Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

40 files changed, 5045 insertions, 4233 deletions

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 9183d480b70b..f269952d207d 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -28,6 +28,7 @@ ice-y := ice_main.o	\
 	 ice_flow.o	\
 	 ice_idc.o	\
 	 ice_devlink.o	\
+	 ice_ddp.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
 	 ice_ethtool.o  \
@@ -42,8 +43,8 @@ ice-$(CONFIG_PCI_IOV) +=	\
 	ice_vf_vsi_vlan_ops.o	\
 	ice_vf_lib.o
 ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o
-ice-$(CONFIG_TTY) += ice_gnss.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
 ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
 ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o
+ice-$(CONFIG_ICE_GNSS) += ice_gnss.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 713069f809ec..b0e29e342401 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -39,7 +39,9 @@
 #include <linux/avf/virtchnl.h>
 #include <linux/cpu_rmap.h>
 #include <linux/dim.h>
+#include <linux/gnss.h>
 #include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/ip.h>
@@ -121,6 +123,8 @@
 
 #define ICE_MAX_MTU	(ICE_AQ_SET_MAC_FRAME_SIZE_MAX - ICE_ETH_PKT_HDR_PAD)
 
+#define ICE_MAX_TSO_SIZE 131072
+
 #define ICE_UP_TABLE_TRANSLATE(val, i) \
 		(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
 		  ICE_AQ_VSI_UP_TABLE_UP##i##_M)
@@ -352,7 +356,6 @@ struct ice_vsi {
 
 	struct ice_vf *vf;		/* VF associated with this VSI */
 
-	u16 ethtype;			/* Ethernet protocol for pause frame */
 	u16 num_gfltr;
 	u16 num_bfltr;
 
@@ -565,9 +568,8 @@ struct ice_pf {
 	struct mutex adev_mutex;	/* lock to protect aux device access */
 	u32 msg_enable;
 	struct ice_ptp ptp;
-	struct tty_driver *ice_gnss_tty_driver;
-	struct tty_port *gnss_tty_port[ICE_GNSS_TTY_MINOR_DEVICES];
-	struct gnss_serial *gnss_serial[ICE_GNSS_TTY_MINOR_DEVICES];
+	struct gnss_serial *gnss_serial;
+	struct gnss_device *gnss_dev;
 	u16 num_rdma_msix;		/* Total MSIX vectors for RDMA driver */
 	u16 rdma_base_vector;
 
@@ -889,7 +891,7 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp,
 int ice_up(struct ice_vsi *vsi);
 int ice_down(struct ice_vsi *vsi);
 int ice_down_up(struct ice_vsi *vsi);
-int ice_vsi_cfg(struct ice_vsi *vsi);
+int ice_vsi_cfg_lan(struct ice_vsi *vsi);
 struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
 int ice_vsi_determine_xdp_res(struct ice_vsi *vsi);
 int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog);
@@ -907,6 +909,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
+void ice_deinit_rdma(struct ice_pf *pf);
 const char *ice_aq_str(enum ice_aq_err aq_err);
 bool ice_is_wol_supported(struct ice_hw *hw);
 void ice_fdir_del_all_fltrs(struct ice_vsi *vsi);
@@ -931,6 +934,8 @@ int ice_open(struct net_device *netdev);
 int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 void ice_service_task_schedule(struct ice_pf *pf);
+int ice_load(struct ice_pf *pf);
+void ice_unload(struct ice_pf *pf);
 
 /**
  * ice_set_rdma_cap - enable RDMA support
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 958c1e435232..838d9b274d68 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1659,14 +1659,24 @@ struct ice_aqc_lldp_get_mib {
 #define ICE_AQ_LLDP_TX_ACTIVE			0
 #define ICE_AQ_LLDP_TX_SUSPENDED		1
 #define ICE_AQ_LLDP_TX_FLUSHED			3
+/* DCBX mode */
+#define ICE_AQ_LLDP_DCBX_M			GENMASK(7, 6)
+#define ICE_AQ_LLDP_DCBX_NA			0
+#define ICE_AQ_LLDP_DCBX_CEE			1
+#define ICE_AQ_LLDP_DCBX_IEEE			2
+
+	u8 state;
+#define ICE_AQ_LLDP_MIB_CHANGE_STATE_M		BIT(0)
+#define ICE_AQ_LLDP_MIB_CHANGE_EXECUTED		0
+#define ICE_AQ_LLDP_MIB_CHANGE_PENDING		1
+
 /* The following bytes are reserved for the Get LLDP MIB command (0x0A00)
  * and in the LLDP MIB Change Event (0x0A01). They are valid for the
  * Get LLDP MIB (0x0A00) response only.
  */
-	u8 reserved1;
 	__le16 local_len;
 	__le16 remote_len;
-	u8 reserved2[2];
+	u8 reserved[2];
 	__le32 addr_high;
 	__le32 addr_low;
 };
@@ -1677,6 +1687,9 @@ struct ice_aqc_lldp_set_mib_change {
 	u8 command;
 #define ICE_AQ_LLDP_MIB_UPDATE_ENABLE		0x0
 #define ICE_AQ_LLDP_MIB_UPDATE_DIS		0x1
+#define ICE_AQ_LLDP_MIB_PENDING_M		BIT(1)
+#define ICE_AQ_LLDP_MIB_PENDING_DISABLE		0
+#define ICE_AQ_LLDP_MIB_PENDING_ENABLE		1
 	u8 reserved[15];
 };
 
@@ -2329,6 +2342,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_lldp_set_local_mib			= 0x0A08,
 	ice_aqc_opc_lldp_stop_start_specific_agent	= 0x0A09,
 	ice_aqc_opc_lldp_filter_ctrl			= 0x0A0A,
+	ice_aqc_opc_lldp_execute_pending_mib		= 0x0A0B,
 
 	/* RSS commands */
 	ice_aqc_opc_set_rss_key				= 0x0B02,
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 554095b25f44..1911d644dfa8 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -355,9 +355,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring)
 {
 	if (ice_ring_uses_build_skb(rx_ring))
 		return ICE_SKB_PAD;
-	else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
-		return XDP_PACKET_HEADROOM;
-
 	return 0;
 }
 
@@ -495,7 +492,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 {
 	struct device *dev = ice_pf_to_dev(ring->vsi->back);
-	u16 num_bufs = ICE_DESC_UNUSED(ring);
+	u32 num_bufs = ICE_RX_DESC_UNUSED(ring);
 	int err;
 
 	ring->rx_buf_len = ring->vsi->rx_buf_len;
@@ -503,8 +500,10 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 	if (ring->vsi->type == ICE_VSI_PF) {
 		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 			/* coverity[check_return] */
-			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->q_index, ring->q_vector->napi.napi_id);
+			__xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					   ring->q_index,
+					   ring->q_vector->napi.napi_id,
+					   ring->vsi->rx_buf_len);
 
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
@@ -524,9 +523,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		} else {
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
-				xdp_rxq_info_reg(&ring->xdp_rxq,
-						 ring->netdev,
-						 ring->q_index, ring->q_vector->napi.napi_id);
+				__xdp_rxq_info_reg(&ring->xdp_rxq,
+						   ring->netdev,
+						   ring->q_index,
+						   ring->q_vector->napi.napi_id,
+						   ring->vsi->rx_buf_len);
 
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_PAGE_SHARED,
@@ -536,6 +537,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		}
 	}
 
+	xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+	ring->xdp.data = NULL;
 	err = ice_setup_rx_ctx(ring);
 	if (err) {
 		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 3e08847505ce..c2fda4fa4188 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -208,6 +208,31 @@ bool ice_is_e810t(struct ice_hw *hw)
 }
 
 /**
+ * ice_is_e823
+ * @hw: pointer to the hardware structure
+ *
+ * returns true if the device is E823-L or E823-C based, false if not.
+ */
+bool ice_is_e823(struct ice_hw *hw)
+{
+	switch (hw->device_id) {
+	case ICE_DEV_ID_E823L_BACKPLANE:
+	case ICE_DEV_ID_E823L_SFP:
+	case ICE_DEV_ID_E823L_10G_BASE_T:
+	case ICE_DEV_ID_E823L_1GBE:
+	case ICE_DEV_ID_E823L_QSFP:
+	case ICE_DEV_ID_E823C_BACKPLANE:
+	case ICE_DEV_ID_E823C_QSFP:
+	case ICE_DEV_ID_E823C_SFP:
+	case ICE_DEV_ID_E823C_10G_BASE_T:
+	case ICE_DEV_ID_E823C_SGMII:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
  * ice_clear_pf_cfg - Clear PF configuration
  * @hw: pointer to the hardware structure
  *
@@ -1088,8 +1113,10 @@ int ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_cqinit;
 
-	hw->port_info = devm_kzalloc(ice_hw_to_dev(hw),
-				     sizeof(*hw->port_info), GFP_KERNEL);
+	if (!hw->port_info)
+		hw->port_info = devm_kzalloc(ice_hw_to_dev(hw),
+					     sizeof(*hw->port_info),
+					     GFP_KERNEL);
 	if (!hw->port_info) {
 		status = -ENOMEM;
 		goto err_unroll_cqinit;
@@ -1217,11 +1244,6 @@ void ice_deinit_hw(struct ice_hw *hw)
 	ice_free_hw_tbls(hw);
 	mutex_destroy(&hw->tnl_lock);
 
-	if (hw->port_info) {
-		devm_kfree(ice_hw_to_dev(hw), hw->port_info);
-		hw->port_info = NULL;
-	}
-
 	/* Attempt to disable FW logging before shutting down control queues */
 	ice_cfg_fw_log(hw, false);
 	ice_destroy_all_ctrlq(hw);
@@ -5504,6 +5526,19 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add)
 }
 
 /**
+ * ice_lldp_execute_pending_mib - execute LLDP pending MIB request
+ * @hw: pointer to HW struct
+ */
+int ice_lldp_execute_pending_mib(struct ice_hw *hw)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_execute_pending_mib);
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+}
+
+/**
  * ice_fw_supports_report_dflt_cfg
  * @hw: pointer to the hardware structure
  *
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 4c6a0b5c9304..8ba5f935a092 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -122,7 +122,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures,
 	   bool ena_auto_link_update);
 int
 ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg,
-	       enum ice_fc_mode fc);
+	       enum ice_fc_mode req_mode);
 bool
 ice_phy_caps_equals_cfg(struct ice_aqc_get_phy_caps_data *caps,
 			struct ice_aqc_set_phy_cfg_data *cfg);
@@ -199,6 +199,7 @@ void
 ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
 bool ice_is_e810t(struct ice_hw *hw);
+bool ice_is_e823(struct ice_hw *hw);
 int
 ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 		     struct ice_aqc_txsched_elem_data *buf);
@@ -221,6 +222,7 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw);
 int
 ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add);
+int ice_lldp_execute_pending_mib(struct ice_hw *hw);
 int
 ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		u16 bus_addr, __le16 addr, u8 params, u8 *data,
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 6be02f9b0b8c..c557dfc50aad 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -73,6 +73,9 @@ ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
 
 	if (!ena_update)
 		cmd->command |= ICE_AQ_LLDP_MIB_UPDATE_DIS;
+	else
+		cmd->command |= FIELD_PREP(ICE_AQ_LLDP_MIB_PENDING_M,
+					   ICE_AQ_LLDP_MIB_PENDING_ENABLE);
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
 }
@@ -566,7 +569,7 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
  * @tlv: Organization specific TLV
  * @dcbcfg: Local store to update ETS REC data
  *
- * Currently only IEEE 802.1Qaz TLV is supported, all others
+ * Currently IEEE 802.1Qaz and CEE DCBX TLV are supported, others
  * will be returned
  */
 static void
@@ -585,7 +588,7 @@ ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
 		ice_parse_cee_tlv(tlv, dcbcfg);
 		break;
 	default:
-		break;
+		break; /* Other OUIs not supported */
 	}
 }
 
