct netlink_ext_ack *extack);
 
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index f0e76f0a6d60..1ccb572ce285 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -202,11 +202,12 @@ static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag)
  * @act: rule action
  * @recipe_id: recipe id for the new rule
  * @rule_idx: pointer to rule index
+ * @direction: ICE_FLTR_RX or ICE_FLTR_TX
  * @add: boolean on whether we are adding filters
  */
 static int
 ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx,
-		 bool add)
+		 u8 direction, bool add)
 {
 	struct ice_sw_rule_lkup_rx_tx *s_rule;
 	u16 s_rule_sz, vsi_num;
@@ -231,9 +232,16 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx,
 
 		act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi_num);
 
-		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
 		s_rule->recipe_id = cpu_to_le16(recipe_id);
-		s_rule->src = cpu_to_le16(hw->port_info->lport);
+		if (direction == ICE_FLTR_RX) {
+			s_rule->hdr.type =
+				cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
+			s_rule->src = cpu_to_le16(hw->port_info->lport);
+		} else {
+			s_rule->hdr.type =
+				cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX);
+			s_rule->src = cpu_to_le16(vsi_num);
+		}
 		s_rule->act = cpu_to_le32(act);
 		s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN);
 		opc = ice_aqc_opc_add_sw_rules;
@@ -266,9 +274,27 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
 {
 	u32 act = ICE_SINGLE_ACT_VSI_FORWARDING |
 		ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE;
+	int err;
+
+	err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id,
+			       ICE_FLTR_RX, add);
+	if (err)
+		goto err_rx;
 
-	return ice_lag_cfg_fltr(lag, act, lag->pf_recipe,
-				&lag->pf_rule_id, add);
+	act = ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT |
+	      ICE_SINGLE_ACT_LB_ENABLE;
+	err = ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_tx_rule_id,
+			       ICE_FLTR_TX, add);
+	if (err)
+		goto err_tx;
+
+	return 0;
+
+err_tx:
+	ice_lag_cfg_fltr(lag, act, lag->pf_recipe, &lag->pf_rx_rule_id,
+			 ICE_FLTR_RX, !add);
+err_rx:
+	return err;
 }
 
 /**
@@ -284,7 +310,7 @@ ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add)
 		  ICE_SINGLE_ACT_DROP;
 
 	return ice_lag_cfg_fltr(lag, act, lag->lport_recipe,
-				&lag->lport_rule_idx, add);
+				&lag->lport_rule_idx, ICE_FLTR_RX, add);
 }
 
 /**
@@ -310,7 +336,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
 	dev = ice_pf_to_dev(lag->pf);
 
 	/* interface not active - remove old default VSI rule */
-	if (bonding_info->slave.state && lag->pf_rule_id) {
+	if (bonding_info->slave.state && lag->pf_rx_rule_id) {
 		if (ice_lag_cfg_dflt_fltr(lag, false))
 			dev_err(dev, "Error removing old default VSI filter\n");
 		if (ice_lag_cfg_drop_fltr(lag, true))
@@ -319,7 +345,7 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
 	}
 
 	/* interface becoming active - add new default VSI rule */
-	if (!bonding_info->slave.state && !lag->pf_rule_id) {
+	if (!bonding_info->slave.state && !lag->pf_rx_rule_id) {
 		if (ice_lag_cfg_dflt_fltr(lag, true))
 			dev_err(dev, "Error adding new default VSI filter\n");
 		if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false))
@@ -714,8 +740,7 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport)
 
 	pf = lag->pf;
 	ice_for_each_vsi(pf, i)
-		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
-				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+		if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF)
 			ice_lag_move_single_vf_nodes(lag, oldport, newport, i);
 }
 
@@ -953,8 +978,7 @@ ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw)
 
 	pf = lag->pf;
 	ice_for_each_vsi(pf, i)
-		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
-				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+		if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF)
 			ice_for_each_traffic_class(tc)
 				ice_lag_reclaim_vf_tc(lag, src_hw, i, tc);
 }
@@ -1976,8 +2000,7 @@ ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw)
 
 	pf = lag->pf;
 	ice_for_each_vsi(pf, i)
-		if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF ||
-				   pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL))
+		if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF)
 			ice_for_each_traffic_class(tc)
 				ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i,
 							      tc);
@@ -2149,7 +2172,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 
 	ice_lag_cfg_cp_fltr(lag, true);
 
-	if (lag->pf_rule_id)
+	if (lag->pf_rx_rule_id)
 		if (ice_lag_cfg_dflt_fltr(lag, true))
 			dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n");
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index 183b38792ef2..bab2c83142a1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -43,7 +43,8 @@ struct ice_lag {
 	u8 primary:1; /* this is primary */
 	u16 pf_recipe;
 	u16 lport_recipe;
-	u16 pf_rule_id;
+	u16 pf_rx_rule_id;
+	u16 pf_tx_rule_id;
 	u16 cp_rule_idx;
 	u16 lport_rule_idx;
 	u8 role;
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index d384ddfcb83e..611577ebc29d 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -160,64 +160,6 @@ struct ice_fltr_desc {
 				(0x1ULL << ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S)
 #define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES	0x1ULL
 
-struct ice_rx_ptype_decoded {
-	u32 known:1;
-	u32 outer_ip:1;
-	u32 outer_ip_ver:2;
-	u32 outer_frag:1;
-	u32 tunnel_type:3;
-	u32 tunnel_end_prot:2;
-	u32 tunnel_end_frag:1;
-	u32 inner_prot:4;
-	u32 payload_layer:3;
-};
-
-enum ice_rx_ptype_outer_ip {
-	ICE_RX_PTYPE_OUTER_L2	= 0,
-	ICE_RX_PTYPE_OUTER_IP	= 1,
-};
-
-enum ice_rx_ptype_outer_ip_ver {
-	ICE_RX_PTYPE_OUTER_NONE	= 0,
-	ICE_RX_PTYPE_OUTER_IPV4	= 1,
-	ICE_RX_PTYPE_OUTER_IPV6	= 2,
-};
-
-enum ice_rx_ptype_outer_fragmented {
-	ICE_RX_PTYPE_NOT_FRAG	= 0,
-	ICE_RX_PTYPE_FRAG	= 1,
-};
-
-enum ice_rx_ptype_tunnel_type {
-	ICE_RX_PTYPE_TUNNEL_NONE		= 0,
-	ICE_RX_PTYPE_TUNNEL_IP_IP		= 1,
-	ICE_RX_PTYPE_TUNNEL_IP_GRENAT		= 2,
-	ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC	= 3,
-	ICE_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN	= 4,
-};
-
-enum ice_rx_ptype_tunnel_end_prot {
-	ICE_RX_PTYPE_TUNNEL_END_NONE	= 0,
-	ICE_RX_PTYPE_TUNNEL_END_IPV4	= 1,
-	ICE_RX_PTYPE_TUNNEL_END_IPV6	= 2,
-};
-
-enum ice_rx_ptype_inner_prot {
-	ICE_RX_PTYPE_INNER_PROT_NONE		= 0,
-	ICE_RX_PTYPE_INNER_PROT_UDP		= 1,
-	ICE_RX_PTYPE_INNER_PROT_TCP		= 2,
-	ICE_RX_PTYPE_INNER_PROT_SCTP		= 3,
-	ICE_RX_PTYPE_INNER_PROT_ICMP		= 4,
-	ICE_RX_PTYPE_INNER_PROT_TIMESYNC	= 5,
-};
-
-enum ice_rx_ptype_payload_layer {
-	ICE_RX_PTYPE_PAYLOAD_LAYER_NONE	= 0,
-	ICE_RX_PTYPE_PAYLOAD_LAYER_PAY2	= 1,
-	ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3	= 2,
-	ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4	= 3,
-};
-
 /* Rx Flex Descriptor
  * This descriptor is used instead of the legacy version descriptor when
  * ice_rlan_ctx.adv_desc is set
@@ -651,266 +593,4 @@ struct ice_tlan_ctx {
 	u8 int_q_state;	/* width not needed - internal - DO NOT WRITE!!! */
 };
 
-/* The ice_ptype_lkup table is used to convert from the 10-bit ptype in the
- * hardware to a bit-field that can be used by SW to more easily determine the
- * packet type.
- *
- * Macros are used to shorten the table lines and make this table human
- * readable.
- *
- * We store the PTYPE in the top byte of the bit field - this is just so that
- * we can check that the table doesn't have a row missing, as the index into
- * the table should be the PTYPE.
- *
- * Typical work flow:
- *
- * IF NOT ice_ptype_lkup[ptype].known
- * THEN
- *      Packet is unknown
- * ELSE IF ice_ptype_lkup[ptype].outer_ip == ICE_RX_PTYPE_OUTER_IP
- *      Use the rest of the fields to look at the tunnels, inner protocols, etc
- * ELSE
- *      Use the enum ice_rx_l2_ptype to decode the packet type
- * ENDIF
- */
-#define ICE_PTYPES								\
-	/* L2 Packet types */							\
-	ICE_PTT_UNUSED_ENTRY(0),						\
-	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),			\
-	ICE_PTT_UNUSED_ENTRY(2),						\
-	ICE_PTT_UNUSED_ENTRY(3),						\
-	ICE_PTT_UNUSED_ENTRY(4),						\
-	ICE_PTT_UNUSED_ENTRY(5),						\
-	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
-	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
-	ICE_PTT_UNUSED_ENTRY(8),						\
-	ICE_PTT_UNUSED_ENTRY(9),						\
-	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
-	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
-	ICE_PTT_UNUSED_ENTRY(12),						\
-	ICE_PTT_UNUSED_ENTRY(13),						\
-	ICE_PTT_UNUSED_ENTRY(14),						\
-	ICE_PTT_UNUSED_ENTRY(15),						\
-	ICE_PTT_UNUSED_ENTRY(16),						\
-	ICE_PTT_UNUSED_ENTRY(17),						\
-	ICE_PTT_UNUSED_ENTRY(18),						\
-	ICE_PTT_UNUSED_ENTRY(19),						\
-	ICE_PTT_UNUSED_ENTRY(20),						\
-	ICE_PTT_UNUSED_ENTRY(21),						\
-										\
-	/* Non Tunneled IPv4 */							\
-	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),		\
-	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),		\
-	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(25),						\
-	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
-	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
-	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
-										\
-	/* IPv4 --> IPv4 */							\
-	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
-	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
-	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(32),						\
-	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
-	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
-	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
-										\
-	/* IPv4 --> IPv6 */							\
-	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
-	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
-	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(39),						\
-	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
-	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
-	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
-										\
-	/* IPv4 --> GRE/NAT */							\
-	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
-										\
-	/* IPv4 --> GRE/NAT --> IPv4 */						\
-	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
-	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
-	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(47),						\
-	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
-	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
-	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
-										\
-	/* IPv4 --> GRE/NAT --> IPv6 */						\
-	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
-	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
-	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(54),						\
-	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
-	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
-	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
-										\
-	/* IPv4 --> GRE/NAT --> MAC */						\
-	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
-										\
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */					\
-	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
-	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
-	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(62),						\
-	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
-	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
-	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
-										\
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */					\
-	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
-	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
-	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(69),						\
-	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
-	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
-	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
-										\
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */					\
-	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
-										\
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */				\
-	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
-	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
-	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(77),						\
-	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
-	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
-	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
-										\
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */				\
-	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
-	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
-	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(84),						\
-	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
-	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
-	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),	\
-										\
-	/* Non Tunneled IPv6 */							\
-	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),		\
-	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),		\
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(91),						\
-	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
-	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
-	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
-										\
-	/* IPv6 --> IPv4 */							\
-	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
-	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
-	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(98),						\
-	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
-	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
-	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
-										\
-	/* IPv6 --> IPv6 */							\
-	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
-	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
-	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(105),						\
-	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
-	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
-	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
-										\
-	/* IPv6 --> GRE/NAT */							\
-	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
-										\
-	/* IPv6 --> GRE/NAT -> IPv4 */						\
-	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
-	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
-	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(113),						\
-	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
-	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
-	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
-										\
-	/* IPv6 --> GRE/NAT -> IPv6 */						\
-	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
-	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
-	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
-	ICE_PTT_UNUSED_ENTRY(120),						\
-	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
-	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
-	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
-										\
-	/* IPv6 --> GRE/NAT -> MAC */						\
-	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
-										\
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */					\
-	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
-	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
-	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(128),						\
-	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
-	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
-	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
-										\
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */					\
-	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
-	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
-	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(135),						\
-	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
-	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
-	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
-										\
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */					\
-	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
-										\
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */				\
-	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
-	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
-	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(143),						\
-	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
-	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
-	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
-										\
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */				\
-	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
-	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
-	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
-	ICE_PTT_UNUSED_ENTRY(150),						\
-	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
-	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
-	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-#define ICE_NUM_DEFINED_PTYPES	154
-
-/* macro to make the table lines short, use explicit indexing with [PTYPE] */
-#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	[PTYPE] = { \
-		1, \
-		ICE_RX_PTYPE_OUTER_##OUTER_IP, \
-		ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \
-		ICE_RX_PTYPE_##OUTER_FRAG, \
-		ICE_RX_PTYPE_TUNNEL_##T, \
-		ICE_RX_PTYPE_TUNNEL_END_##TE, \
-		ICE_RX_PTYPE_##TEF, \
-		ICE_RX_PTYPE_INNER_PROT_##I, \
-		ICE_RX_PTYPE_PAYLOAD_LAYER_##PL }
-
-#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-
-/* shorter macros makes the table fit but are terse */
-#define ICE_RX_PTYPE_NOF		ICE_RX_PTYPE_NOT_FRAG
-#define ICE_RX_PTYPE_FRG		ICE_RX_PTYPE_FRAG
-
-/* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
-static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
-	ICE_PTYPES
-
-	/* unused entries */
-	[ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
-};
-
-static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
-{
-	return ice_ptype_lkup[ptype];
-}
-
-
 #endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 558422120312..5371e91f6bbb 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -7,7 +7,6 @@
 #include "ice_lib.h"
 #include "ice_fltr.h"
 #include "ice_dcb_lib.h"
-#include "ice_devlink.h"
 #include "ice_vsi_vlan_ops.h"
 
 /**
@@ -27,8 +26,6 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type)
 		return "ICE_VSI_CHNL";
 	case ICE_VSI_LB:
 		return "ICE_VSI_LB";
-	case ICE_VSI_SWITCHDEV_CTRL:
-		return "ICE_VSI_SWITCHDEV_CTRL";
 	default:
 		return "unknown";
 	}
@@ -144,7 +141,6 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 {
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-	case ICE_VSI_SWITCHDEV_CTRL:
 	case ICE_VSI_CTRL:
 	case ICE_VSI_LB:
 		/* a user could change the values of num_[tr]x_desc using
@@ -211,21 +207,6 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 					   max_t(int, vsi->alloc_rxq,
 						 vsi->alloc_txq));
 		break;
-	case ICE_VSI_SWITCHDEV_CTRL:
-		/* The number of queues for ctrl VSI is equal to number of PRs
-		 * Each ring is associated to the corresponding VF_PR netdev.
-		 * Tx and Rx rings are always equal
-		 */
-		if (vsi->req_txq && vsi->req_rxq) {
-			vsi->alloc_txq = vsi->req_txq;
-			vsi->alloc_rxq = vsi->req_rxq;
-		} else {
-			vsi->alloc_txq = 1;
-			vsi->alloc_rxq = 1;
-		}
-
-		vsi->num_q_vectors = 1;
-		break;
 	case ICE_VSI_VF:
 		if (vf->num_req_qs)
 			vf->num_vf_qs = vf->num_req_qs;
@@ -522,22 +503,6 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *data)
-{
-	struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
-	struct ice_pf *pf = q_vector->vsi->back;
-	struct ice_repr *repr;
-	unsigned long id;
-
-	if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring)
-		return IRQ_HANDLED;
-
-	xa_for_each(&pf->eswitch.reprs, id, repr)
-		napi_schedule(&repr->q_vector->napi);
-
-	return IRQ_HANDLED;
-}
-
 /**
  * ice_vsi_alloc_stat_arrays - Allocate statistics arrays
  * @vsi: VSI pointer
@@ -600,10 +565,6 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 	}
 
 	switch (vsi->type) {
-	case ICE_VSI_SWITCHDEV_CTRL:
-		/* Setup eswitch MSIX irq handler for VSI */
-		vsi->irq_handler = ice_eswitch_msix_clean_rings;
-		break;
 	case ICE_VSI_PF:
 		/* Setup default MSIX irq handler for VSI */
 		vsi->irq_handler = ice_msix_clean_rings;
@@ -933,11 +894,6 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 					      max_rss_size);
 		vsi->rss_lut_type = ICE_LUT_PF;
 		break;
-	case ICE_VSI_SWITCHDEV_CTRL:
-		vsi->rss_table_size = ICE_LUT_VSI_SIZE;
-		vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size);
-		vsi->rss_lut_type = ICE_LUT_VSI;
-		break;
 	case ICE_VSI_VF:
 		/* VF VSI will get a small RSS table.
 		 * For VSI_LUT, LUT size should be set to 64 bytes.
@@ -1263,7 +1219,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags)
 	case ICE_VSI_PF:
 		ctxt->flags = ICE_AQ_VSI_TYPE_PF;
 		break;
-	case ICE_VSI_SWITCHDEV_CTRL:
 	case ICE_VSI_CHNL:
 		ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2;
 		break;
@@ -2145,7 +2100,6 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi)
 	case ICE_VSI_CHNL:
 	case ICE_VSI_LB:
 	case ICE_VSI_PF:
-	case ICE_VSI_SWITCHDEV_CTRL:
 		max_agg_nodes = ICE_MAX_PF_AGG_NODES;
 		agg_node_id_start = ICE_PF_AGG_NODE_ID_START;
 		agg_node_iter = &pf->pf_agg_node[0];
@@ -2273,10 +2227,8 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi)
 /**
  * ice_vsi_cfg_def - configure default VSI based on the type
  * @vsi: pointer to VSI
- * @params: the parameters to configure this VSI with
  */
-static int
-ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
+static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 {
 	struct device *dev = ice_pf_to_dev(vsi->back);
 	struct ice_pf *pf = vsi->back;
@@ -2284,7 +2236,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 
 	vsi->vsw = pf->first_sw;
 
-	ret = ice_vsi_alloc_def(vsi, params->ch);
+	ret = ice_vsi_alloc_def(vsi, vsi->ch);
 	if (ret)
 		return ret;
 
@@ -2309,7 +2261,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 	ice_vsi_set_tc_cfg(vsi);
 
 	/* create the VSI */
-	ret = ice_vsi_init(vsi, params->flags);
+	ret = ice_vsi_init(vsi, vsi->flags);
 	if (ret)
 		goto unroll_get_qs;
 
@@ -2317,7 +2269,6 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 
 	switch (vsi->type) {
 	case ICE_VSI_CTRL:
-	case ICE_VSI_SWITCHDEV_CTRL:
 	case ICE_VSI_PF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
@@ -2430,23 +2381,16 @@ unroll_vsi_alloc:
 /**
  * ice_vsi_cfg - configure a previously allocated VSI
  * @vsi: pointer to VSI
- * @params: parameters used to configure this VSI
  */
-int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
+int ice_vsi_cfg(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	int ret;
 
-	if (WARN_ON(params->type == ICE_VSI_VF && !params->vf))
+	if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
-	vsi->type = params->type;
-	vsi->port_info = params->pi;
-
-	/* For VSIs which don't have a connected VF, this will be NULL */
-	vsi->vf = params->vf;
-
-	ret = ice_vsi_cfg_def(vsi, params);
+	ret = ice_vsi_cfg_def(vsi);
 	if (ret)
 		return ret;
 
@@ -2532,7 +2476,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
 	 * a port_info structure for it.
 	 */
 	if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) ||
-	    WARN_ON(!params->pi))
+	    WARN_ON(!params->port_info))
 		return NULL;
 
 	vsi = ice_vsi_alloc(pf);
@@ -2541,7 +2485,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
 		return NULL;
 	}
 
-	ret = ice_vsi_cfg(vsi, params);
+	vsi->params = *params;
+	ret = ice_vsi_cfg(vsi);
 	if (ret)
 		goto err_vsi_cfg;
 
@@ -2750,8 +2695,7 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 		} else {
 			ice_vsi_close(vsi);
 		}
-	} else if (vsi->type == ICE_VSI_CTRL ||
-		   vsi->type == ICE_VSI_SWITCHDEV_CTRL) {
+	} else if (vsi->type == ICE_VSI_CTRL) {
 		ice_vsi_close(vsi);
 	}
 }
@@ -3089,7 +3033,6 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
  */
 int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 {
-	struct ice_vsi_cfg_params params = {};
 	struct ice_coalesce_stored *coalesce;
 	int prev_num_q_vectors;
 	struct ice_pf *pf;
@@ -3098,9 +3041,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 	if (!vsi)
 		return -EINVAL;
 
-	params = ice_vsi_to_params(vsi);
-	params.flags = vsi_flags;
-
+	vsi->flags = vsi_flags;
 	pf = vsi->back;
 	if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
@@ -3110,7 +3051,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 		goto err_vsi_cfg;
 
 	ice_vsi_decfg(vsi);
-	ret = ice_vsi_cfg_def(vsi, &params);
+	ret = ice_vsi_cfg_def(vsi);
 	if (ret)
 		goto err_vsi_cfg;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 9cd23afe5f15..94ce8964dda6 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -11,43 +11,6 @@
 #define ICE_VSI_FLAG_INIT	BIT(0)
 #define ICE_VSI_FLAG_NO_INIT	0
 
-/**
- * struct ice_vsi_cfg_params - VSI configuration parameters
- * @pi: pointer to the port_info instance for the VSI
- * @ch: pointer to the channel structure for the VSI, may be NULL
- * @vf: pointer to the VF associated with this VSI, may be NULL
- * @type: the type of VSI to configure
- * @flags: VSI flags used for rebuild and configuration
- *
- * Parameter structure used when configuring a new VSI.
- */
-struct ice_vsi_cfg_params {
-	struct ice_port_info *pi;
-	struct ice_channel *ch;
-	struct ice_vf *vf;
-	enum ice_vsi_type type;
-	u32 flags;
-};
-
-/**
- * ice_vsi_to_params - Get parameters for an existing VSI
- * @vsi: the VSI to get parameters for
- *
- * Fill a parameter structure for reconfiguring a VSI with its current
- * parameters, such as during a rebuild operation.
- */
-static inline struct ice_vsi_cfg_params ice_vsi_to_params(struct ice_vsi *vsi)
-{
-	struct ice_vsi_cfg_params params = {};
-
-	params.pi = vsi->port_info;
-	params.ch = vsi->ch;
-	params.vf = vsi->vf;
-	params.type = vsi->type;
-
-	return params;
-}
-
 const char *ice_vsi_type_str(enum ice_vsi_type vsi_type);
 
 bool ice_pf_state_is_nominal(struct ice_pf *pf);
@@ -101,7 +64,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi);
 void ice_dis_vsi(struct ice_vsi *vsi, bool locked);
 
 int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags);
-int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params);
+int ice_vsi_cfg(struct ice_vsi *vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
 int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 33a164fa325a..f60c022f7960 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -13,7 +13,8 @@
 #include "ice_fltr.h"
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "devlink/devlink_port.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
  * ice tracepoint functions. This must be done exactly once across the
@@ -36,6 +37,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
 
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
 MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_IMPORT_NS(LIBIE);
 MODULE_LICENSE("GPL v2");
 MODULE_FIRMWARE(ICE_DDP_PKG_FILE);
 
@@ -1745,6 +1747,39 @@ static void ice_service_timer(struct timer_list *t)
 }
 
 /**
+ * ice_mdd_maybe_reset_vf - reset VF after MDD event
+ * @pf: pointer to the PF structure
+ * @vf: pointer to the VF structure
+ * @reset_vf_tx: whether Tx MDD has occurred
+ * @reset_vf_rx: whether Rx MDD has occurred
+ *
+ * Since the queue can get stuck on VF MDD events, the PF can be configured to
+ * automatically reset the VF by enabling the private ethtool flag
+ * mdd-auto-reset-vf.
+ */
+static void ice_mdd_maybe_reset_vf(struct ice_pf *pf, struct ice_vf *vf,
+				   bool reset_vf_tx, bool reset_vf_rx)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+
+	if (!test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+		return;
+
+	/* VF MDD event counters will be cleared by reset, so print the event
+	 * prior to reset.
+	 */
+	if (reset_vf_tx)
+		ice_print_vf_tx_mdd_event(vf);
+
+	if (reset_vf_rx)
+		ice_print_vf_rx_mdd_event(vf);
+
+	dev_info(dev, "PF-to-VF reset on PF %d VF %d due to MDD event\n",
+		 pf->hw.pf_id, vf->vf_id);
+	ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK);
+}
+
+/**
  * ice_handle_mdd_event - handle malicious driver detect event
  * @pf: pointer to the PF structure
  *
@@ -1837,6 +1872,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	 */
 	mutex_lock(&pf->vfs.table_lock);
 	ice_for_each_vf(pf, bkt, vf) {
+		bool reset_vf_tx = false, reset_vf_rx = false;
+
 		reg = rd32(hw, VP_MDET_TX_PQM(vf->vf_id));
 		if (reg & VP_MDET_TX_PQM_VALID_M) {
 			wr32(hw, VP_MDET_TX_PQM(vf->vf_id), 0xFFFF);
@@ -1845,6 +1882,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 			if (netif_msg_tx_err(pf))
 				dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n",
 					 vf->vf_id);
+
+			reset_vf_tx = true;
 		}
 
 		reg = rd32(hw, VP_MDET_TX_TCLAN(vf->vf_id));
@@ -1855,6 +1894,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 			if (netif_msg_tx_err(pf))
 				dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n",
 					 vf->vf_id);
+
+			reset_vf_tx = true;
 		}
 
 		reg = rd32(hw, VP_MDET_TX_TDPU(vf->vf_id));
@@ -1865,6 +1906,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 			if (netif_msg_tx_err(pf))
 				dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n",
 					 vf->vf_id);
+
+			reset_vf_tx = true;
 		}
 
 		reg = rd32(hw, VP_MDET_RX(vf->vf_id));
@@ -1876,18 +1919,12 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 				dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n",
 					 vf->vf_id);
 
-			/* Since the queue is disabled on VF Rx MDD events, the
-			 * PF can be configured to reset the VF through ethtool
-			 * private flag mdd-auto-reset-vf.
-			 */
-			if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
-				/* VF MDD event counters will be cleared by
-				 * reset, so print the event prior to reset.
-				 */
-				ice_print_vf_rx_mdd_event(vf);
-				ice_reset_vf(vf, ICE_VF_RESET_LOCK);
-			}
+			reset_vf_rx = true;
 		}
+
+		if (reset_vf_tx || reset_vf_rx)
+			ice_mdd_maybe_reset_vf(pf, vf, reset_vf_tx,
+					       reset_vf_rx);
 	}
 	mutex_unlock(&pf->vfs.table_lock);
 
@@ -3648,7 +3685,7 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 	struct ice_vsi_cfg_params params = {};
 
 	params.type = ICE_VSI_PF;
-	params.pi = pi;
+	params.port_info = pi;
 	params.flags = ICE_VSI_FLAG_INIT;
 
 	return ice_vsi_setup(pf, &params);
@@ -3661,7 +3698,7 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	struct ice_vsi_cfg_params params = {};
 
 	params.type = ICE_VSI_CHNL;
-	params.pi = pi;
+	params.port_info = pi;
 	params.ch = ch;
 	params.flags = ICE_VSI_FLAG_INIT;
 
@@ -3682,7 +3719,7 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 	struct ice_vsi_cfg_params params = {};
 
 	params.type = ICE_VSI_CTRL;
-	params.pi = pi;
+	params.port_info = pi;
 	params.flags = ICE_VSI_FLAG_INIT;
 
 	return ice_vsi_setup(pf, &params);
@@ -3702,7 +3739,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 	struct ice_vsi_cfg_params params = {};
 
 	params.type = ICE_VSI_LB;
-	params.pi = pi;
+	params.port_info = pi;
 	params.flags = ICE_VSI_FLAG_INIT;
 
 	return ice_vsi_setup(pf, &params);
@@ -4417,11 +4454,13 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf)
 /**
  * ice_request_fw - Device initialization routine
  * @pf: pointer to the PF instance
+ * @firmware: double pointer to firmware struct
+ *
+ * Return: zero when successful, negative values otherwise.
  */
-static void ice_request_fw(struct ice_pf *pf)
+static int ice_request_fw(struct ice_pf *pf, const struct firmware **firmware)
 {
 	char *opt_fw_filename = ice_get_opt_fw_name(pf);
-	const struct firmware *firmware = NULL;
 	struct device *dev = ice_pf_to_dev(pf);
 	int err = 0;
 
@@ -4430,29 +4469,95 @@ static void ice_request_fw(struct ice_pf *pf)
 	 * and warning messages for other errors.
 	 */
 	if (opt_fw_filename) {
-		err = firmware_request_nowarn(&firmware, opt_fw_filename, dev);
-		if (err) {
-			kfree(opt_fw_filename);
-			goto dflt_pkg_load;
-		}
-
-		/* request for firmware was successful. Download to device */
-		ice_load_pkg(firmware, pf);
+		err = firmware_request_nowarn(firmware, opt_fw_filename, dev);
 		kfree(opt_fw_filename);
-		release_firmware(firmware);
-		return;
+		if (!err)
+			return err;
+	}
+	err = request_firmware(firmware, ICE_DDP_PKG_FILE, dev);
+	if (err)
+		dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
+
+	return err;
+}
+
+/**
+ * ice_init_tx_topology - performs Tx topology initialization
+ * @hw: pointer to the hardware structure
+ * @firmware: pointer to firmware structure
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int
+ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
+{
+	u8 num_tx_sched_layers = hw->num_tx_sched_layers;
+	struct ice_pf *pf = hw->back;
+	struct device *dev;
+	u8 *buf_copy;
+	int err;
+
+	dev = ice_pf_to_dev(pf);
+	/* ice_cfg_tx_topo buf argument is not a constant,
+	 * so we have to make a copy
+	 */
+	buf_copy = kmemdup(firmware->data, firmware->size, GFP_KERNEL);
+
+	err = ice_cfg_tx_topo(hw, buf_copy, firmware->size);
+	if (!err) {
+		if (hw->num_tx_sched_layers > num_tx_sched_layers)
+			dev_info(dev, "Tx scheduling layers switching feature disabled\n");
+		else
+			dev_info(dev, "Tx scheduling layers switching feature enabled\n");
+		/* if there was a change in topology ice_cfg_tx_topo triggered
+		 * a CORER and we need to re-init hw
+		 */
+		ice_deinit_hw(hw);
+		err = ice_init_hw(hw);
+
+		return err;
+	} else if (err == -EIO) {
+		dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
 	}
 
-dflt_pkg_load:
-	err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
+	return 0;
+}
+
+/**
+ * ice_init_ddp_config - DDP related configuration
+ * @hw: pointer to the hardware structure
+ * @pf: pointer to pf structure
+ *
+ * This function loads DDP file from the disk, then initializes Tx
+ * topology. At the end DDP package is loaded on the card.
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int ice_init_ddp_config(struct ice_hw *hw, struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	const struct firmware *firmware = NULL;
+	int err;
+
+	err = ice_request_fw(pf, &firmware);
 	if (err) {
-		dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
-		return;
+		dev_err(dev, "Fail during requesting FW: %d\n", err);
+		return err;
 	}
 
-	/* request for firmware was successful. Download to device */
+	err = ice_init_tx_topology(hw, firmware);
+	if (err) {
+		dev_err(dev, "Fail during initialization of Tx topology: %d\n",
+			err);
+		release_firmware(firmware);
+		return err;
+	}
+
+	/* Download firmware to device */
 	ice_load_pkg(firmware, pf);
 	release_firmware(firmware);
+
+	return 0;
 }
 
 /**
@@ -4625,9 +4730,11 @@ int ice_init_dev(struct ice_pf *pf)
 
 	ice_init_feature_support(pf);
 
-	ice_request_fw(pf);
+	err = ice_init_ddp_config(hw, pf);
+	if (err)
+		return err;
 
-	/* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
+	/* if ice_init_ddp_config fails, ICE_FLAG_ADV_FEATURES bit won't be
 	 * set in pf->state, which will cause ice_is_safe_mode to return
 	 * true
 	 */
@@ -5093,6 +5200,7 @@ static int
 ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 {
 	struct device *dev = &pdev->dev;
+	struct ice_adapter *adapter;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	int err;
@@ -5145,7 +5253,12 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	pci_set_master(pdev);
 
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter))
+		return PTR_ERR(adapter);
+
 	pf->pdev = pdev;
+	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5179,23 +5292,23 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
-	devl_unlock(priv_to_devlink(pf));
 	if (err)
 		goto err_load;
 
 	err = ice_init_devlink(pf);
 	if (err)
 		goto err_init_devlink;
+	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
 err_init_devlink:
-	devl_lock(priv_to_devlink(pf));
 	ice_unload(pf);
-	devl_unlock(priv_to_devlink(pf));
 err_load:
+	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
 err_init:
+	ice_adapter_put(pdev);
 	pci_disable_device(pdev);
 	return err;
 }
@@ -5290,9 +5403,9 @@ static void ice_remove(struct pci_dev *pdev)
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
 
+	devl_lock(priv_to_devlink(pf));
 	ice_deinit_devlink(pf);
 
-	devl_lock(priv_to_devlink(pf));
 	ice_unload(pf);
 	devl_unlock(priv_to_devlink(pf));
 
@@ -5302,6 +5415,7 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_setup_mc_magic_wake(pf);
 	ice_set_wake(pf);
 
+	ice_adapter_put(pdev);
 	pci_disable_device(pdev);
 }
 
@@ -5321,7 +5435,6 @@ static void ice_shutdown(struct pci_dev *pdev)
 	}
 }
 
-#ifdef CONFIG_PM
 /**
  * ice_prepare_for_shutdown - prep for PCI shutdown
  * @pf: board private structure
@@ -5410,7 +5523,7 @@ err_reinit:
  * Power Management callback to quiesce the device and prepare
  * for D3 transition.
  */
-static int __maybe_unused ice_suspend(struct device *dev)
+static int ice_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct ice_pf *pf;
@@ -5477,7 +5590,7 @@ static int __maybe_unused ice_suspend(struct device *dev)
  * ice_resume - PM callback for waking up from D3
  * @dev: generic device information structure
  */
-static int __maybe_unused ice_resume(struct device *dev)
+static int ice_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	enum ice_reset_req reset_type;
@@ -5528,7 +5641,6 @@ static int __maybe_unused ice_resume(struct device *dev)
 
 	return 0;
 }
-#endif /* CONFIG_PM */
 
 /**
  * ice_pci_err_detected - warning that PCI error has been detected
@@ -5693,16 +5805,22 @@ static const struct pci_device_id ice_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_QSFP), },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SFP), },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SGMII), },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP_DD) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_BACKPLANE) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_QSFP56) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP_DD) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_QSFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), },
 	/* required last entry */
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ice_pci_tbl);
 
-static __maybe_unused SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume);
 
 static const struct pci_error_handlers ice_pci_err_handler = {
 	.error_detected = ice_pci_err_detected,
@@ -5717,9 +5835,7 @@ static struct pci_driver ice_driver = {
 	.id_table = ice_pci_tbl,
 	.probe = ice_probe,
 	.remove = ice_remove,
-#ifdef CONFIG_PM
-	.driver.pm = &ice_pm_ops,
-#endif /* CONFIG_PM */
+	.driver.pm = pm_sleep_ptr(&ice_pm_ops),
 	.shutdown = ice_shutdown,
 	.sriov_configure = ice_sriov_configure,
 	.sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix,
@@ -7055,13 +7171,11 @@ int ice_down(struct ice_vsi *vsi)
 
 	WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state));
 
-	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
 		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
-	} else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) {
-		ice_eswitch_stop_all_tx_queues(vsi->back);
 	}
 
 	ice_vsi_dis_irq(vsi);
@@ -7544,11 +7658,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_vsi_rebuild;
 	}
 
-	err = ice_eswitch_rebuild(pf);
-	if (err) {
-		dev_err(dev, "Switchdev rebuild failed: %d\n", err);
-		goto err_vsi_rebuild;
-	}
+	ice_eswitch_rebuild(pf);
 
 	if (reset_type == ICE_RESET_PFR) {
 		err = ice_rebuild_channels(pf);
@@ -7666,7 +7776,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EBUSY;
 	}
 
-	netdev->mtu = (unsigned int)new_mtu;
+	WRITE_ONCE(netdev->mtu, (unsigned int)new_mtu);
 	err = ice_down_up(vsi);
 	if (err)
 		return err;
@@ -7999,12 +8109,9 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		__u16 mode;
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
+		__u16 mode = nla_get_u16(attr);
 
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-		mode = nla_get_u16(attr);
 		if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB)
 			return -EINVAL;
 		/* Continue  if bridge mode is not being flipped */
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index d4e05d2cb30c..84eab92dc03c 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -18,10 +18,9 @@
  *
  * Read the NVM using the admin queue commands (0x0701)
  */
-static int
-ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length,
-		void *data, bool last_command, bool read_shadow_ram,
-		struct ice_sq_cd *cd)
+int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
+		    u16 length, void *data, bool last_command,
+		    bool read_shadow_ram, struct ice_sq_cd *cd)
 {
 	struct ice_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h
index 774c2317967d..63cdc6bdac58 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.h
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.h
@@ -14,6 +14,9 @@ struct ice_orom_civd_info {
 
 int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access);
 void ice_release_nvm(struct ice_hw *hw);
+int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
+		    u16 length, void *data, bool last_command,
+		    bool read_shadow_ram, struct ice_sq_cd *cd);
 int
 ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
 		  bool read_shadow_ram);
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index f6f27361c3cf..755a9c55267c 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -43,6 +43,7 @@ enum ice_protocol_type {
 	ICE_NVGRE,
 	ICE_GTP,
 	ICE_GTP_NO_PAY,
+	ICE_PFCP,
 	ICE_PPPOE,
 	ICE_L2TPV3,
 	ICE_VLAN_EX,
@@ -61,6 +62,7 @@ enum ice_sw_tunnel_type {
 	ICE_SW_TUN_NVGRE,
 	ICE_SW_TUN_GTPU,
 	ICE_SW_TUN_GTPC,
+	ICE_SW_TUN_PFCP,
 	ICE_ALL_TUNNELS /* All tunnel types including NVGRE */
 };
 
@@ -202,6 +204,15 @@ struct ice_udp_gtp_hdr {
 	u8 rsvrd;
 };
 
+struct ice_pfcp_hdr {
+	u8 flags;
+	u8 msg_type;
+	__be16 length;
+	__be64 seid;
+	__be32 seq;
+	u8 spare;
+} __packed __aligned(__alignof__(u16));
+
 struct ice_pppoe_hdr {
 	u8 rsrvd_ver_type;
 	u8 rsrvd_code;
@@ -418,6 +429,7 @@ union ice_prot_hdr {
 	struct ice_udp_tnl_hdr tnl_hdr;
 	struct ice_nvgre_hdr nvgre_hdr;
 	struct ice_udp_gtp_hdr gtp_hdr;
+	struct ice_pfcp_hdr pfcp_hdr;
 	struct ice_pppoe_hdr pppoe_hdr;
 	struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr;
 	struct ice_hw_metadata metadata;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index c11eba07283c..0f17fc1181d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -374,6 +374,7 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
 	u8 tmr_idx;
 
 	tmr_idx = ice_get_ptp_src_clock_index(hw);
+	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	/* Read the system timestamp pre PHC read */
 	ptp_read_system_prets(sts);
 
@@ -1166,26 +1167,6 @@ static void ice_ptp_reset_cached_phctime(struct ice_pf *pf)
 }
 
 /**
- * ice_ptp_read_time - Read the time from the device
- * @pf: Board private structure
- * @ts: timespec structure to hold the current time value
- * @sts: Optional parameter for holding a pair of system timestamps from
- *       the system clock. Will be ignored if NULL is given.
- *
- * This function reads the source clock registers and stores them in a timespec.
- * However, since the registers are 64 bits of nanoseconds, we must convert the
- * result to a timespec before we can return.
- */
-static void
-ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts,
-		  struct ptp_system_timestamp *sts)
-{
-	u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts);
-
-	*ts = ns_to_timespec64(time_ns);
-}
-
-/**
  * ice_ptp_write_init - Set PHC time to provided value
  * @pf: Board private structure
  * @ts: timespec structure that holds the new time value
@@ -1925,16 +1906,10 @@ ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts,
 		   struct ptp_system_timestamp *sts)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
-	struct ice_hw *hw = &pf->hw;
-
-	if (!ice_ptp_lock(hw)) {
-		dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n");
-		return -EBUSY;
-	}
-
-	ice_ptp_read_time(pf, ts, sts);
-	ice_ptp_unlock(hw);
+	u64 time_ns;
 
+	time_ns = ice_ptp_read_src_clk_reg(pf, sts);
+	*ts = ns_to_timespec64(time_ns);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 187ce9b54e1a..2b9423a173bb 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -274,6 +274,9 @@ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
  */
 static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 {
+	struct ice_pf *pf = container_of(hw, struct ice_pf, hw);
+
+	guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock);
 	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
 	ice_flush(hw);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 5f30fb131f74..d367f4c66dcd 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -3,42 +3,51 @@
 
 #include "ice.h"
 #include "ice_eswitch.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "devlink/devlink_port.h"
 #include "ice_sriov.h"
 #include "ice_tc_lib.h"
 #include "ice_dcb_lib.h"
 
 /**
- * ice_repr_get_sw_port_id - get port ID associated with representor
- * @repr: pointer to port representor
+ * ice_repr_inc_tx_stats - increment Tx statistic by one packet
+ * @repr: repr to increment stats on
+ * @len: length of the packet
+ * @xmit_status: value returned by xmit function
  */
-static int ice_repr_get_sw_port_id(struct ice_repr *repr)
+void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len,
+			   int xmit_status)
 {
-	return repr->src_vsi->back->hw.port_info->lport;
+	struct ice_repr_pcpu_stats *stats;
+
+	if (unlikely(xmit_status != NET_XMIT_SUCCESS &&
+		     xmit_status != NET_XMIT_CN)) {
+		this_cpu_inc(repr->stats->tx_drops);
+		return;
+	}
+
+	stats = this_cpu_ptr(repr->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->tx_packets++;
+	stats->tx_bytes += len;
+	u64_stats_update_end(&stats->syncp);
 }
 
 /**
- * ice_repr_get_phys_port_name - get phys port name
- * @netdev: pointer to port representor netdev
- * @buf: write here port name
- * @len: max length of buf
+ * ice_repr_inc_rx_stats - increment Rx statistic by one packet
+ * @netdev: repr netdev to increment stats on
+ * @len: length of the packet
  */
-static int
-ice_repr_get_phys_port_name(struct net_device *netdev, char *buf, size_t len)
+void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len)
 {
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_repr *repr = np->repr;
-	int res;
-
-	/* Devlink port is registered and devlink core is taking care of name formatting. */
-	if (repr->vf->devlink_port.devlink)
-		return -EOPNOTSUPP;
+	struct ice_repr *repr = ice_netdev_to_repr(netdev);
+	struct ice_repr_pcpu_stats *stats;
 
-	res = snprintf(buf, len, "pf%dvfr%d", ice_repr_get_sw_port_id(repr),
-		       repr->id);
-	if (res <= 0)
-		return -EOPNOTSUPP;
-	return 0;
+	stats = this_cpu_ptr(repr->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += len;
+	u64_stats_update_end(&stats->syncp);
 }
 
 /**
@@ -76,7 +85,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
  * ice_netdev_to_repr - Get port representor for given netdevice
  * @netdev: pointer to port representor netdev
  */
-struct ice_repr *ice_netdev_to_repr(struct net_device *netdev)
+struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 
@@ -139,38 +148,35 @@ static int ice_repr_stop(struct net_device *netdev)
  * ice_repr_sp_stats64 - get slow path stats for port representor
  * @dev: network interface device structure
  * @stats: netlink stats structure
- *
- * RX/TX stats are being swapped here to be consistent with VF stats. In slow
- * path, port representor receives data when the corresponding VF is sending it
- * (and vice versa), TX and RX bytes/packets are effectively swapped on port
- * representor.
  */
 static int
 ice_repr_sp_stats64(const struct net_device *dev,
 		    struct rtnl_link_stats64 *stats)
 {
-	struct ice_netdev_priv *np = netdev_priv(dev);
-	int vf_id = np->repr->vf->vf_id;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
-	u64 pkts, bytes;
-
-	tx_ring = np->vsi->tx_rings[vf_id];
-	ice_fetch_u64_stats_per_ring(&tx_ring->ring_stats->syncp,
-				     tx_ring->ring_stats->stats,
-				     &pkts, &bytes);
-	stats->rx_packets = pkts;
-	stats->rx_bytes = bytes;
-
-	rx_ring = np->vsi->rx_rings[vf_id];
-	ice_fetch_u64_stats_per_ring(&rx_ring->ring_stats->syncp,
-				     rx_ring->ring_stats->stats,
-				     &pkts, &bytes);
-	stats->tx_packets = pkts;
-	stats->tx_bytes = bytes;
-	stats->tx_dropped = rx_ring->ring_stats->rx_stats.alloc_page_failed +
-			    rx_ring->ring_stats->rx_stats.alloc_buf_failed;
-
+	struct ice_repr *repr = ice_netdev_to_repr(dev);
+	int i;
+
+	for_each_possible_cpu(i) {
+		u64 tbytes, tpkts, tdrops, rbytes, rpkts;
+		struct ice_repr_pcpu_stats *repr_stats;
+		unsigned int start;
+
+		repr_stats = per_cpu_ptr(repr->stats, i);
+		do {
+			start = u64_stats_fetch_begin(&repr_stats->syncp);
+			tbytes = repr_stats->tx_bytes;
+			tpkts = repr_stats->tx_packets;
+			tdrops = repr_stats->tx_drops;
+			rbytes = repr_stats->rx_bytes;
+			rpkts = repr_stats->rx_packets;
+		} while (u64_stats_fetch_retry(&repr_stats->syncp, start));
+
+		stats->tx_bytes += tbytes;
+		stats->tx_packets += tpkts;
+		stats->tx_dropped += tdrops;
+		stats->rx_bytes += rbytes;
+		stats->rx_packets += rpkts;
+	}
 	return 0;
 }
 
@@ -240,7 +246,6 @@ ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 }
 
 static const struct net_device_ops ice_repr_netdev_ops = {
-	.ndo_get_phys_port_name = ice_repr_get_phys_port_name,
 	.ndo_get_stats64 = ice_repr_get_stats64,
 	.ndo_open = ice_repr_open,
 	.ndo_stop = ice_repr_stop,
@@ -291,7 +296,7 @@ static void ice_repr_remove_node(struct devlink_port *devlink_port)
  */
 static void ice_repr_rem(struct ice_repr *repr)
 {
-	kfree(repr->q_vector);
+	free_percpu(repr->stats);
 	free_netdev(repr->netdev);
 	kfree(repr);
 }
@@ -331,7 +336,6 @@ static void ice_repr_set_tx_topology(struct ice_pf *pf)
 static struct ice_repr *
 ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac)
 {
-	struct ice_q_vector *q_vector;
 	struct ice_netdev_priv *np;
 	struct ice_repr *repr;
 	int err;
@@ -346,23 +350,22 @@ ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac)
 		goto err_alloc;
 	}
 
+	repr->stats = netdev_alloc_pcpu_stats(struct ice_repr_pcpu_stats);
+	if (!repr->stats) {
+		err = -ENOMEM;
+		goto err_stats;
+	}
+
 	repr->src_vsi = src_vsi;
+	repr->id = src_vsi->vsi_num;
 	np = netdev_priv(repr->netdev);
 	np->repr = repr;
 
-	q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL);
-	if (!q_vector) {
-		err = -ENOMEM;
-		goto err_alloc_q_vector;
-	}
-	repr->q_vector = q_vector;
-	repr->q_id = repr->id;
-
 	ether_addr_copy(repr->parent_mac, parent_mac);
 
 	return repr;
 
-err_alloc_q_vector:
+err_stats:
 	free_netdev(repr->netdev);
 err_alloc:
 	kfree(repr);
@@ -439,15 +442,3 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr)
 	netif_carrier_off(repr->netdev);
 	netif_tx_stop_all_queues(repr->netdev);
 }
-
-/**
- * ice_repr_set_traffic_vsi - set traffic VSI for port representor
- * @repr: repr on with VSI will be set
- * @vsi: pointer to VSI that will be used by port representor to pass traffic
- */
-void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi)
-{
-	struct ice_netdev_priv *np = netdev_priv(repr->netdev);
-
-	np->vsi = vsi;
-}
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index f9aede315716..cff730b15ca0 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -6,20 +6,24 @@
 
 #include <net/dst_metadata.h>
 
+struct ice_repr_pcpu_stats {
+	struct u64_stats_sync syncp;
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 tx_drops;
+};
+
 struct ice_repr {
 	struct ice_vsi *src_vsi;
 	struct ice_vf *vf;
-	struct ice_q_vector *q_vector;
 	struct net_device *netdev;
 	struct metadata_dst *dst;
 	struct ice_esw_br_port *br_port;
-	int q_id;
+	struct ice_repr_pcpu_stats __percpu *stats;
 	u32 id;
 	u8 parent_mac[ETH_ALEN];
-#ifdef CONFIG_ICE_SWITCHDEV
-	/* info about slow path rule */
-	struct ice_rule_query_data sp_rule;
-#endif
 };
 
 struct ice_repr *ice_repr_add_vf(struct ice_vf *vf);
@@ -28,10 +32,12 @@ void ice_repr_rem_vf(struct ice_repr *repr);
 void ice_repr_start_tx_queues(struct ice_repr *repr);
 void ice_repr_stop_tx_queues(struct ice_repr *repr);
 
-void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi);
-
-struct ice_repr *ice_netdev_to_repr(struct net_device *netdev);
+struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev);
 bool ice_is_port_repr_netdev(const struct net_device *netdev);
 
 struct ice_repr *ice_repr_get_by_vsi(struct ice_vsi *vsi);
+
+void ice_repr_inc_tx_stats(struct ice_repr *repr, unsigned int len,
+			   int xmit_status);
+void ice_repr_inc_rx_stats(struct net_device *netdev, unsigned int len);
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index a1525992d14b..ecf8f5d60292 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1128,12 +1128,11 @@ u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
 	 *     5 or less       sw_entry_point_layer
 	 */
 	/* calculate the VSI layer based on number of layers. */
-	if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) {
-		u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
-
-		if (layer > hw->sw_entry_point_layer)
-			return layer;
-	}
+	if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS)
+		return hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
+	else if (hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS)
+		/* qgroup and VSI layers are same */
+		return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET;
 	return hw->sw_entry_point_layer;
 }
 
@@ -1150,13 +1149,10 @@ u8 ice_sched_get_agg_layer(struct ice_hw *hw)
 	 *     7 or less       sw_entry_point_layer
 	 */
 	/* calculate the aggregator layer based on number of layers. */
-	if (hw->num_tx_sched_layers > ICE_AGG_LAYER_OFFSET + 1) {
-		u8 layer = hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET;
-
-		if (layer > hw->sw_entry_point_layer)
-			return layer;
-	}
-	return hw->sw_entry_point_layer;
+	if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS)
+		return hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET;
+	else
+		return hw->sw_entry_point_layer;
 }
 
 /**
@@ -1510,10 +1506,11 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 {
 	struct ice_sched_node *vsi_node, *qgrp_node;
 	struct ice_vsi_ctx *vsi_ctx;
+	u8 qgrp_layer, vsi_layer;
 	u16 max_children;
-	u8 qgrp_layer;
 
 	qgrp_layer = ice_sched_get_qgrp_layer(pi->hw);
+	vsi_layer = ice_sched_get_vsi_layer(pi->hw);
 	max_children = pi->hw->max_children[qgrp_layer];
 
 	vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
@@ -1524,6 +1521,12 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	if (!vsi_node)
 		return NULL;
 
+	/* If the queue group and VSI layer are same then queues
+	 * are all attached directly to VSI
+	 */
+	if (qgrp_layer == vsi_layer)
+		return vsi_node;
+
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
@@ -3199,7 +3202,7 @@ ice_sched_add_rl_profile(struct ice_port_info *pi,
 	u8 profile_type;
 	int status;
 
-	if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM)
+	if (!pi || layer_num >= pi->hw->num_tx_sched_layers)
 		return NULL;
 	switch (rl_type) {
 	case ICE_MIN_BW:
@@ -3215,8 +3218,6 @@ ice_sched_add_rl_profile(struct ice_port_info *pi,
 		return NULL;
 	}
 
-	if (!pi)
-		return NULL;
 	hw = pi->hw;
 	list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num],
 			    list_entry)
@@ -3446,7 +3447,7 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type,
 	struct ice_aqc_rl_profile_info *rl_prof_elem;
 	int status = 0;
 
-	if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM)
+	if (layer_num >= pi->hw->num_tx_sched_layers)
 		return -EINVAL;
 	/* Check the existing list for RL profile */
 	list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num],
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 1aef05ea5a57..7b668083be07 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -6,6 +6,17 @@
 
 #include "ice_common.h"
 
+/**
+ * DOC: ice_sched.h
+ *
+ * This header file stores everything that is needed for broadly understood
+ * scheduler. It consists of defines related to layers, structures related to
+ * aggregator, functions declarations and others.
+ */
+
+#define ICE_SCHED_5_LAYERS	5
+#define ICE_SCHED_9_LAYERS	9
+
 #define SCHED_NODE_NAME_MAX_LEN 32
 
 #define ICE_QGRP_LAYER_OFFSET	2
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index a958fcf3e6be..067712f4923f 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -170,8 +170,6 @@ void ice_free_vfs(struct ice_pf *pf)
 	else
 		dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n");
 
-	ice_eswitch_reserve_cp_queues(pf, -ice_get_num_vfs(pf));
-
 	mutex_lock(&vfs->table_lock);
 
 	ice_for_each_vf(pf, bkt, vf) {
@@ -227,7 +225,7 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 
 	params.type = ICE_VSI_VF;
-	params.pi = ice_vf_get_port_info(vf);
+	params.port_info = ice_vf_get_port_info(vf);
 	params.vf = vf;
 	params.flags = ICE_VSI_FLAG_INIT;
 
@@ -362,13 +360,14 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
  * @vf: VF to calculate the register index for
  * @q_vector: a q_vector associated to the VF
  */
-int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
+void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 {
 	if (!vf || !q_vector)
-		return -EINVAL;
+		return;
 
 	/* always add one to account for the OICR being the first MSIX */
-	return vf->first_vector_idx + q_vector->v_idx + 1;
+	q_vector->vf_reg_idx = q_vector->v_idx + ICE_NONQ_VECS_VF;
+	q_vector->reg_idx = vf->first_vector_idx + q_vector->vf_reg_idx;
 }
 
 /**
@@ -833,11 +832,6 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
 
 		pci_dev_get(vfdev);
 
-		/* set default number of MSI-X */
-		vf->num_msix = pf->vfs.num_msix_per;
-		vf->num_vf_qs = pf->vfs.num_qps_per;
-		ice_vc_set_default_allowlist(vf);
-
 		hash_add_rcu(vfs->table, &vf->entry, vf_id);
 	}
 
@@ -897,7 +891,6 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 		goto err_unroll_sriov;
 	}
 
-	ice_eswitch_reserve_cp_queues(pf, num_vfs);
 	ret = ice_start_vfs(pf);
 	if (ret) {
 		dev_err(dev, "Failed to start %d VFs, err %d\n", num_vfs, ret);
@@ -1869,6 +1862,24 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
 }
 
 /**
+ * ice_print_vf_tx_mdd_event - print VF Tx malicious driver detect event
+ * @vf: pointer to the VF structure
+ */
+void ice_print_vf_tx_mdd_event(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct device *dev;
+
+	dev = ice_pf_to_dev(pf);
+
+	dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
+		 vf->mdd_tx_events.count, pf->hw.pf_id, vf->vf_id,
+		 vf->dev_lan_addr,
+		 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
+			  ? "on" : "off");
+}
+
+/**
  * ice_print_vfs_mdd_events - print VFs malicious driver detect event
  * @pf: pointer to the PF structure
  *
@@ -1876,8 +1887,6 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
  */
 void ice_print_vfs_mdd_events(struct ice_pf *pf)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_hw *hw = &pf->hw;
 	struct ice_vf *vf;
 	unsigned int bkt;
 
@@ -1904,10 +1913,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf)
 		if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) {
 			vf->mdd_tx_events.last_printed =
 							vf->mdd_tx_events.count;
-
-			dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n",
-				 vf->mdd_tx_events.count, hw->pf_id, vf->vf_id,
-				 vf->dev_lan_addr);
+			ice_print_vf_tx_mdd_event(vf);
 		}
 	}
 	mutex_unlock(&pf->vfs.table_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h
index 8488df38b586..8f22313474d6 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.h
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.h
@@ -49,7 +49,7 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state);
 
 int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena);
 
-int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector);
+void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector);
 
 int
 ice_get_vf_stats(struct net_device *netdev, int vf_id,
@@ -58,6 +58,7 @@ void
 ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event);
 void ice_print_vfs_mdd_events(struct ice_pf *pf);
 void ice_print_vf_rx_mdd_event(struct ice_vf *vf);
+void ice_print_vf_tx_mdd_event(struct ice_vf *vf);
 bool
 ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto);
 u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev);
@@ -69,6 +70,7 @@ static inline
 void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { }
 static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { }
 static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { }
+static inline void ice_print_vf_tx_mdd_event(struct ice_vf *vf) { }
 static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { }
 
 static inline int
@@ -130,11 +132,10 @@ ice_set_vf_bw(struct net_device __always_unused *netdev,
 	return -EOPNOTSUPP;
 }
 
-static inline int
+static inline void
 ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf,
 		    struct ice_q_vector __always_unused *q_vector)
 {
-	return 0;
 }
 
 static inline int
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index b4ea935e8300..94d6670d0901 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -42,6 +42,7 @@ enum {
 	ICE_PKT_KMALLOC		= BIT(9),
 	ICE_PKT_PPPOE		= BIT(10),
 	ICE_PKT_L2TPV3		= BIT(11),
+	ICE_PKT_PFCP		= BIT(12),
 };
 
 struct ice_dummy_pkt_offsets {
@@ -1110,6 +1111,77 @@ ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = {
 	0x00, 0x00,
 };
 
+ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv4) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_IPV4_OFOS,	14 },
+	{ ICE_UDP_ILOS,		34 },
+	{ ICE_PFCP,		42 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv4) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x08, 0x00,		/* ICE_ETYPE_OL 12 */
+
+	0x45, 0x00, 0x00, 0x2c, /* ICE_IPV4_OFOS 14 */
+	0x00, 0x01, 0x00, 0x00,
+	0x00, 0x11, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 34 */
+	0x00, 0x18, 0x00, 0x00,
+
+	0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 42 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 byte alignment */
+};
+
+ICE_DECLARE_PKT_OFFSETS(pfcp_session_ipv6) = {
+	{ ICE_MAC_OFOS,		0 },
+	{ ICE_ETYPE_OL,		12 },
+	{ ICE_IPV6_OFOS,	14 },
+	{ ICE_UDP_ILOS,		54 },
+	{ ICE_PFCP,		62 },
+	{ ICE_PROTOCOL_LAST,	0 },
+};
+
+ICE_DECLARE_PKT_TEMPLATE(pfcp_session_ipv6) = {
+	0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x86, 0xdd,		/* ICE_ETYPE_OL 12 */
+
+	0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */
+	0x00, 0x10, 0x11, 0x00, /* Next header UDP */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00, 0x22, 0x65, /* ICE_UDP_ILOS 54 */
+	0x00, 0x18, 0x00, 0x00,
+
+	0x21, 0x01, 0x00, 0x0c, /* ICE_PFCP 62 */
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+
+	0x00, 0x00,		/* 2 bytes for 4 byte alignment */
+};
+
 ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = {
 	{ ICE_MAC_OFOS,		0 },
 	{ ICE_ETYPE_OL,		12 },
@@ -1343,6 +1415,8 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = {
 	ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU),
 	ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6),
 	ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC),
+	ICE_PKT_PROFILE(pfcp_session_ipv6, ICE_PKT_PFCP | ICE_PKT_OUTER_IPV6),
+	ICE_PKT_PROFILE(pfcp_session_ipv4, ICE_PKT_PFCP),
 	ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 |
 					ICE_PKT_INNER_UDP),
 	ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6),
@@ -2075,6 +2149,18 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
 }
 
 /**
+ * ice_init_chk_recipe_reuse_support - check if recipe reuse is supported
+ * @hw: pointer to the hardware structure
+ */
+void ice_init_chk_recipe_reuse_support(struct ice_hw *hw)
+{
+	struct ice_nvm_info *nvm = &hw->flash.nvm;
+
+	hw->recp_reuse = (nvm->major == 0x4 && nvm->minor >= 0x30) ||
+			 nvm->major > 0x4;
+}
+
+/**
  * ice_alloc_recipe - add recipe resource
  * @hw: pointer to the hardware structure
  * @rid: recipe ID returned as response to AQ call
@@ -2083,12 +2169,16 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
 {
 	DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1);
 	u16 buf_len = __struct_size(sw_buf);
+	u16 res_type;
 	int status;
 
 	sw_buf->num_elems = cpu_to_le16(1);
-	sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE <<
-					ICE_AQC_RES_TYPE_S) |
-					ICE_AQC_RES_TYPE_FLAG_SHARED);
+	res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE);
+	if (hw->recp_reuse)
+		res_type |= ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED;
+	else
+		res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED;
+	sw_buf->res_type = cpu_to_le16(res_type);
 	status = ice_aq_alloc_free_res(hw, sw_buf, buf_len,
 				       ice_aqc_opc_alloc_res);
 	if (!status)
@@ -2098,6 +2188,70 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid)
 }
 
 /**
+ * ice_free_recipe_res - free recipe resource
+ * @hw: pointer to the hardware structure
+ * @rid: recipe ID to free
+ *
+ * Return: 0 on success, and others on error
+ */
+static int ice_free_recipe_res(struct ice_hw *hw, u16 rid)
+{
+	return ice_free_hw_res(hw, ICE_AQC_RES_TYPE_RECIPE, 1, &rid);
+}
+
+/**
+ * ice_release_recipe_res - disassociate and free recipe resource
+ * @hw: pointer to the hardware structure
+ * @recp: the recipe struct resource to unassociate and free
+ *
+ * Return: 0 on success, and others on error
+ */
+static int ice_release_recipe_res(struct ice_hw *hw,
+				  struct ice_sw_recipe *recp)
+{
+	DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES);
+	struct ice_switch_info *sw = hw->switch_info;
+	u64 recp_assoc;
+	u32 rid, prof;
+	int status;
+
+	for_each_set_bit(rid, recp->r_bitmap, ICE_MAX_NUM_RECIPES) {
+		for_each_set_bit(prof, recipe_to_profile[rid],
+				 ICE_MAX_NUM_PROFILES) {
+			status = ice_aq_get_recipe_to_profile(hw, prof,
+							      &recp_assoc,
+							      NULL);
+			if (status)
+				return status;
+
+			bitmap_from_arr64(r_bitmap, &recp_assoc,
+					  ICE_MAX_NUM_RECIPES);
+			bitmap_andnot(r_bitmap, r_bitmap, recp->r_bitmap,
+				      ICE_MAX_NUM_RECIPES);
+			bitmap_to_arr64(&recp_assoc, r_bitmap,
+					ICE_MAX_NUM_RECIPES);
+			ice_aq_map_recipe_to_profile(hw, prof,
+						     recp_assoc, NULL);
+
+			clear_bit(rid, profile_to_recipe[prof]);
+			clear_bit(prof, recipe_to_profile[rid]);
+		}
+
+		status = ice_free_recipe_res(hw, rid);
+		if (status)
+			return status;
+
+		sw->recp_list[rid].recp_created = false;
+		sw->recp_list[rid].adv_rule = false;
+		memset(&sw->recp_list[rid].lkup_exts, 0,
+		       sizeof(sw->recp_list[rid].lkup_exts));
+		clear_bit(rid, recp->r_bitmap);
+	}
+
+	return 0;
+}
+
+/**
  * ice_get_recp_to_prof_map - updates recipe to profile mapping
  * @hw: pointer to hardware structure
  *
@@ -2146,6 +2300,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf,
  * @recps: struct that we need to populate
  * @rid: recipe ID that we are populating
  * @refresh_required: true if we should get recipe to profile mapping from FW
+ * @is_add: flag of adding recipe
  *
  * This function is used to populate all the necessary entries into our
  * bookkeeping so that we have a current list of all the recipes that are
@@ -2153,7 +2308,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf,
  */
 static int
 ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
-		    bool *refresh_required)
+		    bool *refresh_required, bool is_add)
 {
 	DECLARE_BITMAP(result_bm, ICE_MAX_FV_WORDS);
 	struct ice_aqc_recipe_data_elem *tmp;
@@ -2270,8 +2425,12 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
 			recps[idx].chain_idx = ICE_INVAL_CHAIN_IND;
 		}
 
-		if (!is_root)
+		if (!is_root) {
+			if (hw->recp_reuse && is_add)
+				recps[idx].recp_created = true;
+
 			continue;
+		}
 
 		/* Only do the following for root recipes entries */
 		memcpy(recps[idx].r_bitmap, root_bufs.recipe_bitmap,
@@ -2295,7 +2454,8 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
 
 	/* Copy result indexes */
 	bitmap_copy(recps[rid].res_idxs, result_bm, ICE_MAX_FV_WORDS);
-	recps[rid].recp_created = true;
+	if (is_add)
+		recps[rid].recp_created = true;
 
 err_unroll:
 	kfree(tmp);
@@ -2446,6 +2606,9 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
 			fi->lan_en = true;
 		}
 	}
+
+	if (fi->flag & ICE_FLTR_TX_ONLY)
+		fi->lan_en = false;
 }
 
 /**
@@ -3821,6 +3984,7 @@ ice_cfg_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, bool set,
 	} else if (f_info.flag & ICE_FLTR_TX) {
 		f_info.src_id = ICE_SRC_ID_VSI;
 		f_info.src = hw_vsi_id;
+		f_info.flag |= ICE_FLTR_TX_ONLY;
 	}
 	f_list_entry.fltr_info = f_info;
 
@@ -4528,6 +4692,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = {
 	ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6),
 	ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22),
 	ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14),
+	ICE_PROTOCOL_ENTRY(ICE_PFCP, 8, 10, 12, 14, 16, 18, 20, 22),
 	ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6),
 	ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10),
 	ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0),
@@ -4561,6 +4726,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = {
 	{ ICE_NVGRE,		ICE_GRE_OF_HW },
 	{ ICE_GTP,		ICE_UDP_OF_HW },
 	{ ICE_GTP_NO_PAY,	ICE_UDP_ILOS_HW },
+	{ ICE_PFCP,		ICE_UDP_ILOS_HW },
 	{ ICE_PPPOE,		ICE_PPPOE_HW },
 	{ ICE_L2TPV3,		ICE_L2TPV3_HW },
 	{ ICE_VLAN_EX,          ICE_VLAN_OF_HW },
@@ -4573,12 +4739,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = {
  * @hw: pointer to the hardware structure
  * @lkup_exts: extension sequence to match
  * @rinfo: information regarding the rule e.g. priority and action info
+ * @is_add: flag of adding recipe
  *
  * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found.
  */
 static u16
 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
-	      const struct ice_adv_rule_info *rinfo)
+	      const struct ice_adv_rule_info *rinfo, bool is_add)
 {
 	bool refresh_required = true;
 	struct ice_sw_recipe *recp;
@@ -4592,11 +4759,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
 		 * entry update it in our SW bookkeeping and continue with the
 		 * matching.
 		 */
-		if (!recp[i].recp_created)
+		if (hw->recp_reuse) {
 			if (ice_get_recp_frm_fw(hw,
 						hw->switch_info->recp_list, i,
-						&refresh_required))
+						&refresh_required, is_add))
 				continue;
+		}
 
 		/* Skip inverse action recipes */
 		if (recp[i].root_buf && recp[i].root_buf->content.act_ctrl &
@@ -5268,6 +5436,9 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo,
 	case ICE_SW_TUN_GTPC:
 		prof_type = ICE_PROF_TUN_GTPC;
 		break;
+	case ICE_SW_TUN_PFCP:
+		prof_type = ICE_PROF_TUN_PFCP;
+		break;
 	case ICE_SW_TUN_AND_NON_TUN:
 	default:
 		prof_type = ICE_PROF_ALL;
@@ -5278,6 +5449,49 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo,
 }
 
 /**
+ * ice_subscribe_recipe - subscribe to an existing recipe
+ * @hw: pointer to the hardware structure
+ * @rid: recipe ID to subscribe to
+ *
+ * Return: 0 on success, and others on error
+ */
+static int ice_subscribe_recipe(struct ice_hw *hw, u16 rid)
+{
+	DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1);
+	u16 buf_len = __struct_size(sw_buf);
+	u16 res_type;
+	int status;
+
+	/* Prepare buffer to allocate resource */
+	sw_buf->num_elems = cpu_to_le16(1);
+	res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, ICE_AQC_RES_TYPE_RECIPE) |
+		   ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_SHARED |
+		   ICE_AQC_RES_TYPE_FLAG_SUBSCRIBE_CTL;
+	sw_buf->res_type = cpu_to_le16(res_type);
+
+	sw_buf->elem[0].e.sw_resp = cpu_to_le16(rid);
+
+	status = ice_aq_alloc_free_res(hw, sw_buf, buf_len,
+				       ice_aqc_opc_alloc_res);
+
+	return status;
+}
+
+/**
+ * ice_subscribable_recp_shared - share an existing subscribable recipe
+ * @hw: pointer to the hardware structure
+ * @rid: recipe ID to subscribe to
+ */
+static void ice_subscribable_recp_shared(struct ice_hw *hw, u16 rid)
+{
+	struct ice_sw_recipe *recps = hw->switch_info->recp_list;
+	u16 sub_rid;
+
+	for_each_set_bit(sub_rid, recps[rid].r_bitmap, ICE_MAX_NUM_RECIPES)
+		ice_subscribe_recipe(hw, sub_rid);
+}
+
+/**
  * ice_add_adv_recipe - Add an advanced recipe that is not part of the default
  * @hw: pointer to hardware structure
  * @lkups: lookup elements or match criteria for the advanced recipe, one
@@ -5299,6 +5513,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	struct ice_sw_fv_list_entry *tmp;
 	struct ice_sw_recipe *rm;
 	int status = 0;
+	u16 rid_tmp;
 	u8 i;
 
 	if (!lkups_cnt)
@@ -5376,10 +5591,14 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	}
 
 	/* Look for a recipe which matches our requested fv / mask list */
-	*rid = ice_find_recp(hw, lkup_exts, rinfo);
-	if (*rid < ICE_MAX_NUM_RECIPES)
+	*rid = ice_find_recp(hw, lkup_exts, rinfo, true);
+	if (*rid < ICE_MAX_NUM_RECIPES) {
 		/* Success if found a recipe that match the existing criteria */
+		if (hw->recp_reuse)
+			ice_subscribable_recp_shared(hw, *rid);
+
 		goto err_unroll;
+	}
 
 	rm->tun_type = rinfo->tun_type;
 	/* Recipe we need does not exist, add a recipe */
@@ -5398,14 +5617,14 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 		status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id,
 						      &recp_assoc, NULL);
 		if (status)
-			goto err_unroll;
+			goto err_free_recipe;
 
 		bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES);
 		bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap,
 			  ICE_MAX_NUM_RECIPES);
 		status = ice_acquire_change_lock(hw, ICE_RES_WRITE);
 		if (status)
-			goto err_unroll;
+			goto err_free_recipe;
 
 		bitmap_to_arr64(&recp_assoc, r_bitmap, ICE_MAX_NUM_RECIPES);
 		status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id,
@@ -5413,7 +5632,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 		ice_release_change_lock(hw);
 
 		if (status)
-			goto err_unroll;
+			goto err_free_recipe;
 
 		/* Update profile to recipe bitmap array */
 		bitmap_copy(profile_to_recipe[fvit->profile_id], r_bitmap,
@@ -5427,6 +5646,16 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	*rid = rm->root_rid;
 	memcpy(&hw->switch_info->recp_list[*rid].lkup_exts, lkup_exts,
 	       sizeof(*lkup_exts));
+	goto err_unroll;
+
+err_free_recipe:
+	if (hw->recp_reuse) {
+		for_each_set_bit(rid_tmp, rm->r_bitmap, ICE_MAX_NUM_RECIPES) {
+			if (!ice_free_recipe_res(hw, rid_tmp))
+				clear_bit(rid_tmp, rm->r_bitmap);
+		}
+	}
+
 err_unroll:
 	list_for_each_entry_safe(r_entry, r_tmp, &rm->rg_list, l_entry) {
 		list_del(&r_entry->l_entry);
@@ -5552,6 +5781,9 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt,
 	case ICE_SW_TUN_VXLAN:
 		match |= ICE_PKT_TUN_UDP;
 		break;
+	case ICE_SW_TUN_PFCP:
+		match |= ICE_PKT_PFCP;
+		break;
 	default:
 		break;
 	}
@@ -5692,6 +5924,9 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt,
 		case ICE_GTP:
 			len = sizeof(struct ice_udp_gtp_hdr);
 			break;
+		case ICE_PFCP:
+			len = sizeof(struct ice_pfcp_hdr);
+			break;
 		case ICE_PPPOE:
 			len = sizeof(struct ice_pppoe_hdr);
 			break;
@@ -6440,7 +6675,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 			return -EIO;
 	}
 
-	rid = ice_find_recp(hw, &lkup_exts, rinfo);
+	rid = ice_find_recp(hw, &lkup_exts, rinfo, false);
 	/* If did not find a recipe that match the existing criteria */
 	if (rid == ICE_MAX_NUM_RECIPES)
 		return -EINVAL;
@@ -6484,14 +6719,21 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 					 ice_aqc_opc_remove_sw_rules, NULL);
 		if (!status || status == -ENOENT) {
 			struct ice_switch_info *sw = hw->switch_info;
+			struct ice_sw_recipe *r_list = sw->recp_list;
 
 			mutex_lock(rule_lock);
 			list_del(&list_elem->list_entry);
 			devm_kfree(ice_hw_to_dev(hw), list_elem->lkups);
 			devm_kfree(ice_hw_to_dev(hw), list_elem);
 			mutex_unlock(rule_lock);
-			if (list_empty(&sw->recp_list[rid].filt_rules))
-				sw->recp_list[rid].adv_rule = false;
+			if (list_empty(&r_list[rid].filt_rules)) {
+				r_list[rid].adv_rule = false;
+
+				/* All rules for this recipe are now removed */
+				if (hw->recp_reuse)
+					ice_release_recipe_res(hw,
+							       &r_list[rid]);
+			}
 		}
 		kfree(s_rule);
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 89ffa1b51b5a..ad98e98c812d 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -8,8 +8,9 @@
 
 #define ICE_SW_CFG_MAX_BUF_LEN 2048
 #define ICE_DFLT_VSI_INVAL 0xff
-#define ICE_FLTR_RX BIT(0)
-#define ICE_FLTR_TX BIT(1)
+#define ICE_FLTR_RX		BIT(0)
+#define ICE_FLTR_TX		BIT(1)
+#define ICE_FLTR_TX_ONLY	BIT(2)
 #define ICE_VSI_INVAL_ID 0xffff
 #define ICE_INVAL_Q_HANDLE 0xFFFF
 
@@ -21,6 +22,8 @@
 #define ICE_PROFID_IPV6_GTPC_NO_TEID			45
 #define ICE_PROFID_IPV6_GTPU_TEID			46
 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER		70
+#define ICE_PROFID_IPV4_PFCP_NODE			79
+#define ICE_PROFID_IPV6_PFCP_SESSION			82
 
 #define ICE_SW_RULE_VSI_LIST_SIZE(s, n)		struct_size((s), vsi, (n))
 #define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l)	struct_size((s), hdr_data, (l))
@@ -429,5 +432,6 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
 int
 ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
 			     struct ice_sq_cd *cd);
+void ice_init_chk_recipe_reuse_support(struct ice_hw *hw);
 
 #endif /* _ICE_SWITCH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 688ccb0615ab..8bd24b33f3a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -37,7 +37,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers,
 	if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC)
 		lkups_cnt++;
 
-	if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS)
+	if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS)
+		lkups_cnt++;
+
+	if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS)
 		lkups_cnt++;
 
 	if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 |
@@ -140,6 +143,8 @@ ice_proto_type_from_tunnel(enum ice_tunnel_type type)
 		return ICE_GTP;
 	case TNL_GTPC:
 		return ICE_GTP_NO_PAY;
+	case TNL_PFCP:
+		return ICE_PFCP;
 	default:
 		return 0;
 	}
@@ -159,6 +164,8 @@ ice_sw_type_from_tunnel(enum ice_tunnel_type type)
 		return ICE_SW_TUN_GTPU;
 	case TNL_GTPC:
 		return ICE_SW_TUN_GTPC;
+	case TNL_PFCP:
+		return ICE_SW_TUN_PFCP;
 	default:
 		return ICE_NON_TUN;
 	}
@@ -221,8 +228,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr,
 		i++;
 	}
 
-	if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS &&
-	    (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) {
+	if (flags & ICE_TC_FLWR_FIELD_GTP_OPTS) {
 		list[i].type = ice_proto_type_from_tunnel(fltr->tunnel_type);
 
 		if (fltr->gtp_pdu_info_masks.pdu_type) {
@@ -239,6 +245,22 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr,
 		i++;
 	}
 
+	if (flags & ICE_TC_FLWR_FIELD_PFCP_OPTS) {
+		struct ice_pfcp_hdr *hdr_h, *hdr_m;
+
+		hdr_h = &list[i].h_u.pfcp_hdr;
+		hdr_m = &list[i].m_u.pfcp_hdr;
+		list[i].type = ICE_PFCP;
+
+		hdr_h->flags = fltr->pfcp_meta_keys.type;
+		hdr_m->flags = fltr->pfcp_meta_masks.type & 0x01;
+
+		hdr_h->seid = fltr->pfcp_meta_keys.seid;
+		hdr_m->seid = fltr->pfcp_meta_masks.seid;
+
+		i++;
+	}
+
 	if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 |
 		     ICE_TC_FLWR_FIELD_ENC_DEST_IPV4)) {
 		list[i].type = ice_proto_type_from_ipv4(false);
@@ -374,8 +396,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
 	if (tc_fltr->tunnel_type != TNL_LAST) {
 		i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i);
 
-		headers = &tc_fltr->inner_headers;
-		inner = true;
+		/* PFCP is considered non-tunneled - don't swap headers. */
+		if (tc_fltr->tunnel_type != TNL_PFCP) {
+			headers = &tc_fltr->inner_headers;
+			inner = true;
+		}
 	}
 
 	if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) {
@@ -629,6 +654,8 @@ static int ice_tc_tun_get_type(struct net_device *tunnel_dev)
 	 */
 	if (netif_is_gtp(tunnel_dev))
 		return TNL_GTPU;
+	if (netif_is_pfcp(tunnel_dev))
+		return TNL_PFCP;
 	return TNL_LAST;
 }
 
@@ -642,13 +669,19 @@ static bool ice_tc_is_dev_uplink(struct net_device *dev)
 	return netif_is_ice(dev) || ice_is_tunnel_supported(dev);
 }
 
-static int ice_tc_setup_redirect_action(struct net_device *filter_dev,
-					struct ice_tc_flower_fltr *fltr,
-					struct net_device *target_dev)
+static int ice_tc_setup_action(struct net_device *filter_dev,
+			       struct ice_tc_flower_fltr *fltr,
+			       struct net_device *target_dev,
+			       enum ice_sw_fwd_act_type action)
 {
 	struct ice_repr *repr;
 
-	fltr->action.fltr_act = ICE_FWD_TO_VSI;
+	if (action != ICE_FWD_TO_VSI && action != ICE_MIRROR_PACKET) {
+		NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action to setup provided");
+		return -EINVAL;
+	}
+
+	fltr->action.fltr_act = action;
 
 	if (ice_is_port_repr_netdev(filter_dev) &&
 	    ice_is_port_repr_netdev(target_dev)) {
@@ -696,41 +729,6 @@ ice_tc_setup_drop_action(struct net_device *filter_dev,
 	return 0;
 }
 
-static int ice_tc_setup_mirror_action(struct net_device *filter_dev,
-				      struct ice_tc_flower_fltr *fltr,
-				      struct net_device *target_dev)
-{
-	struct ice_repr *repr;
-
-	fltr->action.fltr_act = ICE_MIRROR_PACKET;
-
-	if (ice_is_port_repr_netdev(filter_dev) &&
-	    ice_is_port_repr_netdev(target_dev)) {
-		repr = ice_netdev_to_repr(target_dev);
-
-		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-	} else if (ice_is_port_repr_netdev(filter_dev) &&
-		   ice_tc_is_dev_uplink(target_dev)) {
-		repr = ice_netdev_to_repr(filter_dev);
-
-		fltr->dest_vsi = repr->src_vsi->back->eswitch.uplink_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-	} else if (ice_tc_is_dev_uplink(filter_dev) &&
-		   ice_is_port_repr_netdev(target_dev)) {
-		repr = ice_netdev_to_repr(target_dev);
-
-		fltr->dest_vsi = repr->src_vsi;
-		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-	} else {
-		NL_SET_ERR_MSG_MOD(fltr->extack,
-				   "Unsupported netdevice in switchdev mode");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 				       struct ice_tc_flower_fltr *fltr,
 				       struct flow_action_entry *act)
@@ -746,16 +744,19 @@ static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
 		break;
 
 	case FLOW_ACTION_REDIRECT:
-		err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev);
+		err = ice_tc_setup_action(filter_dev, fltr,
+					  act->dev, ICE_FWD_TO_VSI);
 		if (err)
 			return err;
 
 		break;
 
 	case FLOW_ACTION_MIRRED:
-		err = ice_tc_setup_mirror_action(filter_dev, fltr, act->dev);
+		err = ice_tc_setup_action(filter_dev, fltr,
+					  act->dev, ICE_MIRROR_PACKET);
 		if (err)
 			return err;
+
 		break;
 
 	default:
@@ -1409,7 +1410,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
 		}
 	}
 
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) &&
+	    (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) {
 		struct flow_match_enc_opts match;
 
 		flow_rule_match_enc_opts(rule, &match);
@@ -1420,7 +1422,21 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
 		memcpy(&fltr->gtp_pdu_info_masks, &match.mask->data[0],
 		       sizeof(struct gtp_pdu_session_info));
 
-		fltr->flags |= ICE_TC_FLWR_FIELD_ENC_OPTS;
+		fltr->flags |= ICE_TC_FLWR_FIELD_GTP_OPTS;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS) &&
+	    fltr->tunnel_type == TNL_PFCP) {
+		struct flow_match_enc_opts match;
+
+		flow_rule_match_enc_opts(rule, &match);
+
+		memcpy(&fltr->pfcp_meta_keys, match.key->data,
+		       sizeof(struct pfcp_metadata));
+		memcpy(&fltr->pfcp_meta_masks, match.mask->data,
+		       sizeof(struct pfcp_metadata));
+
+		fltr->flags |= ICE_TC_FLWR_FIELD_PFCP_OPTS;
 	}
 
 	return 0;
@@ -1481,10 +1497,14 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 			return err;
 		}
 
-		/* header pointers should point to the inner headers, outer
-		 * header were already set by ice_parse_tunnel_attr
-		 */
-		headers = &fltr->inner_headers;
+		/* PFCP is considered non-tunneled - don't swap headers. */
+		if (fltr->tunnel_type != TNL_PFCP) {
+			/* Header pointers should point to the inner headers,
+			 * outer header were already set by
+			 * ice_parse_tunnel_attr().
+			 */
+			headers = &fltr->inner_headers;
+		}
 	} else if (dissector->used_keys &
 		  (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
 		   BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
@@ -1638,6 +1658,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
 		flow_rule_match_control(rule, &match);
 
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						fltr->extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index 65d387163a46..d84f153517ec 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -4,6 +4,9 @@
 #ifndef _ICE_TC_LIB_H_
 #define _ICE_TC_LIB_H_
 
+#include <linux/bits.h>
+#include <net/pfcp.h>
+
 #define ICE_TC_FLWR_FIELD_DST_MAC		BIT(0)
 #define ICE_TC_FLWR_FIELD_SRC_MAC		BIT(1)
 #define ICE_TC_FLWR_FIELD_VLAN			BIT(2)
@@ -22,7 +25,7 @@
 #define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT	BIT(15)
 #define ICE_TC_FLWR_FIELD_ENC_DST_MAC		BIT(16)
 #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID		BIT(17)
-#define ICE_TC_FLWR_FIELD_ENC_OPTS		BIT(18)
+#define ICE_TC_FLWR_FIELD_GTP_OPTS		BIT(18)
 #define ICE_TC_FLWR_FIELD_CVLAN			BIT(19)
 #define ICE_TC_FLWR_FIELD_PPPOE_SESSID		BIT(20)
 #define ICE_TC_FLWR_FIELD_PPP_PROTO		BIT(21)
@@ -34,6 +37,7 @@
 #define ICE_TC_FLWR_FIELD_VLAN_PRIO		BIT(27)
 #define ICE_TC_FLWR_FIELD_CVLAN_PRIO		BIT(28)
 #define ICE_TC_FLWR_FIELD_VLAN_TPID		BIT(29)
+#define ICE_TC_FLWR_FIELD_PFCP_OPTS		BIT(30)
 
 #define ICE_TC_FLOWER_MASK_32   0xFFFFFFFF
 
@@ -161,6 +165,8 @@ struct ice_tc_flower_fltr {
 	__be32 tenant_id;
 	struct gtp_pdu_session_info gtp_pdu_info_keys;
 	struct gtp_pdu_session_info gtp_pdu_info_masks;
+	struct pfcp_metadata pfcp_meta_keys;
+	struct pfcp_metadata pfcp_meta_masks;
 	u32 flags;
 	u8 tunnel_type;
 	struct ice_tc_flower_action	action;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 97d41d6ebf1f..8bb743f78fcb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1051,8 +1051,7 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 	}
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index af955b0e5dc5..feba314a3fe4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -365,6 +365,7 @@ struct ice_rx_ring {
 	u8 ptp_rx;
 #define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 #define ICE_RX_FLAGS_CRC_STRIP_DIS	BIT(2)
+#define ICE_RX_FLAGS_MULTIDEV		BIT(3)
 	u8 flags;
 	/* CL5 - 5th cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index f8f1d2bdc1be..2719f0e20933 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/filter.h>
+#include <linux/net/intel/libie/rx.h>
 
 #include "ice_txrx_lib.h"
 #include "ice_eswitch.h"
@@ -39,30 +40,6 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val)
 }
 
 /**
- * ice_ptype_to_htype - get a hash type
- * @ptype: the ptype value from the descriptor
- *
- * Returns appropriate hash type (such as PKT_HASH_TYPE_L2/L3/L4) to be used by
- * skb_set_hash based on PTYPE as parsed by HW Rx pipeline and is part of
- * Rx desc.
- */
-static enum pkt_hash_types ice_ptype_to_htype(u16 ptype)
-{
-	struct ice_rx_ptype_decoded decoded = ice_decode_rx_desc_ptype(ptype);
-
-	if (!decoded.known)
-		return PKT_HASH_TYPE_NONE;
-	if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4)
-		return PKT_HASH_TYPE_L4;
-	if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3)
-		return PKT_HASH_TYPE_L3;
-	if (decoded.outer_ip == ICE_RX_PTYPE_OUTER_L2)
-		return PKT_HASH_TYPE_L2;
-
-	return PKT_HASH_TYPE_NONE;
-}
-
-/**
  * ice_get_rx_hash - get RX hash value from descriptor
  * @rx_desc: specific descriptor
  *
@@ -91,14 +68,16 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 		   const union ice_32b_rx_flex_desc *rx_desc,
 		   struct sk_buff *skb, u16 rx_ptype)
 {
+	struct libeth_rx_pt decoded;
 	u32 hash;
 
-	if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
+	decoded = libie_rx_pt_parse(rx_ptype);
+	if (!libeth_rx_pt_has_hash(rx_ring->netdev, decoded))
 		return;
 
 	hash = ice_get_rx_hash(rx_desc);
 	if (likely(hash))
-		skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
+		libeth_rx_pt_set_hash(skb, hash, decoded);
 }
 
 /**
@@ -114,34 +93,26 @@ static void
 ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
 {
-	struct ice_rx_ptype_decoded decoded;
+	struct libeth_rx_pt decoded;
 	u16 rx_status0, rx_status1;
 	bool ipv4, ipv6;
 
-	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
-	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
-
-	decoded = ice_decode_rx_desc_ptype(ptype);
-
 	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
 	skb->ip_summed = CHECKSUM_NONE;
-	skb_checksum_none_assert(skb);
 
-	/* check if Rx checksum is enabled */
-	if (!(ring->netdev->features & NETIF_F_RXCSUM))
+	decoded = libie_rx_pt_parse(ptype);
+	if (!libeth_rx_pt_has_checksum(ring->netdev, decoded))
 		return;
 
+	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
+	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
+
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
 		return;
 
-	if (!(decoded.known && decoded.outer_ip))
-		return;
-
-	ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4);
-	ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6);
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
 
 	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) {
 		ring->vsi->back->hw_rx_eipe_error++;
@@ -169,19 +140,10 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	 * we need to bump the checksum level by 1 to reflect the fact that
 	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.tunnel_type >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT)
+	if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT)
 		skb->csum_level = 1;
 
-	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
-	switch (decoded.inner_prot) {
-	case ICE_RX_PTYPE_INNER_PROT_TCP:
-	case ICE_RX_PTYPE_INNER_PROT_UDP:
-	case ICE_RX_PTYPE_INNER_PROT_SCTP:
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		break;
-	default:
-		break;
-	}
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	return;
 
 checksum_fail:
@@ -236,7 +198,16 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
 
 	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+	if (unlikely(rx_ring->flags & ICE_RX_FLAGS_MULTIDEV)) {
+		struct net_device *netdev = ice_eswitch_get_target(rx_ring,
+								   rx_desc);
+
+		if (ice_is_port_repr_netdev(netdev))
+			ice_repr_inc_rx_stats(netdev, skb->len);
+		skb->protocol = eth_type_trans(skb, netdev);
+	} else {
+		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+	}
 
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 
@@ -527,42 +498,6 @@ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
 	return 0;
 }
 
-/* Define a ptype index -> XDP hash type lookup table.
- * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
- * avoiding possible copy-paste errors.
- */
-#undef ICE_PTT
-#undef ICE_PTT_UNUSED_ENTRY
-
-#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
-
-#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
-
-/* A few supplementary definitions for when XDP hash types do not coincide
- * with what can be generated from ptype definitions
- * by means of preprocessor concatenation.
- */
-#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
-#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
-#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
-#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
-#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
-
-static const enum xdp_rss_hash_type
-ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
-	ICE_PTYPES
-};
-
-#undef XDP_RSS_L3_NONE
-#undef XDP_RSS_L4_NONE
-#undef XDP_RSS_TYPE_PAY2
-#undef XDP_RSS_TYPE_PAY3
-#undef XDP_RSS_TYPE_PAY4
-
-#undef ICE_PTT
-#undef ICE_PTT_UNUSED_ENTRY
-
 /**
  * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
  * @eop_desc: End of Packet descriptor
@@ -570,12 +505,7 @@ ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
 static enum xdp_rss_hash_type
 ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
 {
-	u16 ptype = ice_get_ptype(eop_desc);
-
-	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
-		return 0;
-
-	return ice_ptype_to_xdp_hash[ptype];
+	return libie_rx_pt_parse(ice_get_ptype(eop_desc)).hash_type;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 9ff92dba5823..f0796a93f428 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -150,7 +150,6 @@ enum ice_vsi_type {
 	ICE_VSI_CTRL = 3,	/* equates to ICE_VSI_PF with 1 queue pair */
 	ICE_VSI_CHNL = 4,
 	ICE_VSI_LB = 6,
-	ICE_VSI_SWITCHDEV_CTRL = 7,
 };
 
 struct ice_link_status {
@@ -204,6 +203,7 @@ struct ice_phy_info {
 enum ice_fltr_ptype {
 	/* NONE - used for undef/error */
 	ICE_FLTR_PTYPE_NONF_NONE = 0,
+	ICE_FLTR_PTYPE_NONF_ETH,
 	ICE_FLTR_PTYPE_NONF_IPV4_UDP,
 	ICE_FLTR_PTYPE_NONF_IPV4_TCP,
 	ICE_FLTR_PTYPE_NONF_IPV4_SCTP,
@@ -296,6 +296,7 @@ struct ice_hw_common_caps {
 	bool pcie_reset_avoidance;
 	/* Post update reset restriction */
 	bool reset_restrict_support;
+	bool tx_sched_topo_comp_mode_en;
 };
 
 /* IEEE 1588 TIME_SYNC specific info */
@@ -849,6 +850,8 @@ struct ice_hw {
 
 	u16 max_burst_size;	/* driver sets this value */
 
+	u8 recp_reuse:1;	/* indicates whether FW supports recipe reuse */
+
 	/* Tx Scheduler values */
 	u8 num_tx_sched_layers;
 	u8 num_tx_sched_phys_layers;
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index d10a4be965b5..48a8d462d76a 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -259,20 +259,18 @@ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf)
 int ice_vf_reconfig_vsi(struct ice_vf *vf)
 {
 	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
-	struct ice_vsi_cfg_params params = {};
 	struct ice_pf *pf = vf->pf;
 	int err;
 
 	if (WARN_ON(!vsi))
 		return -EINVAL;
 
-	params = ice_vsi_to_params(vsi);
-	params.flags = ICE_VSI_FLAG_NO_INIT;
+	vsi->flags = ICE_VSI_FLAG_NO_INIT;
 
 	ice_vsi_decfg(vsi);
 	ice_fltr_remove_all(vsi);
 
-	err = ice_vsi_cfg(vsi, &params);
+	err = ice_vsi_cfg(vsi);
 	if (err) {
 		dev_err(ice_pf_to_dev(pf),
 			"Failed to reconfigure the VF%u's VSI, error %d\n",
@@ -992,10 +990,13 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 
 	/* assign default capabilities */
 	vf->spoofchk = true;
-	vf->num_vf_qs = vfs->num_qps_per;
 	ice_vc_set_default_allowlist(vf);
 	ice_virtchnl_set_dflt_ops(vf);
 
+	/* set default number of MSI-X */
+	vf->num_msix = vfs->num_msix_per;
+	vf->num_vf_qs = vfs->num_qps_per;
+
 	/* ctrl_vsi_idx will be set to a valid value only when iAVF
 	 * creates its first fdir rule.
 	 */
@@ -1240,7 +1241,7 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 
 	params.type = ICE_VSI_CTRL;
-	params.pi = ice_vf_get_port_info(vf);
+	params.port_info = ice_vf_get_port_info(vf);
 	params.vf = vf;
 	params.flags = ICE_VSI_FLAG_INIT;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 1ff9818b4c84..1c6ce0c4ed4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -1505,13 +1505,12 @@ error_param:
  * ice_cfg_interrupt
  * @vf: pointer to the VF info
  * @vsi: the VSI being configured
- * @vector_id: vector ID
  * @map: vector map for mapping vectors to queues
  * @q_vector: structure for interrupt vector
  * configure the IRQ to queue map
  */
-static int
-ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id,
+static enum virtchnl_status_code
+ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi,
 		  struct virtchnl_vector_map *map,
 		  struct ice_q_vector *q_vector)
 {
@@ -1531,7 +1530,8 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id,
 		q_vector->num_ring_rx++;
 		q_vector->rx.itr_idx = map->rxitr_idx;
 		vsi->rx_rings[vsi_q_id]->q_vector = q_vector;
-		ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id,
+		ice_cfg_rxq_interrupt(vsi, vsi_q_id,
+				      q_vector->vf_reg_idx,
 				      q_vector->rx.itr_idx);
 	}
 
@@ -1545,7 +1545,8 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id,
 		q_vector->num_ring_tx++;
 		q_vector->tx.itr_idx = map->txitr_idx;
 		vsi->tx_rings[vsi_q_id]->q_vector = q_vector;
-		ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id,
+		ice_cfg_txq_interrupt(vsi, vsi_q_id,
+				      q_vector->vf_reg_idx,
 				      q_vector->tx.itr_idx);
 	}
 
@@ -1619,8 +1620,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 		}
 
 		/* lookout for the invalid queue index */
-		v_ret = (enum virtchnl_status_code)
-			ice_cfg_interrupt(vf, vsi, vector_id, map, q_vector);
+		v_ret = ice_cfg_interrupt(vf, vsi, map, q_vector);
 		if (v_ret)
 			goto error_param;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
index 4a6c850d83ac..7aae7fdcfcdb 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
@@ -72,7 +72,6 @@ void ice_vsi_init_vlan_ops(struct ice_vsi *vsi)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-	case ICE_VSI_SWITCHDEV_CTRL:
 		ice_pf_vsi_init_vlan_ops(vsi);
 		break;
 	case ICE_VSI_VF:
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 1857220d27fe..aa81d1162b81 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -555,8 +555,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 	}
 	net_prefetch(xdp->data_meta);
 
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 5d3532c27d57..52ceda6306a3 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -2234,7 +2234,7 @@ static int idpf_change_mtu(struct net_device *netdev, int new_mtu)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	err = idpf_initiate_soft_reset(vport, IDPF_SR_MTU_CHANGE);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index f5bc4a278074..285da2177ee4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3005,8 +3005,7 @@ struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq,
 	/* prefetch first cache line of first page */
 	net_prefetch(va);
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rxq->q_vector->napi, IDPF_RX_HDR_SIZE,
-			       GFP_ATOMIC);
+	skb = napi_alloc_skb(&rxq->q_vector->napi, IDPF_RX_HDR_SIZE);
 	if (unlikely(!skb)) {
 		idpf_rx_put_page(rx_buf);
 
@@ -3060,7 +3059,7 @@ static struct sk_buff *idpf_rx_hdr_construct_skb(struct idpf_queue *rxq,
 	struct sk_buff *skb;
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rxq->q_vector->napi, size, GFP_ATOMIC);
+	skb = napi_alloc_skb(&rxq->q_vector->napi, size);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index df76493faa75..3d046b81e507 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -8,6 +8,8 @@
 #include <net/tcp.h>
 #include <net/netdev_queues.h>
 
+#include "virtchnl2_lan_desc.h"
+
 #define IDPF_LARGE_MAX_Q			256
 #define IDPF_MAX_Q				16
 #define IDPF_MIN_Q				2
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 4a3c4454d25a..63deb120359c 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -4,6 +4,8 @@
 #ifndef _VIRTCHNL2_H_
 #define _VIRTCHNL2_H_
 
+#include <linux/if_ether.h>
+
 /* All opcodes associated with virtchnl2 are prefixed with virtchnl2 or
  * VIRTCHNL2. Any future opcodes, offloads/capabilities, structures,
  * and defines must be prefixed with virtchnl2 or VIRTCHNL2 to avoid confusion.
@@ -17,8 +19,6 @@
  * must remain unchanged over time, so we specify explicit values for all enums.
  */
 
-#include "virtchnl2_lan_desc.h"
-
 /* This macro is used to generate compilation errors if a structure
  * is not exactly the correct length.
  */
@@ -555,7 +555,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_queue_reg_chunk);
 struct virtchnl2_queue_reg_chunks {
 	__le16 num_chunks;
 	u8 pad[6];
-	struct virtchnl2_queue_reg_chunk chunks[];
+	struct virtchnl2_queue_reg_chunk chunks[] __counted_by_le(num_chunks);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 
@@ -703,7 +703,7 @@ struct virtchnl2_config_tx_queues {
 	__le32 vport_id;
 	__le16 num_qinfo;
 	u8 pad[10];
-	struct virtchnl2_txq_info qinfo[];
+	struct virtchnl2_txq_info qinfo[] __counted_by_le(num_qinfo);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_config_tx_queues);
 
@@ -782,7 +782,7 @@ struct virtchnl2_config_rx_queues {
 	__le32 vport_id;
 	__le16 num_qinfo;
 	u8 pad[18];
-	struct virtchnl2_rxq_info qinfo[];
+	struct virtchnl2_rxq_info qinfo[] __counted_by_le(num_qinfo);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_config_rx_queues);
 
@@ -868,7 +868,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(32, virtchnl2_vector_chunk);
 struct virtchnl2_vector_chunks {
 	__le16 num_vchunks;
 	u8 pad[14];
-	struct virtchnl2_vector_chunk vchunks[];
+	struct virtchnl2_vector_chunk vchunks[] __counted_by_le(num_vchunks);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_vector_chunks);
 
@@ -912,7 +912,7 @@ struct virtchnl2_rss_lut {
 	__le16 lut_entries_start;
 	__le16 lut_entries;
 	u8 pad[4];
-	__le32 lut[];
+	__le32 lut[] __counted_by_le(lut_entries);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(12, virtchnl2_rss_lut);
 
@@ -977,7 +977,7 @@ struct virtchnl2_ptype {
 	u8 ptype_id_8;
 	u8 proto_id_count;
 	__le16 pad;
-	__le16 proto_id[];
+	__le16 proto_id[] __counted_by(proto_id_count);
 } __packed __aligned(2);
 VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
 
@@ -1104,7 +1104,7 @@ struct virtchnl2_rss_key {
 	__le32 vport_id;
 	__le16 key_len;
 	u8 pad;
-	u8 key_flex[];
+	u8 key_flex[] __counted_by_le(key_len);
 } __packed;
 VIRTCHNL2_CHECK_STRUCT_LEN(7, virtchnl2_rss_key);
 
@@ -1131,7 +1131,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_chunk);
 struct virtchnl2_queue_chunks {
 	__le16 num_chunks;
 	u8 pad[6];
-	struct virtchnl2_queue_chunk chunks[];
+	struct virtchnl2_queue_chunk chunks[] __counted_by_le(num_chunks);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_chunks);
 
@@ -1195,7 +1195,7 @@ struct virtchnl2_queue_vector_maps {
 	__le32 vport_id;
 	__le16 num_qv_maps;
 	u8 pad[10];
-	struct virtchnl2_queue_vector qv_maps[];
+	struct virtchnl2_queue_vector qv_maps[] __counted_by_le(num_qv_maps);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_queue_vector_maps);
 
@@ -1247,7 +1247,7 @@ struct virtchnl2_mac_addr_list {
 	__le32 vport_id;
 	__le16 num_mac_addr;
 	u8 pad[2];
-	struct virtchnl2_mac_addr mac_addr_list[];
+	struct virtchnl2_mac_addr mac_addr_list[] __counted_by_le(num_mac_addr);
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_mac_addr_list);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 99977a22b843..61d72250c0ed 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -3272,19 +3272,6 @@ static int igb_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
-static int igb_ethtool_begin(struct net_device *netdev)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	pm_runtime_get_sync(&adapter->pdev->dev);
-	return 0;
-}
-
-static void igb_ethtool_complete(struct net_device *netdev)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	pm_runtime_put(&adapter->pdev->dev);
-}
-
 static u32 igb_get_rxfh_indir_size(struct net_device *netdev)
 {
 	return IGB_RETA_SIZE;
@@ -3508,8 +3495,6 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.set_channels		= igb_set_channels,
 	.get_priv_flags		= igb_get_priv_flags,
 	.set_priv_flags		= igb_set_priv_flags,
-	.begin			= igb_ethtool_begin,
-	.complete		= igb_ethtool_complete,
 	.get_link_ksettings	= igb_get_link_ksettings,
 	.set_link_ksettings	= igb_set_link_ksettings,
 };
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a3f100769e39..fce2930ae6af 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -106,8 +106,6 @@ static int igb_setup_all_rx_resources(struct igb_adapter *);
 static void igb_free_all_tx_resources(struct igb_adapter *);
 static void igb_free_all_rx_resources(struct igb_adapter *);
 static void igb_setup_mrqc(struct igb_adapter *);
-static int igb_probe(struct pci_dev *, const struct pci_device_id *);
-static void igb_remove(struct pci_dev *pdev);
 static void igb_init_queue_configuration(struct igb_adapter *adapter);
 static int igb_sw_init(struct igb_adapter *);
 int igb_open(struct net_device *);
@@ -178,20 +176,6 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf);
 static int igb_disable_sriov(struct pci_dev *dev, bool reinit);
 #endif
 
-static int igb_suspend(struct device *);
-static int igb_resume(struct device *);
-static int igb_runtime_suspend(struct device *dev);
-static int igb_runtime_resume(struct device *dev);
-static int igb_runtime_idle(struct device *dev);
-#ifdef CONFIG_PM
-static const struct dev_pm_ops igb_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(igb_suspend, igb_resume)
-	SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume,
-			igb_runtime_idle)
-};
-#endif
-static void igb_shutdown(struct pci_dev *);
-static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
 #ifdef CONFIG_IGB_DCA
 static int igb_notify_dca(struct notifier_block *, unsigned long, void *);
 static struct notifier_block dca_notifier = {
@@ -219,19 +203,6 @@ static const struct pci_error_handlers igb_err_handler = {
 
 static void igb_init_dmac(struct igb_adapter *adapter, u32 pba);
 
-static struct pci_driver igb_driver = {
-	.name     = igb_driver_name,
-	.id_table = igb_pci_tbl,
-	.probe    = igb_probe,
-	.remove   = igb_remove,
-#ifdef CONFIG_PM
-	.driver.pm = &igb_pm_ops,
-#endif
-	.shutdown = igb_shutdown,
-	.sriov_configure = igb_pci_sriov_configure,
-	.err_handler = &igb_err_handler
-};
-
 MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
 MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver");
 MODULE_LICENSE("GPL v2");
@@ -647,6 +618,8 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw)
 	return adapter->netdev;
 }
 
+static struct pci_driver igb_driver;
+
 /**
  *  igb_init_module - Driver Registration Routine
  *
@@ -2624,6 +2597,9 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct flow_match_eth_addrs match;
 
@@ -6668,7 +6644,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		igb_up(adapter);
@@ -9453,12 +9429,12 @@ static void igb_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int __maybe_unused igb_suspend(struct device *dev)
+static int igb_suspend(struct device *dev)
 {
 	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
-static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
+static int __igb_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -9514,12 +9490,12 @@ static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
 	return err;
 }
 
-static int __maybe_unused igb_resume(struct device *dev)
+static int igb_resume(struct device *dev)
 {
 	return __igb_resume(dev, false);
 }
 
-static int __maybe_unused igb_runtime_idle(struct device *dev)
+static int igb_runtime_idle(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -9530,12 +9506,12 @@ static int __maybe_unused igb_runtime_idle(struct device *dev)
 	return -EBUSY;
 }
 
-static int __maybe_unused igb_runtime_suspend(struct device *dev)
+static int igb_runtime_suspend(struct device *dev)
 {
 	return __igb_shutdown(to_pci_dev(dev), NULL, 1);
 }
 
-static int __maybe_unused igb_runtime_resume(struct device *dev)
+static int igb_runtime_resume(struct device *dev)
 {
 	return __igb_resume(dev, true);
 }
@@ -10157,4 +10133,20 @@ static void igb_nfc_filter_restore(struct igb_adapter *adapter)
 
 	spin_unlock(&adapter->nfc_lock);
 }
+
+static _DEFINE_DEV_PM_OPS(igb_pm_ops, igb_suspend, igb_resume,
+			  igb_runtime_suspend, igb_runtime_resume,
+			  igb_runtime_idle);
+
+static struct pci_driver igb_driver = {
+	.name     = igb_driver_name,
+	.id_table = igb_pci_tbl,
+	.probe    = igb_probe,
+	.remove   = igb_remove,
+	.driver.pm = pm_ptr(&igb_pm_ops),
+	.shutdown = igb_shutdown,
+	.sriov_configure = igb_pci_sriov_configure,
+	.err_handler = &igb_err_handler
+};
+
 /* igb_main.c */
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index b0cf310e6f7b..7661edd7d0f2 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2434,7 +2434,7 @@ static int igbvf_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		igbvf_up(adapter);
@@ -2470,7 +2470,7 @@ static int igbvf_suspend(struct device *dev_d)
 	return 0;
 }
 
-static int __maybe_unused igbvf_resume(struct device *dev_d)
+static int igbvf_resume(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -2957,7 +2957,7 @@ static const struct pci_device_id igbvf_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, igbvf_pci_tbl);
 
-static SIMPLE_DEV_PM_OPS(igbvf_pm_ops, igbvf_suspend, igbvf_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(igbvf_pm_ops, igbvf_suspend, igbvf_resume);
 
 /* PCI Device API Driver */
 static struct pci_driver igbvf_driver = {
@@ -2965,7 +2965,7 @@ static struct pci_driver igbvf_driver = {
 	.id_table	= igbvf_pci_tbl,
 	.probe		= igbvf_probe,
 	.remove		= igbvf_remove,
-	.driver.pm	= &igbvf_pm_ops,
+	.driver.pm	= pm_sleep_ptr(&igbvf_pm_ops),
 	.shutdown	= igbvf_shutdown,
 	.err_handler	= &igbvf_err_handler
 };
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 6bc56c7c181e..8b14c029eda1 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -72,13 +72,46 @@ struct igc_rx_packet_stats {
 	u64 other_packets;
 };
 
+enum igc_tx_buffer_type {
+	IGC_TX_BUFFER_TYPE_SKB,
+	IGC_TX_BUFFER_TYPE_XDP,
+	IGC_TX_BUFFER_TYPE_XSK,
+};
+
+/* wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct igc_tx_buffer {
+	union igc_adv_tx_desc *next_to_watch;
+	unsigned long time_stamp;
+	enum igc_tx_buffer_type type;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
+	unsigned int bytecount;
+	u16 gso_segs;
+	__be16 protocol;
+
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+	u32 tx_flags;
+	bool xsk_pending_ts;
+};
+
 struct igc_tx_timestamp_request {
-	struct sk_buff *skb;   /* reference to the packet being timestamped */
+	union {                /* reference to the packet being timestamped */
+		struct sk_buff *skb;
+		struct igc_tx_buffer *xsk_tx_buffer;
+	};
+	enum igc_tx_buffer_type buffer_type;
 	unsigned long start;   /* when the tstamp request started (jiffies) */
 	u32 mask;              /* _TSYNCTXCTL_TXTT_{X} bit for this request */
 	u32 regl;              /* which TXSTMPL_{X} register should be used */
 	u32 regh;              /* which TXSTMPH_{X} register should be used */
 	u32 flags;             /* flags that should be added to the tx_buffer */
+	u8 xsk_queue_index;    /* Tx queue which requesting timestamp */
+	struct xsk_tx_metadata_compl xsk_meta;	/* ref to xsk Tx metadata */
 };
 
 struct igc_inline_rx_tstamps {
@@ -323,6 +356,9 @@ void igc_disable_tx_ring(struct igc_ring *ring);
 void igc_enable_tx_ring(struct igc_ring *ring);
 int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
 
+/* AF_XDP TX metadata operations */
+extern const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops;
+
 /* igc_dump declarations */
 void igc_rings_dump(struct igc_adapter *adapter);
 void igc_regs_dump(struct igc_adapter *adapter);
@@ -508,32 +544,6 @@ enum igc_boards {
 #define TXD_USE_COUNT(S)	DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD)
 #define DESC_NEEDED	(MAX_SKB_FRAGS + 4)
 
-enum igc_tx_buffer_type {
-	IGC_TX_BUFFER_TYPE_SKB,
-	IGC_TX_BUFFER_TYPE_XDP,
-	IGC_TX_BUFFER_TYPE_XSK,
-};
-
-/* wrapper around a pointer to a socket buffer,
- * so a DMA handle can be stored along with the buffer
- */
-struct igc_tx_buffer {
-	union igc_adv_tx_desc *next_to_watch;
-	unsigned long time_stamp;
-	enum igc_tx_buffer_type type;
-	union {
-		struct sk_buff *skb;
-		struct xdp_frame *xdpf;
-	};
-	unsigned int bytecount;
-	u16 gso_segs;
-	__be16 protocol;
-
-	DEFINE_DMA_UNMAP_ADDR(dma);
-	DEFINE_DMA_UNMAP_LEN(len);
-	u32 tx_flags;
-};
-
 struct igc_rx_buffer {
 	union {
 		struct {
@@ -557,6 +567,13 @@ struct igc_xdp_buff {
 	struct igc_inline_rx_tstamps *rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */
 };
 
+struct igc_metadata_request {
+	struct igc_tx_buffer *tx_buffer;
+	struct xsk_tx_metadata *meta;
+	struct igc_ring *tx_ring;
+	u32 cmd_type;
+};
+
 struct igc_q_vector {
 	struct igc_adapter *adapter;    /* backlink */
 	void __iomem *itr_register;
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 1a64f1ca6ca8..f2c4f1966bb0 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1711,21 +1711,6 @@ static int igc_ethtool_set_eee(struct net_device *netdev,
 	return 0;
 }
 
-static int igc_ethtool_begin(struct net_device *netdev)
-{
-	struct igc_adapter *adapter = netdev_priv(netdev);
-
-	pm_runtime_get_sync(&adapter->pdev->dev);
-	return 0;
-}
-
-static void igc_ethtool_complete(struct net_device *netdev)
-{
-	struct igc_adapter *adapter = netdev_priv(netdev);
-
-	pm_runtime_put(&adapter->pdev->dev);
-}
-
 static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 					  struct ethtool_link_ksettings *cmd)
 {
@@ -2025,8 +2010,6 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.set_priv_flags		= igc_ethtool_set_priv_flags,
 	.get_eee		= igc_ethtool_get_eee,
 	.set_eee		= igc_ethtool_set_eee,
-	.begin			= igc_ethtool_begin,
-	.complete		= igc_ethtool_complete,
 	.get_link_ksettings	= igc_ethtool_get_link_ksettings,
 	.set_link_ksettings	= igc_ethtool_set_link_ksettings,
 	.self_test		= igc_ethtool_diag_test,
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 4d975d620a8e..b5bcabab7a1d 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2712,8 +2712,7 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 
 	net_prefetch(xdp->data_meta);
 
-	skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&ring->q_vector->napi, totalsize);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -2874,6 +2873,89 @@ static void igc_update_tx_stats(struct igc_q_vector *q_vector,
 	q_vector->tx.total_packets += packets;
 }
 
+static void igc_xsk_request_timestamp(void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	struct igc_tx_timestamp_request *tstamp;
+	u32 tx_flags = IGC_TX_FLAGS_TSTAMP;
+	struct igc_adapter *adapter;
+	unsigned long lock_flags;
+	bool found = false;
+	int i;
+
+	if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) {
+		adapter = netdev_priv(tx_ring->netdev);
+
+		spin_lock_irqsave(&adapter->ptp_tx_lock, lock_flags);
+
+		/* Search for available tstamp regs */
+		for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+			tstamp = &adapter->tx_tstamp[i];
+
+			/* tstamp->skb and tstamp->xsk_tx_buffer are in union.
+			 * When tstamp->skb is equal to NULL,
+			 * tstamp->xsk_tx_buffer is equal to NULL as well.
+			 * This condition means that the particular tstamp reg
+			 * is not occupied by other packet.
+			 */
+			if (!tstamp->skb) {
+				found = true;
+				break;
+			}
+		}
+
+		/* Return if no available tstamp regs */
+		if (!found) {
+			adapter->tx_hwtstamp_skipped++;
+			spin_unlock_irqrestore(&adapter->ptp_tx_lock,
+					       lock_flags);
+			return;
+		}
+
+		tstamp->start = jiffies;
+		tstamp->xsk_queue_index = tx_ring->queue_index;
+		tstamp->xsk_tx_buffer = meta_req->tx_buffer;
+		tstamp->buffer_type = IGC_TX_BUFFER_TYPE_XSK;
+
+		/* Hold the transmit completion until timestamp is ready */
+		meta_req->tx_buffer->xsk_pending_ts = true;
+
+		/* Keep the pointer to tx_timestamp, which is located in XDP
+		 * metadata area. It is the location to store the value of
+		 * tx hardware timestamp.
+		 */
+		xsk_tx_metadata_to_compl(meta_req->meta, &tstamp->xsk_meta);
+
+		/* Set timestamp bit based on the _TSTAMP(_X) bit. */
+		tx_flags |= tstamp->flags;
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP,
+						   (IGC_ADVTXD_MAC_TSTAMP));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_1,
+						   (IGC_ADVTXD_TSTAMP_REG_1));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_2,
+						   (IGC_ADVTXD_TSTAMP_REG_2));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_3,
+						   (IGC_ADVTXD_TSTAMP_REG_3));
+
+		spin_unlock_irqrestore(&adapter->ptp_tx_lock, lock_flags);
+	}
+}
+
+static u64 igc_xsk_fill_timestamp(void *_priv)
+{
+	return *(u64 *)_priv;
+}
+
+const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
+	.tmo_request_timestamp		= igc_xsk_request_timestamp,
+	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+};
+
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
 {
 	struct xsk_buff_pool *pool = ring->xsk_pool;
@@ -2895,24 +2977,34 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	budget = igc_desc_unused(ring);
 
 	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
-		u32 cmd_type, olinfo_status;
+		struct igc_metadata_request meta_req;
+		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
+		u32 olinfo_status;
 		dma_addr_t dma;
 
-		cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
-			   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
-			   xdp_desc.len;
+		meta_req.cmd_type = IGC_ADVTXD_DTYP_DATA |
+				    IGC_ADVTXD_DCMD_DEXT |
+				    IGC_ADVTXD_DCMD_IFCS |
+				    IGC_TXD_DCMD | xdp_desc.len;
 		olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT;
 
 		dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
+		meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
 		xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len);
+		bi = &ring->tx_buffer_info[ntu];
+
+		meta_req.tx_ring = ring;
+		meta_req.tx_buffer = bi;
+		meta_req.meta = meta;
+		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
+					&meta_req);
 
 		tx_desc = IGC_TX_DESC(ring, ntu);
-		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 		tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
-		bi = &ring->tx_buffer_info[ntu];
 		bi->type = IGC_TX_BUFFER_TYPE_XSK;
 		bi->protocol = 0;
 		bi->bytecount = xdp_desc.len;
@@ -2975,6 +3067,13 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
 			break;
 
+		/* Hold the completions while there's a pending tx hardware
+		 * timestamp request from XDP Tx metadata.
+		 */
+		if (tx_buffer->type == IGC_TX_BUFFER_TYPE_XSK &&
+		    tx_buffer->xsk_pending_ts)
+			break;
+
 		/* clear next_to_watch to prevent false hangs */
 		tx_buffer->next_to_watch = NULL;
 
@@ -5176,7 +5275,7 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu)
 		igc_down(adapter);
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		igc_up(adapter);
@@ -5930,15 +6029,6 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 	if (err)
 		goto err_req_irq;
 
-	/* Notify the stack of the actual queue counts. */
-	err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
-	if (err)
-		goto err_set_queues;
-
-	err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues);
-	if (err)
-		goto err_set_queues;
-
 	clear_bit(__IGC_DOWN, &adapter->state);
 
 	for (i = 0; i < adapter->num_q_vectors; i++)
@@ -5959,8 +6049,6 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 
 	return IGC_SUCCESS;
 
-err_set_queues:
-	igc_free_irq(adapter);
 err_req_irq:
 	igc_release_hw_control(adapter);
 	igc_power_down_phy_copper_base(&adapter->hw);
@@ -5977,6 +6065,17 @@ err_setup_tx:
 
 int igc_open(struct net_device *netdev)
 {
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	int err;
+
+	/* Notify the stack of the actual queue counts. */
+	err = netif_set_real_num_queues(netdev, adapter->num_tx_queues,
+					adapter->num_rx_queues);
+	if (err) {
+		netdev_err(netdev, "error setting real queue count\n");
+		return err;
+	}
+
 	return __igc_open(netdev, false);
 }
 
@@ -6803,6 +6902,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 	netdev->netdev_ops = &igc_netdev_ops;
 	netdev->xdp_metadata_ops = &igc_xdp_metadata_ops;
+	netdev->xsk_tx_metadata_ops = &igc_xsk_tx_metadata_ops;
 	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
@@ -6928,8 +7028,6 @@ static int igc_probe(struct pci_dev *pdev,
 	device_set_wakeup_enable(&adapter->pdev->dev,
 				 adapter->flags & IGC_FLAG_WOL_SUPPORTED);
 
-	igc_ptp_init(adapter);
-
 	igc_tsn_clear_schedule(adapter);
 
 	/* reset the hardware with the new settings */
@@ -6951,6 +7049,9 @@ static int igc_probe(struct pci_dev *pdev,
 	/* Check if Media Autosense is enabled */
 	adapter->ei = *ei;
 
+	/* do hw tstamp init after resetting */
+	igc_ptp_init(adapter);
+
 	/* print pcie link status and MAC address */
 	pcie_print_link_status(pdev);
 	netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr);
@@ -7108,8 +7209,7 @@ static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int __maybe_unused igc_runtime_suspend(struct device *dev)
+static int igc_runtime_suspend(struct device *dev)
 {
 	return __igc_shutdown(to_pci_dev(dev), NULL, 1);
 }
@@ -7144,7 +7244,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int __maybe_unused igc_resume(struct device *dev)
+static int igc_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7186,23 +7286,21 @@ static int __maybe_unused igc_resume(struct device *dev)
 
 	wr32(IGC_WUS, ~0);
 
-	rtnl_lock();
-	if (!err && netif_running(netdev))
+	if (netif_running(netdev)) {
 		err = __igc_open(netdev, true);
-
-	if (!err)
-		netif_device_attach(netdev);
-	rtnl_unlock();
+		if (!err)
+			netif_device_attach(netdev);
+	}
 
 	return err;
 }
 
-static int __maybe_unused igc_runtime_resume(struct device *dev)
+static int igc_runtime_resume(struct device *dev)
 {
 	return igc_resume(dev);
 }
 
-static int __maybe_unused igc_suspend(struct device *dev)
+static int igc_suspend(struct device *dev)
 {
 	return __igc_shutdown(to_pci_dev(dev), NULL, 0);
 }
@@ -7217,7 +7315,6 @@ static int __maybe_unused igc_runtime_idle(struct device *dev)
 
 	return -EBUSY;
 }
-#endif /* CONFIG_PM */
 
 static void igc_shutdown(struct pci_dev *pdev)
 {
@@ -7332,22 +7429,16 @@ static const struct pci_error_handlers igc_err_handler = {
 	.resume = igc_io_resume,
 };
 
-#ifdef CONFIG_PM
-static const struct dev_pm_ops igc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume)
-	SET_RUNTIME_PM_OPS(igc_runtime_suspend, igc_runtime_resume,
-			   igc_runtime_idle)
-};
-#endif
+static _DEFINE_DEV_PM_OPS(igc_pm_ops, igc_suspend, igc_resume,
+			  igc_runtime_suspend, igc_runtime_resume,
+			  igc_runtime_idle);
 
 static struct pci_driver igc_driver = {
 	.name     = igc_driver_name,
 	.id_table = igc_pci_tbl,
 	.probe    = igc_probe,
 	.remove   = igc_remove,
-#ifdef CONFIG_PM
-	.driver.pm = &igc_pm_ops,
-#endif
+	.driver.pm = pm_ptr(&igc_pm_ops),
 	.shutdown = igc_shutdown,
 	.err_handler = &igc_err_handler,
 };
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 885faaa7b9de..1bb026232efc 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -11,6 +11,7 @@
 #include <linux/ktime.h>
 #include <linux/delay.h>
 #include <linux/iopoll.h>
+#include <net/xdp_sock_drv.h>
 
 #define INCVALUE_MASK		0x7fffffff
 #define ISGN			0x80000000
@@ -545,6 +546,30 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter)
 	wr32(IGC_TSYNCRXCTL, val);
 }
 
+static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter,
+				   struct igc_tx_timestamp_request *tstamp)
+{
+	if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) {
+		/* Release the transmit completion */
+		tstamp->xsk_tx_buffer->xsk_pending_ts = false;
+
+		/* Note: tstamp->skb and tstamp->xsk_tx_buffer are in union.
+		 * By setting tstamp->xsk_tx_buffer to NULL, tstamp->skb will
+		 * become NULL as well.
+		 */
+		tstamp->xsk_tx_buffer = NULL;
+		tstamp->buffer_type = 0;
+
+		/* Trigger txrx interrupt for transmit completion */
+		igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0);
+
+		return;
+	}
+
+	dev_kfree_skb_any(tstamp->skb);
+	tstamp->skb = NULL;
+}
+
 static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter)
 {
 	unsigned long flags;
@@ -555,8 +580,8 @@ static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter)
 	for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
 		struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i];
 
-		dev_kfree_skb_any(tstamp->skb);
-		tstamp->skb = NULL;
+		if (tstamp->skb)
+			igc_ptp_free_tx_buffer(adapter, tstamp);
 	}
 
 	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
@@ -657,8 +682,9 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 static void igc_ptp_tx_timeout(struct igc_adapter *adapter,
 			       struct igc_tx_timestamp_request *tstamp)
 {
-	dev_kfree_skb_any(tstamp->skb);
-	tstamp->skb = NULL;
+	if (tstamp->skb)
+		igc_ptp_free_tx_buffer(adapter, tstamp);
+
 	adapter->tx_hwtstamp_timeouts++;
 
 	netdev_warn(adapter->netdev, "Tx timestamp timeout\n");
@@ -729,10 +755,21 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter,
 	shhwtstamps.hwtstamp =
 		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
 
-	tstamp->skb = NULL;
+	/* Copy the tx hardware timestamp into xdp metadata or skb */
+	if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) {
+		struct xsk_buff_pool *xsk_pool;
+
+		xsk_pool = adapter->tx_ring[tstamp->xsk_queue_index]->xsk_pool;
+		if (xsk_pool && xp_tx_metadata_enabled(xsk_pool)) {
+			xsk_tx_metadata_complete(&tstamp->xsk_meta,
+						 &igc_xsk_tx_metadata_ops,
+						 &shhwtstamps.hwtstamp);
+		}
+	} else {
+		skb_tstamp_tx(skb, &shhwtstamps);
+	}
 
-	skb_tstamp_tx(skb, &shhwtstamps);
-	dev_kfree_skb_any(skb);
+	igc_ptp_free_tx_buffer(adapter, tstamp);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f985252c8c8d..094653e81b97 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6847,7 +6847,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 		   netdev->mtu, new_mtu);
 
 	/* must set new MTU before calling down or up */
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		ixgbe_reinit_locked(adapter);
@@ -6974,7 +6974,7 @@ int ixgbe_close(struct net_device *netdev)
 	return 0;
 }
 
-static int __maybe_unused ixgbe_resume(struct device *dev_d)
+static int ixgbe_resume(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
@@ -7082,7 +7082,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	return 0;
 }
 
-static int __maybe_unused ixgbe_suspend(struct device *dev_d)
+static int ixgbe_suspend(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	int retval;
@@ -10061,15 +10061,10 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		int status;
-		__u16 mode;
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
+		__u16 mode = nla_get_u16(attr);
+		int status = ixgbe_configure_bridge_mode(adapter, mode);
 
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-
-		mode = nla_get_u16(attr);
-		status = ixgbe_configure_bridge_mode(adapter, mode);
 		if (status)
 			return status;
 
@@ -11588,14 +11583,14 @@ static const struct pci_error_handlers ixgbe_err_handler = {
 	.resume = ixgbe_io_resume,
 };
 
-static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume);
 
 static struct pci_driver ixgbe_driver = {
 	.name      = ixgbe_driver_name,
 	.id_table  = ixgbe_pci_tbl,
 	.probe     = ixgbe_probe,
 	.remove    = ixgbe_remove,
-	.driver.pm = &ixgbe_pm_ops,
+	.driver.pm = pm_sleep_ptr(&ixgbe_pm_ops),
 	.shutdown  = ixgbe_shutdown,
 	.sriov_configure = ixgbe_pci_sriov_configure,
 	.err_handler = &ixgbe_err_handler
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index ed440dd0c4f9..897fe357b65b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -2179,7 +2179,6 @@ enum {
 #define IXGBE_PCI_LINK_SPEED_5000 0x2
 #define IXGBE_PCI_LINK_SPEED_8000 0x3
 #define IXGBE_PCI_HEADER_TYPE_REGISTER  0x0E
-#define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80
 #define IXGBE_PCI_DEVICE_CONTROL2_16ms  0x0005
 
 #define IXGBE_PCIDEVCTRL2_TIMEO_MASK	0xf
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index d34d715c59eb..397cb773fabb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -220,8 +220,7 @@ static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
 	net_prefetch(xdp->data_meta);
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 9c960017a6de..b938dc06045d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4292,7 +4292,7 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	       netdev->mtu, new_mtu);
 
 	/* must set new MTU before calling down or up */
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		ixgbevf_reinit_locked(adapter);
@@ -4300,7 +4300,7 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static int __maybe_unused ixgbevf_suspend(struct device *dev_d)
+static int ixgbevf_suspend(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
@@ -4317,7 +4317,7 @@ static int __maybe_unused ixgbevf_suspend(struct device *dev_d)
 	return 0;
 }
 
-static int __maybe_unused ixgbevf_resume(struct device *dev_d)
+static int ixgbevf_resume(struct device *dev_d)
 {
 	struct pci_dev *pdev = to_pci_dev(dev_d);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -4854,7 +4854,7 @@ static const struct pci_error_handlers ixgbevf_err_handler = {
 	.resume = ixgbevf_io_resume,
 };
 
-static SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume);
 
 static struct pci_driver ixgbevf_driver = {
 	.name		= ixgbevf_driver_name,
@@ -4863,7 +4863,7 @@ static struct pci_driver ixgbevf_driver = {
 	.remove		= ixgbevf_remove,
 
 	/* Power Management Hooks */
-	.driver.pm	= &ixgbevf_pm_ops,
+	.driver.pm	= pm_sleep_ptr(&ixgbevf_pm_ops),
 
 	.shutdown	= ixgbevf_shutdown,
 	.err_handler	= &ixgbevf_err_handler
diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig
new file mode 100644
index 000000000000..480293b71dbc
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/Kconfig
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2024 Intel Corporation
+
+config LIBETH
+	tristate
+	select PAGE_POOL
+	help
+	  libeth is a common library containing routines shared between several
+	  drivers, but not yet promoted to the generic kernel API.
diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile
new file mode 100644
index 000000000000..cb99203d1dd2
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2024 Intel Corporation
+
+obj-$(CONFIG_LIBETH)		+= libeth.o
+
+libeth-objs			+= rx.o
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
new file mode 100644
index 000000000000..6221b88c34ac
--- /dev/null
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include <net/libeth/rx.h>
+
+/* Rx buffer management */
+
+/**
+ * libeth_rx_hw_len - get the actual buffer size to be passed to HW
+ * @pp: &page_pool_params of the netdev to calculate the size for
+ * @max_len: maximum buffer size for a single descriptor
+ *
+ * Return: HW-writeable length per one buffer to pass it to the HW accounting:
+ * MTU the @dev has, HW required alignment, minimum and maximum allowed values,
+ * and system's page size.
+ */
+static u32 libeth_rx_hw_len(const struct page_pool_params *pp, u32 max_len)
+{
+	u32 len;
+
+	len = READ_ONCE(pp->netdev->mtu) + LIBETH_RX_LL_LEN;
+	len = ALIGN(len, LIBETH_RX_BUF_STRIDE);
+	len = min3(len, ALIGN_DOWN(max_len ? : U32_MAX, LIBETH_RX_BUF_STRIDE),
+		   pp->max_len);
+
+	return len;
+}
+
+/**
+ * libeth_rx_fq_create - create a PP with the default libeth settings
+ * @fq: buffer queue struct to fill
+ * @napi: &napi_struct covering this PP (no usage outside its poll loops)
+ *
+ * Return: %0 on success, -%errno on failure.
+ */
+int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi)
+{
+	struct page_pool_params pp = {
+		.flags		= PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.order		= LIBETH_RX_PAGE_ORDER,
+		.pool_size	= fq->count,
+		.nid		= fq->nid,
+		.dev		= napi->dev->dev.parent,
+		.netdev		= napi->dev,
+		.napi		= napi,
+		.dma_dir	= DMA_FROM_DEVICE,
+		.offset		= LIBETH_SKB_HEADROOM,
+	};
+	struct libeth_fqe *fqes;
+	struct page_pool *pool;
+
+	/* HW-writeable / syncable length per one page */
+	pp.max_len = LIBETH_RX_PAGE_LEN(pp.offset);
+
+	/* HW-writeable length per buffer */
+	fq->buf_len = libeth_rx_hw_len(&pp, fq->buf_len);
+	/* Buffer size to allocate */
+	fq->truesize = roundup_pow_of_two(SKB_HEAD_ALIGN(pp.offset +
+							 fq->buf_len));
+
+	pool = page_pool_create(&pp);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	fqes = kvcalloc_node(fq->count, sizeof(*fqes), GFP_KERNEL, fq->nid);
+	if (!fqes)
+		goto err_buf;
+
+	fq->fqes = fqes;
+	fq->pp = pool;
+
+	return 0;
+
+err_buf:
+	page_pool_destroy(pool);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, LIBETH);
+
+/**
+ * libeth_rx_fq_destroy - destroy a &page_pool created by libeth
+ * @fq: buffer queue to process
+ */
+void libeth_rx_fq_destroy(struct libeth_fq *fq)
+{
+	kvfree(fq->fqes);
+	page_pool_destroy(fq->pp);
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, LIBETH);
+
+/**
+ * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context
+ * @page: page to recycle
+ *
+ * To be used on exceptions or rare cases not requiring fast inline recycling.
+ */
+void libeth_rx_recycle_slow(struct page *page)
+{
+	page_pool_recycle_direct(page->pp, page);
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, LIBETH);
+
+/* Converting abstract packet type numbers into a software structure with
+ * the packet parameters to do O(1) lookup on Rx.
+ */
+
+static const u16 libeth_rx_pt_xdp_oip[] = {
+	[LIBETH_RX_PT_OUTER_L2]		= XDP_RSS_TYPE_NONE,
+	[LIBETH_RX_PT_OUTER_IPV4]	= XDP_RSS_L3_IPV4,
+	[LIBETH_RX_PT_OUTER_IPV6]	= XDP_RSS_L3_IPV6,
+};
+
+static const u16 libeth_rx_pt_xdp_iprot[] = {
+	[LIBETH_RX_PT_INNER_NONE]	= XDP_RSS_TYPE_NONE,
+	[LIBETH_RX_PT_INNER_UDP]	= XDP_RSS_L4_UDP,
+	[LIBETH_RX_PT_INNER_TCP]	= XDP_RSS_L4_TCP,
+	[LIBETH_RX_PT_INNER_SCTP]	= XDP_RSS_L4_SCTP,
+	[LIBETH_RX_PT_INNER_ICMP]	= XDP_RSS_L4_ICMP,
+	[LIBETH_RX_PT_INNER_TIMESYNC]	= XDP_RSS_TYPE_NONE,
+};
+
+static const u16 libeth_rx_pt_xdp_pl[] = {
+	[LIBETH_RX_PT_PAYLOAD_NONE]	= XDP_RSS_TYPE_NONE,
+	[LIBETH_RX_PT_PAYLOAD_L2]	= XDP_RSS_TYPE_NONE,
+	[LIBETH_RX_PT_PAYLOAD_L3]	= XDP_RSS_TYPE_NONE,
+	[LIBETH_RX_PT_PAYLOAD_L4]	= XDP_RSS_L4,
+};
+
+/**
+ * libeth_rx_pt_gen_hash_type - generate an XDP RSS hash type for a PT
+ * @pt: PT structure to evaluate
+ *
+ * Generates ```hash_type``` field with XDP RSS type values from the parsed
+ * packet parameters if they're obtained dynamically at runtime.
+ */
+void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt)
+{
+	pt->hash_type = 0;
+	pt->hash_type |= libeth_rx_pt_xdp_oip[pt->outer_ip];
+	pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot];
+	pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer];
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, LIBETH);
+
+/* Module */
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("Common Ethernet library");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/intel/libie/Kconfig b/drivers/net/ethernet/intel/libie/Kconfig
new file mode 100644
index 000000000000..33aff6bc8f81
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/Kconfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2024 Intel Corporation
+
+config LIBIE
+	tristate
+	select LIBETH
+	help
+	  libie (Intel Ethernet library) is a common library built on top of
+	  libeth and containing vendor-specific routines shared between several
+	  Intel Ethernet drivers.
diff --git a/drivers/net/ethernet/intel/libie/Makefile b/drivers/net/ethernet/intel/libie/Makefile
new file mode 100644
index 000000000000..bf42c5aeeedd
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2024 Intel Corporation
+
+obj-$(CONFIG_LIBIE)	+= libie.o
+
+libie-objs		+= rx.o
diff --git a/drivers/net/ethernet/intel/libie/rx.c b/drivers/net/ethernet/intel/libie/rx.c
new file mode 100644
index 000000000000..38201ee1e891
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/rx.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include <linux/net/intel/libie/rx.h>
+
+/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed
+ * bitfield struct.
+ */
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions by means of preprocessor
+ * concatenation.
+ */
+#define XDP_RSS_L3_L2			XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE			XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_TIMESYNC		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_L3			XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_L4			XDP_RSS_L4
+
+#define LIBIE_RX_PT(oip, ofrag, tun, tp, tefr, iprot, pl) {		   \
+		.outer_ip		= LIBETH_RX_PT_OUTER_##oip,	   \
+		.outer_frag		= LIBETH_RX_PT_##ofrag,		   \
+		.tunnel_type		= LIBETH_RX_PT_TUNNEL_IP_##tun,	   \
+		.tunnel_end_prot	= LIBETH_RX_PT_TUNNEL_END_##tp,	   \
+		.tunnel_end_frag	= LIBETH_RX_PT_##tefr,		   \
+		.inner_prot		= LIBETH_RX_PT_INNER_##iprot,	   \
+		.payload_layer		= LIBETH_RX_PT_PAYLOAD_##pl,	   \
+		.hash_type		= XDP_RSS_L3_##oip |		   \
+					  XDP_RSS_L4_##iprot |		   \
+					  XDP_RSS_TYPE_##pl,		   \
+	}
+
+#define LIBIE_RX_PT_UNUSED		{ }
+
+#define __LIBIE_RX_PT_L2(iprot, pl)					   \
+	LIBIE_RX_PT(L2, NOT_FRAG, NONE, NONE, NOT_FRAG, iprot, pl)
+#define LIBIE_RX_PT_L2		__LIBIE_RX_PT_L2(NONE, L2)
+#define LIBIE_RX_PT_TS		__LIBIE_RX_PT_L2(TIMESYNC, L2)
+#define LIBIE_RX_PT_L3		__LIBIE_RX_PT_L2(NONE, L3)
+
+#define LIBIE_RX_PT_IP_FRAG(oip)					   \
+	LIBIE_RX_PT(IPV##oip, FRAG, NONE, NONE, NOT_FRAG, NONE, L3)
+#define LIBIE_RX_PT_IP_L3(oip, tun, teprot, tefr)			   \
+	LIBIE_RX_PT(IPV##oip, NOT_FRAG, tun, teprot, tefr, NONE, L3)
+#define LIBIE_RX_PT_IP_L4(oip, tun, teprot, iprot)			   \
+	LIBIE_RX_PT(IPV##oip, NOT_FRAG, tun, teprot, NOT_FRAG, iprot, L4)
+
+#define LIBIE_RX_PT_IP_NOF(oip, tun, ver)				   \
+	LIBIE_RX_PT_IP_L3(oip, tun, ver, NOT_FRAG),			   \
+	LIBIE_RX_PT_IP_L4(oip, tun, ver, UDP),				   \
+	LIBIE_RX_PT_UNUSED,						   \
+	LIBIE_RX_PT_IP_L4(oip, tun, ver, TCP),				   \
+	LIBIE_RX_PT_IP_L4(oip, tun, ver, SCTP),				   \
+	LIBIE_RX_PT_IP_L4(oip, tun, ver, ICMP)
+
+/* IPv oip --> tun --> IPv ver */
+#define LIBIE_RX_PT_IP_TUN_VER(oip, tun, ver)				   \
+	LIBIE_RX_PT_IP_L3(oip, tun, ver, FRAG),				   \
+	LIBIE_RX_PT_IP_NOF(oip, tun, ver)
+
+/* Non Tunneled IPv oip */
+#define LIBIE_RX_PT_IP_RAW(oip)						   \
+	LIBIE_RX_PT_IP_FRAG(oip),					   \
+	LIBIE_RX_PT_IP_NOF(oip, NONE, NONE)
+
+/* IPv oip --> tun --> { IPv4, IPv6 } */
+#define LIBIE_RX_PT_IP_TUN(oip, tun)					   \
+	LIBIE_RX_PT_IP_TUN_VER(oip, tun, IPV4),				   \
+	LIBIE_RX_PT_IP_TUN_VER(oip, tun, IPV6)
+
+/* IPv oip --> GRE/NAT tun --> { x, IPv4, IPv6 } */
+#define LIBIE_RX_PT_IP_GRE(oip, tun)					   \
+	LIBIE_RX_PT_IP_L3(oip, tun, NONE, NOT_FRAG),			   \
+	LIBIE_RX_PT_IP_TUN(oip, tun)
+
+/* Non Tunneled IPv oip
+ * IPv oip --> { IPv4, IPv6 }
+ * IPv oip --> GRE/NAT --> { x, IPv4, IPv6 }
+ * IPv oip --> GRE/NAT --> MAC --> { x, IPv4, IPv6 }
+ * IPv oip --> GRE/NAT --> MAC/VLAN --> { x, IPv4, IPv6 }
+ */
+#define LIBIE_RX_PT_IP(oip)						   \
+	LIBIE_RX_PT_IP_RAW(oip),					   \
+	LIBIE_RX_PT_IP_TUN(oip, IP),					   \
+	LIBIE_RX_PT_IP_GRE(oip, GRENAT),				   \
+	LIBIE_RX_PT_IP_GRE(oip, GRENAT_MAC),				   \
+	LIBIE_RX_PT_IP_GRE(oip, GRENAT_MAC_VLAN)
+
+/* Lookup table mapping for O(1) parsing */
+const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM] = {
+	/* L2 packet types */
+	LIBIE_RX_PT_UNUSED,
+	LIBIE_RX_PT_L2,
+	LIBIE_RX_PT_TS,
+	LIBIE_RX_PT_L2,
+	LIBIE_RX_PT_UNUSED,
+	LIBIE_RX_PT_UNUSED,
+	LIBIE_RX_PT_L2,
+	LIBIE_RX_PT_L2,
+	LIBIE_RX_PT_UNUSED,
+	LIBIE_RX_PT_UNUSED,
+	LIBIE_RX_PT_L2,
+	LIBIE_RX_PT_UNUSED,
+
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+	LIBIE_RX_PT_L3,
+
+	LIBIE_RX_PT_IP(4),
+	LIBIE_RX_PT_IP(6),
+};
+EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, LIBIE);
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("Intel(R) Ethernet common library");
+MODULE_IMPORT_NS(LIBETH);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 1732ec3c3dbd..b06e24562973 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -2301,7 +2301,7 @@ jme_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	netdev_update_features(netdev);
 
 	jme_restart_rx_engine(jme);
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 1d5b7bb6380f..5352fee62d2b 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -519,7 +519,7 @@ ltq_etop_change_mtu(struct net_device *dev, int new_mtu)
 	struct ltq_etop_priv *priv = netdev_priv(dev);
 	unsigned long flags;
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	spin_lock_irqsave(&priv->lock, flags);
 	ltq_etop_w32((ETOP_PLEN_UNDER << 16) | new_mtu, LTQ_ETOP_IGPLEN);
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 8bd4def3622e..07904a528f21 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -419,7 +419,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 	int curr_desc;
 	int ret = 0;
 
-	net_dev->mtu = new_mtu;
+	WRITE_ONCE(net_dev->mtu, new_mtu);
 	priv->rx_buf_size = xrx200_buffer_size(new_mtu);
 	priv->rx_skb_size = xrx200_skb_size(priv->rx_buf_size);
 
@@ -440,7 +440,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 		buff = ch_rx->rx_buff[ch_rx->dma.desc];
 		ret = xrx200_alloc_buf(ch_rx, netdev_alloc_frag);
 		if (ret) {
-			net_dev->mtu = old_mtu;
+			WRITE_ONCE(net_dev->mtu, old_mtu);
 			priv->rx_buf_size = xrx200_buffer_size(old_mtu);
 			priv->rx_skb_size = xrx200_skb_size(priv->rx_buf_size);
 			break;
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index f0bdc06d253d..f35ae2c88091 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2562,7 +2562,7 @@ static int mv643xx_eth_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct mv643xx_eth_private *mp = netdev_priv(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	mv643xx_eth_recalc_skb_size(mp);
 	tx_set_rate(mp, 1000000000, 16777216);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 40a5f1431e4e..41894834fb53 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3259,7 +3259,8 @@ static void mvneta_link_change(struct mvneta_port *pp)
 {
 	u32 gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS);
 
-	phylink_mac_change(pp->phylink, !!(gmac_stat & MVNETA_GMAC_LINK_UP));
+	phylink_pcs_change(&pp->phylink_pcs,
+			   !!(gmac_stat & MVNETA_GMAC_LINK_UP));
 }
 
 /* NAPI handler
@@ -3860,7 +3861,7 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 		return -EINVAL;
 	}
 
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 
 	if (!netif_running(dev)) {
 		if (pp->bm_priv)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 23adf53c2aa1..e91486c48de3 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1375,7 +1375,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu)
 	}
 
 out_set:
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 	dev->wanted_features = dev->features;
 
 	netdev_update_features(dev);
@@ -3434,12 +3434,13 @@ static void mvpp2_isr_handle_ptp(struct mvpp2_port *port)
 		mvpp2_isr_handle_ptp_queue(port, 1);
 }
 
-static void mvpp2_isr_handle_link(struct mvpp2_port *port, bool link)
+static void mvpp2_isr_handle_link(struct mvpp2_port *port,
+				  struct phylink_pcs *pcs, bool link)
 {
 	struct net_device *dev = port->dev;
 
 	if (port->phylink) {
-		phylink_mac_change(port->phylink, link);
+		phylink_pcs_change(pcs, link);
 		return;
 	}
 
@@ -3472,7 +3473,7 @@ static void mvpp2_isr_handle_xlg(struct mvpp2_port *port)
 	if (val & MVPP22_XLG_INT_STAT_LINK) {
 		val = readl(port->base + MVPP22_XLG_STATUS);
 		link = (val & MVPP22_XLG_STATUS_LINK_UP);
-		mvpp2_isr_handle_link(port, link);
+		mvpp2_isr_handle_link(port, &port->pcs_xlg, link);
 	}
 }
 
@@ -3488,7 +3489,7 @@ static void mvpp2_isr_handle_gmac_internal(struct mvpp2_port *port)
 		if (val & MVPP22_GMAC_INT_STAT_LINK) {
 			val = readl(port->base + MVPP2_GMAC_STATUS0);
 			link = (val & MVPP2_GMAC_STATUS0_LINK_UP);
-			mvpp2_isr_handle_link(port, link);
+			mvpp2_isr_handle_link(port, &port->pcs_gmac, link);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 7c9faa714a10..549436efc204 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1096,7 +1096,7 @@ static int octep_change_mtu(struct net_device *netdev, int new_mtu)
 				     true);
 	if (!err) {
 		oct->link_info.mtu = new_mtu;
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	}
 
 	return err;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index dd49d0b8b494..7e6771c9cdbb 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -881,7 +881,7 @@ static int octep_vf_change_mtu(struct net_device *netdev, int new_mtu)
 	err = octep_vf_mbox_set_mtu(oct, new_mtu);
 	if (!err) {
 		oct->link_info.mtu = new_mtu;
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	}
 	return err;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index b86f3224f0b7..27935c54b91b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -24,6 +24,8 @@
 #define DRV_NAME	"Marvell-CGX/RPM"
 #define DRV_STRING      "Marvell CGX/RPM Driver"
 
+#define CGX_RX_STAT_GLOBAL_INDEX	9
+
 static LIST_HEAD(cgx_list);
 
 /* Convert firmware speed encoding to user format(Mbps) */
@@ -701,6 +703,30 @@ u64 cgx_features_get(void *cgxd)
 	return ((struct cgx *)cgxd)->hw_features;
 }
 
+int cgx_stats_reset(void *cgxd, int lmac_id)
+{
+	struct cgx *cgx = cgxd;
+	int stat_id;
+
+	if (!is_lmac_valid(cgx, lmac_id))
+		return -ENODEV;
+
+	for (stat_id = 0 ; stat_id < CGX_RX_STATS_COUNT; stat_id++) {
+		if (stat_id >= CGX_RX_STAT_GLOBAL_INDEX)
+		/* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+			cgx_write(cgx, 0,
+				  (CGXX_CMRX_RX_STAT0 + (stat_id * 8)), 0);
+		else
+			cgx_write(cgx, lmac_id,
+				  (CGXX_CMRX_RX_STAT0 + (stat_id * 8)), 0);
+	}
+
+	for (stat_id = 0 ; stat_id < CGX_TX_STATS_COUNT; stat_id++)
+		cgx_write(cgx, lmac_id, CGXX_CMRX_TX_STAT0 + (stat_id * 8), 0);
+
+	return 0;
+}
+
 static int cgx_set_fec_stats_count(struct cgx_link_user_info *linfo)
 {
 	if (!linfo->fec)
@@ -1788,6 +1814,7 @@ static struct mac_ops	cgx_mac_ops    = {
 	.pfc_config =                   cgx_lmac_pfc_config,
 	.mac_get_pfc_frm_cfg   =        cgx_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			cgx_lmac_reset,
+	.mac_stats_reset       =	cgx_stats_reset,
 };
 
 static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 6f7d1dee5830..dc9ace30554a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -141,6 +141,7 @@ int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id);
 int cgx_lmac_evh_unregister(void *cgxd, int lmac_id);
 int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat);
 int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat);
+int cgx_stats_reset(void *cgxd, int lmac_id);
 int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
 int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable);
 int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
index 0b4cba03f2e8..9ffc6790c513 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h
@@ -132,6 +132,7 @@ struct mac_ops {
 	/* FEC stats */
 	int			(*get_fec_stats)(void *cgxd, int lmac_id,
 						 struct cgx_fec_stats_rsp *rsp);
+	int			(*mac_stats_reset)(void *cgxd, int lmac_id);
 };
 
 struct cgx {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index eb2a20b5a0d0..4a77f6fe2622 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -174,6 +174,7 @@ M(CGX_FEC_STATS,	0x217, cgx_fec_stats, msg_req, cgx_fec_stats_rsp) \
 M(CGX_SET_LINK_MODE,	0x218, cgx_set_link_mode, cgx_set_link_mode_req,\
 			       cgx_set_link_mode_rsp)	\
 M(CGX_GET_PHY_FEC_STATS, 0x219, cgx_get_phy_fec_stats, msg_req, msg_rsp) \
+M(CGX_STATS_RST,	0x21A, cgx_stats_rst, msg_req, msg_rsp)		\
 M(CGX_FEATURES_GET,	0x21B, cgx_features_get, msg_req,		\
 			       cgx_features_info_msg)			\
 M(RPM_STATS,		0x21C, rpm_stats, msg_req, rpm_stats_rsp)	\
@@ -1213,10 +1214,8 @@ struct nix_bp_cfg_req {
 	/* bpid_per_chan = 1 assigns separate bp id for each channel */
 };
 
-/* PF can be mapped to either CGX or LBK interface,
- * so maximum 64 channels are possible.
- */
-#define NIX_MAX_BPID_CHAN	64
+/* Maximum channels any single NIX interface can have */
+#define NIX_MAX_BPID_CHAN	256
 struct nix_bp_cfg_rsp {
 	struct mbox_msghdr hdr;
 	u16	chan_bpid[NIX_MAX_BPID_CHAN]; /* Channel and bpid mapping */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index 76218f1cb459..1b34cf9c9703 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -38,6 +38,7 @@ static struct mac_ops		rpm_mac_ops   = {
 	.pfc_config =                   rpm_lmac_pfc_config,
 	.mac_get_pfc_frm_cfg   =        rpm_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			rpm_lmac_reset,
+	.mac_stats_reset		 =	  rpm_stats_reset,
 };
 
 static struct mac_ops		rpm2_mac_ops   = {
@@ -70,6 +71,7 @@ static struct mac_ops		rpm2_mac_ops   = {
 	.pfc_config =                   rpm_lmac_pfc_config,
 	.mac_get_pfc_frm_cfg   =        rpm_lmac_get_pfc_frm_cfg,
 	.mac_reset   =			rpm_lmac_reset,
+	.mac_stats_reset	    =	rpm_stats_reset,
 };
 
 bool is_dev_rpm2(void *rpmd)
@@ -443,6 +445,21 @@ int rpm_get_tx_stats(void *rpmd, int lmac_id, int idx, u64 *tx_stat)
 	return 0;
 }
 
+int rpm_stats_reset(void *rpmd, int lmac_id)
+{
+	rpm_t *rpm = rpmd;
+	u64 cfg;
+
+	if (!is_lmac_valid(rpm, lmac_id))
+		return -ENODEV;
+
+	cfg = rpm_read(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL);
+	cfg |= RPMX_CMD_CLEAR_TX | RPMX_CMD_CLEAR_RX | BIT_ULL(lmac_id);
+	rpm_write(rpm, 0, RPMX_MTI_STAT_STATN_CONTROL, cfg);
+
+	return 0;
+}
+
 u8 rpm_get_lmac_type(void *rpmd, int lmac_id)
 {
 	rpm_t *rpm = rpmd;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
index b79cfbc6f877..34b11deb0f3c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h
@@ -85,6 +85,8 @@
 #define RPMX_MTI_STAT_STATN_CONTROL			0x10018
 #define RPMX_MTI_STAT_DATA_HI_CDC			0x10038
 #define RPMX_RSFEC_RX_CAPTURE				BIT_ULL(27)
+#define RPMX_CMD_CLEAR_RX				BIT_ULL(30)
+#define RPMX_CMD_CLEAR_TX				BIT_ULL(31)
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_2		0x40050
 #define RPMX_MTI_RSFEC_STAT_COUNTER_CAPTURE_3		0x40058
 #define RPMX_MTI_FCFECX_VL0_CCW_LO			0x38618
@@ -134,4 +136,5 @@ int rpm2_get_nr_lmacs(void *rpmd);
 bool is_dev_rpm2(void *rpmd);
 int rpm_get_fec_stats(void *cgxd, int lmac_id, struct cgx_fec_stats_rsp *rsp);
 int rpm_lmac_reset(void *rpmd, int lmac_id, u8 pf_req_flr);
+int rpm_stats_reset(void *rpmd, int lmac_id);
 #endif /* RPM_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index e9bf9231b018..266ecbc1b97a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -604,6 +604,35 @@ int rvu_mbox_handler_rpm_stats(struct rvu *rvu, struct msg_req *req,
 	return rvu_lmac_get_stats(rvu, req, (void *)rsp);
 }
 
+int rvu_mbox_handler_cgx_stats_rst(struct rvu *rvu, struct msg_req *req,
+				   struct msg_rsp *rsp)
+{
+	int pf = rvu_get_pf(req->hdr.pcifunc);
+	struct rvu_pfvf	*parent_pf;
+	struct mac_ops *mac_ops;
+	u8 cgx_idx, lmac;
+	void *cgxd;
+
+	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+		return LMAC_AF_ERR_PERM_DENIED;
+
+	parent_pf = &rvu->pf[pf];
+	/* To ensure reset cgx stats won't affect VF stats,
+	 *  check if it used by only PF interface.
+	 *  If not, return
+	 */
+	if (parent_pf->cgx_users > 1) {
+		dev_info(rvu->dev, "CGX busy, could not reset statistics\n");
+		return 0;
+	}
+
+	rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac);
+	cgxd = rvu_cgx_pdata(cgx_idx, rvu);
+	mac_ops = get_mac_ops(cgxd);
+
+	return mac_ops->mac_stats_reset(cgxd, lmac);
+}
+
 int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu,
 				   struct msg_req *req,
 				   struct cgx_fec_stats_rsp *rsp)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 96c04f7d93f8..7498ab429963 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1202,7 +1202,8 @@ static int rvu_af_dl_dwrr_mtu_validate(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_dwrr_mtu_set(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1256,7 +1257,8 @@ static int rvu_af_npc_exact_feature_get(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_npc_exact_feature_disable(struct devlink *devlink, u32 id,
-					    struct devlink_param_gset_ctx *ctx)
+					    struct devlink_param_gset_ctx *ctx,
+					    struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1310,7 +1312,8 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_get(struct devlink *devlink, u32
 }
 
 static int rvu_af_dl_npc_mcam_high_zone_percent_set(struct devlink *devlink, u32 id,
-						    struct devlink_param_gset_ctx *ctx)
+						    struct devlink_param_gset_ctx *ctx,
+						    struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1367,7 +1370,8 @@ static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_nix_maxlf_set(struct devlink *devlink, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index c181e7aa9eb6..150635de2bd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -1187,6 +1187,8 @@ static int npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 			action.pf_func = target;
 			action.op = NIX_RX_ACTIONOP_UCAST;
 		}
+		if (req->match_id)
+			action.match_id = req->match_id;
 	}
 
 	entry->action = *(u64 *)&action;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 7e16a341ec58..24fbbef265a6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -363,6 +363,7 @@ struct otx2_flow_config {
 	struct list_head	flow_list;
 	u32			dmacflt_max_flows;
 	u16                     max_flows;
+	refcount_t		mark_flows;
 	struct list_head	flow_list_tc;
 	bool			ntuple;
 };
@@ -465,6 +466,7 @@ struct otx2_nic {
 #define OTX2_FLAG_DMACFLTR_SUPPORT		BIT_ULL(14)
 #define OTX2_FLAG_PTP_ONESTEP_SYNC		BIT_ULL(15)
 #define OTX2_FLAG_ADPTV_INT_COAL_ENABLED BIT_ULL(16)
+#define OTX2_FLAG_TC_MARK_ENABLED		BIT_ULL(17)
 	u64			flags;
 	u64			*cq_op_addr;
 
@@ -961,6 +963,7 @@ void otx2_get_mac_from_af(struct net_device *netdev);
 void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx);
 int otx2_config_pause_frm(struct otx2_nic *pfvf);
 void otx2_setup_segmentation(struct otx2_nic *pfvf);
+int otx2_reset_mac_stats(struct otx2_nic *pfvf);
 
 /* RVU block related APIs */
 int otx2_attach_npa_nix(struct otx2_nic *pfvf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 4e1130496573..99ddf31269d9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -32,7 +32,8 @@ static int otx2_dl_mcam_count_validate(struct devlink *devlink, u32 id,
 }
 
 static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
 	struct otx2_nic *pfvf = otx2_dl->pfvf;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 97a71e9b8563..bc5819237ed7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -252,6 +252,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 
 	pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT;
 
+	refcount_set(&flow_cfg->mark_flows, 1);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 3f46d5e0fb2e..f5bce3e326cc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -67,7 +67,7 @@ static int otx2_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_info(netdev, "Changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (if_up)
 		err = otx2_open(netdev);
@@ -450,7 +450,6 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 	struct mbox_msghdr *msg = NULL;
 	int offset, vf_idx, id, err;
 	struct otx2_mbox_dev *mdev;
-	struct mbox_hdr *req_hdr;
 	struct otx2_mbox *mbox;
 	struct mbox *vf_mbox;
 	struct otx2_nic *pf;
@@ -461,9 +460,8 @@ static void otx2_pfvf_mbox_handler(struct work_struct *work)
 
 	mbox = &pf->mbox_pfvf[0].mbox;
 	mdev = &mbox->dev[vf_idx];
-	req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
 
-	offset = ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
+	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
 	for (id = 0; id < vf_mbox->num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + mbox->rx_start +
@@ -494,7 +492,6 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 	struct otx2_nic *pf = vf_mbox->pfvf;
 	struct otx2_mbox_dev *mdev;
 	int offset, id, vf_idx = 0;
-	struct mbox_hdr *rsp_hdr;
 	struct mbox_msghdr *msg;
 	struct otx2_mbox *mbox;
 
@@ -502,8 +499,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 	mbox = &pf->mbox_pfvf[0].mbox_up;
 	mdev = &mbox->dev[vf_idx];
 
-	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
-	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
+	offset = mbox->rx_start + ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
 	for (id = 0; id < vf_mbox->up_num_msgs; id++) {
 		msg = mdev->mbase + offset;
@@ -1150,6 +1146,23 @@ static int otx2_cgx_config_linkevents(struct otx2_nic *pf, bool enable)
 	return err;
 }
 
+int otx2_reset_mac_stats(struct otx2_nic *pfvf)
+{
+	struct msg_req *req;
+	int err;
+
+	mutex_lock(&pfvf->mbox.lock);
+	req = otx2_mbox_alloc_msg_cgx_stats_rst(&pfvf->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+
+	err = otx2_sync_mbox_msg(&pfvf->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+	return err;
+}
+
 static int otx2_cgx_config_loopback(struct otx2_nic *pf, bool enable)
 {
 	struct msg_req *msg;
@@ -1873,9 +1886,17 @@ int otx2_open(struct net_device *netdev)
 	vec = pf->hw.nix_msixoff + NIX_LF_CINT_VEC_START;
 	for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) {
 		irq_name = &pf->hw.irq_name[vec * NAME_SIZE];
+		int name_len;
 
-		snprintf(irq_name, NAME_SIZE, "%s-rxtx-%d", pf->netdev->name,
-			 qidx);
+		name_len = snprintf(irq_name, NAME_SIZE, "%s-rxtx-%d",
+				    pf->netdev->name, qidx);
+		if (name_len >= NAME_SIZE) {
+			dev_err(pf->dev,
+				"RVUPF%d: IRQ registration failed for CQ%d, irq name is too long\n",
+				rvu_get_pf(pf->pcifunc), qidx);
+			err = -EINVAL;
+			goto err_free_cints;
+		}
 
 		err = request_irq(pci_irq_vector(pf->pdev, vec),
 				  otx2_cq_intr_handler, 0, irq_name,
@@ -3038,6 +3059,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	netdev->min_mtu = OTX2_MIN_MTU;
 	netdev->max_mtu = otx2_get_max_mtu(pf);
 
+	/* reset CGX/RPM MAC stats */
+	otx2_reset_mac_stats(pf);
+
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(dev, "Failed to register netdevice\n");
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index f4655a8c0705..e63cc1eb6d89 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -511,7 +511,15 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			nr_police++;
 			break;
 		case FLOW_ACTION_MARK:
+			if (act->mark & ~OTX2_RX_MATCH_ID_MASK) {
+				NL_SET_ERR_MSG_MOD(extack, "Bad flow mark, only 16 bit supported");
+				return -EOPNOTSUPP;
+			}
 			mark = act->mark;
+			req->match_id = mark & OTX2_RX_MATCH_ID_MASK;
+			req->op = NIX_RX_ACTION_DEFAULT;
+			nic->flags |= OTX2_FLAG_TC_MARK_ENABLED;
+			refcount_inc(&nic->flow_cfg->mark_flows);
 			break;
 
 		case FLOW_ACTION_RX_QUEUE_MAPPING:
@@ -692,10 +700,6 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 		u32 val;
 
 		flow_rule_match_control(rule, &match);
-		if (match.mask->flags & FLOW_DIS_FIRST_FRAG) {
-			NL_SET_ERR_MSG_MOD(extack, "HW doesn't support frag first/later");
-			return -EOPNOTSUPP;
-		}
 
 		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			val = match.key->flags & FLOW_DIS_IS_FRAGMENT;
@@ -713,6 +717,10 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 				return -EOPNOTSUPP;
 			}
 		}
+
+		if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT,
+						     match.mask->flags, extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
@@ -1187,6 +1195,11 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 		return -EINVAL;
 	}
 
+	/* Disable TC MARK flag if they are no rules with skbedit mark action */
+	if (flow_node->req.match_id)
+		if (!refcount_dec_and_test(&flow_cfg->mark_flows))
+			nic->flags &= ~OTX2_FLAG_TC_MARK_ENABLED;
+
 	if (flow_node->is_act_police) {
 		__clear_bit(flow_node->rq, &nic->rq_bmap);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index f828d32737af..a16e9f244117 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -380,6 +380,9 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	if (pfvf->netdev->features & NETIF_F_RXCSUM)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
+	if (pfvf->flags & OTX2_FLAG_TC_MARK_ENABLED)
+		skb->mark = parse->match_id;
+
 	skb_mark_for_recycle(skb);
 
 	napi_gro_frags(napi);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index a82ffca8ce1b..3f1d2655ff77 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -62,6 +62,9 @@
 #define CQ_OP_STAT_OP_ERR       63
 #define CQ_OP_STAT_CQ_ERR       46
 
+/* Packet mark mask */
+#define OTX2_RX_MATCH_ID_MASK 0x0000ffff
+
 struct queue_stats {
 	u64	bytes;
 	u64	pkts;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index cf0aa16d7540..99fcc5661674 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -456,7 +456,7 @@ static int otx2vf_change_mtu(struct net_device *netdev, int new_mtu)
 
 	netdev_info(netdev, "Changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (if_up)
 		err = otx2vf_open(netdev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 1723e9912ae0..070711df612e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -545,6 +545,20 @@ otx2_qos_sw_create_leaf_node(struct otx2_nic *pfvf,
 	return node;
 }
 
+static struct otx2_qos_node
+*otx2_sw_node_find_by_qid(struct otx2_nic *pfvf, u16 qid)
+{
+	struct otx2_qos_node *node = NULL;
+	int bkt;
+
+	hash_for_each(pfvf->qos.qos_hlist, bkt, node, hlist) {
+		if (node->qid == qid)
+			break;
+	}
+
+	return node;
+}
+
 static struct otx2_qos_node *
 otx2_sw_node_find(struct otx2_nic *pfvf, u32 classid)
 {
@@ -917,6 +931,7 @@ static void otx2_qos_enadis_sq(struct otx2_nic *pfvf,
 		otx2_qos_disable_sq(pfvf, qid);
 
 	pfvf->qos.qid_to_sqmap[qid] = node->schq;
+	otx2_qos_txschq_config(pfvf, node);
 	otx2_qos_enable_sq(pfvf, qid);
 }
 
@@ -1475,13 +1490,45 @@ out:
 	return ret;
 }
 
+static int otx2_qos_cur_leaf_nodes(struct otx2_nic *pfvf)
+{
+	int last = find_last_bit(pfvf->qos.qos_sq_bmap, pfvf->hw.tc_tx_queues);
+
+	return last ==  pfvf->hw.tc_tx_queues ? 0 : last + 1;
+}
+
+static void otx2_reset_qdisc(struct net_device *dev, u16 qid)
+{
+	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, qid);
+	struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
+
+	if (!qdisc)
+		return;
+
+	spin_lock_bh(qdisc_lock(qdisc));
+	qdisc_reset(qdisc);
+	spin_unlock_bh(qdisc_lock(qdisc));
+}
+
+static void otx2_cfg_smq(struct otx2_nic *pfvf, struct otx2_qos_node *node,
+			 int qid)
+{
+	struct otx2_qos_node *tmp;
+
+	list_for_each_entry(tmp, &node->child_schq_list, list)
+		if (tmp->level == NIX_TXSCH_LVL_MDQ) {
+			otx2_qos_txschq_config(pfvf, tmp);
+			pfvf->qos.qid_to_sqmap[qid] = tmp->schq;
+		}
+}
+
 static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid,
 			     struct netlink_ext_ack *extack)
 {
 	struct otx2_qos_node *node, *parent;
 	int dwrr_del_node = false;
+	u16 qid, moved_qid;
 	u64 prio;
-	u16 qid;
 
 	netdev_dbg(pfvf->netdev, "TC_HTB_LEAF_DEL classid %04x\n", *classid);
 
@@ -1517,6 +1564,37 @@ static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid,
 	if (!parent->child_static_cnt)
 		parent->max_static_prio = 0;
 
+	moved_qid = otx2_qos_cur_leaf_nodes(pfvf);
+
+	/* last node just deleted */
+	if (moved_qid == 0 || moved_qid == qid)
+		return 0;
+
+	moved_qid--;
+
+	node = otx2_sw_node_find_by_qid(pfvf, moved_qid);
+	if (!node)
+		return 0;
+
+	/* stop traffic to the old queue and disable
+	 * SQ associated with it
+	 */
+	node->qid =  OTX2_QOS_QID_INNER;
+	__clear_bit(moved_qid, pfvf->qos.qos_sq_bmap);
+	otx2_qos_disable_sq(pfvf, moved_qid);
+
+	otx2_reset_qdisc(pfvf->netdev, pfvf->hw.tx_queues + moved_qid);
+
+	/* enable SQ associated with qid and
+	 * update the node
+	 */
+	otx2_cfg_smq(pfvf, node, qid);
+
+	otx2_qos_enable_sq(pfvf, qid);
+	__set_bit(qid, pfvf->qos.qos_sq_bmap);
+	node->qid = qid;
+
+	*classid = node->classid;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
index 8b9455d8a4f7..418101a93149 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
@@ -229,6 +229,10 @@ static int prestera_flower_parse(struct prestera_flow_block *block,
 
 		flow_rule_match_control(f_rule, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_BASIC)) {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
index fc6f7d2746e8..197198ba61b1 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
@@ -419,15 +419,6 @@ struct prestera_msg_vtcam_destroy_req {
 	__le32 vtcam_id;
 };
 
-struct prestera_msg_vtcam_rule_add_req {
-	struct prestera_msg_cmd cmd;
-	__le32 key[__PRESTERA_ACL_RULE_MATCH_TYPE_MAX];
-	__le32 keymask[__PRESTERA_ACL_RULE_MATCH_TYPE_MAX];
-	__le32 vtcam_id;
-	__le32 prio;
-	__le32 n_act;
-};
-
 struct prestera_msg_vtcam_rule_del_req {
 	struct prestera_msg_cmd cmd;
 	__le32 vtcam_id;
@@ -471,6 +462,16 @@ struct prestera_msg_acl_action {
 	};
 };
 
+struct prestera_msg_vtcam_rule_add_req {
+	struct prestera_msg_cmd cmd;
+	__le32 key[__PRESTERA_ACL_RULE_MATCH_TYPE_MAX];
+	__le32 keymask[__PRESTERA_ACL_RULE_MATCH_TYPE_MAX];
+	__le32 vtcam_id;
+	__le32 prio;
+	__le32 n_act;
+	struct prestera_msg_acl_action actions_msg[] __counted_by_le(n_act);
+};
+
 struct prestera_msg_counter_req {
 	struct prestera_msg_cmd cmd;
 	__le32 client;
@@ -702,12 +703,6 @@ struct prestera_msg_flood_domain_destroy_req {
 	__le32 flood_domain_idx;
 };
 
-struct prestera_msg_flood_domain_ports_set_req {
-	struct prestera_msg_cmd cmd;
-	__le32 flood_domain_idx;
-	__le32 ports_num;
-};
-
 struct prestera_msg_flood_domain_ports_reset_req {
 	struct prestera_msg_cmd cmd;
 	__le32 flood_domain_idx;
@@ -725,6 +720,13 @@ struct prestera_msg_flood_domain_port {
 	__le16 port_type;
 };
 
+struct prestera_msg_flood_domain_ports_set_req {
+	struct prestera_msg_cmd cmd;
+	__le32 flood_domain_idx;
+	__le32 ports_num;
+	struct prestera_msg_flood_domain_port ports[] __counted_by_le(ports_num);
+};
+
 struct prestera_msg_mdb_create_req {
 	struct prestera_msg_cmd cmd;
 	__le32 flood_domain_idx;
@@ -1371,23 +1373,18 @@ int prestera_hw_vtcam_rule_add(struct prestera_switch *sw,
 			       struct prestera_acl_hw_action_info *act,
 			       u8 n_act, u32 *rule_id)
 {
-	struct prestera_msg_acl_action *actions_msg;
 	struct prestera_msg_vtcam_rule_add_req *req;
 	struct prestera_msg_vtcam_resp resp;
-	void *buff;
-	u32 size;
+	size_t size;
 	int err;
 	u8 i;
 
-	size = sizeof(*req) + sizeof(*actions_msg) * n_act;
-
-	buff = kzalloc(size, GFP_KERNEL);
-	if (!buff)
+	size = struct_size(req, actions_msg, n_act);
+	req = kzalloc(size, GFP_KERNEL);
+	if (!req)
 		return -ENOMEM;
 
-	req = buff;
 	req->n_act = __cpu_to_le32(n_act);
-	actions_msg = buff + sizeof(*req);
 
 	/* put acl matches into the message */
 	memcpy(req->key, key, sizeof(req->key));
@@ -1395,7 +1392,7 @@ int prestera_hw_vtcam_rule_add(struct prestera_switch *sw,
 
 	/* put acl actions into the message */
 	for (i = 0; i < n_act; i++) {
-		err = prestera_acl_rule_add_put_action(&actions_msg[i],
+		err = prestera_acl_rule_add_put_action(&req->actions_msg[i],
 						       &act[i]);
 		if (err)
 			goto free_buff;
@@ -1411,7 +1408,7 @@ int prestera_hw_vtcam_rule_add(struct prestera_switch *sw,
 
 	*rule_id = __le32_to_cpu(resp.rule_id);
 free_buff:
-	kfree(buff);
+	kfree(req);
 	return err;
 }
 
@@ -2461,14 +2458,13 @@ int prestera_hw_flood_domain_ports_set(struct prestera_flood_domain *domain)
 {
 	struct prestera_flood_domain_port *flood_domain_port;
 	struct prestera_msg_flood_domain_ports_set_req *req;
-	struct prestera_msg_flood_domain_port *ports;
 	struct prestera_switch *sw = domain->sw;
 	struct prestera_port *port;
 	u32 ports_num = 0;
-	int buf_size;
-	void *buff;
+	size_t buf_size;
 	u16 lag_id;
 	int err;
+	int i = 0;
 
 	list_for_each_entry(flood_domain_port, &domain->flood_domain_port_list,
 			    flood_domain_port_node)
@@ -2477,15 +2473,11 @@ int prestera_hw_flood_domain_ports_set(struct prestera_flood_domain *domain)
 	if (!ports_num)
 		return -EINVAL;
 
-	buf_size = sizeof(*req) + sizeof(*ports) * ports_num;
-
-	buff = kmalloc(buf_size, GFP_KERNEL);
-	if (!buff)
+	buf_size = struct_size(req, ports, ports_num);
+	req = kmalloc(buf_size, GFP_KERNEL);
+	if (!req)
 		return -ENOMEM;
 
-	req = buff;
-	ports = buff + sizeof(*req);
-
 	req->flood_domain_idx = __cpu_to_le32(domain->idx);
 	req->ports_num = __cpu_to_le32(ports_num);
 
@@ -2494,31 +2486,30 @@ int prestera_hw_flood_domain_ports_set(struct prestera_flood_domain *domain)
 		if (netif_is_lag_master(flood_domain_port->dev)) {
 			if (prestera_lag_id(sw, flood_domain_port->dev,
 					    &lag_id)) {
-				kfree(buff);
+				kfree(req);
 				return -EINVAL;
 			}
 
-			ports->port_type =
+			req->ports[i].port_type =
 				__cpu_to_le16(PRESTERA_HW_FLOOD_DOMAIN_PORT_TYPE_LAG);
-			ports->lag_id = __cpu_to_le16(lag_id);
+			req->ports[i].lag_id = __cpu_to_le16(lag_id);
 		} else {
 			port = prestera_port_dev_lower_find(flood_domain_port->dev);
 
-			ports->port_type =
+			req->ports[i].port_type =
 				__cpu_to_le16(PRESTERA_HW_FDB_ENTRY_TYPE_REG_PORT);
-			ports->dev_num = __cpu_to_le32(port->dev_id);
-			ports->port_num = __cpu_to_le32(port->hw_id);
+			req->ports[i].dev_num = __cpu_to_le32(port->dev_id);
+			req->ports[i].port_num = __cpu_to_le32(port->hw_id);
 		}
 
-		ports->vid = __cpu_to_le16(flood_domain_port->vid);
-
-		ports++;
+		req->ports[i].vid = __cpu_to_le16(flood_domain_port->vid);
+		i++;
 	}
 
 	err = prestera_cmd(sw, PRESTERA_CMD_TYPE_FLOOD_DOMAIN_PORTS_SET,
 			   &req->cmd, buf_size);
 
-	kfree(buff);
+	kfree(req);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 4fb886c57cd7..63ae01954dfc 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -489,7 +489,7 @@ static int prestera_port_change_mtu(struct net_device *dev, int mtu)
 	if (err)
 		return err;
 
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 
 	return 0;
 }
@@ -821,7 +821,7 @@ static void prestera_port_handle_event(struct prestera_switch *sw,
 
 		if (port->state_mac.oper) {
 			if (port->phy_link)
-				phylink_mac_change(port->phy_link, true);
+				phylink_pcs_change(&port->phylink_pcs, true);
 			else
 				netif_carrier_on(port->dev);
 
@@ -829,7 +829,7 @@ static void prestera_port_handle_event(struct prestera_switch *sw,
 				queue_delayed_work(prestera_wq, caching_dw, 0);
 		} else {
 			if (port->phy_link)
-				phylink_mac_change(port->phy_link, false);
+				phylink_pcs_change(&port->phylink_pcs, false);
 			else if (netif_running(port->dev) && netif_carrier_ok(port->dev))
 				netif_carrier_off(port->dev);
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
index cc2a9ae794be..39d9bf82c115 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
@@ -96,7 +96,7 @@ struct prestera_sdma {
 	struct dma_pool *desc_pool;
 	struct work_struct tx_work;
 	struct napi_struct rx_napi;
-	struct net_device napi_dev;
+	struct net_device *napi_dev;
 	u32 map_addr;
 	u64 dma_mask;
 	/* protect SDMA with concurrent access from multiple CPUs */
@@ -654,13 +654,21 @@ static int prestera_sdma_switch_init(struct prestera_switch *sw)
 	if (err)
 		goto err_evt_register;
 
-	init_dummy_netdev(&sdma->napi_dev);
+	sdma->napi_dev = alloc_netdev_dummy(0);
+	if (!sdma->napi_dev) {
+		dev_err(dev, "not able to initialize dummy device\n");
+		err = -ENOMEM;
+		goto err_alloc_dummy;
+	}
 