@@ -964,6 +967,42 @@ int ice_get_dcb_cfg(struct ice_port_info *pi)
 }
 
 /**
+ * ice_get_dcb_cfg_from_mib_change
+ * @pi: port information structure
+ * @event: pointer to the admin queue receive event
+ *
+ * Set DCB configuration from received MIB Change event
+ */
+void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi,
+				     struct ice_rq_event_info *event)
+{
+	struct ice_dcbx_cfg *dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
+	struct ice_aqc_lldp_get_mib *mib;
+	u8 change_type, dcbx_mode;
+
+	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+
+	change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M,  mib->type);
+	if (change_type == ICE_AQ_LLDP_MIB_REMOTE)
+		dcbx_cfg = &pi->qos_cfg.remote_dcbx_cfg;
+
+	dcbx_mode = FIELD_GET(ICE_AQ_LLDP_DCBX_M, mib->type);
+
+	switch (dcbx_mode) {
+	case ICE_AQ_LLDP_DCBX_IEEE:
+		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE;
+		ice_lldp_to_dcb_cfg(event->msg_buf, dcbx_cfg);
+		break;
+
+	case ICE_AQ_LLDP_DCBX_CEE:
+		pi->qos_cfg.desired_dcbx_cfg = pi->qos_cfg.local_dcbx_cfg;
+		ice_cee_to_dcb_cfg((struct ice_aqc_get_cee_dcb_cfg_resp *)
+				   event->msg_buf, pi);
+		break;
+	}
+}
+
+/**
  * ice_init_dcb
  * @hw: pointer to the HW struct
  * @enable_mib_change: enable MIB change event
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h
index 6abf28a14291..be34650a77d5 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.h
@@ -144,6 +144,8 @@ ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
 		   struct ice_dcbx_cfg *dcbcfg);
 int ice_get_dcb_cfg(struct ice_port_info *pi);
 int ice_set_dcb_cfg(struct ice_port_info *pi);
+void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi,
+				     struct ice_rq_event_info *event);
 int ice_init_dcb(struct ice_hw *hw, bool enable_mib_change);
 int
 ice_query_port_ets(struct ice_port_info *pi,
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 0a55c552189a..c6d4926f0fcf 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -862,7 +862,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 	if (err)
 		goto dcb_init_err;
 
-	return err;
+	return 0;
 
 dcb_init_err:
 	dev_err(dev, "DCB init failed\n");
@@ -947,6 +947,16 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring,
 }
 
 /**
+ * ice_dcb_is_mib_change_pending - Check if MIB change is pending
+ * @state: MIB change state
+ */
+static bool ice_dcb_is_mib_change_pending(u8 state)
+{
+	return ICE_AQ_LLDP_MIB_CHANGE_PENDING ==
+		FIELD_GET(ICE_AQ_LLDP_MIB_CHANGE_STATE_M, state);
+}
+
+/**
  * ice_dcb_process_lldp_set_mib_change - Process MIB change
  * @pf: ptr to ice_pf
  * @event: pointer to the admin queue receive event
@@ -959,6 +969,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_aqc_lldp_get_mib *mib;
 	struct ice_dcbx_cfg tmp_dcbx_cfg;
+	bool pending_handled = true;
 	bool need_reconfig = false;
 	struct ice_port_info *pi;
 	u8 mib_type;
@@ -975,41 +986,58 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 
 	pi = pf->hw.port_info;
 	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+
 	/* Ignore if event is not for Nearest Bridge */
-	mib_type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) &
-		    ICE_AQ_LLDP_BRID_TYPE_M);
+	mib_type = FIELD_GET(ICE_AQ_LLDP_BRID_TYPE_M, mib->type);
 	dev_dbg(dev, "LLDP event MIB bridge type 0x%x\n", mib_type);
 	if (mib_type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID)
 		return;
 
+	/* A pending change event contains accurate config information, and
+	 * the FW setting has not been updaed yet, so detect if change is
+	 * pending to determine where to pull config information from
+	 * (FW vs event)
+	 */
+	if (ice_dcb_is_mib_change_pending(mib->state))
+		pending_handled = false;
+
 	/* Check MIB Type and return if event for Remote MIB update */
-	mib_type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M;
+	mib_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type);
 	dev_dbg(dev, "LLDP event mib type %s\n", mib_type ? "remote" : "local");
 	if (mib_type == ICE_AQ_LLDP_MIB_REMOTE) {
 		/* Update the remote cached instance and return */
-		ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
-					 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
-					 &pi->qos_cfg.remote_dcbx_cfg);
-		if (ret) {
-			dev_err(dev, "Failed to get remote DCB config\n");
-			return;
+		if (!pending_handled) {
+			ice_get_dcb_cfg_from_mib_change(pi, event);
+		} else {
+			ret =
+			  ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+					     ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
+					     &pi->qos_cfg.remote_dcbx_cfg);
+			if (ret)
+				dev_dbg(dev, "Failed to get remote DCB config\n");
 		}
+		return;
 	}
 
+	/* That a DCB change has happened is now determined */
 	mutex_lock(&pf->tc_mutex);
 
 	/* store the old configuration */
-	tmp_dcbx_cfg = pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	tmp_dcbx_cfg = pi->qos_cfg.local_dcbx_cfg;
 
 	/* Reset the old DCBX configuration data */
 	memset(&pi->qos_cfg.local_dcbx_cfg, 0,
 	       sizeof(pi->qos_cfg.local_dcbx_cfg));
 
 	/* Get updated DCBX data from firmware */
-	ret = ice_get_dcb_cfg(pf->hw.port_info);
-	if (ret) {
-		dev_err(dev, "Failed to get DCB config\n");
-		goto out;
+	if (!pending_handled) {
+		ice_get_dcb_cfg_from_mib_change(pi, event);
+	} else {
+		ret = ice_get_dcb_cfg(pi);
+		if (ret) {
+			dev_err(dev, "Failed to get DCB config\n");
+			goto out;
+		}
 	}
 
 	/* No change detected in DCBX configs */
@@ -1036,11 +1064,17 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
 	}
 
+	/* Send Execute Pending MIB Change event if it is a Pending event */
+	if (!pending_handled) {
+		ice_lldp_execute_pending_mib(&pf->hw);
+		pending_handled = true;
+	}
+
 	rtnl_lock();
 	/* disable VSIs affected by DCB changes */
 	ice_dcb_ena_dis_vsi(pf, false, true);
 