-	netif_napi_add(&sdma->napi_dev, &sdma->rx_napi, prestera_sdma_rx_poll);
+	netif_napi_add(sdma->napi_dev, &sdma->rx_napi, prestera_sdma_rx_poll);
 	napi_enable(&sdma->rx_napi);
 
 	return 0;
 
+err_alloc_dummy:
+	prestera_hw_event_handler_unregister(sw, PRESTERA_EVENT_TYPE_RXTX,
+					     prestera_rxtx_handle_event);
 err_evt_register:
 err_tx_init:
 	prestera_sdma_tx_fini(sdma);
@@ -677,6 +685,7 @@ static void prestera_sdma_switch_fini(struct prestera_switch *sw)
 
 	napi_disable(&sdma->rx_napi);
 	netif_napi_del(&sdma->rx_napi);
+	free_netdev(sdma->napi_dev);
 	prestera_hw_event_handler_unregister(sw, PRESTERA_EVENT_TYPE_RXTX,
 					     prestera_rxtx_handle_event);
 	prestera_sdma_tx_fini(sdma);
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index dd6ca2e4fd51..1a59c952aa01 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1188,7 +1188,7 @@ static int pxa168_eth_change_mtu(struct net_device *dev, int mtu)
 {
 	struct pxa168_eth_private *pep = netdev_priv(dev);
 
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 	set_port_config_ext(pep);
 
 	if (!netif_running(dev))
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 1b43704baceb..fcfb34561882 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -2905,13 +2905,13 @@ static int skge_change_mtu(struct net_device *dev, int new_mtu)
 	int err;
 
 	if (!netif_running(dev)) {
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		return 0;
 	}
 
 	skge_down(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	err = skge_up(dev);
 	if (err)
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 07720841a8d7..a7a16eac1891 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -34,6 +34,7 @@
 #include <linux/mii.h>
 #include <linux/of_net.h>
 #include <linux/dmi.h>
+#include <linux/skbuff_ref.h>
 
 #include <asm/irq.h>
 
@@ -2383,7 +2384,7 @@ static int sky2_change_mtu(struct net_device *dev, int new_mtu)
 	u32 imask;
 
 	if (!netif_running(dev)) {
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		netdev_update_features(dev);
 		return 0;
 	}
@@ -2406,7 +2407,7 @@ static int sky2_change_mtu(struct net_device *dev, int new_mtu)
 	sky2_rx_stop(sky2);
 	sky2_rx_clean(sky2);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	netdev_update_features(dev);
 
 	mode = DATA_BLIND_VAL(DATA_BLIND_DEF) |	GM_SMOD_VLAN_ENA;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index caa13b9cedff..cae46290a7ae 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -110,16 +110,16 @@ static const struct mtk_reg_map mt7986_reg_map = {
 	.tx_irq_mask		= 0x461c,
 	.tx_irq_status		= 0x4618,
 	.pdma = {
-		.rx_ptr		= 0x6100,
-		.rx_cnt_cfg	= 0x6104,
-		.pcrx_ptr	= 0x6108,
-		.glo_cfg	= 0x6204,
-		.rst_idx	= 0x6208,
-		.delay_irq	= 0x620c,
-		.irq_status	= 0x6220,
-		.irq_mask	= 0x6228,
-		.adma_rx_dbg0	= 0x6238,
-		.int_grp	= 0x6250,
+		.rx_ptr		= 0x4100,
+		.rx_cnt_cfg	= 0x4104,
+		.pcrx_ptr	= 0x4108,
+		.glo_cfg	= 0x4204,
+		.rst_idx	= 0x4208,
+		.delay_irq	= 0x420c,
+		.irq_status	= 0x4220,
+		.irq_mask	= 0x4228,
+		.adma_rx_dbg0	= 0x4238,
+		.int_grp	= 0x4250,
 	},
 	.qdma = {
 		.qtx_cfg	= 0x4400,
@@ -1107,7 +1107,7 @@ static bool mtk_rx_get_desc(struct mtk_eth *eth, struct mtk_rx_dma_v2 *rxd,
 	rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
 	rxd->rxd3 = READ_ONCE(dma_rxd->rxd3);
 	rxd->rxd4 = READ_ONCE(dma_rxd->rxd4);
-	if (mtk_is_netsys_v2_or_greater(eth)) {
+	if (mtk_is_netsys_v3_or_greater(eth)) {
 		rxd->rxd5 = READ_ONCE(dma_rxd->rxd5);
 		rxd->rxd6 = READ_ONCE(dma_rxd->rxd6);
 	}
@@ -1139,7 +1139,7 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 		eth->scratch_ring = eth->sram_base;
 	else
 		eth->scratch_ring = dma_alloc_coherent(eth->dma_dev,
-						       cnt * soc->txrx.txd_size,
+						       cnt * soc->tx.desc_size,
 						       &eth->phy_scratch_ring,
 						       GFP_KERNEL);
 	if (unlikely(!eth->scratch_ring))
@@ -1155,17 +1155,17 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr)))
 		return -ENOMEM;
 
-	phy_ring_tail = eth->phy_scratch_ring + soc->txrx.txd_size * (cnt - 1);
+	phy_ring_tail = eth->phy_scratch_ring + soc->tx.desc_size * (cnt - 1);
 
 	for (i = 0; i < cnt; i++) {
 		dma_addr_t addr = dma_addr + i * MTK_QDMA_PAGE_SIZE;
 		struct mtk_tx_dma_v2 *txd;
 
-		txd = eth->scratch_ring + i * soc->txrx.txd_size;
+		txd = eth->scratch_ring + i * soc->tx.desc_size;
 		txd->txd1 = addr;
 		if (i < cnt - 1)
 			txd->txd2 = eth->phy_scratch_ring +
-				    (i + 1) * soc->txrx.txd_size;
+				    (i + 1) * soc->tx.desc_size;
 
 		txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE);
 		if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA))
@@ -1416,7 +1416,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	if (itxd == ring->last_free)
 		return -ENOMEM;
 
-	itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size);
+	itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size);
 	memset(itx_buf, 0, sizeof(*itx_buf));
 
 	txd_info.addr = dma_map_single(eth->dma_dev, skb->data, txd_info.size,
@@ -1457,7 +1457,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 
 			memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info));
 			txd_info.size = min_t(unsigned int, frag_size,
-					      soc->txrx.dma_max_len);
+					      soc->tx.dma_max_len);
 			txd_info.qid = queue;
 			txd_info.last = i == skb_shinfo(skb)->nr_frags - 1 &&
 					!(frag_size - txd_info.size);
@@ -1470,7 +1470,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 			mtk_tx_set_dma_desc(dev, txd, &txd_info);
 
 			tx_buf = mtk_desc_to_tx_buf(ring, txd,
-						    soc->txrx.txd_size);
+						    soc->tx.desc_size);
 			if (new_desc)
 				memset(tx_buf, 0, sizeof(*tx_buf));
 			tx_buf->data = (void *)MTK_DMA_DUMMY_DESC;
@@ -1513,7 +1513,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		int next_idx;
 
-		next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->txrx.txd_size),
+		next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->tx.desc_size),
 					 ring->dma_size);
 		mtk_w32(eth, next_idx, MT7628_TX_CTX_IDX0);
 	}
@@ -1522,7 +1522,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 
 err_dma:
 	do {
-		tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size);
+		tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size);
 
 		/* unmap dma */
 		mtk_tx_unmap(eth, tx_buf, NULL, false);
@@ -1547,7 +1547,7 @@ static int mtk_cal_txd_req(struct mtk_eth *eth, struct sk_buff *skb)
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			frag = &skb_shinfo(skb)->frags[i];
 			nfrags += DIV_ROUND_UP(skb_frag_size(frag),
-					       eth->soc->txrx.dma_max_len);
+					       eth->soc->tx.dma_max_len);
 		}
 	} else {
 		nfrags += skb_shinfo(skb)->nr_frags;
@@ -1654,7 +1654,7 @@ static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth)
 
 		ring = &eth->rx_ring[i];
 		idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size);
-		rxd = ring->dma + idx * eth->soc->txrx.rxd_size;
+		rxd = ring->dma + idx * eth->soc->rx.desc_size;
 		if (rxd->rxd2 & RX_DMA_DONE) {
 			ring->calc_idx_update = true;
 			return ring;
@@ -1710,7 +1710,7 @@ static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth,
 	if (IS_ERR(pp))
 		return pp;
 
-	err = __xdp_rxq_info_reg(xdp_q, &eth->dummy_dev, id,
+	err = __xdp_rxq_info_reg(xdp_q, eth->dummy_dev, id,
 				 eth->rx_napi.napi_id, PAGE_SIZE);
 	if (err < 0)
 		goto err_free_pp;
@@ -1822,7 +1822,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf,
 	}
 	htxd = txd;
 
-	tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->txrx.txd_size);
+	tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->tx.desc_size);
 	memset(tx_buf, 0, sizeof(*tx_buf));
 	htx_buf = tx_buf;
 
@@ -1841,7 +1841,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf,
 				goto unmap;
 
 			tx_buf = mtk_desc_to_tx_buf(ring, txd,
-						    soc->txrx.txd_size);
+						    soc->tx.desc_size);
 			memset(tx_buf, 0, sizeof(*tx_buf));
 			n_desc++;
 		}
@@ -1879,7 +1879,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf,
 	} else {
 		int idx;
 
-		idx = txd_to_idx(ring, txd, soc->txrx.txd_size);
+		idx = txd_to_idx(ring, txd, soc->tx.desc_size);
 		mtk_w32(eth, NEXT_DESP_IDX(idx, ring->dma_size),
 			MT7628_TX_CTX_IDX0);
 	}
@@ -1890,7 +1890,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf,
 
 unmap:
 	while (htxd != txd) {
-		tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->txrx.txd_size);
+		tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->tx.desc_size);
 		mtk_tx_unmap(eth, tx_buf, NULL, false);
 
 		htxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
@@ -2021,14 +2021,14 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			goto rx_done;
 
 		idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size);
-		rxd = ring->dma + idx * eth->soc->txrx.rxd_size;
+		rxd = ring->dma + idx * eth->soc->rx.desc_size;
 		data = ring->data[idx];
 
 		if (!mtk_rx_get_desc(eth, &trxd, rxd))
 			break;
 
 		/* find out which mac the packet come from. values start at 1 */
-		if (mtk_is_netsys_v2_or_greater(eth)) {
+		if (mtk_is_netsys_v3_or_greater(eth)) {
 			u32 val = RX_DMA_GET_SPORT_V2(trxd.rxd5);
 
 			switch (val) {
@@ -2140,7 +2140,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		skb->dev = netdev;
 		bytes += skb->len;
 
-		if (mtk_is_netsys_v2_or_greater(eth)) {
+		if (mtk_is_netsys_v3_or_greater(eth)) {
 			reason = FIELD_GET(MTK_RXD5_PPE_CPU_REASON, trxd.rxd5);
 			hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY;
 			if (hash != MTK_RXD5_FOE_ENTRY)
@@ -2156,7 +2156,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			rxdcsum = &trxd.rxd4;
 		}
 
-		if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid)
+		if (*rxdcsum & eth->soc->rx.dma_l4_valid)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
 			skb_checksum_none_assert(skb);
@@ -2280,7 +2280,7 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget,
 			break;
 
 		tx_buf = mtk_desc_to_tx_buf(ring, desc,
-					    eth->soc->txrx.txd_size);
+					    eth->soc->tx.desc_size);
 		if (!tx_buf->data)
 			break;
 
@@ -2331,7 +2331,7 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget,
 		}
 		mtk_tx_unmap(eth, tx_buf, &bq, true);
 
-		desc = ring->dma + cpu * eth->soc->txrx.txd_size;
+		desc = ring->dma + cpu * eth->soc->tx.desc_size;
 		ring->last_free = desc;
 		atomic_inc(&ring->free_count);
 
@@ -2421,7 +2421,7 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 	do {
 		int rx_done;
 
-		mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask,
+		mtk_w32(eth, eth->soc->rx.irq_done_mask,
 			reg_map->pdma.irq_status);
 		rx_done = mtk_poll_rx(napi, budget - rx_done_total, eth);
 		rx_done_total += rx_done;
@@ -2437,10 +2437,10 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 			return budget;
 
 	} while (mtk_r32(eth, reg_map->pdma.irq_status) &
-		 eth->soc->txrx.rx_irq_done_mask);
+		 eth->soc->rx.irq_done_mask);
 
 	if (napi_complete_done(napi, rx_done_total))
-		mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask);
+		mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask);
 
 	return rx_done_total;
 }
@@ -2449,7 +2449,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
 	struct mtk_tx_ring *ring = &eth->tx_ring;
-	int i, sz = soc->txrx.txd_size;
+	int i, sz = soc->tx.desc_size;
 	struct mtk_tx_dma_v2 *txd;
 	int ring_size;
 	u32 ofs, val;
@@ -2572,14 +2572,14 @@ static void mtk_tx_clean(struct mtk_eth *eth)
 	}
 	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && ring->dma) {
 		dma_free_coherent(eth->dma_dev,
-				  ring->dma_size * soc->txrx.txd_size,
+				  ring->dma_size * soc->tx.desc_size,
 				  ring->dma, ring->phys);
 		ring->dma = NULL;
 	}
 
 	if (ring->dma_pdma) {
 		dma_free_coherent(eth->dma_dev,
-				  ring->dma_size * soc->txrx.txd_size,
+				  ring->dma_size * soc->tx.desc_size,
 				  ring->dma_pdma, ring->phys_pdma);
 		ring->dma_pdma = NULL;
 	}
@@ -2634,15 +2634,15 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM) ||
 	    rx_flag != MTK_RX_FLAGS_NORMAL) {
 		ring->dma = dma_alloc_coherent(eth->dma_dev,
-					       rx_dma_size * eth->soc->txrx.rxd_size,
-					       &ring->phys, GFP_KERNEL);
+				rx_dma_size * eth->soc->rx.desc_size,
+				&ring->phys, GFP_KERNEL);
 	} else {
 		struct mtk_tx_ring *tx_ring = &eth->tx_ring;
 
 		ring->dma = tx_ring->dma + tx_ring_size *
-			    eth->soc->txrx.txd_size * (ring_no + 1);
+			    eth->soc->tx.desc_size * (ring_no + 1);
 		ring->phys = tx_ring->phys + tx_ring_size *
-			     eth->soc->txrx.txd_size * (ring_no + 1);
+			     eth->soc->tx.desc_size * (ring_no + 1);
 	}
 
 	if (!ring->dma)
@@ -2653,7 +2653,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 		dma_addr_t dma_addr;
 		void *data;
 
-		rxd = ring->dma + i * eth->soc->txrx.rxd_size;
+		rxd = ring->dma + i * eth->soc->rx.desc_size;
 		if (ring->page_pool) {
 			data = mtk_page_pool_get_buff(ring->page_pool,
 						      &dma_addr, GFP_KERNEL);
@@ -2690,7 +2690,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 
 		rxd->rxd3 = 0;
 		rxd->rxd4 = 0;
-		if (mtk_is_netsys_v2_or_greater(eth)) {
+		if (mtk_is_netsys_v3_or_greater(eth)) {
 			rxd->rxd5 = 0;
 			rxd->rxd6 = 0;
 			rxd->rxd7 = 0;
@@ -2744,7 +2744,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_
 			if (!ring->data[i])
 				continue;
 
-			rxd = ring->dma + i * eth->soc->txrx.rxd_size;
+			rxd = ring->dma + i * eth->soc->rx.desc_size;
 			if (!rxd->rxd1)
 				continue;
 
@@ -2761,7 +2761,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_
 
 	if (!in_sram && ring->dma) {
 		dma_free_coherent(eth->dma_dev,
-				  ring->dma_size * eth->soc->txrx.rxd_size,
+				  ring->dma_size * eth->soc->rx.desc_size,
 				  ring->dma, ring->phys);
 		ring->dma = NULL;
 	}
@@ -3124,7 +3124,7 @@ static void mtk_dma_free(struct mtk_eth *eth)
 			netdev_reset_queue(eth->netdev[i]);
 	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
 		dma_free_coherent(eth->dma_dev,
-				  MTK_QDMA_RING_SIZE * soc->txrx.txd_size,
+				  MTK_QDMA_RING_SIZE * soc->tx.desc_size,
 				  eth->scratch_ring, eth->phy_scratch_ring);
 		eth->scratch_ring = NULL;
 		eth->phy_scratch_ring = 0;
@@ -3174,7 +3174,7 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth)
 
 	eth->rx_events++;
 	if (likely(napi_schedule_prep(&eth->rx_napi))) {
-		mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask);
+		mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask);
 		__napi_schedule(&eth->rx_napi);
 	}
 
@@ -3200,9 +3200,9 @@ static irqreturn_t mtk_handle_irq(int irq, void *_eth)
 	const struct mtk_reg_map *reg_map = eth->soc->reg_map;
 
 	if (mtk_r32(eth, reg_map->pdma.irq_mask) &
-	    eth->soc->txrx.rx_irq_done_mask) {
+	    eth->soc->rx.irq_done_mask) {
 		if (mtk_r32(eth, reg_map->pdma.irq_status) &
-		    eth->soc->txrx.rx_irq_done_mask)
+		    eth->soc->rx.irq_done_mask)
 			mtk_handle_irq_rx(irq, _eth);
 	}
 	if (mtk_r32(eth, reg_map->tx_irq_mask) & MTK_TX_DONE_INT) {
@@ -3220,10 +3220,10 @@ static void mtk_poll_controller(struct net_device *dev)
 	struct mtk_eth *eth = mac->hw;
 
 	mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
-	mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask);
+	mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask);
 	mtk_handle_irq_rx(eth->irq[2], dev);
 	mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
-	mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask);
+	mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask);
 }
 #endif
 
@@ -3387,7 +3387,7 @@ static int mtk_open(struct net_device *dev)
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
 		mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
-		mtk_rx_irq_enable(eth, soc->txrx.rx_irq_done_mask);
+		mtk_rx_irq_enable(eth, soc->rx.irq_done_mask);
 		refcount_set(&eth->dma_refcnt, 1);
 	}
 	else
@@ -3471,7 +3471,7 @@ static int mtk_stop(struct net_device *dev)
 	mtk_gdm_config(eth, MTK_GDMA_DROP_ALL);
 
 	mtk_tx_irq_disable(eth, MTK_TX_DONE_INT);
-	mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask);
+	mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask);
 	napi_disable(&eth->tx_napi);
 	napi_disable(&eth->rx_napi);
 
@@ -3893,7 +3893,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
-	if (mtk_is_netsys_v2_or_greater(eth)) {
+	if (mtk_is_netsys_v3_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
 		mtk_w32(eth,  val | BIT(4), MTK_FE_GLO_MISC);
@@ -3947,9 +3947,9 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 
 	/* FE int grouping */
 	mtk_w32(eth, MTK_TX_DONE_INT, reg_map->pdma.int_grp);
-	mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->pdma.int_grp + 4);
+	mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->pdma.int_grp + 4);
 	mtk_w32(eth, MTK_TX_DONE_INT, reg_map->qdma.int_grp);
-	mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->qdma.int_grp + 4);
+	mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->qdma.int_grp + 4);
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
@@ -4055,7 +4055,7 @@ static int mtk_change_mtu(struct net_device *dev, int new_mtu)
 	}
 
 	mtk_set_mcr_max_rx(mac, length);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	return 0;
 }
@@ -4188,6 +4188,8 @@ static int mtk_free_dev(struct mtk_eth *eth)
 		metadata_dst_free(eth->dsa_meta[i]);
 	}
 
+	free_netdev(eth->dummy_dev);
+
 	return 0;
 }
 
@@ -4983,9 +4985,14 @@ static int mtk_probe(struct platform_device *pdev)
 	/* we run 2 devices on the same DMA ring so we need a dummy device
 	 * for NAPI to work
 	 */
-	init_dummy_netdev(&eth->dummy_dev);
-	netif_napi_add(&eth->dummy_dev, &eth->tx_napi, mtk_napi_tx);
-	netif_napi_add(&eth->dummy_dev, &eth->rx_napi, mtk_napi_rx);
+	eth->dummy_dev = alloc_netdev_dummy(0);
+	if (!eth->dummy_dev) {
+		err = -ENOMEM;
+		dev_err(eth->dev, "failed to allocated dummy device\n");
+		goto err_unreg_netdev;
+	}
+	netif_napi_add(eth->dummy_dev, &eth->tx_napi, mtk_napi_tx);
+	netif_napi_add(eth->dummy_dev, &eth->rx_napi, mtk_napi_rx);
 
 	platform_set_drvdata(pdev, eth);
 	schedule_delayed_work(&eth->reset.monitor_work,
@@ -4993,6 +5000,8 @@ static int mtk_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_unreg_netdev:
+	mtk_unreg_dev(eth);
 err_deinit_ppe:
 	mtk_ppe_deinit(eth);
 	mtk_mdio_cleanup(eth);
@@ -5039,11 +5048,15 @@ static const struct mtk_soc_data mt2701_data = {
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 	.version = 1,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5059,11 +5072,15 @@ static const struct mtk_soc_data mt7621_data = {
 	.offload_version = 1,
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5081,11 +5098,15 @@ static const struct mtk_soc_data mt7622_data = {
 	.hash_offset = 2,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5102,11 +5123,15 @@ static const struct mtk_soc_data mt7623_data = {
 	.hash_offset = 2,
 	.foe_entry_size = MTK_FOE_ENTRY_V1_SIZE,
 	.disable_pll_modes = true,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5121,11 +5146,15 @@ static const struct mtk_soc_data mt7629_data = {
 	.required_pctl = false,
 	.has_accounting = true,
 	.version = 1,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
@@ -5143,14 +5172,18 @@ static const struct mtk_soc_data mt7981_data = {
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma_v2),
-		.rxd_size = sizeof(struct mtk_rx_dma_v2),
-		.rx_irq_done_mask = MTK_RX_DONE_INT_V2,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID_V2,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma_v2),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
 	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID_V2,
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
 };
 
 static const struct mtk_soc_data mt7986_data = {
@@ -5165,14 +5198,18 @@ static const struct mtk_soc_data mt7986_data = {
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V2_SIZE,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma_v2),
-		.rxd_size = sizeof(struct mtk_rx_dma_v2),
-		.rx_irq_done_mask = MTK_RX_DONE_INT_V2,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID_V2,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma_v2),
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
 	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID_V2,
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
 };
 
 static const struct mtk_soc_data mt7988_data = {
@@ -5187,11 +5224,15 @@ static const struct mtk_soc_data mt7988_data = {
 	.hash_offset = 4,
 	.has_accounting = true,
 	.foe_entry_size = MTK_FOE_ENTRY_V3_SIZE,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma_v2),
-		.rxd_size = sizeof(struct mtk_rx_dma_v2),
-		.rx_irq_done_mask = MTK_RX_DONE_INT_V2,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID_V2,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma_v2),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
+		.dma_len_offset = 8,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma_v2),
+		.irq_done_mask = MTK_RX_DONE_INT_V2,
+		.dma_l4_valid = RX_DMA_L4_VALID_V2,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN_V2,
 		.dma_len_offset = 8,
 	},
@@ -5204,11 +5245,15 @@ static const struct mtk_soc_data rt5350_data = {
 	.required_clks = MT7628_CLKS_BITMAP,
 	.required_pctl = false,
 	.version = 1,
-	.txrx = {
-		.txd_size = sizeof(struct mtk_tx_dma),
-		.rxd_size = sizeof(struct mtk_rx_dma),
-		.rx_irq_done_mask = MTK_RX_DONE_INT,
-		.rx_dma_l4_valid = RX_DMA_L4_VALID_PDMA,
+	.tx = {
+		.desc_size = sizeof(struct mtk_tx_dma),
+		.dma_max_len = MTK_TX_DMA_BUF_LEN,
+		.dma_len_offset = 16,
+	},
+	.rx = {
+		.desc_size = sizeof(struct mtk_rx_dma),
+		.irq_done_mask = MTK_RX_DONE_INT,
+		.dma_l4_valid = RX_DMA_L4_VALID_PDMA,
 		.dma_max_len = MTK_TX_DMA_BUF_LEN,
 		.dma_len_offset = 16,
 	},
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 9ae3b8a71d0e..4eab30b44070 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -327,8 +327,8 @@
 /* QDMA descriptor txd3 */
 #define TX_DMA_OWNER_CPU	BIT(31)
 #define TX_DMA_LS0		BIT(30)
-#define TX_DMA_PLEN0(x)		(((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset)
-#define TX_DMA_PLEN1(x)		((x) & eth->soc->txrx.dma_max_len)
+#define TX_DMA_PLEN0(x)		(((x) & eth->soc->tx.dma_max_len) << eth->soc->tx.dma_len_offset)
+#define TX_DMA_PLEN1(x)		((x) & eth->soc->tx.dma_max_len)
 #define TX_DMA_SWC		BIT(14)
 #define TX_DMA_PQID		GENMASK(3, 0)
 #define TX_DMA_ADDR64_MASK	GENMASK(3, 0)
@@ -348,8 +348,8 @@
 /* QDMA descriptor rxd2 */
 #define RX_DMA_DONE		BIT(31)
 #define RX_DMA_LSO		BIT(30)
-#define RX_DMA_PREP_PLEN0(x)	(((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset)
-#define RX_DMA_GET_PLEN0(x)	(((x) >> eth->soc->txrx.dma_len_offset) & eth->soc->txrx.dma_max_len)
+#define RX_DMA_PREP_PLEN0(x)	(((x) & eth->soc->rx.dma_max_len) << eth->soc->rx.dma_len_offset)
+#define RX_DMA_GET_PLEN0(x)	(((x) >> eth->soc->rx.dma_len_offset) & eth->soc->rx.dma_max_len)
 #define RX_DMA_VTAG		BIT(15)
 #define RX_DMA_ADDR64_MASK	GENMASK(3, 0)
 #if IS_ENABLED(CONFIG_64BIT)
@@ -1153,10 +1153,9 @@ struct mtk_reg_map {
  * @foe_entry_size		Foe table entry size.
  * @has_accounting		Bool indicating support for accounting of
  *				offloaded flows.
- * @txd_size			Tx DMA descriptor size.
- * @rxd_size			Rx DMA descriptor size.
- * @rx_irq_done_mask		Rx irq done register mask.
- * @rx_dma_l4_valid		Rx DMA valid register mask.
+ * @desc_size			Tx/Rx DMA descriptor size.
+ * @irq_done_mask		Rx irq done register mask.
+ * @dma_l4_valid		Rx DMA valid register mask.
  * @dma_max_len			Max DMA tx/rx buffer length.
  * @dma_len_offset		Tx/Rx DMA length field offset.
  */
@@ -1174,13 +1173,17 @@ struct mtk_soc_data {
 	bool		has_accounting;
 	bool		disable_pll_modes;
 	struct {
-		u32	txd_size;
-		u32	rxd_size;
-		u32	rx_irq_done_mask;
-		u32	rx_dma_l4_valid;
+		u32	desc_size;
 		u32	dma_max_len;
 		u32	dma_len_offset;
-	} txrx;
+	} tx;
+	struct {
+		u32	desc_size;
+		u32	irq_done_mask;
+		u32	dma_l4_valid;
+		u32	dma_max_len;
+		u32	dma_len_offset;
+	} rx;
 };
 
 #define MTK_DMA_MONITOR_TIMEOUT		msecs_to_jiffies(1000)
@@ -1242,7 +1245,7 @@ struct mtk_eth {
 	spinlock_t			page_lock;
 	spinlock_t			tx_irq_lock;
 	spinlock_t			rx_irq_lock;
-	struct net_device		dummy_dev;
+	struct net_device		*dummy_dev;
 	struct net_device		*netdev[MTK_MAX_DEVS];
 	struct mtk_mac			*mac[MTK_MAX_DEVS];
 	int				irq[3];
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index 6ce0db3a1a92..0acee405a749 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -580,7 +580,7 @@ mtk_flow_entry_update_l2(struct mtk_ppe *ppe, struct mtk_flow_entry *entry)
 
 		idle = cur_idle;
 		entry->data.ib1 &= ~ib1_ts_mask;
-		entry->data.ib1 |= hwe->ib1 & ib1_ts_mask;
+		entry->data.ib1 |= ib1 & ib1_ts_mask;
 	}
 }
 
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index fbb5e9d5af13..aa262e6f4b85 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -273,6 +273,10 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 
 		flow_rule_match_control(rule, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
 	} else {
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5d3fde63b273..4c089cfa027a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1649,7 +1649,7 @@ int mlx4_en_start_port(struct net_device *dev)
 	       sizeof(struct ethtool_flow_id) * MAX_NUM_OF_FS_RULES);
 
 	/* Calculate Rx buf size */
-	dev->mtu = min(dev->mtu, priv->max_mtu);
+	WRITE_ONCE(dev->mtu, min(dev->mtu, priv->max_mtu));
 	mlx4_en_calc_rx_buf(dev);
 	en_dbg(DRV, priv, "Rx buf size:%d\n", priv->rx_skb_size);
 
@@ -2394,7 +2394,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	    !mlx4_en_check_xdp_mtu(dev, new_mtu))
 		return -EOPNOTSUPP;
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (netif_running(dev)) {
 		mutex_lock(&mdev->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index eac49657bd07..8328df8645d5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -42,6 +42,7 @@
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
 #include <linux/irq.h>
+#include <linux/skbuff_ref.h>
 
 #include <net/ip.h>
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7b02ff61126d..98688e4dbec5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -185,7 +185,8 @@ static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
 }
 
 static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
-				       struct devlink_param_gset_ctx *ctx)
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
 {
 	mlx4_internal_err_reset = ctx->val.vbool;
 	return 0;
@@ -202,7 +203,8 @@ static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
 }
 
 static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
-					    struct devlink_param_gset_ctx *ctx)
+					    struct devlink_param_gset_ctx *ctx,
+					    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
 	struct mlx4_dev *dev = &priv->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 4957412ff1f6..20768ef2e9d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -969,19 +969,32 @@ static void cmd_work_handler(struct work_struct *work)
 	bool poll_cmd = ent->polling;
 	struct mlx5_cmd_layout *lay;
 	struct mlx5_core_dev *dev;
-	unsigned long cb_timeout;
-	struct semaphore *sem;
+	unsigned long timeout;
 	unsigned long flags;
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
+
 	dev = container_of(cmd, struct mlx5_core_dev, cmd);
-	cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD));
+	timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD));
 
-	complete(&ent->handling);
-	sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem;
-	down(sem);
 	if (!ent->page_queue) {
+		if (down_timeout(&cmd->vars.sem, timeout)) {
+			mlx5_core_warn(dev, "%s(0x%x) timed out while waiting for a slot.\n",
+				       mlx5_command_str(ent->op), ent->op);
+			if (ent->callback) {
+				ent->callback(-EBUSY, ent->context);
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+				cmd_ent_put(ent);
+			} else {
+				ent->ret = -EBUSY;
+				complete(&ent->done);
+			}
+			complete(&ent->slotted);
+			return;
+		}
 		alloc_ret = cmd_alloc_index(cmd, ent);
 		if (alloc_ret < 0) {
 			mlx5_core_err_rl(dev, "failed to allocate command entry\n");
@@ -994,10 +1007,11 @@ static void cmd_work_handler(struct work_struct *work)
 				ent->ret = -EAGAIN;
 				complete(&ent->done);
 			}
-			up(sem);
+			up(&cmd->vars.sem);
 			return;
 		}
 	} else {
+		down(&cmd->vars.pages_sem);
 		ent->idx = cmd->vars.max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
 		clear_bit(ent->idx, &cmd->vars.bitmask);
@@ -1005,6 +1019,8 @@ static void cmd_work_handler(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
+	complete(&ent->slotted);
+
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -1023,7 +1039,7 @@ static void cmd_work_handler(struct work_struct *work)
 	ent->ts1 = ktime_get_ns();
 	cmd_mode = cmd->mode;
 
-	if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout))
+	if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, timeout))
 		cmd_ent_get(ent);
 	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 
@@ -1143,6 +1159,9 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		ent->ret = -ECANCELED;
 		goto out_err;
 	}
+
+	wait_for_completion(&ent->slotted);
+
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling)
 		wait_for_completion(&ent->done);
 	else if (!wait_for_completion_timeout(&ent->done, timeout))
@@ -1157,6 +1176,9 @@ out_err:
 	} else if (err == -ECANCELED) {
 		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
 			       mlx5_command_str(ent->op), ent->op);
+	} else if (err == -EBUSY) {
+		mlx5_core_warn(dev, "%s(0x%x) timeout while waiting for command semaphore.\n",
+			       mlx5_command_str(ent->op), ent->op);
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1208,6 +1230,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->polling = force_polling;
 
 	init_completion(&ent->handling);
+	init_completion(&ent->slotted);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -1225,7 +1248,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		return 0; /* mlx5_cmd_comp_handler() will put(ent) */
 
 	err = wait_func(dev, ent);
-	if (err == -ETIMEDOUT || err == -ECANCELED)
+	if (err == -ETIMEDOUT || err == -ECANCELED || err == -EBUSY)
 		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
@@ -1611,6 +1634,9 @@ static int cmd_comp_notifier(struct notifier_block *nb,
 	dev = container_of(cmd, struct mlx5_core_dev, cmd);
 	eqe = data;
 
+	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		return NOTIFY_DONE;
+
 	mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 
 	return NOTIFY_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 09652dc89115..36806e813c33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -143,8 +143,8 @@ static ssize_t average_read(struct file *filp, char __user *buf, size_t count,
 	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
 }
 
-static ssize_t average_write(struct file *filp, const char __user *buf,
-			     size_t count, loff_t *pos)
+static ssize_t reset_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *pos)
 {
 	struct mlx5_cmd_stats *stats;
 
@@ -152,6 +152,11 @@ static ssize_t average_write(struct file *filp, const char __user *buf,
 	spin_lock_irq(&stats->lock);
 	stats->sum = 0;
 	stats->n = 0;
+	stats->failed = 0;
+	stats->failed_mbox_status = 0;
+	stats->last_failed_errno = 0;
+	stats->last_failed_mbox_status = 0;
+	stats->last_failed_syndrome = 0;
 	spin_unlock_irq(&stats->lock);
 
 	*pos += count;
@@ -159,11 +164,16 @@ static ssize_t average_write(struct file *filp, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations stats_fops = {
+static const struct file_operations reset_fops = {
+	.owner	= THIS_MODULE,
+	.open	= simple_open,
+	.write	= reset_write,
+};
+
+static const struct file_operations average_fops = {
 	.owner	= THIS_MODULE,
 	.open	= simple_open,
 	.read	= average_read,
-	.write	= average_write,
 };
 
 static ssize_t slots_read(struct file *filp, char __user *buf, size_t count,
@@ -228,8 +238,10 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 				continue;
 			stats->root = debugfs_create_dir(namep, *cmd);
 
+			debugfs_create_file("reset", 0200, stats->root, stats,
+					    &reset_fops);
 			debugfs_create_file("average", 0400, stats->root, stats,
-					    &stats_fops);
+					    &average_fops);
 			debugfs_create_u64("n", 0400, stats->root, &stats->n);
 			debugfs_create_u64("failed", 0400, stats->root, &stats->failed);
 			debugfs_create_u64("failed_mbox_status", 0400, stats->root,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 84db05fb9389..e85fb71bf0b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -320,6 +320,8 @@ struct mlx5e_params {
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
 	bool tx_dim_enabled;
+	bool rx_moder_use_cqe_mode;
+	bool tx_moder_use_cqe_mode;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
 	struct mlx5e_xsk *xsk;
@@ -430,7 +432,7 @@ struct mlx5e_txqsq {
 	u16                        cc;
 	u16                        skb_fifo_cc;
 	u32                        dma_fifo_cc;
-	struct dim                 dim; /* Adaptive Moderation */
+	struct dim                *dim; /* Adaptive Moderation */
 
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
@@ -722,7 +724,7 @@ struct mlx5e_rq {
 	int                    ix;
 	unsigned int           hw_mtu;
 
-	struct dim         dim; /* Dynamic Interrupt Moderation */
+	struct dim            *dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
 	struct bpf_prog __rcu *xdp_prog;
@@ -797,6 +799,10 @@ struct mlx5e_channel {
 	int                        cpu;
 	/* Sync between icosq recovery and XSK enable/disable. */
 	struct mutex               icosq_recovery_lock;
+
+	/* coalescing configuration */
+	struct dim_cq_moder        rx_cq_moder;
+	struct dim_cq_moder        tx_cq_moder;
 };
 
 struct mlx5e_ptp;
@@ -1040,6 +1046,11 @@ void mlx5e_close_rq(struct mlx5e_rq *rq);
 int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
+bool mlx5e_reset_rx_moderation(struct dim_cq_moder *cq_moder, u8 cq_period_mode,
+			       bool dim_enabled);
+bool mlx5e_reset_rx_channels_moderation(struct mlx5e_channels *chs, u8 cq_period_mode,
+					bool dim_enabled, bool keep_dim_state);
+
 struct mlx5e_sq_param;
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
@@ -1060,6 +1071,10 @@ int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder,
 		  struct mlx5e_cq_param *param, struct mlx5e_create_cq_param *ccp,
 		  struct mlx5e_cq *cq);
 void mlx5e_close_cq(struct mlx5e_cq *cq);
+int mlx5e_modify_cq_period_mode(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
+				u8 cq_period_mode);
+int mlx5e_modify_cq_moderation(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
+			       u16 cq_period, u16 cq_max_count, u8 cq_period_mode);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
@@ -1087,6 +1102,7 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 			     void *context, bool reset);
 int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv);
 int mlx5e_num_channels_changed_ctx(struct mlx5e_priv *priv, void *context);
+int mlx5e_update_tc_and_tx_queues_ctx(struct mlx5e_priv *priv, void *context);
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx);
@@ -1118,6 +1134,11 @@ int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev,
 void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 void mlx5e_close_txqsq(struct mlx5e_txqsq *sq);
 
+bool mlx5e_reset_tx_moderation(struct dim_cq_moder *cq_moder, u8 cq_period_mode,
+			       bool dim_enabled);
+bool mlx5e_reset_tx_channels_moderation(struct mlx5e_channels *chs, u8 cq_period_mode,
+					bool dim_enabled, bool keep_dim_state);
+
 static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_ETH(mdev, swp) &&
@@ -1143,7 +1164,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
-int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
@@ -1160,7 +1180,7 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv);
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo);
 void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv,
-			       uint32_t stringset, uint8_t *data);
+			       u32 stringset, u8 *data);
 int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset);
 void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv,
 				     struct ethtool_stats *stats, u64 *data);
@@ -1180,23 +1200,16 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal,
 			       struct kernel_ethtool_coalesce *kernel_coal,
 			       struct netlink_ext_ack *extack);
-int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
-				     struct ethtool_link_ksettings *link_ksettings);
-int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
-				     const struct ethtool_link_ksettings *link_ksettings);
-int mlx5e_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh);
-int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
-		   struct netlink_ext_ack *extack);
+int mlx5e_get_per_queue_coalesce(struct net_device *dev, u32 queue,
+				 struct ethtool_coalesce *coal);
+int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
+				 struct ethtool_coalesce *coal);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info);
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
-void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
-				  struct ethtool_pauseparam *pauseparam);
-int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
-				 struct ethtool_pauseparam *pauseparam);
 
 /* mlx5e generic netdev management API */
 static inline bool
@@ -1222,8 +1235,6 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv);
 void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu);
-void mlx5e_rx_dim_work(struct work_struct *work);
-void mlx5e_tx_dim_work(struct work_struct *work);
 
 void mlx5e_set_xdp_feature(struct net_device *netdev);
 netdev_features_t mlx5e_features_check(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
index 874a1016623c..66e719e88503 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
@@ -3,6 +3,7 @@
 
 #include "channels.h"
 #include "en.h"
+#include "en/dim.h"
 #include "en/ptp.h"
 
 unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs)
@@ -55,3 +56,85 @@ bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn)
 	*rqn = c->rq.rqn;
 	return true;
 }
+
+int mlx5e_channels_rx_change_dim(struct mlx5e_channels *chs, bool enable)
+{
+	int i;
+
+	for (i = 0; i < chs->num; i++) {
+		int err = mlx5e_dim_rx_change(&chs->c[i]->rq, enable);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int mlx5e_channels_tx_change_dim(struct mlx5e_channels *chs, bool enable)
+{
+	int i, tc;
+
+	for (i = 0; i < chs->num; i++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&chs->params); tc++) {
+			int err = mlx5e_dim_tx_change(&chs->c[i]->sq[tc], enable);
+
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+int mlx5e_channels_rx_toggle_dim(struct mlx5e_channels *chs)
+{
+	int i;
+
+	for (i = 0; i < chs->num; i++) {
+		/* If dim is enabled for the channel, reset the dim state so the
+		 * collected statistics will be reset. This is useful for
+		 * supporting legacy interfaces that allow things like changing
+		 * the CQ period mode for all channels without disturbing
+		 * individual channel configurations.
+		 */
+		if (chs->c[i]->rq.dim) {
+			int err;
+
+			mlx5e_dim_rx_change(&chs->c[i]->rq, false);
+			err = mlx5e_dim_rx_change(&chs->c[i]->rq, true);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+int mlx5e_channels_tx_toggle_dim(struct mlx5e_channels *chs)
+{
+	int i, tc;
+
+	for (i = 0; i < chs->num; i++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&chs->params); tc++) {
+			int err;
+
+			/* If dim is enabled for the channel, reset the dim
+			 * state so the collected statistics will be reset. This
+			 * is useful for supporting legacy interfaces that allow
+			 * things like changing the CQ period mode for all
+			 * channels without disturbing individual channel
+			 * configurations.
+			 */
+			if (!chs->c[i]->sq[tc].dim)
+				continue;
+
+			mlx5e_dim_tx_change(&chs->c[i]->sq[tc], false);
+			err = mlx5e_dim_tx_change(&chs->c[i]->sq[tc], true);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
index 6715aa9383b9..eda80f8c6c02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
@@ -15,5 +15,9 @@ void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix,
 void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
 				u32 *vhca_id);
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn);
+int mlx5e_channels_rx_change_dim(struct mlx5e_channels *chs, bool enabled);
+int mlx5e_channels_tx_change_dim(struct mlx5e_channels *chs, bool enabled);
+int mlx5e_channels_rx_toggle_dim(struct mlx5e_channels *chs);
+int mlx5e_channels_tx_toggle_dim(struct mlx5e_channels *chs);
 
 #endif /* __MLX5_EN_CHANNELS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dim.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dim.h
new file mode 100644
index 000000000000..110e2c6b7e51
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dim.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved */
+
+#ifndef __MLX5_EN_DIM_H__
+#define __MLX5_EN_DIM_H__
+
+#include <linux/dim.h>
+#include <linux/types.h>
+#include <linux/mlx5/mlx5_ifc.h>
+
+/* Forward declarations */
+struct mlx5e_rq;
+struct mlx5e_txqsq;
+struct work_struct;
+
+/* convert a boolean value for cqe mode to appropriate dim constant
+ * true  : DIM_CQ_PERIOD_MODE_START_FROM_CQE
+ * false : DIM_CQ_PERIOD_MODE_START_FROM_EQE
+ */
+static inline int mlx5e_dim_cq_period_mode(bool start_from_cqe)
+{
+	return start_from_cqe ? DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+}
+
+static inline enum mlx5_cq_period_mode
+mlx5e_cq_period_mode(enum dim_cq_period_mode cq_period_mode)
+{
+	switch (cq_period_mode) {
+	case DIM_CQ_PERIOD_MODE_START_FROM_EQE:
+		return MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	case DIM_CQ_PERIOD_MODE_START_FROM_CQE:
+		return MLX5_CQ_PERIOD_MODE_START_FROM_CQE;
+	default:
+		WARN_ON_ONCE(true);
+		return MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	}
+}
+
+void mlx5e_rx_dim_work(struct work_struct *work);
+void mlx5e_tx_dim_work(struct work_struct *work);
+int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enabled);
+int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enabled);
+
+#endif /* __MLX5_EN_DIM_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index a3f31d9d527e..ec819dfc98be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -6,6 +6,7 @@
 #include "en/port.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ipsec.h"
+#include <linux/dim.h>
 #include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
@@ -513,77 +514,6 @@ int mlx5e_validate_params(struct mlx5_core_dev *mdev, struct mlx5e_params *param
 	return 0;
 }
 
-static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
-{
-	struct dim_cq_moder moder = {};
-
-	moder.cq_period_mode = cq_period_mode;
-	moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
-	moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
-	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
-		moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE;
-
-	return moder;
-}
-
-static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
-{
-	struct dim_cq_moder moder = {};
-
-	moder.cq_period_mode = cq_period_mode;
-	moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
-	moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
-	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
-		moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
-
-	return moder;
-}
-
-static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
-{
-	return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
-		DIM_CQ_PERIOD_MODE_START_FROM_CQE :
-		DIM_CQ_PERIOD_MODE_START_FROM_EQE;
-}
-
-void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
-{
-	if (params->tx_dim_enabled) {
-		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
-
-		params->tx_cq_moderation = net_dim_get_def_tx_moderation(dim_period_mode);
-	} else {
-		params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode);
-	}
-}
-
-void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
-{
-	if (params->rx_dim_enabled) {
-		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
-
-		params->rx_cq_moderation = net_dim_get_def_rx_moderation(dim_period_mode);
-	} else {
-		params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode);
-	}
-}
-
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
-{
-	mlx5e_reset_tx_moderation(params, cq_period_mode);
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
-			params->tx_cq_moderation.cq_period_mode ==
-				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-}
-
-void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
-{
-	mlx5e_reset_rx_moderation(params, cq_period_mode);
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
-			params->rx_cq_moderation.cq_period_mode ==
-				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-}
-
 bool slow_pci_heuristic(struct mlx5_core_dev *mdev)
 {
 	u32 link_speed = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 9a781f18b57f..749b2ec0436e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -77,11 +77,6 @@ u8 mlx5e_mpwrq_max_log_rq_pkts(struct mlx5_core_dev *mdev, u8 page_shift,
 
 /* Parameter calculations */
 
-void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode);
-void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode);
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode);
-void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode);
-
 bool slow_pci_heuristic(struct mlx5_core_dev *mdev);
 int mlx5e_mpwrq_validate_regular(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index dbe2b19a9570..b4efc780e297 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -292,10 +292,15 @@ enum mlx5e_fec_supported_link_mode {
 	MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X,
 	MLX5E_MAX_FEC_SUPPORTED_LINK_MODE,
 };
 
 #define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X
+#define MLX5E_FEC_FIRST_100G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X
 
 #define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link)			\
 	do {										\
@@ -308,6 +313,17 @@ enum mlx5e_fec_supported_link_mode {
 			*_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link);	\
 	} while (0)
 
+/* Returns true if FEC can be set for a given link mode. */
+static bool mlx5e_is_fec_supported_link_mode(struct mlx5_core_dev *dev,
+					     enum mlx5e_fec_supported_link_mode link_mode)
+{
+	return link_mode < MLX5E_FEC_FIRST_50G_PER_LANE_MODE ||
+	       (link_mode < MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm)) ||
+	       (link_mode >= MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm));
+}
+
 /* get/set FEC admin field for a given speed */
 static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 				 enum mlx5e_fec_supported_link_mode link_mode)
@@ -340,6 +356,18 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X:
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -381,6 +409,18 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X:
 		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 100g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -389,7 +429,6 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 
 bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 {
-	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
 	u32 out[MLX5_ST_SZ_DW(pplm_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {};
 	int sz = MLX5_ST_SZ_BYTES(pplm_reg);
@@ -407,7 +446,7 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 	for (i = 0; i < MLX5E_MAX_FEC_SUPPORTED_LINK_MODE; i++) {
 		u16 fec_caps;
 
-		if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane)
+		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
 		mlx5e_get_fec_cap_field(out, &fec_caps, i);
@@ -420,7 +459,6 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active,
 		       u16 *fec_configured_mode)
 {
-	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
 	u32 out[MLX5_ST_SZ_DW(pplm_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {};
 	int sz = MLX5_ST_SZ_BYTES(pplm_reg);
@@ -445,7 +483,7 @@ int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active,
 
 	*fec_configured_mode = 0;
 	for (i = 0; i < MLX5E_MAX_FEC_SUPPORTED_LINK_MODE; i++) {
-		if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane)
+		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
 		mlx5e_fec_admin_field(out, fec_configured_mode, 0, i);
@@ -489,13 +527,13 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 		u16 conf_fec = fec_policy;
 		u16 fec_caps = 0;
 
-		if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane)
+		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
 		/* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514
 		 * to link modes up to 25G per lane and to
 		 * MLX5E_FEC_RS_544_514 in the new link modes based on
-		 * 50 G per lane
+		 * 50G or 100G per lane
 		 */
 		if (conf_fec == (1 << MLX5E_FEC_RS_528_514) &&
 		    i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index d0af7271da34..afd654583b6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -169,6 +169,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 		WARN_ON_ONCE(!pos->inuse);
 		pos->inuse = false;
 		list_del(&pos->entry);
+		ptpsq->cq_stats->lost_cqe++;
 	}
 	spin_unlock_bh(&cqe_list->tracker_list_lock);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 92065568bb19..6873c1201803 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -117,7 +117,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
 
 bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a,
 					   struct mlx5e_encap_key *b,
-					   __be16 tun_flags);
+					   u32 tun_type);
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index f1d1e1542e81..878cbdbf5ec8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -587,7 +587,7 @@ bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
 
 bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a,
 					   struct mlx5e_encap_key *b,
-					   __be16 tun_flags)
+					   u32 tun_type)
 {
 	struct ip_tunnel_info *a_info;
 	struct ip_tunnel_info *b_info;
@@ -596,8 +596,8 @@ bool mlx5e_tc_tun_encap_info_equal_options(struct mlx5e_encap_key *a,
 	if (!mlx5e_tc_tun_encap_info_equal_generic(a, b))
 		return false;
 
-	a_has_opts = !!(a->ip_tun_key->tun_flags & tun_flags);
-	b_has_opts = !!(b->ip_tun_key->tun_flags & tun_flags);
+	a_has_opts = test_bit(tun_type, a->ip_tun_key->tun_flags);
+	b_has_opts = test_bit(tun_type, b->ip_tun_key->tun_flags);
 
 	/* keys are equal when both don't have any options attached */
 	if (!a_has_opts && !b_has_opts)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
index 2bcd10b6d653..bf969212cc77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -106,12 +106,13 @@ static int mlx5e_gen_ip_tunnel_header_geneve(char buf[],
 	memset(geneveh, 0, sizeof(*geneveh));
 	geneveh->ver = MLX5E_GENEVE_VER;
 	geneveh->opt_len = tun_info->options_len / 4;
-	geneveh->oam = !!(tun_info->key.tun_flags & TUNNEL_OAM);
-	geneveh->critical = !!(tun_info->key.tun_flags & TUNNEL_CRIT_OPT);
+	geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, tun_info->key.tun_flags);
+	geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT,
+				     tun_info->key.tun_flags);
 	mlx5e_tunnel_id_to_vni(tun_info->key.tun_id, geneveh->vni);
 	geneveh->proto_type = htons(ETH_P_TEB);
 
-	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+	if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) {
 		if (!geneveh->opt_len)
 			return -EOPNOTSUPP;
 		ip_tunnel_info_opts_get(geneveh->options, tun_info);
@@ -188,7 +189,7 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
 
 	/* make sure that we're talking about GENEVE options */
 
-	if (enc_opts.key->dst_opt_type != TUNNEL_GENEVE_OPT) {
+	if (enc_opts.key->dst_opt_type != IP_TUNNEL_GENEVE_OPT_BIT) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Matching on GENEVE options: option type is not GENEVE");
 		netdev_warn(priv->netdev,
@@ -337,7 +338,8 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv,
 static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a,
 						 struct mlx5e_encap_key *b)
 {
-	return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_GENEVE_OPT);
+	return mlx5e_tc_tun_encap_info_equal_options(a, b,
+						     IP_TUNNEL_GENEVE_OPT_BIT);
 }
 
 struct mlx5e_tc_tunnel geneve_tunnel = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
index ada14f0574dc..579eda89fc76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
@@ -31,12 +31,16 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[],
 	const struct ip_tunnel_key *tun_key  = &e->tun_info->key;
 	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
 	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	IP_TUNNEL_DECLARE_FLAGS(unsupp) = { };
 	int hdr_len;
 
 	*ip_proto = IPPROTO_GRE;
 
 	/* the HW does not calculate GRE csum or sequences */
-	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
+	__set_bit(IP_TUNNEL_CSUM_BIT, unsupp);
+	__set_bit(IP_TUNNEL_SEQ_BIT, unsupp);
+
+	if (ip_tunnel_flags_intersect(tun_key->tun_flags, unsupp))
 		return -EOPNOTSUPP;
 
 	greh->protocol = htons(ETH_P_TEB);
@@ -44,7 +48,7 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[],
 	/* GRE key */
 	hdr_len	= mlx5e_tc_tun_calc_hlen_gretap(e);
 	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
-	if (tun_key->tun_flags & TUNNEL_KEY) {
+	if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) {
 		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
 		*ptr = tun_id;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index a184d739d5f8..e4e487c8431b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -90,7 +90,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
 	const struct vxlan_metadata *md;
 	struct vxlanhdr *vxh;
 
-	if ((tun_key->tun_flags & TUNNEL_VXLAN_OPT) &&
+	if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags) &&
 	    e->tun_info->options_len != sizeof(*md))
 		return -EOPNOTSUPP;
 	vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
@@ -99,7 +99,7 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
 	udp->dest = tun_key->tp_dst;
 	vxh->vx_flags = VXLAN_HF_VNI;
 	vxh->vx_vni = vxlan_vni_field(tun_id);
-	if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) {
+	if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_key->tun_flags)) {
 		md = ip_tunnel_info_opts(e->tun_info);
 		vxlan_build_gbp_hdr(vxh, md);
 	}
@@ -125,7 +125,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (enc_opts.key->dst_opt_type != TUNNEL_VXLAN_OPT) {
+	if (enc_opts.key->dst_opt_type != IP_TUNNEL_VXLAN_OPT_BIT) {
 		NL_SET_ERR_MSG_MOD(extack, "Wrong VxLAN option type: not GBP");
 		return -EOPNOTSUPP;
 	}
@@ -208,7 +208,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 static bool mlx5e_tc_tun_encap_info_equal_vxlan(struct mlx5e_encap_key *a,
 						struct mlx5e_encap_key *b)
 {
-	return mlx5e_tc_tun_encap_info_equal_options(a, b, TUNNEL_VXLAN_OPT);
+	return mlx5e_tc_tun_encap_info_equal_options(a, b,
+						     IP_TUNNEL_VXLAN_OPT_BIT);
 }
 
 static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 82b5ca1be4f3..4610621a340e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -565,7 +565,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	linear = !!(dma_len - inline_hdr_sz);
 	ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT + linear + !!inline_hdr_sz;
 
-	/* check_result must be 0 if sinfo is passed. */
+	/* check_result must be 0 if xdptxd->has_frags is true. */
 	if (!check_result) {
 		int stop_room = 1;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 06592b9f0424..9240cfe25d10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -28,8 +28,10 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 			      struct mlx5e_xsk_param *xsk,
 			      struct mlx5_core_dev *mdev)
 {
-	/* AF_XDP doesn't support frames larger than PAGE_SIZE. */
-	if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) {
+	/* AF_XDP doesn't support frames larger than PAGE_SIZE,
+	 * and xsk->chunk_size is limited to 65535 bytes.
+	 */
+	if ((size_t)xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) {
 		mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size,
 			      MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE);
 		return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
index c7d191f66ad1..4f83e3172767 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
@@ -73,7 +73,7 @@ void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule)
 
 struct mlx5_flow_handle *mlx5e_accel_fs_add_sk(struct mlx5e_flow_steering *fs,
 					       struct sock *sk, u32 tirn,
-					       uint32_t flow_tag)
+					       u32 flow_tag)
 {
 	struct mlx5e_accel_fs_tcp *fs_tcp = mlx5e_fs_get_accel_tcp(fs);
 	struct mlx5_flow_destination dest = {};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.h
index a032bff482a6..7e899c716267 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.h
@@ -11,14 +11,14 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs);
 void mlx5e_accel_fs_tcp_destroy(struct mlx5e_flow_steering *fs);
 struct mlx5_flow_handle *mlx5e_accel_fs_add_sk(struct mlx5e_flow_steering *fs,
 					       struct sock *sk, u32 tirn,
-					       uint32_t flow_tag);
+					       u32 flow_tag);
 void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule);
 #else
 static inline int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs) { return 0; }
 static inline void mlx5e_accel_fs_tcp_destroy(struct mlx5e_flow_steering *fs) {}
 static inline struct mlx5_flow_handle *mlx5e_accel_fs_add_sk(struct mlx5e_flow_steering *fs,
 							     struct sock *sk, u32 tirn,
-							     uint32_t flow_tag)
+							     u32 flow_tag)
 { return ERR_PTR(-EOPNOTSUPP); }
 static inline void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule) {}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index dd36b04e30a0..92bf3fa44a3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -78,13 +78,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_hw)
 	unsigned int i;
 
 	if (!priv->ipsec)
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_ipsec_hw_stats_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, mlx5e_ipsec_hw_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw)
@@ -92,14 +89,14 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw)
 	int i;
 
 	if (!priv->ipsec)
-		return idx;
+		return;
 
 	mlx5e_accel_ipsec_fs_read_stats(priv, &priv->ipsec->hw_stats);
 	for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->hw_stats,
-						      mlx5e_ipsec_hw_stats_desc, i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->hw_stats,
+						mlx5e_ipsec_hw_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_sw)
@@ -115,9 +112,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_sw)
 
 	if (priv->ipsec)
 		for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       mlx5e_ipsec_sw_stats_desc[i].format);
-	return idx;
+			ethtool_puts(data, mlx5e_ipsec_sw_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw)
@@ -126,9 +121,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw)
 
 	if (priv->ipsec)
 		for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
-			data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->sw_stats,
-							      mlx5e_ipsec_sw_stats_desc, i);
-	return idx;
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR_ATOMIC64(
+					      &priv->ipsec->sw_stats,
+					      mlx5e_ipsec_sw_stats_desc, i));
 }
 
 MLX5E_DEFINE_STATS_GRP(ipsec_hw, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index adc6d8ea0960..07a04a142a2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -95,8 +95,8 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv);
 void mlx5e_ktls_cleanup(struct mlx5e_priv *priv);
 
 int mlx5e_ktls_get_count(struct mlx5e_priv *priv);
-int mlx5e_ktls_get_strings(struct mlx5e_priv *priv, uint8_t *data);
-int mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 *data);
+void mlx5e_ktls_get_strings(struct mlx5e_priv *priv, u8 **data);
+void mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 **data);
 
 #else
 static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
@@ -144,15 +144,9 @@ static inline bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev)
 static inline int mlx5e_ktls_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_ktls_cleanup(struct mlx5e_priv *priv) { }
 static inline int mlx5e_ktls_get_count(struct mlx5e_priv *priv) { return 0; }
-static inline int mlx5e_ktls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
-{
-	return 0;
-}
+static inline void mlx5e_ktls_get_strings(struct mlx5e_priv *priv, u8 **data) { }
 
-static inline int mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 *data)
-{
-	return 0;
-}
+static inline void mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 **data) { }
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_stats.c
index 7c1c0eb16787..60be2d72eb9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_stats.c
@@ -58,35 +58,31 @@ int mlx5e_ktls_get_count(struct mlx5e_priv *priv)
 	return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
 }
 
-int mlx5e_ktls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
+void mlx5e_ktls_get_strings(struct mlx5e_priv *priv, u8 **data)
 {
-	unsigned int i, n, idx = 0;
+	unsigned int i, n;
 
 	if (!priv->tls)
-		return 0;
+		return;
 
 	n = mlx5e_ktls_get_count(priv);
 
 	for (i = 0; i < n; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_ktls_sw_stats_desc[i].format);
-
-	return n;
+		ethtool_puts(data, mlx5e_ktls_sw_stats_desc[i].format);
 }
 
-int mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 *data)
+void mlx5e_ktls_get_stats(struct mlx5e_priv *priv, u64 **data)
 {
-	unsigned int i, n, idx = 0;
+	unsigned int i, n;
 
 	if (!priv->tls)
-		return 0;
+		return;
 
 	n = mlx5e_ktls_get_count(priv);
 
 	for (i = 0; i < n; i++)
-		data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats,
-						      mlx5e_ktls_sw_stats_desc,
-						      i);
-
-	return n;
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats,
+						mlx5e_ktls_sw_stats_desc, i));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
index 4559ee16a11a..4bb47d48061d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_stats.c
@@ -38,16 +38,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(macsec_hw)
 	unsigned int i;
 
 	if (!priv->macsec)
-		return idx;
+		return;
 
 	if (!mlx5e_is_macsec_device(priv->mdev))
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_MACSEC_HW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_macsec_hw_stats_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, mlx5e_macsec_hw_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw)
@@ -56,19 +53,18 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(macsec_hw)
 	int i;
 
 	if (!priv->macsec)
-		return idx;
+		return;
 
 	if (!mlx5e_is_macsec_device(priv->mdev))
-		return idx;
+		return;
 
 	macsec_fs = priv->mdev->macsec_fs;
 	mlx5_macsec_fs_get_stats_fill(macsec_fs, mlx5_macsec_fs_get_stats(macsec_fs));
 	for (i = 0; i < NUM_MACSEC_HW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_macsec_fs_get_stats(macsec_fs),
-						   mlx5e_macsec_hw_stats_desc,
-						   i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(
+				      mlx5_macsec_fs_get_stats(macsec_fs),
+				      mlx5e_macsec_hw_stats_desc, i));
 }
 
 MLX5E_DEFINE_STATS_GRP(macsec_hw, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
index ca9cfbf57d8f..298bb74ec5e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
@@ -30,21 +30,22 @@
  * SOFTWARE.
  */
 
-#include <linux/dim.h>
 #include "en.h"
+#include "en/dim.h"
 
 static void
 mlx5e_complete_dim_work(struct dim *dim, struct dim_cq_moder moder,
 			struct mlx5_core_dev *mdev, struct mlx5_core_cq *mcq)
 {
-	mlx5_core_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts);
+	mlx5e_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts,
+				   mlx5e_cq_period_mode(moder.cq_period_mode));
 	dim->state = DIM_START_MEASURE;
 }
 
 void mlx5e_rx_dim_work(struct work_struct *work)
 {
 	struct dim *dim = container_of(work, struct dim, work);
-	struct mlx5e_rq *rq = container_of(dim, struct mlx5e_rq, dim);
+	struct mlx5e_rq *rq = dim->priv;
 	struct dim_cq_moder cur_moder =
 		net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 
@@ -54,9 +55,95 @@ void mlx5e_rx_dim_work(struct work_struct *work)
 void mlx5e_tx_dim_work(struct work_struct *work)
 {
 	struct dim *dim = container_of(work, struct dim, work);
-	struct mlx5e_txqsq *sq = container_of(dim, struct mlx5e_txqsq, dim);
+	struct mlx5e_txqsq *sq = dim->priv;
 	struct dim_cq_moder cur_moder =
 		net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
 
 	mlx5e_complete_dim_work(dim, cur_moder, sq->cq.mdev, &sq->cq.mcq);
 }
+
+static struct dim *mlx5e_dim_enable(struct mlx5_core_dev *mdev,
+				    void (*work_fun)(struct work_struct *), int cpu,
+				    u8 cq_period_mode, struct mlx5_core_cq *mcq,
+				    void *queue)
+{
+	struct dim *dim;
+	int err;
+
+	dim = kvzalloc_node(sizeof(*dim), GFP_KERNEL, cpu_to_node(cpu));
+	if (!dim)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&dim->work, work_fun);
+
+	dim->mode = cq_period_mode;
+	dim->priv = queue;
+
+	err = mlx5e_modify_cq_period_mode(mdev, mcq, dim->mode);
+	if (err) {
+		kvfree(dim);
+		return ERR_PTR(err);
+	}
+
+	return dim;
+}
+
+static void mlx5e_dim_disable(struct dim *dim)
+{
+	cancel_work_sync(&dim->work);
+	kvfree(dim);
+}
+
+int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable)
+{
+	if (enable == !!rq->dim)
+		return 0;
+
+	if (enable) {
+		struct mlx5e_channel *c = rq->channel;
+		struct dim *dim;
+
+		dim = mlx5e_dim_enable(rq->mdev, mlx5e_rx_dim_work, c->cpu,
+				       c->rx_cq_moder.cq_period_mode, &rq->cq.mcq, rq);
+		if (IS_ERR(dim))
+			return PTR_ERR(dim);
+
+		rq->dim = dim;
+
+		__set_bit(MLX5E_RQ_STATE_DIM, &rq->state);
+	} else {
+		__clear_bit(MLX5E_RQ_STATE_DIM, &rq->state);
+
+		mlx5e_dim_disable(rq->dim);
+		rq->dim = NULL;
+	}
+
+	return 0;
+}
+
+int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable)
+{
+	if (enable == !!sq->dim)
+		return 0;
+
+	if (enable) {
+		struct mlx5e_channel *c = sq->channel;
+		struct dim *dim;
+
+		dim = mlx5e_dim_enable(sq->mdev, mlx5e_tx_dim_work, c->cpu,
+				       c->tx_cq_moder.cq_period_mode, &sq->cq.mcq, sq);
+		if (IS_ERR(dim))
+			return PTR_ERR(dim);
+
+		sq->dim = dim;
+
+		__set_bit(MLX5E_SQ_STATE_DIM, &sq->state);
+	} else {
+		__clear_bit(MLX5E_SQ_STATE_DIM, &sq->state);
+
+		mlx5e_dim_disable(sq->dim);
+		sq->dim = NULL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 67a29826bb57..3320f12ba2db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -30,9 +30,12 @@
  * SOFTWARE.
  */
 
+#include <linux/dim.h>
 #include <linux/ethtool_netlink.h>
 
 #include "en.h"
+#include "en/channels.h"
+#include "en/dim.h"
 #include "en/port.h"
 #include "en/params.h"
 #include "en/ptp.h"
@@ -219,6 +222,13 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_800GAUI_8_800GBASE_CR8_KR8, ext,
+				       ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT);
 }
 
 static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
@@ -269,8 +279,7 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
 	switch (stringset) {
 	case ETH_SS_PRIV_FLAGS:
 		for (i = 0; i < MLX5E_NUM_PFLAGS; i++)
-			strcpy(data + i * ETH_GSTRING_LEN,
-			       mlx5e_priv_flags[i].name);
+			ethtool_puts(&data, mlx5e_priv_flags[i].name);
 		break;
 
 	case ETH_SS_TEST:
@@ -559,16 +568,13 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 	coal->rx_coalesce_usecs		= rx_moder->usec;
 	coal->rx_max_coalesced_frames	= rx_moder->pkts;
 	coal->use_adaptive_rx_coalesce	= priv->channels.params.rx_dim_enabled;
+	kernel_coal->use_cqe_mode_rx    = priv->channels.params.rx_moder_use_cqe_mode;
 
 	tx_moder = &priv->channels.params.tx_cq_moderation;
 	coal->tx_coalesce_usecs		= tx_moder->usec;
 	coal->tx_max_coalesced_frames	= tx_moder->pkts;
 	coal->use_adaptive_tx_coalesce	= priv->channels.params.tx_dim_enabled;
-
-	kernel_coal->use_cqe_mode_rx =
-		MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_BASED_MODER);
-	kernel_coal->use_cqe_mode_tx =
-		MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_CQE_BASED_MODER);
+	kernel_coal->use_cqe_mode_tx    = priv->channels.params.tx_moder_use_cqe_mode;
 
 	return 0;
 }
@@ -583,11 +589,73 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal);
 }
 
+static int mlx5e_ethtool_get_per_queue_coalesce(struct mlx5e_priv *priv, u32 queue,
+						struct ethtool_coalesce *coal)
+{
+	struct dim_cq_moder cur_moder;
+	struct mlx5e_channels *chs;
+	struct mlx5e_channel *c;
+
+	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&priv->state_lock);
+
+	chs = &priv->channels;
+	if (chs->num <= queue) {
+		mutex_unlock(&priv->state_lock);
+		return -EINVAL;
+	}
+
+	c = chs->c[queue];
+
+	coal->use_adaptive_rx_coalesce = !!c->rq.dim;
+	if (coal->use_adaptive_rx_coalesce) {
+		cur_moder = net_dim_get_rx_moderation(c->rq.dim->mode,
+						      c->rq.dim->profile_ix);
+
+		coal->rx_coalesce_usecs = cur_moder.usec;
+		coal->rx_max_coalesced_frames = cur_moder.pkts;
+	} else {
+		coal->rx_coalesce_usecs = c->rx_cq_moder.usec;
+		coal->rx_max_coalesced_frames = c->rx_cq_moder.pkts;
+	}
+
+	coal->use_adaptive_tx_coalesce = !!c->sq[0].dim;
+	if (coal->use_adaptive_tx_coalesce) {
+		/* NOTE: Will only display DIM coalesce profile information of
+		 * first channel. The current interface cannot display this
+		 * information for all tc.
+		 */
+		cur_moder = net_dim_get_tx_moderation(c->sq[0].dim->mode,
+						      c->sq[0].dim->profile_ix);
+
+		coal->tx_coalesce_usecs = cur_moder.usec;
+		coal->tx_max_coalesced_frames = cur_moder.pkts;
+
+	} else {
+		coal->tx_coalesce_usecs = c->tx_cq_moder.usec;
+		coal->tx_max_coalesced_frames = c->tx_cq_moder.pkts;
+	}
+
+	mutex_unlock(&priv->state_lock);
+
+	return 0;
+}
+
+int mlx5e_get_per_queue_coalesce(struct net_device *dev, u32 queue,
+				 struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return mlx5e_ethtool_get_per_queue_coalesce(priv, queue, coal);
+}
+
 #define MLX5E_MAX_COAL_TIME		MLX5_MAX_CQ_PERIOD
 #define MLX5E_MAX_COAL_FRAMES		MLX5_MAX_CQ_COUNT
 
 static void
-mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
+mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct dim_cq_moder *moder)
 {
 	int tc;
 	int i;
@@ -595,38 +663,35 @@ mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coal
 	for (i = 0; i < priv->channels.num; ++i) {
 		struct mlx5e_channel *c = priv->channels.c[i];
 		struct mlx5_core_dev *mdev = c->mdev;
+		enum mlx5_cq_period_mode mode;
+
+		mode = mlx5e_cq_period_mode(moder->cq_period_mode);
+		c->tx_cq_moder = *moder;
 
 		for (tc = 0; tc < c->num_tc; tc++) {
-			mlx5_core_modify_cq_moderation(mdev,
-						&c->sq[tc].cq.mcq,
-						coal->tx_coalesce_usecs,
-						coal->tx_max_coalesced_frames);
+			mlx5e_modify_cq_moderation(mdev, &c->sq[tc].cq.mcq,
+						   moder->usec, moder->pkts,
+						   mode);
 		}
 	}
 }
 
 static void
-mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
+mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct dim_cq_moder *moder)
 {
 	int i;
 
 	for (i = 0; i < priv->channels.num; ++i) {
 		struct mlx5e_channel *c = priv->channels.c[i];
 		struct mlx5_core_dev *mdev = c->mdev;
+		enum mlx5_cq_period_mode mode;
 
-		mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq,
-					       coal->rx_coalesce_usecs,
-					       coal->rx_max_coalesced_frames);
-	}
-}
+		mode = mlx5e_cq_period_mode(moder->cq_period_mode);
+		c->rx_cq_moder = *moder;
 
-/* convert a boolean value of cq_mode to mlx5 period mode
- * true  : MLX5_CQ_PERIOD_MODE_START_FROM_CQE
- * false : MLX5_CQ_PERIOD_MODE_START_FROM_EQE
- */
-static int cqe_mode_to_period_mode(bool val)
-{
-	return val ? MLX5_CQ_PERIOD_MODE_START_FROM_CQE : MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+		mlx5e_modify_cq_moderation(mdev, &c->rq.cq.mcq, moder->usec, moder->pkts,
+					   mode);
+	}
 }
 
 int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
@@ -636,13 +701,14 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 {
 	struct dim_cq_moder *rx_moder, *tx_moder;
 	struct mlx5_core_dev *mdev = priv->mdev;
+	bool rx_dim_enabled, tx_dim_enabled;
 	struct mlx5e_params new_params;
 	bool reset_rx, reset_tx;
-	bool reset = true;
 	u8 cq_period_mode;
 	int err = 0;
 
-	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+	if (!MLX5_CAP_GEN(mdev, cq_moderation) ||
+	    !MLX5_CAP_GEN(mdev, cq_period_mode_modify))
 		return -EOPNOTSUPP;
 
 	if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME ||
@@ -665,60 +731,70 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	rx_dim_enabled = !!coal->use_adaptive_rx_coalesce;
+	tx_dim_enabled = !!coal->use_adaptive_tx_coalesce;
+
 	mutex_lock(&priv->state_lock);
 	new_params = priv->channels.params;
 
-	rx_moder          = &new_params.rx_cq_moderation;
-	rx_moder->usec    = coal->rx_coalesce_usecs;
-	rx_moder->pkts    = coal->rx_max_coalesced_frames;
-	new_params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce;
+	cq_period_mode = mlx5e_dim_cq_period_mode(kernel_coal->use_cqe_mode_rx);
+	reset_rx = mlx5e_reset_rx_channels_moderation(&priv->channels, cq_period_mode,
+						      rx_dim_enabled, false);
+	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_BASED_MODER, cq_period_mode);
 
-	tx_moder          = &new_params.tx_cq_moderation;
-	tx_moder->usec    = coal->tx_coalesce_usecs;
-	tx_moder->pkts    = coal->tx_max_coalesced_frames;
-	new_params.tx_dim_enabled = !!coal->use_adaptive_tx_coalesce;
+	cq_period_mode = mlx5e_dim_cq_period_mode(kernel_coal->use_cqe_mode_tx);
+	reset_tx = mlx5e_reset_tx_channels_moderation(&priv->channels, cq_period_mode,
+						      tx_dim_enabled, false);
+	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_TX_CQE_BASED_MODER, cq_period_mode);
 
-	reset_rx = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled;
-	reset_tx = !!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled;
+	reset_rx |= rx_dim_enabled != new_params.rx_dim_enabled;
+	reset_tx |= tx_dim_enabled != new_params.tx_dim_enabled;
 
-	cq_period_mode = cqe_mode_to_period_mode(kernel_coal->use_cqe_mode_rx);
-	if (cq_period_mode != rx_moder->cq_period_mode) {
-		mlx5e_set_rx_cq_mode_params(&new_params, cq_period_mode);
-		reset_rx = true;
-	}
+	/* Solely used for global ethtool get coalesce */
+	rx_moder = &new_params.rx_cq_moderation;
+	new_params.rx_dim_enabled = rx_dim_enabled;
+	new_params.rx_moder_use_cqe_mode = kernel_coal->use_cqe_mode_rx;
 
-	cq_period_mode = cqe_mode_to_period_mode(kernel_coal->use_cqe_mode_tx);
-	if (cq_period_mode != tx_moder->cq_period_mode) {
-		mlx5e_set_tx_cq_mode_params(&new_params, cq_period_mode);
-		reset_tx = true;
-	}
+	tx_moder = &new_params.tx_cq_moderation;
+	new_params.tx_dim_enabled = tx_dim_enabled;
+	new_params.tx_moder_use_cqe_mode = kernel_coal->use_cqe_mode_tx;
 
 	if (reset_rx) {
-		u8 mode = MLX5E_GET_PFLAG(&new_params,
-					  MLX5E_PFLAG_RX_CQE_BASED_MODER);
+		mlx5e_channels_rx_change_dim(&priv->channels, false);
+		mlx5e_reset_rx_moderation(rx_moder, new_params.rx_moder_use_cqe_mode,
+					  rx_dim_enabled);
+
+		mlx5e_set_priv_channels_rx_coalesce(priv, rx_moder);
+	} else if (!rx_dim_enabled) {
+		rx_moder->usec = coal->rx_coalesce_usecs;
+		rx_moder->pkts = coal->rx_max_coalesced_frames;
 
-		mlx5e_reset_rx_moderation(&new_params, mode);
+		mlx5e_set_priv_channels_rx_coalesce(priv, rx_moder);
 	}
+
 	if (reset_tx) {
-		u8 mode = MLX5E_GET_PFLAG(&new_params,
-					  MLX5E_PFLAG_TX_CQE_BASED_MODER);
+		mlx5e_channels_tx_change_dim(&priv->channels, false);
+		mlx5e_reset_tx_moderation(tx_moder, new_params.tx_moder_use_cqe_mode,
+					  tx_dim_enabled);
 
-		mlx5e_reset_tx_moderation(&new_params, mode);
-	}
+		mlx5e_set_priv_channels_tx_coalesce(priv, tx_moder);
+	} else if (!tx_dim_enabled) {
+		tx_moder->usec = coal->tx_coalesce_usecs;
+		tx_moder->pkts = coal->tx_max_coalesced_frames;
 
-	/* If DIM state hasn't changed, it's possible to modify interrupt
-	 * moderation parameters on the fly, even if the channels are open.
-	 */
-	if (!reset_rx && !reset_tx && test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		if (!coal->use_adaptive_rx_coalesce)
-			mlx5e_set_priv_channels_rx_coalesce(priv, coal);
-		if (!coal->use_adaptive_tx_coalesce)
-			mlx5e_set_priv_channels_tx_coalesce(priv, coal);
-		reset = false;
+		mlx5e_set_priv_channels_tx_coalesce(priv, tx_moder);
 	}
 
-	err = mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, reset);
+	/* DIM enable/disable Rx and Tx channels */
+	err = mlx5e_channels_rx_change_dim(&priv->channels, rx_dim_enabled);
+	if (err)
+		goto state_unlock;
+	err = mlx5e_channels_tx_change_dim(&priv->channels, tx_dim_enabled);
+	if (err)
+		goto state_unlock;
 
+	err = mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, false);
+state_unlock:
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
@@ -733,6 +809,88 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	return mlx5e_ethtool_set_coalesce(priv, coal, kernel_coal, extack);
 }
 
+static int mlx5e_ethtool_set_per_queue_coalesce(struct mlx5e_priv *priv, u32 queue,
+						struct ethtool_coalesce *coal)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	bool rx_dim_enabled, tx_dim_enabled;
+	struct mlx5e_channels *chs;
+	struct mlx5e_channel *c;
+	int err = 0;
+	int tc;
+
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		return -EOPNOTSUPP;
+
+	if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs > MLX5E_MAX_COAL_TIME) {
+		netdev_info(priv->netdev, "%s: maximum coalesce time supported is %lu usecs\n",
+			    __func__, MLX5E_MAX_COAL_TIME);
+		return -ERANGE;
+	}
+
+	if (coal->tx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES ||
+	    coal->rx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES) {
+		netdev_info(priv->netdev, "%s: maximum coalesced frames supported is %lu\n",
+			    __func__, MLX5E_MAX_COAL_FRAMES);
+		return -ERANGE;
+	}
+
+	rx_dim_enabled = !!coal->use_adaptive_rx_coalesce;
+	tx_dim_enabled = !!coal->use_adaptive_tx_coalesce;
+
+	mutex_lock(&priv->state_lock);
+
+	chs = &priv->channels;
+	if (chs->num <= queue) {
+		mutex_unlock(&priv->state_lock);
+		return -EINVAL;
+	}
+
+	c = chs->c[queue];
+
+	err = mlx5e_dim_rx_change(&c->rq, rx_dim_enabled);
+	if (err)
+		goto state_unlock;
+
+	for (tc = 0; tc < c->num_tc; tc++) {
+		err = mlx5e_dim_tx_change(&c->sq[tc], tx_dim_enabled);
+		if (err)
+			goto state_unlock;
+	}
+
+	if (!rx_dim_enabled) {
+		c->rx_cq_moder.usec = coal->rx_coalesce_usecs;
+		c->rx_cq_moder.pkts = coal->rx_max_coalesced_frames;
+
+		mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq,
+					       coal->rx_coalesce_usecs,
+					       coal->rx_max_coalesced_frames);
+	}
+
+	if (!tx_dim_enabled) {
+		c->tx_cq_moder.usec = coal->tx_coalesce_usecs;
+		c->tx_cq_moder.pkts = coal->tx_max_coalesced_frames;
+
+		for (tc = 0; tc < c->num_tc; tc++)
+			mlx5_core_modify_cq_moderation(mdev, &c->sq[tc].cq.mcq,
+						       coal->tx_coalesce_usecs,
+						       coal->tx_max_coalesced_frames);
+	}
+
+state_unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
+				 struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal);
+}
+
 static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
 					unsigned long *supported_modes,
 					u32 eth_proto_cap)
@@ -1018,8 +1176,8 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
 
-int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
-				     struct ethtool_link_ksettings *link_ksettings)
+static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
+					    struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {};
@@ -1189,8 +1347,8 @@ static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_suppo
 	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
 }
 
-int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
-				     const struct ethtool_link_ksettings *link_ksettings)
+static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+					    const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_port_eth_proto eproto;
@@ -1290,7 +1448,7 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
+static int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 rss_context = rxfh->rss_context;
@@ -1303,8 +1461,8 @@ int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 	return err;
 }
 
-int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
-		   struct netlink_ext_ack *extack)
+static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	u32 *rss_context = &rxfh->rss_context;
@@ -1446,8 +1604,8 @@ static void mlx5e_get_pause_stats(struct net_device *netdev,
 	mlx5e_stats_pause_get(priv, pause_stats);
 }
 
-void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
-				  struct ethtool_pauseparam *pauseparam)
+static void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
+					 struct ethtool_pauseparam *pauseparam)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
@@ -1468,8 +1626,8 @@ static void mlx5e_get_pauseparam(struct net_device *netdev,
 	mlx5e_ethtool_get_pauseparam(priv, pauseparam);
 }
 
-int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
-				 struct ethtool_pauseparam *pauseparam)
+static int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
+					struct ethtool_pauseparam *pauseparam)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
@@ -1908,7 +2066,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 	if (enable && !MLX5_CAP_GEN(priv->mdev, cq_period_start_from_cqe))
 		return -EOPNOTSUPP;
 
-	cq_period_mode = cqe_mode_to_period_mode(enable);
+	cq_period_mode = mlx5e_dim_cq_period_mode(enable);
 
 	current_cq_period_mode = is_rx_cq ?
 		priv->channels.params.rx_cq_moderation.cq_period_mode :
@@ -1918,12 +2076,22 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 		return 0;
 
 	new_params = priv->channels.params;
-	if (is_rx_cq)
-		mlx5e_set_rx_cq_mode_params(&new_params, cq_period_mode);
-	else
-		mlx5e_set_tx_cq_mode_params(&new_params, cq_period_mode);
+	if (is_rx_cq) {
+		mlx5e_reset_rx_channels_moderation(&priv->channels, cq_period_mode,
+						   false, true);
+		mlx5e_channels_rx_toggle_dim(&priv->channels);
+		MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
+				cq_period_mode);
+	} else {
+		mlx5e_reset_tx_channels_moderation(&priv->channels, cq_period_mode,
+						   false, true);
+		mlx5e_channels_tx_toggle_dim(&priv->channels);
+		MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
+				cq_period_mode);
+	}
 
-	return mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, true);
+	/* Update pflags of existing channels without resetting them */
+	return mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, false);
 }
 
 static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable)
@@ -2124,7 +2292,7 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable)
 	 */
 
 	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_num_channels_changed_ctx, NULL, true);
+				       mlx5e_update_tc_and_tx_queues_ctx, NULL, true);
 	if (!err)
 		priv->tx_ptp_opened = true;
 
@@ -2422,6 +2590,14 @@ static void mlx5e_get_rmon_stats(struct net_device *netdev,
 	mlx5e_stats_rmon_get(priv, rmon_stats, ranges);
 }
 
+static void mlx5e_get_ts_stats(struct net_device *netdev,
+			       struct ethtool_ts_stats *ts_stats)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5e_stats_ts_get(priv, ts_stats);
+}
+
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
@@ -2440,6 +2616,8 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.set_channels      = mlx5e_set_channels,
 	.get_coalesce      = mlx5e_get_coalesce,
 	.set_coalesce      = mlx5e_set_coalesce,
+	.get_per_queue_coalesce = mlx5e_get_per_queue_coalesce,
+	.set_per_queue_coalesce = mlx5e_set_per_queue_coalesce,
 	.get_link_ksettings  = mlx5e_get_link_ksettings,
 	.set_link_ksettings  = mlx5e_set_link_ksettings,
 	.get_rxfh_key_size   = mlx5e_get_rxfh_key_size,
@@ -2471,5 +2649,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_eth_mac_stats = mlx5e_get_eth_mac_stats,
 	.get_eth_ctrl_stats = mlx5e_get_eth_ctrl_stats,
 	.get_rmon_stats    = mlx5e_get_rmon_stats,
+	.get_ts_stats      = mlx5e_get_ts_stats,
 	.get_link_ext_stats = mlx5e_get_link_ext_stats
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 777d311d44ef..8c5b291a171f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -896,8 +896,7 @@ static void mlx5e_set_inner_ttc_params(struct mlx5e_flow_steering *fs,
 	int tt;
 
 	memset(ttc_params, 0, sizeof(*ttc_params));
-	ttc_params->ns = mlx5_get_flow_namespace(fs->mdev,
-						 MLX5_FLOW_NAMESPACE_KERNEL);
+	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 	ft_attr->level = MLX5E_INNER_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_NIC_PRIO;
 
@@ -920,8 +919,7 @@ void mlx5e_set_ttc_params(struct mlx5e_flow_steering *fs,
 	int tt;
 
 	memset(ttc_params, 0, sizeof(*ttc_params));
-	ttc_params->ns = mlx5_get_flow_namespace(fs->mdev,
-						 MLX5_FLOW_NAMESPACE_KERNEL);
+	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 	ft_attr->level = MLX5E_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_NIC_PRIO;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 319930c04093..b758bc72ac36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/dim.h>
 #include <net/tc_act/tc_gact.h>
 #include <linux/mlx5/fs.h>
 #include <net/vxlan.h>
@@ -43,6 +44,7 @@
 #include <net/xdp_sock_drv.h>
 #include "eswitch.h"
 #include "en.h"
+#include "en/dim.h"
 #include "en/txrx.h"
 #include "en_tc.h"
 #include "en_rep.h"
@@ -960,17 +962,6 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		}
 	}
 
-	INIT_WORK(&rq->dim.work, mlx5e_rx_dim_work);
-
-	switch (params->rx_cq_moderation.cq_period_mode) {
-	case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
-		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
-		break;
-	case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
-	default:
-		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
-	}
-
 	return 0;
 
 err_destroy_page_pool:
@@ -1020,6 +1011,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 		mlx5e_free_wqe_alloc_info(rq);
 	}
 
+	kvfree(rq->dim);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
 	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
@@ -1300,8 +1292,21 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 	if (MLX5_CAP_ETH(mdev, cqe_checksum_full))
 		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state);
 
-	if (params->rx_dim_enabled)
-		__set_bit(MLX5E_RQ_STATE_DIM, &rq->state);
+	if (rq->channel && !params->rx_dim_enabled) {
+		rq->channel->rx_cq_moder = params->rx_cq_moderation;
+	} else if (rq->channel) {
+		u8 cq_period_mode;
+
+		cq_period_mode = params->rx_moder_use_cqe_mode ?
+					 DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+					 DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		mlx5e_reset_rx_moderation(&rq->channel->rx_cq_moder, cq_period_mode,
+					  params->rx_dim_enabled);
+
+		err = mlx5e_dim_rx_change(rq, params->rx_dim_enabled);
+		if (err)
+			goto err_destroy_rq;
+	}
 
 	/* We disable csum_complete when XDP is enabled since
 	 * XDP programs might manipulate packets which will render
@@ -1347,7 +1352,8 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
-	cancel_work_sync(&rq->dim.work);
+	if (rq->dim)
+		cancel_work_sync(&rq->dim->work);
 	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
@@ -1623,9 +1629,6 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
-	INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work);
-	sq->dim.mode = params->tx_cq_moderation.cq_period_mode;
-
 	return 0;
 
 err_sq_wq_destroy:
@@ -1636,6 +1639,7 @@ err_sq_wq_destroy:
 
 void mlx5e_free_txqsq(struct mlx5e_txqsq *sq)
 {
+	kvfree(sq->dim);
 	mlx5e_free_txqsq_db(sq);
 	mlx5_wq_destroy(&sq->wq_ctrl);
 }
@@ -1791,11 +1795,27 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
 	if (tx_rate)
 		mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
 
-	if (params->tx_dim_enabled)
-		sq->state |= BIT(MLX5E_SQ_STATE_DIM);
+	if (sq->channel && !params->tx_dim_enabled) {
+		sq->channel->tx_cq_moder = params->tx_cq_moderation;
+	} else if (sq->channel) {
+		u8 cq_period_mode;
+
+		cq_period_mode = params->tx_moder_use_cqe_mode ?
+					 DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+					 DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		mlx5e_reset_tx_moderation(&sq->channel->tx_cq_moder,
+					  cq_period_mode,
+					  params->tx_dim_enabled);
+
+		err = mlx5e_dim_tx_change(sq, params->tx_dim_enabled);
+		if (err)
+			goto err_destroy_sq;
+	}
 
 	return 0;
 