-	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	ret = ice_query_port_ets(pi, &buf, sizeof(buf), NULL);
 	if (ret) {
 		dev_err(dev, "Query Port ETS failed\n");
 		goto unlock_rtnl;
@@ -1055,4 +1089,8 @@ unlock_rtnl:
 	rtnl_unlock();
 out:
 	mutex_unlock(&pf->tc_mutex);
+
+	/* Send Execute Pending MIB Change event if it is a Pending event */
+	if (!pending_handled)
+		ice_lldp_execute_pending_mib(&pf->hw);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
new file mode 100644
index 000000000000..d71ed210f9c4
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -0,0 +1,1897 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice.h"
+#include "ice_ddp.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
+ * prefixes will be saved to allow enabling double VLAN mode.
+ */
+#define ICE_DVM_PRE "BOOST_MAC_VLAN_DVM" /* enable these entries */
+#define ICE_SVM_PRE "BOOST_MAC_VLAN_SVM" /* disable these entries */
+
+/* To support tunneling entries by PF, the package will append the PF number to
+ * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc.
+ */
+#define ICE_TNL_PRE "TNL_"
+static const struct ice_tunnel_type_scan tnls[] = {
+	{ TNL_VXLAN, "TNL_VXLAN_PF" },
+	{ TNL_GENEVE, "TNL_GENEVE_PF" },
+	{ TNL_LAST, "" }
+};
+
+/**
+ * ice_verify_pkg - verify package
+ * @pkg: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * Verifies various attributes of the package file, including length, format
+ * version, and the requirement of at least one segment.
+ */
+enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
+{
+	u32 seg_count;
+	u32 i;
+
+	if (len < struct_size(pkg, seg_offset, 1))
+		return ICE_DDP_PKG_INVALID_FILE;
+
+	if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ ||
+	    pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR ||
+	    pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD ||
+	    pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT)
+		return ICE_DDP_PKG_INVALID_FILE;
+
+	/* pkg must have at least one segment */
+	seg_count = le32_to_cpu(pkg->seg_count);
+	if (seg_count < 1)
+		return ICE_DDP_PKG_INVALID_FILE;
+
+	/* make sure segment array fits in package length */
+	if (len < struct_size(pkg, seg_offset, seg_count))
+		return ICE_DDP_PKG_INVALID_FILE;
+
+	/* all segments must fit within length */
+	for (i = 0; i < seg_count; i++) {
+		u32 off = le32_to_cpu(pkg->seg_offset[i]);
+		struct ice_generic_seg_hdr *seg;
+
+		/* segment header must fit */
+		if (len < off + sizeof(*seg))
+			return ICE_DDP_PKG_INVALID_FILE;
+
+		seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off);
+
+		/* segment body must fit */
+		if (len < off + le32_to_cpu(seg->seg_size))
+			return ICE_DDP_PKG_INVALID_FILE;
+	}
+
+	return ICE_DDP_PKG_SUCCESS;
+}
+
+/**
+ * ice_free_seg - free package segment pointer
+ * @hw: pointer to the hardware structure
+ *
+ * Frees the package segment pointer in the proper manner, depending on if the
+ * segment was allocated or just the passed in pointer was stored.
+ */
+void ice_free_seg(struct ice_hw *hw)
+{
+	if (hw->pkg_copy) {
+		devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy);
+		hw->pkg_copy = NULL;
+		hw->pkg_size = 0;
+	}
+	hw->seg = NULL;
+}
+
+/**
+ * ice_chk_pkg_version - check package version for compatibility with driver
+ * @pkg_ver: pointer to a version structure to check
+ *
+ * Check to make sure that the package about to be downloaded is compatible with
+ * the driver. To be compatible, the major and minor components of the package
+ * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR
+ * definitions.
+ */
+static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver)
+{
+	if (pkg_ver->major > ICE_PKG_SUPP_VER_MAJ ||
+	    (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ &&
+	     pkg_ver->minor > ICE_PKG_SUPP_VER_MNR))
+		return ICE_DDP_PKG_FILE_VERSION_TOO_HIGH;
+	else if (pkg_ver->major < ICE_PKG_SUPP_VER_MAJ ||
+		 (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ &&
+		  pkg_ver->minor < ICE_PKG_SUPP_VER_MNR))
+		return ICE_DDP_PKG_FILE_VERSION_TOO_LOW;
+
+	return ICE_DDP_PKG_SUCCESS;
+}
+
+/**
+ * ice_pkg_val_buf
+ * @buf: pointer to the ice buffer
+ *
+ * This helper function validates a buffer's header.
+ */
+struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf)
+{
+	struct ice_buf_hdr *hdr;
+	u16 section_count;
+	u16 data_end;
+
+	hdr = (struct ice_buf_hdr *)buf->buf;
+	/* verify data */
+	section_count = le16_to_cpu(hdr->section_count);
+	if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT)
+		return NULL;
+
+	data_end = le16_to_cpu(hdr->data_end);
+	if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END)
+		return NULL;
+
+	return hdr;
+}
+
+/**
+ * ice_find_buf_table
+ * @ice_seg: pointer to the ice segment
+ *
+ * Returns the address of the buffer table within the ice segment.
+ */
+static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg)
+{
+	struct ice_nvm_table *nvms = (struct ice_nvm_table *)
+		(ice_seg->device_table + le32_to_cpu(ice_seg->device_table_count));
+
+	return (__force struct ice_buf_table *)(nvms->vers +
+						le32_to_cpu(nvms->table_count));
+}
+
+/**
+ * ice_pkg_enum_buf
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ *
+ * This function will enumerate all the buffers in the ice segment. The first
+ * call is made with the ice_seg parameter non-NULL; on subsequent calls,
+ * ice_seg is set to NULL which continues the enumeration. When the function
+ * returns a NULL pointer, then the end of the buffers has been reached, or an
+ * unexpected value has been detected (for example an invalid section count or
+ * an invalid buffer end value).
+ */
+static struct ice_buf_hdr *ice_pkg_enum_buf(struct ice_seg *ice_seg,
+					    struct ice_pkg_enum *state)
+{
+	if (ice_seg) {
+		state->buf_table = ice_find_buf_table(ice_seg);
+		if (!state->buf_table)
+			return NULL;
+
+		state->buf_idx = 0;
+		return ice_pkg_val_buf(state->buf_table->buf_array);
+	}
+
+	if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count))
+		return ice_pkg_val_buf(state->buf_table->buf_array +
+				       state->buf_idx);
+	else
+		return NULL;
+}
+
+/**
+ * ice_pkg_advance_sect
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ *
+ * This helper function will advance the section within the ice segment,
+ * also advancing the buffer if needed.
+ */
+static bool ice_pkg_advance_sect(struct ice_seg *ice_seg,
+				 struct ice_pkg_enum *state)
+{
+	if (!ice_seg && !state->buf)
+		return false;
+
+	if (!ice_seg && state->buf)
+		if (++state->sect_idx < le16_to_cpu(state->buf->section_count))
+			return true;
+
+	state->buf = ice_pkg_enum_buf(ice_seg, state);
+	if (!state->buf)
+		return false;
+
+	/* start of new buffer, reset section index */
+	state->sect_idx = 0;
+	return true;
+}
+
+/**
+ * ice_pkg_enum_section
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ * @sect_type: section type to enumerate
+ *
+ * This function will enumerate all the sections of a particular type in the
+ * ice segment. The first call is made with the ice_seg parameter non-NULL;
+ * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
+ * When the function returns a NULL pointer, then the end of the matching
+ * sections has been reached.
+ */
+void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
+			   u32 sect_type)
+{
+	u16 offset, size;
+
+	if (ice_seg)
+		state->type = sect_type;
+
+	if (!ice_pkg_advance_sect(ice_seg, state))
+		return NULL;
+
+	/* scan for next matching section */
+	while (state->buf->section_entry[state->sect_idx].type !=
+	       cpu_to_le32(state->type))
+		if (!ice_pkg_advance_sect(NULL, state))
+			return NULL;
+
+	/* validate section */
+	offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
+	if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF)
+		return NULL;
+
+	size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size);
+	if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ)
+		return NULL;
+
+	/* make sure the section fits in the buffer */
+	if (offset + size > ICE_PKG_BUF_SIZE)
+		return NULL;
+
+	state->sect_type =
+		le32_to_cpu(state->buf->section_entry[state->sect_idx].type);
+
+	/* calc pointer to this section */
+	state->sect =
+		((u8 *)state->buf) +
+		le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
+
+	return state->sect;
+}
+
+/**
+ * ice_pkg_enum_entry
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ * @sect_type: section type to enumerate
+ * @offset: pointer to variable that receives the offset in the table (optional)
+ * @handler: function that handles access to the entries into the section type
+ *
+ * This function will enumerate all the entries in particular section type in
+ * the ice segment. The first call is made with the ice_seg parameter non-NULL;
+ * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
+ * When the function returns a NULL pointer, then the end of the entries has
+ * been reached.
+ *
+ * Since each section may have a different header and entry size, the handler
+ * function is needed to determine the number and location entries in each
+ * section.
+ *
+ * The offset parameter is optional, but should be used for sections that
+ * contain an offset for each section table. For such cases, the section handler
+ * function must return the appropriate offset + index to give the absolution
+ * offset for each entry. For example, if the base for a section's header
+ * indicates a base offset of 10, and the index for the entry is 2, then
+ * section handler function should set the offset to 10 + 2 = 12.
+ */
+static void *ice_pkg_enum_entry(struct ice_seg *ice_seg,
+				struct ice_pkg_enum *state, u32 sect_type,
+				u32 *offset,
+				void *(*handler)(u32 sect_type, void *section,
+						 u32 index, u32 *offset))
+{
+	void *entry;
+
+	if (ice_seg) {
+		if (!handler)
+			return NULL;
+
+		if (!ice_pkg_enum_section(ice_seg, state, sect_type))
+			return NULL;
+
+		state->entry_idx = 0;
+		state->handler = handler;
+	} else {
+		state->entry_idx++;
+	}
+
+	if (!state->handler)
+		return NULL;
+
+	/* get entry */
+	entry = state->handler(state->sect_type, state->sect, state->entry_idx,
+			       offset);
+	if (!entry) {
+		/* end of a section, look for another section of this type */
+		if (!ice_pkg_enum_section(NULL, state, 0))
+			return NULL;
+
+		state->entry_idx = 0;
+		entry = state->handler(state->sect_type, state->sect,
+				       state->entry_idx, offset);
+	}
+
+	return entry;
+}
+
+/**
+ * ice_sw_fv_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the field vector entry to be returned
+ * @offset: ptr to variable that receives the offset in the field vector table
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * This function treats the given section as of type ice_sw_fv_section and
+ * enumerates offset field. "offset" is an index into the field vector table.
+ */
+static void *ice_sw_fv_handler(u32 sect_type, void *section, u32 index,
+			       u32 *offset)
+{
+	struct ice_sw_fv_section *fv_section = section;
+
+	if (!section || sect_type != ICE_SID_FLD_VEC_SW)
+		return NULL;
+	if (index >= le16_to_cpu(fv_section->count))
+		return NULL;
+	if (offset)
+		/* "index" passed in to this function is relative to a given
+		 * 4k block. To get to the true index into the field vector
+		 * table need to add the relative index to the base_offset
+		 * field of this section
+		 */
+		*offset = le16_to_cpu(fv_section->base_offset) + index;
+	return fv_section->fv + index;
+}
+
+/**
+ * ice_get_prof_index_max - get the max profile index for used profile
+ * @hw: pointer to the HW struct
+ *
+ * Calling this function will get the max profile index for used profile
+ * and store the index number in struct ice_switch_info *switch_info
+ * in HW for following use.
+ */
+static int ice_get_prof_index_max(struct ice_hw *hw)
+{
+	u16 prof_index = 0, j, max_prof_index = 0;
+	struct ice_pkg_enum state;
+	struct ice_seg *ice_seg;
+	bool flag = false;
+	struct ice_fv *fv;
+	u32 offset;
+
+	memset(&state, 0, sizeof(state));
+
+	if (!hw->seg)
+		return -EINVAL;
+
+	ice_seg = hw->seg;
+
+	do {
+		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
+					&offset, ice_sw_fv_handler);
+		if (!fv)
+			break;
+		ice_seg = NULL;
+
+		/* in the profile that not be used, the prot_id is set to 0xff
+		 * and the off is set to 0x1ff for all the field vectors.
+		 */
+		for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++)
+			if (fv->ew[j].prot_id != ICE_PROT_INVALID ||
+			    fv->ew[j].off != ICE_FV_OFFSET_INVAL)
+				flag = true;
+		if (flag && prof_index > max_prof_index)
+			max_prof_index = prof_index;
+
+		prof_index++;
+		flag = false;
+	} while (fv);
+
+	hw->switch_info->max_used_prof_index = max_prof_index;
+
+	return 0;
+}
+
+/**
+ * ice_get_ddp_pkg_state - get DDP pkg state after download
+ * @hw: pointer to the HW struct
+ * @already_loaded: indicates if pkg was already loaded onto the device
+ */
+static enum ice_ddp_state ice_get_ddp_pkg_state(struct ice_hw *hw,
+						bool already_loaded)
+{
+	if (hw->pkg_ver.major == hw->active_pkg_ver.major &&
+	    hw->pkg_ver.minor == hw->active_pkg_ver.minor &&
+	    hw->pkg_ver.update == hw->active_pkg_ver.update &&
+	    hw->pkg_ver.draft == hw->active_pkg_ver.draft &&
+	    !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) {
+		if (already_loaded)
+			return ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED;
+		else
+			return ICE_DDP_PKG_SUCCESS;
+	} else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ ||
+		   hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) {
+		return ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED;
+	} else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
+		   hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) {
+		return ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED;
+	} else {
+		return ICE_DDP_PKG_ERR;
+	}
+}
+
+/**
+ * ice_init_pkg_regs - initialize additional package registers
+ * @hw: pointer to the hardware structure
+ */
+static void ice_init_pkg_regs(struct ice_hw *hw)
+{
+#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF
+#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF
+#define ICE_SW_BLK_IDX 0
+
+	/* setup Switch block input mask, which is 48-bits in two parts */
+	wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L);
+	wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H);
+}
+
+/**
+ * ice_marker_ptype_tcam_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the Marker PType TCAM entry to be returned
+ * @offset: pointer to receive absolute offset, always 0 for ptype TCAM sections
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * Handles enumeration of individual Marker PType TCAM entries.
+ */
+static void *ice_marker_ptype_tcam_handler(u32 sect_type, void *section,
+					   u32 index, u32 *offset)
+{
+	struct ice_marker_ptype_tcam_section *marker_ptype;
+
+	if (sect_type != ICE_SID_RXPARSER_MARKER_PTYPE)
+		return NULL;
+
+	if (index > ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF)
+		return NULL;
+
+	if (offset)
+		*offset = 0;
+
+	marker_ptype = section;
+	if (index >= le16_to_cpu(marker_ptype->count))
+		return NULL;
+
+	return marker_ptype->tcam + index;
+}
+
+/**
+ * ice_add_dvm_hint
+ * @hw: pointer to the HW structure
+ * @val: value of the boost entry
+ * @enable: true if entry needs to be enabled, or false if needs to be disabled
+ */
+static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable)
+{
+	if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) {
+		hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val;
+		hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable;
+		hw->dvm_upd.count++;
+	}
+}
+
+/**
+ * ice_add_tunnel_hint
+ * @hw: pointer to the HW structure
+ * @label_name: label text
+ * @val: value of the tunnel port boost entry
+ */
+static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val)
+{
+	if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) {
+		u16 i;
+
+		for (i = 0; tnls[i].type != TNL_LAST; i++) {
+			size_t len = strlen(tnls[i].label_prefix);
+
+			/* Look for matching label start, before continuing */
+			if (strncmp(label_name, tnls[i].label_prefix, len))
+				continue;
+
+			/* Make sure this label matches our PF. Note that the PF
+			 * character ('0' - '7') will be located where our
+			 * prefix string's null terminator is located.
+			 */
+			if ((label_name[len] - '0') == hw->pf_id) {
+				hw->tnl.tbl[hw->tnl.count].type = tnls[i].type;
+				hw->tnl.tbl[hw->tnl.count].valid = false;
+				hw->tnl.tbl[hw->tnl.count].boost_addr = val;
+				hw->tnl.tbl[hw->tnl.count].port = 0;
+				hw->tnl.count++;
+				break;
+			}
+		}
+	}
+}
+
+/**
+ * ice_label_enum_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the label entry to be returned
+ * @offset: pointer to receive absolute offset, always zero for label sections
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * Handles enumeration of individual label entries.
+ */
+static void *ice_label_enum_handler(u32 __always_unused sect_type,
+				    void *section, u32 index, u32 *offset)
+{
+	struct ice_label_section *labels;
+
+	if (!section)
+		return NULL;
+
+	if (index > ICE_MAX_LABELS_IN_BUF)
+		return NULL;
+
+	if (offset)
+		*offset = 0;
+
+	labels = section;
+	if (index >= le16_to_cpu(labels->count))
+		return NULL;
+
+	return labels->label + index;
+}
+
+/**
+ * ice_enum_labels
+ * @ice_seg: pointer to the ice segment (NULL on subsequent calls)
+ * @type: the section type that will contain the label (0 on subsequent calls)
+ * @state: ice_pkg_enum structure that will hold the state of the enumeration
+ * @value: pointer to a value that will return the label's value if found
+ *
+ * Enumerates a list of labels in the package. The caller will call
+ * ice_enum_labels(ice_seg, type, ...) to start the enumeration, then call
+ * ice_enum_labels(NULL, 0, ...) to continue. When the function returns a NULL
+ * the end of the list has been reached.
+ */
+static char *ice_enum_labels(struct ice_seg *ice_seg, u32 type,
+			     struct ice_pkg_enum *state, u16 *value)
+{
+	struct ice_label *label;
+
+	/* Check for valid label section on first call */
+	if (type && !(type >= ICE_SID_LBL_FIRST && type <= ICE_SID_LBL_LAST))
+		return NULL;
+
+	label = ice_pkg_enum_entry(ice_seg, state, type, NULL,
+				   ice_label_enum_handler);
+	if (!label)
+		return NULL;
+
+	*value = le16_to_cpu(label->value);
+	return label->name;
+}
+
+/**
+ * ice_boost_tcam_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the boost TCAM entry to be returned
+ * @offset: pointer to receive absolute offset, always 0 for boost TCAM sections
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * Handles enumeration of individual boost TCAM entries.
+ */
+static void *ice_boost_tcam_handler(u32 sect_type, void *section, u32 index,
+				    u32 *offset)
+{
+	struct ice_boost_tcam_section *boost;
+
+	if (!section)
+		return NULL;
+
+	if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM)
+		return NULL;
+
+	if (index > ICE_MAX_BST_TCAMS_IN_BUF)
+		return NULL;
+
+	if (offset)
+		*offset = 0;
+
+	boost = section;
+	if (index >= le16_to_cpu(boost->count))
+		return NULL;
+
+	return boost->tcam + index;
+}
+
+/**
+ * ice_find_boost_entry
+ * @ice_seg: pointer to the ice segment (non-NULL)
+ * @addr: Boost TCAM address of entry to search for
+ * @entry: returns pointer to the entry
+ *
+ * Finds a particular Boost TCAM entry and returns a pointer to that entry
+ * if it is found. The ice_seg parameter must not be NULL since the first call
+ * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure.
+ */
+static int ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr,
+				struct ice_boost_tcam_entry **entry)
+{
+	struct ice_boost_tcam_entry *tcam;
+	struct ice_pkg_enum state;
+
+	memset(&state, 0, sizeof(state));
+
+	if (!ice_seg)
+		return -EINVAL;
+
+	do {
+		tcam = ice_pkg_enum_entry(ice_seg, &state,
+					  ICE_SID_RXPARSER_BOOST_TCAM, NULL,
+					  ice_boost_tcam_handler);
+		if (tcam && le16_to_cpu(tcam->addr) == addr) {
+			*entry = tcam;
+			return 0;
+		}
+
+		ice_seg = NULL;
+	} while (tcam);
+
+	*entry = NULL;
+	return -EIO;
+}
+
+/**
+ * ice_is_init_pkg_successful - check if DDP init was successful
+ * @state: state of the DDP pkg after download
+ */
+bool ice_is_init_pkg_successful(enum ice_ddp_state state)
+{
+	switch (state) {
+	case ICE_DDP_PKG_SUCCESS:
+	case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED:
+	case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ice_pkg_buf_alloc
+ * @hw: pointer to the HW structure
+ *
+ * Allocates a package buffer and returns a pointer to the buffer header.
+ * Note: all package contents must be in Little Endian form.
+ */
+struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw)
+{
+	struct ice_buf_build *bld;
+	struct ice_buf_hdr *buf;
+
+	bld = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*bld), GFP_KERNEL);
+	if (!bld)
+		return NULL;
+
+	buf = (struct ice_buf_hdr *)bld;
+	buf->data_end =
+		cpu_to_le16(offsetof(struct ice_buf_hdr, section_entry));
+	return bld;
+}
+