+err_destroy_sq:
+	mlx5e_destroy_sq(c->mdev, sq->sqn);
 err_free_txqsq:
 	mlx5e_free_txqsq(sq);
 
@@ -1847,7 +1867,8 @@ void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	struct mlx5_core_dev *mdev = sq->mdev;
 	struct mlx5_rate_limit rl = {0};
 
-	cancel_work_sync(&sq->dim.work);
+	if (sq->dim)
+		cancel_work_sync(&sq->dim->work);
 	cancel_work_sync(&sq->recover_work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
@@ -1866,6 +1887,49 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_tx_err_cqe(sq);
 }
 
+static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
+{
+	return (struct dim_cq_moder) {
+		.cq_period_mode = cq_period_mode,
+		.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS,
+		.usec = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+				MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE :
+				MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC,
+	};
+}
+
+bool mlx5e_reset_tx_moderation(struct dim_cq_moder *cq_moder, u8 cq_period_mode,
+			       bool dim_enabled)
+{
+	bool reset_needed = cq_moder->cq_period_mode != cq_period_mode;
+
+	if (dim_enabled)
+		*cq_moder = net_dim_get_def_tx_moderation(cq_period_mode);
+	else
+		*cq_moder = mlx5e_get_def_tx_moderation(cq_period_mode);
+
+	return reset_needed;
+}
+
+bool mlx5e_reset_tx_channels_moderation(struct mlx5e_channels *chs, u8 cq_period_mode,
+					bool dim_enabled, bool keep_dim_state)
+{
+	bool reset = false;
+	int i, tc;
+
+	for (i = 0; i < chs->num; i++) {
+		for (tc = 0; tc < mlx5e_get_dcb_num_tc(&chs->params); tc++) {
+			if (keep_dim_state)
+				dim_enabled = !!chs->c[i]->sq[tc].dim;
+
+			reset |= mlx5e_reset_tx_moderation(&chs->c[i]->tx_cq_moder,
+							   cq_period_mode, dim_enabled);
+		}
+	}
+
+	return reset;
+}
+
 static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
 			    struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
 			    work_func_t recover_work_func)
@@ -2089,7 +2153,8 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
+	MLX5_SET(cqc, cqc, cq_period_mode, mlx5e_cq_period_mode(param->cq_period_mode));
+
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
@@ -2127,8 +2192,10 @@ int mlx5e_open_cq(struct mlx5_core_dev *mdev, struct dim_cq_moder moder,
 	if (err)
 		goto err_free_cq;
 
-	if (MLX5_CAP_GEN(mdev, cq_moderation))
-		mlx5_core_modify_cq_moderation(mdev, &cq->mcq, moder.usec, moder.pkts);
+	if (MLX5_CAP_GEN(mdev, cq_moderation) &&
+	    MLX5_CAP_GEN(mdev, cq_period_mode_modify))
+		mlx5e_modify_cq_moderation(mdev, &cq->mcq, moder.usec, moder.pkts,
+					   mlx5e_cq_period_mode(moder.cq_period_mode));
 	return 0;
 
 err_free_cq:
@@ -2143,6 +2210,40 @@ void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
+int mlx5e_modify_cq_period_mode(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
+				u8 cq_period_mode)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_cq_in)] = {};
+	void *cqc;
+
+	MLX5_SET(modify_cq_in, in, cqn, cq->cqn);
+	cqc = MLX5_ADDR_OF(modify_cq_in, in, cq_context);
+	MLX5_SET(cqc, cqc, cq_period_mode, mlx5e_cq_period_mode(cq_period_mode));
+	MLX5_SET(modify_cq_in, in,
+		 modify_field_select_resize_field_select.modify_field_select.modify_field_select,
+		 MLX5_CQ_MODIFY_PERIOD_MODE);
+
+	return mlx5_core_modify_cq(dev, cq, in, sizeof(in));
+}
+
+int mlx5e_modify_cq_moderation(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
+			       u16 cq_period, u16 cq_max_count, u8 cq_period_mode)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_cq_in)] = {};
+	void *cqc;
+
+	MLX5_SET(modify_cq_in, in, cqn, cq->cqn);
+	cqc = MLX5_ADDR_OF(modify_cq_in, in, cq_context);
+	MLX5_SET(cqc, cqc, cq_period, cq_period);
+	MLX5_SET(cqc, cqc, cq_max_count, cq_max_count);
+	MLX5_SET(cqc, cqc, cq_period_mode, cq_period_mode);
+	MLX5_SET(modify_cq_in, in,
+		 modify_field_select_resize_field_select.modify_field_select.modify_field_select,
+		 MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT | MLX5_CQ_MODIFY_PERIOD_MODE);
+
+	return mlx5_core_modify_cq(dev, cq, in, sizeof(in));
+}
+
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_create_cq_param *ccp,
@@ -2901,7 +3002,28 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
 	return err;
 }
 
-static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
+static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
+					   struct mlx5e_params *params)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int num_comp_vectors, ix, irq;
+
+	num_comp_vectors = mlx5_comp_vectors_max(mdev);
+
+	for (ix = 0; ix < params->num_channels; ix++) {
+		cpumask_clear(priv->scratchpad.cpumask);
+
+		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
+			int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
+
+			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
+		}
+
+		netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix);
+	}
+}
+
+static int mlx5e_update_tc_and_tx_queues(struct mlx5e_priv *priv)
 {
 	struct netdev_tc_txq old_tc_to_txq[TC_MAX_QUEUE], *tc_to_txq;
 	struct net_device *netdev = priv->netdev;
@@ -2925,22 +3047,10 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	err = mlx5e_update_tx_netdev_queues(priv);
 	if (err)
 		goto err_tcs;
-	err = netif_set_real_num_rx_queues(netdev, nch);
-	if (err) {
-		netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err);
-		goto err_txqs;
-	}
+	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
 
 	return 0;
 
-err_txqs:
-	/* netif_set_real_num_rx_queues could fail only when nch increased. Only
-	 * one of nch and ntc is changed in this function. That means, the call
-	 * to netif_set_real_num_tx_queues below should not fail, because it
-	 * decreases the number of TX queues.
-	 */
-	WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs));
-
 err_tcs:
 	WARN_ON_ONCE(mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc,
 					  old_tc_to_txq));
@@ -2948,42 +3058,32 @@ err_out:
 	return err;
 }
 
-static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues);
-
-static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
-					   struct mlx5e_params *params)
-{
-	int ix;
-
-	for (ix = 0; ix < params->num_channels; ix++) {
-		int num_comp_vectors, irq, vec_ix;
-		struct mlx5_core_dev *mdev;
-
-		mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
-		num_comp_vectors = mlx5_comp_vectors_max(mdev);
-		cpumask_clear(priv->scratchpad.cpumask);
-		vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
-
-		for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) {
-			int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
-
-			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
-		}
-
-		netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix);
-	}
-}
+MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_tc_and_tx_queues);
 
 static int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
 {
 	u16 count = priv->channels.params.num_channels;
+	struct net_device *netdev = priv->netdev;
+	int old_num_rxqs;
 	int err;
 
-	err = mlx5e_update_netdev_queues(priv);
-	if (err)
+	old_num_rxqs = netdev->real_num_rx_queues;
+	err = netif_set_real_num_rx_queues(netdev, count);
+	if (err) {
+		netdev_warn(netdev, "%s: netif_set_real_num_rx_queues failed, %d\n",
+			    __func__, err);
 		return err;
-
-	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
+	}
+	err = mlx5e_update_tc_and_tx_queues(priv);
+	if (err) {
+		/* mlx5e_update_tc_and_tx_queues can fail if channels or TCs number increases.
+		 * Since channel number changed, it increased. That means, the call to
+		 * netif_set_real_num_rx_queues below should not fail, because it
+		 * decreases the number of RX queues.
+		 */
+		WARN_ON_ONCE(netif_set_real_num_rx_queues(netdev, old_num_rxqs));
+		return err;
+	}
 
 	/* This function may be called on attach, before priv->rx_res is created. */
 	if (priv->rx_res) {
@@ -3516,7 +3616,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
 	mlx5e_params_mqprio_dcb_set(&new_params, tc ? tc : 1);
 
 	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_num_channels_changed_ctx, NULL, true);
+				       mlx5e_update_tc_and_tx_queues_ctx, NULL, true);
 
 	if (!err && priv->mqprio_rl) {
 		mlx5e_mqprio_rl_cleanup(priv->mqprio_rl);
@@ -3617,10 +3717,8 @@ static struct mlx5e_mqprio_rl *mlx5e_mqprio_rl_create(struct mlx5_core_dev *mdev
 static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
 					 struct tc_mqprio_qopt_offload *mqprio)
 {
-	mlx5e_fp_preactivate preactivate;
 	struct mlx5e_params new_params;
 	struct mlx5e_mqprio_rl *rl;
-	bool nch_changed;
 	int err;
 
 	err = mlx5e_mqprio_channel_validate(priv, mqprio);
@@ -3634,10 +3732,8 @@ static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
 	new_params = priv->channels.params;
 	mlx5e_params_mqprio_channel_set(&new_params, mqprio, rl);
 
-	nch_changed = mlx5e_get_dcb_num_tc(&priv->channels.params) > 1;
-	preactivate = nch_changed ? mlx5e_num_channels_changed_ctx :
-		mlx5e_update_netdev_queues_ctx;
-	err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true);
+	err = mlx5e_safe_switch_params(priv, &new_params,
+				       mlx5e_update_tc_and_tx_queues_ctx, NULL, true);
 	if (err) {
 		if (rl) {
 			mlx5e_mqprio_rl_cleanup(rl);
@@ -3960,6 +4056,47 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable)
 	return mlx5_set_port_fcs(mdev, !enable);
 }
 
+static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+{
+	return (struct dim_cq_moder) {
+		.cq_period_mode = cq_period_mode,
+		.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS,
+		.usec = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+				MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE :
+				MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC,
+	};
+}
+
+bool mlx5e_reset_rx_moderation(struct dim_cq_moder *cq_moder, u8 cq_period_mode,
+			       bool dim_enabled)
+{
+	bool reset_needed = cq_moder->cq_period_mode != cq_period_mode;
+
+	if (dim_enabled)
+		*cq_moder = net_dim_get_def_rx_moderation(cq_period_mode);
+	else
+		*cq_moder = mlx5e_get_def_rx_moderation(cq_period_mode);
+
+	return reset_needed;
+}
+
+bool mlx5e_reset_rx_channels_moderation(struct mlx5e_channels *chs, u8 cq_period_mode,
+					bool dim_enabled, bool keep_dim_state)
+{
+	bool reset = false;
+	int i;
+
+	for (i = 0; i < chs->num; i++) {
+		if (keep_dim_state)
+			dim_enabled = !!chs->c[i]->rq.dim;
+
+		reset |= mlx5e_reset_rx_moderation(&chs->c[i]->rx_cq_moder,
+						   cq_period_mode, dim_enabled);
+	}
+
+	return reset;
+}
+
 static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable)
 {
 	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {};
@@ -4383,7 +4520,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, reset);
 
 out:
-	netdev->mtu = params->sw_mtu;
+	WRITE_ONCE(netdev->mtu, params->sw_mtu);
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
@@ -4950,10 +5087,7 @@ static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
 		mode = nla_get_u16(attr);
 		if (mode > BRIDGE_MODE_VEPA)
 			return -EINVAL;
@@ -5027,7 +5161,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 {
 	struct mlx5e_params *params = &priv->channels.params;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u8 rx_cq_period_mode;
 
 	params->sw_mtu = mtu;
 	params->hard_mtu = MLX5E_ETH_HARD_MTU;
@@ -5061,13 +5194,16 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
-	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
-			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
-			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
-	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
-	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
+	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation) &&
+				 MLX5_CAP_GEN(mdev, cq_period_mode_modify);
+	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation) &&
+				 MLX5_CAP_GEN(mdev, cq_period_mode_modify);
+	params->rx_moder_use_cqe_mode = !!MLX5_CAP_GEN(mdev, cq_period_start_from_cqe);
+	params->tx_moder_use_cqe_mode = false;
+	mlx5e_reset_rx_moderation(&params->rx_cq_moderation, params->rx_moder_use_cqe_mode,
+				  params->rx_dim_enabled);
+	mlx5e_reset_tx_moderation(&params->tx_cq_moderation, params->tx_moder_use_cqe_mode,
+				  params->tx_dim_enabled);
 
 	/* TX inline */
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
@@ -5565,7 +5701,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	mlx5e_ipsec_cleanup(priv);
 }
 
-int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
+static int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
 {
 	return mlx5e_refresh_tirs(priv, false, false);
 }
@@ -6058,7 +6194,7 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 	return 0;
 }
 
-static int _mlx5e_suspend(struct auxiliary_device *adev)
+static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg)
 {
 	struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev);
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
@@ -6067,7 +6203,7 @@ static int _mlx5e_suspend(struct auxiliary_device *adev)
 	struct mlx5_core_dev *pos;
 	int i;
 
-	if (!netif_device_present(netdev)) {
+	if (!pre_netdev_reg && !netif_device_present(netdev)) {
 		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
 			mlx5_sd_for_each_dev(i, mdev, pos)
 				mlx5e_destroy_mdev_resources(pos);
@@ -6090,7 +6226,7 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 
 	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
 	if (actual_adev)
-		err = _mlx5e_suspend(actual_adev);
+		err = _mlx5e_suspend(actual_adev, false);
 
 	mlx5_sd_cleanup(mdev);
 	return err;
@@ -6157,7 +6293,7 @@ static int _mlx5e_probe(struct auxiliary_device *adev)
 	return 0;
 
 err_resume:
-	_mlx5e_suspend(adev);
+	_mlx5e_suspend(adev, true);
 err_profile_cleanup:
 	profile->cleanup(priv);
 err_destroy_netdev:
@@ -6197,7 +6333,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev)
 	mlx5_core_uplink_netdev_set(mdev, NULL);
 	mlx5e_dcbnl_delete_app(priv);
 	unregister_netdev(priv->netdev);
-	_mlx5e_suspend(adev);
+	_mlx5e_suspend(adev, false);
 	priv->profile->cleanup(priv);
 	mlx5e_destroy_netdev(priv);
 	mlx5e_devlink_port_unregister(mlx5e_dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 05527418fa64..8790d57dc6db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/dim.h>
 #include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
 #include <net/switchdev.h>
@@ -40,6 +41,7 @@
 
 #include "eswitch.h"
 #include "en.h"
+#include "en/dim.h"
 #include "en_rep.h"
 #include "en/params.h"
 #include "en/txrx.h"
@@ -135,9 +137,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(sw_rep)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       sw_rep_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, sw_rep_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw_rep)
@@ -145,9 +145,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw_rep)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
-						   sw_rep_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(&priv->stats.sw,
+						   sw_rep_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw_rep)
@@ -176,11 +176,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport_rep)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_rep_stats_desc[i].format);
+		ethtool_puts(data, vport_rep_stats_desc[i].format);
 	for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vport_rep_loopback_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, vport_rep_loopback_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep)
@@ -188,12 +186,14 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport_rep)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_REP_HW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
-						   vport_rep_stats_desc, i);
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
+						   vport_rep_stats_desc, i));
 	for (i = 0; i < NUM_VPORT_REP_LOOPBACK_COUNTERS(priv->mdev); i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
-						   vport_rep_loopback_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_CPU(&priv->stats.rep_stats,
+					     vport_rep_loopback_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep)
@@ -275,8 +275,42 @@ out:
 	kvfree(out);
 }
 
+static int mlx5e_rep_query_aggr_q_counter(struct mlx5_core_dev *dev, int vport, void *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
+
+	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
+	MLX5_SET(query_q_counter_in, in, other_vport, 1);
+	MLX5_SET(query_q_counter_in, in, vport_number, vport);
+	MLX5_SET(query_q_counter_in, in, aggregate, 1);
+
+	return mlx5_cmd_exec_inout(dev, query_q_counter, in, out);
+}
+
+static void mlx5e_rep_update_vport_q_counter(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_stats *rep_stats = &priv->stats.rep_stats;
+	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	int err;
+
+	if (!MLX5_CAP_GEN(priv->mdev, q_counter_other_vport) ||
+	    !MLX5_CAP_GEN(priv->mdev, q_counter_aggregation))
+		return;
+
+	err = mlx5e_rep_query_aggr_q_counter(priv->mdev, rep->vport, out);
+	if (err) {
+		netdev_warn(priv->netdev, "failed reading stats on vport %d, error %d\n",
+			    rep->vport, err);
+		return;
+	}
+
+	rep_stats->rx_vport_out_of_buffer = MLX5_GET(query_q_counter_out, out, out_of_buffer);
+}
+
 static void mlx5e_rep_get_strings(struct net_device *dev,
-				  u32 stringset, uint8_t *data)
+				  u32 stringset, u8 *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -394,6 +428,8 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 	.set_channels      = mlx5e_rep_set_channels,
 	.get_coalesce      = mlx5e_rep_get_coalesce,
 	.set_coalesce      = mlx5e_rep_set_coalesce,
+	.get_per_queue_coalesce = mlx5e_get_per_queue_coalesce,
+	.set_per_queue_coalesce = mlx5e_set_per_queue_coalesce,
 	.get_rxfh_key_size   = mlx5e_rep_get_rxfh_key_size,
 	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
 };
@@ -804,10 +840,6 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_params *params;
 
-	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
-					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
-					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
-
 	params = &priv->channels.params;
 
 	params->num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS;
@@ -835,7 +867,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	/* CQ moderation params */
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
+	params->rx_moder_use_cqe_mode = !!MLX5_CAP_GEN(mdev, cq_period_start_from_cqe);
 
 	params->mqprio.num_tc       = 1;
 	if (rep->vport != MLX5_VPORT_UPLINK)
@@ -1231,6 +1263,12 @@ static int mlx5e_update_rep_rx(struct mlx5e_priv *priv)
 	return 0;
 }
 
+static void mlx5e_rep_stats_update_ndo_stats(struct mlx5e_priv *priv)
+{
+	mlx5e_stats_update_ndo_stats(priv);
+	mlx5e_rep_update_vport_q_counter(priv);
+}
+
 static int mlx5e_rep_event_mpesw(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1423,7 +1461,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.enable		        = mlx5e_rep_enable,
 	.disable	        = mlx5e_rep_disable,
 	.update_rx		= mlx5e_update_rep_rx,
-	.update_stats           = mlx5e_stats_update_ndo_stats,
+	.update_stats           = mlx5e_rep_stats_update_ndo_stats,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= 1,
 	.stats_grps		= mlx5e_rep_stats_grps,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 08a75654f5f1..5bf8318cc48b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -359,7 +359,7 @@ int mlx5e_self_test_fill_strings(struct mlx5e_priv *priv, u8 *data)
 		if (st.cond_func && st.cond_func(priv))
 			continue;
 		if (data)
-			strcpy(data + count * ETH_GSTRING_LEN, st.name);
+			ethtool_puts(&data, st.name);
 		count++;
 	}
 	return count;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index f3d0898bdbc6..e211c41cec06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -41,6 +41,11 @@
 #include <net/page_pool/helpers.h>
 #endif
 
+void mlx5e_ethtool_put_stat(u64 **data, u64 val)
+{
+	*(*data)++ = val;
+}
+
 static unsigned int stats_grps_num(struct mlx5e_priv *priv)
 {
 	return !priv->profile->stats_grps_num ? 0 :
@@ -90,17 +95,17 @@ void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx)
 	int i;
 
 	for (i = 0; i < num_stats_grps; i++)
-		idx = stats_grps[i]->fill_stats(priv, data, idx);
+		stats_grps[i]->fill_stats(priv, &data);
 }
 
 void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data)
 {
 	mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
 	const unsigned int num_stats_grps = stats_grps_num(priv);
-	int i, idx = 0;
+	int i;
 
 	for (i = 0; i < num_stats_grps; i++)
-		idx = stats_grps[i]->fill_strings(priv, data, idx);
+		stats_grps[i]->fill_strings(priv, &data);
 }
 
 /* Concrete NIC Stats */
@@ -257,8 +262,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(sw)
 	int i;
 
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, sw_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw)
@@ -266,8 +270,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(sw)
 	int i;
 
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->stats.sw, sw_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(data,
+				       MLX5E_READ_CTR64_CPU(&priv->stats.sw,
+							    sw_stats_desc, i));
 }
 
 static void mlx5e_stats_grp_sw_update_stats_xdp_red(struct mlx5e_sw_stats *s,
@@ -591,14 +596,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt)
 	int i;
 
 	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       q_stats_desc[i].format);
+		ethtool_puts(data, q_stats_desc[i].format);
 
 	for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       drop_rq_stats_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, drop_rq_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
@@ -606,12 +607,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
 	int i;
 
 	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
-		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
-						   q_stats_desc, i);
+		mlx5e_ethtool_put_stat(data,
+				       MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
+							    q_stats_desc, i));
 	for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
-		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
-						   drop_rq_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
+						   drop_rq_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt)
@@ -685,18 +687,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vnic_env)
 	int i;
 
 	for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vnic_env_stats_steer_desc[i].format);
+		ethtool_puts(data, vnic_env_stats_steer_desc[i].format);
 
 	for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vnic_env_stats_dev_oob_desc[i].format);
+		ethtool_puts(data, vnic_env_stats_dev_oob_desc[i].format);
 
 	for (i = 0; i < NUM_VNIC_ENV_DROP_COUNTERS(priv->mdev); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vnic_env_stats_drop_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, vnic_env_stats_drop_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vnic_env)
@@ -704,18 +701,22 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vnic_env)
 	int i;
 
 	for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vnic.query_vnic_env_out,
-						  vnic_env_stats_steer_desc, i);
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(priv->stats.vnic.query_vnic_env_out,
+					    vnic_env_stats_steer_desc, i));
 
 	for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
-						  vnic_env_stats_dev_oob_desc, i);
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
+					    vnic_env_stats_dev_oob_desc, i));
 
 	for (i = 0; i < NUM_VNIC_ENV_DROP_COUNTERS(priv->mdev); i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
-						  vnic_env_stats_drop_desc, i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
+					    vnic_env_stats_drop_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env)
@@ -798,13 +799,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vport)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, vport_stats_desc[i].format);
+		ethtool_puts(data, vport_stats_desc[i].format);
 
 	for (i = 0; i < NUM_VPORT_LOOPBACK_COUNTERS(priv->mdev); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vport_loopback_stats_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, vport_loopback_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport)
@@ -812,14 +810,16 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport)
 	int i;
 
 	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
-						  vport_stats_desc, i);
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
+					    vport_stats_desc, i));
 
 	for (i = 0; i < NUM_VPORT_LOOPBACK_COUNTERS(priv->mdev); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
-						  vport_loopback_stats_desc, i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(priv->stats.vport.query_vport_out,
+					    vport_loopback_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport)
@@ -868,8 +868,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(802_3)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_802_3_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, pport_802_3_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(802_3)
@@ -877,9 +876,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(802_3)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.IEEE_802_3_counters,
-						  pport_802_3_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_BE(
+				      &priv->stats.pport.IEEE_802_3_counters,
+				      pport_802_3_stats_desc, i));
 }
 
 #define MLX5_BASIC_PPCNT_SUPPORTED(mdev) \
@@ -1029,8 +1029,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(2863)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2863_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, pport_2863_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2863)
@@ -1038,9 +1037,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2863)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2863_counters,
-						  pport_2863_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_BE(
+				      &priv->stats.pport.RFC_2863_counters,
+				      pport_2863_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(2863)
@@ -1088,8 +1088,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(2819)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2819_stats_desc[i].format);
-	return idx;
+		ethtool_puts(data, pport_2819_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2819)
@@ -1097,9 +1096,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(2819)
 	int i;
 
 	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
-						  pport_2819_stats_desc, i);
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_BE(
+				      &priv->stats.pport.RFC_2819_counters,
+				      pport_2819_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(2819)
@@ -1172,6 +1172,51 @@ void mlx5e_stats_rmon_get(struct mlx5e_priv *priv,
 	*ranges = mlx5e_rmon_ranges;
 }
 
+void mlx5e_stats_ts_get(struct mlx5e_priv *priv,
+			struct ethtool_ts_stats *ts_stats)
+{
+	int i, j;
+
+	mutex_lock(&priv->state_lock);
+
+	if (priv->tx_ptp_opened) {
+		struct mlx5e_ptp *ptp = priv->channels.ptp;
+
+		ts_stats->pkts = 0;
+		ts_stats->err = 0;
+		ts_stats->lost = 0;
+
+		/* Aggregate stats across all TCs */
+		for (i = 0; i < ptp->num_tc; i++) {
+			struct mlx5e_ptp_cq_stats *stats =
+				ptp->ptpsq[i].cq_stats;
+
+			ts_stats->pkts += stats->cqe;
+			ts_stats->err += stats->abort + stats->err_cqe +
+				stats->late_cqe;
+			ts_stats->lost += stats->lost_cqe;
+		}
+	} else {
+		/* DMA layer will always successfully timestamp packets. Other
+		 * counters do not make sense for this layer.
+		 */
+		ts_stats->pkts = 0;
+
+		/* Aggregate stats across all SQs */
+		for (j = 0; j < priv->channels.num; j++) {
+			struct mlx5e_channel *c = priv->channels.c[j];
+
+			for (i = 0; i < c->num_tc; i++) {
+				struct mlx5e_sq_stats *stats = c->sq[i].stats;
+
+				ts_stats->pkts += stats->timestamps;
+			}
+		}
+	}
+
+	mutex_unlock(&priv->state_lock);
+}
+
 #define PPORT_PHY_STATISTICAL_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.phys_layer_statistical_cntrs.c##_high)
@@ -1215,21 +1260,18 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	strcpy(data + (idx++) * ETH_GSTRING_LEN, "link_down_events_phy");
+	ethtool_puts(data, "link_down_events_phy");
 
 	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_phy_statistical_stats_desc[i].format);
+		ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       pport_phy_statistical_err_lanes_stats_desc[i].format);
-
-	return idx;
+			ethtool_puts(data,
+				     pport_phy_statistical_err_lanes_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
@@ -1238,24 +1280,29 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 	int i;
 
 	/* link_down_events_phy has special handling since it is not stored in __be64 format */
-	data[idx++] = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
-			       counter_set.phys_layer_cntrs.link_down_events);
+	mlx5e_ethtool_put_stat(
+		data, MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
+			       counter_set.phys_layer_cntrs.link_down_events));
 
 	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-		data[idx++] =
-			MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters,
-					    pport_phy_statistical_stats_desc, i);
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(
+				&priv->stats.pport.phy_statistical_counters,
+				pport_phy_statistical_stats_desc, i));
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters,
-						    pport_phy_statistical_err_lanes_stats_desc,
-						    i);
-	return idx;
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport
+						 .phy_statistical_counters,
+					pport_phy_statistical_err_lanes_stats_desc,
+					i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
@@ -1436,9 +1483,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(eth_ext)
 
 	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
 		for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       pport_eth_ext_stats_desc[i].format);
-	return idx;
+			ethtool_puts(data, pport_eth_ext_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(eth_ext)
@@ -1447,10 +1492,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(eth_ext)
 
 	if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters))
 		for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pport.eth_ext_counters,
-						    pport_eth_ext_stats_desc, i);
-	return idx;
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport.eth_ext_counters,
+					pport_eth_ext_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(eth_ext)
@@ -1516,19 +1562,16 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pcie)
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
 		for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       pcie_perf_stats_desc[i].format);
+			ethtool_puts(data, pcie_perf_stats_desc[i].format);
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
 		for (i = 0; i < NUM_PCIE_PERF_COUNTERS64; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       pcie_perf_stats_desc64[i].format);
+			ethtool_puts(data, pcie_perf_stats_desc64[i].format);
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
 		for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       pcie_perf_stall_stats_desc[i].format);
-	return idx;
+			ethtool_puts(data,
+				     pcie_perf_stall_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie)
@@ -1537,22 +1580,27 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie)
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group))
 		for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						    pcie_perf_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR32_BE(
+					&priv->stats.pcie.pcie_perf_counters,
+					pcie_perf_stats_desc, i));
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt))
 		for (i = 0; i < NUM_PCIE_PERF_COUNTERS64; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pcie.pcie_perf_counters,
-						    pcie_perf_stats_desc64, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pcie.pcie_perf_counters,
+					pcie_perf_stats_desc64, i));
 
 	if (MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled))
 		for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						    pcie_perf_stall_stats_desc, i);
-	return idx;
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR32_BE(
+					&priv->stats.pcie.pcie_perf_counters,
+					pcie_perf_stall_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pcie)
@@ -1609,18 +1657,18 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(per_port_buff_congest)
 	int i, prio;
 
 	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
-		return idx;
+		return;
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_TC_PRIO_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_tc_prio_stats_desc[i].format, prio);
+			ethtool_sprintf(data,
+					pport_per_tc_prio_stats_desc[i].format,
+					prio);
 		for (i = 0; i < NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_tc_congest_prio_stats_desc[i].format, prio);
+			ethtool_sprintf(data,
+					pport_per_tc_congest_prio_stats_desc[i].format,
+					prio);
 	}
-
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(per_port_buff_congest)
@@ -1630,20 +1678,24 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(per_port_buff_congest)
 	int i, prio;
 
 	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
-		return idx;
+		return;
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_TC_PRIO_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&pport->per_tc_prio_counters[prio],
-						    pport_per_tc_prio_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&pport->per_tc_prio_counters[prio],
+					pport_per_tc_prio_stats_desc, i));
 		for (i = 0; i < NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS ; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&pport->per_tc_congest_prio_counters[prio],
-						    pport_per_tc_congest_prio_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&pport->per_tc_congest_prio_counters
+						 [prio],
+					pport_per_tc_congest_prio_stats_desc,
+					i));
 	}
-
-	return idx;
 }
 
 static void mlx5e_grp_per_tc_prio_update_stats(struct mlx5e_priv *priv)
@@ -1728,35 +1780,33 @@ static int mlx5e_grp_per_prio_traffic_get_num_stats(void)
 	return NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * NUM_PPORT_PRIO;
 }
 
-static int mlx5e_grp_per_prio_traffic_fill_strings(struct mlx5e_priv *priv,
-						   u8 *data,
-						   int idx)
+static void mlx5e_grp_per_prio_traffic_fill_strings(struct mlx5e_priv *priv,
+						    u8 **data)
 {
 	int i, prio;
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_traffic_stats_desc[i].format, prio);
+			ethtool_sprintf(data,
+					pport_per_prio_traffic_stats_desc[i].format,
+					prio);
 	}
-
-	return idx;
 }
 
-static int mlx5e_grp_per_prio_traffic_fill_stats(struct mlx5e_priv *priv,
-						 u64 *data,
-						 int idx)
+static void mlx5e_grp_per_prio_traffic_fill_stats(struct mlx5e_priv *priv,
+						  u64 **data)
 {
 	int i, prio;
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
-						    pport_per_prio_traffic_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport
+						 .per_prio_counters[prio],
+					pport_per_prio_traffic_stats_desc, i));
 	}
-
-	return idx;
 }
 
 static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
@@ -1816,9 +1866,8 @@ static int mlx5e_grp_per_prio_pfc_get_num_stats(struct mlx5e_priv *priv)
 		NUM_PPORT_PFC_STALL_COUNTERS(priv);
 }
 
-static int mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
-					       u8 *data,
-					       int idx)
+static void mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
+						u8 **data)
 {
 	unsigned long pfc_combined;
 	int i, prio;
@@ -1829,28 +1878,26 @@ static int mlx5e_grp_per_prio_pfc_fill_strings(struct mlx5e_priv *priv,
 			char pfc_string[ETH_GSTRING_LEN];
 
 			snprintf(pfc_string, sizeof(pfc_string), "prio%d", prio);
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_pfc_stats_desc[i].format, pfc_string);
+			ethtool_sprintf(data,
+					pport_per_prio_pfc_stats_desc[i].format,
+					pfc_string);
 		}
 	}
 
 	if (mlx5e_query_global_pause_combined(priv)) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				pport_per_prio_pfc_stats_desc[i].format, "global");
+			ethtool_sprintf(data,
+					pport_per_prio_pfc_stats_desc[i].format,
+					"global");
 		}
 	}
 
 	for (i = 0; i < NUM_PPORT_PFC_STALL_COUNTERS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_pfc_stall_stats_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, pport_pfc_stall_stats_desc[i].format);
 }
 
-static int mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
-					     u64 *data,
-					     int idx)
+static void mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
+					      u64 **data)
 {
 	unsigned long pfc_combined;
 	int i, prio;
@@ -1858,25 +1905,30 @@ static int mlx5e_grp_per_prio_pfc_fill_stats(struct mlx5e_priv *priv,
 	pfc_combined = mlx5e_query_pfc_combined(priv);
 	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
-						    pport_per_prio_pfc_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport
+						 .per_prio_counters[prio],
+					pport_per_prio_pfc_stats_desc, i));
 		}
 	}
 
 	if (mlx5e_query_global_pause_combined(priv)) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			data[idx++] =
-				MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
-						    pport_per_prio_pfc_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport.per_prio_counters[0],
+					pport_per_prio_pfc_stats_desc, i));
 		}
 	}
 
 	for (i = 0; i < NUM_PPORT_PFC_STALL_COUNTERS(priv); i++)
-		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
-						  pport_pfc_stall_stats_desc, i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_BE(
+				      &priv->stats.pport.per_prio_counters[0],
+				      pport_pfc_stall_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(per_prio)
@@ -1887,16 +1939,14 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(per_prio)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(per_prio)
 {
-	idx = mlx5e_grp_per_prio_traffic_fill_strings(priv, data, idx);
-	idx = mlx5e_grp_per_prio_pfc_fill_strings(priv, data, idx);
-	return idx;
+	mlx5e_grp_per_prio_traffic_fill_strings(priv, data);
+	mlx5e_grp_per_prio_pfc_fill_strings(priv, data);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(per_prio)
 {
-	idx = mlx5e_grp_per_prio_traffic_fill_stats(priv, data, idx);
-	idx = mlx5e_grp_per_prio_pfc_fill_stats(priv, data, idx);
-	return idx;
+	mlx5e_grp_per_prio_traffic_fill_stats(priv, data);
+	mlx5e_grp_per_prio_pfc_fill_stats(priv, data);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(per_prio)
@@ -1944,12 +1994,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pme)
 	int i;
 
 	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format);
+		ethtool_puts(data, mlx5e_pme_status_desc[i].format);
 
 	for (i = 0; i < NUM_PME_ERR_STATS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format);
-
-	return idx;
+		ethtool_puts(data, mlx5e_pme_error_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pme)
@@ -1960,14 +2008,14 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pme)
 	mlx5_get_pme_stats(priv->mdev, &pme_stats);
 
 	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.status_counters,
-						   mlx5e_pme_status_desc, i);
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(pme_stats.status_counters,
+						   mlx5e_pme_status_desc, i));
 
 	for (i = 0; i < NUM_PME_ERR_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.error_counters,
-						   mlx5e_pme_error_desc, i);
-
-	return idx;
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(pme_stats.error_counters,
+						   mlx5e_pme_error_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pme) { return; }
@@ -1979,12 +2027,12 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(tls)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(tls)
 {
-	return idx + mlx5e_ktls_get_strings(priv, data + idx * ETH_GSTRING_LEN);
+	mlx5e_ktls_get_strings(priv, data);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(tls)
 {
-	return idx + mlx5e_ktls_get_stats(priv, data + idx);
+	mlx5e_ktls_get_stats(priv, data);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(tls) { return; }
@@ -2063,6 +2111,7 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, added_vlan_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, timestamps) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, mpwqe_blks) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, mpwqe_pkts) },
 #ifdef CONFIG_MLX5_EN_TLS
@@ -2175,6 +2224,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = {
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) },
 	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, late_cqe) },
+	{ MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, lost_cqe) },
 };
 
 static const struct counter_desc ptp_rq_stats_desc[] = {
@@ -2214,6 +2264,7 @@ static const struct counter_desc qos_sq_stats_desc[] = {
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, added_vlan_packets) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, timestamps) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, mpwqe_blks) },
 	{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, mpwqe_pkts) },
 #ifdef CONFIG_MLX5_EN_TLS
@@ -2264,10 +2315,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qos)
 
 	for (qid = 0; qid < max_qos_sqs; qid++)
 		for (i = 0; i < NUM_QOS_SQ_STATS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				qos_sq_stats_desc[i].format, qid);
-
-	return idx;
+			ethtool_sprintf(data, qos_sq_stats_desc[i].format, qid);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qos)
@@ -2284,10 +2332,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qos)
 		struct mlx5e_sq_stats *s = READ_ONCE(stats[qid]);
 
 		for (i = 0; i < NUM_QOS_SQ_STATS; i++)
-			data[idx++] = MLX5E_READ_CTR64_CPU(s, qos_sq_stats_desc, i);
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_CPU(s, qos_sq_stats_desc, i));
 	}
-
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qos) { return; }
@@ -2312,29 +2360,29 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp)
 	int i, tc;
 
 	if (!priv->tx_ptp_opened && !priv->rx_ptp_opened)
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_PTP_CH_STATS; i++)
-		sprintf(data + (idx++) * ETH_GSTRING_LEN,
-			"%s", ptp_ch_stats_desc[i].format);
+		ethtool_puts(data, ptp_ch_stats_desc[i].format);
 
 	if (priv->tx_ptp_opened) {
 		for (tc = 0; tc < priv->max_opened_tc; tc++)
 			for (i = 0; i < NUM_PTP_SQ_STATS; i++)
-				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					ptp_sq_stats_desc[i].format, tc);
+				ethtool_sprintf(data,
+						ptp_sq_stats_desc[i].format,
+						tc);
 
 		for (tc = 0; tc < priv->max_opened_tc; tc++)
 			for (i = 0; i < NUM_PTP_CQ_STATS; i++)
-				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					ptp_cq_stats_desc[i].format, tc);
+				ethtool_sprintf(data,
+						ptp_cq_stats_desc[i].format,
+						tc);
 	}
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				ptp_rq_stats_desc[i].format, MLX5E_PTP_CHANNEL_IX);
+			ethtool_sprintf(data, ptp_rq_stats_desc[i].format,
+					MLX5E_PTP_CHANNEL_IX);
 	}
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ptp)
@@ -2342,33 +2390,35 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ptp)
 	int i, tc;
 
 	if (!priv->tx_ptp_opened && !priv->rx_ptp_opened)
-		return idx;
+		return;
 
 	for (i = 0; i < NUM_PTP_CH_STATS; i++)
-		data[idx++] =
-			MLX5E_READ_CTR64_CPU(&priv->ptp_stats.ch,
-					     ptp_ch_stats_desc, i);
+		mlx5e_ethtool_put_stat(
+			data, MLX5E_READ_CTR64_CPU(&priv->ptp_stats.ch,
+						   ptp_ch_stats_desc, i));
 
 	if (priv->tx_ptp_opened) {
 		for (tc = 0; tc < priv->max_opened_tc; tc++)
 			for (i = 0; i < NUM_PTP_SQ_STATS; i++)
-				data[idx++] =
-					MLX5E_READ_CTR64_CPU(&priv->ptp_stats.sq[tc],
-							     ptp_sq_stats_desc, i);
+				mlx5e_ethtool_put_stat(
+					data, MLX5E_READ_CTR64_CPU(
+						      &priv->ptp_stats.sq[tc],
+						      ptp_sq_stats_desc, i));
 
 		for (tc = 0; tc < priv->max_opened_tc; tc++)
 			for (i = 0; i < NUM_PTP_CQ_STATS; i++)
-				data[idx++] =
-					MLX5E_READ_CTR64_CPU(&priv->ptp_stats.cq[tc],
-							     ptp_cq_stats_desc, i);
+				mlx5e_ethtool_put_stat(
+					data, MLX5E_READ_CTR64_CPU(
+						      &priv->ptp_stats.cq[tc],
+						      ptp_cq_stats_desc, i));
 	}
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
-			data[idx++] =
+			mlx5e_ethtool_put_stat(
+				data,
 				MLX5E_READ_CTR64_CPU(&priv->ptp_stats.rq,
-						     ptp_rq_stats_desc, i);
+						     ptp_rq_stats_desc, i));
 	}
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; }
@@ -2394,38 +2444,29 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
 
 	for (i = 0; i < max_nch; i++)
 		for (j = 0; j < NUM_CH_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				ch_stats_desc[j].format, i);
+			ethtool_sprintf(data, ch_stats_desc[j].format, i);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				rq_stats_desc[j].format, i);
+			ethtool_sprintf(data, rq_stats_desc[j].format, i);
 		for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				xskrq_stats_desc[j].format, i);
+			ethtool_sprintf(data, xskrq_stats_desc[j].format, i);
 		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				rq_xdpsq_stats_desc[j].format, i);
+			ethtool_sprintf(data, rq_xdpsq_stats_desc[j].format, i);
 	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
-				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					sq_stats_desc[j].format,
-					i + tc * max_nch);
+				ethtool_sprintf(data, sq_stats_desc[j].format,
+						i + tc * max_nch);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				xsksq_stats_desc[j].format, i);
+			ethtool_sprintf(data, xsksq_stats_desc[j].format, i);
 		for (j = 0; j < NUM_XDPSQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				xdpsq_stats_desc[j].format, i);
+			ethtool_sprintf(data, xdpsq_stats_desc[j].format, i);
 	}
-
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
@@ -2436,44 +2477,50 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
 
 	for (i = 0; i < max_nch; i++)
 		for (j = 0; j < NUM_CH_STATS; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->ch,
-						     ch_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->ch,
+					      ch_stats_desc, j));
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->rq,
-						     rq_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->rq,
+					      rq_stats_desc, j));
 		for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xskrq,
-						     xskrq_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->xskrq,
+					      xskrq_stats_desc, j));
 		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->rq_xdpsq,
-						     rq_xdpsq_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->rq_xdpsq,
+					      rq_xdpsq_stats_desc, j));
 	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
-				data[idx++] =
-					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->sq[tc],
-							     sq_stats_desc, j);
+				mlx5e_ethtool_put_stat(
+					data,
+					MLX5E_READ_CTR64_CPU(
+						&priv->channel_stats[i]->sq[tc],
+						sq_stats_desc, j));
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xsksq,
-						     xsksq_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->xsksq,
+					      xsksq_stats_desc, j));
 		for (j = 0; j < NUM_XDPSQ_STATS; j++)
-			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xdpsq,
-						     xdpsq_stats_desc, j);
+			mlx5e_ethtool_put_stat(
+				data, MLX5E_READ_CTR64_CPU(
+					      &priv->channel_stats[i]->xdpsq,
+					      xdpsq_stats_desc, j));
 	}
-
-	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(channels) { return; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 12b3607afecd..650732288616 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -71,11 +71,13 @@ struct mlx5e_priv;
 struct mlx5e_stats_grp {
 	u16 update_stats_mask;
 	int (*get_num_stats)(struct mlx5e_priv *priv);
-	int (*fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx);
-	int (*fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx);
+	void (*fill_strings)(struct mlx5e_priv *priv, u8 **data);
+	void (*fill_stats)(struct mlx5e_priv *priv, u64 **data);
 	void (*update_stats)(struct mlx5e_priv *priv);
 };
 
+void mlx5e_ethtool_put_stat(u64 **data, u64 val);
+
 typedef const struct mlx5e_stats_grp *const mlx5e_stats_grp_t;
 
 #define MLX5E_STATS_GRP_OP(grp, name) mlx5e_stats_grp_ ## grp ## _ ## name
@@ -87,10 +89,10 @@ typedef const struct mlx5e_stats_grp *const mlx5e_stats_grp_t;
 	void MLX5E_STATS_GRP_OP(grp, update_stats)(struct mlx5e_priv *priv)
 
 #define MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(grp) \
-	int MLX5E_STATS_GRP_OP(grp, fill_strings)(struct mlx5e_priv *priv, u8 *data, int idx)
+	void MLX5E_STATS_GRP_OP(grp, fill_strings)(struct mlx5e_priv *priv, u8 **data)
 
 #define MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(grp) \
-	int MLX5E_STATS_GRP_OP(grp, fill_stats)(struct mlx5e_priv *priv, u64 *data, int idx)
+	void MLX5E_STATS_GRP_OP(grp, fill_stats)(struct mlx5e_priv *priv, u64 **data)
 
 #define MLX5E_STATS_GRP(grp) mlx5e_stats_grp_ ## grp
 
@@ -126,6 +128,8 @@ void mlx5e_stats_eth_ctrl_get(struct mlx5e_priv *priv,
 void mlx5e_stats_rmon_get(struct mlx5e_priv *priv,
 			  struct ethtool_rmon_stats *rmon,
 			  const struct ethtool_rmon_hist_range **ranges);
+void mlx5e_stats_ts_get(struct mlx5e_priv *priv,
+			struct ethtool_ts_stats *ts_stats);
 void mlx5e_get_link_ext_stats(struct net_device *dev,
 			      struct ethtool_link_ext_stats *stats);
 
@@ -429,6 +433,7 @@ struct mlx5e_sq_stats {
 	u64 stopped;
 	u64 dropped;
 	u64 recover;
+	u64 timestamps;
 	/* dirtied @completion */
 	u64 cqes ____cacheline_aligned_in_smp;
 	u64 wake;
@@ -461,6 +466,7 @@ struct mlx5e_ptp_cq_stats {
 	u64 abort;
 	u64 abort_abs_diff_ns;
 	u64 late_cqe;
+	u64 lost_cqe;
 };
 
 struct mlx5e_rep_stats {
@@ -478,6 +484,7 @@ struct mlx5e_rep_stats {
 	u64 tx_vport_rdma_multicast_bytes;
 	u64 vport_loopback_packets;
 	u64 vport_loopback_bytes;
+	u64 rx_vport_out_of_buffer;
 };
 
 struct mlx5e_stats {
@@ -498,6 +505,7 @@ static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport
 	vf_vport->tx_packets = rep_stats->vport_tx_packets;
 	vf_vport->rx_bytes = rep_stats->vport_rx_bytes;
 	vf_vport->tx_bytes = rep_stats->vport_tx_bytes;
+	vf_vport->rx_missed_errors = rep_stats->rx_vport_out_of_buffer;
 }
 
 extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 31ed26cac9bf..30673292e15f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -835,8 +835,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
 
 	memset(ttc_params, 0, sizeof(*ttc_params));
 
-	ttc_params->ns = mlx5_get_flow_namespace(hp->func_mdev,
-						 MLX5_FLOW_NAMESPACE_KERNEL);
+	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_KERNEL;
 	for (tt = 0; tt < MLX5_NUM_TT; tt++) {
 		ttc_params->dests[tt].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
 		ttc_params->dests[tt].tir_num =
@@ -2802,12 +2801,6 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		flow_rule_match_control(rule, &match);
 		addr_type = match.key->addr_type;
 
-		/* the HW doesn't support frag first/later */
-		if (match.mask->flags & FLOW_DIS_FIRST_FRAG) {
-			NL_SET_ERR_MSG_MOD(extack, "Match on frag first/later is not supported");
-			return -EOPNOTSUPP;
-		}
-
 		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
@@ -2820,6 +2813,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			else
 				*match_level = MLX5_MATCH_L3;
 		}
+
+		if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT,
+						     match.mask->flags, extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -5464,6 +5461,7 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct tunnel_match_enc_opts enc_opts = {};
 	struct mlx5_rep_uplink_priv *uplink_priv;
+	IP_TUNNEL_DECLARE_FLAGS(flags) = { };
 	struct mlx5e_rep_priv *uplink_rpriv;
 	struct metadata_dst *tun_dst;
 	struct tunnel_match_key key;
@@ -5471,6 +5469,8 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb
 	struct net_device *dev;
 	int err;
 
+	__set_bit(IP_TUNNEL_KEY_BIT, flags);
+
 	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
 	tun_id = tunnel_id >> ENC_OPTS_BITS;
 
@@ -5503,14 +5503,14 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb
 	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
 		tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst,
 					   key.enc_ip.tos, key.enc_ip.ttl,
-					   key.enc_tp.dst, TUNNEL_KEY,
+					   key.enc_tp.dst, flags,
 					   key32_to_tunnel_id(key.enc_key_id.keyid),
 					   enc_opts.key.len);
 		break;
 	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
 		tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst,
 					     key.enc_ip.tos, key.enc_ip.ttl,
-					     key.enc_tp.dst, 0, TUNNEL_KEY,
+					     key.enc_tp.dst, 0, flags,
 					     key32_to_tunnel_id(key.enc_key_id.keyid),
 					     enc_opts.key.len);
 		break;
@@ -5528,11 +5528,16 @@ static bool mlx5e_tc_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb
 
 	tun_dst->u.tun_info.key.tp_src = key.enc_tp.src;
 
-	if (enc_opts.key.len)
+	if (enc_opts.key.len) {
+		ip_tunnel_flags_zero(flags);
+		if (enc_opts.key.dst_opt_type)
+			__set_bit(enc_opts.key.dst_opt_type, flags);
+
 		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
 					enc_opts.key.data,
 					enc_opts.key.len,
-					enc_opts.key.dst_opt_type);
+					flags);
+	}
 
 	skb_dst_set(skb, (struct dst_entry *)tun_dst);
 	dev = dev_get_by_index(&init_net, key.filter_ifindex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index e21a3b4128ce..099bf1078889 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -749,11 +749,13 @@ static void mlx5e_consume_skb(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		u64 ts = get_cqe_ts(cqe);
 
 		hwts.hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, ts);
-		if (sq->ptpsq)
+		if (sq->ptpsq) {
 			mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_CQE_HWTSTAMP,
 						      hwts.hwtstamp, sq->ptpsq->cq_stats);
-		else
+		} else {
 			skb_tstamp_tx(skb, &hwts);
+			sq->stats->timestamps++;
+		}
 	}
 
 	napi_consume_skb(skb, napi_budget);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index a7d9b7cb4297..5873fde65c2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -55,7 +55,7 @@ static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
 		return;
 
 	dim_update_sample(sq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample);
-	net_dim(&sq->dim, dim_sample);
+	net_dim(sq->dim, dim_sample);
 }
 
 static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
@@ -67,7 +67,7 @@ static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
 		return;
 
 	dim_update_sample(rq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample);
-	net_dim(&rq->dim, dim_sample);
+	net_dim(rq->dim, dim_sample);
 }
 
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 40a6cb052a2d..5693986ae656 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -688,6 +688,12 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	if (err)
 		goto err2;
 
+	/* Skip page eq creation when the device does not request for page requests */
+	if (MLX5_CAP_GEN(dev, page_request_disable)) {
+		mlx5_core_dbg(dev, "Skip page EQ creation\n");
+		return 0;
+	}
+
 	param = (struct mlx5_eq_param) {
 		.irq = table->ctrl_irq,
 		.nent = /* TODO: sriov max_vf + */ 1,
@@ -716,7 +722,8 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 
-	cleanup_async_eq(dev, &table->pages_eq, "pages");
+	if (!MLX5_CAP_GEN(dev, page_request_disable))
+		cleanup_async_eq(dev, &table->pages_eq, "pages");
 	cleanup_async_eq(dev, &table->async_eq, "async");
 	mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ);
 	mlx5_cmd_use_polling(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 1b9bc32efd6f..c5ea1d1d2b03 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -1874,7 +1874,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 				 "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n",
 				 addr, vid, vport_num);
 			NL_SET_ERR_MSG_FMT_MOD(extack,
-					       "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n",
+					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n",
 					       addr, vid, vport_num);
 			return -EINVAL;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index d8e739cbcbce..f8869c9b6802 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -98,6 +98,8 @@ static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 	.port_fn_ipsec_packet_get = mlx5_devlink_port_fn_ipsec_packet_get,
 	.port_fn_ipsec_packet_set = mlx5_devlink_port_fn_ipsec_packet_set,
 #endif /* CONFIG_XFRM_OFFLOAD */
+	.port_fn_max_io_eqs_get = mlx5_devlink_port_fn_max_io_eqs_get,
+	.port_fn_max_io_eqs_set = mlx5_devlink_port_fn_max_io_eqs_set,
 };
 
 static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw,
@@ -143,6 +145,8 @@ static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = {
 	.port_fn_state_get = mlx5_devlink_sf_port_fn_state_get,
 	.port_fn_state_set = mlx5_devlink_sf_port_fn_state_set,
 #endif
+	.port_fn_max_io_eqs_get = mlx5_devlink_port_fn_max_io_eqs_get,
+	.port_fn_max_io_eqs_set = mlx5_devlink_port_fn_max_io_eqs_set,
 };
 
 int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1789800faaeb..17f78091ad30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1805,7 +1805,8 @@ err:
 }
 
 static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id,
-					  struct devlink_param_gset_ctx *ctx)
+					  struct devlink_param_gset_ctx *ctx,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 349e28a6dd8d..88745dc6aed5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -573,6 +573,13 @@ int mlx5_devlink_port_fn_ipsec_packet_get(struct devlink_port *port, bool *is_en
 int mlx5_devlink_port_fn_ipsec_packet_set(struct devlink_port *port, bool enable,
 					  struct netlink_ext_ack *extack);
 #endif /* CONFIG_XFRM_OFFLOAD */
+int mlx5_devlink_port_fn_max_io_eqs_get(struct devlink_port *port,
+					u32 *max_io_eqs,
+					struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_max_io_eqs_set(struct devlink_port *port,
+					u32 max_io_eqs,
+					struct netlink_ext_ack *extack);
+
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
@@ -833,7 +840,7 @@ int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw,
 					     struct mlx5_eswitch *slave_esw, int max_slaves);
 void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw,
 					      struct mlx5_eswitch *slave_esw);
-int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
+int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw);
 
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev);
 void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev);
@@ -925,7 +932,7 @@ mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw,
 static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) { return 0; }
 
 static inline int
-mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
 {
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 844d3e3a65dd..592143d5e1da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -67,6 +67,8 @@
 
 #define MLX5_ESW_FT_OFFLOADS_DROP_RULE (1)
 
+#define MLX5_ESW_MAX_CTRL_EQS 4
+
 static struct esw_vport_tbl_namespace mlx5_esw_vport_tbl_mirror_ns = {
 	.max_fte = MLX5_ESW_VPORT_TBL_SIZE,
 	.max_num_groups = MLX5_ESW_VPORT_TBL_NUM_GROUPS,
@@ -2411,7 +2413,8 @@ err:
 }
 
 static int esw_port_metadata_set(struct devlink *devlink, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
@@ -2502,6 +2505,16 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 	esw_offloads_cleanup_reps(esw);
 }
 
+static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
+				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
+			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED)
+		return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+
+	return 0;
+}
+
 static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
 				      struct mlx5_eswitch_rep *rep, u8 rep_type)
 {
@@ -2526,13 +2539,11 @@ static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
 	int err;
 
 	rep = mlx5_eswitch_get_rep(esw, vport_num);
-	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
-		if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
-				   REP_REGISTERED, REP_LOADED) == REP_REGISTERED) {
-			err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
-			if (err)
-				goto err_reps;
-		}
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_reps;
+	}
 
 	return 0;
 
@@ -3277,7 +3288,7 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
 		esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
-int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
 {
 	struct mlx5_eswitch_rep *rep;
 	unsigned long i;
@@ -3290,13 +3301,13 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
 	if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 		return 0;
 
-	ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK);
+	ret = __esw_offloads_load_rep(esw, rep, REP_IB);
 	if (ret)
 		return ret;
 
 	mlx5_esw_for_each_rep(esw, i, rep) {
 		if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
-			mlx5_esw_offloads_rep_load(esw, rep->vport);
+			__esw_offloads_load_rep(esw, rep, REP_IB);
 	}
 
 	return 0;
@@ -4568,3 +4579,98 @@ unlock:
 	return err;
 }
 #endif /* CONFIG_XFRM_OFFLOAD */
+
+int
+mlx5_devlink_port_fn_max_io_eqs_get(struct devlink_port *port, u32 *max_io_eqs,
+				    struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	u16 vport_num = vport->vport;
+	struct mlx5_eswitch *esw;
+	void *query_ctx;
+	void *hca_caps;
+	u32 max_eqs;
+	int err;
+
+	esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_vport_get_other_func_cap(esw->dev, vport_num, query_ctx,
+					    MLX5_CAP_GENERAL);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed getting HCA caps");
+		goto out;
+	}
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	max_eqs = MLX5_GET(cmd_hca_cap, hca_caps, max_num_eqs);
+	if (max_eqs < MLX5_ESW_MAX_CTRL_EQS)
+		*max_io_eqs = 0;
+	else
+		*max_io_eqs = max_eqs - MLX5_ESW_MAX_CTRL_EQS;
+out:
+	mutex_unlock(&esw->state_lock);
+	kfree(query_ctx);
+	return err;
+}
+
+int
+mlx5_devlink_port_fn_max_io_eqs_set(struct devlink_port *port, u32 max_io_eqs,
+				    struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	u16 vport_num = vport->vport;
+	struct mlx5_eswitch *esw;
+	void *query_ctx;
+	void *hca_caps;
+	u16 max_eqs;
+	int err;
+
+	esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device doesn't support VHCA management");
+		return -EOPNOTSUPP;
+	}
+
+	if (check_add_overflow(max_io_eqs, MLX5_ESW_MAX_CTRL_EQS, &max_eqs)) {
+		NL_SET_ERR_MSG_MOD(extack, "Supplied value out of range");
+		return -EINVAL;
+	}
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_vport_get_other_func_cap(esw->dev, vport_num, query_ctx,
+					    MLX5_CAP_GENERAL);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed getting HCA caps");
+		goto out;
+	}
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	MLX5_SET(cmd_hca_cap, hca_caps, max_num_eqs, max_eqs);
+
+	err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num,
+					    MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "Failed setting HCA caps");
+
+out:
+	mutex_unlock(&esw->state_lock);
+	kfree(query_ctx);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index cf085a478e3e..32cdacc34a0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3332,7 +3332,8 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 }
 
 static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	enum mlx5_flow_steering_mode mode;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index e7faf7e73ca4..2d95a9b7b44e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -283,7 +283,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	return 0;
 }
 
-int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id)
+int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, u32 *sw_owner_id)
 {
 	u32 in[MLX5_ST_SZ_DW(init_hca_in)] = {};
 	int i;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 2911aa34a5be..979c49ae6b5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -52,7 +52,8 @@ static void mlx5_set_fw_rst_ack(struct mlx5_core_dev *dev)
 }
 
 static int mlx5_fw_reset_enable_remote_dev_reset_set(struct devlink *devlink, u32 id,
-						     struct devlink_param_gset_ctx *ctx)
+						     struct devlink_param_gset_ctx *ctx,
+						     struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_fw_reset *fw_reset;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index d77be1b4dd9c..8e0404c0d1ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -531,7 +531,7 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu)
 	if (err)
 		goto out;
 
-	netdev->mtu = new_params.sw_mtu;
+	WRITE_ONCE(netdev->mtu, new_params.sw_mtu);
 
 out:
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index f87471306f6b..028a76944d82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -280,7 +280,7 @@ static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu)
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
 
 	mutex_lock(&priv->state_lock);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	mutex_unlock(&priv->state_lock);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 69d482f7c5a2..f7f0476a4a58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -713,7 +713,6 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 	return 0;
 }
 
-#define MLX5_LAG_OFFLOADS_SUPPORTED_PORTS 4
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 {
 #ifdef CONFIG_MLX5_ESWITCH
@@ -739,8 +738,6 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 		if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode)
 			return false;
 
-	if (mode == MLX5_ESWITCH_OFFLOADS && ldev->ports > MLX5_LAG_OFFLOADS_SUPPORTED_PORTS)
-		return false;
 #else
 	for (i = 0; i < ldev->ports; i++)
 		if (mlx5_sriov_is_enabled(ldev->pf[i].dev))
@@ -814,7 +811,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 	if (shared_fdb)
 		for (i = 0; i < ldev->ports; i++)
 			if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV))
-				mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch);
+				mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 }
 
 static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
@@ -922,7 +919,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			mlx5_rescan_drivers_locked(dev0);
 
 			for (i = 0; i < ldev->ports; i++) {
-				err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch);
+				err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 				if (err)
 					break;
 			}
@@ -933,7 +930,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 				mlx5_deactivate_lag(ldev);
 				mlx5_lag_add_devices(ldev);
 				for (i = 0; i < ldev->ports; i++)
-					mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch);
+					mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 				mlx5_core_err(dev0, "Failed to enable lag\n");
 				return;
 			}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 82889f30506e..571ea26edd0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -99,7 +99,7 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 	mlx5_rescan_drivers_locked(dev0);
 	for (i = 0; i < ldev->ports; i++) {
-		err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch);
+		err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 		if (err)
 			goto err_rescan_drivers;
 	}
@@ -113,7 +113,7 @@ err_rescan_drivers:
 err_add_devices:
 	mlx5_lag_add_devices(ldev);
 	for (i = 0; i < ldev->ports; i++)
-		mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch);
+		mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 	mlx5_mpesw_metadata_cleanup(ldev);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index 101b3bb90863..c16b462ddedf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -449,13 +449,11 @@ static void set_tt_map(struct mlx5_lag_port_sel *port_sel,
 static void mlx5_lag_set_inner_ttc_params(struct mlx5_lag *ldev,
 					  struct ttc_params *ttc_params)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
 	struct mlx5_lag_port_sel *port_sel = &ldev->port_sel;
 	struct mlx5_flow_table_attr *ft_attr;
 	int tt;
 
-	ttc_params->ns = mlx5_get_flow_namespace(dev,
-						 MLX5_FLOW_NAMESPACE_PORT_SEL);
+	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_PORT_SEL;
 	ft_attr = &ttc_params->ft_attr;
 	ft_attr->level = MLX5_LAG_FT_LEVEL_INNER_TTC;
 
@@ -470,13 +468,11 @@ static void mlx5_lag_set_inner_ttc_params(struct mlx5_lag *ldev,
 static void mlx5_lag_set_outer_ttc_params(struct mlx5_lag *ldev,
 					  struct ttc_params *ttc_params)
 {
-	struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev;
 	struct mlx5_lag_port_sel *port_sel = &ldev->port_sel;
 	struct mlx5_flow_table_attr *ft_attr;
 	int tt;
 
-	ttc_params->ns = mlx5_get_flow_namespace(dev,
-						 MLX5_FLOW_NAMESPACE_PORT_SEL);
+	ttc_params->ns_type = MLX5_FLOW_NAMESPACE_PORT_SEL;
 	ft_attr = &ttc_params->ft_attr;
 	ft_attr->level = MLX5_LAG_FT_LEVEL_TTC;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index b78f2ba25c19..9f13cea16446 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -9,21 +9,24 @@
 #include "mlx5_core.h"
 #include "lib/fs_ttc.h"
 
-#define MLX5_TTC_NUM_GROUPS	3
-#define MLX5_TTC_GROUP1_SIZE	(BIT(3) + MLX5_NUM_TUNNEL_TT)
-#define MLX5_TTC_GROUP2_SIZE	 BIT(1)
-#define MLX5_TTC_GROUP3_SIZE	 BIT(0)
-#define MLX5_TTC_TABLE_SIZE	(MLX5_TTC_GROUP1_SIZE +\
-				 MLX5_TTC_GROUP2_SIZE +\
-				 MLX5_TTC_GROUP3_SIZE)
-
-#define MLX5_INNER_TTC_NUM_GROUPS	3
-#define MLX5_INNER_TTC_GROUP1_SIZE	BIT(3)
-#define MLX5_INNER_TTC_GROUP2_SIZE	BIT(1)
-#define MLX5_INNER_TTC_GROUP3_SIZE	BIT(0)
-#define MLX5_INNER_TTC_TABLE_SIZE	(MLX5_INNER_TTC_GROUP1_SIZE +\
-					 MLX5_INNER_TTC_GROUP2_SIZE +\
-					 MLX5_INNER_TTC_GROUP3_SIZE)
+#define MLX5_TTC_MAX_NUM_GROUPS		4
+#define MLX5_TTC_GROUP_TCPUDP_SIZE	(MLX5_TT_IPV6_UDP + 1)
+
+struct mlx5_fs_ttc_groups {
+	bool use_l4_type;
+	int num_groups;
+	int group_size[MLX5_TTC_MAX_NUM_GROUPS];
+};
+
+static int mlx5_fs_ttc_table_size(const struct mlx5_fs_ttc_groups *groups)
+{
+	int i, sz = 0;
+
+	for (i = 0; i < groups->num_groups; i++)
+		sz += groups->group_size[i];
+
+	return sz;
+}
 
 /* L3/L4 traffic type classifier */
 struct mlx5_ttc_table {
@@ -138,6 +141,53 @@ static struct mlx5_etype_proto ttc_tunnel_rules[] = {
 
 };
 
+enum TTC_GROUP_TYPE {
+	TTC_GROUPS_DEFAULT = 0,
+	TTC_GROUPS_USE_L4_TYPE = 1,
+};
+
+static const struct mlx5_fs_ttc_groups ttc_groups[] = {
+	[TTC_GROUPS_DEFAULT] = {
+		.num_groups = 3,
+		.group_size = {
+			BIT(3) + MLX5_NUM_TUNNEL_TT,
+			BIT(1),
+			BIT(0),
+		},
+	},
+	[TTC_GROUPS_USE_L4_TYPE] = {
+		.use_l4_type = true,
+		.num_groups = 4,
+		.group_size = {
+			MLX5_TTC_GROUP_TCPUDP_SIZE,
+			BIT(3) + MLX5_NUM_TUNNEL_TT - MLX5_TTC_GROUP_TCPUDP_SIZE,
+			BIT(1),
+			BIT(0),
+		},
+	},
+};
+
+static const struct mlx5_fs_ttc_groups inner_ttc_groups[] = {
+	[TTC_GROUPS_DEFAULT] = {
+		.num_groups = 3,
+		.group_size = {
+			BIT(3),
+			BIT(1),
+			BIT(0),
+		},
+	},
+	[TTC_GROUPS_USE_L4_TYPE] = {
+		.use_l4_type = true,
+		.num_groups = 4,
+		.group_size = {
+			MLX5_TTC_GROUP_TCPUDP_SIZE,
+			BIT(3) - MLX5_TTC_GROUP_TCPUDP_SIZE,
+			BIT(1),
+			BIT(0),
+		},
+	},
+};
+
 u8 mlx5_get_proto_by_tunnel_type(enum mlx5_tunnel_types tt)
 {
 	return ttc_tunnel_rules[tt].proto;
@@ -188,9 +238,29 @@ static u8 mlx5_etype_to_ipv(u16 ethertype)
 	return 0;
 }
 
+static void mlx5_fs_ttc_set_match_proto(void *headers_c, void *headers_v,
+					u8 proto, bool use_l4_type)
+{
+	int l4_type;
+
+	if (use_l4_type && (proto == IPPROTO_TCP || proto == IPPROTO_UDP)) {
+		if (proto == IPPROTO_TCP)
+			l4_type = MLX5_PACKET_L4_TYPE_TCP;
+		else
+			l4_type = MLX5_PACKET_L4_TYPE_UDP;
+
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, l4_type);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, l4_type, l4_type);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, proto);
+	}
+}
+
 static struct mlx5_flow_handle *
 mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
-		       struct mlx5_flow_destination *dest, u16 etype, u8 proto)
+		       struct mlx5_flow_destination *dest, u16 etype, u8 proto,
+		       bool use_l4_type)
 {
 	int match_ipv_outer =
 		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
@@ -207,8 +277,13 @@ mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
 
 	if (proto) {
 		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
-		MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto);
+		mlx5_fs_ttc_set_match_proto(MLX5_ADDR_OF(fte_match_param,
+							 spec->match_criteria,
+							 outer_headers),
+					    MLX5_ADDR_OF(fte_match_param,
+							 spec->match_value,
+							 outer_headers),
+					    proto, use_l4_type);
 	}
 
 	ipv = mlx5_etype_to_ipv(etype);
@@ -234,7 +309,8 @@ mlx5_generate_ttc_rule(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
 
 static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
 					 struct ttc_params *params,
-					 struct mlx5_ttc_table *ttc)
+					 struct mlx5_ttc_table *ttc,
+					 bool use_l4_type)
 {
 	struct mlx5_flow_handle **trules;
 	struct mlx5_ttc_rule *rules;
@@ -251,7 +327,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
 			continue;
 		rule->rule = mlx5_generate_ttc_rule(dev, ft, &params->dests[tt],
 						    ttc_rules[tt].etype,
-						    ttc_rules[tt].proto);
+						    ttc_rules[tt].proto,
+						    use_l4_type);
 		if (IS_ERR(rule->rule)) {
 			err = PTR_ERR(rule->rule);
 			rule->rule = NULL;
@@ -273,7 +350,8 @@ static int mlx5_generate_ttc_table_rules(struct mlx5_core_dev *dev,
 		trules[tt] = mlx5_generate_ttc_rule(dev, ft,
 						    &params->tunnel_dests[tt],
 						    ttc_tunnel_rules[tt].etype,
-						    ttc_tunnel_rules[tt].proto);
+						    ttc_tunnel_rules[tt].proto,
+						    use_l4_type);
 		if (IS_ERR(trules[tt])) {
 			err = PTR_ERR(trules[tt]);
 			trules[tt] = NULL;
@@ -289,7 +367,8 @@ del_rules:
 }
 
 static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
-					bool use_ipv)
+					bool use_ipv,
+					const struct mlx5_fs_ttc_groups *groups)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	int ix = 0;
@@ -297,7 +376,7 @@ static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
 	int err;
 	u8 *mc;
 
-	ttc->g = kcalloc(MLX5_TTC_NUM_GROUPS, sizeof(*ttc->g), GFP_KERNEL);
+	ttc->g = kcalloc(groups->num_groups, sizeof(*ttc->g), GFP_KERNEL);
 	if (!ttc->g)
 		return -ENOMEM;
 	in = kvzalloc(inlen, GFP_KERNEL);
@@ -307,16 +386,31 @@ static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
 		return -ENOMEM;
 	}
 
-	/* L4 Group */
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
-	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
 	if (use_ipv)
 		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version);
 	else
 		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype);
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+
+	/* TCP UDP group */
+	if (groups->use_l4_type) {
+		MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.l4_type);
+		MLX5_SET_CFG(in, start_flow_index, ix);
+		ix += groups->group_size[ttc->num_groups];
+		MLX5_SET_CFG(in, end_flow_index, ix - 1);
+		ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+		if (IS_ERR(ttc->g[ttc->num_groups]))
+			goto err;
+		ttc->num_groups++;
+
+		MLX5_SET(fte_match_param, mc, outer_headers.l4_type, 0);
+	}
+
+	/* L4 Group */
+	MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_TTC_GROUP1_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -326,7 +420,7 @@ static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
 	/* L3 Group */
 	MLX5_SET(fte_match_param, mc, outer_headers.ip_protocol, 0);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_TTC_GROUP2_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -336,7 +430,7 @@ static int mlx5_create_ttc_table_groups(struct mlx5_ttc_table *ttc,
 	/* Any Group */
 	memset(in, 0, inlen);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_TTC_GROUP3_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -358,7 +452,7 @@ static struct mlx5_flow_handle *
 mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev,
 			     struct mlx5_flow_table *ft,
 			     struct mlx5_flow_destination *dest,
-			     u16 etype, u8 proto)
+			     u16 etype, u8 proto, bool use_l4_type)
 {
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
@@ -379,8 +473,13 @@ mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev,
 
 	if (proto) {
 		spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS;
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol);
-		MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto);
+		mlx5_fs_ttc_set_match_proto(MLX5_ADDR_OF(fte_match_param,
+							 spec->match_criteria,
+							 inner_headers),
+					    MLX5_ADDR_OF(fte_match_param,
+							 spec->match_value,
+							 inner_headers),
+					    proto, use_l4_type);
 	}
 
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
@@ -395,7 +494,8 @@ mlx5_generate_inner_ttc_rule(struct mlx5_core_dev *dev,
 
 static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev,
 					       struct ttc_params *params,
-					       struct mlx5_ttc_table *ttc)
+					       struct mlx5_ttc_table *ttc,
+					       bool use_l4_type)
 {
 	struct mlx5_ttc_rule *rules;
 	struct mlx5_flow_table *ft;
@@ -413,7 +513,8 @@ static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev,
 		rule->rule = mlx5_generate_inner_ttc_rule(dev, ft,
 							  &params->dests[tt],
 							  ttc_rules[tt].etype,
-							  ttc_rules[tt].proto);
+							  ttc_rules[tt].proto,
+							  use_l4_type);
 		if (IS_ERR(rule->rule)) {
 			err = PTR_ERR(rule->rule);
 			rule->rule = NULL;
@@ -430,7 +531,8 @@ del_rules:
 	return err;
 }
 
-static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
+static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc,
+					      const struct mlx5_fs_ttc_groups *groups)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	int ix = 0;
@@ -438,8 +540,7 @@ static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
 	int err;
 	u8 *mc;
 
-	ttc->g = kcalloc(MLX5_INNER_TTC_NUM_GROUPS, sizeof(*ttc->g),
-			 GFP_KERNEL);
+	ttc->g = kcalloc(groups->num_groups, sizeof(*ttc->g), GFP_KERNEL);
 	if (!ttc->g)
 		return -ENOMEM;
 	in = kvzalloc(inlen, GFP_KERNEL);
@@ -449,13 +550,28 @@ static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
 		return -ENOMEM;
 	}
 
-	/* L4 Group */
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
-	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol);
 	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version);
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS);
+
+	/* TCP UDP group */
+	if (groups->use_l4_type) {
+		MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.l4_type);
+		MLX5_SET_CFG(in, start_flow_index, ix);
+		ix += groups->group_size[ttc->num_groups];
+		MLX5_SET_CFG(in, end_flow_index, ix - 1);
+		ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
+		if (IS_ERR(ttc->g[ttc->num_groups]))
+			goto err;
+		ttc->num_groups++;
+
+		MLX5_SET(fte_match_param, mc, inner_headers.l4_type, 0);
+	}
+
+	/* L4 Group */
+	MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_INNER_TTC_GROUP1_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -465,7 +581,7 @@ static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
 	/* L3 Group */
 	MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_INNER_TTC_GROUP2_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -475,7 +591,7 @@ static int mlx5_create_inner_ttc_table_groups(struct mlx5_ttc_table *ttc)
 	/* Any Group */
 	memset(in, 0, inlen);
 	MLX5_SET_CFG(in, start_flow_index, ix);
-	ix += MLX5_INNER_TTC_GROUP3_SIZE;
+	ix += groups->group_size[ttc->num_groups];
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ttc->g[ttc->num_groups] = mlx5_create_flow_group(ttc->t, in);
 	if (IS_ERR(ttc->g[ttc->num_groups]))
@@ -496,27 +612,47 @@ err:
 struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 						   struct ttc_params *params)
 {
+	const struct mlx5_fs_ttc_groups *groups;
+	struct mlx5_flow_namespace *ns;
 	struct mlx5_ttc_table *ttc;
+	bool use_l4_type;
 	int err;
 
 	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
 	if (!ttc)
 		return ERR_PTR(-ENOMEM);
 
+	switch (params->ns_type) {
+	case MLX5_FLOW_NAMESPACE_PORT_SEL:
+		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
+			MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(dev, inner_l4_type);
+		break;
+	case MLX5_FLOW_NAMESPACE_KERNEL:
+		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
+			MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(dev, inner_l4_type);
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
+			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
+
 	WARN_ON_ONCE(params->ft_attr.max_fte);
-	params->ft_attr.max_fte = MLX5_INNER_TTC_TABLE_SIZE;
-	ttc->t = mlx5_create_flow_table(params->ns, &params->ft_attr);
+	params->ft_attr.max_fte = mlx5_fs_ttc_table_size(groups);
+	ttc->t = mlx5_create_flow_table(ns, &params->ft_attr);
 	if (IS_ERR(ttc->t)) {
 		err = PTR_ERR(ttc->t);
 		kvfree(ttc);
 		return ERR_PTR(err);
 	}
 
-	err = mlx5_create_inner_ttc_table_groups(ttc);
+	err = mlx5_create_inner_ttc_table_groups(ttc, groups);
 	if (err)
 		goto destroy_ft;
 
-	err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc);
+	err = mlx5_generate_inner_ttc_table_rules(dev, params, ttc, use_l4_type);
 	if (err)
 		goto destroy_ft;
 
@@ -549,27 +685,47 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool match_ipv_outer =
 		MLX5_CAP_FLOWTABLE_NIC_RX(dev,
 					  ft_field_support.outer_ip_version);
+	const struct mlx5_fs_ttc_groups *groups;
+	struct mlx5_flow_namespace *ns;
 	struct mlx5_ttc_table *ttc;
+	bool use_l4_type;
 	int err;
 
 	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
 	if (!ttc)
 		return ERR_PTR(-ENOMEM);
 
+	switch (params->ns_type) {
+	case MLX5_FLOW_NAMESPACE_PORT_SEL:
+		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
+			MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(dev, outer_l4_type);
+		break;
+	case MLX5_FLOW_NAMESPACE_KERNEL:
+		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
+			MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(dev, outer_l4_type);
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
+			       &ttc_groups[TTC_GROUPS_DEFAULT];
+
 	WARN_ON_ONCE(params->ft_attr.max_fte);
-	params->ft_attr.max_fte = MLX5_TTC_TABLE_SIZE;
-	ttc->t = mlx5_create_flow_table(params->ns, &params->ft_attr);
+	params->ft_attr.max_fte = mlx5_fs_ttc_table_size(groups);
+	ttc->t = mlx5_create_flow_table(ns, &params->ft_attr);
 	if (IS_ERR(ttc->t)) {
 		err = PTR_ERR(ttc->t);
 		kvfree(ttc);
 		return ERR_PTR(err);
 	}
 
-	err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer);
+	err = mlx5_create_ttc_table_groups(ttc, match_ipv_outer, groups);
 	if (err)
 		goto destroy_ft;
 
-	err = mlx5_generate_ttc_table_rules(dev, params, ttc);
+	err = mlx5_generate_ttc_table_rules(dev, params, ttc, use_l4_type);
 	if (err)
 		goto destroy_ft;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
index 85fef0cd1c07..92eea6bea310 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
@@ -40,7 +40,7 @@ struct mlx5_ttc_rule {
 struct mlx5_ttc_table;
 
 struct ttc_params {
-	struct mlx5_flow_namespace *ns;
+	enum mlx5_flow_namespace_type ns_type;
 	struct mlx5_flow_table_attr ft_attr;
 	struct mlx5_flow_destination dests[MLX5_NUM_TT];
 	DECLARE_BITMAP(ignore_dests, MLX5_NUM_TT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 331ce47f51a1..6574c145dc1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1680,6 +1680,8 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev)
 	struct devlink *devlink = priv_to_devlink(dev);
 	int err;
 
+	devl_lock(devlink);
+	devl_register(devlink);
 	dev->state = MLX5_DEVICE_STATE_UP;
 	err = mlx5_function_enable(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
 	if (err) {
@@ -1693,27 +1695,21 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev)
 		goto query_hca_caps_err;
 	}
 
-	devl_lock(devlink);
-	devl_register(devlink);
-
 	err = mlx5_devlink_params_register(priv_to_devlink(dev));
 	if (err) {
 		mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err);
-		goto params_reg_err;
+		goto query_hca_caps_err;
 	}
 
 	devl_unlock(devlink);
 	return 0;
 
-params_reg_err:
-	devl_unregister(devlink);
-	devl_unlock(devlink);
 query_hca_caps_err:
-	devl_unregister(devlink);
-	devl_unlock(devlink);
 	mlx5_function_disable(dev, true);
 out:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+	devl_unregister(devlink);
+	devl_unlock(devlink);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 58732f44940f..c38342b9f320 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -205,7 +205,7 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev);
 void mlx5_cmd_disable(struct mlx5_core_dev *dev);
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 			enum mlx5_cmdif_state cmdif_state);
-int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
+int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, u32 *sw_owner_id);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index dcf58efac159..d894a88fa9f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -660,6 +660,9 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 	mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
 		      npages, boot ? "boot" : "init", func_id);
 
+	if (!npages)
+		return 0;
+
 	return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 6bac8ad70ba6..fb8787e30d3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -508,58 +508,6 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
 }
 
 /**
- * mlx5_msix_alloc - allocate msix interrupt
- * @dev: mlx5 device from which to request
- * @handler: interrupt handler
- * @affdesc: affinity descriptor
- * @name: interrupt name
- *
- * Returns: struct msi_map with result encoded.
- * Note: the caller must make sure to release the irq by calling
- *       mlx5_msix_free() if shutdown was initiated.
- */
-struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev,
-			       irqreturn_t (*handler)(int, void *),
-			       const struct irq_affinity_desc *affdesc,
-			       const char *name)
-{
-	struct msi_map map;
-	int err;
-
-	if (!dev->pdev) {
-		map.virq = 0;
-		map.index = -EINVAL;
-		return map;
-	}
-
-	map = pci_msix_alloc_irq_at(dev->pdev, MSI_ANY_INDEX, affdesc);
-	if (!map.virq)
-		return map;
-
-	err = request_irq(map.virq, handler, 0, name, NULL);
-	if (err) {
-		mlx5_core_warn(dev, "err %d\n", err);
-		pci_msix_free_irq(dev->pdev, map);
-		map.virq = 0;
-		map.index = -ENOMEM;
-	}
-	return map;
-}
-EXPORT_SYMBOL(mlx5_msix_alloc);
-
-/**
- * mlx5_msix_free - free a previously allocated msix interrupt
- * @dev: mlx5 device associated with interrupt
- * @map: map previously returned by mlx5_msix_alloc()
- */
-void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map)
-{
-	free_irq(map.virq, NULL);
-	pci_msix_free_irq(dev->pdev, map);
-}
-EXPORT_SYMBOL(mlx5_msix_free);
-
-/**
  * mlx5_irq_release_vector - release one IRQ back to the system.
  * @irq: the irq to release.
  */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index 7ebe71280827..b2986175d9af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -60,6 +60,13 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 		goto remap_err;
 	}
 
+	/* Peer devlink logic expects to work on unregistered devlink instance. */
+	err = mlx5_core_peer_devlink_set(sf_dev, devlink);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err);
+		goto peer_devlink_set_err;
+	}
+
 	if (MLX5_ESWITCH_MANAGER(sf_dev->parent_mdev))
 		err = mlx5_init_one_light(mdev);
 	else
@@ -69,20 +76,10 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 		goto init_one_err;
 	}
 
-	err = mlx5_core_peer_devlink_set(sf_dev, devlink);
-	if (err) {
-		mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err);
-		goto peer_devlink_set_err;
-	}
-
 	return 0;
 
-peer_devlink_set_err:
-	if (mlx5_dev_is_lightweight(sf_dev->mdev))
-		mlx5_uninit_one_light(sf_dev->mdev);
-	else
-		mlx5_uninit_one(sf_dev->mdev);
 init_one_err:
+peer_devlink_set_err:
 	iounmap(mdev->iseg);
 remap_err:
 	mlx5_mdev_uninit(mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
index f708b029425a..e9f6c7ed7a7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
@@ -1883,7 +1883,7 @@ dr_ste_v0_build_tnl_gtpu_flex_parser_1_init(struct mlx5dr_ste_build *sb,
 
 static int dr_ste_v0_build_tnl_header_0_1_tag(struct mlx5dr_match_param *value,
 					      struct mlx5dr_ste_build *sb,
-					      uint8_t *tag)
+					      u8 *tag)
 {
 	struct mlx5dr_match_misc5 *misc5 = &value->misc5;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index dd856cde188d..1d49704b9542 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -1897,7 +1897,7 @@ void dr_ste_v1_build_flex_parser_tnl_geneve_init(struct mlx5dr_ste_build *sb,
 
 static int dr_ste_v1_build_tnl_header_0_1_tag(struct mlx5dr_match_param *value,
 					      struct mlx5dr_ste_build *sb,
-					      uint8_t *tag)
+					      u8 *tag)
 {
 	struct mlx5dr_match_misc5 *misc5 = &value->misc5;
 
@@ -2129,7 +2129,7 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb,
 static int
 dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_tag(struct mlx5dr_match_param *value,
 							 struct mlx5dr_ste_build *sb,
-							 uint8_t *tag)
+							 u8 *tag)
 {
 	u8 parser_id = sb->caps->flex_parser_id_geneve_tlv_option_0;
 	struct mlx5dr_match_misc *misc = &value->misc;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index f42a1b1c9368..bf66d996e32e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -8,7 +8,6 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
-#include <linux/wait.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
@@ -36,6 +35,11 @@ enum mlxsw_pci_queue_type {
 
 #define MLXSW_PCI_QUEUE_TYPE_COUNT	4
 
+enum mlxsw_pci_cq_type {
+	MLXSW_PCI_CQ_SDQ,
+	MLXSW_PCI_CQ_RDQ,
+};
+
 static const u16 mlxsw_pci_doorbell_type_offset[] = {
 	MLXSW_PCI_DOORBELL_SDQ_OFFSET,	/* for type MLXSW_PCI_QUEUE_TYPE_SDQ */
 	MLXSW_PCI_DOORBELL_RDQ_OFFSET,	/* for type MLXSW_PCI_QUEUE_TYPE_RDQ */
@@ -78,18 +82,15 @@ struct mlxsw_pci_queue {
 	u8 num; /* queue number */
 	u8 elem_size; /* size of one element */
 	enum mlxsw_pci_queue_type type;
-	struct tasklet_struct tasklet; /* queue processing tasklet */
 	struct mlxsw_pci *pci;
 	union {
 		struct {
-			u32 comp_sdq_count;
-			u32 comp_rdq_count;
 			enum mlxsw_pci_cqe_v v;
+			struct mlxsw_pci_queue *dq;
+			struct napi_struct napi;
 		} cq;
 		struct {
-			u32 ev_cmd_count;
-			u32 ev_comp_count;
-			u32 ev_other_count;
+			struct tasklet_struct tasklet;
 		} eq;
 	} u;
 };
@@ -120,9 +121,6 @@ struct mlxsw_pci {
 		struct mlxsw_pci_mem_item out_mbox;
 		struct mlxsw_pci_mem_item in_mbox;
 		struct mutex lock; /* Lock access to command registers */
-		bool nopoll;
-		wait_queue_head_t wait;
-		bool wait_done;
 		struct {
 			u8 status;
 			u64 out_param;
@@ -131,13 +129,43 @@ struct mlxsw_pci {
 	struct mlxsw_bus_info bus_info;
 	const struct pci_device_id *id;
 	enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */
-	u8 num_sdq_cqs; /* Number of CQs used for SDQs */
+	u8 num_cqs; /* Number of CQs */
+	u8 num_sdqs; /* Number of SDQs */
 	bool skip_reset;
+	struct net_device *napi_dev_tx;
+	struct net_device *napi_dev_rx;
 };
 
-static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
+static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci)
+{
+	int err;
+
+	mlxsw_pci->napi_dev_tx = alloc_netdev_dummy(0);
+	if (!mlxsw_pci->napi_dev_tx)
+		return -ENOMEM;
+	strscpy(mlxsw_pci->napi_dev_tx->name, "mlxsw_tx",
+		sizeof(mlxsw_pci->napi_dev_tx->name));
+
+	mlxsw_pci->napi_dev_rx = alloc_netdev_dummy(0);
+	if (!mlxsw_pci->napi_dev_rx) {
+		err = -ENOMEM;
+		goto err_alloc_rx;
+	}
+	strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx",
+		sizeof(mlxsw_pci->napi_dev_rx->name));
+	dev_set_threaded(mlxsw_pci->napi_dev_rx, true);
+
+	return 0;
+
+err_alloc_rx:
+	free_netdev(mlxsw_pci->napi_dev_tx);
+	return err;
+}
+
+static void mlxsw_pci_napi_devs_fini(struct mlxsw_pci *mlxsw_pci)
 {
-	tasklet_schedule(&q->tasklet);
+	free_netdev(mlxsw_pci->napi_dev_rx);
+	free_netdev(mlxsw_pci->napi_dev_tx);
 }
 
 static char *__mlxsw_pci_queue_elem_get(struct mlxsw_pci_queue *q,
@@ -187,25 +215,6 @@ mlxsw_pci_queue_type_group_get(struct mlxsw_pci *mlxsw_pci,
 	return &mlxsw_pci->queues[q_type];
 }
 
-static u8 __mlxsw_pci_queue_count(struct mlxsw_pci *mlxsw_pci,
-				  enum mlxsw_pci_queue_type q_type)
-{
-	struct mlxsw_pci_queue_type_group *queue_group;
-
-	queue_group = mlxsw_pci_queue_type_group_get(mlxsw_pci, q_type);
-	return queue_group->count;
-}
-
-static u8 mlxsw_pci_sdq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_SDQ);
-}
-
-static u8 mlxsw_pci_cq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_CQ);
-}
-
 static struct mlxsw_pci_queue *
 __mlxsw_pci_queue_get(struct mlxsw_pci *mlxsw_pci,
 		      enum mlxsw_pci_queue_type q_type, u8 q_num)
@@ -220,23 +229,16 @@ static struct mlxsw_pci_queue *mlxsw_pci_sdq_get(struct mlxsw_pci *mlxsw_pci,
 				     MLXSW_PCI_QUEUE_TYPE_SDQ, q_num);
 }
 