+static bool ice_is_gtp_u_profile(u16 prof_idx)
+{
+	return (prof_idx >= ICE_PROFID_IPV6_GTPU_TEID &&
+		prof_idx <= ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER) ||
+	       prof_idx == ICE_PROFID_IPV4_GTPU_TEID;
+}
+
+static bool ice_is_gtp_c_profile(u16 prof_idx)
+{
+	switch (prof_idx) {
+	case ICE_PROFID_IPV4_GTPC_TEID:
+	case ICE_PROFID_IPV4_GTPC_NO_TEID:
+	case ICE_PROFID_IPV6_GTPC_TEID:
+	case ICE_PROFID_IPV6_GTPC_NO_TEID:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ice_get_sw_prof_type - determine switch profile type
+ * @hw: pointer to the HW structure
+ * @fv: pointer to the switch field vector
+ * @prof_idx: profile index to check
+ */
+static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw,
+					       struct ice_fv *fv, u32 prof_idx)
+{
+	u16 i;
+
+	if (ice_is_gtp_c_profile(prof_idx))
+		return ICE_PROF_TUN_GTPC;
+
+	if (ice_is_gtp_u_profile(prof_idx))
+		return ICE_PROF_TUN_GTPU;
+
+	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 &&
+		    fv->ew[i].off == ICE_VNI_OFFSET)
+			return ICE_PROF_TUN_UDP;
+
+		/* GRE tunnel will have GRE protocol */
+		if (fv->ew[i].prot_id == (u8)ICE_PROT_GRE_OF)
+			return ICE_PROF_TUN_GRE;
+	}
+
+	return ICE_PROF_NON_TUN;
+}
+
+/**
+ * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type
+ * @hw: pointer to hardware structure
+ * @req_profs: type of profiles requested
+ * @bm: pointer to memory for returning the bitmap of field vectors
+ */
+void ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs,
+			  unsigned long *bm)
+{
+	struct ice_pkg_enum state;
+	struct ice_seg *ice_seg;
+	struct ice_fv *fv;
+
+	if (req_profs == ICE_PROF_ALL) {
+		bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES);
+		return;
+	}
+
+	memset(&state, 0, sizeof(state));
+	bitmap_zero(bm, ICE_MAX_NUM_PROFILES);
+	ice_seg = hw->seg;
+	do {
+		enum ice_prof_type prof_type;
+		u32 offset;
+
+		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
+					&offset, ice_sw_fv_handler);
+		ice_seg = NULL;
+
+		if (fv) {
+			/* Determine field vector type */
+			prof_type = ice_get_sw_prof_type(hw, fv, offset);
+
+			if (req_profs & prof_type)
+				set_bit((u16)offset, bm);
+		}
+	} while (fv);
+}
+
+/**
+ * ice_get_sw_fv_list
+ * @hw: pointer to the HW structure
+ * @lkups: list of protocol types
+ * @bm: bitmap of field vectors to consider
+ * @fv_list: Head of a list
+ *
+ * Finds all the field vector entries from switch block that contain
+ * a given protocol ID and offset and returns a list of structures of type
+ * "ice_sw_fv_list_entry". Every structure in the list has a field vector
+ * definition and profile ID information
+ * NOTE: The caller of the function is responsible for freeing the memory
+ * allocated for every list entry.
+ */
+int ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups,
+		       unsigned long *bm, struct list_head *fv_list)
+{
+	struct ice_sw_fv_list_entry *fvl;
+	struct ice_sw_fv_list_entry *tmp;
+	struct ice_pkg_enum state;
+	struct ice_seg *ice_seg;
+	struct ice_fv *fv;
+	u32 offset;
+
+	memset(&state, 0, sizeof(state));
+
+	if (!lkups->n_val_words || !hw->seg)
+		return -EINVAL;
+
+	ice_seg = hw->seg;
+	do {
+		u16 i;
+
+		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
+					&offset, ice_sw_fv_handler);
+		if (!fv)
+			break;
+		ice_seg = NULL;
+
+		/* If field vector is not in the bitmap list, then skip this
+		 * profile.
+		 */
+		if (!test_bit((u16)offset, bm))
+			continue;
+
+		for (i = 0; i < lkups->n_val_words; i++) {
+			int j;
+
+			for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++)
+				if (fv->ew[j].prot_id ==
+					    lkups->fv_words[i].prot_id &&
+				    fv->ew[j].off == lkups->fv_words[i].off)
+					break;
+			if (j >= hw->blk[ICE_BLK_SW].es.fvw)
+				break;
+			if (i + 1 == lkups->n_val_words) {
+				fvl = devm_kzalloc(ice_hw_to_dev(hw),
+						   sizeof(*fvl), GFP_KERNEL);
+				if (!fvl)
+					goto err;
+				fvl->fv_ptr = fv;
+				fvl->profile_id = offset;
+				list_add(&fvl->list_entry, fv_list);
+				break;
+			}
+		}
+	} while (fv);
+	if (list_empty(fv_list)) {
+		dev_warn(ice_hw_to_dev(hw),
+			 "Required profiles not found in currently loaded DDP package");
+		return -EIO;
+	}
+
+	return 0;
+
+err:
+	list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) {
+		list_del(&fvl->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), fvl);
+	}
+
+	return -ENOMEM;
+}
+
+/**
+ * ice_init_prof_result_bm - Initialize the profile result index bitmap
+ * @hw: pointer to hardware structure
+ */
+void ice_init_prof_result_bm(struct ice_hw *hw)
+{
+	struct ice_pkg_enum state;
+	struct ice_seg *ice_seg;
+	struct ice_fv *fv;
+
+	memset(&state, 0, sizeof(state));
+
+	if (!hw->seg)
+		return;
+
+	ice_seg = hw->seg;
+	do {
+		u32 off;
+		u16 i;
+
+		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
+					&off, ice_sw_fv_handler);
+		ice_seg = NULL;
+		if (!fv)
+			break;
+
+		bitmap_zero(hw->switch_info->prof_res_bm[off],
+			    ICE_MAX_FV_WORDS);
+
+		/* Determine empty field vector indices, these can be
+		 * used for recipe results. Skip index 0, since it is
+		 * always used for Switch ID.
+		 */
+		for (i = 1; i < ICE_MAX_FV_WORDS; i++)
+			if (fv->ew[i].prot_id == ICE_PROT_INVALID &&
+			    fv->ew[i].off == ICE_FV_OFFSET_INVAL)
+				set_bit(i, hw->switch_info->prof_res_bm[off]);
+	} while (fv);
+}
+
+/**
+ * ice_pkg_buf_free
+ * @hw: pointer to the HW structure
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Frees a package buffer
+ */
+void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld)
+{
+	devm_kfree(ice_hw_to_dev(hw), bld);
+}
+
+/**
+ * ice_pkg_buf_reserve_section
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ * @count: the number of sections to reserve
+ *
+ * Reserves one or more section table entries in a package buffer. This routine
+ * can be called multiple times as long as they are made before calling
+ * ice_pkg_buf_alloc_section(). Once ice_pkg_buf_alloc_section()
+ * is called once, the number of sections that can be allocated will not be able
+ * to be increased; not using all reserved sections is fine, but this will
+ * result in some wasted space in the buffer.
+ * Note: all package contents must be in Little Endian form.
+ */
+int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count)
+{
+	struct ice_buf_hdr *buf;
+	u16 section_count;
+	u16 data_end;
+
+	if (!bld)
+		return -EINVAL;
+
+	buf = (struct ice_buf_hdr *)&bld->buf;
+
+	/* already an active section, can't increase table size */
+	section_count = le16_to_cpu(buf->section_count);
+	if (section_count > 0)
+		return -EIO;
+
+	if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT)
+		return -EIO;
+	bld->reserved_section_table_entries += count;
+
+	data_end = le16_to_cpu(buf->data_end) +
+		   flex_array_size(buf, section_entry, count);
+	buf->data_end = cpu_to_le16(data_end);
+
+	return 0;
+}
+
+/**
+ * ice_pkg_buf_alloc_section
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ * @type: the section type value
+ * @size: the size of the section to reserve (in bytes)
+ *
+ * Reserves memory in the buffer for a section's content and updates the
+ * buffers' status accordingly. This routine returns a pointer to the first
+ * byte of the section start within the buffer, which is used to fill in the
+ * section contents.
+ * Note: all package contents must be in Little Endian form.
+ */
+void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size)
+{
+	struct ice_buf_hdr *buf;
+	u16 sect_count;
+	u16 data_end;
+
+	if (!bld || !type || !size)
+		return NULL;
+
+	buf = (struct ice_buf_hdr *)&bld->buf;
+
+	/* check for enough space left in buffer */
+	data_end = le16_to_cpu(buf->data_end);
+
+	/* section start must align on 4 byte boundary */
+	data_end = ALIGN(data_end, 4);
+
+	if ((data_end + size) > ICE_MAX_S_DATA_END)
+		return NULL;
+
+	/* check for more available section table entries */
+	sect_count = le16_to_cpu(buf->section_count);
+	if (sect_count < bld->reserved_section_table_entries) {
+		void *section_ptr = ((u8 *)buf) + data_end;
+
+		buf->section_entry[sect_count].offset = cpu_to_le16(data_end);
+		buf->section_entry[sect_count].size = cpu_to_le16(size);
+		buf->section_entry[sect_count].type = cpu_to_le32(type);
+
+		data_end += size;
+		buf->data_end = cpu_to_le16(data_end);
+
+		buf->section_count = cpu_to_le16(sect_count + 1);
+		return section_ptr;
+	}
+
+	/* no free section table entries */
+	return NULL;
+}
+
+/**
+ * ice_pkg_buf_alloc_single_section
+ * @hw: pointer to the HW structure
+ * @type: the section type value
+ * @size: the size of the section to reserve (in bytes)
+ * @section: returns pointer to the section
+ *
+ * Allocates a package buffer with a single section.
+ * Note: all package contents must be in Little Endian form.
+ */
+struct ice_buf_build *ice_pkg_buf_alloc_single_section(struct ice_hw *hw,
+						       u32 type, u16 size,
+						       void **section)
+{
+	struct ice_buf_build *buf;
+
+	if (!section)
+		return NULL;
+
+	buf = ice_pkg_buf_alloc(hw);
+	if (!buf)
+		return NULL;
+
+	if (ice_pkg_buf_reserve_section(buf, 1))
+		goto ice_pkg_buf_alloc_single_section_err;
+
+	*section = ice_pkg_buf_alloc_section(buf, type, size);
+	if (!*section)
+		goto ice_pkg_buf_alloc_single_section_err;
+
+	return buf;
+
+ice_pkg_buf_alloc_single_section_err:
+	ice_pkg_buf_free(hw, buf);
+	return NULL;
+}
+
+/**
+ * ice_pkg_buf_get_active_sections
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Returns the number of active sections. Before using the package buffer
+ * in an update package command, the caller should make sure that there is at
+ * least one active section - otherwise, the buffer is not legal and should
+ * not be used.
+ * Note: all package contents must be in Little Endian form.
+ */
+u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld)
+{
+	struct ice_buf_hdr *buf;
+
+	if (!bld)
+		return 0;
+
+	buf = (struct ice_buf_hdr *)&bld->buf;
+	return le16_to_cpu(buf->section_count);
+}
+
+/**
+ * ice_pkg_buf
+ * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
+ *
+ * Return a pointer to the buffer's header
+ */
+struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
+{
+	if (!bld)
+		return NULL;
+
+	return &bld->buf;
+}
+
+static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err)
+{
+	switch (aq_err) {
+	case ICE_AQ_RC_ENOSEC:
+	case ICE_AQ_RC_EBADSIG:
+		return ICE_DDP_PKG_FILE_SIGNATURE_INVALID;
+	case ICE_AQ_RC_ESVN:
+		return ICE_DDP_PKG_FILE_REVISION_TOO_LOW;
+	case ICE_AQ_RC_EBADMAN:
+	case ICE_AQ_RC_EBADBUF:
+		return ICE_DDP_PKG_LOAD_ERROR;
+	default:
+		return ICE_DDP_PKG_ERR;
+	}
+}
+
+/**
+ * ice_acquire_global_cfg_lock
+ * @hw: pointer to the HW structure
+ * @access: access type (read or write)
+ *
+ * This function will request ownership of the global config lock for reading
+ * or writing of the package. When attempting to obtain write access, the
+ * caller must check for the following two return values:
+ *
+ * 0         -  Means the caller has acquired the global config lock
+ *              and can perform writing of the package.
+ * -EALREADY - Indicates another driver has already written the
+ *             package or has found that no update was necessary; in
+ *             this case, the caller can just skip performing any
+ *             update of the package.
+ */
+static int ice_acquire_global_cfg_lock(struct ice_hw *hw,
+				       enum ice_aq_res_access_type access)
+{
+	int status;
+
+	status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access,
+				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
+
+	if (!status)
+		mutex_lock(&ice_global_cfg_lock_sw);
+	else if (status == -EALREADY)
+		ice_debug(hw, ICE_DBG_PKG,
+			  "Global config lock: No work to do\n");
+
+	return status;
+}
+
+/**
+ * ice_release_global_cfg_lock
+ * @hw: pointer to the HW structure
+ *
+ * This function will release the global config lock.
+ */
+static void ice_release_global_cfg_lock(struct ice_hw *hw)
+{
+	mutex_unlock(&ice_global_cfg_lock_sw);
+	ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID);
+}
+
+/**
+ * ice_dwnld_cfg_bufs
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains global config lock and downloads the package configuration buffers
+ * to the firmware. Metadata buffers are skipped, and the first metadata buffer
+ * found indicates that the rest of the buffers are all metadata buffers.
+ */
+static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw,
+					     struct ice_buf *bufs, u32 count)
+{
+	enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS;
+	struct ice_buf_hdr *bh;
+	enum ice_aq_err err;
+	u32 offset, info, i;
+	int status;
+
+	if (!bufs || !count)
+		return ICE_DDP_PKG_ERR;
+
+	/* If the first buffer's first section has its metadata bit set
+	 * then there are no buffers to be downloaded, and the operation is
+	 * considered a success.
+	 */
+	bh = (struct ice_buf_hdr *)bufs;
+	if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
+		return ICE_DDP_PKG_SUCCESS;
+
+	status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
+	if (status) {
+		if (status == -EALREADY)
+			return ICE_DDP_PKG_ALREADY_LOADED;
+		return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status);
+	}
+
+	for (i = 0; i < count; i++) {
+		bool last = ((i + 1) == count);
+
+		if (!last) {
+			/* check next buffer for metadata flag */
+			bh = (struct ice_buf_hdr *)(bufs + i + 1);
+
+			/* A set metadata flag in the next buffer will signal
+			 * that the current buffer will be the last buffer
+			 * downloaded
+			 */
+			if (le16_to_cpu(bh->section_count))
+				if (le32_to_cpu(bh->section_entry[0].type) &
+				    ICE_METADATA_BUF)
+					last = true;
+		}
+
+		bh = (struct ice_buf_hdr *)(bufs + i);
+
+		status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last,
+					     &offset, &info, NULL);
+
+		/* Save AQ status from download package */
+		if (status) {
+			ice_debug(hw, ICE_DBG_PKG,
+				  "Pkg download failed: err %d off %d inf %d\n",
+				  status, offset, info);
+			err = hw->adminq.sq_last_status;
+			state = ice_map_aq_err_to_ddp_state(err);
+			break;
+		}
+
+		if (last)
+			break;
+	}
+
+	if (!status) {
+		status = ice_set_vlan_mode(hw);
+		if (status)
+			ice_debug(hw, ICE_DBG_PKG,
+				  "Failed to set VLAN mode: err %d\n", status);
+	}
+
+	ice_release_global_cfg_lock(hw);
+
+	return state;
+}
+
+/**
+ * ice_aq_get_pkg_info_list
+ * @hw: pointer to the hardware structure
+ * @pkg_info: the buffer which will receive the information list
+ * @buf_size: the size of the pkg_info information buffer
+ * @cd: pointer to command details structure or NULL
+ *
+ * Get Package Info List (0x0C43)
+ */
+static int ice_aq_get_pkg_info_list(struct ice_hw *hw,
+				    struct ice_aqc_get_pkg_info_resp *pkg_info,
+				    u16 buf_size, struct ice_sq_cd *cd)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list);
+
+	return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd);
+}
+
+/**
+ * ice_download_pkg
+ * @hw: pointer to the hardware structure
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package.
+ */
+static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw,
+					   struct ice_seg *ice_seg)
+{
+	struct ice_buf_table *ice_buf_tbl;
+	int status;
+
+	ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
+		  ice_seg->hdr.seg_format_ver.major,
+		  ice_seg->hdr.seg_format_ver.minor,
+		  ice_seg->hdr.seg_format_ver.update,
+		  ice_seg->hdr.seg_format_ver.draft);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
+		  le32_to_cpu(ice_seg->hdr.seg_type),
+		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
+
+	ice_buf_tbl = ice_find_buf_table(ice_seg);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
+		  le32_to_cpu(ice_buf_tbl->buf_count));
+
+	status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
+				    le32_to_cpu(ice_buf_tbl->buf_count));
+
+	ice_post_pkg_dwnld_vlan_mode_cfg(hw);
+
+	return status;
+}
+
+/**
+ * ice_aq_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package buffer to transfer
+ * @buf_size: the size of the package buffer
+ * @last_buf: last buffer indicator
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cd: pointer to command details structure or NULL
+ *
+ * Download Package (0x0C40)
+ */
+int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			u16 buf_size, bool last_buf, u32 *error_offset,
+			u32 *error_info, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_download_pkg *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	if (error_offset)
+		*error_offset = 0;
+	if (error_info)
+		*error_info = 0;
+
+	cmd = &desc.params.download_pkg;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	if (last_buf)
+		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
+
+	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+	if (status == -EIO) {
+		/* Read error from buffer only when the FW returned an error */
+		struct ice_aqc_download_pkg_resp *resp;
+
+		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
+		if (error_offset)
+			*error_offset = le32_to_cpu(resp->error_offset);
+		if (error_info)
+			*error_info = le32_to_cpu(resp->error_info);
+	}
+
+	return status;
+}
+
+/**
+ * ice_aq_upload_section
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package buffer which will receive the section
+ * @buf_size: the size of the package buffer
+ * @cd: pointer to command details structure or NULL
+ *
+ * Upload Section (0x0C41)
+ */
+int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			  u16 buf_size, struct ice_sq_cd *cd)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+}
+
+/**
+ * ice_aq_update_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_buf: the package cmd buffer
+ * @buf_size: the size of the package cmd buffer
+ * @last_buf: last buffer indicator
+ * @error_offset: returns error offset
+ * @error_info: returns error information
+ * @cd: pointer to command details structure or NULL
+ *
+ * Update Package (0x0C42)
+ */
+static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			     u16 buf_size, bool last_buf, u32 *error_offset,
+			     u32 *error_info, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_download_pkg *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	if (error_offset)
+		*error_offset = 0;
+	if (error_info)
+		*error_info = 0;
+
+	cmd = &desc.params.download_pkg;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	if (last_buf)
+		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
+
+	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
+	if (status == -EIO) {
+		/* Read error from buffer only when the FW returned an error */
+		struct ice_aqc_download_pkg_resp *resp;
+
+		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
+		if (error_offset)
+			*error_offset = le32_to_cpu(resp->error_offset);
+		if (error_info)
+			*error_info = le32_to_cpu(resp->error_info);
+	}
+
+	return status;
+}
+
+/**
+ * ice_update_pkg_no_lock
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ */
+int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+	int status = 0;
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i);
+		bool last = ((i + 1) == count);
+		u32 offset, info;
+
+		status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end),
+					   last, &offset, &info, NULL);
+
+		if (status) {
+			ice_debug(hw, ICE_DBG_PKG,
+				  "Update pkg failed: err %d off %d inf %d\n",
+				  status, offset, info);
+			break;
+		}
+	}
+
+	return status;
+}
+
+/**
+ * ice_update_pkg
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains change lock and updates package.
+ */
+int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+	int status;
+
+	status = ice_acquire_change_lock(hw, ICE_RES_WRITE);
+	if (status)
+		return status;
+
+	status = ice_update_pkg_no_lock(hw, bufs, count);
+
+	ice_release_change_lock(hw);
+
+	return status;
+}
+
+/**
+ * ice_find_seg_in_pkg
+ * @hw: pointer to the hardware structure
+ * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK)
+ * @pkg_hdr: pointer to the package header to be searched
+ *
+ * This function searches a package file for a particular segment type. On
+ * success it returns a pointer to the segment header, otherwise it will
+ * return NULL.
+ */
+struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
+						struct ice_pkg_hdr *pkg_hdr)
+{
+	u32 i;
+
+	ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n",
+		  pkg_hdr->pkg_format_ver.major, pkg_hdr->pkg_format_ver.minor,
+		  pkg_hdr->pkg_format_ver.update,
+		  pkg_hdr->pkg_format_ver.draft);
+
+	/* Search all package segments for the requested segment type */
+	for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) {
+		struct ice_generic_seg_hdr *seg;
+
+		seg = (struct ice_generic_seg_hdr
+			       *)((u8 *)pkg_hdr +
+				  le32_to_cpu(pkg_hdr->seg_offset[i]));
+
+		if (le32_to_cpu(seg->seg_type) == seg_type)
+			return seg;
+	}
+
+	return NULL;
+}
+
+/**
+ * ice_init_pkg_info
+ * @hw: pointer to the hardware structure
+ * @pkg_hdr: pointer to the driver's package hdr
+ *
+ * Saves off the package details into the HW structure.
+ */
+static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw,
+					    struct ice_pkg_hdr *pkg_hdr)
+{
+	struct ice_generic_seg_hdr *seg_hdr;
+
+	if (!pkg_hdr)
+		return ICE_DDP_PKG_ERR;
+
+	seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr);
+	if (seg_hdr) {
+		struct ice_meta_sect *meta;
+		struct ice_pkg_enum state;
+
+		memset(&state, 0, sizeof(state));
+
+		/* Get package information from the Metadata Section */
+		meta = ice_pkg_enum_section((struct ice_seg *)seg_hdr, &state,
+					    ICE_SID_METADATA);
+		if (!meta) {
+			ice_debug(hw, ICE_DBG_INIT,
+				  "Did not find ice metadata section in package\n");
+			return ICE_DDP_PKG_INVALID_FILE;
+		}
+
+		hw->pkg_ver = meta->ver;
+		memcpy(hw->pkg_name, meta->name, sizeof(meta->name));
+
+		ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n",
+			  meta->ver.major, meta->ver.minor, meta->ver.update,
+			  meta->ver.draft, meta->name);
+
+		hw->ice_seg_fmt_ver = seg_hdr->seg_format_ver;
+		memcpy(hw->ice_seg_id, seg_hdr->seg_id, sizeof(hw->ice_seg_id));
+
+		ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n",
+			  seg_hdr->seg_format_ver.major,
+			  seg_hdr->seg_format_ver.minor,
+			  seg_hdr->seg_format_ver.update,
+			  seg_hdr->seg_format_ver.draft, seg_hdr->seg_id);
+	} else {
+		ice_debug(hw, ICE_DBG_INIT,
+			  "Did not find ice segment in driver package\n");
+		return ICE_DDP_PKG_INVALID_FILE;
+	}
+
+	return ICE_DDP_PKG_SUCCESS;
+}
+
+/**
+ * ice_get_pkg_info
+ * @hw: pointer to the hardware structure
+ *
+ * Store details of the package currently loaded in HW into the HW structure.
+ */
+static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw)
+{
+	enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS;
+	struct ice_aqc_get_pkg_info_resp *pkg_info;
+	u16 size;
+	u32 i;
+
+	size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT);
+	pkg_info = kzalloc(size, GFP_KERNEL);
+	if (!pkg_info)
+		return ICE_DDP_PKG_ERR;
+
+	if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) {
+		state = ICE_DDP_PKG_ERR;
+		goto init_pkg_free_alloc;
+	}
+
+	for (i = 0; i < le32_to_cpu(pkg_info->count); i++) {
+#define ICE_PKG_FLAG_COUNT 4
+		char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 };
+		u8 place = 0;
+
+		if (pkg_info->pkg_info[i].is_active) {
+			flags[place++] = 'A';
+			hw->active_pkg_ver = pkg_info->pkg_info[i].ver;
+			hw->active_track_id =
+				le32_to_cpu(pkg_info->pkg_info[i].track_id);
+			memcpy(hw->active_pkg_name, pkg_info->pkg_info[i].name,
+			       sizeof(pkg_info->pkg_info[i].name));
+			hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm;
+		}
+		if (pkg_info->pkg_info[i].is_active_at_boot)
+			flags[place++] = 'B';
+		if (pkg_info->pkg_info[i].is_modified)
+			flags[place++] = 'M';
+		if (pkg_info->pkg_info[i].is_in_nvm)
+			flags[place++] = 'N';
+
+		ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n", i,
+			  pkg_info->pkg_info[i].ver.major,
+			  pkg_info->pkg_info[i].ver.minor,
+			  pkg_info->pkg_info[i].ver.update,
+			  pkg_info->pkg_info[i].ver.draft,
+			  pkg_info->pkg_info[i].name, flags);
+	}
+
+init_pkg_free_alloc:
+	kfree(pkg_info);
+
+	return state;
+}
+
+/**
+ * ice_chk_pkg_compat
+ * @hw: pointer to the hardware structure
+ * @ospkg: pointer to the package hdr
+ * @seg: pointer to the package segment hdr
+ *
+ * This function checks the package version compatibility with driver and NVM
+ */
+static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw,
+					     struct ice_pkg_hdr *ospkg,
+					     struct ice_seg **seg)
+{
+	struct ice_aqc_get_pkg_info_resp *pkg;
+	enum ice_ddp_state state;
+	u16 size;
+	u32 i;
+
+	/* Check package version compatibility */
+	state = ice_chk_pkg_version(&hw->pkg_ver);
+	if (state) {
+		ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n");
+		return state;
+	}
+
+	/* find ICE segment in given package */
+	*seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE,
+						     ospkg);
+	if (!*seg) {
+		ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n");
+		return ICE_DDP_PKG_INVALID_FILE;
+	}
+
+	/* Check if FW is compatible with the OS package */
+	size = struct_size(pkg, pkg_info, ICE_PKG_CNT);
+	pkg = kzalloc(size, GFP_KERNEL);
+	if (!pkg)
+		return ICE_DDP_PKG_ERR;
+
+	if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) {
+		state = ICE_DDP_PKG_LOAD_ERROR;
+		goto fw_ddp_compat_free_alloc;
+	}
+
+	for (i = 0; i < le32_to_cpu(pkg->count); i++) {
+		/* loop till we find the NVM package */
+		if (!pkg->pkg_info[i].is_in_nvm)
+			continue;
+		if ((*seg)->hdr.seg_format_ver.major !=
+			    pkg->pkg_info[i].ver.major ||
+		    (*seg)->hdr.seg_format_ver.minor >
+			    pkg->pkg_info[i].ver.minor) {
+			state = ICE_DDP_PKG_FW_MISMATCH;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "OS package is not compatible with NVM.\n");
+		}
+		/* done processing NVM package so break */
+		break;
+	}
+fw_ddp_compat_free_alloc:
+	kfree(pkg);
+	return state;
+}
+
+/**
+ * ice_init_pkg_hints
+ * @hw: pointer to the HW structure
+ * @ice_seg: pointer to the segment of the package scan (non-NULL)
+ *
+ * This function will scan the package and save off relevant information
+ * (hints or metadata) for driver use. The ice_seg parameter must not be NULL
+ * since the first call to ice_enum_labels requires a pointer to an actual
+ * ice_seg structure.
+ */
+static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+	struct ice_pkg_enum state;
+	char *label_name;
+	u16 val;
+	int i;
+
+	memset(&hw->tnl, 0, sizeof(hw->tnl));
+	memset(&state, 0, sizeof(state));
+
+	if (!ice_seg)
+		return;
+
+	label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state,
+				     &val);
+
+	while (label_name) {
+		if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE)))
+			/* check for a tunnel entry */
+			ice_add_tunnel_hint(hw, label_name, val);
+
+		/* check for a dvm mode entry */
+		else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE)))
+			ice_add_dvm_hint(hw, val, true);
+
+		/* check for a svm mode entry */
+		else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE)))
+			ice_add_dvm_hint(hw, val, false);
+
+		label_name = ice_enum_labels(NULL, 0, &state, &val);
+	}
+
+	/* Cache the appropriate boost TCAM entry pointers for tunnels */
+	for (i = 0; i < hw->tnl.count; i++) {
+		ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr,
+				     &hw->tnl.tbl[i].boost_entry);
+		if (hw->tnl.tbl[i].boost_entry) {
+			hw->tnl.tbl[i].valid = true;
+			if (hw->tnl.tbl[i].type < __TNL_TYPE_CNT)
+				hw->tnl.valid_count[hw->tnl.tbl[i].type]++;
+		}
+	}
+
+	/* Cache the appropriate boost TCAM entry pointers for DVM and SVM */
+	for (i = 0; i < hw->dvm_upd.count; i++)
+		ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr,
+				     &hw->dvm_upd.tbl[i].boost_entry);
+}
+
+/**
+ * ice_fill_hw_ptype - fill the enabled PTYPE bit information
+ * @hw: pointer to the HW structure
+ */
+static void ice_fill_hw_ptype(struct ice_hw *hw)
+{
+	struct ice_marker_ptype_tcam_entry *tcam;
+	struct ice_seg *seg = hw->seg;
+	struct ice_pkg_enum state;
+
+	bitmap_zero(hw->hw_ptype, ICE_FLOW_PTYPE_MAX);
+	if (!seg)
+		return;
+
+	memset(&state, 0, sizeof(state));
+
+	do {
+		tcam = ice_pkg_enum_entry(seg, &state,
+					  ICE_SID_RXPARSER_MARKER_PTYPE, NULL,
+					  ice_marker_ptype_tcam_handler);
+		if (tcam &&
+		    le16_to_cpu(tcam->addr) < ICE_MARKER_PTYPE_TCAM_ADDR_MAX &&
+		    le16_to_cpu(tcam->ptype) < ICE_FLOW_PTYPE_MAX)
+			set_bit(le16_to_cpu(tcam->ptype), hw->hw_ptype);
+
+		seg = NULL;
+	} while (tcam);
+}
+
+/**
+ * ice_init_pkg - initialize/download package
+ * @hw: pointer to the hardware structure
+ * @buf: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * This function initializes a package. The package contains HW tables
+ * required to do packet processing. First, the function extracts package
+ * information such as version. Then it finds the ice configuration segment
+ * within the package; this function then saves a copy of the segment pointer
+ * within the supplied package buffer. Next, the function will cache any hints
+ * from the package, followed by downloading the package itself. Note, that if
+ * a previous PF driver has already downloaded the package successfully, then
+ * the current driver will not have to download the package again.
+ *
+ * The local package contents will be used to query default behavior and to
+ * update specific sections of the HW's version of the package (e.g. to update
+ * the parse graph to understand new protocols).
+ *
+ * This function stores a pointer to the package buffer memory, and it is
+ * expected that the supplied buffer will not be freed immediately. If the
+ * package buffer needs to be freed, such as when read from a file, use
+ * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this
+ * case.
+ */
+enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
+{
+	bool already_loaded = false;
+	enum ice_ddp_state state;
+	struct ice_pkg_hdr *pkg;
+	struct ice_seg *seg;
+
+	if (!buf || !len)
+		return ICE_DDP_PKG_ERR;
+
+	pkg = (struct ice_pkg_hdr *)buf;
+	state = ice_verify_pkg(pkg, len);
+	if (state) {
+		ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n",
+			  state);
+		return state;
+	}
+
+	/* initialize package info */
+	state = ice_init_pkg_info(hw, pkg);
+	if (state)
+		return state;
+
+	/* before downloading the package, check package version for
+	 * compatibility with driver
+	 */
+	state = ice_chk_pkg_compat(hw, pkg, &seg);
+	if (state)
+		return state;
+
+	/* initialize package hints and then download package */
+	ice_init_pkg_hints(hw, seg);
+	state = ice_download_pkg(hw, seg);
+	if (state == ICE_DDP_PKG_ALREADY_LOADED) {
+		ice_debug(hw, ICE_DBG_INIT,
+			  "package previously loaded - no work.\n");
+		already_loaded = true;
+	}
+
+	/* Get information on the package currently loaded in HW, then make sure
+	 * the driver is compatible with this version.
+	 */
+	if (!state || state == ICE_DDP_PKG_ALREADY_LOADED) {
+		state = ice_get_pkg_info(hw);
+		if (!state)
+			state = ice_get_ddp_pkg_state(hw, already_loaded);
+	}
+
+	if (ice_is_init_pkg_successful(state)) {
+		hw->seg = seg;
+		/* on successful package download update other required
+		 * registers to support the package and fill HW tables
+		 * with package content.
+		 */
+		ice_init_pkg_regs(hw);
+		ice_fill_blk_tbls(hw);
+		ice_fill_hw_ptype(hw);
+		ice_get_prof_index_max(hw);
+	} else {
+		ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", state);
+	}
+
+	return state;
+}
+
+/**
+ * ice_copy_and_init_pkg - initialize/download a copy of the package