-static struct mlxsw_pci_queue *mlxsw_pci_rdq_get(struct mlxsw_pci *mlxsw_pci,
-						 u8 q_num)
-{
-	return __mlxsw_pci_queue_get(mlxsw_pci,
-				     MLXSW_PCI_QUEUE_TYPE_RDQ, q_num);
-}
-
 static struct mlxsw_pci_queue *mlxsw_pci_cq_get(struct mlxsw_pci *mlxsw_pci,
 						u8 q_num)
 {
 	return __mlxsw_pci_queue_get(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_CQ, q_num);
 }
 
-static struct mlxsw_pci_queue *mlxsw_pci_eq_get(struct mlxsw_pci *mlxsw_pci,
-						u8 q_num)
+static struct mlxsw_pci_queue *mlxsw_pci_eq_get(struct mlxsw_pci *mlxsw_pci)
 {
-	return __mlxsw_pci_queue_get(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_EQ, q_num);
+	/* There is only one EQ at index 0. */
+	return __mlxsw_pci_queue_get(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_EQ, 0);
 }
 
 static void __mlxsw_pci_queue_doorbell_set(struct mlxsw_pci *mlxsw_pci,
@@ -291,7 +293,9 @@ static dma_addr_t __mlxsw_pci_queue_page_get(struct mlxsw_pci_queue *q,
 static int mlxsw_pci_sdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			      struct mlxsw_pci_queue *q)
 {
+	struct mlxsw_pci_queue *cq;
 	int tclass;
+	u8 cq_num;
 	int lp;
 	int i;
 	int err;
@@ -304,7 +308,8 @@ static int mlxsw_pci_sdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 						  MLXSW_CMD_MBOX_SW2HW_DQ_SDQ_LP_WQE;
 
 	/* Set CQ of same number of this SDQ. */
-	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num);
+	cq_num = q->num;
+	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, cq_num);
 	mlxsw_cmd_mbox_sw2hw_dq_sdq_lp_set(mbox, lp);
 	mlxsw_cmd_mbox_sw2hw_dq_sdq_tclass_set(mbox, tclass);
 	mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */
@@ -317,6 +322,9 @@ static int mlxsw_pci_sdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	err = mlxsw_cmd_sw2hw_sdq(mlxsw_pci->core, mbox, q->num);
 	if (err)
 		return err;
+
+	cq = mlxsw_pci_cq_get(mlxsw_pci, cq_num);
+	cq->u.cq.dq = q;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
 	return 0;
 }
@@ -399,7 +407,9 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			      struct mlxsw_pci_queue *q)
 {
 	struct mlxsw_pci_queue_elem_info *elem_info;
-	u8 sdq_count = mlxsw_pci_sdq_count(mlxsw_pci);
+	u8 sdq_count = mlxsw_pci->num_sdqs;
+	struct mlxsw_pci_queue *cq;
+	u8 cq_num;
 	int i;
 	int err;
 
@@ -409,7 +419,8 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	/* Set CQ of same number of this RDQ with base
 	 * above SDQ count as the lower ones are assigned to SDQs.
 	 */
-	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, sdq_count + q->num);
+	cq_num = sdq_count + q->num;
+	mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, cq_num);
 	mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
 		dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
@@ -421,6 +432,9 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	if (err)
 		return err;
 
+	cq = mlxsw_pci_cq_get(mlxsw_pci, cq_num);
+	cq->u.cq.dq = q;
+
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
 
 	for (i = 0; i < q->count; i++) {
@@ -441,6 +455,7 @@ rollback:
 		elem_info = mlxsw_pci_queue_elem_info_get(q, i);
 		mlxsw_pci_rdq_skb_free(mlxsw_pci, elem_info);
 	}
+	cq->u.cq.dq = NULL;
 	mlxsw_cmd_hw2sw_rdq(mlxsw_pci->core, q->num);
 
 	return err;
@@ -465,54 +480,11 @@ static void mlxsw_pci_cq_pre_init(struct mlxsw_pci *mlxsw_pci,
 	q->u.cq.v = mlxsw_pci->max_cqe_ver;
 
 	if (q->u.cq.v == MLXSW_PCI_CQE_V2 &&
-	    q->num < mlxsw_pci->num_sdq_cqs &&
+	    q->num < mlxsw_pci->num_sdqs &&
 	    !mlxsw_core_sdq_supports_cqe_v2(mlxsw_pci->core))
 		q->u.cq.v = MLXSW_PCI_CQE_V1;
 }
 
-static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
-			     struct mlxsw_pci_queue *q)
-{
-	int i;
-	int err;
-
-	q->consumer_counter = 0;
-
-	for (i = 0; i < q->count; i++) {
-		char *elem = mlxsw_pci_queue_elem_get(q, i);
-
-		mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1);
-	}
-
-	if (q->u.cq.v == MLXSW_PCI_CQE_V1)
-		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
-				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1);
-	else if (q->u.cq.v == MLXSW_PCI_CQE_V2)
-		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
-				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2);
-
-	mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
-	mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
-	mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
-	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
-		dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
-
-		mlxsw_cmd_mbox_sw2hw_cq_pa_set(mbox, i, mapaddr);
-	}
-	err = mlxsw_cmd_sw2hw_cq(mlxsw_pci->core, mbox, q->num);
-	if (err)
-		return err;
-	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
-	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
-	return 0;
-}
-
-static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
-			      struct mlxsw_pci_queue *q)
-{
-	mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
-}
-
 static unsigned int mlxsw_pci_read32_off(struct mlxsw_pci *mlxsw_pci,
 					 ptrdiff_t off)
 {
@@ -692,9 +664,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
 
 out:
-	/* Everything is set up, ring doorbell to pass elem to HW */
 	q->producer_counter++;
-	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
 	return;
 }
 
@@ -714,58 +684,165 @@ static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q)
 	return elem;
 }
 
-static void mlxsw_pci_cq_tasklet(struct tasklet_struct *t)
+static bool mlxsw_pci_cq_cqe_to_handle(struct mlxsw_pci_queue *q)
 {
-	struct mlxsw_pci_queue *q = from_tasklet(q, t, tasklet);
+	struct mlxsw_pci_queue_elem_info *elem_info;
+	bool owner_bit;
+
+	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+	owner_bit = mlxsw_pci_cqe_owner_get(q->u.cq.v, elem_info->elem);
+	return !mlxsw_pci_elem_hw_owned(q, owner_bit);
+}
+
+static int mlxsw_pci_napi_poll_cq_rx(struct napi_struct *napi, int budget)
+{
+	struct mlxsw_pci_queue *q = container_of(napi, struct mlxsw_pci_queue,
+						 u.cq.napi);
+	struct mlxsw_pci_queue *rdq = q->u.cq.dq;
 	struct mlxsw_pci *mlxsw_pci = q->pci;
+	int work_done = 0;
 	char *cqe;
-	int items = 0;
-	int credits = q->count >> 1;
+
+	/* If the budget is 0, Rx processing should be skipped. */
+	if (unlikely(!budget))
+		return 0;
 
 	while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) {
 		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
 		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
 		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
-		char ncqe[MLXSW_PCI_CQE_SIZE_MAX];
 
-		memcpy(ncqe, cqe, q->elem_size);
-		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+		if (unlikely(sendq)) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
 
-		if (sendq) {
-			struct mlxsw_pci_queue *sdq;
+		if (unlikely(dqn != rdq->num)) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
 
-			sdq = mlxsw_pci_sdq_get(mlxsw_pci, dqn);
-			mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
-						 wqe_counter, q->u.cq.v, ncqe);
-			q->u.cq.comp_sdq_count++;
-		} else {
-			struct mlxsw_pci_queue *rdq;
+		mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
+					 wqe_counter, q->u.cq.v, cqe);
 
-			rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
-			mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
-						 wqe_counter, q->u.cq.v, ncqe);
-			q->u.cq.comp_rdq_count++;
-		}
-		if (++items == credits)
+		if (++work_done == budget)
 			break;
 	}
-	if (items)
+
+	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, rdq);
+
+	if (work_done < budget)
+		goto processing_completed;
+
+	/* The driver still has outstanding work to do, budget was exhausted.
+	 * Return exactly budget. In that case, the NAPI instance will be polled
+	 * again.
+	 */
+	if (mlxsw_pci_cq_cqe_to_handle(q))
+		goto out;
+
+	/* The driver processed all the completions and handled exactly
+	 * 'budget'. Return 'budget - 1' to distinguish from the case that
+	 * driver still has completions to handle.
+	 */
+	if (work_done == budget)
+		work_done--;
+
+processing_completed:
+	if (napi_complete_done(napi, work_done))
 		mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
+out:
+	return work_done;
 }
 
-static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
+static int mlxsw_pci_napi_poll_cq_tx(struct napi_struct *napi, int budget)
 {
-	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT :
-					       MLXSW_PCI_CQE01_COUNT;
+	struct mlxsw_pci_queue *q = container_of(napi, struct mlxsw_pci_queue,
+						 u.cq.napi);
+	struct mlxsw_pci_queue *sdq = q->u.cq.dq;
+	struct mlxsw_pci *mlxsw_pci = q->pci;
+	int work_done = 0;
+	char *cqe;
+
+	while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) {
+		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
+		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
+		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
+		char ncqe[MLXSW_PCI_CQE_SIZE_MAX];
+
+		if (unlikely(!sendq)) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		if (unlikely(dqn != sdq->num)) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		memcpy(ncqe, cqe, q->elem_size);
+		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+
+		mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
+					 wqe_counter, q->u.cq.v, ncqe);
+
+		work_done++;
+	}
+
+	/* If the budget is 0 napi_complete_done() should never be called. */
+	if (unlikely(!budget))
+		goto processing_completed;
+
+	work_done = min(work_done, budget - 1);
+	if (unlikely(!napi_complete_done(napi, work_done)))
+		goto out;
+
+processing_completed:
+	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
+out:
+	return work_done;
 }
 
-static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q)
+static enum mlxsw_pci_cq_type
+mlxsw_pci_cq_type(const struct mlxsw_pci *mlxsw_pci,
+		  const struct mlxsw_pci_queue *q)
 {
-	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE :
-					       MLXSW_PCI_CQE01_SIZE;
+	/* Each CQ is mapped to one DQ. The first 'num_sdqs' queues are used
+	 * for SDQs and the rest are used for RDQs.
+	 */
+	if (q->num < mlxsw_pci->num_sdqs)
+		return MLXSW_PCI_CQ_SDQ;
+
+	return MLXSW_PCI_CQ_RDQ;
 }
 
-static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
+static void mlxsw_pci_cq_napi_setup(struct mlxsw_pci_queue *q,
+				    enum mlxsw_pci_cq_type cq_type)
+{
+	struct mlxsw_pci *mlxsw_pci = q->pci;
+
+	switch (cq_type) {
+	case MLXSW_PCI_CQ_SDQ:
+		netif_napi_add(mlxsw_pci->napi_dev_tx, &q->u.cq.napi,
+			       mlxsw_pci_napi_poll_cq_tx);
+		break;
+	case MLXSW_PCI_CQ_RDQ:
+		netif_napi_add(mlxsw_pci->napi_dev_rx, &q->u.cq.napi,
+			       mlxsw_pci_napi_poll_cq_rx);
+		break;
+	}
+
+	napi_enable(&q->u.cq.napi);
+}
+
+static void mlxsw_pci_cq_napi_teardown(struct mlxsw_pci_queue *q)
+{
+	napi_disable(&q->u.cq.napi);
+	netif_napi_del(&q->u.cq.napi);
+}
+
+static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
 	int i;
@@ -776,39 +853,50 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	for (i = 0; i < q->count; i++) {
 		char *elem = mlxsw_pci_queue_elem_get(q, i);
 
-		mlxsw_pci_eqe_owner_set(elem, 1);
+		mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1);
 	}
 
-	mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */
-	mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */
-	mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count));
+	if (q->u.cq.v == MLXSW_PCI_CQE_V1)
+		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1);
+	else if (q->u.cq.v == MLXSW_PCI_CQE_V2)
+		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2);
+
+	mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
+	mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
+	mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
 		dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
 
-		mlxsw_cmd_mbox_sw2hw_eq_pa_set(mbox, i, mapaddr);
+		mlxsw_cmd_mbox_sw2hw_cq_pa_set(mbox, i, mapaddr);
 	}
-	err = mlxsw_cmd_sw2hw_eq(mlxsw_pci->core, mbox, q->num);
+	err = mlxsw_cmd_sw2hw_cq(mlxsw_pci->core, mbox, q->num);
 	if (err)
 		return err;
+	mlxsw_pci_cq_napi_setup(q, mlxsw_pci_cq_type(mlxsw_pci, q));
 	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
 	return 0;
 }
 
-static void mlxsw_pci_eq_fini(struct mlxsw_pci *mlxsw_pci,
+static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
 			      struct mlxsw_pci_queue *q)
 {
-	mlxsw_cmd_hw2sw_eq(mlxsw_pci->core, q->num);
+	mlxsw_pci_cq_napi_teardown(q);
+	mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
 }
 
-static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe)
+static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
 {
-	mlxsw_pci->cmd.comp.status = mlxsw_pci_eqe_cmd_status_get(eqe);
-	mlxsw_pci->cmd.comp.out_param =
-		((u64) mlxsw_pci_eqe_cmd_out_param_h_get(eqe)) << 32 |
-		mlxsw_pci_eqe_cmd_out_param_l_get(eqe);
-	mlxsw_pci->cmd.wait_done = true;
-	wake_up(&mlxsw_pci->cmd.wait);
+	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT :
+					     MLXSW_PCI_CQE01_COUNT;
+}
+
+static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q)
+{
+	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE :
+					       MLXSW_PCI_CQE01_SIZE;
 }
 
 static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q)
@@ -829,52 +917,79 @@ static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q)
 
 static void mlxsw_pci_eq_tasklet(struct tasklet_struct *t)
 {
-	struct mlxsw_pci_queue *q = from_tasklet(q, t, tasklet);
-	struct mlxsw_pci *mlxsw_pci = q->pci;
-	u8 cq_count = mlxsw_pci_cq_count(mlxsw_pci);
 	unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_MAX)];
-	char *eqe;
-	u8 cqn;
-	bool cq_handle = false;
-	int items = 0;
+	struct mlxsw_pci_queue *q = from_tasklet(q, t, u.eq.tasklet);
+	struct mlxsw_pci *mlxsw_pci = q->pci;
 	int credits = q->count >> 1;
+	u8 cqn, cq_count;
+	int items = 0;
+	char *eqe;
 
 	memset(&active_cqns, 0, sizeof(active_cqns));
 
 	while ((eqe = mlxsw_pci_eq_sw_eqe_get(q))) {
+		cqn = mlxsw_pci_eqe_cqn_get(eqe);
+		set_bit(cqn, active_cqns);
 
-		/* Command interface completion events are always received on
-		 * queue MLXSW_PCI_EQ_ASYNC_NUM (EQ0) and completion events
-		 * are mapped to queue MLXSW_PCI_EQ_COMP_NUM (EQ1).
-		 */
-		switch (q->num) {
-		case MLXSW_PCI_EQ_ASYNC_NUM:
-			mlxsw_pci_eq_cmd_event(mlxsw_pci, eqe);
-			q->u.eq.ev_cmd_count++;
-			break;
-		case MLXSW_PCI_EQ_COMP_NUM:
-			cqn = mlxsw_pci_eqe_cqn_get(eqe);
-			set_bit(cqn, active_cqns);
-			cq_handle = true;
-			q->u.eq.ev_comp_count++;
-			break;
-		default:
-			q->u.eq.ev_other_count++;
-		}
 		if (++items == credits)
 			break;
 	}
-	if (items) {
-		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
-		mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
-	}
 
-	if (!cq_handle)
+	if (!items)
 		return;
+
+	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
+
+	cq_count = mlxsw_pci->num_cqs;
 	for_each_set_bit(cqn, active_cqns, cq_count) {
 		q = mlxsw_pci_cq_get(mlxsw_pci, cqn);
-		mlxsw_pci_queue_tasklet_schedule(q);
+		napi_schedule(&q->u.cq.napi);
+	}
+}
+
+static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
+			     struct mlxsw_pci_queue *q)
+{
+	int i;
+	int err;
+
+	/* We expect to initialize only one EQ, which gets num=0 as it is
+	 * located at index zero. We use the EQ as EQ1, so set the number for
+	 * future use.
+	 */
+	WARN_ON_ONCE(q->num);
+	q->num = MLXSW_PCI_EQ_COMP_NUM;
+
+	q->consumer_counter = 0;
+
+	for (i = 0; i < q->count; i++) {
+		char *elem = mlxsw_pci_queue_elem_get(q, i);
+
+		mlxsw_pci_eqe_owner_set(elem, 1);
+	}
+
+	mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */
+	mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */
+	mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count));
+	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
+		dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
+
+		mlxsw_cmd_mbox_sw2hw_eq_pa_set(mbox, i, mapaddr);
 	}
+	err = mlxsw_cmd_sw2hw_eq(mlxsw_pci->core, mbox, q->num);
+	if (err)
+		return err;
+	tasklet_setup(&q->u.eq.tasklet, mlxsw_pci_eq_tasklet);
+	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
+	return 0;
+}
+
+static void mlxsw_pci_eq_fini(struct mlxsw_pci *mlxsw_pci,
+			      struct mlxsw_pci_queue *q)
+{
+	mlxsw_cmd_hw2sw_eq(mlxsw_pci->core, q->num);
 }
 
 struct mlxsw_pci_queue_ops {
@@ -886,7 +1001,6 @@ struct mlxsw_pci_queue_ops {
 		    struct mlxsw_pci_queue *q);
 	void (*fini)(struct mlxsw_pci *mlxsw_pci,
 		     struct mlxsw_pci_queue *q);
-	void (*tasklet)(struct tasklet_struct *t);
 	u16 (*elem_count_f)(const struct mlxsw_pci_queue *q);
 	u8 (*elem_size_f)(const struct mlxsw_pci_queue *q);
 	u16 elem_count;
@@ -914,7 +1028,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
 	.pre_init	= mlxsw_pci_cq_pre_init,
 	.init		= mlxsw_pci_cq_init,
 	.fini		= mlxsw_pci_cq_fini,
-	.tasklet	= mlxsw_pci_cq_tasklet,
 	.elem_count_f	= mlxsw_pci_cq_elem_count,
 	.elem_size_f	= mlxsw_pci_cq_elem_size
 };
@@ -923,7 +1036,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_EQ,
 	.init		= mlxsw_pci_eq_init,
 	.fini		= mlxsw_pci_eq_fini,
-	.tasklet	= mlxsw_pci_eq_tasklet,
 	.elem_count	= MLXSW_PCI_EQE_COUNT,
 	.elem_size	= MLXSW_PCI_EQE_SIZE
 };
@@ -948,9 +1060,6 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	q->type = q_ops->type;
 	q->pci = mlxsw_pci;
 
-	if (q_ops->tasklet)
-		tasklet_setup(&q->tasklet, q_ops->tasklet);
-
 	mem_item->size = MLXSW_PCI_AQ_SIZE;
 	mem_item->buf = dma_alloc_coherent(&mlxsw_pci->pdev->dev,
 					   mem_item->size, &mem_item->mapaddr,
@@ -1074,7 +1183,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 
 	if (num_sdqs + num_rdqs > num_cqs ||
 	    num_sdqs < MLXSW_PCI_SDQS_MIN ||
-	    num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_COUNT) {
+	    num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_MAX) {
 		dev_err(&pdev->dev, "Unsupported number of queues\n");
 		return -EINVAL;
 	}
@@ -1089,10 +1198,11 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 		return -EINVAL;
 	}
 
-	mlxsw_pci->num_sdq_cqs = num_sdqs;
+	mlxsw_pci->num_cqs = num_cqs;
+	mlxsw_pci->num_sdqs = num_sdqs;
 
 	err = mlxsw_pci_queue_group_init(mlxsw_pci, mbox, &mlxsw_pci_eq_ops,
-					 num_eqs);
+					 MLXSW_PCI_EQS_COUNT);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to initialize event queues\n");
 		return err;
@@ -1119,8 +1229,6 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 		goto err_rdqs_init;
 	}
 
-	/* We have to poll in command interface until queues are initialized */
-	mlxsw_pci->cmd.nopoll = true;
 	return 0;
 
 err_rdqs_init:
@@ -1134,7 +1242,6 @@ err_cqs_init:
 
 static void mlxsw_pci_aqs_fini(struct mlxsw_pci *mlxsw_pci)
 {
-	mlxsw_pci->cmd.nopoll = false;
 	mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_rdq_ops);
 	mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_sdq_ops);
 	mlxsw_pci_queue_group_fini(mlxsw_pci, &mlxsw_pci_cq_ops);
@@ -1432,12 +1539,9 @@ static irqreturn_t mlxsw_pci_eq_irq_handler(int irq, void *dev_id)
 {
 	struct mlxsw_pci *mlxsw_pci = dev_id;
 	struct mlxsw_pci_queue *q;
-	int i;
 
-	for (i = 0; i < MLXSW_PCI_EQS_COUNT; i++) {
-		q = mlxsw_pci_eq_get(mlxsw_pci, i);
-		mlxsw_pci_queue_tasklet_schedule(q);
-	}
+	q = mlxsw_pci_eq_get(mlxsw_pci);
+	tasklet_schedule(&q->u.eq.tasklet);
 	return IRQ_HANDLED;
 }
 
@@ -1709,6 +1813,10 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_requery_resources;
 
+	err = mlxsw_pci_napi_devs_init(mlxsw_pci);
+	if (err)
+		goto err_napi_devs_init;
+
 	err = mlxsw_pci_aqs_init(mlxsw_pci, mbox);
 	if (err)
 		goto err_aqs_init;
@@ -1726,6 +1834,8 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 err_request_eq_irq:
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 err_aqs_init:
+	mlxsw_pci_napi_devs_fini(mlxsw_pci);
+err_napi_devs_init:
 err_requery_resources:
 err_config_profile:
 err_cqe_v_check:
@@ -1753,6 +1863,7 @@ static void mlxsw_pci_fini(void *bus_priv)
 
 	free_irq(pci_irq_vector(mlxsw_pci->pdev, 0), mlxsw_pci);
 	mlxsw_pci_aqs_fini(mlxsw_pci);
+	mlxsw_pci_napi_devs_fini(mlxsw_pci);
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 }
@@ -1761,7 +1872,7 @@ static struct mlxsw_pci_queue *
 mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci,
 		   const struct mlxsw_tx_info *tx_info)
 {
-	u8 ctl_sdq_count = mlxsw_pci_sdq_count(mlxsw_pci) - 1;
+	u8 ctl_sdq_count = mlxsw_pci->num_sdqs - 1;
 	u8 sdqn;
 
 	if (tx_info->is_emad) {
@@ -1860,9 +1971,9 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 {
 	struct mlxsw_pci *mlxsw_pci = bus_priv;
 	dma_addr_t in_mapaddr = 0, out_mapaddr = 0;
-	bool evreq = mlxsw_pci->cmd.nopoll;
 	unsigned long timeout = msecs_to_jiffies(MLXSW_PCI_CIR_TIMEOUT_MSECS);
-	bool *p_wait_done = &mlxsw_pci->cmd.wait_done;
+	unsigned long end;
+	bool wait_done;
 	int err;
 
 	*p_status = MLXSW_CMD_STATUS_OK;
@@ -1886,36 +1997,28 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 	mlxsw_pci_write32(mlxsw_pci, CIR_IN_MODIFIER, in_mod);
 	mlxsw_pci_write32(mlxsw_pci, CIR_TOKEN, 0);
 
-	*p_wait_done = false;
+	wait_done = false;
 
 	wmb(); /* all needs to be written before we write control register */
 	mlxsw_pci_write32(mlxsw_pci, CIR_CTRL,
 			  MLXSW_PCI_CIR_CTRL_GO_BIT |
-			  (evreq ? MLXSW_PCI_CIR_CTRL_EVREQ_BIT : 0) |
 			  (opcode_mod << MLXSW_PCI_CIR_CTRL_OPCODE_MOD_SHIFT) |
 			  opcode);
 
-	if (!evreq) {
-		unsigned long end;
-
-		end = jiffies + timeout;
-		do {
-			u32 ctrl = mlxsw_pci_read32(mlxsw_pci, CIR_CTRL);
+	end = jiffies + timeout;
+	do {
+		u32 ctrl = mlxsw_pci_read32(mlxsw_pci, CIR_CTRL);
 
-			if (!(ctrl & MLXSW_PCI_CIR_CTRL_GO_BIT)) {
-				*p_wait_done = true;
-				*p_status = ctrl >> MLXSW_PCI_CIR_CTRL_STATUS_SHIFT;
-				break;
-			}
-			cond_resched();
-		} while (time_before(jiffies, end));
-	} else {
-		wait_event_timeout(mlxsw_pci->cmd.wait, *p_wait_done, timeout);
-		*p_status = mlxsw_pci->cmd.comp.status;
-	}
+		if (!(ctrl & MLXSW_PCI_CIR_CTRL_GO_BIT)) {
+			wait_done = true;
+			*p_status = ctrl >> MLXSW_PCI_CIR_CTRL_STATUS_SHIFT;
+			break;
+		}
+		cond_resched();
+	} while (time_before(jiffies, end));
 
 	err = 0;
-	if (*p_wait_done) {
+	if (wait_done) {
 		if (*p_status)
 			err = -EIO;
 	} else {
@@ -1929,14 +2032,12 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 		 */
 		__be32 tmp;
 
-		if (!evreq) {
-			tmp = cpu_to_be32(mlxsw_pci_read32(mlxsw_pci,
-							   CIR_OUT_PARAM_HI));
-			memcpy(out_mbox, &tmp, sizeof(tmp));
-			tmp = cpu_to_be32(mlxsw_pci_read32(mlxsw_pci,
-							   CIR_OUT_PARAM_LO));
-			memcpy(out_mbox + sizeof(tmp), &tmp, sizeof(tmp));
-		}
+		tmp = cpu_to_be32(mlxsw_pci_read32(mlxsw_pci,
+						   CIR_OUT_PARAM_HI));
+		memcpy(out_mbox, &tmp, sizeof(tmp));
+		tmp = cpu_to_be32(mlxsw_pci_read32(mlxsw_pci,
+						   CIR_OUT_PARAM_LO));
+		memcpy(out_mbox + sizeof(tmp), &tmp, sizeof(tmp));
 	} else if (!err && out_mbox) {
 		memcpy(out_mbox, mlxsw_pci->cmd.out_mbox.buf, out_mbox_size);
 	}
@@ -2015,7 +2116,6 @@ static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci)
 	int err;
 
 	mutex_init(&mlxsw_pci->cmd.lock);
-	init_waitqueue_head(&mlxsw_pci->cmd.wait);
 
 	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 7cdf0ce24f28..6bed495dcf0f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -42,8 +42,8 @@
 	((offset) + (type_offset) + (num) * 4)
 
 #define MLXSW_PCI_CQS_MAX	96
-#define MLXSW_PCI_EQS_COUNT	2
-#define MLXSW_PCI_EQ_ASYNC_NUM	0
+#define MLXSW_PCI_EQS_MAX	2
+#define MLXSW_PCI_EQS_COUNT	1
 #define MLXSW_PCI_EQ_COMP_NUM	1
 
 #define MLXSW_PCI_SDQS_MIN	2 /* EMAD and control traffic */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 8892654c685f..8adf86a6f5cc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4786,8 +4786,11 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR	BIT(8)
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4		BIT(9)
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2		BIT(10)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_1_100GBASE_CR_KR		BIT(11)
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4		BIT(12)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_2_200GBASE_CR2_KR2		BIT(13)
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_8				BIT(15)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_4_400GBASE_CR4_KR4		BIT(16)
 #define MLXSW_REG_PTYS_EXT_ETH_SPEED_800GAUI_8				BIT(19)
 
 /* reg_ptys_ext_eth_proto_cap
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index bb642e9bb6cf..030ed71f945d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -825,7 +825,7 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu)
 	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu);
 	if (err)
 		goto err_port_mtu_set;
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 	return 0;
 
 err_port_mtu_set:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 92a406f02eae..b1d08e958bf9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1504,7 +1504,8 @@ mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id,
 
 static int
 mlxsw_sp_acl_tcam_region_rehash_intrvl_set(struct devlink *devlink, u32 id,
-					   struct devlink_param_gset_ctx *ctx)
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 0f29e9c19411..a755b0a901d3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1649,6 +1649,18 @@ mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2[] = {
 	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2)
 
 static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_100gaui_1_100gbase_cr_kr[] = {
+	ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseDR_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_100GAUI_1_100GBASE_CR_KR_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_100gaui_1_100gbase_cr_kr)
+
+static const enum ethtool_link_mode_bit_indices
 mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = {
 	ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
 	ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
@@ -1661,6 +1673,18 @@ mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = {
 	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4)
 
 static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_200gaui_2_200gbase_cr2_kr2[] = {
+	ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_200GAUI_2_200GBASE_CR2_KR2_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_2_200gbase_cr2_kr2)
+
+static const enum ethtool_link_mode_bit_indices
 mlxsw_sp2_mask_ethtool_400gaui_8[] = {
 	ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT,
 	ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT,
@@ -1673,6 +1697,18 @@ mlxsw_sp2_mask_ethtool_400gaui_8[] = {
 	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_400gaui_8)
 
 static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_400gaui_4_400gbase_cr4_kr4[] = {
+	ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
+	ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT,
+	ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_400GAUI_4_400GBASE_CR4_KR4_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_400gaui_4_400gbase_cr4_kr4)
+
+static const enum ethtool_link_mode_bit_indices
 mlxsw_sp2_mask_ethtool_800gaui_8[] = {
 	ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT,
 	ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT,
@@ -1817,6 +1853,14 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = {
 		.width		= 2,
 	},
 	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_1_100GBASE_CR_KR,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_100gaui_1_100gbase_cr_kr,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_100GAUI_1_100GBASE_CR_KR_LEN,
+		.mask_sup_width	= MLXSW_SP_PORT_MASK_WIDTH_1X,
+		.speed		= SPEED_100000,
+		.width		= 1,
+	},
+	{
 		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4,
 		.mask_ethtool	= mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4,
 		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN,
@@ -1826,6 +1870,14 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = {
 		.width		= 4,
 	},
 	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_2_200GBASE_CR2_KR2,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_200gaui_2_200gbase_cr2_kr2,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_200GAUI_2_200GBASE_CR2_KR2_LEN,
+		.mask_sup_width	= MLXSW_SP_PORT_MASK_WIDTH_2X,
+		.speed		= SPEED_200000,
+		.width		= 2,
+	},
+	{
 		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_8,
 		.mask_ethtool	= mlxsw_sp2_mask_ethtool_400gaui_8,
 		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_400GAUI_8_LEN,
@@ -1834,6 +1886,14 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = {
 		.width		= 8,
 	},
 	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_4_400GBASE_CR4_KR4,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_400gaui_4_400gbase_cr4_kr4,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_400GAUI_4_400GBASE_CR4_KR4_LEN,
+		.mask_sup_width	= MLXSW_SP_PORT_MASK_WIDTH_4X,
+		.speed		= SPEED_400000,
+		.width		= 4,
+	},
+	{
 		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_800GAUI_8,
 		.mask_ethtool	= mlxsw_sp2_mask_ethtool_800gaui_8,
 		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_800GAUI_8_LEN,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 9fd1ca079258..f07955b5439f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -595,6 +595,10 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 
 		flow_rule_match_control(rule, &match);
 		addr_type = match.key->addr_type;
+
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 3340b4a694c3..d761a1235994 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -8,7 +8,7 @@
 #include "spectrum_ipip.h"
 #include "reg.h"
 
-struct ip_tunnel_parm
+struct ip_tunnel_parm_kern
 mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev)
 {
 	struct ip_tunnel *tun = netdev_priv(ol_dev);
@@ -24,27 +24,29 @@ mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev)
 	return tun->parms;
 }
 
-static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm *parms)
+static bool
+mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm_kern *parms)
 {
-	return !!(parms->i_flags & TUNNEL_KEY);
+	return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags);
 }
 
 static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms)
 {
-	return !!(parms->i_flags & TUNNEL_KEY);
+	return test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags);
 }
 
-static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm *parms)
+static bool
+mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm_kern *parms)
 {
-	return !!(parms->o_flags & TUNNEL_KEY);
+	return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags);
 }
 
 static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms)
 {
-	return !!(parms->o_flags & TUNNEL_KEY);
+	return test_bit(IP_TUNNEL_KEY_BIT, parms->o_flags);
 }
 
-static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm *parms)
+static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm_kern *parms)
 {
 	return mlxsw_sp_ipip_parms4_has_ikey(parms) ?
 		be32_to_cpu(parms->i_key) : 0;
@@ -56,7 +58,7 @@ static u32 mlxsw_sp_ipip_parms6_ikey(const struct __ip6_tnl_parm *parms)
 		be32_to_cpu(parms->i_key) : 0;
 }
 
-static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm *parms)
+static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm_kern *parms)
 {
 	return mlxsw_sp_ipip_parms4_has_okey(parms) ?
 		be32_to_cpu(parms->o_key) : 0;
@@ -69,7 +71,7 @@ static u32 mlxsw_sp_ipip_parms6_okey(const struct __ip6_tnl_parm *parms)
 }
 
 static union mlxsw_sp_l3addr
-mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm *parms)
+mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm_kern *parms)
 {
 	return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.saddr };
 }
@@ -81,7 +83,7 @@ mlxsw_sp_ipip_parms6_saddr(const struct __ip6_tnl_parm *parms)
 }
 
 static union mlxsw_sp_l3addr
-mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm *parms)
+mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm_kern *parms)
 {
 	return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.daddr };
 }
@@ -96,7 +98,7 @@ union mlxsw_sp_l3addr
 mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
 			   const struct net_device *ol_dev)
 {
-	struct ip_tunnel_parm parms4;
+	struct ip_tunnel_parm_kern parms4;
 	struct __ip6_tnl_parm parms6;
 
 	switch (proto) {
@@ -115,7 +117,9 @@ mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto,
 static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev)
 {
 
-	struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev);
+	struct ip_tunnel_parm_kern parms4;
+
+	parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev);
 
 	return mlxsw_sp_ipip_parms4_daddr(&parms4).addr4;
 }
@@ -124,7 +128,7 @@ static union mlxsw_sp_l3addr
 mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto,
 			   const struct net_device *ol_dev)
 {
-	struct ip_tunnel_parm parms4;
+	struct ip_tunnel_parm_kern parms4;
 	struct __ip6_tnl_parm parms6;
 
 	switch (proto) {
@@ -150,7 +154,7 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr)
 static struct mlxsw_sp_ipip_parms
 mlxsw_sp_ipip_netdev_parms_init_gre4(const struct net_device *ol_dev)
 {
-	struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev);
+	struct ip_tunnel_parm_kern parms = mlxsw_sp_ipip_netdev_parms4(ol_dev);
 
 	return (struct mlxsw_sp_ipip_parms) {
 		.proto = MLXSW_SP_L3_PROTO_IPV4,
@@ -187,8 +191,8 @@ mlxsw_sp_ipip_decap_config_gre4(struct mlxsw_sp *mlxsw_sp,
 {
 	u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb);
 	u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb);
+	struct ip_tunnel_parm_kern parms;
 	char rtdp_pl[MLXSW_REG_RTDP_LEN];
-	struct ip_tunnel_parm parms;
 	unsigned int type_check;
 	bool has_ikey;
 	u32 daddr4;
@@ -238,12 +242,15 @@ static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp,
 					   const struct net_device *ol_dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(ol_dev);
-	__be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */
 	bool inherit_ttl = tunnel->parms.iph.ttl == 0;
 	bool inherit_tos = tunnel->parms.iph.tos & 0x1;
+	IP_TUNNEL_DECLARE_FLAGS(okflags) = { };
+
+	/* We can't offload any other features. */
+	__set_bit(IP_TUNNEL_KEY_BIT, okflags);
 
-	return (tunnel->parms.i_flags & ~okflags) == 0 &&
-	       (tunnel->parms.o_flags & ~okflags) == 0 &&
+	return ip_tunnel_flags_subset(tunnel->parms.i_flags, okflags) &&
+	       ip_tunnel_flags_subset(tunnel->parms.o_flags, okflags) &&
 	       inherit_ttl && inherit_tos &&
 	       mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV4, ol_dev);
 }
@@ -252,7 +259,7 @@ static struct mlxsw_sp_rif_ipip_lb_config
 mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp,
 				      const struct net_device *ol_dev)
 {
-	struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev);
+	struct ip_tunnel_parm_kern parms = mlxsw_sp_ipip_netdev_parms4(ol_dev);
 	enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt;
 
 	lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(&parms) ?
@@ -439,10 +446,13 @@ static bool mlxsw_sp_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp,
 	struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev);
 	bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS;
 	bool inherit_ttl = tparm.hop_limit == 0;
-	__be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */
+	IP_TUNNEL_DECLARE_FLAGS(okflags) = { };
+
+	/* We can't offload any other features. */
+	__set_bit(IP_TUNNEL_KEY_BIT, okflags);
 
-	return (tparm.i_flags & ~okflags) == 0 &&
-	       (tparm.o_flags & ~okflags) == 0 &&
+	return ip_tunnel_flags_subset(tparm.i_flags, okflags) &&
+	       ip_tunnel_flags_subset(tparm.o_flags, okflags) &&
 	       inherit_ttl && inherit_tos &&
 	       mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
index a35f009da561..a66173779641 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
@@ -9,7 +9,7 @@
 #include <linux/if_tunnel.h>
 #include <net/ip6_tunnel.h>
 
-struct ip_tunnel_parm
+struct ip_tunnel_parm_kern
 mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev);
 struct __ip6_tnl_parm
 mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index af50ff9e5f26..4b5fd71c897d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -413,8 +413,8 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 			    __be32 *saddrp, __be32 *daddrp)
 {
 	struct ip_tunnel *tun = netdev_priv(to_dev);
+	struct ip_tunnel_parm_kern parms;
 	struct net_device *dev = NULL;
-	struct ip_tunnel_parm parms;
 	struct rtable *rt = NULL;
 	struct flowi4 fl4;
 
@@ -451,7 +451,7 @@ mlxsw_sp_span_entry_gretap4_parms(struct mlxsw_sp *mlxsw_sp,
 				  const struct net_device *to_dev,
 				  struct mlxsw_sp_span_parms *sparmsp)
 {
-	struct ip_tunnel_parm tparm = mlxsw_sp_ipip_netdev_parms4(to_dev);
+	struct ip_tunnel_parm_kern tparm = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	union mlxsw_sp_l3addr saddr = { .addr4 = tparm.iph.saddr };
 	union mlxsw_sp_l3addr daddr = { .addr4 = tparm.iph.daddr };
 	bool inherit_tos = tparm.iph.tos & 0x1;
@@ -461,7 +461,8 @@ mlxsw_sp_span_entry_gretap4_parms(struct mlxsw_sp *mlxsw_sp,
 
 	if (!(to_dev->flags & IFF_UP) ||
 	    /* Reject tunnels with GRE keys, checksums, etc. */
-	    tparm.i_flags || tparm.o_flags ||
+	    !ip_tunnel_flags_empty(tparm.i_flags) ||
+	    !ip_tunnel_flags_empty(tparm.o_flags) ||
 	    /* Require a fixed TTL and a TOS copied from the mirrored packet. */
 	    inherit_ttl || !inherit_tos ||
 	    /* A destination address may not be "any". */
@@ -539,7 +540,7 @@ mlxsw_sp_span_gretap6_route(const struct net_device *to_dev,
 	if (!dst || dst->error)
 		goto out;
 
-	rt6 = container_of(dst, struct rt6_info, dst);
+	rt6 = dst_rt6_info(dst);
 
 	dev = dst->dev;
 	*saddrp = fl6.saddr;
@@ -565,7 +566,8 @@ mlxsw_sp_span_entry_gretap6_parms(struct mlxsw_sp *mlxsw_sp,
 
 	if (!(to_dev->flags & IFF_UP) ||
 	    /* Reject tunnels with GRE keys, checksums, etc. */
-	    tparm.i_flags || tparm.o_flags ||
+	    !ip_tunnel_flags_empty(tparm.i_flags) ||
+	    !ip_tunnel_flags_empty(tparm.o_flags) ||
 	    /* Require a fixed TTL and a TOS copied from the mirrored packet. */
 	    inherit_ttl || !inherit_tos ||
 	    /* A destination address may not be "any". */
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index c5aeeb964c17..dc1d9f774565 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -5427,7 +5427,7 @@ static int netdev_change_mtu(struct net_device *dev, int new_mtu)
 	}
 	hw_mtu = (hw_mtu + 3) & ~3;
 	hw_priv->mtu = hw_mtu;
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c
index 443128adbcb6..3885d6fbace1 100644
--- a/drivers/net/ethernet/microchip/encx24j600-regmap.c
+++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c
@@ -75,7 +75,7 @@ static int regmap_encx24j600_sfr_read(void *context, u8 reg, u8 *val,
 		if (unlikely(ret))
 			return ret;
 	} else {
-		/* Translate registers that are more effecient using
+		/* Translate registers that are more efficient using
 		 * 3-byte SPI commands
 		 */
 		switch (reg) {
@@ -129,7 +129,7 @@ static int regmap_encx24j600_sfr_update(struct encx24j600_context *ctx,
 		if (unlikely(ret))
 			return ret;
 	} else {
-		/* Translate registers that are more effecient using
+		/* Translate registers that are more efficient using
 		 * 3-byte SPI commands
 		 */
 		switch (reg) {
diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index d7c8aa77ec75..b011bf5c2305 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -569,7 +569,7 @@ static void encx24j600_dump_config(struct encx24j600_priv *priv,
 	pr_info(DRV_NAME " MABBIPG: %04X\n", encx24j600_read_reg(priv,
 								 MABBIPG));
 
-	/* PHY configuation */
+	/* PHY configuration */
 	pr_info(DRV_NAME " PHCON1:  %04X\n", encx24j600_read_phy(priv, PHCON1));
 	pr_info(DRV_NAME " PHCON2:  %04X\n", encx24j600_read_phy(priv, PHCON2));
 	pr_info(DRV_NAME " PHANA:   %04X\n", encx24j600_read_phy(priv, PHANA));
@@ -837,7 +837,9 @@ static void encx24j600_hw_tx(struct encx24j600_priv *priv)
 		dump_packet("TX", priv->tx_skb->len, priv->tx_skb->data);
 
 	if (encx24j600_read_reg(priv, EIR) & TXABTIF)
-		/* Last transmition aborted due to error. Reset TX interface */
+		/* Last transmission aborted due to error.
+		 * Reset TX interface
+		 */
 		encx24j600_reset_hw_tx(priv);
 
 	/* Clear the TXIF flag if were previously set */
@@ -1112,7 +1114,6 @@ MODULE_DEVICE_TABLE(spi, encx24j600_spi_id_table);
 static struct spi_driver encx24j600_spi_net_driver = {
 	.driver = {
 		.name	= DRV_NAME,
-		.owner	= THIS_MODULE,
 		.bus	= &spi_bus_type,
 	},
 	.probe		= encx24j600_spi_probe,
diff --git a/drivers/net/ethernet/microchip/encx24j600_hw.h b/drivers/net/ethernet/microchip/encx24j600_hw.h
index 34c5a289898c..2522f4f48b67 100644
--- a/drivers/net/ethernet/microchip/encx24j600_hw.h
+++ b/drivers/net/ethernet/microchip/encx24j600_hw.h
@@ -243,7 +243,7 @@ int devm_regmap_init_encx24j600(struct device *dev,
 
 /* MAIPG */
 /* value of the high byte is given by the reserved bits,
- * value of the low byte is recomended setting of the
+ * value of the low byte is recommended setting of the
  * IPG parameter.
  */
 #define MAIPGH_VAL 0x0C
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 8a6ae171e375..d0f4ff4ee075 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -1076,15 +1076,10 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev,
 
 	buf = lan743x_csr_read(adapter, MAC_CR);
 	if (buf & MAC_CR_EEE_EN_) {
-		eee->eee_enabled = true;
-		eee->tx_lpi_enabled = true;
 		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
 		buf = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
 		eee->tx_lpi_timer = buf;
 	} else {
-		eee->eee_enabled = false;
-		eee->eee_active = false;
-		eee->tx_lpi_enabled = false;
 		eee->tx_lpi_timer = 0;
 	}
 
@@ -1097,7 +1092,6 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev,
 	struct lan743x_adapter *adapter;
 	struct phy_device *phydev;
 	u32 buf = 0;
-	int ret = 0;
 
 	if (!netdev)
 		return -EINVAL;
@@ -1114,23 +1108,8 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev,
 	}
 
 	if (eee->eee_enabled) {
-		ret = phy_init_eee(phydev, false);
-		if (ret) {
-			netif_err(adapter, drv, adapter->netdev,
-				  "EEE initialization failed\n");
-			return ret;
-		}
-
 		buf = (u32)eee->tx_lpi_timer;
 		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, buf);
-
-		buf = lan743x_csr_read(adapter, MAC_CR);
-		buf |= MAC_CR_EEE_EN_;
-		lan743x_csr_write(adapter, MAC_CR, buf);
-	} else {
-		buf = lan743x_csr_read(adapter, MAC_CR);
-		buf &= ~MAC_CR_EEE_EN_;
-		lan743x_csr_write(adapter, MAC_CR, buf);
 	}
 
 	return phy_ethtool_set_eee(phydev, eee);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 75a988c0bd79..6be8a43c908a 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -803,7 +803,7 @@ static int lan743x_mdiobus_read_c22(struct mii_bus *bus, int phy_id, int index)
 	u32 val, mii_access;
 	int ret;
 
-	/* comfirm MII not busy */
+	/* confirm MII not busy */
 	ret = lan743x_mac_mii_wait_till_not_busy(adapter);
 	if (ret < 0)
 		return ret;
@@ -868,7 +868,7 @@ static int lan743x_mdiobus_read_c45(struct mii_bus *bus, int phy_id,
 	u32 mmd_access;
 	int ret;
 
-	/* comfirm MII not busy */
+	/* confirm MII not busy */
 	ret = lan743x_mac_mii_wait_till_not_busy(adapter);
 	if (ret < 0)
 		return ret;
@@ -1462,6 +1462,13 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 		    phydev->interface == PHY_INTERFACE_MODE_1000BASEX ||
 		    phydev->interface == PHY_INTERFACE_MODE_2500BASEX)
 			lan743x_sgmii_config(adapter);
+
+		data = lan743x_csr_read(adapter, MAC_CR);
+		if (phydev->enable_tx_lpi)
+			data |=  MAC_CR_EEE_EN_;
+		else
+			data &= ~MAC_CR_EEE_EN_;
+		lan743x_csr_write(adapter, MAC_CR, data);
 	}
 }
 
@@ -3177,7 +3184,7 @@ static int lan743x_netdev_change_mtu(struct net_device *netdev, int new_mtu)
 
 	ret = lan743x_mac_set_mtu(adapter, new_mtu);
 	if (!ret)
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 2801f08bf1c9..dcea6652d56d 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -58,7 +58,7 @@ int lan743x_gpio_init(struct lan743x_adapter *adapter)
 static void lan743x_ptp_wait_till_cmd_done(struct lan743x_adapter *adapter,
 					   u32 bit_mask)
 {
-	int timeout = 1000;
+	int timeout = PTP_CMD_CTL_TIMEOUT_CNT;
 	u32 data = 0;
 
 	while (timeout &&
@@ -555,7 +555,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
 			if (half == wf_high) {
 				/* It's 50% match. Use the toggle option */
 				pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_TOGGLE_;
-				/* In this case, devide period value by 2 */
+				/* In this case, divide period value by 2 */
 				ts_period = ns_to_timespec64(div_s64(period64, 2));
 				period_sec = ts_period.tv_sec;
 				period_nsec = ts_period.tv_nsec;
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index e26d4eff7133..0d29914cd460 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -21,6 +21,7 @@
 #define LAN743X_PTP_N_EXTTS		4
 #define LAN743X_PTP_N_PPS		0
 #define PCI11X1X_PTP_IO_MAX_CHANNELS	8
+#define PTP_CMD_CTL_TIMEOUT_CNT		50
 
 struct lan743x_adapter;
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h
index f3b1e0d31826..e706163ce9cc 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h
@@ -78,7 +78,7 @@
 /* Classified internal priority for queuing */
 #define IFH_POS_QOS_CLASS            100
 
-/* Bit mask with eight cpu copy classses */
+/* Bit mask with eight cpu copy classes */
 #define IFH_POS_CPUQ                 92
 
 /* Relearn + learn flags (*) */
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 2635ef8958c8..b12d3b8a64fd 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -276,7 +276,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb,
 		++i;
 	}
 
-	/* Inidcate EOF and valid bytes in the last word */
+	/* Indicate EOF and valid bytes in the last word */
 	lan_wr(QS_INJ_CTRL_GAP_SIZE_SET(1) |
 	       QS_INJ_CTRL_VLD_BYTES_SET(skb->len < LAN966X_BUFFER_MIN_SZ ?
 				     0 : last) |
@@ -402,7 +402,7 @@ static int lan966x_port_change_mtu(struct net_device *dev, int new_mtu)
 
 	lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(LAN966X_HW_MTU(new_mtu)),
 	       lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port));
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (!lan966x->fdma)
 		return 0;
@@ -520,7 +520,7 @@ bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, struct sk_buff *skb)
 	u32 val;
 
 	/* The IGMP and MLD frames are not forward by the HW if
-	 * multicast snooping is enabled, therefor don't mark as
+	 * multicast snooping is enabled, therefore don't mark as
 	 * offload to allow the SW to forward the frames accordingly.
 	 */
 	val = lan_rd(lan966x, ANA_CPU_FWD_CFG(port));
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index caa9e0533c96..f8bebbcf77b2 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -326,7 +326,7 @@ struct lan966x {
 
 	u8 base_mac[ETH_ALEN];
 
-	spinlock_t tx_lock; /* lock for frame transmition */
+	spinlock_t tx_lock; /* lock for frame transmission */
 
 	struct net_device *bridge;
 	u16 bridge_mask;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index 2e83bbb9477e..fdfa4040d9ee 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -88,7 +88,7 @@ static void lan966x_port_link_down(struct lan966x_port *port)
 		SYS_FRONT_PORT_MODE_HDX_MODE,
 		lan966x, SYS_FRONT_PORT_MODE(port->chip_port));
 
-	/* 8: Flush the queues accociated with the port */
+	/* 8: Flush the queues associated with the port */
 	lan_rmw(QSYS_SW_PORT_MODE_AGING_MODE_SET(3),
 		QSYS_SW_PORT_MODE_AGING_MODE,
 		lan966x, QSYS_SW_PORT_MODE(port->chip_port));
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
index d696cf9dbd19..43913d6204e1 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
@@ -45,6 +45,7 @@ static bool lan966x_tc_is_known_etype(struct vcap_tc_flower_parse_usage *st,
 static int
 lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 {
+	struct netlink_ext_ack *extack = st->fco->common.extack;
 	struct flow_match_control match;
 	int err = 0;
 
@@ -59,7 +60,7 @@ lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 						    VCAP_KF_L3_FRAGMENT,
 						    VCAP_BIT_0);
 		if (err)
-			goto out;
+			goto bad_frag_out;
 	}
 
 	if (match.mask->flags & FLOW_DIS_FIRST_FRAG) {
@@ -72,15 +73,20 @@ lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 						    VCAP_KF_L3_FRAG_OFS_GT0,
 						    VCAP_BIT_1);
 		if (err)
-			goto out;
+			goto bad_frag_out;
 	}
 
+	if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT |
+					     FLOW_DIS_FIRST_FRAG,
+					     match.mask->flags, extack))
+		return -EOPNOTSUPP;
+
 	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
 
 	return err;
 
-out:
-	NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error");
+bad_frag_out:
+	NL_SET_ERR_MSG_MOD(extack, "ip_frag parse error");
 	return err;
 }
 
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
index 3c44660128da..fa34a739c748 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
@@ -157,7 +157,7 @@ void lan966x_vlan_port_apply(struct lan966x_port *port)
 
 	pvid = lan966x_vlan_port_get_pvid(port);
 
-	/* Ingress clasification (ANA_PORT_VLAN_CFG) */
+	/* Ingress classification (ANA_PORT_VLAN_CFG) */
 	/* Default vlan to classify for untagged frames (may be zero) */
 	val = ANA_VLAN_CFG_VLAN_VID_SET(pvid);
 	if (port->vlan_aware)
diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile
index 1cb1cc3f1a85..b68fe9c9a656 100644
--- a/drivers/net/ethernet/microchip/sparx5/Makefile
+++ b/drivers/net/ethernet/microchip/sparx5/Makefile
@@ -10,7 +10,8 @@ sparx5-switch-y  := sparx5_main.o sparx5_packet.o \
  sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o \
  sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o \
  sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o \
- sparx5_tc_matchall.o sparx5_pool.o sparx5_sdlb.o sparx5_police.o sparx5_psfp.o
+ sparx5_tc_matchall.o sparx5_pool.o sparx5_sdlb.o sparx5_police.o \
+ sparx5_psfp.o sparx5_mirror.o
 
 sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o
 sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 141897dfe388..1915998f6079 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -143,7 +143,7 @@ static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 
 static void sparx5_fdma_rx_deactivate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
-	/* Dectivate the RX channel */
+	/* Deactivate the RX channel */
 	spx5_rmw(0, BIT(rx->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
 		 sparx5, FDMA_CH_ACTIVATE);
 
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index 3c066b62e689..b64c814eac11 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -899,6 +899,9 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 		dev_err(sparx5->dev, "PTP failed\n");
 		goto cleanup_ports;
 	}
+
+	INIT_LIST_HEAD(&sparx5->mall_entries);
+
 	goto cleanup_config;
 
 cleanup_ports:
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 316fed5f2735..1982ae03b4fe 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -18,6 +18,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/hrtimer.h>
 #include <linux/debugfs.h>
+#include <net/flow_offload.h>
 
 #include "sparx5_main_regs.h"
 
@@ -173,6 +174,7 @@ struct sparx5_port {
 	struct phylink_config phylink_config;
 	struct phylink *phylink;
 	struct phylink_pcs phylink_pcs;
+	struct flow_stats mirror_stats;
 	u16 portno;
 	/* Ingress default VLAN (pvid) */
 	u16 pvid;
@@ -227,6 +229,22 @@ struct sparx5_mdb_entry {
 	u16 pgid_idx;
 };
 
+struct sparx5_mall_mirror_entry {
+	u32 idx;
+	struct sparx5_port *port;
+};
+
+struct sparx5_mall_entry {
+	struct list_head list;
+	struct sparx5_port *port;
+	unsigned long cookie;
+	enum flow_action_id type;
+	bool ingress;
+	union {
+		struct sparx5_mall_mirror_entry mirror;
+	};
+};
+
 #define SPARX5_PTP_TIMEOUT		msecs_to_jiffies(10)
 #define SPARX5_SKB_CB(skb) \
 	((struct sparx5_skb_cb *)((skb)->cb))
@@ -295,6 +313,7 @@ struct sparx5 {
 	struct vcap_control *vcap_ctrl;
 	/* PGID allocation map */
 	u8 pgid_map[PGID_TABLE_SIZE];
+	struct list_head mall_entries;
 	/* Common root for debugfs */
 	struct dentry *debugfs_root;
 };
@@ -541,6 +560,12 @@ void sparx5_psfp_init(struct sparx5 *sparx5);
 void sparx5_new_base_time(struct sparx5 *sparx5, const u32 cycle_time,
 			  const ktime_t org_base_time, ktime_t *new_base_time);
 
+/* sparx5_mirror.c */
+int sparx5_mirror_add(struct sparx5_mall_entry *entry);
+void sparx5_mirror_del(struct sparx5_mall_entry *entry);
+void sparx5_mirror_stats(struct sparx5_mall_entry *entry,
+			 struct flow_stats *fstats);
+
 /* Clock period in picoseconds */
 static inline u32 sparx5_clk_period(enum sparx5_core_clockfreq cclock)
 {
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
index bd03a0a3c1da..22acc1f3380c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h
@@ -83,6 +83,64 @@ enum sparx5_target {
 #define ANA_AC_OWN_UPSID_OWN_UPSID_GET(x)\
 	FIELD_GET(ANA_AC_OWN_UPSID_OWN_UPSID, x)
 
+/*      ANA_AC:MIRROR_PROBE:PROBE_CFG */
+#define ANA_AC_PROBE_CFG(g) \
+	__REG(TARGET_ANA_AC, 0, 1, 893696, g, 3, 32, 0, 0, 1, 4)
+
+#define ANA_AC_PROBE_CFG_PROBE_RX_CPU_AND_VD GENMASK(31, 27)
+#define ANA_AC_PROBE_CFG_PROBE_RX_CPU_AND_VD_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_RX_CPU_AND_VD, x)
+#define ANA_AC_PROBE_CFG_PROBE_RX_CPU_AND_VD_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_RX_CPU_AND_VD, x)
+
+#define ANA_AC_PROBE_CFG_PROBE_CPU_SET      GENMASK(26, 19)
+#define ANA_AC_PROBE_CFG_PROBE_CPU_SET_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_CPU_SET, x)
+#define ANA_AC_PROBE_CFG_PROBE_CPU_SET_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_CPU_SET, x)
+
+#define ANA_AC_PROBE_CFG_PROBE_VID          GENMASK(18, 6)
+#define ANA_AC_PROBE_CFG_PROBE_VID_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_VID, x)
+#define ANA_AC_PROBE_CFG_PROBE_VID_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_VID, x)
+
+#define ANA_AC_PROBE_CFG_PROBE_VLAN_MODE    GENMASK(5, 4)
+#define ANA_AC_PROBE_CFG_PROBE_VLAN_MODE_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_VLAN_MODE, x)
+#define ANA_AC_PROBE_CFG_PROBE_VLAN_MODE_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_VLAN_MODE, x)
+
+#define ANA_AC_PROBE_CFG_PROBE_MAC_MODE     GENMASK(3, 2)
+#define ANA_AC_PROBE_CFG_PROBE_MAC_MODE_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_MAC_MODE, x)
+#define ANA_AC_PROBE_CFG_PROBE_MAC_MODE_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_MAC_MODE, x)
+
+#define ANA_AC_PROBE_CFG_PROBE_DIRECTION    GENMASK(1, 0)
+#define ANA_AC_PROBE_CFG_PROBE_DIRECTION_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_CFG_PROBE_DIRECTION, x)
+#define ANA_AC_PROBE_CFG_PROBE_DIRECTION_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_CFG_PROBE_DIRECTION, x)
+
+/*      ANA_AC:MIRROR_PROBE:PROBE_PORT_CFG */
+#define ANA_AC_PROBE_PORT_CFG(g) \
+	__REG(TARGET_ANA_AC, 0, 1, 893696, g, 3, 32, 8, 0, 1, 4)
+
+/*      ANA_AC:MIRROR_PROBE:PROBE_PORT_CFG1 */
+#define ANA_AC_PROBE_PORT_CFG1(g) \
+	__REG(TARGET_ANA_AC, 0, 1, 893696, g, 3, 32, 12, 0, 1, 4)
+
+/*      ANA_AC:MIRROR_PROBE:PROBE_PORT_CFG2 */
+#define ANA_AC_PROBE_PORT_CFG2(g) \
+	__REG(TARGET_ANA_AC, 0, 1, 893696, g, 3, 32, 16, 0, 1, 4)
+
+#define ANA_AC_PROBE_PORT_CFG2_PROBE_PORT_MASK2 BIT(0)
+#define ANA_AC_PROBE_PORT_CFG2_PROBE_PORT_MASK2_SET(x)\
+	FIELD_PREP(ANA_AC_PROBE_PORT_CFG2_PROBE_PORT_MASK2, x)
+#define ANA_AC_PROBE_PORT_CFG2_PROBE_PORT_MASK2_GET(x)\
+	FIELD_GET(ANA_AC_PROBE_PORT_CFG2_PROBE_PORT_MASK2, x)
+
 /*      ANA_AC:SRC:SRC_CFG */
 #define ANA_AC_SRC_CFG(g)         __REG(TARGET_ANA_AC,\
 					0, 1, 849920, g, 102, 16, 0, 0, 1, 4)
@@ -6203,6 +6261,16 @@ enum sparx5_target {
 #define QFWD_SWITCH_PORT_MODE_LEARNALL_MORE_GET(x)\
 	FIELD_GET(QFWD_SWITCH_PORT_MODE_LEARNALL_MORE, x)
 
+/*      QFWD:SYSTEM:FRAME_COPY_CFG */
+#define QFWD_FRAME_COPY_CFG(r)\
+	__REG(TARGET_QFWD, 0, 1, 0, 0, 1, 340, 284, r, 12, 4)
+
+#define QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL   GENMASK(12, 6)
+#define QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL_SET(x)\
+	FIELD_PREP(QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL, x)
+#define QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL_GET(x)\
+	FIELD_GET(QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL, x)
+
 /*      QRES:RES_CTRL:RES_CFG */
 #define QRES_RES_CFG(g)           __REG(TARGET_QRES,\
 					0, 1, 0, g, 5120, 16, 0, 0, 1, 4)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c
new file mode 100644
index 000000000000..15db423be4aa
--- /dev/null
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Microchip Sparx5 Switch driver
+ *
+ * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries.
+ */
+
+#include "sparx5_main.h"
+#include "sparx5_main_regs.h"
+#include "sparx5_tc.h"
+
+#define SPX5_MIRROR_PROBE_MAX 3
+#define SPX5_MIRROR_DISABLED 0
+#define SPX5_MIRROR_EGRESS 1
+#define SPX5_MIRROR_INGRESS 2
+#define SPX5_MIRROR_MONITOR_PORT_DEFAULT 65
+#define SPX5_QFWD_MP_OFFSET 9 /* Mirror port offset in the QFWD register */
+
+/* Convert from bool ingress/egress to mirror direction */
+static u32 sparx5_mirror_to_dir(bool ingress)
+{
+	return ingress ? SPX5_MIRROR_INGRESS : SPX5_MIRROR_EGRESS;
+}
+
+/* Get ports belonging to this mirror */
+static u64 sparx5_mirror_port_get(struct sparx5 *sparx5, u32 idx)
+{
+	return (u64)spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG1(idx)) << 32 |
+	       spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG(idx));
+}
+
+/* Add port to mirror (only front ports) */
+static void sparx5_mirror_port_add(struct sparx5 *sparx5, u32 idx, u32 portno)
+{
+	u32 val, reg = portno;
+
+	reg = portno / BITS_PER_BYTE;
+	val = BIT(portno % BITS_PER_BYTE);
+
+	if (reg == 0)
+		return spx5_rmw(val, val, sparx5, ANA_AC_PROBE_PORT_CFG(idx));
+	else
+		return spx5_rmw(val, val, sparx5, ANA_AC_PROBE_PORT_CFG1(idx));
+}
+
+/* Delete port from mirror (only front ports) */
+static void sparx5_mirror_port_del(struct sparx5 *sparx5, u32 idx, u32 portno)
+{
+	u32 val, reg = portno;
+
+	reg = portno / BITS_PER_BYTE;
+	val = BIT(portno % BITS_PER_BYTE);
+
+	if (reg == 0)
+		return spx5_rmw(0, val, sparx5, ANA_AC_PROBE_PORT_CFG(idx));
+	else
+		return spx5_rmw(0, val, sparx5, ANA_AC_PROBE_PORT_CFG1(idx));
+}
+
+/* Check if mirror contains port */
+static bool sparx5_mirror_contains(struct sparx5 *sparx5, u32 idx, u32 portno)
+{
+	return (sparx5_mirror_port_get(sparx5, idx) & BIT_ULL(portno)) != 0;
+}
+
+/* Check if mirror is empty */
+static bool sparx5_mirror_is_empty(struct sparx5 *sparx5, u32 idx)
+{
+	return sparx5_mirror_port_get(sparx5, idx) == 0;
+}
+
+/* Get direction of mirror */
+static u32 sparx5_mirror_dir_get(struct sparx5 *sparx5, u32 idx)
+{
+	u32 val = spx5_rd(sparx5, ANA_AC_PROBE_CFG(idx));
+
+	return ANA_AC_PROBE_CFG_PROBE_DIRECTION_GET(val);
+}
+
+/* Set direction of mirror */
+static void sparx5_mirror_dir_set(struct sparx5 *sparx5, u32 idx, u32 dir)
+{
+	spx5_rmw(ANA_AC_PROBE_CFG_PROBE_DIRECTION_SET(dir),
+		 ANA_AC_PROBE_CFG_PROBE_DIRECTION, sparx5,
+		 ANA_AC_PROBE_CFG(idx));
+}
+
+/* Set the monitor port for this mirror */
+static void sparx5_mirror_monitor_set(struct sparx5 *sparx5, u32 idx,
+				      u32 portno)
+{
+	spx5_rmw(QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL_SET(portno),
+		 QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL, sparx5,
+		 QFWD_FRAME_COPY_CFG(idx + SPX5_QFWD_MP_OFFSET));
+}
+
+/* Get the monitor port of this mirror */
+static u32 sparx5_mirror_monitor_get(struct sparx5 *sparx5, u32 idx)
+{
+	u32 val = spx5_rd(sparx5,
+			  QFWD_FRAME_COPY_CFG(idx + SPX5_QFWD_MP_OFFSET));
+
+	return QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL_GET(val);
+}
+
+/* Check if port is the monitor port of this mirror */
+static bool sparx5_mirror_has_monitor(struct sparx5 *sparx5, u32 idx,
+				      u32 portno)
+{
+	return sparx5_mirror_monitor_get(sparx5, idx) == portno;
+}
+
+/* Get a suitable mirror for this port */
+static int sparx5_mirror_get(struct sparx5_port *sport,
+			     struct sparx5_port *mport, u32 dir, u32 *idx)
+{
+	struct sparx5 *sparx5 = sport->sparx5;
+	u32 i;
+
+	/* Check if this port is already used as a monitor port */
+	for (i = 0; i < SPX5_MIRROR_PROBE_MAX; i++)
+		if (sparx5_mirror_has_monitor(sparx5, i, sport->portno))
+			return -EINVAL;
+
+	/* Check if existing mirror can be reused
+	 * (same direction and monitor port).
+	 */
+	for (i = 0; i < SPX5_MIRROR_PROBE_MAX; i++) {
+		if (sparx5_mirror_dir_get(sparx5, i) == dir &&
+		    sparx5_mirror_has_monitor(sparx5, i, mport->portno)) {
+			*idx = i;
+			return 0;
+		}
+	}
+
+	/* Return free mirror */
+	for (i = 0; i < SPX5_MIRROR_PROBE_MAX; i++) {
+		if (sparx5_mirror_is_empty(sparx5, i)) {
+			*idx = i;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+int sparx5_mirror_add(struct sparx5_mall_entry *entry)
+{
+	u32 mirror_idx, dir = sparx5_mirror_to_dir(entry->ingress);
+	struct sparx5_port *sport, *mport;
+	struct sparx5 *sparx5;
+	int err;
+
+	/* Source port */
+	sport = entry->port;
+	/* monitor port */
+	mport = entry->mirror.port;
+	sparx5 = sport->sparx5;
+
+	if (sport->portno == mport->portno)
+		return -EINVAL;
+
+	err = sparx5_mirror_get(sport, mport, dir, &mirror_idx);
+	if (err)
+		return err;
+
+	if (sparx5_mirror_contains(sparx5, mirror_idx, sport->portno))
+		return -EEXIST;
+
+	/* Add port to mirror */
+	sparx5_mirror_port_add(sparx5, mirror_idx, sport->portno);
+
+	/* Set direction of mirror */
+	sparx5_mirror_dir_set(sparx5, mirror_idx, dir);
+
+	/* Set monitor port for mirror */
+	sparx5_mirror_monitor_set(sparx5, mirror_idx, mport->portno);
+
+	entry->mirror.idx = mirror_idx;
+
+	return 0;
+}
+
+void sparx5_mirror_del(struct sparx5_mall_entry *entry)
+{
+	struct sparx5_port *port = entry->port;
+	struct sparx5 *sparx5 = port->sparx5;
+	u32 mirror_idx = entry->mirror.idx;
+
+	sparx5_mirror_port_del(sparx5, mirror_idx, port->portno);
+	if (!sparx5_mirror_is_empty(sparx5, mirror_idx))
+		return;
+
+	sparx5_mirror_dir_set(sparx5, mirror_idx, SPX5_MIRROR_DISABLED);
+
+	sparx5_mirror_monitor_set(sparx5,
+				  mirror_idx,
+				  SPX5_MIRROR_MONITOR_PORT_DEFAULT);
+}
+
+void sparx5_mirror_stats(struct sparx5_mall_entry *entry,
+			 struct flow_stats *fstats)
+{
+	struct sparx5_port *port = entry->port;
+	struct rtnl_link_stats64 new_stats;
+	struct flow_stats *old_stats;
+
+	old_stats = &entry->port->mirror_stats;
+	sparx5_get_stats64(port->ndev, &new_stats);
+
+	if (entry->ingress) {
+		flow_stats_update(fstats,
+				  new_stats.rx_bytes - old_stats->bytes,
+				  new_stats.rx_packets - old_stats->pkts,
+				  new_stats.rx_dropped - old_stats->drops,
+				  old_stats->lastused,
+				  FLOW_ACTION_HW_STATS_IMMEDIATE);
+
+		old_stats->bytes = new_stats.rx_bytes;
+		old_stats->pkts = new_stats.rx_packets;
+		old_stats->drops = new_stats.rx_dropped;
+		old_stats->lastused = jiffies;
+	} else {
+		flow_stats_update(fstats,
+				  new_stats.tx_bytes - old_stats->bytes,
+				  new_stats.tx_packets - old_stats->pkts,
+				  new_stats.tx_dropped - old_stats->drops,
+				  old_stats->lastused,
+				  FLOW_ACTION_HW_STATS_IMMEDIATE);
+
+		old_stats->bytes = new_stats.tx_bytes;
+		old_stats->pkts = new_stats.tx_packets;
+		old_stats->drops = new_stats.tx_dropped;
+		old_stats->lastused = jiffies;
+	}
+}
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index ac7e1cffbcec..f3f5fb420468 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -67,7 +67,7 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap)
 	for (i = 0; i < IFH_LEN; i++)
 		ifh[i] = spx5_rd(sparx5, QS_XTR_RD(grp));
 
-	/* Decode IFH (whats needed) */
+	/* Decode IFH (what's needed) */
 	sparx5_ifh_parse(ifh, &fi);
 
 	/* Map to port netdev */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index 60dd2fd603a8..062e486c002c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -370,7 +370,7 @@ static int sparx5_port_disable(struct sparx5 *sparx5, struct sparx5_port *port,
 	/* 6: Wait while the last frame is exiting the queues */
 	usleep_range(8 * spd_prm, 10 * spd_prm);
 
-	/* 7: Flush the queues accociated with the port->portno */
+	/* 7: Flush the queues associated with the port->portno */
 	spx5_rmw(HSCH_FLUSH_CTRL_FLUSH_PORT_SET(port->portno) |
 		 HSCH_FLUSH_CTRL_FLUSH_DST_SET(1) |
 		 HSCH_FLUSH_CTRL_FLUSH_SRC_SET(1) |
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
index 4af85d108a06..0b4abc3eb53d 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c
@@ -190,7 +190,7 @@ static int sparx5_port_bridge_join(struct sparx5_port *port,
 	/* Remove standalone port entry */
 	sparx5_mact_forget(sparx5, ndev->dev_addr, 0);
 
-	/* Port enters in bridge mode therefor don't need to copy to CPU
+	/* Port enters in bridge mode therefore don't need to copy to CPU
 	 * frames for multicast in case the bridge is not requesting them
 	 */
 	__dev_mc_unsync(ndev, sparx5_mc_unsync);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
index 55f255a3c9db..8d67d9f24c76 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
@@ -159,13 +159,14 @@ out:
 static int
 sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 {
+	struct netlink_ext_ack *extack = st->fco->common.extack;
 	struct flow_match_control mt;
 	u32 value, mask;
 	int err = 0;
 
 	flow_rule_match_control(st->frule, &mt);
 
-	if (mt.mask->flags) {
+	if (mt.mask->flags & (FLOW_DIS_IS_FRAGMENT | FLOW_DIS_FIRST_FRAG)) {
 		u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT);
 		u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT);
 		u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask;
@@ -178,7 +179,7 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 		u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx];
 
 		if (vdt == FRAG_INVAL) {
-			NL_SET_ERR_MSG_MOD(st->fco->common.extack,
+			NL_SET_ERR_MSG_MOD(extack,
 					   "Match on invalid fragment flag combination");
 			return -EINVAL;
 		}
@@ -190,16 +191,19 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st)
 		err = vcap_rule_add_key_u32(st->vrule,
 					    VCAP_KF_L3_FRAGMENT_TYPE,
 					    value, mask);
-		if (err)
-			goto out;
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "ip_frag parse error");
+			return err;
+		}
 	}
 
-	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
+	if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT |
+					     FLOW_DIS_FIRST_FRAG,
+					     mt.mask->flags, extack))
+		return -EOPNOTSUPP;
 
-	return err;
+	st->used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL);
 
-out:
-	NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error");
 	return err;
 }
 
@@ -1023,6 +1027,64 @@ static int sparx5_tc_action_vlan_push(struct vcap_admin *admin,
 	return err;
 }
 
+static void sparx5_tc_flower_set_port_mask(struct vcap_u72_action *ports,
+					   struct net_device *ndev)
+{
+	struct sparx5_port *port = netdev_priv(ndev);
+	int byidx = port->portno / BITS_PER_BYTE;
+	int biidx = port->portno % BITS_PER_BYTE;
+
+	ports->value[byidx] |= BIT(biidx);
+}
+
+static int sparx5_tc_action_mirred(struct vcap_admin *admin,
+				   struct vcap_rule *vrule,
+				   struct flow_cls_offload *fco,
+				   struct flow_action_entry *act)
+{
+	struct vcap_u72_action ports = {0};
+	int err;
+
+	if (admin->vtype != VCAP_TYPE_IS0 && admin->vtype != VCAP_TYPE_IS2) {
+		NL_SET_ERR_MSG_MOD(fco->common.extack,
+				   "Mirror action not supported in this VCAP");
+		return -EOPNOTSUPP;
+	}
+
+	err = vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE,
+				       SPX5_PMM_OR_DSTMASK);
+	if (err)
+		return err;
+
+	sparx5_tc_flower_set_port_mask(&ports, act->dev);
+
+	return vcap_rule_add_action_u72(vrule, VCAP_AF_PORT_MASK, &ports);
+}
+
+static int sparx5_tc_action_redirect(struct vcap_admin *admin,
+				     struct vcap_rule *vrule,
+				     struct flow_cls_offload *fco,
+				     struct flow_action_entry *act)
+{
+	struct vcap_u72_action ports = {0};
+	int err;
+
+	if (admin->vtype != VCAP_TYPE_IS0 && admin->vtype != VCAP_TYPE_IS2) {
+		NL_SET_ERR_MSG_MOD(fco->common.extack,
+				   "Redirect action not supported in this VCAP");
+		return -EOPNOTSUPP;
+	}
+
+	err = vcap_rule_add_action_u32(vrule, VCAP_AF_MASK_MODE,
+				       SPX5_PMM_REPLACE_ALL);
+	if (err)
+		return err;
+
+	sparx5_tc_flower_set_port_mask(&ports, act->dev);
+
+	return vcap_rule_add_action_u72(vrule, VCAP_AF_PORT_MASK, &ports);
+}
+
 /* Remove rule keys that may prevent templates from matching a keyset */
 static void sparx5_tc_flower_simplify_rule(struct vcap_admin *admin,
 					   struct vcap_rule *vrule,
@@ -1169,6 +1231,16 @@ static int sparx5_tc_flower_replace(struct net_device *ndev,
 			if (err)
 				goto out;
 			break;
+		case FLOW_ACTION_MIRRED:
+			err = sparx5_tc_action_mirred(admin, vrule, fco, act);
+			if (err)
+				goto out;
+			break;
+		case FLOW_ACTION_REDIRECT:
+			err = sparx5_tc_action_redirect(admin, vrule, fco, act);
+			if (err)
+				goto out;
+			break;
 		case FLOW_ACTION_ACCEPT:
 			err = sparx5_tc_set_actionset(admin, vrule);
 			if (err)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c
index d88a93f22606..6b4d1d7b9730 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c
@@ -11,11 +11,44 @@
 #include "sparx5_main.h"
 #include "sparx5_vcap_impl.h"
 
+static struct sparx5_mall_entry *
+sparx5_tc_matchall_entry_find(struct list_head *entries, unsigned long cookie)
+{
+	struct sparx5_mall_entry *entry;
+
+	list_for_each_entry(entry, entries, list) {
+		if (entry->cookie == cookie)
+			return entry;
+	}
+
+	return NULL;
+}
+
+static void sparx5_tc_matchall_parse_action(struct sparx5_port *port,
+					    struct sparx5_mall_entry *entry,
+					    struct flow_action_entry *action,
+					    bool ingress,
+					    unsigned long cookie)
+{
+	entry->port = port;
+	entry->type = action->id;
+	entry->ingress = ingress;
+	entry->cookie = cookie;
+}
+
+static void
+sparx5_tc_matchall_parse_mirror_action(struct sparx5_mall_entry *entry,
+				       struct flow_action_entry *action)
+{
+	entry->mirror.port = netdev_priv(action->dev);
+}
+
 static int sparx5_tc_matchall_replace(struct net_device *ndev,
 				      struct tc_cls_matchall_offload *tmo,
 				      bool ingress)
 {
 	struct sparx5_port *port = netdev_priv(ndev);
+	struct sparx5_mall_entry *mall_entry;
 	struct flow_action_entry *action;
 	struct sparx5 *sparx5;
 	int err;
@@ -27,8 +60,45 @@ static int sparx5_tc_matchall_replace(struct net_device *ndev,
 	}
 	action = &tmo->rule->action.entries[0];
 
+	mall_entry = kzalloc(sizeof(*mall_entry), GFP_KERNEL);
+	if (!mall_entry)
+		return -ENOMEM;
+
+	sparx5_tc_matchall_parse_action(port,
+					mall_entry,
+					action,
+					ingress,
+					tmo->cookie);
+
 	sparx5 = port->sparx5;
 	switch (action->id) {
+	case FLOW_ACTION_MIRRED:
+		sparx5_tc_matchall_parse_mirror_action(mall_entry, action);
+		err = sparx5_mirror_add(mall_entry);
+		if (err) {
+			switch (err) {
+			case -EEXIST:
+				NL_SET_ERR_MSG_MOD(tmo->common.extack,
+						   "Mirroring already exists");
+				break;
+			case -EINVAL:
+				NL_SET_ERR_MSG_MOD(tmo->common.extack,
+						   "Cannot mirror a monitor port");
+				break;
+			case -ENOENT:
+				NL_SET_ERR_MSG_MOD(tmo->common.extack,
+						   "No more mirror probes available");
+				break;
+			default:
+				NL_SET_ERR_MSG_MOD(tmo->common.extack,
+						   "Unknown error");
+				break;
+			}
+			return err;
+		}
+		/* Get baseline stats for this port */
+		sparx5_mirror_stats(mall_entry, &tmo->stats);
+		break;
 	case FLOW_ACTION_GOTO:
 		err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev,
 					  tmo->common.chain_index,
@@ -59,6 +129,9 @@ static int sparx5_tc_matchall_replace(struct net_device *ndev,
 		NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action");
 		return -EOPNOTSUPP;
 	}
+
+	list_add_tail(&mall_entry->list, &sparx5->mall_entries);
+
 	return 0;
 }
 
@@ -67,19 +140,51 @@ static int sparx5_tc_matchall_destroy(struct net_device *ndev,
 				      bool ingress)
 {
 	struct sparx5_port *port = netdev_priv(ndev);
-	struct sparx5 *sparx5;
-	int err;
+	struct sparx5 *sparx5 = port->sparx5;
+	struct sparx5_mall_entry *entry;
+	int err = 0;
 
-	sparx5 = port->sparx5;
-	if (!tmo->rule && tmo->cookie) {
+	entry = sparx5_tc_matchall_entry_find(&sparx5->mall_entries,
+					      tmo->cookie);
+	if (!entry)
+		return -ENOENT;
+
+	if (entry->type == FLOW_ACTION_MIRRED) {
+		sparx5_mirror_del(entry);
+	} else if (entry->type == FLOW_ACTION_GOTO) {
 		err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev,
 					  0, 0, tmo->cookie, false);
-		if (err)
-			return err;
-		return 0;
+	} else {
+		NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action");
+		err = -EOPNOTSUPP;
 	}
-	NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action");
-	return -EOPNOTSUPP;
+
+	list_del(&entry->list);
+
+	return err;
+}
+
+static int sparx5_tc_matchall_stats(struct net_device *ndev,
+				    struct tc_cls_matchall_offload *tmo,
+				    bool ingress)
+{
+	struct sparx5_port *port = netdev_priv(ndev);
+	struct sparx5 *sparx5 = port->sparx5;
+	struct sparx5_mall_entry *entry;
+
+	entry = sparx5_tc_matchall_entry_find(&sparx5->mall_entries,
+					      tmo->cookie);
+	if (!entry)
+		return -ENOENT;
+
+	if (entry->type == FLOW_ACTION_MIRRED) {
+		sparx5_mirror_stats(entry, &tmo->stats);
+	} else {
+		NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
 int sparx5_tc_matchall(struct net_device *ndev,
@@ -91,6 +196,8 @@ int sparx5_tc_matchall(struct net_device *ndev,
 		return sparx5_tc_matchall_replace(ndev, tmo, ingress);
 	case TC_CLSMATCHALL_DESTROY:
 		return sparx5_tc_matchall_destroy(ndev, tmo, ingress);
+	case TC_CLSMATCHALL_STATS:
+		return sparx5_tc_matchall_stats(ndev, tmo, ingress);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h
index c3569a4c7b69..4735fad05708 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_ag_api.h
@@ -290,7 +290,7 @@ enum vcap_keyfield_set {
  *   Sparx5: TCP flag RST , LAN966x: TCP: TCP flag RST. PTP over UDP: messageType
  *   bit 3
  * VCAP_KF_L4_SEQUENCE_EQ0_IS: W1, sparx5: is2/es2, lan966x: is2
- *   Set if TCP sequence number is 0, LAN966x: Overlayed with PTP over UDP:
+ *   Set if TCP sequence number is 0, LAN966x: Overlaid with PTP over UDP:
  *   messageType bit 0
  * VCAP_KF_L4_SPORT: W16, sparx5: is0/is2/es2, lan966x: is1/is2
  *   TCP/UDP source port
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c
index ef980e4e5bc2..2687765abe52 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c
@@ -327,7 +327,7 @@ static int vcap_find_keystream_typegroup_sw(struct vcap_control *vctrl,
 }
 
 /* Verify that the typegroup information, subword count, keyset and type id
- * are in sync and correct, return the list of matchin keysets
+ * are in sync and correct, return the list of matching keysets
  */
 int
 vcap_find_keystream_keysets(struct vcap_control *vctrl,
@@ -2907,6 +2907,18 @@ int vcap_rule_add_action_u32(struct vcap_rule *rule,
 }
 EXPORT_SYMBOL_GPL(vcap_rule_add_action_u32);
 
+/* Add a 72 bit action field with value to the rule */
+int vcap_rule_add_action_u72(struct vcap_rule *rule,
+			     enum vcap_action_field action,
+			     struct vcap_u72_action *fieldval)
+{
+	struct vcap_client_actionfield_data data;
+
+	memcpy(&data.u72, fieldval, sizeof(data.u72));
+	return vcap_rule_add_action(rule, action, VCAP_FIELD_U72, &data);
+}
+EXPORT_SYMBOL_GPL(vcap_rule_add_action_u72);
+
 static int vcap_read_counter(struct vcap_rule_internal *ri,
 			     struct vcap_counter *ctr)
 {
@@ -2931,7 +2943,7 @@ void vcap_netbytes_copy(u8 *dst, u8 *src, int count)
 }
 EXPORT_SYMBOL_GPL(vcap_netbytes_copy);
 
-/* Convert validation error code into tc extact error message */
+/* Convert validation error code into tc extack error message */
 void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule)
 {
 	switch (vrule->exterr) {
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
index 88641508f885..cdf79e17ca54 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h
@@ -200,6 +200,8 @@ int vcap_rule_add_action_bit(struct vcap_rule *rule,
 			     enum vcap_action_field action, enum vcap_bit val);
 int vcap_rule_add_action_u32(struct vcap_rule *rule,
 			     enum vcap_action_field action, u32 value);
+int vcap_rule_add_action_u72(struct vcap_rule *rule, enum vcap_action_field action,
+			     struct vcap_u72_action *fieldval);
 
 /* Get number of rules in a vcap instance lookup chain id range */
 int vcap_admin_rule_count(struct vcap_admin *admin, int cid);
@@ -236,7 +238,7 @@ const struct vcap_set *vcap_keyfieldset(struct vcap_control *vctrl,
 /* Copy to host byte order */
 void vcap_netbytes_copy(u8 *dst, u8 *src, int count);
 
-/* Convert validation error code into tc extact error message */
+/* Convert validation error code into tc extack error message */
 void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule);
 
 /* Cleanup a VCAP instance */
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h
index df81d9ff502b..844bdf6b5f45 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h
@@ -109,7 +109,7 @@ int vcap_addr_keysets(struct vcap_control *vctrl, struct net_device *ndev,
 		      struct vcap_keyset_list *kslist);
 
 /* Verify that the typegroup information, subword count, keyset and type id
- * are in sync and correct, return the list of matchin keysets
+ * are in sync and correct, return the list of matching keysets
  */
 int vcap_find_keystream_keysets(struct vcap_control *vctrl, enum vcap_type vt,
 				u32 *keystream, u32 *mskstream, bool mask,
diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig
index 01eb7445ead9..286f0d5697a1 100644
--- a/drivers/net/ethernet/microsoft/Kconfig
+++ b/drivers/net/ethernet/microsoft/Kconfig
@@ -17,7 +17,8 @@ if NET_VENDOR_MICROSOFT
 
 config MICROSOFT_MANA
 	tristate "Microsoft Azure Network Adapter (MANA) support"
-	depends on PCI_MSI && X86_64
+	depends on PCI_MSI
+	depends on X86_64 || (ARM64 && !CPU_BIG_ENDIAN && ARM64_4K_PAGES)
 	depends on PCI_HYPERV
 	select AUXILIARY_BUS
 	select PAGE_POOL
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d8af5e7e15b4..d087cf954f75 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -690,12 +690,12 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu)
 		goto out;
 	}
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 	err = mana_attach(ndev);
 	if (err) {
 		netdev_err(ndev, "mana_attach failed: %d\n", err);
-		ndev->mtu = old_mtu;
+		WRITE_ONCE(ndev->mtu, old_mtu);
 	}
 
 out:
@@ -1058,11 +1058,10 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 	struct mana_cfg_rx_steer_req_v2 *req;
 	struct mana_cfg_rx_steer_resp resp = {};
 	struct net_device *ndev = apc->ndev;
-	mana_handle_t *req_indir_tab;
 	u32 req_buf_size;
 	int err;
 
-	req_buf_size = sizeof(*req) + sizeof(mana_handle_t) * num_entries;
+	req_buf_size = struct_size(req, indir_tab, num_entries);
 	req = kzalloc(req_buf_size, GFP_KERNEL);
 	if (!req)
 		return -ENOMEM;
@@ -1074,7 +1073,8 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 
 	req->vport = apc->port_handle;
 	req->num_indir_entries = num_entries;
-	req->indir_tab_offset = sizeof(*req);
+	req->indir_tab_offset = offsetof(struct mana_cfg_rx_steer_req_v2,
+					 indir_tab);
 	req->rx_enable = rx;
 	req->rss_enable = apc->rss_state;
 	req->update_default_rxobj = update_default_rxobj;
@@ -1086,11 +1086,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 	if (update_key)
 		memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE);
 
-	if (update_tab) {
-		req_indir_tab = (mana_handle_t *)(req + 1);
-		memcpy(req_indir_tab, apc->rxobj_table,
-		       req->num_indir_entries * sizeof(mana_handle_t));
-	}
+	if (update_tab)
+		memcpy(req->indir_tab, apc->rxobj_table,
+		       flex_array_size(req, indir_tab, req->num_indir_entries));
 
 	err = mana_send_request(apc->ac, req, req_buf_size, &resp,
 				sizeof(resp));
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 33b438c6aec5..a057ec3dab97 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -609,11 +609,8 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
 			return ret;
 	}
 
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_match_control match;
-
-		flow_rule_match_control(rule, &match);
-	}
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
 		struct flow_match_vlan match;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 7b7e1c5b00f4..b7d9657a7af3 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -3036,11 +3036,11 @@ static int myri10ge_change_mtu(struct net_device *dev, int new_mtu)
 		/* if we change the mtu on an active device, we must
 		 * reset the device so the firmware sees the change */
 		myri10ge_close(dev);
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		myri10ge_open(dev);
-	} else
-		dev->mtu = new_mtu;
-
+	} else {
+		WRITE_ONCE(dev->mtu, new_mtu);
+	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 650a5a166070..ad0c14849115 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -2526,7 +2526,7 @@ static void __set_rx_mode(struct net_device *dev)
 
 static int natsemi_change_mtu(struct net_device *dev, int new_mtu)
 {
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	/* synchronized against open : rtnl_lock() held by caller */
 	if (netif_running(dev)) {
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 55408f16fbbc..f235e76e4ce9 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -6637,7 +6637,7 @@ static int s2io_change_mtu(struct net_device *dev, int new_mtu)
 	struct s2io_nic *sp = netdev_priv(dev);
 	int ret = 0;
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	if (netif_running(dev)) {
 		s2io_stop_all_tx_queue(sp);
 		s2io_card_down(sp);
diff --git a/drivers/net/ethernet/netronome/nfp/devlink_param.c b/drivers/net/ethernet/netronome/nfp/devlink_param.c
index a655f9e69a7b..0e1a3800f371 100644
--- a/drivers/net/ethernet/netronome/nfp/devlink_param.c
+++ b/drivers/net/ethernet/netronome/nfp/devlink_param.c
@@ -132,7 +132,8 @@ exit_close_nsp:
 
 static int
 nfp_devlink_param_u8_set(struct devlink *devlink, u32 id,
-			 struct devlink_param_gset_ctx *ctx)
+			 struct devlink_param_gset_ctx *ctx,
+			 struct netlink_ext_ack *extack)
 {
 	const struct nfp_devlink_param_u8_arg *arg;
 	struct nfp_pf *pf = devlink_priv(devlink);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 2c3f62907958..aca2a7417af3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -396,6 +396,17 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
 	return 0;
 }
 
+#define NFP_FL_CHECK(flag) ({				\
+	IP_TUNNEL_DECLARE_FLAGS(__check) = { };		\
+	__be16 __res;					\
+							\
+	__set_bit(IP_TUNNEL_##flag##_BIT, __check);	\
+	__res = ip_tunnel_flags_to_be16(__check);	\
+							\
+	BUILD_BUG_ON(__builtin_constant_p(__res) &&	\
+		     NFP_FL_TUNNEL_##flag != __res);	\
+})
+
 static int
 nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	       const struct flow_action_entry *act,
@@ -410,6 +421,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
+	__be16 tun_flags;
 
 	if (!IS_ENABLED(CONFIG_IPV6) && ipv6)
 		return -EOPNOTSUPP;
@@ -417,9 +429,10 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	if (ipv6 && !(priv->flower_ext_feats & NFP_FL_FEATS_IPV6_TUN))
 		return -EOPNOTSUPP;
 
-	BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM ||
-		     NFP_FL_TUNNEL_KEY	!= TUNNEL_KEY ||
-		     NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT);
+	NFP_FL_CHECK(CSUM);
+	NFP_FL_CHECK(KEY);
+	NFP_FL_CHECK(GENEVE_OPT);
+
 	if (ip_tun->options_len &&
 	    (tun_type != NFP_FL_TUNNEL_GENEVE ||
 	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))) {
@@ -427,7 +440,9 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 		return -EOPNOTSUPP;
 	}
 
-	if (ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS) {
+	tun_flags = ip_tunnel_flags_to_be16(ip_tun->key.tun_flags);
+	if (!ip_tunnel_flags_is_be16_compat(ip_tun->key.tun_flags) ||
+	    (tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "unsupported offload: loaded firmware does not support tunnel flag offload");
 		return -EOPNOTSUPP;
@@ -442,7 +457,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 		FIELD_PREP(NFP_FL_PRE_TUN_INDEX, pretun_idx);
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
-	if (ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY)
+	if (tun_flags & NFP_FL_TUNNEL_KEY)
 		set_tun->tun_id = ip_tun->key.tun_id;
 
 	if (ip_tun->key.ttl) {
@@ -486,7 +501,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	}
 
 	set_tun->tos = ip_tun->key.tos;
-	set_tun->tun_flags = ip_tun->key.tun_flags;
+	set_tun->tun_flags = tun_flags;
 
 	if (tun_type == NFP_FL_TUNNEL_GENEVE) {
 		set_tun->tun_proto = htons(ETH_P_TEB);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 0aceef9fe582..8e0a890381b6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -527,10 +527,10 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		struct flow_match_control ctl;
 
 		flow_rule_match_control(rule, &ctl);
-		if (ctl.key->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) {
-			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on unknown control flag");
+
+		if (!flow_rule_is_supp_control_flags(NFP_FLOWER_SUPPORTED_CTLFLAGS,
+						     ctl.mask->flags, extack))
 			return -EOPNOTSUPP;
-		}
 	}
 
 	ret_key_ls->key_layer = key_layer;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 635d33c0d6d3..ea75b9a06313 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -160,6 +160,7 @@ static const struct nfp_devlink_versions_simple {
 	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_REV,	"assembly.revision", },
 	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE, "assembly.vendor", },
 	{ "board.model", /* code name */		"assembly.model", },
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_PART_NUMBER, "pn", },
 };
 
 static int
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index f28e769e6fda..182ba0a8b095 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1526,7 +1526,7 @@ static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp)
 	*dp = nn->dp;
 	nn->dp = new_dp;
 
-	nn->dp.netdev->mtu = new_dp.mtu;
+	WRITE_ONCE(nn->dp.netdev->mtu, new_dp.mtu);
 
 	if (!netif_is_rxfh_configured(nn->dp.netdev))
 		nfp_net_rss_init_itbl(nn);
@@ -2289,10 +2289,7 @@ static int nfp_net_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	if (!br_spec)
 		return -EINVAL;
 
-	nla_for_each_nested(attr, br_spec, rem) {
-		if (nla_type(attr) != IFLA_BRIDGE_MODE)
-			continue;
-
+	nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
 		new_ctrl = nn->dp.ctrl;
 		mode = nla_get_u16(attr);
 		if (mode == BRIDGE_MODE_VEPA)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
index a614df095b08..2dd37557185e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
@@ -34,8 +34,11 @@ enum nfp_dumpspec_type {
 
 /* generic type plus length */
 struct nfp_dump_tl {
-	__be32 type;
-	__be32 length;	/* chunk length to follow, aligned to 8 bytes */
+	/* New members must be added within the struct_group() macro below. */
+	struct_group_tagged(nfp_dump_tl_hdr, hdr,
+		__be32 type;
+		__be32 length;	/* chunk length to follow, aligned to 8 bytes */
+	);
 	char data[];
 };
 
@@ -55,19 +58,19 @@ struct nfp_dump_common_cpp {
 
 /* CSR dumpables */
 struct nfp_dumpspec_csr {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	struct nfp_dump_common_cpp cpp;
 	__be32 register_width;	/* in bits */
 };
 
 struct nfp_dumpspec_rtsym {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	char rtsym[];
 };
 
 /* header for register dumpable */
 struct nfp_dump_csr {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	struct nfp_dump_common_cpp cpp;
 	__be32 register_width;	/* in bits */
 	__be32 error;		/* error code encountered while reading */
@@ -75,7 +78,7 @@ struct nfp_dump_csr {
 };
 
 struct nfp_dump_rtsym {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	struct nfp_dump_common_cpp cpp;
 	__be32 error;		/* error code encountered while reading */
 	u8 padded_name_length;	/* pad so data starts at 8 byte boundary */
@@ -84,12 +87,12 @@ struct nfp_dump_rtsym {
 };
 
 struct nfp_dump_prolog {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	__be32 dump_level;
 };
 
 struct nfp_dump_error {
-	struct nfp_dump_tl tl;
+	struct nfp_dump_tl_hdr tl;
 	__be32 error;
 	char padding[4];
 	char spec[];
@@ -449,6 +452,8 @@ static int
 nfp_dump_csr_range(struct nfp_pf *pf, struct nfp_dumpspec_csr *spec_csr,
 		   struct nfp_dump_state *dump)
 {
+	struct nfp_dump_tl *spec_csr_tl =
+			container_of(&spec_csr->tl, struct nfp_dump_tl, hdr);
 	struct nfp_dump_csr *dump_header = dump->p;
 	u32 reg_sz, header_size, total_size;
 	u32 cpp_rd_addr, max_rd_addr;
@@ -458,7 +463,7 @@ nfp_dump_csr_range(struct nfp_pf *pf, struct nfp_dumpspec_csr *spec_csr,
 	int err;
 
 	if (!nfp_csr_spec_valid(spec_csr))
-		return nfp_dump_error_tlv(&spec_csr->tl, -EINVAL, dump);
+		return nfp_dump_error_tlv(spec_csr_tl, -EINVAL, dump);
 
 	reg_sz = be32_to_cpu(spec_csr->register_width) / BITS_PER_BYTE;
 	header_size = ALIGN8(sizeof(*dump_header));
@@ -466,7 +471,7 @@ nfp_dump_csr_range(struct nfp_pf *pf, struct nfp_dumpspec_csr *spec_csr,
 		     ALIGN8(be32_to_cpu(spec_csr->cpp.dump_length));
 	dest = dump->p + header_size;
 
-	err = nfp_add_tlv(be32_to_cpu(spec_csr->tl.type), total_size, dump);
+	err = nfp_add_tlv(be32_to_cpu(spec_csr_tl->type), total_size, dump);
 	if (err)
 		return err;
 
@@ -552,6 +557,8 @@ nfp_dump_indirect_csr_range(struct nfp_pf *pf,
 			    struct nfp_dumpspec_csr *spec_csr,
 			    struct nfp_dump_state *dump)
 {
+	struct nfp_dump_tl *spec_csr_tl =
+			container_of(&spec_csr->tl, struct nfp_dump_tl, hdr);
 	struct nfp_dump_csr *dump_header = dump->p;
 	u32 reg_sz, header_size, total_size;
 	u32 cpp_rd_addr, max_rd_addr;
@@ -560,7 +567,7 @@ nfp_dump_indirect_csr_range(struct nfp_pf *pf,
 	int err;
 
 	if (!nfp_csr_spec_valid(spec_csr))
-		return nfp_dump_error_tlv(&spec_csr->tl, -EINVAL, dump);
+		return nfp_dump_error_tlv(spec_csr_tl, -EINVAL, dump);
 
 	reg_sz = be32_to_cpu(spec_csr->register_width) / BITS_PER_BYTE;
 	header_size = ALIGN8(sizeof(*dump_header));
@@ -569,7 +576,7 @@ nfp_dump_indirect_csr_range(struct nfp_pf *pf,
 	total_size = header_size + ALIGN8(reg_data_length);
 	dest = dump->p + header_size;
 
-	err = nfp_add_tlv(be32_to_cpu(spec_csr->tl.type), total_size, dump);
+	err = nfp_add_tlv(be32_to_cpu(spec_csr_tl->type), total_size, dump);
 	if (err)
 		return err;
 
@@ -597,6 +604,8 @@ static int
 nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec,
 		      struct nfp_dump_state *dump)
 {
+	struct nfp_dump_tl *spec_tl =
+			container_of(&spec->tl, struct nfp_dump_tl, hdr);
 	struct nfp_dump_rtsym *dump_header = dump->p;
 	struct nfp_dumpspec_cpp_isl_id cpp_params;
 	struct nfp_rtsym_table *rtbl = pf->rtbl;
@@ -607,14 +616,14 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec,
 	void *dest;
 	int err;
 
-	tl_len = be32_to_cpu(spec->tl.length);
+	tl_len = be32_to_cpu(spec_tl->length);
 	key_len = strnlen(spec->rtsym, tl_len);
 	if (key_len == tl_len)
-		return nfp_dump_error_tlv(&spec->tl, -EINVAL, dump);
+		return nfp_dump_error_tlv(spec_tl, -EINVAL, dump);
 
 	sym = nfp_rtsym_lookup(rtbl, spec->rtsym);
 	if (!sym)
-		return nfp_dump_error_tlv(&spec->tl, -ENOENT, dump);
+		return nfp_dump_error_tlv(spec_tl, -ENOENT, dump);
 
 	sym_size = nfp_rtsym_size(sym);
 	header_size =
@@ -622,7 +631,7 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec,
 	total_size = header_size + ALIGN8(sym_size);
 	dest = dump->p + header_size;
 
-	err = nfp_add_tlv(be32_to_cpu(spec->tl.type), total_size, dump);
+	err = nfp_add_tlv(be32_to_cpu(spec_tl->type), total_size, dump);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 3af1229a3f08..eee0bfc41074 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -177,7 +177,7 @@ static int nfp_repr_change_mtu(struct net_device *netdev, int new_mtu)
 	if (err)
 		return err;
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index fa1f78b03cb2..2aa4ad9cf96e 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -946,7 +946,7 @@ static int nixge_change_mtu(struct net_device *ndev, int new_mtu)
 	     NIXGE_MAX_JUMBO_FRAME_SIZE)
 		return -EINVAL;
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 31f896c4aa26..720f577929db 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -3098,7 +3098,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
 	int old_mtu;
 
 	old_mtu = dev->mtu;
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	/* return early if the buffer sizes will not change */
 	if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 28b7cec485ef..4ac29cd59f2b 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2184,7 +2184,7 @@ static int pch_gbe_change_mtu(struct net_device *netdev, int new_mtu)
 		}
 	} else {
 		pch_gbe_reset(adapter);
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		adapter->hw.mac.max_frame_size = max_frame;
 	}
 
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index ed7dd0a04235..62ba269da902 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -1639,7 +1639,7 @@ static int pasemi_mac_change_mtu(struct net_device *dev, int new_mtu)
 	reg |= PAS_MAC_CFG_MACCFG_MAXF(new_mtu + ETH_HLEN + 4);
 	write_mac_reg(mac, PAS_MAC_CFG_MACCFG, reg);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	/* MTU + ETH_HLEN + VLAN_HLEN + 2 64B cachelines */
 	mac->bufsz = new_mtu + ETH_HLEN + ETH_FCS_LEN + LOCAL_SKB_ALIGN + 128;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 7f0c6cdc375e..24870da3f484 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1761,13 +1761,13 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu)
 
 	/* if we're not running, nothing more to do */
 	if (!netif_running(netdev)) {
-		netdev->mtu = new_mtu;
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		return 0;
 	}
 
 	mutex_lock(&lif->queue_lock);
 	ionic_stop_queues_reconfig(lif);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	err = ionic_start_queues_reconfig(lif);
 	mutex_unlock(&lif->queue_lock);
 
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
index 6e12cd21ac90..89c8b2349694 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
@@ -960,7 +960,7 @@ int netxen_nic_change_mtu(struct net_device *netdev, int mtu)
 		rc = adapter->set_mtu(adapter, mtu);
 
 	if (!rc)
-		netdev->mtu = mtu;
+		WRITE_ONCE(netdev->mtu, mtu);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 1d719726f72b..b7def3b54937 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -662,8 +662,6 @@ struct qed_hwfn {
 };
 
 struct pci_params {
-	int		pm_cap;
-
 	unsigned long	mem_start;
 	unsigned long	mem_end;
 	unsigned int	irq;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index dad8e617c393..1adc7fbb3f2f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -132,7 +132,8 @@ static int qed_dl_param_get(struct devlink *dl, u32 id,
 }
 
 static int qed_dl_param_set(struct devlink *dl, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct qed_devlink *qed_dl = devlink_priv(dl);
 	struct qed_dev *cdev;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index d39e198fe8db..f915c423fe70 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -323,8 +323,7 @@ static int qed_init_pci(struct qed_dev *cdev, struct pci_dev *pdev)
 		goto err2;
 	}
 
-	cdev->pci_params.pm_cap = pci_find_capability(pdev, PCI_CAP_ID_PM);
-	if (IS_PF(cdev) && !cdev->pci_params.pm_cap)
+	if (IS_PF(cdev) && !pdev->pm_cap)
 		DP_NOTICE(cdev, "Cannot find power management capability\n");
 
 	rc = dma_set_mask_and_coherent(&cdev->pdev->dev, DMA_BIT_MASK(64));
@@ -1206,7 +1205,6 @@ out:
 static int qed_slowpath_wq_start(struct qed_dev *cdev)
 {
 	struct qed_hwfn *hwfn;
-	char name[NAME_SIZE];
 	int i;
 
 	if (IS_VF(cdev))
@@ -1215,11 +1213,11 @@ static int qed_slowpath_wq_start(struct qed_dev *cdev)
 	for_each_hwfn(cdev, i) {
 		hwfn = &cdev->hwfns[i];
 
-		snprintf(name, NAME_SIZE, "slowpath-%02x:%02x.%02x",
-			 cdev->pdev->bus->number,
-			 PCI_SLOT(cdev->pdev->devfn), hwfn->abs_pf_id);
+		hwfn->slowpath_wq = alloc_workqueue("slowpath-%02x:%02x.%02x",
+					 0, 0, cdev->pdev->bus->number,
+					 PCI_SLOT(cdev->pdev->devfn),
+					 hwfn->abs_pf_id);
 
-		hwfn->slowpath_wq = alloc_workqueue(name, 0, 0);
 		if (!hwfn->slowpath_wq) {
 			DP_NOTICE(hwfn, "Cannot create slowpath workqueue\n");
 			return -ENOMEM;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index ae3ebf0cf999..f497f6ca1018 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1026,7 +1026,7 @@ static int qede_get_regs_len(struct net_device *ndev)
 static void qede_update_mtu(struct qede_dev *edev,
 			    struct qede_reload_args *args)
 {
-	edev->ndev->mtu = args->u.mtu;
+	WRITE_ONCE(edev->ndev->mtu, args->u.mtu);
 }
 
 /* Netdevice NDOs */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index cb6b33a228ea..985026dd816f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1520,8 +1520,8 @@ static int qede_flow_spec_validate_unused(struct qede_dev *edev,
 	return 0;
 }
 
-static int qede_set_v4_tuple_to_profile(struct qede_dev *edev,
-					struct qede_arfs_tuple *t)
+static int qede_set_v4_tuple_to_profile(struct qede_arfs_tuple *t,
+					struct netlink_ext_ack *extack)
 {
 	/* We must have Only 4-tuples/l4 port/src ip/dst ip
 	 * as an input.
@@ -1538,7 +1538,7 @@ static int qede_set_v4_tuple_to_profile(struct qede_dev *edev,
 		   t->dst_ipv4 && !t->src_ipv4) {
 		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
 	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid N-tuple");
 		return -EOPNOTSUPP;
 	}
 
@@ -1549,9 +1549,9 @@ static int qede_set_v4_tuple_to_profile(struct qede_dev *edev,
 	return 0;
 }
 
-static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
-					struct qede_arfs_tuple *t,
-					struct in6_addr *zaddr)
+static int qede_set_v6_tuple_to_profile(struct qede_arfs_tuple *t,
+					struct in6_addr *zaddr,
+					struct netlink_ext_ack *extack)
 {
 	/* We must have Only 4-tuples/l4 port/src ip/dst ip
 	 * as an input.
@@ -1573,7 +1573,7 @@ static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
 		   !memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr))) {
 		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
 	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid N-tuple");
 		return -EOPNOTSUPP;
 	}
 
@@ -1671,7 +1671,7 @@ static int qede_parse_actions(struct qede_dev *edev,
 	int i;
 
 	if (!flow_action_has_entries(flow_action)) {
-		DP_NOTICE(edev, "No actions received\n");
+		NL_SET_ERR_MSG_MOD(extack, "No actions received");
 		return -EINVAL;
 	}
 
@@ -1687,7 +1687,8 @@ static int qede_parse_actions(struct qede_dev *edev,
 				break;
 
 			if (act->queue.index >= QEDE_RSS_COUNT(edev)) {
-				DP_INFO(edev, "Queue out-of-bounds\n");
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Queue out-of-bounds");
 				return -EINVAL;
 			}
 			break;
@@ -1700,8 +1701,8 @@ static int qede_parse_actions(struct qede_dev *edev,
 }
 
 static int
-qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule,
-		      struct qede_arfs_tuple *t)
+qede_flow_parse_ports(struct flow_rule *rule, struct qede_arfs_tuple *t,
+		      struct netlink_ext_ack *extack)
 {
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
 		struct flow_match_ports match;
@@ -1709,7 +1710,8 @@ qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule,
 		flow_rule_match_ports(rule, &match);
 		if ((match.key->src && match.mask->src != htons(U16_MAX)) ||
 		    (match.key->dst && match.mask->dst != htons(U16_MAX))) {
-			DP_NOTICE(edev, "Do not support ports masks\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Do not support ports masks");
 			return -EINVAL;
 		}
 
@@ -1721,10 +1723,12 @@ qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule,
 }
 
 static int
-qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule,
-			  struct qede_arfs_tuple *t)
+qede_flow_parse_v6_common(struct flow_rule *rule,
+			  struct qede_arfs_tuple *t,
+			  struct netlink_ext_ack *extack)
 {
 	struct in6_addr zero_addr, addr;
+	int err;
 
 	memset(&zero_addr, 0, sizeof(addr));
 	memset(&addr, 0xff, sizeof(addr));
@@ -1737,8 +1741,8 @@ qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule,
 		     memcmp(&match.mask->src, &addr, sizeof(addr))) ||
 		    (memcmp(&match.key->dst, &zero_addr, sizeof(addr)) &&
 		     memcmp(&match.mask->dst, &addr, sizeof(addr)))) {
-			DP_NOTICE(edev,
-				  "Do not support IPv6 address prefix/mask\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Do not support IPv6 address prefix/mask");
 			return -EINVAL;
 		}
 
@@ -1746,23 +1750,28 @@ qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule,
 		memcpy(&t->dst_ipv6, &match.key->dst, sizeof(addr));
 	}
 
-	if (qede_flow_parse_ports(edev, rule, t))
-		return -EINVAL;
+	err = qede_flow_parse_ports(rule, t, extack);
+	if (err)
+		return err;
 
-	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
+	return qede_set_v6_tuple_to_profile(t, &zero_addr, extack);
 }
 
 static int
-qede_flow_parse_v4_common(struct qede_dev *edev, struct flow_rule *rule,
-			struct qede_arfs_tuple *t)
+qede_flow_parse_v4_common(struct flow_rule *rule,
+			  struct qede_arfs_tuple *t,
+			  struct netlink_ext_ack *extack)
 {
+	int err;
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
 		struct flow_match_ipv4_addrs match;
 
 		flow_rule_match_ipv4_addrs(rule, &match);
 		if ((match.key->src && match.mask->src != htonl(U32_MAX)) ||
 		    (match.key->dst && match.mask->dst != htonl(U32_MAX))) {
-			DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Do not support ipv4 prefix/masks");
 			return -EINVAL;
 		}
 
@@ -1770,55 +1779,57 @@ qede_flow_parse_v4_common(struct qede_dev *edev, struct flow_rule *rule,
 		t->dst_ipv4 = match.key->dst;
 	}
 
-	if (qede_flow_parse_ports(edev, rule, t))
-		return -EINVAL;
+	err = qede_flow_parse_ports(rule, t, extack);
+	if (err)
+		return err;
 
-	return qede_set_v4_tuple_to_profile(edev, t);
+	return qede_set_v4_tuple_to_profile(t, extack);
 }
 
 static int
-qede_flow_parse_tcp_v6(struct qede_dev *edev, struct flow_rule *rule,
-		     struct qede_arfs_tuple *tuple)
+qede_flow_parse_tcp_v6(struct flow_rule *rule, struct qede_arfs_tuple *tuple,
+		       struct netlink_ext_ack *extack)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_flow_parse_v6_common(edev, rule, tuple);
+	return qede_flow_parse_v6_common(rule, tuple, extack);
 }
 
 static int
-qede_flow_parse_tcp_v4(struct qede_dev *edev, struct flow_rule *rule,
-		     struct qede_arfs_tuple *tuple)
+qede_flow_parse_tcp_v4(struct flow_rule *rule, struct qede_arfs_tuple *tuple,
+		       struct netlink_ext_ack *extack)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_flow_parse_v4_common(edev, rule, tuple);
+	return qede_flow_parse_v4_common(rule, tuple, extack);
 }
 
 static int
-qede_flow_parse_udp_v6(struct qede_dev *edev, struct flow_rule *rule,
-		     struct qede_arfs_tuple *tuple)
+qede_flow_parse_udp_v6(struct flow_rule *rule, struct qede_arfs_tuple *tuple,
+		       struct netlink_ext_ack *extack)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_flow_parse_v6_common(edev, rule, tuple);
+	return qede_flow_parse_v6_common(rule, tuple, extack);
 }
 
 static int
-qede_flow_parse_udp_v4(struct qede_dev *edev, struct flow_rule *rule,
-		     struct qede_arfs_tuple *tuple)
+qede_flow_parse_udp_v4(struct flow_rule *rule, struct qede_arfs_tuple *tuple,
+		       struct netlink_ext_ack *extack)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_flow_parse_v4_common(edev, rule, tuple);
+	return qede_flow_parse_v4_common(rule, tuple, extack);
 }
 
 static int
-qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
-		     struct flow_rule *rule, struct qede_arfs_tuple *tuple)
+qede_parse_flow_attr(__be16 proto, struct flow_rule *rule,
+		     struct qede_arfs_tuple *tuple,
+		     struct netlink_ext_ack *extack)
 {
 	struct flow_dissector *dissector = rule->match.dissector;
 	int rc = -EINVAL;
@@ -1832,14 +1843,18 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
 	      BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT_ULL(FLOW_DISSECTOR_KEY_PORTS))) {
-		DP_NOTICE(edev, "Unsupported key set:0x%llx\n",
-			  dissector->used_keys);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported key used: 0x%llx",
+				       dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (proto != htons(ETH_P_IP) &&
 	    proto != htons(ETH_P_IPV6)) {
-		DP_NOTICE(edev, "Unsupported proto=0x%x\n", proto);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported proto=0x%x",
+				       proto);
 		return -EPROTONOSUPPORT;
 	}
 
@@ -1851,15 +1866,15 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
 	}
 
 	if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP))
-		rc = qede_flow_parse_tcp_v4(edev, rule, tuple);
+		rc = qede_flow_parse_tcp_v4(rule, tuple, extack);
 	else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6))
-		rc = qede_flow_parse_tcp_v6(edev, rule, tuple);
+		rc = qede_flow_parse_tcp_v6(rule, tuple, extack);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP))
-		rc = qede_flow_parse_udp_v4(edev, rule, tuple);
+		rc = qede_flow_parse_udp_v4(rule, tuple, extack);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6))
-		rc = qede_flow_parse_udp_v6(edev, rule, tuple);
+		rc = qede_flow_parse_udp_v6(rule, tuple, extack);
 	else
-		DP_NOTICE(edev, "Invalid protocol request\n");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid protocol request");
 
 	return rc;
 }
@@ -1867,6 +1882,7 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
 int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 			    struct flow_cls_offload *f)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
 	struct qede_arfs_fltr_node *n;
 	struct qede_arfs_tuple t;
 	int min_hlen, rc;
@@ -1879,7 +1895,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse flower attribute and prepare filter */
-	rc = qede_parse_flow_attr(edev, proto, f->rule, &t);
+	rc = qede_parse_flow_attr(proto, f->rule, &t, extack);
 	if (rc)
 		goto unlock;
 
@@ -1894,7 +1910,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse tc actions and get the vf_id */
-	rc = qede_parse_actions(edev, &f->rule->action, f->common.extack);
+	rc = qede_parse_actions(edev, &f->rule->action, extack);
 	if (rc)
 		goto unlock;
 
@@ -1941,8 +1957,11 @@ unlock:
 static int qede_flow_spec_validate(struct qede_dev *edev,
 				   struct flow_action *flow_action,
 				   struct qede_arfs_tuple *t,
-				   __u32 location)
+				   __u32 location,
+				   struct netlink_ext_ack *extack)
 {
+	int err;
+
 	if (location >= QEDE_RFS_MAX_FLTR) {
 		DP_INFO(edev, "Location out-of-bounds\n");
 		return -EINVAL;
@@ -1963,8 +1982,9 @@ static int qede_flow_spec_validate(struct qede_dev *edev,
 		return -EINVAL;
 	}
 
-	if (qede_parse_actions(edev, flow_action, NULL))
-		return -EINVAL;
+	err = qede_parse_actions(edev, flow_action, extack);
+	if (err)
+		return err;
 
 	return 0;
 }
@@ -1975,11 +1995,13 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev,
 {
 	struct ethtool_rx_flow_spec_input input = {};
 	struct ethtool_rx_flow_rule *flow;
+	struct netlink_ext_ack extack;
 	__be16 proto;
-	int err = 0;
+	int err;
 
-	if (qede_flow_spec_validate_unused(edev, fs))
-		return -EOPNOTSUPP;
+	err = qede_flow_spec_validate_unused(edev, fs);
+	if (err)
+		return err;
 
 	switch ((fs->flow_type & ~FLOW_EXT)) {
 	case TCP_V4_FLOW:
@@ -2001,14 +2023,16 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev,
 	if (IS_ERR(flow))
 		return PTR_ERR(flow);
 
-	err = qede_parse_flow_attr(edev, proto, flow->rule, t);
+	err = qede_parse_flow_attr(proto, flow->rule, t, &extack);
 	if (err)
 		goto err_out;
 
 	/* Make sure location is valid and filter isn't already set */
 	err = qede_flow_spec_validate(edev, &flow->rule->action, t,
-				      fs->location);
+				      fs->location, &extack);
 err_out:
+	if (extack._msg)
+		DP_NOTICE(edev, "%s\n", extack._msg);
 	ethtool_rx_flow_rule_destroy(flow);
 	return err;
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 4b8bc46f55c2..ae4ee0326ee1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -1015,7 +1015,7 @@ int qlcnic_change_mtu(struct net_device *netdev, int mtu)
 	rc = qlcnic_fw_cmd_set_mtu(adapter, mtu);
 
 	if (!rc)
-		netdev->mtu = mtu;
+		WRITE_ONCE(netdev->mtu, mtu);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 4c06f55878de..99d4647bf245 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -216,7 +216,7 @@ static int emac_change_mtu(struct net_device *netdev, int new_mtu)
 	netif_dbg(adpt, hw, adpt->netdev,
 		  "changing MTU from %d to %d\n", netdev->mtu,
 		  new_mtu);
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev))
 		return emac_reinit_locked(adpt);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 9d2a9562c96f..f1e40aade127 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -90,7 +90,7 @@ static int rmnet_vnd_change_mtu(struct net_device *rmnet_dev, int new_mtu)
 	    new_mtu > (priv->real_dev->mtu - headroom))
 		return -EINVAL;
 
-	rmnet_dev->mtu = new_mtu;
+	WRITE_ONCE(rmnet_dev->mtu, new_mtu);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index f5786d78ed23..5652da8a178c 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -1277,14 +1277,14 @@ static int cp_change_mtu(struct net_device *dev, int new_mtu)
 
 	/* if network interface not up, no need for complexity */
 	if (!netif_running(dev)) {
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		cp_set_rxbufsize(cp);	/* set new rx buf size */
 		return 0;
 	}
 
 	/* network IS up, close it, reset MTU, and come up again. */
 	cp_close(dev);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	cp_set_rxbufsize(cp);
 	return cp_open(dev);
 }
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0fc5fe564ae5..5abbea91bc07 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2229,6 +2229,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		 * the wild. Let's disable detection.
 		 * { 0x7cf, 0x540,	RTL_GIGA_MAC_VER_45 },
 		 */
+		/* Realtek calls it RTL8168M, but it's handled like RTL8168H */
+		{ 0x7cf, 0x6c0,	RTL_GIGA_MAC_VER_46 },
 
 		/* 8168G family. */
 		{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44 },
@@ -3922,7 +3924,7 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	netdev_update_features(dev);
 	rtl_jumbo_config(tp);
 	rtl_set_eee_txidle_timer(tp);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 9b1f639f64a1..4d100283c30f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2423,7 +2423,7 @@ static int ravb_change_mtu(struct net_device *ndev, int new_mtu)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 	if (netif_running(ndev)) {
 		synchronize_irq(priv->emac_irq);
@@ -2564,6 +2564,7 @@ static int ravb_mdio_init(struct ravb_private *priv)
 {
 	struct platform_device *pdev = priv->pdev;
 	struct device *dev = &pdev->dev;
+	struct device_node *mdio_node;
 	struct phy_device *phydev;
 	struct device_node *pn;
 	int error;
@@ -2583,7 +2584,13 @@ static int ravb_mdio_init(struct ravb_private *priv)
 		 pdev->name, pdev->id);
 
 	/* Register MDIO bus */
-	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+	mdio_node = of_get_child_by_name(dev->of_node, "mdio");
+	if (!mdio_node) {
+		/* backwards compatibility for DT lacking mdio subnode */
+		mdio_node = of_node_get(dev->of_node);
+	}
+	error = of_mdiobus_register(priv->mii_bus, mdio_node);
+	of_node_put(mdio_node);
 	if (error)
 		goto out_free_bus;
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 0786eb0da391..7a25903e35c3 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2624,7 +2624,7 @@ static int sh_eth_change_mtu(struct net_device *ndev, int new_mtu)
 	if (netif_running(ndev))
 		return -EBUSY;
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 	netdev_update_features(ndev);
 
 	return 0;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 755db89db909..e097ce3e69ea 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1967,7 +1967,7 @@ static int rocker_port_change_mtu(struct net_device *dev, int new_mtu)
 		rocker_port_stop(dev);
 
 	netdev_info(dev, "MTU change from %d to %d\n", dev->mtu, new_mtu);
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	err = rocker_cmd_set_port_settings_mtu(rocker_port, new_mtu);
 	if (err)
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index ecbe3994f2b1..12c8396b6942 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -1804,7 +1804,7 @@ static int sxgbe_set_features(struct net_device *dev,
  */
 static int sxgbe_change_mtu(struct net_device *dev, int new_mtu)
 {
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (!netif_running(dev))
 		return 0;
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index 551f890db90a..4ebd5ae23eca 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -302,7 +302,7 @@ int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 	efx_stop_all(efx);
 
 	mutex_lock(&efx->mac_lock);
-	net_dev->mtu = new_mtu;
+	WRITE_ONCE(net_dev->mtu, new_mtu);
 	efx_mac_reconfigure(efx, true);
 	mutex_unlock(&efx->mac_lock);
 
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 1cb32aedd89c..8925745f1c17 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -2125,7 +2125,7 @@ static int ef4_change_mtu(struct net_device *net_dev, int new_mtu)
 	ef4_stop_all(efx);
 
 	mutex_lock(&efx->mac_lock);
-	net_dev->mtu = new_mtu;
+	WRITE_ONCE(net_dev->mtu, new_mtu);
 	ef4_mac_reconfigure(efx);
 	mutex_unlock(&efx->mac_lock);
 
diff --git a/drivers/net/ethernet/sfc/siena/efx_common.c b/drivers/net/ethernet/sfc/siena/efx_common.c
index 88e5bc347a44..cf195162e270 100644
--- a/drivers/net/ethernet/sfc/siena/efx_common.c
+++ b/drivers/net/ethernet/sfc/siena/efx_common.c
@@ -306,7 +306,7 @@ int efx_siena_change_mtu(struct net_device *net_dev, int new_mtu)
 	efx_siena_stop_all(efx);
 
 	mutex_lock(&efx->mac_lock);
-	net_dev->mtu = new_mtu;
+	WRITE_ONCE(net_dev->mtu, new_mtu);
 	efx_siena_mac_reconfigure(efx, true);
 	mutex_unlock(&efx->mac_lock);
 
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 82e8891a619a..9d140203e273 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -273,11 +273,10 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx,
 			match->value.ip_firstfrag = fm.key->flags & FLOW_DIS_FIRST_FRAG;
 			match->mask.ip_firstfrag = true;
 		}
-		if (fm.mask->flags & ~(FLOW_DIS_IS_FRAGMENT | FLOW_DIS_FIRST_FRAG)) {
-			NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on control.flags %#x",
-					       fm.mask->flags);
+		if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT |
+						     FLOW_DIS_FIRST_FRAG,
+						     fm.mask->flags, extack))
 			return -EOPNOTSUPP;
-		}
 	}
 	if (dissector->used_keys &
 	    ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) |
diff --git a/drivers/net/ethernet/sis/Kconfig b/drivers/net/ethernet/sis/Kconfig
index 775d76d9890e..7e498bdbca73 100644
--- a/drivers/net/ethernet/sis/Kconfig
+++ b/drivers/net/ethernet/sis/Kconfig
@@ -19,7 +19,7 @@ if NET_VENDOR_SIS
 
 config SIS900
 	tristate "SiS 900/7016 PCI Fast Ethernet Adapter support"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	select CRC32
 	select MII
 	help
@@ -35,7 +35,7 @@ config SIS900
 
 config SIS190
 	tristate "SiS190/SiS191 gigabit ethernet support"
-	depends on PCI
+	depends on PCI && HAS_IOPORT
 	select CRC32
 	select MII
 	help
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index cb7fec226cab..85b850372efe 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -2273,7 +2273,7 @@ static int sis900_set_config(struct net_device *dev, struct ifmap *map)
 		 * (which seems to be different from the ifport(pcmcia) definition) */
 		switch(map->port){
 		case IF_PORT_UNKNOWN: /* use auto here */
-			dev->if_port = map->port;
+			WRITE_ONCE(dev->if_port, map->port);
 			/* we are going to change the media type, so the Link
 			 * will be temporary down and we need to reflect that
 			 * here. When the Link comes up again, it will be
@@ -2294,7 +2294,7 @@ static int sis900_set_config(struct net_device *dev, struct ifmap *map)
 			break;
 
 		case IF_PORT_10BASET: /* 10BaseT */
-			dev->if_port = map->port;
+			WRITE_ONCE(dev->if_port, map->port);
 
 			/* we are going to change the media type, so the Link
 			 * will be temporary down and we need to reflect that
@@ -2315,7 +2315,7 @@ static int sis900_set_config(struct net_device *dev, struct ifmap *map)
 
 		case IF_PORT_100BASET: /* 100BaseT */
 		case IF_PORT_100BASETX: /* 100BaseTx */
-			dev->if_port = map->port;
+			WRITE_ONCE(dev->if_port, map->port);
 
 			/* we are going to change the media type, so the Link
 			 * will be temporary down and we need to reflect that
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 5f22a8a4d27b..13ce9086a9ca 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -54,7 +54,7 @@ config SMC91X
 
 config PCMCIA_SMC91C92
 	tristate "SMC 91Cxx PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	select CRC32
 	select MII
 	help
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index 29bb19f42de9..86e3ec25df07 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -1595,7 +1595,7 @@ static int s9k_config(struct net_device *dev, struct ifmap *map)
 	    return -EOPNOTSUPP;
 	else if (map->port > 2)
 	    return -EINVAL;
-	dev->if_port = map->port;
+	WRITE_ONCE(dev->if_port, map->port);
 	netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
 	smc_reset(dev);
     }
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 46eee747c699..45ef5ac0788a 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -156,8 +156,8 @@ static inline void mcf_outsw(void *a, unsigned char *p, int l)
 		writew(*wp++, a);
 }
 
-#define SMC_inw(a, r)		_swapw(readw((a) + (r)))
-#define SMC_outw(lp, v, a, r)	writew(_swapw(v), (a) + (r))
+#define SMC_inw(a, r)		ioread16be((a) + (r))
+#define SMC_outw(lp, v, a, r)	iowrite16be(v, (a) + (r))
 #define SMC_insw(a, r, p, l)	mcf_insw(a + r, p, l)
 #define SMC_outsw(a, r, p, l)	mcf_outsw(a + r, p, l)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 4ec61f1ee71a..05cc07b8f48c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -142,6 +142,18 @@ config DWMAC_ROCKCHIP
 	  This selects the Rockchip RK3288 SoC glue layer support for
 	  the stmmac device driver.
 
+config DWMAC_RZN1
+	tristate "Renesas RZ/N1 dwmac support"
+	default ARCH_RZN1
+	depends on OF && (ARCH_RZN1 || COMPILE_TEST)
+	select PCS_RZN1_MIIC
+	help
+	  Support for Ethernet controller on Renesas RZ/N1 SoC family.
+
+	  This selects the Renesas RZ/N1 SoC glue layer support for
+	  the stmmac device driver. This support can make use of a custom MII
+	  converter PCS device.
+
 config DWMAC_SOCFPGA
 	tristate "SOCFPGA dwmac support"
 	default ARCH_INTEL_SOCFPGA
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 26cad4344701..c2f0e91f6bf8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
+obj-$(CONFIG_DWMAC_RZN1)	+= dwmac-rzn1.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
 obj-$(CONFIG_DWMAC_STARFIVE)	+= dwmac-starfive.o
 obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 3b7d4ac1e7be..9cd62b2110a1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -594,7 +594,7 @@ struct mac_device_info {
 	const struct stmmac_mmc_ops *mmc;
 	const struct stmmac_est_ops *est;
 	struct dw_xpcs *xpcs;
-	struct phylink_pcs *lynx_pcs; /* Lynx external PCS */
+	struct phylink_pcs *phylink_pcs;
 	struct mii_regs mii;	/* MII register Addresses */
 	struct mac_link link;
 	void __iomem *pcsr;     /* vpointer to device CSRs */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 281687d7083b..4ba15873d5b1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -171,6 +171,9 @@ static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed)
 
 	switch (gmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		div = get_clk_div_rgmii(gmac, speed);
 		clk_bits = NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
 			   NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
@@ -410,6 +413,9 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	val |= NSS_COMMON_GMAC_CTL_CSYS_REQ;
 	switch (gmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val |= NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL;
 		break;
 	case PHY_INTERFACE_MODE_SGMII:
@@ -425,6 +431,9 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	val &= ~(1 << NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id));
 	switch (gmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) <<
 			NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
 		break;
@@ -442,6 +451,9 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id);
 	switch (gmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val |= NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
 			NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
 		break;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 382e8de1255d..7ae04d8d291c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -12,10 +12,8 @@
 #include <linux/clk.h>
 #include <linux/phy.h>
 #include <linux/of_net.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c
new file mode 100644
index 000000000000..848cf3c01f4a
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rzn1.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2024 Schneider-Electric
+ *
+ * Clément Léger <clement.leger@bootlin.com>
+ */
+
+#include <linux/of.h>
+#include <linux/pcs-rzn1-miic.h>
+#include <linux/phylink.h>
+#include <linux/platform_device.h>
+
+#include "stmmac_platform.h"
+#include "stmmac.h"
+
+static int rzn1_dwmac_pcs_init(struct stmmac_priv *priv)
+{
+	struct device_node *np = priv->device->of_node;
+	struct device_node *pcs_node;
+	struct phylink_pcs *pcs;
+
+	pcs_node = of_parse_phandle(np, "pcs-handle", 0);
+
+	if (pcs_node) {
+		pcs = miic_create(priv->device, pcs_node);
+		of_node_put(pcs_node);
+		if (IS_ERR(pcs))
+			return PTR_ERR(pcs);
+
+		priv->hw->phylink_pcs = pcs;
+	}
+
+	return 0;
+}
+
+static void rzn1_dwmac_pcs_exit(struct stmmac_priv *priv)
+{
+	if (priv->hw->phylink_pcs)
+		miic_destroy(priv->hw->phylink_pcs);
+}
+
+static int rzn1_dwmac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
+
+	plat_dat->bsp_priv = plat_dat;
+	plat_dat->pcs_init = rzn1_dwmac_pcs_init;
+	plat_dat->pcs_exit = rzn1_dwmac_pcs_exit;
+
+	ret = stmmac_dvr_probe(dev, plat_dat, &stmmac_res);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct of_device_id rzn1_dwmac_match[] = {
+	{ .compatible = "renesas,rzn1-gmac" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rzn1_dwmac_match);
+
+static struct platform_driver rzn1_dwmac_driver = {
+	.probe  = rzn1_dwmac_probe,
+	.remove_new = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "rzn1-dwmac",
+		.of_match_table = rzn1_dwmac_match,
+	},
+};
+module_platform_driver(rzn1_dwmac_driver);
+
+MODULE_AUTHOR("Clément Léger <clement.leger@bootlin.com>");
+MODULE_DESCRIPTION("Renesas RZN1 DWMAC specific glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 68f85e4605cb..b3d45f9dfb55 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -379,6 +379,56 @@ static int socfpga_gen10_set_phy_mode(struct socfpga_dwmac *dwmac)
 	return 0;
 }
 
+static int socfpga_dwmac_pcs_init(struct stmmac_priv *priv)
+{
+	struct socfpga_dwmac *dwmac = priv->plat->bsp_priv;
+	struct regmap_config pcs_regmap_cfg = {
+		.reg_bits = 16,
+		.val_bits = 16,
+		.reg_shift = REGMAP_UPSHIFT(1),
+	};
+	struct mdio_regmap_config mrc;
+	struct regmap *pcs_regmap;
+	struct phylink_pcs *pcs;
+	struct mii_bus *pcs_bus;
+
+	if (!dwmac->tse_pcs_base)
+		return 0;
+
+	pcs_regmap = devm_regmap_init_mmio(priv->device, dwmac->tse_pcs_base,
+					   &pcs_regmap_cfg);
+	if (IS_ERR(pcs_regmap))
+		return PTR_ERR(pcs_regmap);
+
+	memset(&mrc, 0, sizeof(mrc));
+	mrc.regmap = pcs_regmap;
+	mrc.parent = priv->device;
+	mrc.valid_addr = 0x0;
+	mrc.autoscan = false;
+
+	/* Can't use ndev->name here because it will not have been initialised,
+	 * and in any case, the user can rename network interfaces at runtime.
+	 */
+	snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii",
+		 dev_name(priv->device));
+	pcs_bus = devm_mdio_regmap_register(priv->device, &mrc);
+	if (IS_ERR(pcs_bus))
+		return PTR_ERR(pcs_bus);
+
+	pcs = lynx_pcs_create_mdiodev(pcs_bus, 0);
+	if (IS_ERR(pcs))
+		return PTR_ERR(pcs);
+
+	priv->hw->phylink_pcs = pcs;
+	return 0;
+}
+
+static void socfpga_dwmac_pcs_exit(struct stmmac_priv *priv)
+{
+	if (priv->hw->phylink_pcs)
+		lynx_pcs_destroy(priv->hw->phylink_pcs);
+}
+
 static int socfpga_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -426,6 +476,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	dwmac->ops = ops;
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
+	plat_dat->pcs_init = socfpga_dwmac_pcs_init;
+	plat_dat->pcs_exit = socfpga_dwmac_pcs_exit;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
@@ -444,48 +496,6 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_dvr_remove;
 
-	/* Create a regmap for the PCS so that it can be used by the PCS driver,
-	 * if we have such a PCS
-	 */
-	if (dwmac->tse_pcs_base) {
-		struct regmap_config pcs_regmap_cfg;
-		struct mdio_regmap_config mrc;
-		struct regmap *pcs_regmap;
-		struct mii_bus *pcs_bus;
-
-		memset(&pcs_regmap_cfg, 0, sizeof(pcs_regmap_cfg));
-		memset(&mrc, 0, sizeof(mrc));
-
-		pcs_regmap_cfg.reg_bits = 16;
-		pcs_regmap_cfg.val_bits = 16;
-		pcs_regmap_cfg.reg_shift = REGMAP_UPSHIFT(1);
-
-		pcs_regmap = devm_regmap_init_mmio(&pdev->dev, dwmac->tse_pcs_base,
-						   &pcs_regmap_cfg);
-		if (IS_ERR(pcs_regmap)) {
-			ret = PTR_ERR(pcs_regmap);
-			goto err_dvr_remove;
-		}
-
-		mrc.regmap = pcs_regmap;
-		mrc.parent = &pdev->dev;
-		mrc.valid_addr = 0x0;
-		mrc.autoscan = false;
-
-		snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", ndev->name);
-		pcs_bus = devm_mdio_regmap_register(&pdev->dev, &mrc);
-		if (IS_ERR(pcs_bus)) {
-			ret = PTR_ERR(pcs_bus);
-			goto err_dvr_remove;
-		}
-
-		stpriv->hw->lynx_pcs = lynx_pcs_create_mdiodev(pcs_bus, 0);
-		if (IS_ERR(stpriv->hw->lynx_pcs)) {
-			ret = PTR_ERR(stpriv->hw->lynx_pcs);
-			goto err_dvr_remove;
-		}
-	}
-
 	return 0;
 
 err_dvr_remove:
@@ -494,17 +504,6 @@ err_dvr_remove:
 	return ret;
 }
 
-static void socfpga_dwmac_remove(struct platform_device *pdev)
-{
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-	struct phylink_pcs *pcs = priv->hw->lynx_pcs;
-
-	stmmac_pltfr_remove(pdev);
-
-	lynx_pcs_destroy(pcs);
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int socfpga_dwmac_resume(struct device *dev)
 {
@@ -576,7 +575,7 @@ MODULE_DEVICE_TABLE(of, socfpga_dwmac_match);
 
 static struct platform_driver socfpga_dwmac_driver = {
 	.probe  = socfpga_dwmac_probe,
-	.remove_new = socfpga_dwmac_remove,
+	.remove_new = stmmac_pltfr_remove,
 	.driver = {
 		.name           = "socfpga-dwmac",
 		.pm		= &socfpga_dwmac_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index a38226d7cc6a..b25774d69195 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -68,7 +68,7 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 		init_waitqueue_head(&priv->tstamp_busy_wait);
 }
 
-static void dwmac4_phylink_get_caps(struct stmmac_priv *priv)
+static void dwmac4_update_caps(struct stmmac_priv *priv)
 {
 	if (priv->plat->tx_queues_to_use > 1)
 		priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD);
@@ -1190,7 +1190,7 @@ static void dwmac4_set_hw_vlan_mode(struct mac_device_info *hw)
 
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
-	.phylink_get_caps = dwmac4_phylink_get_caps,
+	.update_caps = dwmac4_update_caps,
 	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
@@ -1235,7 +1235,7 @@ const struct stmmac_ops dwmac4_ops = {
 
 const struct stmmac_ops dwmac410_ops = {
 	.core_init = dwmac4_core_init,
-	.phylink_get_caps = dwmac4_phylink_get_caps,
+	.update_caps = dwmac4_update_caps,
 	.set_mac = stmmac_dwmac4_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
@@ -1284,7 +1284,7 @@ const struct stmmac_ops dwmac410_ops = {
 
 const struct stmmac_ops dwmac510_ops = {
 	.core_init = dwmac4_core_init,
-	.phylink_get_caps = dwmac4_phylink_get_caps,
+	.update_caps = dwmac4_update_caps,
 	.set_mac = stmmac_dwmac4_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 7be04b54738b..90384db228b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -308,8 +308,8 @@ struct stmmac_est;
 struct stmmac_ops {
 	/* MAC core initialization */
 	void (*core_init)(struct mac_device_info *hw, struct net_device *dev);
-	/* Get phylink capabilities */
-	void (*phylink_get_caps)(struct stmmac_priv *priv);
+	/* Update MAC capabilities */
+	void (*update_caps)(struct stmmac_priv *priv);
 	/* Enable the MAC RX/TX */
 	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
@@ -430,8 +430,8 @@ struct stmmac_ops {
 
 #define stmmac_core_init(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, core_init, __args)
-#define stmmac_mac_phylink_get_caps(__priv) \
-	stmmac_do_void_callback(__priv, mac, phylink_get_caps, __priv)
+#define stmmac_mac_update_caps(__priv) \
+	stmmac_do_void_callback(__priv, mac, update_caps, __priv)
 #define stmmac_mac_set(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_mac, __args)
 #define stmmac_rx_ipc(__priv, __args...) \
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index dddcaa9220cc..b23b920eedb1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -221,6 +221,20 @@ struct stmmac_dma_conf {
 	unsigned int dma_tx_size;
 };
 
+#define EST_GCL         1024
+struct stmmac_est {
+	int enable;
+	u32 btr_reserve[2];
+	u32 btr_offset[2];
+	u32 btr[2];
+	u32 ctr[2];
+	u32 ter;
+	u32 gcl_unaligned[EST_GCL];
+	u32 gcl[EST_GCL];
+	u32 gcl_size;
+	u32 max_sdu[MTL_MAX_TX_QUEUES];
+};
+
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
@@ -261,6 +275,9 @@ struct stmmac_priv {
 	struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp;
 	struct stmmac_safety_stats sstats;
 	struct plat_stmmacenet_data *plat;
+	/* Protect est parameters */
+	struct mutex est_lock;
+	struct stmmac_est *est;
 	struct dma_features dma_cap;
 	struct stmmac_counters mmc;
 	int hw_cap_support;
@@ -360,7 +377,8 @@ enum stmmac_state {
 int stmmac_mdio_unregister(struct net_device *ndev);
 int stmmac_mdio_register(struct net_device *ndev);
 int stmmac_mdio_reset(struct mii_bus *mii);
-int stmmac_xpcs_setup(struct mii_bus *mii);
+int stmmac_pcs_setup(struct net_device *ndev);
+void stmmac_pcs_clean(struct net_device *ndev);
 void stmmac_set_ethtool_ops(struct net_device *netdev);
 
 int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7c6fb14b5555..2e9a2da605f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -936,6 +936,22 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
 			priv->pause, tx_cnt);
 }
 
+static unsigned long stmmac_mac_get_caps(struct phylink_config *config,
+					 phy_interface_t interface)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+
+	/* Refresh the MAC-specific capabilities */
+	stmmac_mac_update_caps(priv);
+
+	config->mac_capabilities = priv->hw->link.caps;
+
+	if (priv->plat->max_speed)
+		phylink_limit_mac_speed(config, priv->plat->max_speed);
+
+	return config->mac_capabilities;
+}
+
 static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config,
 						 phy_interface_t interface)
 {
@@ -944,10 +960,7 @@ static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config,
 	if (priv->hw->xpcs)
 		return &priv->hw->xpcs->pcs;
 
-	if (priv->hw->lynx_pcs)
-		return priv->hw->lynx_pcs;
-
-	return NULL;
+	return priv->hw->phylink_pcs;
 }
 
 static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
@@ -1105,6 +1118,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 }
 
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
+	.mac_get_caps = stmmac_mac_get_caps,
 	.mac_select_pcs = stmmac_mac_select_pcs,
 	.mac_config = stmmac_mac_config,
 	.mac_link_down = stmmac_mac_link_down,
@@ -1204,12 +1218,14 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	int mode = priv->plat->phy_interface;
 	struct fwnode_handle *fwnode;
 	struct phylink *phylink;
-	int max_speed;
 
 	priv->phylink_config.dev = &priv->dev->dev;
 	priv->phylink_config.type = PHYLINK_NETDEV;
 	priv->phylink_config.mac_managed_pm = true;
 
+	/* Stmmac always requires an RX clock for hardware initialization */
+	priv->phylink_config.mac_requires_rxc = true;
+
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
 		priv->phylink_config.ovr_an_inband =
@@ -1225,15 +1241,6 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 		xpcs_get_interfaces(priv->hw->xpcs,
 				    priv->phylink_config.supported_interfaces);
 
-	/* Get the MAC specific capabilities */
-	stmmac_mac_phylink_get_caps(priv);
-
-	priv->phylink_config.mac_capabilities = priv->hw->link.caps;
-
-	max_speed = priv->plat->max_speed;
-	if (max_speed)
-		phylink_limit_mac_speed(&priv->phylink_config, max_speed);
-
 	fwnode = priv->plat->port_node;
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
@@ -2491,9 +2498,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		if (!xsk_tx_peek_desc(pool, &xdp_desc))
 			break;
 
-		if (priv->plat->est && priv->plat->est->enable &&
-		    priv->plat->est->max_sdu[queue] &&
-		    xdp_desc.len > priv->plat->est->max_sdu[queue]) {
+		if (priv->est && priv->est->enable &&
+		    priv->est->max_sdu[queue] &&
+		    xdp_desc.len > priv->est->max_sdu[queue]) {
 			priv->xstats.max_sdu_txq_drop[queue]++;
 			continue;
 		}
@@ -3396,6 +3403,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	u32 chan;
 	int ret;
 
+	/* Make sure RX clock is enabled */
+	if (priv->hw->phylink_pcs)
+		phylink_pcs_pre_init(priv->phylink, priv->hw->phylink_pcs);
+
 	/* DMA initialization and SW reset */
 	ret = stmmac_init_dma_engine(priv);
 	if (ret < 0) {
@@ -3945,8 +3956,7 @@ static int __stmmac_open(struct net_device *dev,
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI &&
 	    (!priv->hw->xpcs ||
-	     xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73) &&
-	    !priv->hw->lynx_pcs) {
+	     xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) {
 		ret = stmmac_init_phy(dev);
 		if (ret) {
 			netdev_err(priv->dev,
@@ -4528,9 +4538,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 			return stmmac_tso_xmit(skb, dev);
 	}
 
-	if (priv->plat->est && priv->plat->est->enable &&
-	    priv->plat->est->max_sdu[queue] &&
-	    skb->len > priv->plat->est->max_sdu[queue]){
+	if (priv->est && priv->est->enable &&
+	    priv->est->max_sdu[queue] &&
+	    skb->len > priv->est->max_sdu[queue]){
 		priv->xstats.max_sdu_txq_drop[queue]++;
 		goto max_sdu_err;
 	}
@@ -4909,9 +4919,9 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 	if (stmmac_tx_avail(priv, queue) < STMMAC_TX_THRESH(priv))
 		return STMMAC_XDP_CONSUMED;
 
-	if (priv->plat->est && priv->plat->est->enable &&
-	    priv->plat->est->max_sdu[queue] &&
-	    xdpf->len > priv->plat->est->max_sdu[queue]) {
+	if (priv->est && priv->est->enable &&
+	    priv->est->max_sdu[queue] &&
+	    xdpf->len > priv->est->max_sdu[queue]) {
 		priv->xstats.max_sdu_txq_drop[queue]++;
 		return STMMAC_XDP_CONSUMED;
 	}
@@ -5094,9 +5104,8 @@ static struct sk_buff *stmmac_construct_skb_zc(struct stmmac_channel *ch,
 	unsigned int datasize = xdp->data_end - xdp->data;
 	struct sk_buff *skb;
 
-	skb = __napi_alloc_skb(&ch->rxtx_napi,
-			       xdp->data_end - xdp->data_hard_start,
-			       GFP_ATOMIC | __GFP_NOWARN);
+	skb = napi_alloc_skb(&ch->rxtx_napi,
+			     xdp->data_end - xdp->data_hard_start);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -5900,7 +5909,7 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
 		stmmac_set_rx_mode(dev);
 	}
 
-	dev->mtu = mtu;
+	WRITE_ONCE(dev->mtu, mtu);
 	netdev_update_features(dev);
 
 	return 0;
@@ -7327,7 +7336,6 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int ret = 0, i;
-	int max_speed;
 
 	if (netif_running(dev))
 		stmmac_release(dev);
@@ -7341,14 +7349,6 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt)
 			priv->rss.table[i] = ethtool_rxfh_indir_default(i,
 									rx_cnt);
 
-	stmmac_mac_phylink_get_caps(priv);
-
-	priv->phylink_config.mac_capabilities = priv->hw->link.caps;
-
-	max_speed = priv->plat->max_speed;
-	if (max_speed)
-		phylink_limit_mac_speed(&priv->phylink_config, max_speed);
-
 	stmmac_napi_add(dev);
 
 	if (netif_running(dev))
@@ -7754,11 +7754,9 @@ int stmmac_dvr_probe(struct device *device,
 	if (priv->plat->speed_mode_2500)
 		priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
 
-	if (priv->plat->mdio_bus_data && priv->plat->mdio_bus_data->has_xpcs) {
-		ret = stmmac_xpcs_setup(priv->mii);
-		if (ret)
-			goto error_xpcs_setup;
-	}
+	ret = stmmac_pcs_setup(ndev);
+	if (ret)
+		goto error_pcs_setup;
 
 	ret = stmmac_phy_setup(priv);
 	if (ret) {
@@ -7789,8 +7787,9 @@ int stmmac_dvr_probe(struct device *device,
 
 error_netdev_register:
 	phylink_destroy(priv->phylink);
-error_xpcs_setup:
 error_phy_setup:
+	stmmac_pcs_clean(ndev);
+error_pcs_setup:
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
@@ -7832,6 +7831,9 @@ void stmmac_dvr_remove(struct device *dev)
 	if (priv->plat->stmmac_rst)
 		reset_control_assert(priv->plat->stmmac_rst);
 	reset_control_assert(priv->plat->stmmac_ahb_rst);
+
+	stmmac_pcs_clean(ndev);
+
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0542cfd1817e..aa43117134d3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -495,34 +495,57 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 	return 0;
 }
 
-int stmmac_xpcs_setup(struct mii_bus *bus)
+int stmmac_pcs_setup(struct net_device *ndev)
 {
-	struct net_device *ndev = bus->priv;
+	struct dw_xpcs *xpcs = NULL;
 	struct stmmac_priv *priv;
-	struct dw_xpcs *xpcs;
+	int ret = -ENODEV;
 	int mode, addr;
 
 	priv = netdev_priv(ndev);
 	mode = priv->plat->phy_interface;
 
-	/* Try to probe the XPCS by scanning all addresses. */
-	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
-		xpcs = xpcs_create_mdiodev(bus, addr, mode);
-		if (IS_ERR(xpcs))
-			continue;
-
-		priv->hw->xpcs = xpcs;
-		break;
+	if (priv->plat->pcs_init) {
+		ret = priv->plat->pcs_init(priv);
+	} else if (priv->plat->mdio_bus_data &&
+		   priv->plat->mdio_bus_data->has_xpcs) {
+		/* Try to probe the XPCS by scanning all addresses */
+		for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+			xpcs = xpcs_create_mdiodev(priv->mii, addr, mode);
+			if (IS_ERR(xpcs))
+				continue;
+
+			ret = 0;
+			break;
+		}
+	} else {
+		return 0;
 	}
 
-	if (!priv->hw->xpcs) {
+	if (ret) {
 		dev_warn(priv->device, "No xPCS found\n");
-		return -ENODEV;
+		return ret;
 	}
 
+	priv->hw->xpcs = xpcs;
+
 	return 0;
 }
 
+void stmmac_pcs_clean(struct net_device *ndev)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	if (priv->plat->pcs_exit)
+		priv->plat->pcs_exit(priv);
+
+	if (!priv->hw->xpcs)
+		return;
+
+	xpcs_destroy(priv->hw->xpcs);
+	priv->hw->xpcs = NULL;
+}
+
 /**
  * stmmac_mdio_register
  * @ndev: net device structure
@@ -679,9 +702,6 @@ int stmmac_mdio_unregister(struct net_device *ndev)
 	if (!priv->mii)
 		return 0;
 
-	if (priv->hw->xpcs)
-		xpcs_destroy(priv->hw->xpcs);
-
 	mdiobus_unregister(priv->mii);
 	priv->mii->priv = NULL;
 	mdiobus_free(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index e04830a3a1fb..a6b1de9a251d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -68,13 +68,13 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 	nsec = reminder;
 
 	/* If EST is enabled, disabled it before adjust ptp time. */
-	if (priv->plat->est && priv->plat->est->enable) {
+	if (priv->est && priv->est->enable) {
 		est_rst = true;
-		mutex_lock(&priv->plat->est->lock);
-		priv->plat->est->enable = false;
-		stmmac_est_configure(priv, priv, priv->plat->est,
+		mutex_lock(&priv->est_lock);
+		priv->est->enable = false;
+		stmmac_est_configure(priv, priv, priv->est,
 				     priv->plat->clk_ptp_rate);
-		mutex_unlock(&priv->plat->est->lock);
+		mutex_unlock(&priv->est_lock);
 	}
 
 	write_lock_irqsave(&priv->ptp_lock, flags);
@@ -87,24 +87,24 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 		ktime_t current_time_ns, basetime;
 		u64 cycle_time;
 
-		mutex_lock(&priv->plat->est->lock);
+		mutex_lock(&priv->est_lock);
 		priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time);
 		current_time_ns = timespec64_to_ktime(current_time);
-		time.tv_nsec = priv->plat->est->btr_reserve[0];
-		time.tv_sec = priv->plat->est->btr_reserve[1];
+		time.tv_nsec = priv->est->btr_reserve[0];
+		time.tv_sec = priv->est->btr_reserve[1];
 		basetime = timespec64_to_ktime(time);
-		cycle_time = (u64)priv->plat->est->ctr[1] * NSEC_PER_SEC +
-			     priv->plat->est->ctr[0];
+		cycle_time = (u64)priv->est->ctr[1] * NSEC_PER_SEC +
+			     priv->est->ctr[0];
 		time = stmmac_calc_tas_basetime(basetime,
 						current_time_ns,
 						cycle_time);
 
-		priv->plat->est->btr[0] = (u32)time.tv_nsec;
-		priv->plat->est->btr[1] = (u32)time.tv_sec;
-		priv->plat->est->enable = true;
-		ret = stmmac_est_configure(priv, priv, priv->plat->est,
+		priv->est->btr[0] = (u32)time.tv_nsec;
+		priv->est->btr[1] = (u32)time.tv_sec;
+		priv->est->enable = true;
+		ret = stmmac_est_configure(priv, priv, priv->est,
 					   priv->plat->clk_ptp_rate);
-		mutex_unlock(&priv->plat->est->lock);
+		mutex_unlock(&priv->est_lock);
 		if (ret)
 			netdev_err(priv->dev, "failed to configure EST\n");
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index cce00719937d..222540b55480 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -918,7 +918,6 @@ struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
 static void tc_taprio_map_maxsdu_txq(struct stmmac_priv *priv,
 				     struct tc_taprio_qopt_offload *qopt)
 {
-	struct plat_stmmacenet_data *plat = priv->plat;
 	u32 num_tc = qopt->mqprio.qopt.num_tc;
 	u32 offset, count, i, j;
 
@@ -933,7 +932,7 @@ static void tc_taprio_map_maxsdu_txq(struct stmmac_priv *priv,
 		count = qopt->mqprio.qopt.count[i];
 
 		for (j = offset; j < offset + count; j++)
-			plat->est->max_sdu[j] = qopt->max_sdu[i] + ETH_HLEN - ETH_TLEN;
+			priv->est->max_sdu[j] = qopt->max_sdu[i] + ETH_HLEN - ETH_TLEN;
 	}
 }
 
@@ -941,7 +940,6 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 			       struct tc_taprio_qopt_offload *qopt)
 {
 	u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
-	struct plat_stmmacenet_data *plat = priv->plat;
 	struct timespec64 time, current_time, qopt_time;
 	ktime_t current_time_ns;
 	bool fpe = false;
@@ -998,23 +996,25 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 	if (qopt->cycle_time_extension >= BIT(wid + 7))
 		return -ERANGE;
 
-	if (!plat->est) {
-		plat->est = devm_kzalloc(priv->device, sizeof(*plat->est),
+	if (!priv->est) {
+		priv->est = devm_kzalloc(priv->device, sizeof(*priv->est),
 					 GFP_KERNEL);
-		if (!plat->est)
+		if (!priv->est)
 			return -ENOMEM;
 
-		mutex_init(&priv->plat->est->lock);
+		mutex_init(&priv->est_lock);
 	} else {
-		memset(plat->est, 0, sizeof(*plat->est));
+		mutex_lock(&priv->est_lock);
+		memset(priv->est, 0, sizeof(*priv->est));
+		mutex_unlock(&priv->est_lock);
 	}
 
 	size = qopt->num_entries;
 
-	mutex_lock(&priv->plat->est->lock);
-	priv->plat->est->gcl_size = size;
-	priv->plat->est->enable = qopt->cmd == TAPRIO_CMD_REPLACE;
-	mutex_unlock(&priv->plat->est->lock);
+	mutex_lock(&priv->est_lock);
+	priv->est->gcl_size = size;
+	priv->est->enable = qopt->cmd == TAPRIO_CMD_REPLACE;
+	mutex_unlock(&priv->est_lock);
 
 	for (i = 0; i < size; i++) {
 		s64 delta_ns = qopt->entries[i].interval;
@@ -1042,33 +1042,33 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 			return -EOPNOTSUPP;
 		}
 
-		priv->plat->est->gcl[i] = delta_ns | (gates << wid);
+		priv->est->gcl[i] = delta_ns | (gates << wid);
 	}
 
-	mutex_lock(&priv->plat->est->lock);
+	mutex_lock(&priv->est_lock);
 	/* Adjust for real system time */
 	priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time);
 	current_time_ns = timespec64_to_ktime(current_time);
 	time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns,
 					qopt->cycle_time);
 
-	priv->plat->est->btr[0] = (u32)time.tv_nsec;
-	priv->plat->est->btr[1] = (u32)time.tv_sec;
+	priv->est->btr[0] = (u32)time.tv_nsec;
+	priv->est->btr[1] = (u32)time.tv_sec;
 
 	qopt_time = ktime_to_timespec64(qopt->base_time);
-	priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec;
-	priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec;
+	priv->est->btr_reserve[0] = (u32)qopt_time.tv_nsec;
+	priv->est->btr_reserve[1] = (u32)qopt_time.tv_sec;
 
 	ctr = qopt->cycle_time;
-	priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
-	priv->plat->est->ctr[1] = (u32)ctr;
+	priv->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
+	priv->est->ctr[1] = (u32)ctr;
 
-	priv->plat->est->ter = qopt->cycle_time_extension;
+	priv->est->ter = qopt->cycle_time_extension;
 
 	tc_taprio_map_maxsdu_txq(priv, qopt);
 
 	if (fpe && !priv->dma_cap.fpesel) {
-		mutex_unlock(&priv->plat->est->lock);
+		mutex_unlock(&priv->est_lock);
 		return -EOPNOTSUPP;
 	}
 
@@ -1077,9 +1077,9 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 	 */
 	priv->plat->fpe_cfg->enable = fpe;
 
-	ret = stmmac_est_configure(priv, priv, priv->plat->est,
+	ret = stmmac_est_configure(priv, priv, priv->est,
 				   priv->plat->clk_ptp_rate);
-	mutex_unlock(&priv->plat->est->lock);
+	mutex_unlock(&priv->est_lock);
 	if (ret) {
 		netdev_err(priv->dev, "failed to configure EST\n");
 		goto disable;
@@ -1095,17 +1095,17 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 	return 0;
 
 disable:
-	if (priv->plat->est) {
-		mutex_lock(&priv->plat->est->lock);
-		priv->plat->est->enable = false;
-		stmmac_est_configure(priv, priv, priv->plat->est,
+	if (priv->est) {
+		mutex_lock(&priv->est_lock);
+		priv->est->enable = false;
+		stmmac_est_configure(priv, priv, priv->est,
 				     priv->plat->clk_ptp_rate);
 		/* Reset taprio status */
 		for (i = 0; i < priv->plat->tx_queues_to_use; i++) {
 			priv->xstats.max_sdu_txq_drop[i] = 0;
 			priv->xstats.mtl_est_txq_hlbf[i] = 0;
 		}
-		mutex_unlock(&priv->plat->est->lock);
+		mutex_unlock(&priv->est_lock);
 	}
 
 	priv->plat->fpe_cfg->enable = false;
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index bfb903506367..b8948d5b779a 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -73,6 +73,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
+#include <linux/skbuff_ref.h>
 #include <linux/ethtool.h>
 #include <linux/crc32.h>
 #include <linux/random.h>
@@ -3803,7 +3804,7 @@ static int cas_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct cas *cp = netdev_priv(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 	if (!netif_running(dev) || !netif_device_present(dev))
 		return 0;
 
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index f68aa813d4fb..41a27ae58ced 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6751,7 +6751,7 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu)
 	orig_jumbo = (dev->mtu > ETH_DATA_LEN);
 	new_jumbo = (new_mtu > ETH_DATA_LEN);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	if (!netif_running(dev) ||
 	    (orig_jumbo == new_jumbo))
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 9bd1df8308d2..3e5f9b17c777 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -949,17 +949,6 @@ static irqreturn_t gem_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void gem_poll_controller(struct net_device *dev)
-{
-	struct gem *gp = netdev_priv(dev);
-
-	disable_irq(gp->pdev->irq);
-	gem_interrupt(gp->pdev->irq, dev);
-	enable_irq(gp->pdev->irq);
-}
-#endif
-
 static void gem_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct gem *gp = netdev_priv(dev);
@@ -2499,7 +2488,7 @@ static int gem_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct gem *gp = netdev_priv(dev);
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	/* We'll just catch it later when the device is up'd or resumed */
 	if (!netif_running(dev) || !netif_device_present(dev))
@@ -2839,9 +2828,6 @@ static const struct net_device_ops gem_netdev_ops = {
 	.ndo_change_mtu		= gem_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address    = gem_set_mac_address,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller    = gem_poll_controller,
-#endif
 };
 
 static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
index 36b948820c1e..d1793b6154c7 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -823,7 +823,7 @@ static int xlgmac_change_mtu(struct net_device *netdev, int mtu)
 		return ret;
 
 	pdata->rx_buf_size = ret;
-	netdev->mtu = mtu;
+	WRITE_ONCE(netdev->mtu, mtu);
 
 	xlgmac_restart_dev(pdata);
 
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index ca409515ead5..ede5f7890fb4 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -756,7 +756,7 @@ static int bdx_change_mtu(struct net_device *ndev, int new_mtu)
 {
 	ENTER;
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 	if (netif_running(ndev)) {
 		bdx_close(ndev);
 		bdx_open(ndev);
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 1530d13984d4..1729eb0e0b41 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -167,7 +167,7 @@ config TI_KEYSTONE_NETCP_ETHSS
 
 config TLAN
 	tristate "TI ThunderLAN support"
-	depends on (PCI || EISA)
+	depends on (PCI || EISA) && HAS_IOPORT
 	help
 	  If you have a PCI Ethernet network card based on the ThunderLAN chip
 	  which is supported by this driver, say Y here.
@@ -198,6 +198,21 @@ config TI_ICSSG_PRUETH
 	  to support the Ethernet operation. Currently, it supports Ethernet
 	  with 1G and 100M link speed.
 
+config TI_ICSSG_PRUETH_SR1
+	tristate "TI Gigabit PRU SR1.0 Ethernet driver"
+	select PHYLIB
+	select TI_ICSS_IEP
+	select TI_K3_CPPI_DESC_POOL
+	depends on PRU_REMOTEPROC
+	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	help
+	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
+	  This subsystem is available on the AM65 SR1.0 platform.
+
+	  This driver requires firmware binaries which will run on the PRUs
+	  to support the Ethernet operation. Currently, it supports Ethernet
+	  with 1G, 100M and 10M link speed.
+
 config TI_ICSS_IEP
 	tristate "TI PRU ICSS IEP driver"
 	depends on PTP_1588_CLOCK_OPTIONAL
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index d8590304f3df..6e086b4c0384 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -33,10 +33,19 @@ obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
 
 obj-$(CONFIG_TI_ICSSG_PRUETH) += icssg-prueth.o
 icssg-prueth-y := icssg/icssg_prueth.o \
+		  icssg/icssg_common.o \
 		  icssg/icssg_classifier.o \
 		  icssg/icssg_queues.o \
 		  icssg/icssg_config.o \
 		  icssg/icssg_mii_cfg.o \
 		  icssg/icssg_stats.o \
 		  icssg/icssg_ethtool.o
+obj-$(CONFIG_TI_ICSSG_PRUETH_SR1) += icssg-prueth-sr1.o
+icssg-prueth-sr1-y := icssg/icssg_prueth_sr1.o \
+		      icssg/icssg_common.o \
+		      icssg/icssg_classifier.o \
+		      icssg/icssg_config.o \
+		      icssg/icssg_mii_cfg.o \
+		      icssg/icssg_stats.o \
+		      icssg/icssg_ethtool.o
 obj-$(CONFIG_TI_ICSS_IEP) += icssg/icss_iep.o
diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index d6ce2c9f0a8d..a1d0935d1ebe 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -695,6 +695,17 @@ static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev,
 					 struct ethtool_ts_info *info)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	unsigned int ptp_v2_filter;
+
+	ptp_v2_filter = BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+			BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+			BIT(HWTSTAMP_FILTER_PTP_V2_EVENT)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_SYNC)	 |
+			BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ);
 
 	if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS))
 		return ethtool_op_get_ts_info(ndev, info);
@@ -708,7 +719,7 @@ static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev,
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->phc_index = am65_cpts_phc_index(common->cpts);
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
-	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | ptp_v2_filter;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 1d00e21808c1..4e50b3792888 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/bpf_trace.h>
 #include <linux/clk.h>
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
@@ -30,6 +31,7 @@
 #include <linux/sys_soc.h>
 #include <linux/dma/ti-cppi5.h>
 #include <linux/dma/k3-udma-glue.h>
+#include <net/page_pool/helpers.h>
 #include <net/switchdev.h>
 
 #include "cpsw_ale.h"
@@ -101,6 +103,12 @@
 #define AM65_CPSW_PN_TS_CTL_TX_HOST_TS_EN	BIT(11)
 #define AM65_CPSW_PN_TS_CTL_MSG_TYPE_EN_SHIFT	16
 
+#define AM65_CPSW_PN_TS_CTL_RX_ANX_F_EN		BIT(0)
+#define AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN	BIT(1)
+#define AM65_CPSW_PN_TS_CTL_RX_VLAN_LT2_EN	BIT(2)
+#define AM65_CPSW_PN_TS_CTL_RX_ANX_D_EN		BIT(3)
+#define AM65_CPSW_PN_TS_CTL_RX_ANX_E_EN		BIT(9)
+
 /* AM65_CPSW_PORTN_REG_TS_SEQ_LTYPE_REG register fields */
 #define AM65_CPSW_PN_TS_SEQ_ID_OFFSET_SHIFT	16
 
@@ -124,6 +132,11 @@
 	 AM65_CPSW_PN_TS_CTL_TX_ANX_E_EN |	\
 	 AM65_CPSW_PN_TS_CTL_TX_ANX_F_EN)
 
+#define AM65_CPSW_TS_RX_ANX_ALL_EN		\
+	(AM65_CPSW_PN_TS_CTL_RX_ANX_D_EN |	\
+	 AM65_CPSW_PN_TS_CTL_RX_ANX_E_EN |	\
+	 AM65_CPSW_PN_TS_CTL_RX_ANX_F_EN)
+
 #define AM65_CPSW_ALE_AGEOUT_DEFAULT	30
 /* Number of TX/RX descriptors */
 #define AM65_CPSW_MAX_TX_DESC	500
@@ -138,6 +151,18 @@
 
 #define AM65_CPSW_DEFAULT_TX_CHNS	8
 
+/* CPPI streaming packet interface */
+#define AM65_CPSW_CPPI_TX_FLOW_ID  0x3FFF
+#define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7
+
+/* XDP */
+#define AM65_CPSW_XDP_CONSUMED 2
+#define AM65_CPSW_XDP_REDIRECT 1
+#define AM65_CPSW_XDP_PASS     0
+
+/* Include headroom compatible with both skb and xdpf */
+#define AM65_CPSW_HEADROOM (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN)
+
 static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave,
 				      const u8 *dev_addr)
 {
@@ -305,12 +330,11 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev,
 }
 
 static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
-				  struct sk_buff *skb)
+				  struct page *page)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	struct cppi5_host_desc_t *desc_rx;
 	struct device *dev = common->dev;
-	u32 pkt_len = skb_tailroom(skb);
 	dma_addr_t desc_dma;
 	dma_addr_t buf_dma;
 	void *swdata;
@@ -322,20 +346,22 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
 	}
 	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
 
-	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len,
-				 DMA_FROM_DEVICE);
+	buf_dma = dma_map_single(rx_chn->dma_dev,
+				 page_address(page) + AM65_CPSW_HEADROOM,
+				 AM65_CPSW_MAX_PACKET_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
 		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-		dev_err(dev, "Failed to map rx skb buffer\n");
+		dev_err(dev, "Failed to map rx buffer\n");
 		return -EINVAL;
 	}
 
 	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 AM65_CPSW_NAV_PS_DATA_SIZE);
 	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
-	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, AM65_CPSW_MAX_PACKET_SIZE,
+			       buf_dma, AM65_CPSW_MAX_PACKET_SIZE);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	*((void **)swdata) = skb;
+	*((void **)swdata) = page_address(page);
 
 	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0, desc_rx, desc_dma);
 }
@@ -369,25 +395,137 @@ static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common);
 static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port);
 static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port);
 
+static void am65_cpsw_destroy_xdp_rxqs(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct xdp_rxq_info *rxq;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		if (!common->ports[i].ndev)
+			continue;
+
+		rxq = &common->ports[i].xdp_rxq;
+
+		if (xdp_rxq_info_is_reg(rxq))
+			xdp_rxq_info_unreg(rxq);
+	}
+
+	if (rx_chn->page_pool) {
+		page_pool_destroy(rx_chn->page_pool);
+		rx_chn->page_pool = NULL;
+	}
+}
+
+static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct page_pool_params pp_params = {
+		.flags = PP_FLAG_DMA_MAP,
+		.order = 0,
+		.pool_size = AM65_CPSW_MAX_RX_DESC,
+		.nid = dev_to_node(common->dev),
+		.dev = common->dev,
+		.dma_dir = DMA_BIDIRECTIONAL,
+		.napi = &common->napi_rx,
+	};
+	struct xdp_rxq_info *rxq;
+	struct page_pool *pool;
+	int i, ret;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	rx_chn->page_pool = pool;
+
+	for (i = 0; i < common->port_num; i++) {
+		if (!common->ports[i].ndev)
+			continue;
+
+		rxq = &common->ports[i].xdp_rxq;
+
+		ret = xdp_rxq_info_reg(rxq, common->ports[i].ndev, i, 0);
+		if (ret)
+			goto err;
+
+		ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	am65_cpsw_destroy_xdp_rxqs(common);
+	return ret;
+}
+
+static int am65_cpsw_nuss_desc_idx(struct k3_cppi_desc_pool *desc_pool,
+				   void *desc,
+				   unsigned char dsize_log2)
+{
+	void *pool_addr = k3_cppi_desc_pool_cpuaddr(desc_pool);
+
+	return (desc - pool_addr) >> dsize_log2;
+}
+
+static void am65_cpsw_nuss_set_buf_type(struct am65_cpsw_tx_chn *tx_chn,
+					struct cppi5_host_desc_t *desc,
+					enum am65_cpsw_tx_buf_type buf_type)
+{
+	int desc_idx;
+
+	desc_idx = am65_cpsw_nuss_desc_idx(tx_chn->desc_pool, desc,
+					   tx_chn->dsize_log2);
+	k3_cppi_desc_pool_desc_info_set(tx_chn->desc_pool, desc_idx,
+					(void *)buf_type);
+}
+
+static enum am65_cpsw_tx_buf_type am65_cpsw_nuss_buf_type(struct am65_cpsw_tx_chn *tx_chn,
+							  dma_addr_t desc_dma)
+{
+	struct cppi5_host_desc_t *desc_tx;
+	int desc_idx;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
+	desc_idx = am65_cpsw_nuss_desc_idx(tx_chn->desc_pool, desc_tx,
+					   tx_chn->dsize_log2);
+
+	return (enum am65_cpsw_tx_buf_type)k3_cppi_desc_pool_desc_info(tx_chn->desc_pool,
+								       desc_idx);
+}
+
+static inline void am65_cpsw_put_page(struct am65_cpsw_rx_chn *rx_chn,
+				      struct page *page,
+				      bool allow_direct,
+				      int desc_idx)
+{
+	page_pool_put_full_page(rx_chn->page_pool, page, allow_direct);
+	rx_chn->pages[desc_idx] = NULL;
+}
+
 static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct am65_cpsw_rx_chn *rx_chn = data;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb;
 	dma_addr_t buf_dma;
 	u32 buf_dma_len;
+	void *page_addr;
 	void **swdata;
+	int desc_idx;
 
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
+	page_addr = *swdata;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
-
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	dev_kfree_skb_any(skb);
+	desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx,
+					   rx_chn->dsize_log2);
+	am65_cpsw_put_page(rx_chn, virt_to_page(page_addr), false, desc_idx);
 }
 
 static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
@@ -440,12 +578,32 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 	dev_kfree_skb_any(skb);
 }
 
+static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
+					   struct net_device *ndev,
+					   unsigned int len)
+{
+	struct sk_buff *skb;
+
+	len += AM65_CPSW_HEADROOM;
+
+	skb = build_skb(page_addr, len);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, AM65_CPSW_HEADROOM);
+	skb->dev = ndev;
+
+	return skb;
+}
+
 static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 {
 	struct am65_cpsw_host *host_p = am65_common_get_host(common);
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
 	int port_idx, i, ret, tx;
-	struct sk_buff *skb;
 	u32 val, port_mask;
+	struct page *page;
 
 	if (common->usage_count)
 		return 0;
@@ -505,25 +663,29 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 
 	am65_cpsw_qos_tx_p0_rate_init(common);
 
-	for (i = 0; i < common->rx_chns.descs_num; i++) {
-		skb = __netdev_alloc_skb_ip_align(NULL,
-						  AM65_CPSW_MAX_PACKET_SIZE,
-						  GFP_KERNEL);
-		if (!skb) {
+	ret = am65_cpsw_create_xdp_rxqs(common);
+	if (ret) {
+		dev_err(common->dev, "Failed to create XDP rx queues\n");
+		return ret;
+	}
+
+	for (i = 0; i < rx_chn->descs_num; i++) {
+		page = page_pool_dev_alloc_pages(rx_chn->page_pool);
+		if (!page) {
 			ret = -ENOMEM;
-			dev_err(common->dev, "cannot allocate skb\n");
 			if (i)
 				goto fail_rx;
 
 			return ret;
 		}
+		rx_chn->pages[i] = page;
 
-		ret = am65_cpsw_nuss_rx_push(common, skb);
+		ret = am65_cpsw_nuss_rx_push(common, page);
 		if (ret < 0) {
 			dev_err(common->dev,
-				"cannot submit skb to channel rx, error %d\n",
+				"cannot submit page to channel rx: %d\n",
 				ret);
-			kfree_skb(skb);
+			am65_cpsw_put_page(rx_chn, page, false, i);
 			if (i)
 				goto fail_rx;
 
@@ -531,27 +693,27 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 		}
 	}
 
-	ret = k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn);
+	ret = k3_udma_glue_enable_rx_chn(rx_chn->rx_chn);
 	if (ret) {
 		dev_err(common->dev, "couldn't enable rx chn: %d\n", ret);
 		goto fail_rx;
 	}
 
 	for (tx = 0; tx < common->tx_ch_num; tx++) {
-		ret = k3_udma_glue_enable_tx_chn(common->tx_chns[tx].tx_chn);
+		ret = k3_udma_glue_enable_tx_chn(tx_chn[tx].tx_chn);
 		if (ret) {
 			dev_err(common->dev, "couldn't enable tx chn %d: %d\n",
 				tx, ret);
 			tx--;
 			goto fail_tx;
 		}
-		napi_enable(&common->tx_chns[tx].napi_tx);
+		napi_enable(&tx_chn[tx].napi_tx);
 	}
 
 	napi_enable(&common->napi_rx);
 	if (common->rx_irq_disabled) {
 		common->rx_irq_disabled = false;
-		enable_irq(common->rx_chns.irq);
+		enable_irq(rx_chn->irq);
 	}
 
 	dev_dbg(common->dev, "cpsw_nuss started\n");
@@ -559,22 +721,23 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 
 fail_tx:
 	while (tx >= 0) {
-		napi_disable(&common->tx_chns[tx].napi_tx);
-		k3_udma_glue_disable_tx_chn(common->tx_chns[tx].tx_chn);
+		napi_disable(&tx_chn[tx].napi_tx);
+		k3_udma_glue_disable_tx_chn(tx_chn[tx].tx_chn);
 		tx--;
 	}
 
-	k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn);
+	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
 
 fail_rx:
-	k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, 0,
-				  &common->rx_chns,
+	k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, 0, rx_chn,
 				  am65_cpsw_nuss_rx_cleanup, 0);
 	return ret;
 }
 
 static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 {
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
 	int i;
 
 	if (common->usage_count != 1)
@@ -590,26 +753,25 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 	reinit_completion(&common->tdown_complete);
 
 	for (i = 0; i < common->tx_ch_num; i++)
-		k3_udma_glue_tdown_tx_chn(common->tx_chns[i].tx_chn, false);
+		k3_udma_glue_tdown_tx_chn(tx_chn[i].tx_chn, false);
 
 	i = wait_for_completion_timeout(&common->tdown_complete,
 					msecs_to_jiffies(1000));
 	if (!i)
 		dev_err(common->dev, "tx timeout\n");
 	for (i = 0; i < common->tx_ch_num; i++) {
-		napi_disable(&common->tx_chns[i].napi_tx);
-		hrtimer_cancel(&common->tx_chns[i].tx_hrtimer);
+		napi_disable(&tx_chn[i].napi_tx);
+		hrtimer_cancel(&tx_chn[i].tx_hrtimer);
 	}
 
 	for (i = 0; i < common->tx_ch_num; i++) {
-		k3_udma_glue_reset_tx_chn(common->tx_chns[i].tx_chn,
-					  &common->tx_chns[i],
+		k3_udma_glue_reset_tx_chn(tx_chn[i].tx_chn, &tx_chn[i],
 					  am65_cpsw_nuss_tx_cleanup);
-		k3_udma_glue_disable_tx_chn(common->tx_chns[i].tx_chn);
+		k3_udma_glue_disable_tx_chn(tx_chn[i].tx_chn);
 	}
 
 	reinit_completion(&common->tdown_complete);
-	k3_udma_glue_tdown_rx_chn(common->rx_chns.rx_chn, true);
+	k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true);
 
 	if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) {
 		i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000));
@@ -621,17 +783,22 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 	hrtimer_cancel(&common->rx_hrtimer);
 
 	for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
-		k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, i,
-					  &common->rx_chns,
+		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn,
 					  am65_cpsw_nuss_rx_cleanup, !!i);
 
-	k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn);
+	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
 
 	cpsw_ale_stop(common->ale);
 
 	writel(0, common->cpsw_base + AM65_CPSW_REG_CTL);
 	writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN);
 
+	for (i = 0; i < rx_chn->descs_num; i++) {
+		if (rx_chn->pages[i])
+			am65_cpsw_put_page(rx_chn, rx_chn->pages[i], false, i);
+	}
+	am65_cpsw_destroy_xdp_rxqs(common);
+
 	dev_dbg(common->dev, "cpsw_nuss stopped\n");
 	return 0;
 }
@@ -749,16 +916,149 @@ runtime_put:
 	return ret;
 }
 
-static void am65_cpsw_nuss_rx_ts(struct sk_buff *skb, u32 *psdata)
+static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
+				  struct am65_cpsw_tx_chn *tx_chn,
+				  struct xdp_frame *xdpf,
+				  enum am65_cpsw_tx_buf_type buf_type)
 {
-	struct skb_shared_hwtstamps *ssh;
-	u64 ns;
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct cppi5_host_desc_t *host_desc;
+	struct netdev_queue *netif_txq;
+	dma_addr_t dma_desc, dma_buf;
+	u32 pkt_len = xdpf->len;
+	void **swdata;
+	int ret;
+
+	host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (unlikely(!host_desc)) {
+		ndev->stats.tx_dropped++;
+		return -ENOMEM;
+	}
+
+	am65_cpsw_nuss_set_buf_type(tx_chn, host_desc, buf_type);
 
-	ns = ((u64)psdata[1] << 32) | psdata[0];
+	dma_buf = dma_map_single(tx_chn->dma_dev, xdpf->data,
+				 pkt_len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(tx_chn->dma_dev, dma_buf))) {
+		ndev->stats.tx_dropped++;
+		ret = -ENOMEM;
+		goto pool_free;
+	}
+
+	cppi5_hdesc_init(host_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 AM65_CPSW_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(host_desc, AM65_CPSW_CPPI_TX_PKT_TYPE);
+	cppi5_hdesc_set_pktlen(host_desc, pkt_len);
+	cppi5_desc_set_pktids(&host_desc->hdr, 0, AM65_CPSW_CPPI_TX_FLOW_ID);
+	cppi5_desc_set_tags_ids(&host_desc->hdr, 0, port->port_id);
+
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &dma_buf);
+	cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, pkt_len);
+
+	swdata = cppi5_hdesc_get_swdata(host_desc);
+	*(swdata) = xdpf;
+
+	/* Report BQL before sending the packet */
+	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+	netdev_tx_sent_queue(netif_txq, pkt_len);
+
+	dma_desc = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, host_desc);
+	if (AM65_CPSW_IS_CPSW2G(common)) {
+		ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, host_desc,
+					       dma_desc);
+	} else {
+		spin_lock_bh(&tx_chn->lock);
+		ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, host_desc,
+					       dma_desc);
+		spin_unlock_bh(&tx_chn->lock);
+	}
+	if (ret) {
+		/* Inform BQL */
+		netdev_tx_completed_queue(netif_txq, 1, pkt_len);
+		ndev->stats.tx_errors++;
+		goto dma_unmap;
+	}
+
+	return 0;
 
-	ssh = skb_hwtstamps(skb);
-	memset(ssh, 0, sizeof(*ssh));
-	ssh->hwtstamp = ns_to_ktime(ns);
+dma_unmap:
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &dma_buf);
+	dma_unmap_single(tx_chn->dma_dev, dma_buf, pkt_len, DMA_TO_DEVICE);
+pool_free:
+	k3_cppi_desc_pool_free(tx_chn->desc_pool, host_desc);
+	return ret;
+}
+
+static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+			     struct am65_cpsw_port *port,
+			     struct xdp_buff *xdp,
+			     int desc_idx, int cpu, int *len)
+{
+	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct net_device *ndev = port->ndev;
+	int ret = AM65_CPSW_XDP_CONSUMED;
+	struct am65_cpsw_tx_chn *tx_chn;
+	struct netdev_queue *netif_txq;
+	struct xdp_frame *xdpf;
+	struct bpf_prog *prog;
+	struct page *page;
+	u32 act;
+
+	prog = READ_ONCE(port->xdp_prog);
+	if (!prog)
+		return AM65_CPSW_XDP_PASS;
+
+	act = bpf_prog_run_xdp(prog, xdp);
+	/* XDP prog might have changed packet data and boundaries */
+	*len = xdp->data_end - xdp->data;
+
+	switch (act) {
+	case XDP_PASS:
+		ret = AM65_CPSW_XDP_PASS;
+		goto out;
+	case XDP_TX:
+		tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES];
+		netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf))
+			break;
+
+		__netif_tx_lock(netif_txq, cpu);
+		ret = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf,
+					     AM65_CPSW_TX_BUF_TYPE_XDP_TX);
+		__netif_tx_unlock(netif_txq);
+		if (ret)
+			break;
+
+		ndev->stats.rx_bytes += *len;
+		ndev->stats.rx_packets++;
+		ret = AM65_CPSW_XDP_CONSUMED;
+		goto out;
+	case XDP_REDIRECT:
+		if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
+			break;
+
+		ndev->stats.rx_bytes += *len;
+		ndev->stats.rx_packets++;
+		ret = AM65_CPSW_XDP_REDIRECT;
+		goto out;
+	default:
+		bpf_warn_invalid_xdp_action(ndev, prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(ndev, prog, act);
+		fallthrough;
+	case XDP_DROP:
+		ndev->stats.rx_dropped++;
+	}
+
+	page = virt_to_head_page(xdp->data);
+	am65_cpsw_put_page(rx_chn, page, true, desc_idx);
+
+out:
+	return ret;
 }
 
 /* RX psdata[2] word format - checksum information */
@@ -795,7 +1095,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info)
 }
 
 static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
-				     u32 flow_idx)
+				     u32 flow_idx, int cpu)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0, csum_info;
@@ -803,13 +1103,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	struct am65_cpsw_ndev_stats *stats;
 	struct cppi5_host_desc_t *desc_rx;
 	struct device *dev = common->dev;
-	struct sk_buff *skb, *new_skb;
+	struct page *page, *new_page;
 	dma_addr_t desc_dma, buf_dma;
 	struct am65_cpsw_port *port;
+	int headroom, desc_idx, ret;
 	struct net_device *ndev;
+	struct sk_buff *skb;
+	struct xdp_buff	xdp;
+	void *page_addr;
 	void **swdata;
 	u32 *psdata;
-	int ret = 0;
 
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_idx, &desc_dma);
 	if (ret) {
@@ -830,7 +1133,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 		__func__, flow_idx, &desc_dma);
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
+	page_addr = *swdata;
+	page = virt_to_page(page_addr);
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
@@ -838,12 +1142,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	dev_dbg(dev, "%s rx port_id:%d\n", __func__, port_id);
 	port = am65_common_get_port(common, port_id);
 	ndev = port->ndev;
-	skb->dev = ndev;
-
 	psdata = cppi5_hdesc_get_psdata(desc_rx);
-	/* add RX timestamp */
-	if (port->rx_ts_enabled)
-		am65_cpsw_nuss_rx_ts(skb, psdata);
 	csum_info = psdata[2];
 	dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info);
 
@@ -851,36 +1150,64 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, AM65_CPSW_MAX_PACKET_SIZE);
-	if (new_skb) {
-		ndev_priv = netdev_priv(ndev);
-		am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark);
-		skb_put(skb, pkt_len);
-		skb->protocol = eth_type_trans(skb, ndev);
-		am65_cpsw_nuss_rx_csum(skb, csum_info);
-		napi_gro_receive(&common->napi_rx, skb);
-
-		stats = this_cpu_ptr(ndev_priv->stats);
-
-		u64_stats_update_begin(&stats->syncp);
-		stats->rx_packets++;
-		stats->rx_bytes += pkt_len;
-		u64_stats_update_end(&stats->syncp);
-		kmemleak_not_leak(new_skb);
-	} else {
-		ndev->stats.rx_dropped++;
-		new_skb = skb;
+	desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx,
+					   rx_chn->dsize_log2);
+
+	skb = am65_cpsw_build_skb(page_addr, ndev,
+				  AM65_CPSW_MAX_PACKET_SIZE);
+	if (unlikely(!skb)) {
+		new_page = page;
+		goto requeue;
 	}
 
+	if (port->xdp_prog) {
+		xdp_init_buff(&xdp, AM65_CPSW_MAX_PACKET_SIZE, &port->xdp_rxq);
+
+		xdp_prepare_buff(&xdp, page_addr, skb_headroom(skb),
+				 pkt_len, false);
+
+		ret = am65_cpsw_run_xdp(common, port, &xdp, desc_idx,
+					cpu, &pkt_len);
+		if (ret != AM65_CPSW_XDP_PASS)
+			return ret;
+
+		/* Compute additional headroom to be reserved */
+		headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb);
+		skb_reserve(skb, headroom);
+	}
+
+	ndev_priv = netdev_priv(ndev);
+	am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark);
+	skb_put(skb, pkt_len);
+	if (port->rx_ts_enabled)
+		am65_cpts_rx_timestamp(common->cpts, skb);
+	skb_mark_for_recycle(skb);
+	skb->protocol = eth_type_trans(skb, ndev);
+	am65_cpsw_nuss_rx_csum(skb, csum_info);
+	napi_gro_receive(&common->napi_rx, skb);
+
+	stats = this_cpu_ptr(ndev_priv->stats);
+
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += pkt_len;
+	u64_stats_update_end(&stats->syncp);
+
+	new_page = page_pool_dev_alloc_pages(rx_chn->page_pool);
+	if (unlikely(!new_page))
+		return -ENOMEM;
+	rx_chn->pages[desc_idx] = new_page;
+
 	if (netif_dormant(ndev)) {
-		dev_kfree_skb_any(new_skb);
+		am65_cpsw_put_page(rx_chn, new_page, true, desc_idx);
 		ndev->stats.rx_dropped++;
 		return 0;
 	}
 
-	ret = am65_cpsw_nuss_rx_push(common, new_skb);
+requeue:
+	ret = am65_cpsw_nuss_rx_push(common, new_page);
 	if (WARN_ON(ret < 0)) {
-		dev_kfree_skb_any(new_skb);
+		am65_cpsw_put_page(rx_chn, new_page, true, desc_idx);
 		ndev->stats.rx_errors++;
 		ndev->stats.rx_dropped++;
 	}
@@ -901,6 +1228,8 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 {
 	struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx);
 	int flow = AM65_CPSW_MAX_RX_FLOWS;
+	int cpu = smp_processor_id();
+	bool xdp_redirect = false;
 	int cur_budget, ret;
 	int num_rx = 0;
 
@@ -909,9 +1238,12 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 		cur_budget = budget - num_rx;
 
 		while (cur_budget--) {
-			ret = am65_cpsw_nuss_rx_packets(common, flow);
-			if (ret)
+			ret = am65_cpsw_nuss_rx_packets(common, flow, cpu);
+			if (ret) {
+				if (ret == AM65_CPSW_XDP_REDIRECT)
+					xdp_redirect = true;
 				break;
+			}
 			num_rx++;
 		}
 
@@ -919,6 +1251,9 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 			break;
 	}
 
+	if (xdp_redirect)
+		xdp_do_flush();
+
 	dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget);
 
 	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
@@ -938,8 +1273,8 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 }
 
 static struct sk_buff *
-am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn,
-			       dma_addr_t desc_dma)
+am65_cpsw_nuss_tx_compl_packet_skb(struct am65_cpsw_tx_chn *tx_chn,
+				   dma_addr_t desc_dma)
 {
 	struct am65_cpsw_ndev_priv *ndev_priv;
 	struct am65_cpsw_ndev_stats *stats;
@@ -968,6 +1303,39 @@ am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn,
 	return skb;
 }
 
+static struct xdp_frame *
+am65_cpsw_nuss_tx_compl_packet_xdp(struct am65_cpsw_common *common,
+				   struct am65_cpsw_tx_chn *tx_chn,
+				   dma_addr_t desc_dma,
+				   struct net_device **ndev)
+{
+	struct am65_cpsw_ndev_priv *ndev_priv;
+	struct am65_cpsw_ndev_stats *stats;
+	struct cppi5_host_desc_t *desc_tx;
+	struct am65_cpsw_port *port;
+	struct xdp_frame *xdpf;
+	u32 port_id = 0;
+	void **swdata;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
+	cppi5_desc_get_tags_ids(&desc_tx->hdr, NULL, &port_id);
+	swdata = cppi5_hdesc_get_swdata(desc_tx);
+	xdpf = *(swdata);
+	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+
+	port = am65_common_get_port(common, port_id);
+	*ndev = port->ndev;
+
+	ndev_priv = netdev_priv(*ndev);
+	stats = this_cpu_ptr(ndev_priv->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->tx_packets++;
+	stats->tx_bytes += xdpf->len;
+	u64_stats_update_end(&stats->syncp);
+
+	return xdpf;
+}
+
 static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev,
 				   struct netdev_queue *netif_txq)
 {
@@ -988,11 +1356,13 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d
 static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 					   int chn, unsigned int budget, bool *tdown)
 {
+	enum am65_cpsw_tx_buf_type buf_type;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
 	unsigned int total_bytes = 0;
 	struct net_device *ndev;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
@@ -1013,10 +1383,21 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 			break;
 		}
 
-		skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
-		total_bytes = skb->len;
-		ndev = skb->dev;
-		napi_consume_skb(skb, budget);
+		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
+		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
+			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
+			ndev = skb->dev;
+			total_bytes = skb->len;
+			napi_consume_skb(skb, budget);
+		} else {
+			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
+								  desc_dma, &ndev);
+			total_bytes = xdpf->len;
+			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				xdp_return_frame(xdpf);
+		}
 		num_tx++;
 
 		netif_txq = netdev_get_tx_queue(ndev, chn);
@@ -1034,11 +1415,13 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
 					      int chn, unsigned int budget, bool *tdown)
 {
+	enum am65_cpsw_tx_buf_type buf_type;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
 	unsigned int total_bytes = 0;
 	struct net_device *ndev;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
@@ -1057,11 +1440,21 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
 			break;
 		}
 
-		skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma);
-
-		ndev = skb->dev;
-		total_bytes += skb->len;
-		napi_consume_skb(skb, budget);
+		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
+		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
+			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
+			ndev = skb->dev;
+			total_bytes += skb->len;
+			napi_consume_skb(skb, budget);
+		} else {
+			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
+								  desc_dma, &ndev);
+			total_bytes += xdpf->len;
+			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				xdp_return_frame(xdpf);
+		}
 		num_tx++;
 	}
 
@@ -1183,10 +1576,13 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 		goto busy_stop_q;
 	}
 
+	am65_cpsw_nuss_set_buf_type(tx_chn, first_desc,
+				    AM65_CPSW_TX_BUF_TYPE_SKB);
+
 	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 AM65_CPSW_NAV_PS_DATA_SIZE);
-	cppi5_desc_set_pktids(&first_desc->hdr, 0, 0x3FFF);
-	cppi5_hdesc_set_pkttype(first_desc, 0x7);
+	cppi5_desc_set_pktids(&first_desc->hdr, 0, AM65_CPSW_CPPI_TX_FLOW_ID);
+	cppi5_hdesc_set_pkttype(first_desc, AM65_CPSW_CPPI_TX_PKT_TYPE);
 	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, port->port_id);
 
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
@@ -1225,6 +1621,9 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 			goto busy_free_descs;
 		}
 
+		am65_cpsw_nuss_set_buf_type(tx_chn, next_desc,
+					    AM65_CPSW_TX_BUF_TYPE_SKB);
+
 		buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size,
 					   DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(tx_chn->dma_dev, buf_dma))) {
@@ -1334,7 +1733,6 @@ static int am65_cpsw_nuss_ndo_slave_set_mac_address(struct net_device *ndev,
 static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 				       struct ifreq *ifr)
 {
-	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	u32 ts_ctrl, seq_id, ts_ctrl_ltype2, ts_vlan_ltype;
 	struct hwtstamp_config cfg;
@@ -1358,11 +1756,6 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 	case HWTSTAMP_FILTER_NONE:
 		port->rx_ts_enabled = false;
 		break;
-	case HWTSTAMP_FILTER_ALL:
-	case HWTSTAMP_FILTER_SOME:
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
@@ -1372,10 +1765,13 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-	case HWTSTAMP_FILTER_NTP_ALL:
 		port->rx_ts_enabled = true;
-		cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		return -EOPNOTSUPP;
 	default:
 		return -ERANGE;
 	}
@@ -1405,6 +1801,10 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 		ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN |
 			   AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN;
 
+	if (port->rx_ts_enabled)
+		ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN |
+			   AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN;
+
 	writel(seq_id, port->port_base + AM65_CPSW_PORTN_REG_TS_SEQ_LTYPE_REG);
 	writel(ts_vlan_ltype, port->port_base +
 	       AM65_CPSW_PORTN_REG_TS_VLAN_LTYPE_REG);
@@ -1412,9 +1812,6 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 	       AM65_CPSW_PORTN_REG_TS_CTL_LTYPE2);
 	writel(ts_ctrl, port->port_base + AM65_CPSW_PORTN_REG_TS_CTL);
 
-	/* en/dis RX timestamp */
-	am65_cpts_rx_enable(common->cpts, port->rx_ts_enabled);
-
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
 
@@ -1431,7 +1828,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev,
 	cfg.tx_type = port->tx_ts_enabled ?
 		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
 	cfg.rx_filter = port->rx_ts_enabled ?
-			HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+			HWTSTAMP_FILTER_PTP_V2_EVENT : HWTSTAMP_FILTER_NONE;
 
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
@@ -1488,6 +1885,59 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev,
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
+static int am65_cpsw_xdp_prog_setup(struct net_device *ndev,
+				    struct bpf_prog *prog)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	bool running = netif_running(ndev);
+	struct bpf_prog *old_prog;
+
+	if (running)
+		am65_cpsw_nuss_ndo_slave_stop(ndev);
+
+	old_prog = xchg(&port->xdp_prog, prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (running)
+		return am65_cpsw_nuss_ndo_slave_open(ndev);
+
+	return 0;
+}
+
+static int am65_cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return am65_cpsw_xdp_prog_setup(ndev, bpf->prog);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int am65_cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+				  struct xdp_frame **frames, u32 flags)
+{
+	struct am65_cpsw_tx_chn *tx_chn;
+	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
+	int i, nxmit = 0;
+
+	tx_chn = &am65_ndev_to_common(ndev)->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES];
+	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+
+	__netif_tx_lock(netif_txq, cpu);
+	for (i = 0; i < n; i++) {
+		if (am65_cpsw_xdp_tx_frame(ndev, tx_chn, frames[i],
+					   AM65_CPSW_TX_BUF_TYPE_XDP_NDO))
+			break;
+		nxmit++;
+	}
+	__netif_tx_unlock(netif_txq);
+
+	return nxmit;
+}
+
 static const struct net_device_ops am65_cpsw_nuss_netdev_ops = {
 	.ndo_open		= am65_cpsw_nuss_ndo_slave_open,
 	.ndo_stop		= am65_cpsw_nuss_ndo_slave_stop,
@@ -1502,6 +1952,8 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = {
 	.ndo_eth_ioctl		= am65_cpsw_nuss_ndo_slave_ioctl,
 	.ndo_setup_tc           = am65_cpsw_qos_ndo_setup_tc,
 	.ndo_set_tx_maxrate	= am65_cpsw_qos_ndo_tx_p0_set_maxrate,
+	.ndo_bpf		= am65_cpsw_ndo_bpf,
+	.ndo_xdp_xmit		= am65_cpsw_ndo_xdp_xmit,
 };
 
 static void am65_cpsw_disable_phy(struct phy *phy)
@@ -1772,7 +2224,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 		.mode = K3_RINGACC_RING_MODE_RING,
 		.flags = 0
 	};
-	u32 hdesc_size;
+	u32 hdesc_size, hdesc_size_out;
 	int i, ret = 0;
 
 	hdesc_size = cppi5_hdesc_calc_size(true, AM65_CPSW_NAV_PS_DATA_SIZE,
@@ -1816,6 +2268,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 			goto err;
 		}
 
+		hdesc_size_out = k3_cppi_desc_pool_desc_size(tx_chn->desc_pool);
+		tx_chn->dsize_log2 = __fls(hdesc_size_out);
+		WARN_ON(hdesc_size_out != (1 << tx_chn->dsize_log2));
+
 		tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn);
 		if (tx_chn->irq < 0) {
 			dev_err(dev, "Failed to get tx dma irq %d\n",
@@ -1862,8 +2318,8 @@ static void am65_cpsw_nuss_free_rx_chns(void *data)
 static void am65_cpsw_nuss_remove_rx_chns(void *data)
 {
 	struct am65_cpsw_common *common = data;
-	struct am65_cpsw_rx_chn *rx_chn;
 	struct device *dev = common->dev;
+	struct am65_cpsw_rx_chn *rx_chn;
 
 	rx_chn = &common->rx_chns;
 	devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common);
@@ -1873,11 +2329,7 @@ static void am65_cpsw_nuss_remove_rx_chns(void *data)
 
 	netif_napi_del(&common->napi_rx);
 
-	if (!IS_ERR_OR_NULL(rx_chn->desc_pool))
-		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
-
-	if (!IS_ERR_OR_NULL(rx_chn->rx_chn))
-		k3_udma_glue_release_rx_chn(rx_chn->rx_chn);
+	am65_cpsw_nuss_free_rx_chns(common);
 
 	common->rx_flow_id_base = -1;
 }
@@ -1888,7 +2340,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 	struct k3_udma_glue_rx_channel_cfg rx_cfg = { 0 };
 	u32  max_desc_num = AM65_CPSW_MAX_RX_DESC;
 	struct device *dev = common->dev;
-	u32 hdesc_size;
+	u32 hdesc_size, hdesc_size_out;
 	u32 fdqring_id;
 	int i, ret = 0;
 
@@ -1920,6 +2372,17 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 		goto err;
 	}
 
+	hdesc_size_out = k3_cppi_desc_pool_desc_size(rx_chn->desc_pool);
+	rx_chn->dsize_log2 = __fls(hdesc_size_out);
+	WARN_ON(hdesc_size_out != (1 << rx_chn->dsize_log2));
+
+	rx_chn->page_pool = NULL;
+
+	rx_chn->pages = devm_kcalloc(dev, rx_chn->descs_num,
+				     sizeof(*rx_chn->pages), GFP_KERNEL);
+	if (!rx_chn->pages)
+		return -ENOMEM;
+
 	common->rx_flow_id_base =
 			k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn);
 	dev_info(dev, "set new flow-id-base %u\n", common->rx_flow_id_base);
@@ -2252,6 +2715,9 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 				  NETIF_F_HW_TC;
 	port->ndev->features = port->ndev->hw_features |
 			       NETIF_F_HW_VLAN_CTAG_FILTER;
+	port->ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+				   NETDEV_XDP_ACT_REDIRECT |
+				   NETDEV_XDP_ACT_NDO_XMIT;
 	port->ndev->vlan_features |=  NETIF_F_SG;
 	port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops;
 	port->ndev->ethtool_ops = &am65_cpsw_ethtool_ops_slave;
@@ -2315,6 +2781,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	if (ret)
 		dev_err(dev, "failed to add percpu stat free action %d\n", ret);
 
+	port->xdp_prog = NULL;
+
 	if (!common->dma_ndev)
 		common->dma_ndev = port->ndev;
 
@@ -2588,7 +3056,8 @@ static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port)
 }
 
 static int am65_cpsw_dl_switch_mode_set(struct devlink *dl, u32 id,
-					struct devlink_param_gset_ctx *ctx)
+					struct devlink_param_gset_ctx *ctx,
+					struct netlink_ext_ack *extack)
 {
 	struct am65_cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct am65_cpsw_common *cpsw = dl_priv->common;
@@ -2922,7 +3391,8 @@ static const struct am65_cpsw_pdata j784s4_cpswxg_pdata = {
 	.quirks = 0,
 	.ale_dev_id = "am64-cpswxg",
 	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
-	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_USXGMII),
+	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
+		       BIT(PHY_INTERFACE_MODE_USXGMII),
 };
 
 static const struct of_device_id am65_cpsw_nuss_of_mtable[] = {
@@ -2958,9 +3428,9 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	struct device_node *node;
 	struct resource *res;
 	struct clk *clk;
+	int ale_entries;
 	u64 id_temp;
 	int ret, i;
-	int ale_entries;
 
 	common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL);
 	if (!common)
@@ -3172,10 +3642,10 @@ static int am65_cpsw_nuss_suspend(struct device *dev)
 static int am65_cpsw_nuss_resume(struct device *dev)
 {
 	struct am65_cpsw_common *common = dev_get_drvdata(dev);
+	struct am65_cpsw_host *host_p = am65_common_get_host(common);
 	struct am65_cpsw_port *port;
 	struct net_device *ndev;
 	int i, ret;
-	struct am65_cpsw_host *host_p = am65_common_get_host(common);
 
 	ret = am65_cpsw_nuss_init_tx_chns(common);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 7da0492dc091..d8ce88dc9c89 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/soc/ti/k3-ringacc.h>
 #include <net/devlink.h>
+#include <net/xdp.h>
 #include "am65-cpsw-qos.h"
 
 struct am65_cpts;
@@ -56,10 +57,18 @@ struct am65_cpsw_port {
 	bool				rx_ts_enabled;
 	struct am65_cpsw_qos		qos;
 	struct devlink_port		devlink_port;
+	struct bpf_prog			*xdp_prog;
+	struct xdp_rxq_info		xdp_rxq;
 	/* Only for suspend resume context */
 	u32				vid_context;
 };
 
+enum am65_cpsw_tx_buf_type {
+	AM65_CPSW_TX_BUF_TYPE_SKB,
+	AM65_CPSW_TX_BUF_TYPE_XDP_TX,
+	AM65_CPSW_TX_BUF_TYPE_XDP_NDO,
+};
+
 struct am65_cpsw_host {
 	struct am65_cpsw_common		*common;
 	void __iomem			*port_base;
@@ -80,6 +89,7 @@ struct am65_cpsw_tx_chn {
 	int irq;
 	u32 id;
 	u32 descs_num;
+	unsigned char dsize_log2;
 	char tx_chn_name[128];
 	u32 rate_mbps;
 };
@@ -89,7 +99,10 @@ struct am65_cpsw_rx_chn {
 	struct device *dma_dev;
 	struct k3_cppi_desc_pool *desc_pool;
 	struct k3_udma_glue_rx_channel *rx_chn;
+	struct page_pool *page_pool;
+	struct page **pages;
 	u32 descs_num;
+	unsigned char dsize_log2;
 	int irq;
 };
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
index 816e73a3d6e4..fa96db7c1a13 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-qos.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -9,6 +9,7 @@
 
 #include <linux/pm_runtime.h>
 #include <linux/math.h>
+#include <linux/math64.h>
 #include <linux/time.h>
 #include <linux/units.h>
 #include <net/pkt_cls.h>
@@ -837,6 +838,7 @@ static int am65_cpsw_taprio_replace(struct net_device *ndev,
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	struct am65_cpts *cpts = common->cpts;
 	struct am65_cpsw_est *est_new;
+	u64 cur_time, n;
 	int ret, tact;
 
 	if (!netif_running(ndev)) {
@@ -888,13 +890,21 @@ static int am65_cpsw_taprio_replace(struct net_device *ndev,
 	if (tact == TACT_PROG)
 		am65_cpsw_timer_stop(ndev);
 
-	if (!est_new->taprio.base_time)
-		est_new->taprio.base_time = am65_cpts_ns_gettime(cpts);
-
 	am65_cpsw_port_est_get_buf_num(ndev, est_new);
 	am65_cpsw_est_set_sched_list(ndev, est_new);
 	am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf);
 
+	/* If the base-time is in the past, start schedule from the time:
+	 * base_time + (N*cycle_time)
+	 * where N is the smallest possible integer such that the above
+	 * time is in the future.
+	 */
+	cur_time = am65_cpts_ns_gettime(cpts);
+	if (est_new->taprio.base_time < cur_time) {
+		n = div64_u64(cur_time - est_new->taprio.base_time, est_new->taprio.cycle_time);
+		est_new->taprio.base_time += (n + 1) * est_new->taprio.cycle_time;
+	}
+
 	am65_cpsw_est_set(ndev, 1);
 
 	if (tact == TACT_PROG) {
@@ -1008,6 +1018,9 @@ static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		NL_SET_ERR_MSG_MOD(extack, "Not matching on eth address");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index f89716b1cfb6..59d6ab989c55 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -275,15 +275,13 @@ static bool am65_cpts_fifo_pop_event(struct am65_cpts *cpts,
 	return true;
 }
 
-static int am65_cpts_fifo_read(struct am65_cpts *cpts)
+static int __am65_cpts_fifo_read(struct am65_cpts *cpts)
 {
 	struct ptp_clock_event pevent;
 	struct am65_cpts_event *event;
 	bool schedule = false;
 	int i, type, ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&cpts->lock, flags);
 	for (i = 0; i < AM65_CPTS_FIFO_DEPTH; i++) {
 		event = list_first_entry_or_null(&cpts->pool,
 						 struct am65_cpts_event, list);
@@ -312,8 +310,7 @@ static int am65_cpts_fifo_read(struct am65_cpts *cpts)
 			event->tmo = jiffies +
 				msecs_to_jiffies(AM65_CPTS_EVENT_RX_TX_TIMEOUT);
 
-			list_del_init(&event->list);
-			list_add_tail(&event->list, &cpts->events);
+			list_move_tail(&event->list, &cpts->events);
 
 			dev_dbg(cpts->dev,
 				"AM65_CPTS_EV_TX e1:%08x e2:%08x t:%lld\n",
@@ -356,14 +353,24 @@ static int am65_cpts_fifo_read(struct am65_cpts *cpts)
 	}
 
 out:
-	spin_unlock_irqrestore(&cpts->lock, flags);
-
 	if (schedule)
 		ptp_schedule_worker(cpts->ptp_clock, 0);
 
 	return ret;
 }
 
+static int am65_cpts_fifo_read(struct am65_cpts *cpts)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	ret = __am65_cpts_fifo_read(cpts);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	return ret;
+}
+
 static u64 am65_cpts_gettime(struct am65_cpts *cpts,
 			     struct ptp_system_timestamp *sts)
 {
@@ -864,29 +871,6 @@ static long am65_cpts_ts_work(struct ptp_clock_info *ptp)
 	return delay;
 }
 
-/**
- * am65_cpts_rx_enable - enable rx timestamping
- * @cpts: cpts handle
- * @en: enable
- *
- * This functions enables rx packets timestamping. The CPTS can timestamp all
- * rx packets.
- */
-void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
-{
-	u32 val;
-
-	mutex_lock(&cpts->ptp_clk_lock);
-	val = am65_cpts_read32(cpts, control);
-	if (en)
-		val |= AM65_CPTS_CONTROL_TSTAMP_EN;
-	else
-		val &= ~AM65_CPTS_CONTROL_TSTAMP_EN;
-	am65_cpts_write32(cpts, val, control);
-	mutex_unlock(&cpts->ptp_clk_lock);
-}
-EXPORT_SYMBOL_GPL(am65_cpts_rx_enable);
-
 static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid)
 {
 	unsigned int ptp_class = ptp_classify_raw(skb);
@@ -911,6 +895,69 @@ static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid)
 	return 1;
 }
 
+static u64 am65_cpts_find_rx_ts(struct am65_cpts *cpts, u32 skb_mtype_seqid)
+{
+	struct list_head *this, *next;
+	struct am65_cpts_event *event;
+	unsigned long flags;
+	u32 mtype_seqid;
+	u64 ns = 0;
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	__am65_cpts_fifo_read(cpts);
+	list_for_each_safe(this, next, &cpts->events) {
+		event = list_entry(this, struct am65_cpts_event, list);
+		if (time_after(jiffies, event->tmo)) {
+			list_move(&event->list, &cpts->pool);
+			continue;
+		}
+
+		mtype_seqid = event->event1 &
+			      (AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK |
+			       AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK |
+			       AM65_CPTS_EVENT_1_EVENT_TYPE_MASK);
+
+		if (mtype_seqid == skb_mtype_seqid) {
+			ns = event->timestamp;
+			list_move(&event->list, &cpts->pool);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	return ns;
+}
+
+void am65_cpts_rx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb)
+{
+	struct am65_cpts_skb_cb_data *skb_cb = (struct am65_cpts_skb_cb_data *)skb->cb;
+	struct skb_shared_hwtstamps *ssh;
+	int ret;
+	u64 ns;
+
+	/* am65_cpts_rx_timestamp() is called before eth_type_trans(), so
+	 * skb MAC Hdr properties are not configured yet. Hence need to
+	 * reset skb MAC header here
+	 */
+	skb_reset_mac_header(skb);
+	ret = am65_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
+		return; /* if not PTP class packet */
+
+	skb_cb->skb_mtype_seqid |= (AM65_CPTS_EV_RX << AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT);
+
+	dev_dbg(cpts->dev, "%s mtype seqid %08x\n", __func__, skb_cb->skb_mtype_seqid);
+
+	ns = am65_cpts_find_rx_ts(cpts, skb_cb->skb_mtype_seqid);
+	if (!ns)
+		return;
+
+	ssh = skb_hwtstamps(skb);
+	memset(ssh, 0, sizeof(*ssh));
+	ssh->hwtstamp = ns_to_ktime(ns);
+}
+EXPORT_SYMBOL_GPL(am65_cpts_rx_timestamp);
+
 /**
  * am65_cpts_tx_timestamp - save tx packet for timestamping
  * @cpts: cpts handle
diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h
index 6e14df0be113..6099d772799d 100644
--- a/drivers/net/ethernet/ti/am65-cpts.h
+++ b/drivers/net/ethernet/ti/am65-cpts.h
@@ -22,9 +22,9 @@ void am65_cpts_release(struct am65_cpts *cpts);
 struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs,
 				   struct device_node *node);
 int am65_cpts_phc_index(struct am65_cpts *cpts);
+void am65_cpts_rx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
 void am65_cpts_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
 void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
-void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en);
 u64 am65_cpts_ns_gettime(struct am65_cpts *cpts);
 int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx,
 			  struct am65_cpts_estf_cfg *cfg);
@@ -48,17 +48,18 @@ static inline int am65_cpts_phc_index(struct am65_cpts *cpts)
 	return -1;
 }
 
-static inline void am65_cpts_tx_timestamp(struct am65_cpts *cpts,
+static inline void am65_cpts_rx_timestamp(struct am65_cpts *cpts,
 					  struct sk_buff *skb)
 {
 }
 
-static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts,
-					       struct sk_buff *skb)
+static inline void am65_cpts_tx_timestamp(struct am65_cpts *cpts,
+					  struct sk_buff *skb)
 {
 }
 
-static inline void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
+static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts,
+					       struct sk_buff *skb)
 {
 }
 
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 087dcb67505a..2baa198ebfa0 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1625,7 +1625,8 @@ static int cpsw_dl_switch_mode_get(struct devlink *dl, u32 id,
 }
 
 static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct cpsw_common *cpsw = dl_priv->cpsw;
@@ -1762,7 +1763,8 @@ static int cpsw_dl_ale_ctrl_get(struct devlink *dl, u32 id,
 }
 
 static int cpsw_dl_ale_ctrl_set(struct devlink *dl, u32 id,
-				struct devlink_param_gset_ctx *ctx)
+				struct devlink_param_gset_ctx *ctx,
+				struct netlink_ext_ack *extack)
 {
 	struct cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct cpsw_common *cpsw = dl_priv->cpsw;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 764ed298b570..6fe4edabba44 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1404,6 +1404,9 @@ static int cpsw_qos_clsflower_add_policer(struct cpsw_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_rule_match_has_control_flags(rule, extack))
+		return -EOPNOTSUPP;
+
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		NL_SET_ERR_MSG_MOD(extack, "Not matching on eth address");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
index 6df53ab17fbc..79ba47bb3602 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
@@ -274,6 +274,16 @@ static void rx_class_set_or(struct regmap *miig_rt, int slice, int n,
 	regmap_write(miig_rt, offset, data);
 }
 
+static u32 rx_class_get_or(struct regmap *miig_rt, int slice, int n)
+{
+	u32 offset, val;
+
+	offset = RX_CLASS_N_REG(slice, n, RX_CLASS_OR_EN);
+	regmap_read(miig_rt, offset, &val);
+
+	return val;
+}
+
 void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac)
 {
 	regmap_write(miig_rt, MAC_INTERFACE_0, (u32)(mac[0] | mac[1] << 8 |
@@ -288,6 +298,26 @@ void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac)
 	regmap_write(miig_rt, offs[slice].mac1, (u32)(mac[4] | mac[5] << 8));
 }
 
+static void icssg_class_ft1_add_mcast(struct regmap *miig_rt, int slice,
+				      int slot, const u8 *addr, const u8 *mask)
+{
+	u32 val;
+	int i;
+
+	WARN(slot >= FT1_NUM_SLOTS, "invalid slot: %d\n", slot);
+
+	rx_class_ft1_set_da(miig_rt, slice, slot, addr);
+	rx_class_ft1_set_da_mask(miig_rt, slice, slot, mask);
+	rx_class_ft1_cfg_set_type(miig_rt, slice, slot, FT1_CFG_TYPE_EQ);
+
+	/* Enable the FT1 slot in OR enable for all classifiers */
+	for (i = 0; i < ICSSG_NUM_CLASSIFIERS_IN_USE; i++) {
+		val = rx_class_get_or(miig_rt, slice, i);
+		val |= RX_CLASS_FT_FT1_MATCH(slot);
+		rx_class_set_or(miig_rt, slice, i, val);
+	}
+}
+
 /* disable all RX traffic */
 void icssg_class_disable(struct regmap *miig_rt, int slice)
 {
@@ -331,30 +361,95 @@ void icssg_class_disable(struct regmap *miig_rt, int slice)
 	regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0);
 }
 
-void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti)
+void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti,
+			 bool is_sr1)
 {
+	int num_classifiers = is_sr1 ? ICSSG_NUM_CLASSIFIERS_IN_USE : 1;
 	u32 data;
+	int n;
 
 	/* defaults */
 	icssg_class_disable(miig_rt, slice);
 
 	/* Setup Classifier */
-	/* match on Broadcast or MAC_PRU address */
-	data = RX_CLASS_FT_BC | RX_CLASS_FT_DA_P;
+	for (n = 0; n < num_classifiers; n++) {
+		/* match on Broadcast or MAC_PRU address */
+		data = RX_CLASS_FT_BC | RX_CLASS_FT_DA_P;
 
-	/* multicast */
-	if (allmulti)
-		data |= RX_CLASS_FT_MC;
+		/* multicast */
+		if (allmulti)
+			data |= RX_CLASS_FT_MC;
 
-	rx_class_set_or(miig_rt, slice, 0, data);
+		rx_class_set_or(miig_rt, slice, n, data);
 
-	/* set CFG1 for OR_OR_AND for classifier */
-	rx_class_sel_set_type(miig_rt, slice, 0, RX_CLASS_SEL_TYPE_OR_OR_AND);
+		/* set CFG1 for OR_OR_AND for classifier */
+		rx_class_sel_set_type(miig_rt, slice, n,
+				      RX_CLASS_SEL_TYPE_OR_OR_AND);
+	}
 
 	/* clear CFG2 */
 	regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0);
 }
 
+void icssg_class_promiscuous_sr1(struct regmap *miig_rt, int slice)
+{
+	u32 data, offset;
+	int n;
+
+	/* defaults */
+	icssg_class_disable(miig_rt, slice);
+
+	/* Setup Classifier */
+	for (n = 0; n < ICSSG_NUM_CLASSIFIERS_IN_USE; n++) {
+		/* set RAW_MASK to bypass filters */
+		offset = RX_CLASS_GATES_N_REG(slice, n);
+		regmap_read(miig_rt, offset, &data);
+		data |= RX_CLASS_GATES_RAW_MASK;
+		regmap_write(miig_rt, offset, data);
+	}
+}
+
+void icssg_class_add_mcast_sr1(struct regmap *miig_rt, int slice,
+			       struct net_device *ndev)
+{
+	u8 mask_addr[6] = { 0, 0, 0, 0, 0, 0xff };
+	struct netdev_hw_addr *ha;
+	int slot = 2;
+
+	rx_class_ft1_set_start_len(miig_rt, slice, 0, 6);
+	/* reserve first 2 slots for
+	 *	1) 01-80-C2-00-00-XX Known Service Ethernet Multicast addresses
+	 *	2) 01-00-5e-00-00-XX Local Network Control Block
+	 *			      (224.0.0.0 - 224.0.0.255  (224.0.0/24))
+	 */
+	icssg_class_ft1_add_mcast(miig_rt, slice, 0,
+				  eth_reserved_addr_base, mask_addr);
+	icssg_class_ft1_add_mcast(miig_rt, slice, 1,
+				  eth_ipv4_mcast_addr_base, mask_addr);
+	mask_addr[5] = 0;
+	netdev_for_each_mc_addr(ha, ndev) {
+		/* skip addresses matching reserved slots */
+		if (!memcmp(eth_reserved_addr_base, ha->addr, 5) ||
+		    !memcmp(eth_ipv4_mcast_addr_base, ha->addr, 5)) {
+			netdev_dbg(ndev, "mcast skip %pM\n", ha->addr);
+			continue;
+		}
+
+		if (slot >= FT1_NUM_SLOTS) {
+			netdev_dbg(ndev,
+				   "can't add more than %d MC addresses, enabling allmulti\n",
+				   FT1_NUM_SLOTS);
+			icssg_class_default(miig_rt, slice, 1, true);
+			break;
+		}
+
+		netdev_dbg(ndev, "mcast add %pM\n", ha->addr);
+		icssg_class_ft1_add_mcast(miig_rt, slice, slot,
+					  ha->addr, mask_addr);
+		slot++;
+	}
+}
+
 /* required for SAV check */
 void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr)
 {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
new file mode 100644
index 000000000000..088ab8076db4
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -0,0 +1,1252 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Texas Instruments ICSSG Ethernet Driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) Siemens AG, 2024
+ *
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/dma/ti-cppi5.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/remoteproc/pruss.h>
+#include <linux/regmap.h>
+#include <linux/remoteproc.h>
+
+#include "icssg_prueth.h"
+#include "../k3-cppi-desc-pool.h"
+
+/* Netif debug messages possible */
+#define PRUETH_EMAC_DEBUG       (NETIF_MSG_DRV | \
+				 NETIF_MSG_PROBE | \
+				 NETIF_MSG_LINK | \
+				 NETIF_MSG_TIMER | \
+				 NETIF_MSG_IFDOWN | \
+				 NETIF_MSG_IFUP | \
+				 NETIF_MSG_RX_ERR | \
+				 NETIF_MSG_TX_ERR | \
+				 NETIF_MSG_TX_QUEUED | \
+				 NETIF_MSG_INTR | \
+				 NETIF_MSG_TX_DONE | \
+				 NETIF_MSG_RX_STATUS | \
+				 NETIF_MSG_PKTDATA | \
+				 NETIF_MSG_HW | \
+				 NETIF_MSG_WOL)
+
+#define prueth_napi_to_emac(napi) container_of(napi, struct prueth_emac, napi_rx)
+
+void prueth_cleanup_rx_chns(struct prueth_emac *emac,
+			    struct prueth_rx_chn *rx_chn,
+			    int max_rflows)
+{
+	if (rx_chn->desc_pool)
+		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
+
+	if (rx_chn->rx_chn)
+		k3_udma_glue_release_rx_chn(rx_chn->rx_chn);
+}
+
+void prueth_cleanup_tx_chns(struct prueth_emac *emac)
+{
+	int i;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		if (tx_chn->desc_pool)
+			k3_cppi_desc_pool_destroy(tx_chn->desc_pool);
+
+		if (tx_chn->tx_chn)
+			k3_udma_glue_release_tx_chn(tx_chn->tx_chn);
+
+		/* Assume prueth_cleanup_tx_chns() is called at the
+		 * end after all channel resources are freed
+		 */
+		memset(tx_chn, 0, sizeof(*tx_chn));
+	}
+}
+
+void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		if (tx_chn->irq)
+			free_irq(tx_chn->irq, tx_chn);
+		netif_napi_del(&tx_chn->napi_tx);
+	}
+}
+
+void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
+		      struct cppi5_host_desc_t *desc)
+{
+	struct cppi5_host_desc_t *first_desc, *next_desc;
+	dma_addr_t buf_dma, next_desc_dma;
+	u32 buf_dma_len;
+
+	first_desc = desc;
+	next_desc = first_desc;
+
+	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len,
+			 DMA_TO_DEVICE);
+
+	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
+	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+	while (next_desc_dma) {
+		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						       next_desc_dma);
+		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
+
+		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
+			       DMA_TO_DEVICE);
+
+		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
+		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
+
+		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
+	}
+
+	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
+}
+
+int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
+			     int budget, bool *tdown)
+{
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_tx;
+	struct netdev_queue *netif_txq;
+	struct prueth_tx_chn *tx_chn;
+	unsigned int total_bytes = 0;
+	struct sk_buff *skb;
+	dma_addr_t desc_dma;
+	int res, num_tx = 0;
+	void **swdata;
+
+	tx_chn = &emac->tx_chns[chn];
+
+	while (true) {
+		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
+		if (res == -ENODATA)
+			break;
+
+		/* teardown completion */
+		if (cppi5_desc_is_tdcm(desc_dma)) {
+			if (atomic_dec_and_test(&emac->tdown_cnt))
+				complete(&emac->tdown_complete);
+			*tdown = true;
+			break;
+		}
+
+		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						     desc_dma);
+		swdata = cppi5_hdesc_get_swdata(desc_tx);
+
+		/* was this command's TX complete? */
+		if (emac->is_sr1 && *(swdata) == emac->cmd_data) {
+			prueth_xmit_free(tx_chn, desc_tx);
+			continue;
+		}
+
+		skb = *(swdata);
+		prueth_xmit_free(tx_chn, desc_tx);
+
+		ndev = skb->dev;
+		ndev->stats.tx_packets++;
+		ndev->stats.tx_bytes += skb->len;
+		total_bytes += skb->len;
+		napi_consume_skb(skb, budget);
+		num_tx++;
+	}
+
+	if (!num_tx)
+		return 0;
+
+	netif_txq = netdev_get_tx_queue(ndev, chn);
+	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
+
+	if (netif_tx_queue_stopped(netif_txq)) {
+		/* If the TX queue was stopped, wake it now
+		 * if we have enough room.
+		 */
+		__netif_tx_lock(netif_txq, smp_processor_id());
+		if (netif_running(ndev) &&
+		    (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
+		     MAX_SKB_FRAGS))
+			netif_tx_wake_queue(netif_txq);
+		__netif_tx_unlock(netif_txq);
+	}
+
+	return num_tx;
+}
+
+static enum hrtimer_restart emac_tx_timer_callback(struct hrtimer *timer)
+{
+	struct prueth_tx_chn *tx_chns =
+			container_of(timer, struct prueth_tx_chn, tx_hrtimer);
+
+	enable_irq(tx_chns->irq);
+	return HRTIMER_NORESTART;
+}
+
+static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget)
+{
+	struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx);
+	struct prueth_emac *emac = tx_chn->emac;
+	bool tdown = false;
+	int num_tx_packets;
+
+	num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget,
+						  &tdown);
+
+	if (num_tx_packets >= budget)
+		return budget;
+
+	if (napi_complete_done(napi_tx, num_tx_packets)) {
+		if (unlikely(tx_chn->tx_pace_timeout_ns && !tdown)) {
+			hrtimer_start(&tx_chn->tx_hrtimer,
+				      ns_to_ktime(tx_chn->tx_pace_timeout_ns),
+				      HRTIMER_MODE_REL_PINNED);
+		} else {
+			enable_irq(tx_chn->irq);
+		}
+	}
+
+	return num_tx_packets;
+}
+
+static irqreturn_t prueth_tx_irq(int irq, void *dev_id)
+{
+	struct prueth_tx_chn *tx_chn = dev_id;
+
+	disable_irq_nosync(irq);
+	napi_schedule(&tx_chn->napi_tx);
+
+	return IRQ_HANDLED;
+}
+
+int prueth_ndev_add_tx_napi(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int i, ret;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll);
+		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL_PINNED);
+		tx_chn->tx_hrtimer.function = &emac_tx_timer_callback;
+		ret = request_irq(tx_chn->irq, prueth_tx_irq,
+				  IRQF_TRIGGER_HIGH, tx_chn->name,
+				  tx_chn);
+		if (ret) {
+			netif_napi_del(&tx_chn->napi_tx);
+			dev_err(prueth->dev, "unable to request TX IRQ %d\n",
+				tx_chn->irq);
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	prueth_ndev_del_tx_napi(emac, i);
+	return ret;
+}
+
+int prueth_init_tx_chns(struct prueth_emac *emac)
+{
+	static const struct k3_ring_cfg ring_cfg = {
+		.elm_size = K3_RINGACC_RING_ELSIZE_8,
+		.mode = K3_RINGACC_RING_MODE_RING,
+		.flags = 0,
+		.size = PRUETH_MAX_TX_DESC,
+	};
+	struct k3_udma_glue_tx_channel_cfg tx_cfg;
+	struct device *dev = emac->prueth->dev;
+	struct net_device *ndev = emac->ndev;
+	int ret, slice, i;
+	u32 hdesc_size;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0)
+		return slice;
+
+	init_completion(&emac->tdown_complete);
+
+	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
+					   PRUETH_NAV_SW_DATA_SIZE);
+	memset(&tx_cfg, 0, sizeof(tx_cfg));
+	tx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
+	tx_cfg.tx_cfg = ring_cfg;
+	tx_cfg.txcq_cfg = ring_cfg;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
+
+		/* To differentiate channels for SLICE0 vs SLICE1 */
+		snprintf(tx_chn->name, sizeof(tx_chn->name),
+			 "tx%d-%d", slice, i);
+
+		tx_chn->emac = emac;
+		tx_chn->id = i;
+		tx_chn->descs_num = PRUETH_MAX_TX_DESC;
+
+		tx_chn->tx_chn =
+			k3_udma_glue_request_tx_chn(dev, tx_chn->name,
+						    &tx_cfg);
+		if (IS_ERR(tx_chn->tx_chn)) {
+			ret = PTR_ERR(tx_chn->tx_chn);
+			tx_chn->tx_chn = NULL;
+			netdev_err(ndev,
+				   "Failed to request tx dma ch: %d\n", ret);
+			goto fail;
+		}
+
+		tx_chn->dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn->tx_chn);
+		tx_chn->desc_pool =
+			k3_cppi_desc_pool_create_name(tx_chn->dma_dev,
+						      tx_chn->descs_num,
+						      hdesc_size,
+						      tx_chn->name);
+		if (IS_ERR(tx_chn->desc_pool)) {
+			ret = PTR_ERR(tx_chn->desc_pool);
+			tx_chn->desc_pool = NULL;
+			netdev_err(ndev, "Failed to create tx pool: %d\n", ret);
+			goto fail;
+		}
+
+		ret = k3_udma_glue_tx_get_irq(tx_chn->tx_chn);
+		if (ret < 0) {
+			netdev_err(ndev, "failed to get tx irq\n");
+			goto fail;
+		}
+		tx_chn->irq = ret;
+
+		snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d",
+			 dev_name(dev), tx_chn->id);
+	}
+
+	return 0;
+
+fail:
+	prueth_cleanup_tx_chns(emac);
+	return ret;
+}
+
+int prueth_init_rx_chns(struct prueth_emac *emac,
+			struct prueth_rx_chn *rx_chn,
+			char *name, u32 max_rflows,
+			u32 max_desc_num)
+{
+	struct k3_udma_glue_rx_channel_cfg rx_cfg;
+	struct device *dev = emac->prueth->dev;
+	struct net_device *ndev = emac->ndev;
+	u32 fdqring_id, hdesc_size;
+	int i, ret = 0, slice;
+	int flow_id_base;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0)
+		return slice;
+
+	/* To differentiate channels for SLICE0 vs SLICE1 */
+	snprintf(rx_chn->name, sizeof(rx_chn->name), "%s%d", name, slice);
+
+	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
+					   PRUETH_NAV_SW_DATA_SIZE);
+	memset(&rx_cfg, 0, sizeof(rx_cfg));
+	rx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
+	rx_cfg.flow_id_num = max_rflows;
+	rx_cfg.flow_id_base = -1; /* udmax will auto select flow id base */
+
+	/* init all flows */
+	rx_chn->dev = dev;
+	rx_chn->descs_num = max_desc_num;
+
+	rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, rx_chn->name,
+						     &rx_cfg);
+	if (IS_ERR(rx_chn->rx_chn)) {
+		ret = PTR_ERR(rx_chn->rx_chn);
+		rx_chn->rx_chn = NULL;
+		netdev_err(ndev, "Failed to request rx dma ch: %d\n", ret);
+		goto fail;
+	}
+
+	rx_chn->dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn->rx_chn);
+	rx_chn->desc_pool = k3_cppi_desc_pool_create_name(rx_chn->dma_dev,
+							  rx_chn->descs_num,
+							  hdesc_size,
+							  rx_chn->name);
+	if (IS_ERR(rx_chn->desc_pool)) {
+		ret = PTR_ERR(rx_chn->desc_pool);
+		rx_chn->desc_pool = NULL;
+		netdev_err(ndev, "Failed to create rx pool: %d\n", ret);
+		goto fail;
+	}
+
+	flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn);
+	if (emac->is_sr1 && !strcmp(name, "rxmgm")) {
+		emac->rx_mgm_flow_id_base = flow_id_base;
+		netdev_dbg(ndev, "mgm flow id base = %d\n", flow_id_base);
+	} else {
+		emac->rx_flow_id_base = flow_id_base;
+		netdev_dbg(ndev, "flow id base = %d\n", flow_id_base);
+	}
+
+	fdqring_id = K3_RINGACC_RING_ID_ANY;
+	for (i = 0; i < rx_cfg.flow_id_num; i++) {
+		struct k3_ring_cfg rxring_cfg = {
+			.elm_size = K3_RINGACC_RING_ELSIZE_8,
+			.mode = K3_RINGACC_RING_MODE_RING,
+			.flags = 0,
+		};
+		struct k3_ring_cfg fdqring_cfg = {
+			.elm_size = K3_RINGACC_RING_ELSIZE_8,
+			.flags = K3_RINGACC_RING_SHARED,
+		};
+		struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = {
+			.rx_cfg = rxring_cfg,
+			.rxfdq_cfg = fdqring_cfg,
+			.ring_rxq_id = K3_RINGACC_RING_ID_ANY,
+			.src_tag_lo_sel =
+				K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG,
+		};
+
+		rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
+		rx_flow_cfg.rx_cfg.size = max_desc_num;
+		rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
+		rx_flow_cfg.rxfdq_cfg.mode = emac->prueth->pdata.fdqring_mode;
+
+		ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn,
+						i, &rx_flow_cfg);
+		if (ret) {
+			netdev_err(ndev, "Failed to init rx flow%d %d\n",
+				   i, ret);
+			goto fail;
+		}
+		if (!i)
+			fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
+								     i);
+		ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
+		if (ret <= 0) {
+			if (!ret)
+				ret = -ENXIO;
+			netdev_err(ndev, "Failed to get rx dma irq");
+			goto fail;
+		}
+		rx_chn->irq[i] = ret;
+	}
+
+	return 0;
+
+fail:
+	prueth_cleanup_rx_chns(emac, rx_chn, max_rflows);
+	return ret;
+}
+
+int prueth_dma_rx_push(struct prueth_emac *emac,
+		       struct sk_buff *skb,
+		       struct prueth_rx_chn *rx_chn)
+{
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_rx;
+	u32 pkt_len = skb_tailroom(skb);
+	dma_addr_t desc_dma;
+	dma_addr_t buf_dma;
+	void **swdata;
+
+	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
+	if (!desc_rx) {
+		netdev_err(ndev, "rx push: failed to allocate descriptor\n");
+		return -ENOMEM;
+	}
+	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
+
+	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
+		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+		netdev_err(ndev, "rx push: failed to map rx pkt buffer\n");
+		return -EINVAL;
+	}
+
+	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
+
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	*swdata = skb;
+
+	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0,
+					desc_rx, desc_dma);
+}
+
+u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns)
+{
+	u32 iepcount_lo, iepcount_hi, hi_rollover_count;
+	u64 ns;
+
+	iepcount_lo = lo & GENMASK(19, 0);
+	iepcount_hi = (hi & GENMASK(11, 0)) << 12 | lo >> 20;
+	hi_rollover_count = hi >> 11;
+
+	ns = ((u64)hi_rollover_count) << 23 | (iepcount_hi + hi_sw);
+	ns = ns * cycle_time_ns + iepcount_lo;
+
+	return ns;
+}
+
+void emac_rx_timestamp(struct prueth_emac *emac,
+		       struct sk_buff *skb, u32 *psdata)
+{
+	struct skb_shared_hwtstamps *ssh;
+	u64 ns;
+
+	if (emac->is_sr1) {
+		ns = (u64)psdata[1] << 32 | psdata[0];
+	} else {
+		u32 hi_sw = readl(emac->prueth->shram.va +
+				  TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET);
+		ns = icssg_ts_to_ns(hi_sw, psdata[1], psdata[0],
+				    IEP_DEFAULT_CYCLE_TIME_NS);
+	}
+
+	ssh = skb_hwtstamps(skb);
+	memset(ssh, 0, sizeof(*ssh));
+	ssh->hwtstamp = ns_to_ktime(ns);
+}
+
+static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
+{
+	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
+	u32 buf_dma_len, pkt_len, port_id = 0;
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb, *new_skb;
+	dma_addr_t desc_dma, buf_dma;
+	void **swdata;
+	u32 *psdata;
+	int ret;
+
+	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
+	if (ret) {
+		if (ret != -ENODATA)
+			netdev_err(ndev, "rx pop: failed: %d\n", ret);
+		return ret;
+	}
+
+	if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */
+		return 0;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+
+	psdata = cppi5_hdesc_get_psdata(desc_rx);
+	/* RX HW timestamp */
+	if (emac->rx_ts_enabled)
+		emac_rx_timestamp(emac, skb, psdata);
+
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
+	/* firmware adds 4 CRC bytes, strip them */
+	pkt_len -= 4;
+	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	skb->dev = ndev;
+	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
+	/* if allocation fails we drop the packet but push the
+	 * descriptor back to the ring with old skb to prevent a stall
+	 */
+	if (!new_skb) {
+		ndev->stats.rx_dropped++;
+		new_skb = skb;
+	} else {
+		/* send the filled skb up the n/w stack */
+		skb_put(skb, pkt_len);
+		skb->protocol = eth_type_trans(skb, ndev);
+		napi_gro_receive(&emac->napi_rx, skb);
+		ndev->stats.rx_bytes += pkt_len;
+		ndev->stats.rx_packets++;
+	}
+
+	/* queue another RX DMA */
+	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns);
+	if (WARN_ON(ret < 0)) {
+		dev_kfree_skb_any(new_skb);
+		ndev->stats.rx_errors++;
+		ndev->stats.rx_dropped++;
+	}
+
+	return ret;
+}
+
+static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct prueth_rx_chn *rx_chn = data;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb;
+	dma_addr_t buf_dma;
+	u32 buf_dma_len;
+	void **swdata;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len,
+			 DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	dev_kfree_skb_any(skb);
+}
+
+static int prueth_tx_ts_cookie_get(struct prueth_emac *emac)
+{
+	int i;
+
+	/* search and get the next free slot */
+	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
+		if (!emac->tx_ts_skb[i]) {
+			emac->tx_ts_skb[i] = ERR_PTR(-EBUSY); /* reserve slot */
+			return i;
+		}
+	}
+
+	return -EBUSY;
+}
+
+/**
+ * emac_ndo_start_xmit - EMAC Transmit function
+ * @skb: SKB pointer
+ * @ndev: EMAC network adapter
+ *
+ * Called by the system to transmit a packet  - we queue the packet in
+ * EMAC hardware transmit queue
+ * Doesn't wait for completion we'll check for TX completion in
+ * emac_tx_complete_packets().
+ *
+ * Return: enum netdev_tx
+ */
+enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct netdev_queue *netif_txq;
+	struct prueth_tx_chn *tx_chn;
+	dma_addr_t desc_dma, buf_dma;
+	int i, ret = 0, q_idx;
+	bool in_tx_ts = 0;
+	int tx_ts_cookie;
+	void **swdata;
+	u32 pkt_len;
+	u32 *epib;
+
+	pkt_len = skb_headlen(skb);
+	q_idx = skb_get_queue_mapping(skb);
+
+	tx_chn = &emac->tx_chns[q_idx];
+	netif_txq = netdev_get_tx_queue(ndev, q_idx);
+
+	/* Map the linear buffer */
+	buf_dma = dma_map_single(tx_chn->dma_dev, skb->data, pkt_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+		netdev_err(ndev, "tx: failed to map skb buffer\n");
+		ret = NETDEV_TX_OK;
+		goto drop_free_skb;
+	}
+
+	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (!first_desc) {
+		netdev_dbg(ndev, "tx: failed to allocate descriptor\n");
+		dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE);
+		goto drop_stop_q_busy;
+	}
+
+	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(first_desc, 0);
+	epib = first_desc->epib;
+	epib[0] = 0;
+	epib[1] = 0;
+	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+	    emac->tx_ts_enabled) {
+		tx_ts_cookie = prueth_tx_ts_cookie_get(emac);
+		if (tx_ts_cookie >= 0) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			/* Request TX timestamp */
+			epib[0] = (u32)tx_ts_cookie;
+			epib[1] = 0x80000000;	/* TX TS request */
+			emac->tx_ts_skb[tx_ts_cookie] = skb_get(skb);
+			in_tx_ts = 1;
+		}
+	}
+
+	/* set dst tag to indicate internal qid at the firmware which is at
+	 * bit8..bit15. bit0..bit7 indicates port num for directed
+	 * packets in case of switch mode operation
+	 */
+	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
+	swdata = cppi5_hdesc_get_swdata(first_desc);
+	*swdata = skb;
+
+	/* Handle the case where skb is fragmented in pages */
+	cur_desc = first_desc;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		u32 frag_size = skb_frag_size(frag);
+
+		next_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+		if (!next_desc) {
+			netdev_err(ndev,
+				   "tx: failed to allocate frag. descriptor\n");
+			goto free_desc_stop_q_busy_cleanup_tx_ts;
+		}
+
+		buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+			netdev_err(ndev, "tx: Failed to map skb page\n");
+			k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
+			ret = NETDEV_TX_OK;
+			goto cleanup_tx_ts;
+		}
+
+		cppi5_hdesc_reset_hbdesc(next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+		cppi5_hdesc_attach_buf(next_desc,
+				       buf_dma, frag_size, buf_dma, frag_size);
+
+		desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool,
+						      next_desc);
+		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma);
+		cppi5_hdesc_link_hbdesc(cur_desc, desc_dma);
+
+		pkt_len += frag_size;
+		cur_desc = next_desc;
+	}
+	WARN_ON_ONCE(pkt_len != skb->len);
+
+	/* report bql before sending packet */
+	netdev_tx_sent_queue(netif_txq, pkt_len);
+
+	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
+	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
+	/* cppi5_desc_dump(first_desc, 64); */
+
+	skb_tx_timestamp(skb);  /* SW timestamp if SKBTX_IN_PROGRESS not set */
+	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (ret) {
+		netdev_err(ndev, "tx: push failed: %d\n", ret);
+		goto drop_free_descs;
+	}
+
+	if (in_tx_ts)
+		atomic_inc(&emac->tx_ts_pending);
+
+	if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) {
+		netif_tx_stop_queue(netif_txq);
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+
+		if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
+		    MAX_SKB_FRAGS)
+			netif_tx_wake_queue(netif_txq);
+	}
+
+	return NETDEV_TX_OK;
+
+cleanup_tx_ts:
+	if (in_tx_ts) {
+		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
+		emac->tx_ts_skb[tx_ts_cookie] = NULL;
+	}
+
+drop_free_descs:
+	prueth_xmit_free(tx_chn, first_desc);
+
+drop_free_skb:
+	dev_kfree_skb_any(skb);
+
+	/* error */
+	ndev->stats.tx_dropped++;
+	netdev_err(ndev, "tx: error: %d\n", ret);
+
+	return ret;
+
+free_desc_stop_q_busy_cleanup_tx_ts:
+	if (in_tx_ts) {
+		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
+		emac->tx_ts_skb[tx_ts_cookie] = NULL;
+	}
+	prueth_xmit_free(tx_chn, first_desc);
+
+drop_stop_q_busy:
+	netif_tx_stop_queue(netif_txq);
+	return NETDEV_TX_BUSY;
+}
+
+static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
+{
+	struct prueth_tx_chn *tx_chn = data;
+	struct cppi5_host_desc_t *desc_tx;
+	struct sk_buff *skb;
+	void **swdata;
+
+	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
+	swdata = cppi5_hdesc_get_swdata(desc_tx);
+	skb = *(swdata);
+	prueth_xmit_free(tx_chn, desc_tx);
+
+	dev_kfree_skb_any(skb);
+}
+
+irqreturn_t prueth_rx_irq(int irq, void *dev_id)
+{
+	struct prueth_emac *emac = dev_id;
+
+	disable_irq_nosync(irq);
+	napi_schedule(&emac->napi_rx);
+
+	return IRQ_HANDLED;
+}
+
+void prueth_emac_stop(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice;
+
+	switch (emac->port_id) {
+	case PRUETH_PORT_MII0:
+		slice = ICSS_SLICE0;
+		break;
+	case PRUETH_PORT_MII1:
+		slice = ICSS_SLICE1;
+		break;
+	default:
+		netdev_err(emac->ndev, "invalid port\n");
+		return;
+	}
+
+	emac->fw_running = 0;
+	if (!emac->is_sr1)
+		rproc_shutdown(prueth->txpru[slice]);
+	rproc_shutdown(prueth->rtu[slice]);
+	rproc_shutdown(prueth->pru[slice]);
+}
+
+void prueth_cleanup_tx_ts(struct prueth_emac *emac)
+{
+	int i;
+
+	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
+		if (emac->tx_ts_skb[i]) {
+			dev_kfree_skb_any(emac->tx_ts_skb[i]);
+			emac->tx_ts_skb[i] = NULL;
+		}
+	}
+}
+
+int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget)
+{
+	struct prueth_emac *emac = prueth_napi_to_emac(napi_rx);
+	int rx_flow = emac->is_sr1 ?
+		PRUETH_RX_FLOW_DATA_SR1 : PRUETH_RX_FLOW_DATA;
+	int flow = emac->is_sr1 ?
+		PRUETH_MAX_RX_FLOWS_SR1 : PRUETH_MAX_RX_FLOWS;
+	int num_rx = 0;
+	int cur_budget;
+	int ret;
+
+	while (flow--) {
+		cur_budget = budget - num_rx;
+
+		while (cur_budget--) {
+			ret = emac_rx_packet(emac, flow);
+			if (ret)
+				break;
+			num_rx++;
+		}
+
+		if (num_rx >= budget)
+			break;
+	}
+
+	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
+		if (unlikely(emac->rx_pace_timeout_ns)) {
+			hrtimer_start(&emac->rx_hrtimer,
+				      ns_to_ktime(emac->rx_pace_timeout_ns),
+				      HRTIMER_MODE_REL_PINNED);
+		} else {
+			enable_irq(emac->rx_chns.irq[rx_flow]);
+		}
+	}
+
+	return num_rx;
+}
+
+int prueth_prepare_rx_chan(struct prueth_emac *emac,
+			   struct prueth_rx_chn *chn,
+			   int buf_size)
+{
+	struct sk_buff *skb;
+	int i, ret;
+
+	for (i = 0; i < chn->descs_num; i++) {
+		skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL);
+		if (!skb)
+			return -ENOMEM;
+
+		ret = prueth_dma_rx_push(emac, skb, chn);
+		if (ret < 0) {
+			netdev_err(emac->ndev,
+				   "cannot submit skb for rx chan %s ret %d\n",
+				   chn->name, ret);
+			kfree_skb(skb);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num,
+			  bool free_skb)
+{
+	int i;
+
+	for (i = 0; i < ch_num; i++) {
+		if (free_skb)
+			k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn,
+						  &emac->tx_chns[i],
+						  prueth_tx_cleanup);
+		k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn);
+	}
+}
+
+void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
+			  int num_flows, bool disable)
+{
+	int i;
+
+	for (i = 0; i < num_flows; i++)
+		k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn,
+					  prueth_rx_cleanup, !!i);
+	if (disable)
+		k3_udma_glue_disable_rx_chn(chn->rx_chn);
+}
+
+void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue)
+{
+	ndev->stats.tx_errors++;
+}
+
+static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		emac->tx_ts_enabled = 0;
+		break;
+	case HWTSTAMP_TX_ON:
+		emac->tx_ts_enabled = 1;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		emac->rx_ts_enabled = 0;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		emac->rx_ts_enabled = 1;
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
+}
+
+static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	config.flags = 0;
+	config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+			    -EFAULT : 0;
+}
+
+int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		return emac_get_ts_config(ndev, ifr);
+	case SIOCSHWTSTAMP:
+		return emac_set_ts_config(ndev, ifr);
+	default:
+		break;
+	}
+
+	return phy_do_ioctl(ndev, ifr, cmd);
+}
+
+void emac_ndo_get_stats64(struct net_device *ndev,
+			  struct rtnl_link_stats64 *stats)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	emac_update_hardware_stats(emac);
+
+	stats->rx_packets     = emac_get_stat_by_name(emac, "rx_packets");
+	stats->rx_bytes       = emac_get_stat_by_name(emac, "rx_bytes");
+	stats->tx_packets     = emac_get_stat_by_name(emac, "tx_packets");
+	stats->tx_bytes       = emac_get_stat_by_name(emac, "tx_bytes");
+	stats->rx_crc_errors  = emac_get_stat_by_name(emac, "rx_crc_errors");
+	stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors");
+	stats->multicast      = emac_get_stat_by_name(emac, "rx_multicast_frames");
+
+	stats->rx_errors  = ndev->stats.rx_errors;
+	stats->rx_dropped = ndev->stats.rx_dropped;
+	stats->tx_errors  = ndev->stats.tx_errors;
+	stats->tx_dropped = ndev->stats.tx_dropped;
+}
+
+int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name,
+				size_t len)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int ret;
+
+	ret = snprintf(name, len, "p%d", emac->port_id);
+	if (ret >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* get emac_port corresponding to eth_node name */
+int prueth_node_port(struct device_node *eth_node)
+{
+	u32 port_id;
+	int ret;
+
+	ret = of_property_read_u32(eth_node, "reg", &port_id);
+	if (ret)
+		return ret;
+
+	if (port_id == 0)
+		return PRUETH_PORT_MII0;
+	else if (port_id == 1)
+		return PRUETH_PORT_MII1;
+	else
+		return PRUETH_PORT_INVALID;
+}
+
+/* get MAC instance corresponding to eth_node name */
+int prueth_node_mac(struct device_node *eth_node)
+{
+	u32 port_id;
+	int ret;
+
+	ret = of_property_read_u32(eth_node, "reg", &port_id);
+	if (ret)
+		return ret;
+
+	if (port_id == 0)
+		return PRUETH_MAC0;
+	else if (port_id == 1)
+		return PRUETH_MAC1;
+	else
+		return PRUETH_MAC_INVALID;
+}
+
+void prueth_netdev_exit(struct prueth *prueth,
+			struct device_node *eth_node)
+{
+	struct prueth_emac *emac;
+	enum prueth_mac mac;
+
+	mac = prueth_node_mac(eth_node);
+	if (mac == PRUETH_MAC_INVALID)
+		return;
+
+	emac = prueth->emac[mac];
+	if (!emac)
+		return;
+
+	if (of_phy_is_fixed_link(emac->phy_node))
+		of_phy_deregister_fixed_link(emac->phy_node);
+
+	netif_napi_del(&emac->napi_rx);
+
+	pruss_release_mem_region(prueth->pruss, &emac->dram);
+	destroy_workqueue(emac->cmd_wq);
+	free_netdev(emac->ndev);
+	prueth->emac[mac] = NULL;
+}
+
+int prueth_get_cores(struct prueth *prueth, int slice, bool is_sr1)
+{
+	struct device *dev = prueth->dev;
+	enum pruss_pru_id pruss_id;
+	struct device_node *np;
+	int idx = -1, ret;
+
+	np = dev->of_node;
+
+	switch (slice) {
+	case ICSS_SLICE0:
+		idx = 0;
+		break;
+	case ICSS_SLICE1:
+		idx = is_sr1 ? 2 : 3;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	prueth->pru[slice] = pru_rproc_get(np, idx, &pruss_id);
+	if (IS_ERR(prueth->pru[slice])) {
+		ret = PTR_ERR(prueth->pru[slice]);
+		prueth->pru[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get PRU%d\n", slice);
+	}
+	prueth->pru_id[slice] = pruss_id;
+
+	idx++;
+	prueth->rtu[slice] = pru_rproc_get(np, idx, NULL);
+	if (IS_ERR(prueth->rtu[slice])) {
+		ret = PTR_ERR(prueth->rtu[slice]);
+		prueth->rtu[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get RTU%d\n", slice);
+	}
+
+	if (is_sr1)
+		return 0;
+
+	idx++;
+	prueth->txpru[slice] = pru_rproc_get(np, idx, NULL);
+	if (IS_ERR(prueth->txpru[slice])) {
+		ret = PTR_ERR(prueth->txpru[slice]);
+		prueth->txpru[slice] = NULL;
+		return dev_err_probe(dev, ret, "unable to get TX_PRU%d\n", slice);
+	}
+
+	return 0;
+}
+
+void prueth_put_cores(struct prueth *prueth, int slice)
+{
+	if (prueth->txpru[slice])
+		pru_rproc_put(prueth->txpru[slice]);
+
+	if (prueth->rtu[slice])
+		pru_rproc_put(prueth->rtu[slice]);
+
+	if (prueth->pru[slice])
+		pru_rproc_put(prueth->pru[slice]);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int prueth_suspend(struct device *dev)
+{
+	struct prueth *prueth = dev_get_drvdata(dev);
+	struct net_device *ndev;
+	int i, ret;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		ndev = prueth->registered_netdevs[i];
+
+		if (!ndev)
+			continue;
+
+		if (netif_running(ndev)) {
+			netif_device_detach(ndev);
+			ret = ndev->netdev_ops->ndo_stop(ndev);
+			if (ret < 0) {
+				netdev_err(ndev, "failed to stop: %d", ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int prueth_resume(struct device *dev)
+{
+	struct prueth *prueth = dev_get_drvdata(dev);
+	struct net_device *ndev;
+	int i, ret;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		ndev = prueth->registered_netdevs[i];
+
+		if (!ndev)
+			continue;
+
+		if (netif_running(ndev)) {
+			ret = ndev->netdev_ops->ndo_open(ndev);
+			if (ret < 0) {
+				netdev_err(ndev, "failed to start: %d", ret);
+				return ret;
+			}
+			netif_device_attach(ndev);
+		}
+	}
+
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+const struct dev_pm_ops prueth_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(prueth_suspend, prueth_resume)
+};
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 99de8a40ed60..15f2235bf90f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -20,6 +20,8 @@
 /* IPG is in core_clk cycles */
 #define MII_RT_TX_IPG_100M	0x17
 #define MII_RT_TX_IPG_1G	0xb
+#define MII_RT_TX_IPG_100M_SR1	0x166
+#define MII_RT_TX_IPG_1G_SR1	0x1a
 
 #define	ICSSG_QUEUES_MAX		64
 #define	ICSSG_QUEUE_OFFSET		0xd00
@@ -202,23 +204,29 @@ void icssg_config_ipg(struct prueth_emac *emac)
 {
 	struct prueth *prueth = emac->prueth;
 	int slice = prueth_emac_slice(emac);
+	u32 ipg;
 
 	switch (emac->speed) {
 	case SPEED_1000:
-		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_1G);
+		ipg = emac->is_sr1 ? MII_RT_TX_IPG_1G_SR1 : MII_RT_TX_IPG_1G;
 		break;
 	case SPEED_100:
-		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M);
+		ipg = emac->is_sr1 ? MII_RT_TX_IPG_100M_SR1 : MII_RT_TX_IPG_100M;
 		break;
 	case SPEED_10:
+		/* Firmware hardcodes IPG for SR1.0 */
+		if (emac->is_sr1)
+			return;
 		/* IPG for 10M is same as 100M */
-		icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M);
+		ipg = MII_RT_TX_IPG_100M;
 		break;
 	default:
 		/* Other links speeds not supported */
 		netdev_err(emac->ndev, "Unsupported link speed\n");
 		return;
 	}
+
+	icssg_mii_update_ipg(prueth->mii_rt, slice, ipg);
 }
 
 static void emac_r30_cmd_init(struct prueth_emac *emac)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index 43eb0922172a..cf2ea4bd22a2 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -109,6 +109,62 @@ enum icssg_port_state_cmd {
 
 #define ICSSG_FLAG_MASK		0xff00ffff
 
+/* SR1.0-specific bits */
+#define PRUETH_MAX_RX_FLOWS_SR1			4	/* excluding default flow */
+#define PRUETH_RX_FLOW_DATA_SR1			3       /* highest priority flow */
+#define PRUETH_MAX_RX_MGM_DESC_SR1		8
+#define PRUETH_MAX_RX_MGM_FLOWS_SR1		2	/* excluding default flow */
+#define PRUETH_RX_MGM_FLOW_RESPONSE_SR1		0
+#define PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1	1
+
+#define PRUETH_NUM_BUF_POOLS_SR1		16
+#define PRUETH_EMAC_BUF_POOL_START_SR1		8
+#define PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1	128
+#define PRUETH_EMAC_BUF_SIZE_SR1		1536
+#define PRUETH_EMAC_NUM_BUF_SR1			4
+#define PRUETH_EMAC_BUF_POOL_SIZE_SR1	(PRUETH_EMAC_NUM_BUF_SR1 * \
+					 PRUETH_EMAC_BUF_SIZE_SR1)
+#define MSMC_RAM_SIZE_SR1	(SZ_64K + SZ_32K + SZ_2K) /* 0x1880 x 8 x 2 */
+
+struct icssg_sr1_config {
+	__le32 status;		/* Firmware status */
+	__le32 addr_lo;		/* MSMC Buffer pool base address low. */
+	__le32 addr_hi;		/* MSMC Buffer pool base address high. Must be 0 */
+	__le32 tx_buf_sz[16];	/* Array of buffer pool sizes */
+	__le32 num_tx_threads;	/* Number of active egress threads, 1 to 4 */
+	__le32 tx_rate_lim_en;	/* Bitmask: Egress rate limit en per thread */
+	__le32 rx_flow_id;	/* RX flow id for first rx ring */
+	__le32 rx_mgr_flow_id;	/* RX flow id for the first management ring */
+	__le32 flags;		/* TBD */
+	__le32 n_burst;		/* for debug */
+	__le32 rtu_status;	/* RTU status */
+	__le32 info;		/* reserved */
+	__le32 reserve;
+	__le32 rand_seed;	/* Used for the random number generation at fw */
+} __packed;
+
+/* SR1.0 shutdown command to stop processing at firmware.
+ * Command format: 0x8101ss00, where
+ *	- ss: sequence number. Currently not used by driver.
+ */
+#define ICSSG_SHUTDOWN_CMD_SR1		0x81010000
+
+/* SR1.0 pstate speed/duplex command to set speed and duplex settings
+ * in firmware.
+ * Command format: 0x8102ssPN, where
+ *	- ss: sequence number. Currently not used by driver.
+ *	- P: port number (for switch mode).
+ *	- N: Speed/Duplex state:
+ *		0x0 - 10Mbps/Half duplex;
+ *		0x8 - 10Mbps/Full duplex;
+ *		0x2 - 100Mbps/Half duplex;
+ *		0xa - 100Mbps/Full duplex;
+ *		0xc - 1Gbps/Full duplex;
+ *		NOTE: The above are the same value as bits [3..1](slice 0)
+ *		      or bits [7..5](slice 1) of RGMII CFG register.
+ */
+#define ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1	0x81020000
+
 struct icssg_setclock_desc {
 	u8 request;
 	u8 restore;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index 9a7dd7efcf69..c8d0f45cc5b1 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -142,6 +142,9 @@ static int emac_set_channels(struct net_device *ndev,
 
 	emac->tx_ch_num = ch->tx_count;
 
+	if (emac->is_sr1)
+		emac->tx_ch_num++;
+
 	return 0;
 }
 
@@ -152,8 +155,17 @@ static void emac_get_channels(struct net_device *ndev,
 
 	ch->max_rx = 1;
 	ch->max_tx = PRUETH_MAX_TX_QUEUES;
+
+	/* Disable multiple TX channels due to timeouts
+	 * when using more than one queue */
+	if (emac->is_sr1)
+		ch->max_tx = 1;
+
 	ch->rx_count = 1;
 	ch->tx_count = emac->tx_ch_num;
+
+	if (emac->is_sr1)
+		ch->tx_count--;
 }
 
 static const struct ethtool_rmon_hist_range emac_rmon_ranges[] = {
@@ -189,6 +201,93 @@ static void emac_get_rmon_stats(struct net_device *ndev,
 	rmon_stats->hist_tx[4] = emac_get_stat_by_name(emac, "tx_bucket5_frames");
 }
 
+static int emac_get_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth_tx_chn *tx_chn;
+
+	tx_chn = &emac->tx_chns[0];
+
+	coal->rx_coalesce_usecs = emac->rx_pace_timeout_ns / 1000;
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000;
+
+	return 0;
+}
+
+static int emac_get_per_queue_coalesce(struct net_device *ndev, u32 queue,
+				       struct ethtool_coalesce *coal)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth_tx_chn *tx_chn;
+
+	if (queue >= PRUETH_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &emac->tx_chns[queue];
+
+	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000;
+
+	return 0;
+}
+
+static int emac_set_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_tx_chn *tx_chn;
+
+	tx_chn = &emac->tx_chns[0];
+
+	if (coal->rx_coalesce_usecs &&
+	    coal->rx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for rx-usecs\n",
+			 ICSSG_MIN_COALESCE_USECS);
+		coal->rx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	if (coal->tx_coalesce_usecs &&
+	    coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs\n",
+			 ICSSG_MIN_COALESCE_USECS);
+		coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	emac->rx_pace_timeout_ns = coal->rx_coalesce_usecs * 1000;
+	tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
+static int emac_set_per_queue_coalesce(struct net_device *ndev, u32 queue,
+				       struct ethtool_coalesce *coal)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_tx_chn *tx_chn;
+
+	if (queue >= PRUETH_MAX_TX_QUEUES)
+		return -EINVAL;
+
+	tx_chn = &emac->tx_chns[queue];
+
+	if (coal->tx_coalesce_usecs &&
+	    coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) {
+		dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs for tx-%u\n",
+			 ICSSG_MIN_COALESCE_USECS, queue);
+		coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS;
+	}
+
+	tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
 const struct ethtool_ops icssg_ethtool_ops = {
 	.get_drvinfo = emac_get_drvinfo,
 	.get_msglevel = emac_get_msglevel,
@@ -197,6 +296,12 @@ const struct ethtool_ops icssg_ethtool_ops = {
 	.get_ethtool_stats = emac_get_ethtool_stats,
 	.get_strings = emac_get_strings,
 	.get_ts_info = emac_get_ts_info,
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
+				     ETHTOOL_COALESCE_TX_USECS,
+	.get_coalesce = emac_get_coalesce,
+	.set_coalesce = emac_set_coalesce,
+	.get_per_queue_coalesce = emac_get_per_queue_coalesce,
+	.set_per_queue_coalesce = emac_set_per_queue_coalesce,
 	.get_channels = emac_get_channels,
 	.set_channels = emac_set_channels,
 	.get_link_ksettings = emac_get_link_ksettings,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index b69af69a1ccd..7c9e9518f555 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -34,570 +34,9 @@
 
 #define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver"
 
-/* Netif debug messages possible */
-#define PRUETH_EMAC_DEBUG       (NETIF_MSG_DRV | \
-				 NETIF_MSG_PROBE | \
-				 NETIF_MSG_LINK | \
-				 NETIF_MSG_TIMER | \
-				 NETIF_MSG_IFDOWN | \
-				 NETIF_MSG_IFUP | \
-				 NETIF_MSG_RX_ERR | \
-				 NETIF_MSG_TX_ERR | \
-				 NETIF_MSG_TX_QUEUED | \
-				 NETIF_MSG_INTR | \
-				 NETIF_MSG_TX_DONE | \
-				 NETIF_MSG_RX_STATUS | \
-				 NETIF_MSG_PKTDATA | \
-				 NETIF_MSG_HW | \
-				 NETIF_MSG_WOL)
-
-#define prueth_napi_to_emac(napi) container_of(napi, struct prueth_emac, napi_rx)
-
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
 
-#define IEP_DEFAULT_CYCLE_TIME_NS	1000000	/* 1 ms */
-
-static void prueth_cleanup_rx_chns(struct prueth_emac *emac,
-				   struct prueth_rx_chn *rx_chn,
-				   int max_rflows)
-{
-	if (rx_chn->desc_pool)
-		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
-
-	if (rx_chn->rx_chn)
-		k3_udma_glue_release_rx_chn(rx_chn->rx_chn);
-}
-
-static void prueth_cleanup_tx_chns(struct prueth_emac *emac)
-{
-	int i;
-
-	for (i = 0; i < emac->tx_ch_num; i++) {
-		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
-
-		if (tx_chn->desc_pool)
-			k3_cppi_desc_pool_destroy(tx_chn->desc_pool);
-
-		if (tx_chn->tx_chn)
-			k3_udma_glue_release_tx_chn(tx_chn->tx_chn);
-
-		/* Assume prueth_cleanup_tx_chns() is called at the
-		 * end after all channel resources are freed
-		 */
-		memset(tx_chn, 0, sizeof(*tx_chn));
-	}
-}
-
-static void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num)
-{
-	int i;
-
-	for (i = 0; i < num; i++) {
-		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
-
-		if (tx_chn->irq)
-			free_irq(tx_chn->irq, tx_chn);
-		netif_napi_del(&tx_chn->napi_tx);
-	}
-}
-
-static void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
-			     struct cppi5_host_desc_t *desc)
-{
-	struct cppi5_host_desc_t *first_desc, *next_desc;
-	dma_addr_t buf_dma, next_desc_dma;
-	u32 buf_dma_len;
-
-	first_desc = desc;
-	next_desc = first_desc;
-
-	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
-	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
-
-	dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len,
-			 DMA_TO_DEVICE);
-
-	next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc);
-	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
-	while (next_desc_dma) {
-		next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-						       next_desc_dma);
-		cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len);
-		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
-
-		dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len,
-			       DMA_TO_DEVICE);
-
-		next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc);
-		k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma);
-
-		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
-	}
-
-	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
-}
-
-static int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
-				    int budget)
-{
-	struct net_device *ndev = emac->ndev;
-	struct cppi5_host_desc_t *desc_tx;
-	struct netdev_queue *netif_txq;
-	struct prueth_tx_chn *tx_chn;
-	unsigned int total_bytes = 0;
-	struct sk_buff *skb;
-	dma_addr_t desc_dma;
-	int res, num_tx = 0;
-	void **swdata;
-
-	tx_chn = &emac->tx_chns[chn];
-
-	while (true) {
-		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
-		if (res == -ENODATA)
-			break;
-
-		/* teardown completion */
-		if (cppi5_desc_is_tdcm(desc_dma)) {
-			if (atomic_dec_and_test(&emac->tdown_cnt))
-				complete(&emac->tdown_complete);
-			break;
-		}
-
-		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-						     desc_dma);
-		swdata = cppi5_hdesc_get_swdata(desc_tx);
-
-		skb = *(swdata);
-		prueth_xmit_free(tx_chn, desc_tx);
-
-		ndev = skb->dev;
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += skb->len;
-		total_bytes += skb->len;
-		napi_consume_skb(skb, budget);
-		num_tx++;
-	}
-
-	if (!num_tx)
-		return 0;
-
-	netif_txq = netdev_get_tx_queue(ndev, chn);
-	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
-
-	if (netif_tx_queue_stopped(netif_txq)) {
-		/* If the TX queue was stopped, wake it now
-		 * if we have enough room.
-		 */
-		__netif_tx_lock(netif_txq, smp_processor_id());
-		if (netif_running(ndev) &&
-		    (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
-		     MAX_SKB_FRAGS))
-			netif_tx_wake_queue(netif_txq);
-		__netif_tx_unlock(netif_txq);
-	}
-
-	return num_tx;
-}
-
-static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget)
-{
-	struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx);
-	struct prueth_emac *emac = tx_chn->emac;
-	int num_tx_packets;
-
-	num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget);
-
-	if (num_tx_packets >= budget)
-		return budget;
-
-	if (napi_complete_done(napi_tx, num_tx_packets))
-		enable_irq(tx_chn->irq);
-
-	return num_tx_packets;
-}
-
-static irqreturn_t prueth_tx_irq(int irq, void *dev_id)
-{
-	struct prueth_tx_chn *tx_chn = dev_id;
-
-	disable_irq_nosync(irq);
-	napi_schedule(&tx_chn->napi_tx);
-
-	return IRQ_HANDLED;
-}
-
-static int prueth_ndev_add_tx_napi(struct prueth_emac *emac)
-{
-	struct prueth *prueth = emac->prueth;
-	int i, ret;
-
-	for (i = 0; i < emac->tx_ch_num; i++) {
-		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
-
-		netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll);
-		ret = request_irq(tx_chn->irq, prueth_tx_irq,
-				  IRQF_TRIGGER_HIGH, tx_chn->name,
-				  tx_chn);
-		if (ret) {
-			netif_napi_del(&tx_chn->napi_tx);
-			dev_err(prueth->dev, "unable to request TX IRQ %d\n",
-				tx_chn->irq);
-			goto fail;
-		}
-	}
-
-	return 0;
-fail:
-	prueth_ndev_del_tx_napi(emac, i);
-	return ret;
-}
-
-static int prueth_init_tx_chns(struct prueth_emac *emac)
-{
-	static const struct k3_ring_cfg ring_cfg = {
-		.elm_size = K3_RINGACC_RING_ELSIZE_8,
-		.mode = K3_RINGACC_RING_MODE_RING,
-		.flags = 0,
-		.size = PRUETH_MAX_TX_DESC,
-	};
-	struct k3_udma_glue_tx_channel_cfg tx_cfg;
-	struct device *dev = emac->prueth->dev;
-	struct net_device *ndev = emac->ndev;
-	int ret, slice, i;
-	u32 hdesc_size;
-
-	slice = prueth_emac_slice(emac);
-	if (slice < 0)
-		return slice;
-
-	init_completion(&emac->tdown_complete);
-
-	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
-					   PRUETH_NAV_SW_DATA_SIZE);
-	memset(&tx_cfg, 0, sizeof(tx_cfg));
-	tx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
-	tx_cfg.tx_cfg = ring_cfg;
-	tx_cfg.txcq_cfg = ring_cfg;
-
-	for (i = 0; i < emac->tx_ch_num; i++) {
-		struct prueth_tx_chn *tx_chn = &emac->tx_chns[i];
-
-		/* To differentiate channels for SLICE0 vs SLICE1 */
-		snprintf(tx_chn->name, sizeof(tx_chn->name),
-			 "tx%d-%d", slice, i);
-
-		tx_chn->emac = emac;
-		tx_chn->id = i;
-		tx_chn->descs_num = PRUETH_MAX_TX_DESC;
-
-		tx_chn->tx_chn =
-			k3_udma_glue_request_tx_chn(dev, tx_chn->name,
-						    &tx_cfg);
-		if (IS_ERR(tx_chn->tx_chn)) {
-			ret = PTR_ERR(tx_chn->tx_chn);
-			tx_chn->tx_chn = NULL;
-			netdev_err(ndev,
-				   "Failed to request tx dma ch: %d\n", ret);
-			goto fail;
-		}
-
-		tx_chn->dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn->tx_chn);
-		tx_chn->desc_pool =
-			k3_cppi_desc_pool_create_name(tx_chn->dma_dev,
-						      tx_chn->descs_num,
-						      hdesc_size,
-						      tx_chn->name);
-		if (IS_ERR(tx_chn->desc_pool)) {
-			ret = PTR_ERR(tx_chn->desc_pool);
-			tx_chn->desc_pool = NULL;
-			netdev_err(ndev, "Failed to create tx pool: %d\n", ret);
-			goto fail;
-		}
-
-		ret = k3_udma_glue_tx_get_irq(tx_chn->tx_chn);
-		if (ret < 0) {
-			netdev_err(ndev, "failed to get tx irq\n");
-			goto fail;
-		}
-		tx_chn->irq = ret;
-
-		snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d",
-			 dev_name(dev), tx_chn->id);
-	}
-
-	return 0;
-
-fail:
-	prueth_cleanup_tx_chns(emac);
-	return ret;
-}
-
-static int prueth_init_rx_chns(struct prueth_emac *emac,
-			       struct prueth_rx_chn *rx_chn,
-			       char *name, u32 max_rflows,
-			       u32 max_desc_num)
-{
-	struct k3_udma_glue_rx_channel_cfg rx_cfg;
-	struct device *dev = emac->prueth->dev;
-	struct net_device *ndev = emac->ndev;
-	u32 fdqring_id, hdesc_size;
-	int i, ret = 0, slice;
-
-	slice = prueth_emac_slice(emac);
-	if (slice < 0)
-		return slice;
-
-	/* To differentiate channels for SLICE0 vs SLICE1 */
-	snprintf(rx_chn->name, sizeof(rx_chn->name), "%s%d", name, slice);
-
-	hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE,
-					   PRUETH_NAV_SW_DATA_SIZE);
-	memset(&rx_cfg, 0, sizeof(rx_cfg));
-	rx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE;
-	rx_cfg.flow_id_num = max_rflows;
-	rx_cfg.flow_id_base = -1; /* udmax will auto select flow id base */
-
-	/* init all flows */
-	rx_chn->dev = dev;
-	rx_chn->descs_num = max_desc_num;
-
-	rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, rx_chn->name,
-						     &rx_cfg);
-	if (IS_ERR(rx_chn->rx_chn)) {
-		ret = PTR_ERR(rx_chn->rx_chn);
-		rx_chn->rx_chn = NULL;
-		netdev_err(ndev, "Failed to request rx dma ch: %d\n", ret);
-		goto fail;
-	}
-
-	rx_chn->dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn->rx_chn);
-	rx_chn->desc_pool = k3_cppi_desc_pool_create_name(rx_chn->dma_dev,
-							  rx_chn->descs_num,
-							  hdesc_size,
-							  rx_chn->name);
-	if (IS_ERR(rx_chn->desc_pool)) {
-		ret = PTR_ERR(rx_chn->desc_pool);
-		rx_chn->desc_pool = NULL;
-		netdev_err(ndev, "Failed to create rx pool: %d\n", ret);
-		goto fail;
-	}
-
-	emac->rx_flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn);
-	netdev_dbg(ndev, "flow id base = %d\n", emac->rx_flow_id_base);
-
-	fdqring_id = K3_RINGACC_RING_ID_ANY;
-	for (i = 0; i < rx_cfg.flow_id_num; i++) {
-		struct k3_ring_cfg rxring_cfg = {
-			.elm_size = K3_RINGACC_RING_ELSIZE_8,
-			.mode = K3_RINGACC_RING_MODE_RING,
-			.flags = 0,
-		};
-		struct k3_ring_cfg fdqring_cfg = {
-			.elm_size = K3_RINGACC_RING_ELSIZE_8,
-			.flags = K3_RINGACC_RING_SHARED,
-		};
-		struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = {
-			.rx_cfg = rxring_cfg,
-			.rxfdq_cfg = fdqring_cfg,
-			.ring_rxq_id = K3_RINGACC_RING_ID_ANY,
-			.src_tag_lo_sel =
-				K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG,
-		};
-
-		rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
-		rx_flow_cfg.rx_cfg.size = max_desc_num;
-		rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
-		rx_flow_cfg.rxfdq_cfg.mode = emac->prueth->pdata.fdqring_mode;
-
-		ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn,
-						i, &rx_flow_cfg);
-		if (ret) {
-			netdev_err(ndev, "Failed to init rx flow%d %d\n",
-				   i, ret);
-			goto fail;
-		}
-		if (!i)
-			fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
-								     i);
-		ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
-		if (ret <= 0) {
-			if (!ret)
-				ret = -ENXIO;
-			netdev_err(ndev, "Failed to get rx dma irq");
-			goto fail;
-		}
-		rx_chn->irq[i] = ret;
-	}
-
-	return 0;
-
-fail:
-	prueth_cleanup_rx_chns(emac, rx_chn, max_rflows);
-	return ret;
-}
-
-static int prueth_dma_rx_push(struct prueth_emac *emac,
-			      struct sk_buff *skb,
-			      struct prueth_rx_chn *rx_chn)
-{
-	struct net_device *ndev = emac->ndev;
-	struct cppi5_host_desc_t *desc_rx;
-	u32 pkt_len = skb_tailroom(skb);
-	dma_addr_t desc_dma;
-	dma_addr_t buf_dma;
-	void **swdata;
-
-	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
-	if (!desc_rx) {
-		netdev_err(ndev, "rx push: failed to allocate descriptor\n");
-		return -ENOMEM;
-	}
-	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
-
-	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
-		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-		netdev_err(ndev, "rx push: failed to map rx pkt buffer\n");
-		return -EINVAL;
-	}
-
-	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
-			 PRUETH_NAV_PS_DATA_SIZE);
-	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
-	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
-
-	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	*swdata = skb;
-
-	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0,
-					desc_rx, desc_dma);
-}
-
-static u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns)
-{
-	u32 iepcount_lo, iepcount_hi, hi_rollover_count;
-	u64 ns;
-
-	iepcount_lo = lo & GENMASK(19, 0);
-	iepcount_hi = (hi & GENMASK(11, 0)) << 12 | lo >> 20;
-	hi_rollover_count = hi >> 11;
-
-	ns = ((u64)hi_rollover_count) << 23 | (iepcount_hi + hi_sw);
-	ns = ns * cycle_time_ns + iepcount_lo;
-
-	return ns;
-}
-
-static void emac_rx_timestamp(struct prueth_emac *emac,
-			      struct sk_buff *skb, u32 *psdata)
-{
-	struct skb_shared_hwtstamps *ssh;
-	u64 ns;
-
-	u32 hi_sw = readl(emac->prueth->shram.va +
-			  TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET);
-	ns = icssg_ts_to_ns(hi_sw, psdata[1], psdata[0],
-			    IEP_DEFAULT_CYCLE_TIME_NS);
-
-	ssh = skb_hwtstamps(skb);
-	memset(ssh, 0, sizeof(*ssh));
-	ssh->hwtstamp = ns_to_ktime(ns);
-}
-
-static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
-{
-	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
-	u32 buf_dma_len, pkt_len, port_id = 0;
-	struct net_device *ndev = emac->ndev;
-	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb, *new_skb;
-	dma_addr_t desc_dma, buf_dma;
-	void **swdata;
-	u32 *psdata;
-	int ret;
-
-	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
-	if (ret) {
-		if (ret != -ENODATA)
-			netdev_err(ndev, "rx pop: failed: %d\n", ret);
-		return ret;
-	}
-
-	if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */
-		return 0;
-
-	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
-
-	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-
-	psdata = cppi5_hdesc_get_psdata(desc_rx);
-	/* RX HW timestamp */
-	if (emac->rx_ts_enabled)
-		emac_rx_timestamp(emac, skb, psdata);
-
-	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
-	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
-	/* firmware adds 4 CRC bytes, strip them */
-	pkt_len -= 4;
-	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
-
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
-	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
-	skb->dev = ndev;
-	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
-	/* if allocation fails we drop the packet but push the
-	 * descriptor back to the ring with old skb to prevent a stall
-	 */
-	if (!new_skb) {
-		ndev->stats.rx_dropped++;
-		new_skb = skb;
-	} else {
-		/* send the filled skb up the n/w stack */
-		skb_put(skb, pkt_len);
-		skb->protocol = eth_type_trans(skb, ndev);
-		napi_gro_receive(&emac->napi_rx, skb);
-		ndev->stats.rx_bytes += pkt_len;
-		ndev->stats.rx_packets++;
-	}
-
-	/* queue another RX DMA */
-	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns);
-	if (WARN_ON(ret < 0)) {
-		dev_kfree_skb_any(new_skb);
-		ndev->stats.rx_errors++;
-		ndev->stats.rx_dropped++;
-	}
-
-	return ret;
-}
-
-static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
-{
-	struct prueth_rx_chn *rx_chn = data;
-	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb;
-	dma_addr_t buf_dma;
-	u32 buf_dma_len;
-	void **swdata;
-
-	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
-
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len,
-			 DMA_FROM_DEVICE);
-	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
-	dev_kfree_skb_any(skb);
-}
-
 static int emac_get_tx_ts(struct prueth_emac *emac,
 			  struct emac_tx_ts_response *rsp)
 {
@@ -663,208 +102,6 @@ static void tx_ts_work(struct prueth_emac *emac)
 	}
 }
 
-static int prueth_tx_ts_cookie_get(struct prueth_emac *emac)
-{
-	int i;
-
-	/* search and get the next free slot */
-	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
-		if (!emac->tx_ts_skb[i]) {
-			emac->tx_ts_skb[i] = ERR_PTR(-EBUSY); /* reserve slot */
-			return i;
-		}
-	}
-
-	return -EBUSY;
-}
-
-/**
- * emac_ndo_start_xmit - EMAC Transmit function
- * @skb: SKB pointer
- * @ndev: EMAC network adapter
- *
- * Called by the system to transmit a packet  - we queue the packet in
- * EMAC hardware transmit queue
- * Doesn't wait for completion we'll check for TX completion in
- * emac_tx_complete_packets().
- *
- * Return: enum netdev_tx
- */
-static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
-{
-	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
-	struct prueth_emac *emac = netdev_priv(ndev);
-	struct netdev_queue *netif_txq;
-	struct prueth_tx_chn *tx_chn;
-	dma_addr_t desc_dma, buf_dma;
-	int i, ret = 0, q_idx;
-	bool in_tx_ts = 0;
-	int tx_ts_cookie;
-	void **swdata;
-	u32 pkt_len;
-	u32 *epib;
-
-	pkt_len = skb_headlen(skb);
-	q_idx = skb_get_queue_mapping(skb);
-
-	tx_chn = &emac->tx_chns[q_idx];
-	netif_txq = netdev_get_tx_queue(ndev, q_idx);
-
-	/* Map the linear buffer */
-	buf_dma = dma_map_single(tx_chn->dma_dev, skb->data, pkt_len, DMA_TO_DEVICE);
-	if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
-		netdev_err(ndev, "tx: failed to map skb buffer\n");
-		ret = NETDEV_TX_OK;
-		goto drop_free_skb;
-	}
-
-	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
-	if (!first_desc) {
-		netdev_dbg(ndev, "tx: failed to allocate descriptor\n");
-		dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE);
-		goto drop_stop_q_busy;
-	}
-
-	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
-			 PRUETH_NAV_PS_DATA_SIZE);
-	cppi5_hdesc_set_pkttype(first_desc, 0);
-	epib = first_desc->epib;
-	epib[0] = 0;
-	epib[1] = 0;
-	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-	    emac->tx_ts_enabled) {
-		tx_ts_cookie = prueth_tx_ts_cookie_get(emac);
-		if (tx_ts_cookie >= 0) {
-			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-			/* Request TX timestamp */
-			epib[0] = (u32)tx_ts_cookie;
-			epib[1] = 0x80000000;	/* TX TS request */
-			emac->tx_ts_skb[tx_ts_cookie] = skb_get(skb);
-			in_tx_ts = 1;
-		}
-	}
-
-	/* set dst tag to indicate internal qid at the firmware which is at
-	 * bit8..bit15. bit0..bit7 indicates port num for directed
-	 * packets in case of switch mode operation
-	 */
-	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
-	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
-	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
-	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*swdata = skb;
-
-	/* Handle the case where skb is fragmented in pages */
-	cur_desc = first_desc;
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		u32 frag_size = skb_frag_size(frag);
-
-		next_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
-		if (!next_desc) {
-			netdev_err(ndev,
-				   "tx: failed to allocate frag. descriptor\n");
-			goto free_desc_stop_q_busy_cleanup_tx_ts;
-		}
-
-		buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size,
-					   DMA_TO_DEVICE);
-		if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
-			netdev_err(ndev, "tx: Failed to map skb page\n");
-			k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
-			ret = NETDEV_TX_OK;
-			goto cleanup_tx_ts;
-		}
-
-		cppi5_hdesc_reset_hbdesc(next_desc);
-		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
-		cppi5_hdesc_attach_buf(next_desc,
-				       buf_dma, frag_size, buf_dma, frag_size);
-
-		desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool,
-						      next_desc);
-		k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma);
-		cppi5_hdesc_link_hbdesc(cur_desc, desc_dma);
-
-		pkt_len += frag_size;
-		cur_desc = next_desc;
-	}
-	WARN_ON_ONCE(pkt_len != skb->len);
-
-	/* report bql before sending packet */
-	netdev_tx_sent_queue(netif_txq, pkt_len);
-
-	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
-	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
-	/* cppi5_desc_dump(first_desc, 64); */
-
-	skb_tx_timestamp(skb);  /* SW timestamp if SKBTX_IN_PROGRESS not set */
-	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
-	if (ret) {
-		netdev_err(ndev, "tx: push failed: %d\n", ret);
-		goto drop_free_descs;
-	}
-
-	if (in_tx_ts)
-		atomic_inc(&emac->tx_ts_pending);
-
-	if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) {
-		netif_tx_stop_queue(netif_txq);
-		/* Barrier, so that stop_queue visible to other cpus */
-		smp_mb__after_atomic();
-
-		if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >=
-		    MAX_SKB_FRAGS)
-			netif_tx_wake_queue(netif_txq);
-	}
-
-	return NETDEV_TX_OK;
-
-cleanup_tx_ts:
-	if (in_tx_ts) {
-		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
-		emac->tx_ts_skb[tx_ts_cookie] = NULL;
-	}
-
-drop_free_descs:
-	prueth_xmit_free(tx_chn, first_desc);
-
-drop_free_skb:
-	dev_kfree_skb_any(skb);
-
-	/* error */
-	ndev->stats.tx_dropped++;
-	netdev_err(ndev, "tx: error: %d\n", ret);
-
-	return ret;
-
-free_desc_stop_q_busy_cleanup_tx_ts:
-	if (in_tx_ts) {
-		dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]);
-		emac->tx_ts_skb[tx_ts_cookie] = NULL;
-	}
-	prueth_xmit_free(tx_chn, first_desc);
-
-drop_stop_q_busy:
-	netif_tx_stop_queue(netif_txq);
-	return NETDEV_TX_BUSY;
-}
-
-static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
-{
-	struct prueth_tx_chn *tx_chn = data;
-	struct cppi5_host_desc_t *desc_tx;
-	struct sk_buff *skb;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	prueth_xmit_free(tx_chn, desc_tx);
-
-	dev_kfree_skb_any(skb);
-}
-
 static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
@@ -875,22 +112,6 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t prueth_rx_irq(int irq, void *dev_id)
-{
-	struct prueth_emac *emac = dev_id;
-
-	disable_irq_nosync(irq);
-	napi_schedule(&emac->napi_rx);
-
-	return IRQ_HANDLED;
-}
-
-struct icssg_firmwares {
-	char *pru;
-	char *rtu;
-	char *txpru;
-};
-
 static struct icssg_firmwares icssg_emac_firmwares[] = {
 	{
 		.pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf",
@@ -955,41 +176,6 @@ halt_pru:
 	return ret;
 }
 
-static void prueth_emac_stop(struct prueth_emac *emac)
-{
-	struct prueth *prueth = emac->prueth;
-	int slice;
-
-	switch (emac->port_id) {
-	case PRUETH_PORT_MII0:
-		slice = ICSS_SLICE0;
-		break;
-	case PRUETH_PORT_MII1:
-		slice = ICSS_SLICE1;
-		break;
-	default:
-		netdev_err(emac->ndev, "invalid port\n");
-		return;
-	}
-
-	emac->fw_running = 0;
-	rproc_shutdown(prueth->txpru[slice]);
-	rproc_shutdown(prueth->rtu[slice]);
-	rproc_shutdown(prueth->pru[slice]);
-}
-
-static void prueth_cleanup_tx_ts(struct prueth_emac *emac)
-{
-	int i;
-
-	for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) {
-		if (emac->tx_ts_skb[i]) {
-			dev_kfree_skb_any(emac->tx_ts_skb[i]);
-			emac->tx_ts_skb[i] = NULL;
-		}
-	}
-}
-
 /* called back by PHY layer if there is change in link state of hw port*/
 static void emac_adjust_link(struct net_device *ndev)
 {
@@ -1057,84 +243,14 @@ static void emac_adjust_link(struct net_device *ndev)
 	}
 }
 
-static int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget)
+static enum hrtimer_restart emac_rx_timer_callback(struct hrtimer *timer)
 {
-	struct prueth_emac *emac = prueth_napi_to_emac(napi_rx);
+	struct prueth_emac *emac =
+			container_of(timer, struct prueth_emac, rx_hrtimer);
 	int rx_flow = PRUETH_RX_FLOW_DATA;
-	int flow = PRUETH_MAX_RX_FLOWS;
-	int num_rx = 0;
-	int cur_budget;
-	int ret;
-
-	while (flow--) {
-		cur_budget = budget - num_rx;
-
-		while (cur_budget--) {
-			ret = emac_rx_packet(emac, flow);
-			if (ret)
-				break;
-			num_rx++;
-		}
-
-		if (num_rx >= budget)
-			break;
-	}
 
-	if (num_rx < budget && napi_complete_done(napi_rx, num_rx))
-		enable_irq(emac->rx_chns.irq[rx_flow]);
-
-	return num_rx;
-}
-
-static int prueth_prepare_rx_chan(struct prueth_emac *emac,
-				  struct prueth_rx_chn *chn,
-				  int buf_size)
-{
-	struct sk_buff *skb;
-	int i, ret;
-
-	for (i = 0; i < chn->descs_num; i++) {
-		skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL);
-		if (!skb)
-			return -ENOMEM;
-
-		ret = prueth_dma_rx_push(emac, skb, chn);
-		if (ret < 0) {
-			netdev_err(emac->ndev,
-				   "cannot submit skb for rx chan %s ret %d\n",
-				   chn->name, ret);
-			kfree_skb(skb);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num,
-				 bool free_skb)
-{
-	int i;
-
-	for (i = 0; i < ch_num; i++) {
-		if (free_skb)
-			k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn,
-						  &emac->tx_chns[i],
-						  prueth_tx_cleanup);
-		k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn);
-	}
-}
-
-static void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
-				 int num_flows, bool disable)
-{
-	int i;
-
-	for (i = 0; i < num_flows; i++)
-		k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn,
-					  prueth_rx_cleanup, !!i);
-	if (disable)
-		k3_udma_glue_disable_rx_chn(chn->rx_chn);
+	enable_irq(emac->rx_chns.irq[rx_flow]);
+	return HRTIMER_NORESTART;
 }
 
 static int emac_phy_connect(struct prueth_emac *emac)
@@ -1331,7 +447,7 @@ static int emac_ndo_open(struct net_device *ndev)
 	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
 	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
 
-	icssg_class_default(prueth->miig_rt, slice, 0);
+	icssg_class_default(prueth->miig_rt, slice, 0, false);
 
 	/* Notify the stack of the actual queue counts. */
 	ret = netif_set_real_num_tx_queues(ndev, num_data_chn);
@@ -1476,8 +592,10 @@ static int emac_ndo_stop(struct net_device *ndev)
 		netdev_err(ndev, "tx teardown timeout\n");
 
 	prueth_reset_tx_chan(emac, emac->tx_ch_num, true);
-	for (i = 0; i < emac->tx_ch_num; i++)
+	for (i = 0; i < emac->tx_ch_num; i++) {
 		napi_disable(&emac->tx_chns[i].napi_tx);
+		hrtimer_cancel(&emac->tx_chns[i].tx_hrtimer);
+	}
 
 	max_rx_flows = PRUETH_MAX_RX_FLOWS;
 	k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true);
@@ -1485,6 +603,7 @@ static int emac_ndo_stop(struct net_device *ndev)
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true);
 
 	napi_disable(&emac->napi_rx);
+	hrtimer_cancel(&emac->rx_hrtimer);
 
 	cancel_work_sync(&emac->rx_mode_work);
 
@@ -1510,11 +629,6 @@ static int emac_ndo_stop(struct net_device *ndev)
 	return 0;
 }
 
-static void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue)
-{
-	ndev->stats.tx_errors++;
-}
-
 static void emac_ndo_set_rx_mode_work(struct work_struct *work)
 {
 	struct prueth_emac *emac = container_of(work, struct prueth_emac, rx_mode_work);
@@ -1560,116 +674,6 @@ static void emac_ndo_set_rx_mode(struct net_device *ndev)
 	queue_work(emac->cmd_wq, &emac->rx_mode_work);
 }
 
-static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr)
-{
-	struct prueth_emac *emac = netdev_priv(ndev);
-	struct hwtstamp_config config;
-
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
-	switch (config.tx_type) {
-	case HWTSTAMP_TX_OFF:
-		emac->tx_ts_enabled = 0;
-		break;
-	case HWTSTAMP_TX_ON:
-		emac->tx_ts_enabled = 1;
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	switch (config.rx_filter) {
-	case HWTSTAMP_FILTER_NONE:
-		emac->rx_ts_enabled = 0;
-		break;
-	case HWTSTAMP_FILTER_ALL:
-	case HWTSTAMP_FILTER_SOME:
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
-	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
-	case HWTSTAMP_FILTER_PTP_V2_EVENT:
-	case HWTSTAMP_FILTER_PTP_V2_SYNC:
-	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-	case HWTSTAMP_FILTER_NTP_ALL:
-		emac->rx_ts_enabled = 1;
-		config.rx_filter = HWTSTAMP_FILTER_ALL;
-		break;
-	default:
-		return -ERANGE;
-	}
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-		-EFAULT : 0;
-}
-
-static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr)
-{
-	struct prueth_emac *emac = netdev_priv(ndev);
-	struct hwtstamp_config config;
-
-	config.flags = 0;
-	config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
-
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-			    -EFAULT : 0;
-}
-
-static int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	case SIOCGHWTSTAMP:
-		return emac_get_ts_config(ndev, ifr);
-	case SIOCSHWTSTAMP:
-		return emac_set_ts_config(ndev, ifr);
-	default:
-		break;
-	}
-
-	return phy_do_ioctl(ndev, ifr, cmd);
-}
-
-static void emac_ndo_get_stats64(struct net_device *ndev,
-				 struct rtnl_link_stats64 *stats)
-{
-	struct prueth_emac *emac = netdev_priv(ndev);
-
-	emac_update_hardware_stats(emac);
-
-	stats->rx_packets     = emac_get_stat_by_name(emac, "rx_packets");
-	stats->rx_bytes       = emac_get_stat_by_name(emac, "rx_bytes");
-	stats->tx_packets     = emac_get_stat_by_name(emac, "tx_packets");
-	stats->tx_bytes       = emac_get_stat_by_name(emac, "tx_bytes");
-	stats->rx_crc_errors  = emac_get_stat_by_name(emac, "rx_crc_errors");
-	stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors");
-	stats->multicast      = emac_get_stat_by_name(emac, "rx_multicast_frames");
-
-	stats->rx_errors  = ndev->stats.rx_errors;
-	stats->rx_dropped = ndev->stats.rx_dropped;
-	stats->tx_errors  = ndev->stats.tx_errors;
-	stats->tx_dropped = ndev->stats.tx_dropped;
-}
-
-static int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name,
-				       size_t len)
-{
-	struct prueth_emac *emac = netdev_priv(ndev);
-	int ret;
-
-	ret = snprintf(name, len, "p%d", emac->port_id);
-	if (ret >= len)
-		return -EINVAL;
-
-	return 0;
-}
-
 static const struct net_device_ops emac_netdev_ops = {
 	.ndo_open = emac_ndo_open,
 	.ndo_stop = emac_ndo_stop,
@@ -1683,42 +687,6 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_get_phys_port_name = emac_ndo_get_phys_port_name,
 };
 
-/* get emac_port corresponding to eth_node name */
-static int prueth_node_port(struct device_node *eth_node)
-{
-	u32 port_id;
-	int ret;
-
-	ret = of_property_read_u32(eth_node, "reg", &port_id);
-	if (ret)
-		return ret;
-
-	if (port_id == 0)
-		return PRUETH_PORT_MII0;
-	else if (port_id == 1)
-		return PRUETH_PORT_MII1;
-	else
-		return PRUETH_PORT_INVALID;
-}
-
-/* get MAC instance corresponding to eth_node name */
-static int prueth_node_mac(struct device_node *eth_node)
-{
-	u32 port_id;
-	int ret;
-
-	ret = of_property_read_u32(eth_node, "reg", &port_id);
-	if (ret)
-		return ret;
-
-	if (port_id == 0)
-		return PRUETH_MAC0;
-	else if (port_id == 1)
-		return PRUETH_MAC1;
-	else
-		return PRUETH_MAC_INVALID;
-}
-
 static int prueth_netdev_init(struct prueth *prueth,
 			      struct device_node *eth_node)
 {
@@ -1846,6 +814,9 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->features = ndev->hw_features;
 
 	netif_napi_add(ndev, &emac->napi_rx, emac_napi_rx_poll);
+	hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_PINNED);
+	emac->rx_hrtimer.function = &emac_rx_timer_callback;
 	prueth->emac[mac] = emac;
 
 	return 0;
@@ -1862,90 +833,6 @@ free_ndev:
 	return ret;
 }
 
-static void prueth_netdev_exit(struct prueth *prueth,
-			       struct device_node *eth_node)
-{
-	struct prueth_emac *emac;
-	enum prueth_mac mac;
-
-	mac = prueth_node_mac(eth_node);
-	if (mac == PRUETH_MAC_INVALID)
-		return;
-
-	emac = prueth->emac[mac];
-	if (!emac)
-		return;
-
-	if (of_phy_is_fixed_link(emac->phy_node))
-		of_phy_deregister_fixed_link(emac->phy_node);
-
-	netif_napi_del(&emac->napi_rx);
-
-	pruss_release_mem_region(prueth->pruss, &emac->dram);
-	destroy_workqueue(emac->cmd_wq);
-	free_netdev(emac->ndev);
-	prueth->emac[mac] = NULL;
-}
-
-static int prueth_get_cores(struct prueth *prueth, int slice)
-{
-	struct device *dev = prueth->dev;
-	enum pruss_pru_id pruss_id;
-	struct device_node *np;
-	int idx = -1, ret;
-
-	np = dev->of_node;
-
-	switch (slice) {
-	case ICSS_SLICE0:
-		idx = 0;
-		break;
-	case ICSS_SLICE1:
-		idx = 3;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	prueth->pru[slice] = pru_rproc_get(np, idx, &pruss_id);
-	if (IS_ERR(prueth->pru[slice])) {
-		ret = PTR_ERR(prueth->pru[slice]);
-		prueth->pru[slice] = NULL;
-		return dev_err_probe(dev, ret, "unable to get PRU%d\n", slice);
-	}
-	prueth->pru_id[slice] = pruss_id;
-
-	idx++;
-	prueth->rtu[slice] = pru_rproc_get(np, idx, NULL);
-	if (IS_ERR(prueth->rtu[slice])) {
-		ret = PTR_ERR(prueth->rtu[slice]);
-		prueth->rtu[slice] = NULL;
-		return dev_err_probe(dev, ret, "unable to get RTU%d\n", slice);
-	}
-
-	idx++;
-	prueth->txpru[slice] = pru_rproc_get(np, idx, NULL);
-	if (IS_ERR(prueth->txpru[slice])) {
-		ret = PTR_ERR(prueth->txpru[slice]);
-		prueth->txpru[slice] = NULL;
-		return dev_err_probe(dev, ret, "unable to get TX_PRU%d\n", slice);
-	}
-
-	return 0;
-}
-
-static void prueth_put_cores(struct prueth *prueth, int slice)
-{
-	if (prueth->txpru[slice])
-		pru_rproc_put(prueth->txpru[slice]);
-
-	if (prueth->rtu[slice])
-		pru_rproc_put(prueth->rtu[slice]);
-
-	if (prueth->pru[slice])
-		pru_rproc_put(prueth->pru[slice]);
-}
-
 static int prueth_probe(struct platform_device *pdev)
 {
 	struct device_node *eth_node, *eth_ports_node;
@@ -2036,13 +923,13 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	if (eth0_node) {
-		ret = prueth_get_cores(prueth, ICSS_SLICE0);
+		ret = prueth_get_cores(prueth, ICSS_SLICE0, false);
 		if (ret)
 			goto put_cores;
 	}
 
 	if (eth1_node) {
-		ret = prueth_get_cores(prueth, ICSS_SLICE1);
+		ret = prueth_get_cores(prueth, ICSS_SLICE1, false);
 		if (ret)
 			goto put_cores;
 	}
@@ -2275,62 +1162,6 @@ static void prueth_remove(struct platform_device *pdev)
 		prueth_put_cores(prueth, ICSS_SLICE0);
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int prueth_suspend(struct device *dev)
-{
-	struct prueth *prueth = dev_get_drvdata(dev);
-	struct net_device *ndev;
-	int i, ret;
-
-	for (i = 0; i < PRUETH_NUM_MACS; i++) {
-		ndev = prueth->registered_netdevs[i];
-
-		if (!ndev)
-			continue;
-
-		if (netif_running(ndev)) {
-			netif_device_detach(ndev);
-			ret = emac_ndo_stop(ndev);
-			if (ret < 0) {
-				netdev_err(ndev, "failed to stop: %d", ret);
-				return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int prueth_resume(struct device *dev)
-{
-	struct prueth *prueth = dev_get_drvdata(dev);
-	struct net_device *ndev;
-	int i, ret;
-
-	for (i = 0; i < PRUETH_NUM_MACS; i++) {
-		ndev = prueth->registered_netdevs[i];
-
-		if (!ndev)
-			continue;
-
-		if (netif_running(ndev)) {
-			ret = emac_ndo_open(ndev);
-			if (ret < 0) {
-				netdev_err(ndev, "failed to start: %d", ret);
-				return ret;
-			}
-			netif_device_attach(ndev);
-		}
-	}
-
-	return 0;
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static const struct dev_pm_ops prueth_dev_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(prueth_suspend, prueth_resume)
-};
-
 static const struct prueth_pdata am654_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 	.quirk_10m_link_issue = 1,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 8b6d6b497010..a78c5eb75fb8 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -55,6 +55,8 @@
 #define ICSSG_NUM_STANDARD_STATS 31
 #define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS)
 
+#define IEP_DEFAULT_CYCLE_TIME_NS	1000000	/* 1 ms */
+
 /* Firmware status codes */
 #define ICSS_HS_FW_READY 0x55555555
 #define ICSS_HS_FW_DEAD 0xDEAD0000	/* lower 16 bits contain error code */
@@ -106,6 +108,8 @@ struct prueth_tx_chn {
 	u32 descs_num;
 	unsigned int irq;
 	char name[32];
+	struct hrtimer tx_hrtimer;
+	unsigned long tx_pace_timeout_ns;
 };
 
 struct prueth_rx_chn {
@@ -125,8 +129,12 @@ struct prueth_rx_chn {
 
 #define PRUETH_MAX_TX_TS_REQUESTS	50 /* Max simultaneous TX_TS requests */
 
+/* Minimum coalesce time in usecs for both Tx and Rx */
+#define ICSSG_MIN_COALESCE_USECS 20
+
 /* data for each emac port */
 struct prueth_emac {
+	bool is_sr1;
 	bool fw_running;
 	struct prueth *prueth;
 	struct net_device *ndev;
@@ -155,6 +163,10 @@ struct prueth_emac {
 	int rx_flow_id_base;
 	int tx_ch_num;
 
+	/* SR1.0 Management channel */
+	struct prueth_rx_chn rx_mgm_chn;
+	int rx_mgm_flow_id_base;
+
 	spinlock_t lock;	/* serialize access */
 
 	/* TX HW Timestamping */
@@ -165,7 +177,7 @@ struct prueth_emac {
 
 	u8 cmd_seq;
 	/* shutdown related */
-	u32 cmd_data[4];
+	__le32 cmd_data[4];
 	struct completion cmd_complete;
 	/* Mutex to serialize access to firmware command interface */
 	struct mutex cmd_lock;
@@ -176,6 +188,10 @@ struct prueth_emac {
 
 	struct delayed_work stats_work;
 	u64 stats[ICSSG_NUM_STATS];
+
+	/* RX IRQ Coalescing Related */
+	struct hrtimer rx_hrtimer;
+	unsigned long rx_pace_timeout_ns;
 };
 
 /**
@@ -188,6 +204,12 @@ struct prueth_pdata {
 	u32	quirk_10m_link_issue:1;
 };
 
+struct icssg_firmwares {
+	char *pru;
+	char *rtu;
+	char *txpru;
+};
+
 /**
  * struct prueth - PRUeth structure
  * @dev: device
@@ -243,6 +265,13 @@ struct emac_tx_ts_response {
 	u32 hi_ts;
 };
 
+struct emac_tx_ts_response_sr1 {
+	__le32 lo_ts;
+	__le32 hi_ts;
+	__le32 reserved;
+	__le32 cookie;
+};
+
 /* get PRUSS SLICE number from prueth_emac */
 static inline int prueth_emac_slice(struct prueth_emac *emac)
 {
@@ -257,12 +286,17 @@ static inline int prueth_emac_slice(struct prueth_emac *emac)
 }
 
 extern const struct ethtool_ops icssg_ethtool_ops;
+extern const struct dev_pm_ops prueth_dev_pm_ops;
 
 /* Classifier helpers */
 void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac);
 void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac);
 void icssg_class_disable(struct regmap *miig_rt, int slice);
-void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti);
+void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti,
+			 bool is_sr1);
+void icssg_class_promiscuous_sr1(struct regmap *miig_rt, int slice);
+void icssg_class_add_mcast_sr1(struct regmap *miig_rt, int slice,
+			       struct net_device *ndev);
 void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr);
 
 /* config helpers */
@@ -285,4 +319,54 @@ u32 icssg_queue_level(struct prueth *prueth, int queue);
 void emac_stats_work_handler(struct work_struct *work);
 void emac_update_hardware_stats(struct prueth_emac *emac);
 int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name);
+
+/* Common functions */
+void prueth_cleanup_rx_chns(struct prueth_emac *emac,
+			    struct prueth_rx_chn *rx_chn,
+			    int max_rflows);
+void prueth_cleanup_tx_chns(struct prueth_emac *emac);
+void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num);
+void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
+		      struct cppi5_host_desc_t *desc);
+int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
+			     int budget, bool *tdown);
+int prueth_ndev_add_tx_napi(struct prueth_emac *emac);
+int prueth_init_tx_chns(struct prueth_emac *emac);
+int prueth_init_rx_chns(struct prueth_emac *emac,
+			struct prueth_rx_chn *rx_chn,
+			char *name, u32 max_rflows,
+			u32 max_desc_num);
+int prueth_dma_rx_push(struct prueth_emac *emac,
+		       struct sk_buff *skb,
+		       struct prueth_rx_chn *rx_chn);
+void emac_rx_timestamp(struct prueth_emac *emac,
+		       struct sk_buff *skb, u32 *psdata);
+enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+irqreturn_t prueth_rx_irq(int irq, void *dev_id);
+void prueth_emac_stop(struct prueth_emac *emac);
+void prueth_cleanup_tx_ts(struct prueth_emac *emac);
+int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget);
+int prueth_prepare_rx_chan(struct prueth_emac *emac,
+			   struct prueth_rx_chn *chn,
+			   int buf_size);
+void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num,
+			  bool free_skb);
+void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
+			  int num_flows, bool disable);
+void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue);
+int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd);
+void emac_ndo_get_stats64(struct net_device *ndev,
+			  struct rtnl_link_stats64 *stats);
+int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name,
+				size_t len);
+int prueth_node_port(struct device_node *eth_node);
+int prueth_node_mac(struct device_node *eth_node);
+void prueth_netdev_exit(struct prueth *prueth,
+			struct device_node *eth_node);
+int prueth_get_cores(struct prueth *prueth, int slice, bool is_sr1);
+void prueth_put_cores(struct prueth *prueth, int slice);
+
+/* Revision specific helper */
+u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns);
+
 #endif /* __NET_TI_ICSSG_PRUETH_H */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
new file mode 100644
index 000000000000..7b3304bbd7fc
--- /dev/null
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -0,0 +1,1181 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Texas Instruments ICSSG SR1.0 Ethernet Driver
+ *
+ * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (c) Siemens AG, 2024
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/genalloc.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/phy.h>
+#include <linux/remoteproc/pruss.h>
+#include <linux/pruss_driver.h>
+
+#include "icssg_prueth.h"
+#include "icssg_mii_rt.h"
+#include "../k3-cppi-desc-pool.h"
+
+#define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG SR1.0 Ethernet driver"
+
+/* SR1: Set buffer sizes for the pools. There are 8 internal queues
+ * implemented in firmware, but only 4 tx channels/threads in the Egress
+ * direction to firmware. Need a high priority queue for management
+ * messages since they shouldn't be blocked even during high traffic
+ * situation. So use Q0-Q2 as data queues and Q3 as management queue
+ * in the max case. However for ease of configuration, use the max
+ * data queue + 1 for management message if we are not using max
+ * case.
+ *
+ * Allocate 4 MTU buffers per data queue.  Firmware requires
+ * pool sizes to be set for internal queues. Set the upper 5 queue
+ * pool size to min size of 128 bytes since there are only 3 tx
+ * data channels and management queue requires only minimum buffer.
+ * i.e lower queues are used by driver and highest priority queue
+ * from that is used for management message.
+ */
+
+static int emac_egress_buf_pool_size[] = {
+	PRUETH_EMAC_BUF_POOL_SIZE_SR1, PRUETH_EMAC_BUF_POOL_SIZE_SR1,
+	PRUETH_EMAC_BUF_POOL_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1,
+	PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1,
+	PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1
+};
+
+static void icssg_config_sr1(struct prueth *prueth, struct prueth_emac *emac,
+			     int slice)
+{
+	struct icssg_sr1_config config;
+	void __iomem *va;
+	int i, index;
+
+	memset(&config, 0, sizeof(config));
+	config.addr_lo = cpu_to_le32(lower_32_bits(prueth->msmcram.pa));
+	config.addr_hi = cpu_to_le32(upper_32_bits(prueth->msmcram.pa));
+	config.rx_flow_id = cpu_to_le32(emac->rx_flow_id_base); /* flow id for host port */
+	config.rx_mgr_flow_id = cpu_to_le32(emac->rx_mgm_flow_id_base); /* for mgm ch */
+	config.rand_seed = cpu_to_le32(get_random_u32());
+
+	for (i = PRUETH_EMAC_BUF_POOL_START_SR1; i < PRUETH_NUM_BUF_POOLS_SR1; i++) {
+		index =  i - PRUETH_EMAC_BUF_POOL_START_SR1;
+		config.tx_buf_sz[i] = cpu_to_le32(emac_egress_buf_pool_size[index]);
+	}
+
+	va = prueth->shram.va + slice * ICSSG_CONFIG_OFFSET_SLICE1;
+	memcpy_toio(va, &config, sizeof(config));
+
+	emac->speed = SPEED_1000;
+	emac->duplex = DUPLEX_FULL;
+}
+
+static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd)
+{
+	struct cppi5_host_desc_t *first_desc;
+	u32 pkt_len = sizeof(emac->cmd_data);
+	__le32 *data = emac->cmd_data;
+	dma_addr_t desc_dma, buf_dma;
+	struct prueth_tx_chn *tx_chn;
+	void **swdata;
+	int ret = 0;
+	u32 *epib;
+
+	netdev_dbg(emac->ndev, "Sending cmd %x\n", cmd);
+
+	/* only one command at a time allowed to firmware */
+	mutex_lock(&emac->cmd_lock);
+	data[0] = cpu_to_le32(cmd);
+
+	/* highest priority channel for management messages */
+	tx_chn = &emac->tx_chns[emac->tx_ch_num - 1];
+
+	/* Map the linear buffer */
+	buf_dma = dma_map_single(tx_chn->dma_dev, data, pkt_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+		netdev_err(emac->ndev, "cmd %x: failed to map cmd buffer\n", cmd);
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (!first_desc) {
+		netdev_err(emac->ndev, "cmd %x: failed to allocate descriptor\n", cmd);
+		dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE);
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(first_desc, PRUETH_PKT_TYPE_CMD);
+	epib = first_desc->epib;
+	epib[0] = 0;
+	epib[1] = 0;
+
+	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
+	swdata = cppi5_hdesc_get_swdata(first_desc);
+	*swdata = data;
+
+	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
+	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
+
+	/* send command */
+	reinit_completion(&emac->cmd_complete);
+	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (ret) {
+		netdev_err(emac->ndev, "cmd %x: push failed: %d\n", cmd, ret);
+		goto free_desc;
+	}
+	ret = wait_for_completion_timeout(&emac->cmd_complete, msecs_to_jiffies(100));
+	if (!ret)
+		netdev_err(emac->ndev, "cmd %x: completion timeout\n", cmd);
+
+	mutex_unlock(&emac->cmd_lock);
+
+	return ret;
+free_desc:
+	prueth_xmit_free(tx_chn, first_desc);
+err_unlock:
+	mutex_unlock(&emac->cmd_lock);
+
+	return ret;
+}
+
+static void icssg_config_set_speed_sr1(struct prueth_emac *emac)
+{
+	u32 cmd = ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1, val;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+
+	val = icssg_rgmii_get_speed(prueth->miig_rt, slice);
+	/* firmware expects speed settings in bit 2-1 */
+	val <<= 1;
+	cmd |= val;
+
+	val = icssg_rgmii_get_fullduplex(prueth->miig_rt, slice);
+	/* firmware expects full duplex settings in bit 3 */
+	val <<= 3;
+	cmd |= val;
+
+	emac_send_command_sr1(emac, cmd);
+}
+
+/* called back by PHY layer if there is change in link state of hw port*/
+static void emac_adjust_link_sr1(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+	struct prueth *prueth = emac->prueth;
+	bool new_state = false;
+	unsigned long flags;
+
+	if (phydev->link) {
+		/* check the mode of operation - full/half duplex */
+		if (phydev->duplex != emac->duplex) {
+			new_state = true;
+			emac->duplex = phydev->duplex;
+		}
+		if (phydev->speed != emac->speed) {
+			new_state = true;
+			emac->speed = phydev->speed;
+		}
+		if (!emac->link) {
+			new_state = true;
+			emac->link = 1;
+		}
+	} else if (emac->link) {
+		new_state = true;
+		emac->link = 0;
+
+		/* f/w should support 100 & 1000 */
+		emac->speed = SPEED_1000;
+
+		/* half duplex may not be supported by f/w */
+		emac->duplex = DUPLEX_FULL;
+	}
+
+	if (new_state) {
+		phy_print_status(phydev);
+
+		/* update RGMII and MII configuration based on PHY negotiated
+		 * values
+		 */
+		if (emac->link) {
+			/* Set the RGMII cfg for gig en and full duplex */
+			icssg_update_rgmii_cfg(prueth->miig_rt, emac);
+
+			/* update the Tx IPG based on 100M/1G speed */
+			spin_lock_irqsave(&emac->lock, flags);
+			icssg_config_ipg(emac);
+			spin_unlock_irqrestore(&emac->lock, flags);
+			icssg_config_set_speed_sr1(emac);
+		}
+	}
+
+	if (emac->link) {
+		/* reactivate the transmit queue */
+		netif_tx_wake_all_queues(ndev);
+	} else {
+		netif_tx_stop_all_queues(ndev);
+		prueth_cleanup_tx_ts(emac);
+	}
+}
+
+static int emac_phy_connect(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	struct net_device *ndev = emac->ndev;
+	/* connect PHY */
+	ndev->phydev = of_phy_connect(emac->ndev, emac->phy_node,
+				      &emac_adjust_link_sr1, 0,
+				      emac->phy_if);
+	if (!ndev->phydev) {
+		dev_err(prueth->dev, "couldn't connect to phy %s\n",
+			emac->phy_node->full_name);
+		return -ENODEV;
+	}
+
+	if (!emac->half_duplex) {
+		dev_dbg(prueth->dev, "half duplex mode is not supported\n");
+		phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
+	}
+
+	/* Remove 100Mbits half-duplex due to RGMII misreporting connection
+	 * as full duplex */
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+
+	/* remove unsupported modes */
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Pause_BIT);
+	phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT);
+
+	if (emac->phy_if == PHY_INTERFACE_MODE_MII)
+		phy_set_max_speed(ndev->phydev, SPEED_100);
+
+	return 0;
+}
+
+/* get one packet from requested flow_id
+ *
+ * Returns skb pointer if packet found else NULL
+ * Caller must free the returned skb.
+ */
+static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac,
+					     u32 flow_id)
+{
+	struct prueth_rx_chn *rx_chn = &emac->rx_mgm_chn;
+	struct net_device *ndev = emac->ndev;
+	struct cppi5_host_desc_t *desc_rx;
+	struct sk_buff *skb, *new_skb;
+	dma_addr_t desc_dma, buf_dma;
+	u32 buf_dma_len, pkt_len;
+	void **swdata;
+	int ret;
+
+	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
+	if (ret) {
+		if (ret != -ENODATA)
+			netdev_err(ndev, "rx mgm pop: failed: %d\n", ret);
+		return NULL;
+	}
+
+	if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown */
+		return NULL;
+
+	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
+
+	/* Fix FW bug about incorrect PSDATA size */
+	if (cppi5_hdesc_get_psdata_size(desc_rx) != PRUETH_NAV_PS_DATA_SIZE) {
+		cppi5_hdesc_update_psdata_size(desc_rx,
+					       PRUETH_NAV_PS_DATA_SIZE);
+	}
+
+	swdata = cppi5_hdesc_get_swdata(desc_rx);
+	skb = *swdata;
+	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
+	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
+
+	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+
+	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
+	/* if allocation fails we drop the packet but push the
+	 * descriptor back to the ring with old skb to prevent a stall
+	 */
+	if (!new_skb) {
+		netdev_err(ndev,
+			   "skb alloc failed, dropped mgm pkt from flow %d\n",
+			   flow_id);
+		new_skb = skb;
+		skb = NULL;	/* return NULL */
+	} else {
+		/* return the filled skb */
+		skb_put(skb, pkt_len);
+	}
+
+	/* queue another DMA */
+	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_mgm_chn);
+	if (WARN_ON(ret < 0))
+		dev_kfree_skb_any(new_skb);
+
+	return skb;
+}
+
+static void prueth_tx_ts_sr1(struct prueth_emac *emac,
+			     struct emac_tx_ts_response_sr1 *tsr)
+{
+	struct skb_shared_hwtstamps ssh;
+	u32 hi_ts, lo_ts, cookie;
+	struct sk_buff *skb;
+	u64 ns;
+
+	hi_ts = le32_to_cpu(tsr->hi_ts);
+	lo_ts = le32_to_cpu(tsr->lo_ts);
+
+	ns = (u64)hi_ts << 32 | lo_ts;
+
+	cookie = le32_to_cpu(tsr->cookie);
+	if (cookie >= PRUETH_MAX_TX_TS_REQUESTS) {
+		netdev_dbg(emac->ndev, "Invalid TX TS cookie 0x%x\n",
+			   cookie);
+		return;
+	}
+
+	skb = emac->tx_ts_skb[cookie];
+	emac->tx_ts_skb[cookie] = NULL;	/* free slot */
+
+	memset(&ssh, 0, sizeof(ssh));
+	ssh.hwtstamp = ns_to_ktime(ns);
+
+	skb_tstamp_tx(skb, &ssh);
+	dev_consume_skb_any(skb);
+}
+
+static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id)
+{
+	struct prueth_emac *emac = dev_id;
+	struct sk_buff *skb;
+
+	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1);
+	if (!skb)
+		return IRQ_NONE;
+
+	prueth_tx_ts_sr1(emac, (void *)skb->data);
+	dev_kfree_skb_any(skb);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id)
+{
+	struct prueth_emac *emac = dev_id;
+	struct sk_buff *skb;
+	u32 rsp;
+
+	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1);
+	if (!skb)
+		return IRQ_NONE;
+
+	/* Process command response */
+	rsp = le32_to_cpu(*(__le32 *)skb->data) & 0xffff0000;
+	if (rsp == ICSSG_SHUTDOWN_CMD_SR1) {
+		netdev_dbg(emac->ndev, "f/w Shutdown cmd resp %x\n", rsp);
+		complete(&emac->cmd_complete);
+	} else if (rsp == ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1) {
+		netdev_dbg(emac->ndev, "f/w Speed/Duplex cmd rsp %x\n", rsp);
+		complete(&emac->cmd_complete);
+	}
+
+	dev_kfree_skb_any(skb);
+
+	return IRQ_HANDLED;
+}
+
+static struct icssg_firmwares icssg_sr1_emac_firmwares[] = {
+	{
+		.pru = "ti-pruss/am65x-pru0-prueth-fw.elf",
+		.rtu = "ti-pruss/am65x-rtu0-prueth-fw.elf",
+	},
+	{
+		.pru = "ti-pruss/am65x-pru1-prueth-fw.elf",
+		.rtu = "ti-pruss/am65x-rtu1-prueth-fw.elf",
+	}
+};
+
+static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
+{
+	struct icssg_firmwares *firmwares;
+	struct device *dev = prueth->dev;
+	int slice, ret;
+
+	firmwares = icssg_sr1_emac_firmwares;
+
+	slice = prueth_emac_slice(emac);
+	if (slice < 0) {
+		netdev_err(emac->ndev, "invalid port\n");
+		return -EINVAL;
+	}
+
+	icssg_config_sr1(prueth, emac, slice);
+
+	ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru);
+	ret = rproc_boot(prueth->pru[slice]);
+	if (ret) {
+		dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
+		return -EINVAL;
+	}
+
+	ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu);
+	ret = rproc_boot(prueth->rtu[slice]);
+	if (ret) {
+		dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
+		goto halt_pru;
+	}
+
+	emac->fw_running = 1;
+	return 0;
+
+halt_pru:
+	rproc_shutdown(prueth->pru[slice]);
+
+	return ret;
+}
+
+/**
+ * emac_ndo_open - EMAC device open
+ * @ndev: network adapter device
+ *
+ * Called when system wants to start the interface.
+ *
+ * Return: 0 for a successful open, or appropriate error code
+ */
+static int emac_ndo_open(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int num_data_chn = emac->tx_ch_num - 1;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+	struct device *dev = prueth->dev;
+	int max_rx_flows, rx_flow;
+	int ret, i;
+
+	/* clear SMEM and MSMC settings for all slices */
+	if (!prueth->emacs_initialized) {
+		memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
+		memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
+	}
+
+	/* set h/w MAC as user might have re-configured */
+	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
+
+	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
+
+	icssg_class_default(prueth->miig_rt, slice, 0, true);
+
+	/* Notify the stack of the actual queue counts. */
+	ret = netif_set_real_num_tx_queues(ndev, num_data_chn);
+	if (ret) {
+		dev_err(dev, "cannot set real number of tx queues\n");
+		return ret;
+	}
+
+	init_completion(&emac->cmd_complete);
+	ret = prueth_init_tx_chns(emac);
+	if (ret) {
+		dev_err(dev, "failed to init tx channel: %d\n", ret);
+		return ret;
+	}
+
+	max_rx_flows = PRUETH_MAX_RX_FLOWS_SR1;
+	ret = prueth_init_rx_chns(emac, &emac->rx_chns, "rx",
+				  max_rx_flows, PRUETH_MAX_RX_DESC);
+	if (ret) {
+		dev_err(dev, "failed to init rx channel: %d\n", ret);
+		goto cleanup_tx;
+	}
+
+	ret = prueth_init_rx_chns(emac, &emac->rx_mgm_chn, "rxmgm",
+				  PRUETH_MAX_RX_MGM_FLOWS_SR1,
+				  PRUETH_MAX_RX_MGM_DESC_SR1);
+	if (ret) {
+		dev_err(dev, "failed to init rx mgmt channel: %d\n",
+			ret);
+		goto cleanup_rx;
+	}
+
+	ret = prueth_ndev_add_tx_napi(emac);
+	if (ret)
+		goto cleanup_rx_mgm;
+
+	/* we use only the highest priority flow for now i.e. @irq[3] */
+	rx_flow = PRUETH_RX_FLOW_DATA_SR1;
+	ret = request_irq(emac->rx_chns.irq[rx_flow], prueth_rx_irq,
+			  IRQF_TRIGGER_HIGH, dev_name(dev), emac);
+	if (ret) {
+		dev_err(dev, "unable to request RX IRQ\n");
+		goto cleanup_napi;
+	}
+
+	ret = request_threaded_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1],
+				   NULL, prueth_rx_mgm_rsp_thread,
+				   IRQF_ONESHOT | IRQF_TRIGGER_HIGH,
+				   dev_name(dev), emac);
+	if (ret) {
+		dev_err(dev, "unable to request RX Management RSP IRQ\n");
+		goto free_rx_irq;
+	}
+
+	ret = request_threaded_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1],
+				   NULL, prueth_rx_mgm_ts_thread_sr1,
+				   IRQF_ONESHOT | IRQF_TRIGGER_HIGH,
+				   dev_name(dev), emac);
+	if (ret) {
+		dev_err(dev, "unable to request RX Management TS IRQ\n");
+		goto free_rx_mgm_rsp_irq;
+	}
+
+	/* reset and start PRU firmware */
+	ret = prueth_emac_start(prueth, emac);
+	if (ret)
+		goto free_rx_mgmt_ts_irq;
+
+	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+
+	/* Prepare RX */
+	ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE);
+	if (ret)
+		goto stop;
+
+	ret = prueth_prepare_rx_chan(emac, &emac->rx_mgm_chn, 64);
+	if (ret)
+		goto reset_rx_chn;
+
+	ret = k3_udma_glue_enable_rx_chn(emac->rx_mgm_chn.rx_chn);
+	if (ret)
+		goto reset_rx_chn;
+
+	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	if (ret)
+		goto reset_rx_mgm_chn;
+
+	for (i = 0; i < emac->tx_ch_num; i++) {
+		ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn);
+		if (ret)
+			goto reset_tx_chan;
+	}
+
+	/* Enable NAPI in Tx and Rx direction */
+	for (i = 0; i < emac->tx_ch_num; i++)
+		napi_enable(&emac->tx_chns[i].napi_tx);
+	napi_enable(&emac->napi_rx);
+
+	/* start PHY */
+	phy_start(ndev->phydev);
+
+	prueth->emacs_initialized++;
+
+	queue_work(system_long_wq, &emac->stats_work.work);
+
+	return 0;
+
+reset_tx_chan:
+	/* Since interface is not yet up, there is wouldn't be
+	 * any SKB for completion. So set false to free_skb
+	 */
+	prueth_reset_tx_chan(emac, i, false);
+reset_rx_mgm_chn:
+	prueth_reset_rx_chan(&emac->rx_mgm_chn,
+			     PRUETH_MAX_RX_MGM_FLOWS_SR1, true);
+reset_rx_chn:
+	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false);
+stop:
+	prueth_emac_stop(emac);
+free_rx_mgmt_ts_irq:
+	free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1],
+		 emac);
+free_rx_mgm_rsp_irq:
+	free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1],
+		 emac);
+free_rx_irq:
+	free_irq(emac->rx_chns.irq[rx_flow], emac);
+cleanup_napi:
+	prueth_ndev_del_tx_napi(emac, emac->tx_ch_num);
+cleanup_rx_mgm:
+	prueth_cleanup_rx_chns(emac, &emac->rx_mgm_chn,
+			       PRUETH_MAX_RX_MGM_FLOWS_SR1);
+cleanup_rx:
+	prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows);
+cleanup_tx:
+	prueth_cleanup_tx_chns(emac);
+
+	return ret;
+}
+
+/**
+ * emac_ndo_stop - EMAC device stop
+ * @ndev: network adapter device
+ *
+ * Called when system wants to stop or down the interface.
+ *
+ * Return: Always 0 (Success)
+ */
+static int emac_ndo_stop(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	int rx_flow = PRUETH_RX_FLOW_DATA_SR1;
+	struct prueth *prueth = emac->prueth;
+	int max_rx_flows;
+	int ret, i;
+
+	/* inform the upper layers. */
+	netif_tx_stop_all_queues(ndev);
+
+	/* block packets from wire */
+	if (ndev->phydev)
+		phy_stop(ndev->phydev);
+
+	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
+
+	emac_send_command_sr1(emac, ICSSG_SHUTDOWN_CMD_SR1);
+
+	atomic_set(&emac->tdown_cnt, emac->tx_ch_num);
+	/* ensure new tdown_cnt value is visible */
+	smp_mb__after_atomic();
+	/* tear down and disable UDMA channels */
+	reinit_completion(&emac->tdown_complete);
+	for (i = 0; i < emac->tx_ch_num; i++)
+		k3_udma_glue_tdown_tx_chn(emac->tx_chns[i].tx_chn, false);
+
+	ret = wait_for_completion_timeout(&emac->tdown_complete,
+					  msecs_to_jiffies(1000));
+	if (!ret)
+		netdev_err(ndev, "tx teardown timeout\n");
+
+	prueth_reset_tx_chan(emac, emac->tx_ch_num, true);
+	for (i = 0; i < emac->tx_ch_num; i++)
+		napi_disable(&emac->tx_chns[i].napi_tx);
+
+	max_rx_flows = PRUETH_MAX_RX_FLOWS_SR1;
+	k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true);
+
+	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true);
+	/* Teardown RX MGM channel */
+	k3_udma_glue_tdown_rx_chn(emac->rx_mgm_chn.rx_chn, true);
+	prueth_reset_rx_chan(&emac->rx_mgm_chn,
+			     PRUETH_MAX_RX_MGM_FLOWS_SR1, true);
+
+	napi_disable(&emac->napi_rx);
+
+	/* Destroying the queued work in ndo_stop() */
+	cancel_delayed_work_sync(&emac->stats_work);
+
+	/* stop PRUs */
+	prueth_emac_stop(emac);
+
+	free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1], emac);
+	free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1], emac);
+	free_irq(emac->rx_chns.irq[rx_flow], emac);
+	prueth_ndev_del_tx_napi(emac, emac->tx_ch_num);
+	prueth_cleanup_tx_chns(emac);
+
+	prueth_cleanup_rx_chns(emac, &emac->rx_mgm_chn, PRUETH_MAX_RX_MGM_FLOWS_SR1);
+	prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows);
+
+	prueth->emacs_initialized--;
+
+	return 0;
+}
+
+static void emac_ndo_set_rx_mode_sr1(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	bool allmulti = ndev->flags & IFF_ALLMULTI;
+	bool promisc = ndev->flags & IFF_PROMISC;
+	struct prueth *prueth = emac->prueth;
+	int slice = prueth_emac_slice(emac);
+
+	if (promisc) {
+		icssg_class_promiscuous_sr1(prueth->miig_rt, slice);
+		return;
+	}
+
+	if (allmulti) {
+		icssg_class_default(prueth->miig_rt, slice, 1, true);
+		return;
+	}
+
+	icssg_class_default(prueth->miig_rt, slice, 0, true);
+	if (!netdev_mc_empty(ndev)) {
+		/* program multicast address list into Classifier */
+		icssg_class_add_mcast_sr1(prueth->miig_rt, slice, ndev);
+	}
+}
+
+static const struct net_device_ops emac_netdev_ops = {
+	.ndo_open = emac_ndo_open,
+	.ndo_stop = emac_ndo_stop,
+	.ndo_start_xmit = emac_ndo_start_xmit,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_tx_timeout = emac_ndo_tx_timeout,
+	.ndo_set_rx_mode = emac_ndo_set_rx_mode_sr1,
+	.ndo_eth_ioctl = emac_ndo_ioctl,
+	.ndo_get_stats64 = emac_ndo_get_stats64,
+	.ndo_get_phys_port_name = emac_ndo_get_phys_port_name,
+};
+
+static int prueth_netdev_init(struct prueth *prueth,
+			      struct device_node *eth_node)
+{
+	struct prueth_emac *emac;
+	struct net_device *ndev;
+	enum prueth_port port;
+	enum prueth_mac mac;
+	/* Only enable one TX channel due to timeouts when
+	 * using multiple channels */
+	int num_tx_chn = 1;
+	int ret;
+
+	port = prueth_node_port(eth_node);
+	if (port == PRUETH_PORT_INVALID)
+		return -EINVAL;
+
+	mac = prueth_node_mac(eth_node);
+	if (mac == PRUETH_MAC_INVALID)
+		return -EINVAL;
+
+	ndev = alloc_etherdev_mq(sizeof(*emac), num_tx_chn);
+	if (!ndev)
+		return -ENOMEM;
+
+	emac = netdev_priv(ndev);
+	emac->is_sr1 = 1;
+	emac->prueth = prueth;
+	emac->ndev = ndev;
+	emac->port_id = port;
+	emac->cmd_wq = create_singlethread_workqueue("icssg_cmd_wq");
+	if (!emac->cmd_wq) {
+		ret = -ENOMEM;
+		goto free_ndev;
+	}
+
+	INIT_DELAYED_WORK(&emac->stats_work, emac_stats_work_handler);
+
+	ret = pruss_request_mem_region(prueth->pruss,
+				       port == PRUETH_PORT_MII0 ?
+				       PRUSS_MEM_DRAM0 : PRUSS_MEM_DRAM1,
+				       &emac->dram);
+	if (ret) {
+		dev_err(prueth->dev, "unable to get DRAM: %d\n", ret);
+		ret = -ENOMEM;
+		goto free_wq;
+	}
+
+	/* SR1.0 uses a dedicated high priority channel
+	 * to send commands to the firmware
+	 */
+	emac->tx_ch_num = 2;
+
+	SET_NETDEV_DEV(ndev, prueth->dev);
+	spin_lock_init(&emac->lock);
+	mutex_init(&emac->cmd_lock);
+
+	emac->phy_node = of_parse_phandle(eth_node, "phy-handle", 0);
+	if (!emac->phy_node && !of_phy_is_fixed_link(eth_node)) {
+		dev_err(prueth->dev, "couldn't find phy-handle\n");
+		ret = -ENODEV;
+		goto free;
+	} else if (of_phy_is_fixed_link(eth_node)) {
+		ret = of_phy_register_fixed_link(eth_node);
+		if (ret) {
+			ret = dev_err_probe(prueth->dev, ret,
+					    "failed to register fixed-link phy\n");
+			goto free;
+		}
+
+		emac->phy_node = eth_node;
+	}
+
+	ret = of_get_phy_mode(eth_node, &emac->phy_if);
+	if (ret) {
+		dev_err(prueth->dev, "could not get phy-mode property\n");
+		goto free;
+	}
+
+	if (emac->phy_if != PHY_INTERFACE_MODE_MII &&
+	    !phy_interface_mode_is_rgmii(emac->phy_if)) {
+		dev_err(prueth->dev, "PHY mode unsupported %s\n", phy_modes(emac->phy_if));
+		ret = -EINVAL;
+		goto free;
+	}
+
+	/* AM65 SR2.0 has TX Internal delay always enabled by hardware
+	 * and it is not possible to disable TX Internal delay. The below
+	 * switch case block describes how we handle different phy modes
+	 * based on hardware restriction.
+	 */
+	switch (emac->phy_if) {
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		emac->phy_if = PHY_INTERFACE_MODE_RGMII_RXID;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		emac->phy_if = PHY_INTERFACE_MODE_RGMII;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		dev_err(prueth->dev, "RGMII mode without TX delay is not supported");
+		ret = -EINVAL;
+		goto free;
+	default:
+		break;
+	}
+
+	/* get mac address from DT and set private and netdev addr */
+	ret = of_get_ethdev_address(eth_node, ndev);
+	if (!is_valid_ether_addr(ndev->dev_addr)) {
+		eth_hw_addr_random(ndev);
+		dev_warn(prueth->dev, "port %d: using random MAC addr: %pM\n",
+			 port, ndev->dev_addr);
+	}
+	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
+
+	ndev->min_mtu = PRUETH_MIN_PKT_SIZE;
+	ndev->max_mtu = PRUETH_MAX_MTU;
+	ndev->netdev_ops = &emac_netdev_ops;
+	ndev->ethtool_ops = &icssg_ethtool_ops;
+	ndev->hw_features = NETIF_F_SG;
+	ndev->features = ndev->hw_features;
+
+	netif_napi_add(ndev, &emac->napi_rx, emac_napi_rx_poll);
+	prueth->emac[mac] = emac;
+
+	return 0;
+
+free:
+	pruss_release_mem_region(prueth->pruss, &emac->dram);
+free_wq:
+	destroy_workqueue(emac->cmd_wq);
+free_ndev:
+	emac->ndev = NULL;
+	prueth->emac[mac] = NULL;
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static int prueth_probe(struct platform_device *pdev)
+{
+	struct device_node *eth_node, *eth_ports_node;
+	struct device_node  *eth0_node = NULL;
+	struct device_node  *eth1_node = NULL;
+	struct device *dev = &pdev->dev;
+	struct device_node *np;
+	struct prueth *prueth;
+	struct pruss *pruss;
+	u32 msmc_ram_size;
+	int i, ret;
+
+	np = dev->of_node;
+
+	prueth = devm_kzalloc(dev, sizeof(*prueth), GFP_KERNEL);
+	if (!prueth)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, prueth);
+	prueth->pdev = pdev;
+	prueth->pdata = *(const struct prueth_pdata *)device_get_match_data(dev);
+
+	prueth->dev = dev;
+	eth_ports_node = of_get_child_by_name(np, "ethernet-ports");
+	if (!eth_ports_node)
+		return -ENOENT;
+
+	for_each_child_of_node(eth_ports_node, eth_node) {
+		u32 reg;
+
+		if (strcmp(eth_node->name, "port"))
+			continue;
+		ret = of_property_read_u32(eth_node, "reg", &reg);
+		if (ret < 0) {
+			dev_err(dev, "%pOF error reading port_id %d\n",
+				eth_node, ret);
+		}
+
+		of_node_get(eth_node);
+
+		if (reg == 0) {
+			eth0_node = eth_node;
+			if (!of_device_is_available(eth0_node)) {
+				of_node_put(eth0_node);
+				eth0_node = NULL;
+			}
+		} else if (reg == 1) {
+			eth1_node = eth_node;
+			if (!of_device_is_available(eth1_node)) {
+				of_node_put(eth1_node);
+				eth1_node = NULL;
+			}
+		} else {
+			dev_err(dev, "port reg should be 0 or 1\n");
+		}
+	}
+
+	of_node_put(eth_ports_node);
+
+	/* At least one node must be present and available else we fail */
+	if (!eth0_node && !eth1_node) {
+		dev_err(dev, "neither port0 nor port1 node available\n");
+		return -ENODEV;
+	}
+
+	if (eth0_node == eth1_node) {
+		dev_err(dev, "port0 and port1 can't have same reg\n");
+		of_node_put(eth0_node);
+		return -ENODEV;
+	}
+
+	prueth->eth_node[PRUETH_MAC0] = eth0_node;
+	prueth->eth_node[PRUETH_MAC1] = eth1_node;
+
+	prueth->miig_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-g-rt");
+	if (IS_ERR(prueth->miig_rt)) {
+		dev_err(dev, "couldn't get ti,mii-g-rt syscon regmap\n");
+		return -ENODEV;
+	}
+
+	prueth->mii_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-rt");
+	if (IS_ERR(prueth->mii_rt)) {
+		dev_err(dev, "couldn't get ti,mii-rt syscon regmap\n");
+		return -ENODEV;
+	}
+
+	if (eth0_node) {
+		ret = prueth_get_cores(prueth, ICSS_SLICE0, true);
+		if (ret)
+			goto put_cores;
+	}
+
+	if (eth1_node) {
+		ret = prueth_get_cores(prueth, ICSS_SLICE1, true);
+		if (ret)
+			goto put_cores;
+	}
+
+	pruss = pruss_get(eth0_node ?
+			  prueth->pru[ICSS_SLICE0] : prueth->pru[ICSS_SLICE1]);
+	if (IS_ERR(pruss)) {
+		ret = PTR_ERR(pruss);
+		dev_err(dev, "unable to get pruss handle\n");
+		goto put_cores;
+	}
+
+	prueth->pruss = pruss;
+
+	ret = pruss_request_mem_region(pruss, PRUSS_MEM_SHRD_RAM2,
+				       &prueth->shram);
+	if (ret) {
+		dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret);
+		goto put_pruss;
+	}
+
+	prueth->sram_pool = of_gen_pool_get(np, "sram", 0);
+	if (!prueth->sram_pool) {
+		dev_err(dev, "unable to get SRAM pool\n");
+		ret = -ENODEV;
+
+		goto put_mem;
+	}
+
+	msmc_ram_size = MSMC_RAM_SIZE_SR1;
+
+	prueth->msmcram.va = (void __iomem *)gen_pool_alloc(prueth->sram_pool,
+							    msmc_ram_size);
+
+	if (!prueth->msmcram.va) {
+		ret = -ENOMEM;
+		dev_err(dev, "unable to allocate MSMC resource\n");
+		goto put_mem;
+	}
+	prueth->msmcram.pa = gen_pool_virt_to_phys(prueth->sram_pool,
+						   (unsigned long)prueth->msmcram.va);
+	prueth->msmcram.size = msmc_ram_size;
+	memset_io(prueth->msmcram.va, 0, msmc_ram_size);
+	dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa,
+		prueth->msmcram.va, prueth->msmcram.size);
+
+	if (eth0_node) {
+		ret = prueth_netdev_init(prueth, eth0_node);
+		if (ret) {
+			dev_err_probe(dev, ret, "netdev init %s failed\n",
+				      eth0_node->name);
+			goto free_pool;
+		}
+
+		if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL))
+			prueth->emac[PRUETH_MAC0]->half_duplex = 1;
+	}
+
+	if (eth1_node) {
+		ret = prueth_netdev_init(prueth, eth1_node);
+		if (ret) {
+			dev_err_probe(dev, ret, "netdev init %s failed\n",
+				      eth1_node->name);
+			goto netdev_exit;
+		}
+
+		if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL))
+			prueth->emac[PRUETH_MAC1]->half_duplex = 1;
+	}
+
+	/* register the network devices */
+	if (eth0_node) {
+		ret = register_netdev(prueth->emac[PRUETH_MAC0]->ndev);
+		if (ret) {
+			dev_err(dev, "can't register netdev for port MII0\n");
+			goto netdev_exit;
+		}
+
+		prueth->registered_netdevs[PRUETH_MAC0] = prueth->emac[PRUETH_MAC0]->ndev;
+		emac_phy_connect(prueth->emac[PRUETH_MAC0]);
+		phy_attached_info(prueth->emac[PRUETH_MAC0]->ndev->phydev);
+	}
+
+	if (eth1_node) {
+		ret = register_netdev(prueth->emac[PRUETH_MAC1]->ndev);
+		if (ret) {
+			dev_err(dev, "can't register netdev for port MII1\n");
+			goto netdev_unregister;
+		}
+
+		prueth->registered_netdevs[PRUETH_MAC1] = prueth->emac[PRUETH_MAC1]->ndev;
+		emac_phy_connect(prueth->emac[PRUETH_MAC1]);
+		phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev);
+	}
+
+	dev_info(dev, "TI PRU SR1.0 ethernet driver initialized: %s EMAC mode\n",
+		 (!eth0_node || !eth1_node) ? "single" : "dual");
+
+	if (eth1_node)
+		of_node_put(eth1_node);
+	if (eth0_node)
+		of_node_put(eth0_node);
+
+	return 0;
+
+netdev_unregister:
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		if (!prueth->registered_netdevs[i])
+			continue;
+
+		if (prueth->emac[i]->ndev->phydev) {
+			phy_disconnect(prueth->emac[i]->ndev->phydev);
+			prueth->emac[i]->ndev->phydev = NULL;
+		}
+		unregister_netdev(prueth->registered_netdevs[i]);
+	}
+
+netdev_exit:
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		eth_node = prueth->eth_node[i];
+		if (!eth_node)
+			continue;
+
+		prueth_netdev_exit(prueth, eth_node);
+	}
+
+free_pool:
+	gen_pool_free(prueth->sram_pool,
+		      (unsigned long)prueth->msmcram.va, msmc_ram_size);
+
+put_mem:
+	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+
+put_pruss:
+	pruss_put(prueth->pruss);
+
+put_cores:
+	if (eth1_node) {
+		prueth_put_cores(prueth, ICSS_SLICE1);
+		of_node_put(eth1_node);
+	}
+
+	if (eth0_node) {
+		prueth_put_cores(prueth, ICSS_SLICE0);
+		of_node_put(eth0_node);
+	}
+
+	return ret;
+}
+
+static void prueth_remove(struct platform_device *pdev)
+{
+	struct prueth *prueth = platform_get_drvdata(pdev);
+	struct device_node *eth_node;
+	int i;
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		if (!prueth->registered_netdevs[i])
+			continue;
+		phy_stop(prueth->emac[i]->ndev->phydev);
+		phy_disconnect(prueth->emac[i]->ndev->phydev);
+		prueth->emac[i]->ndev->phydev = NULL;
+		unregister_netdev(prueth->registered_netdevs[i]);
+	}
+
+	for (i = 0; i < PRUETH_NUM_MACS; i++) {
+		eth_node = prueth->eth_node[i];
+		if (!eth_node)
+			continue;
+
+		prueth_netdev_exit(prueth, eth_node);
+	}
+
+	gen_pool_free(prueth->sram_pool,
+		      (unsigned long)prueth->msmcram.va,
+		      MSMC_RAM_SIZE_SR1);
+
+	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+
+	pruss_put(prueth->pruss);
+
+	if (prueth->eth_node[PRUETH_MAC1])
+		prueth_put_cores(prueth, ICSS_SLICE1);
+
+	if (prueth->eth_node[PRUETH_MAC0])
+		prueth_put_cores(prueth, ICSS_SLICE0);
+}
+
+static const struct prueth_pdata am654_sr1_icssg_pdata = {
+	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
+};
+
+static const struct of_device_id prueth_dt_match[] = {
+	{ .compatible = "ti,am654-sr1-icssg-prueth", .data = &am654_sr1_icssg_pdata },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, prueth_dt_match);
+
+static struct platform_driver prueth_driver = {
+	.probe = prueth_probe,
+	.remove_new = prueth_remove,
+	.driver = {
+		.name = "icssg-prueth-sr1",
+		.of_match_table = prueth_dt_match,
+		.pm = &prueth_dev_pm_ops,
+	},
+};
+module_platform_driver(prueth_driver);
+
+MODULE_AUTHOR("Roger Quadros <rogerq@ti.com>");
+MODULE_AUTHOR("Md Danish Anwar <danishanwar@ti.com>");
+MODULE_AUTHOR("Diogo Ivo <diogo.ivo@siemens.com>");
+MODULE_DESCRIPTION(PRUETH_MODULE_DESCRIPTION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
index 05cc7aab1ec8..739bae8e11ee 100644
--- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
+++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
@@ -22,6 +22,7 @@ struct k3_cppi_desc_pool {
 	size_t			mem_size;
 	size_t			num_desc;
 	struct gen_pool		*gen_pool;
+	void			**desc_infos;
 };
 
 void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool)
@@ -37,7 +38,11 @@ void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool)
 		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem,
 				  pool->dma_addr);
 
+	kfree(pool->desc_infos);
+
 	gen_pool_destroy(pool->gen_pool);	/* frees pool->name */
+
+	kfree(pool);
 }
 EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_destroy);
 
@@ -50,7 +55,7 @@ k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
 	const char *pool_name = NULL;
 	int ret = -ENOMEM;
 
-	pool = devm_kzalloc(dev, sizeof(*pool), GFP_KERNEL);
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool)
 		return ERR_PTR(ret);
 
@@ -62,18 +67,21 @@ k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
 	pool_name = kstrdup_const(name ? name : dev_name(pool->dev),
 				  GFP_KERNEL);
 	if (!pool_name)
-		return ERR_PTR(-ENOMEM);
+		goto gen_pool_create_fail;
 
 	pool->gen_pool = gen_pool_create(ilog2(pool->desc_size), -1);
 	if (!pool->gen_pool) {
-		ret = -ENOMEM;
-		dev_err(pool->dev, "pool create failed %d\n", ret);
 		kfree_const(pool_name);
 		goto gen_pool_create_fail;
 	}
 
 	pool->gen_pool->name = pool_name;
 
+	pool->desc_infos = kcalloc(pool->num_desc,
+				   sizeof(*pool->desc_infos), GFP_KERNEL);
+	if (!pool->desc_infos)
+		goto gen_pool_desc_infos_alloc_fail;
+
 	pool->cpumem = dma_alloc_coherent(pool->dev, pool->mem_size,
 					  &pool->dma_addr, GFP_KERNEL);
 
@@ -94,9 +102,11 @@ gen_pool_add_virt_fail:
 	dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem,
 			  pool->dma_addr);
 dma_alloc_fail:
+	kfree(pool->desc_infos);
+gen_pool_desc_infos_alloc_fail:
 	gen_pool_destroy(pool->gen_pool);	/* frees pool->name */
 gen_pool_create_fail:
-	devm_kfree(pool->dev, pool);
+	kfree(pool);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_create_name);
@@ -132,5 +142,31 @@ size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool)
 }
 EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_avail);
 
+size_t k3_cppi_desc_pool_desc_size(const struct k3_cppi_desc_pool *pool)
+{
+	return pool->desc_size;
+}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_size);
+
+void *k3_cppi_desc_pool_cpuaddr(const struct k3_cppi_desc_pool *pool)
+{
+	return pool->cpumem;
+}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_cpuaddr);
+
+void k3_cppi_desc_pool_desc_info_set(struct k3_cppi_desc_pool *pool,
+				     int desc_idx, void *info)
+{
+	pool->desc_infos[desc_idx] = info;
+}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_info_set);
+
+void *k3_cppi_desc_pool_desc_info(const struct k3_cppi_desc_pool *pool,
+				  int desc_idx)
+{
+	return pool->desc_infos[desc_idx];
+}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_info);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("TI K3 CPPI5 descriptors pool API");
diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.h b/drivers/net/ethernet/ti/k3-cppi-desc-pool.h
index a7e3fa5e7b62..851d352b338b 100644
--- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.h
+++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.h
@@ -26,5 +26,11 @@ k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma);
 void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool);
 void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr);
 size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool);
+size_t k3_cppi_desc_pool_desc_size(const struct k3_cppi_desc_pool *pool);
+void *k3_cppi_desc_pool_cpuaddr(const struct k3_cppi_desc_pool *pool);
+void k3_cppi_desc_pool_desc_info_set(struct k3_cppi_desc_pool *pool,
+				     int desc_idx, void *info);
+void *k3_cppi_desc_pool_desc_info(const struct k3_cppi_desc_pool *pool,
+				  int desc_idx);
 
 #endif /* K3_CPPI_DESC_POOL_H_ */
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index da287ef65be7..00773f5e4d7e 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -20,6 +20,7 @@ config VIA_RHINE
 	tristate "VIA Rhine support"
 	depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP)
 	depends on PCI || ARCH_VT8500 || COMPILE_TEST
+	depends on HAS_IOPORT
 	depends on HAS_DMA
 	select CRC32
 	select MII
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 1c6b2a9bba08..55fff4d0d380 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2294,7 +2294,7 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu)
 	int ret = 0;
 
 	if (!netif_running(dev)) {
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 		goto out_0;
 	}
 
@@ -2336,7 +2336,7 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu)
 		tmp_vptr->rx = rx;
 		tmp_vptr->tx = tx;
 
-		dev->mtu = new_mtu;
+		WRITE_ONCE(dev->mtu, new_mtu);
 
 		velocity_init_registers(vptr, VELOCITY_INIT_COLD);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 945c13d1a982..3662483bfe2e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1408,7 +1408,7 @@ int wx_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct wx *wx = netdev_priv(netdev);
 
-	netdev->mtu = new_mtu;
+	WRITE_ONCE(netdev->mtu, new_mtu);
 	wx_set_rx_buffer_len(wx);
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 93295916b1d2..5f502265f0a6 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -302,7 +302,7 @@ irqreturn_t txgbe_link_irq_handler(int irq, void *data)
 	status = rd32(wx, TXGBE_CFG_PORT_ST);
 	up = !!(status & TXGBE_CFG_PORT_ST_LINK_UP);
 
-	phylink_mac_change(wx->phylink, up);
+	phylink_pcs_change(&txgbe->xpcs->pcs, up);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 807ead678551..fa5500decc96 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -359,6 +359,7 @@
  * @app2:         MM2S/S2MM User Application Field 2.
  * @app3:         MM2S/S2MM User Application Field 3.
  * @app4:         MM2S/S2MM User Application Field 4.
+ * @skb:          Pointer to SKB transferred using DMA
  */
 struct axidma_bd {
 	u32 next;	/* Physical address of next buffer descriptor */
@@ -399,7 +400,6 @@ struct skbuf_dma_descriptor {
  * struct axienet_local - axienet private per device data
  * @ndev:	Pointer for net_device to which it will be attached.
  * @dev:	Pointer to device structure
- * @phy_node:	Pointer to device node structure
  * @phylink:	Pointer to phylink instance
  * @phylink_config: phylink configuration settings
  * @pcs_phy:	Reference to PCS/PMA PHY if used
@@ -537,7 +537,7 @@ struct axienet_local {
 };
 
 /**
- * struct axiethernet_option - Used to set axi ethernet hardware options
+ * struct axienet_option - Used to set axi ethernet hardware options
  * @opt:	Option to be set.
  * @reg:	Register offset to be written for setting the option
  * @m_or:	Mask to be ORed for setting the option in the register
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index aaf780fd4f5e..c29809cd9201 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1641,7 +1641,7 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu)
 		XAE_TRL_SIZE) > lp->rxmem)
 		return -EINVAL;
 
-	ndev->mtu = new_mtu;
+	WRITE_ONCE(ndev->mtu, new_mtu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 2f07fde361aa..9ca2643c921e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -20,7 +20,14 @@
 #define DEFAULT_MDIO_FREQ	2500000 /* 2.5 MHz */
 #define DEFAULT_HOST_CLOCK	150000000 /* 150 MHz */
 
-/* Wait till MDIO interface is ready to accept a new transaction.*/
+/**
+ * axienet_mdio_wait_until_ready - MDIO wait function
+ * @lp:	Pointer to axienet local data structure.
+ *
+ * Return :	0 on success, Negative value on errors
+ *
+ * Wait till MDIO interface is ready to accept a new transaction.
+ */
 static int axienet_mdio_wait_until_ready(struct axienet_local *lp)
 {
 	u32 val;
@@ -30,14 +37,24 @@ static int axienet_mdio_wait_until_ready(struct axienet_local *lp)
 				  1, 20000);
 }
 
-/* Enable the MDIO MDC. Called prior to a read/write operation */
+/**
+ * axienet_mdio_mdc_enable - MDIO MDC enable function
+ * @lp:	Pointer to axienet local data structure.
+ *
+ * Enable the MDIO MDC. Called prior to a read/write operation
+ */
 static void axienet_mdio_mdc_enable(struct axienet_local *lp)
 {
 	axienet_iow(lp, XAE_MDIO_MC_OFFSET,
 		    ((u32)lp->mii_clk_div | XAE_MDIO_MC_MDIOEN_MASK));
 }
 
-/* Disable the MDIO MDC. Called after a read/write operation*/
+/**
+ * axienet_mdio_mdc_disable - MDIO MDC disable function
+ * @lp:	Pointer to axienet local data structure.
+ *
+ * Disable the MDIO MDC. Called after a read/write operation
+ */
 static void axienet_mdio_mdc_disable(struct axienet_local *lp)
 {
 	u32 mc_reg;
diff --git a/drivers/net/ethernet/xircom/Kconfig b/drivers/net/ethernet/xircom/Kconfig
index 7497b9bea511..bfbdcf758afb 100644
--- a/drivers/net/ethernet/xircom/Kconfig
+++ b/drivers/net/ethernet/xircom/Kconfig
@@ -19,7 +19,7 @@ if NET_VENDOR_XIRCOM
 
 config PCMCIA_XIRC2PS
 	tristate "Xircom 16-bit PCMCIA support"
-	depends on PCMCIA
+	depends on PCMCIA && HAS_IOPORT
 	help
 	  Say Y here if you intend to attach a Xircom 16-bit PCMCIA (PC-card)
 	  Ethernet or Fast Ethernet card to your computer.
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index e9bc38fd2025..a31d5d5e6593 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1366,10 +1366,10 @@ do_config(struct net_device *dev, struct ifmap *map)
 	    return -EINVAL;
 	if (!map->port) {
 	    local->probe_port = 1;
-	    dev->if_port = 1;
+	    WRITE_ONCE(dev->if_port, 1);
 	} else {
 	    local->probe_port = 0;
-	    dev->if_port = map->port;
+	    WRITE_ONCE(dev->if_port, map->port);
 	}
 	netdev_info(dev, "switching to %s port\n", if_names[dev->if_port]);
 	do_reset(dev,1);  /* not the fine way :-) */
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index e0d26148dfd9..8aff6a73ca0a 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1233,7 +1233,7 @@ static int ixp4xx_eth_change_mtu(struct net_device *dev, int new_mtu)
 			return ret;
 	}
 
-	dev->mtu = new_mtu;
+	WRITE_ONCE(dev->mtu, new_mtu);
 
 	return 0;
 }
author	Linus Torvalds <torvalds@linux-foundation.org>	2024-05-15 05:42:24 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2024-05-15 05:42:24 +0300
commit	1b294a1f35616977caddaddf3e9d28e576a1adbc (patch)
tree	723a406740083006b8f8724b5c5e532d4efa431d /drivers/net/ethernet
parent	b850dc206a57ae272c639e31ac202ec0c2f46960 (diff)
parent	654de42f3fc6edc29d743c1dbcd1424f7793f63d (diff)
download	linux-1b294a1f35616977caddaddf3e9d28e576a1adbc.tar.xz