+ * @hw: pointer to the hardware structure
+ * @buf: pointer to the package buffer
+ * @len: size of the package buffer
+ *
+ * This function copies the package buffer, and then calls ice_init_pkg() to
+ * initialize the copied package contents.
+ *
+ * The copying is necessary if the package buffer supplied is constant, or if
+ * the memory may disappear shortly after calling this function.
+ *
+ * If the package buffer resides in the data segment and can be modified, the
+ * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg().
+ *
+ * However, if the package buffer needs to be copied first, such as when being
+ * read from a file, the caller should use ice_copy_and_init_pkg().
+ *
+ * This function will first copy the package buffer, before calling
+ * ice_init_pkg(). The caller is free to immediately destroy the original
+ * package buffer, as the new copy will be managed by this function and
+ * related routines.
+ */
+enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf,
+					 u32 len)
+{
+	enum ice_ddp_state state;
+	u8 *buf_copy;
+
+	if (!buf || !len)
+		return ICE_DDP_PKG_ERR;
+
+	buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL);
+
+	state = ice_init_pkg(hw, buf_copy, len);
+	if (!ice_is_init_pkg_successful(state)) {
+		/* Free the copy, since we failed to initialize the package */
+		devm_kfree(ice_hw_to_dev(hw), buf_copy);
+	} else {
+		/* Track the copied pkg so we can free it later */
+		hw->pkg_copy = buf_copy;
+		hw->pkg_size = len;
+	}
+
+	return state;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h
new file mode 100644
index 000000000000..37eadb3d27a8
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.h
@@ -0,0 +1,445 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2022, Intel Corporation. */
+
+#ifndef _ICE_DDP_H_
+#define _ICE_DDP_H_
+
+#include "ice_type.h"
+
+/* Package minimal version supported */
+#define ICE_PKG_SUPP_VER_MAJ 1
+#define ICE_PKG_SUPP_VER_MNR 3
+
+/* Package format version */
+#define ICE_PKG_FMT_VER_MAJ 1
+#define ICE_PKG_FMT_VER_MNR 0
+#define ICE_PKG_FMT_VER_UPD 0
+#define ICE_PKG_FMT_VER_DFT 0
+
+#define ICE_PKG_CNT 4
+
+#define ICE_FV_OFFSET_INVAL 0x1FF
+
+/* Extraction Sequence (Field Vector) Table */
+struct ice_fv_word {
+	u8 prot_id;
+	u16 off; /* Offset within the protocol header */
+	u8 resvrd;
+} __packed;
+
+#define ICE_MAX_NUM_PROFILES 256
+
+#define ICE_MAX_FV_WORDS 48
+struct ice_fv {
+	struct ice_fv_word ew[ICE_MAX_FV_WORDS];
+};
+
+enum ice_ddp_state {
+	/* Indicates that this call to ice_init_pkg
+	 * successfully loaded the requested DDP package
+	 */
+	ICE_DDP_PKG_SUCCESS = 0,
+
+	/* Generic error for already loaded errors, it is mapped later to
+	 * the more specific one (one of the next 3)
+	 */
+	ICE_DDP_PKG_ALREADY_LOADED = -1,
+
+	/* Indicates that a DDP package of the same version has already been
+	 * loaded onto the device by a previous call or by another PF
+	 */
+	ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED = -2,
+
+	/* The device has a DDP package that is not supported by the driver */
+	ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED = -3,
+
+	/* The device has a compatible package
+	 * (but different from the request) already loaded
+	 */
+	ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED = -4,
+
+	/* The firmware loaded on the device is not compatible with
+	 * the DDP package loaded
+	 */
+	ICE_DDP_PKG_FW_MISMATCH = -5,
+
+	/* The DDP package file is invalid */
+	ICE_DDP_PKG_INVALID_FILE = -6,
+
+	/* The version of the DDP package provided is higher than
+	 * the driver supports
+	 */
+	ICE_DDP_PKG_FILE_VERSION_TOO_HIGH = -7,
+
+	/* The version of the DDP package provided is lower than the
+	 * driver supports
+	 */
+	ICE_DDP_PKG_FILE_VERSION_TOO_LOW = -8,
+
+	/* The signature of the DDP package file provided is invalid */
+	ICE_DDP_PKG_FILE_SIGNATURE_INVALID = -9,
+
+	/* The DDP package file security revision is too low and not
+	 * supported by firmware
+	 */
+	ICE_DDP_PKG_FILE_REVISION_TOO_LOW = -10,
+
+	/* An error occurred in firmware while loading the DDP package */
+	ICE_DDP_PKG_LOAD_ERROR = -11,
+
+	/* Other errors */
+	ICE_DDP_PKG_ERR = -12
+};
+
+/* Package and segment headers and tables */
+struct ice_pkg_hdr {
+	struct ice_pkg_ver pkg_format_ver;
+	__le32 seg_count;
+	__le32 seg_offset[];
+};
+
+/* generic segment */
+struct ice_generic_seg_hdr {
+#define SEGMENT_TYPE_METADATA 0x00000001
+#define SEGMENT_TYPE_ICE 0x00000010
+	__le32 seg_type;
+	struct ice_pkg_ver seg_format_ver;
+	__le32 seg_size;
+	char seg_id[ICE_PKG_NAME_SIZE];
+};
+
+/* ice specific segment */
+
+union ice_device_id {
+	struct {
+		__le16 device_id;
+		__le16 vendor_id;
+	} dev_vend_id;
+	__le32 id;
+};
+
+struct ice_device_id_entry {
+	union ice_device_id device;
+	union ice_device_id sub_device;
+};
+
+struct ice_seg {
+	struct ice_generic_seg_hdr hdr;
+	__le32 device_table_count;
+	struct ice_device_id_entry device_table[];
+};
+
+struct ice_nvm_table {
+	__le32 table_count;
+	__le32 vers[];
+};
+
+struct ice_buf {
+#define ICE_PKG_BUF_SIZE 4096
+	u8 buf[ICE_PKG_BUF_SIZE];
+};
+
+struct ice_buf_table {
+	__le32 buf_count;
+	struct ice_buf buf_array[];
+};
+
+struct ice_run_time_cfg_seg {
+	struct ice_generic_seg_hdr hdr;
+	u8 rsvd[8];
+	struct ice_buf_table buf_table;
+};
+
+/* global metadata specific segment */
+struct ice_global_metadata_seg {
+	struct ice_generic_seg_hdr hdr;
+	struct ice_pkg_ver pkg_ver;
+	__le32 rsvd;
+	char pkg_name[ICE_PKG_NAME_SIZE];
+};
+
+#define ICE_MIN_S_OFF 12
+#define ICE_MAX_S_OFF 4095
+#define ICE_MIN_S_SZ 1
+#define ICE_MAX_S_SZ 4084
+
+/* section information */
+struct ice_section_entry {
+	__le32 type;
+	__le16 offset;
+	__le16 size;
+};
+
+#define ICE_MIN_S_COUNT 1
+#define ICE_MAX_S_COUNT 511
+#define ICE_MIN_S_DATA_END 12
+#define ICE_MAX_S_DATA_END 4096
+
+#define ICE_METADATA_BUF 0x80000000
+
+struct ice_buf_hdr {
+	__le16 section_count;
+	__le16 data_end;
+	struct ice_section_entry section_entry[];
+};
+
+#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz)                                 \
+	((ICE_PKG_BUF_SIZE -                                                  \
+	  struct_size((struct ice_buf_hdr *)0, section_entry, 1) - (hd_sz)) / \
+	 (ent_sz))
+
+/* ice package section IDs */
+#define ICE_SID_METADATA 1
+#define ICE_SID_XLT0_SW 10
+#define ICE_SID_XLT_KEY_BUILDER_SW 11
+#define ICE_SID_XLT1_SW 12
+#define ICE_SID_XLT2_SW 13
+#define ICE_SID_PROFID_TCAM_SW 14
+#define ICE_SID_PROFID_REDIR_SW 15
+#define ICE_SID_FLD_VEC_SW 16
+#define ICE_SID_CDID_KEY_BUILDER_SW 17
+
+struct ice_meta_sect {
+	struct ice_pkg_ver ver;
+#define ICE_META_SECT_NAME_SIZE 28
+	char name[ICE_META_SECT_NAME_SIZE];
+	__le32 track_id;
+};
+
+#define ICE_SID_CDID_REDIR_SW 18
+
+#define ICE_SID_XLT0_ACL 20
+#define ICE_SID_XLT_KEY_BUILDER_ACL 21
+#define ICE_SID_XLT1_ACL 22
+#define ICE_SID_XLT2_ACL 23
+#define ICE_SID_PROFID_TCAM_ACL 24
+#define ICE_SID_PROFID_REDIR_ACL 25
+#define ICE_SID_FLD_VEC_ACL 26
+#define ICE_SID_CDID_KEY_BUILDER_ACL 27
+#define ICE_SID_CDID_REDIR_ACL 28
+
+#define ICE_SID_XLT0_FD 30
+#define ICE_SID_XLT_KEY_BUILDER_FD 31
+#define ICE_SID_XLT1_FD 32
+#define ICE_SID_XLT2_FD 33
+#define ICE_SID_PROFID_TCAM_FD 34
+#define ICE_SID_PROFID_REDIR_FD 35
+#define ICE_SID_FLD_VEC_FD 36
+#define ICE_SID_CDID_KEY_BUILDER_FD 37
+#define ICE_SID_CDID_REDIR_FD 38
+
+#define ICE_SID_XLT0_RSS 40
+#define ICE_SID_XLT_KEY_BUILDER_RSS 41
+#define ICE_SID_XLT1_RSS 42
+#define ICE_SID_XLT2_RSS 43
+#define ICE_SID_PROFID_TCAM_RSS 44
+#define ICE_SID_PROFID_REDIR_RSS 45
+#define ICE_SID_FLD_VEC_RSS 46
+#define ICE_SID_CDID_KEY_BUILDER_RSS 47
+#define ICE_SID_CDID_REDIR_RSS 48
+
+#define ICE_SID_RXPARSER_MARKER_PTYPE 55
+#define ICE_SID_RXPARSER_BOOST_TCAM 56
+#define ICE_SID_RXPARSER_METADATA_INIT 58
+#define ICE_SID_TXPARSER_BOOST_TCAM 66
+
+#define ICE_SID_XLT0_PE 80
+#define ICE_SID_XLT_KEY_BUILDER_PE 81
+#define ICE_SID_XLT1_PE 82
+#define ICE_SID_XLT2_PE 83
+#define ICE_SID_PROFID_TCAM_PE 84
+#define ICE_SID_PROFID_REDIR_PE 85
+#define ICE_SID_FLD_VEC_PE 86
+#define ICE_SID_CDID_KEY_BUILDER_PE 87
+#define ICE_SID_CDID_REDIR_PE 88
+
+/* Label Metadata section IDs */
+#define ICE_SID_LBL_FIRST 0x80000010
+#define ICE_SID_LBL_RXPARSER_TMEM 0x80000018
+/* The following define MUST be updated to reflect the last label section ID */
+#define ICE_SID_LBL_LAST 0x80000038
+
+/* Label ICE runtime configuration section IDs */
+#define ICE_SID_TX_5_LAYER_TOPO 0x10
+
+enum ice_block {
+	ICE_BLK_SW = 0,
+	ICE_BLK_ACL,
+	ICE_BLK_FD,
+	ICE_BLK_RSS,
+	ICE_BLK_PE,
+	ICE_BLK_COUNT
+};
+
+enum ice_sect {
+	ICE_XLT0 = 0,
+	ICE_XLT_KB,
+	ICE_XLT1,
+	ICE_XLT2,
+	ICE_PROF_TCAM,
+	ICE_PROF_REDIR,
+	ICE_VEC_TBL,
+	ICE_CDID_KB,
+	ICE_CDID_REDIR,
+	ICE_SECT_COUNT
+};
+
+/* package labels */
+struct ice_label {
+	__le16 value;
+#define ICE_PKG_LABEL_SIZE 64
+	char name[ICE_PKG_LABEL_SIZE];
+};
+
+struct ice_label_section {
+	__le16 count;
+	struct ice_label label[];
+};
+
+#define ICE_MAX_LABELS_IN_BUF                                             \
+	ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_label_section *)0, \
+					   label, 1) -                    \
+				       sizeof(struct ice_label),          \
+			       sizeof(struct ice_label))
+
+struct ice_sw_fv_section {
+	__le16 count;
+	__le16 base_offset;
+	struct ice_fv fv[];
+};
+
+struct ice_sw_fv_list_entry {
+	struct list_head list_entry;
+	u32 profile_id;
+	struct ice_fv *fv_ptr;
+};
+
+/* The BOOST TCAM stores the match packet header in reverse order, meaning
+ * the fields are reversed; in addition, this means that the normally big endian
+ * fields of the packet are now little endian.
+ */
+struct ice_boost_key_value {
+#define ICE_BOOST_REMAINING_HV_KEY 15
+	u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY];
+	__le16 hv_dst_port_key;
+	__le16 hv_src_port_key;
+	u8 tcam_search_key;
+} __packed;
+
+struct ice_boost_key {
+	struct ice_boost_key_value key;
+	struct ice_boost_key_value key2;
+};
+
+/* package Boost TCAM entry */
+struct ice_boost_tcam_entry {
+	__le16 addr;
+	__le16 reserved;
+	/* break up the 40 bytes of key into different fields */
+	struct ice_boost_key key;
+	u8 boost_hit_index_group;
+	/* The following contains bitfields which are not on byte boundaries.
+	 * These fields are currently unused by driver software.
+	 */
+#define ICE_BOOST_BIT_FIELDS 43
+	u8 bit_fields[ICE_BOOST_BIT_FIELDS];
+};
+
+struct ice_boost_tcam_section {
+	__le16 count;
+	__le16 reserved;
+	struct ice_boost_tcam_entry tcam[];
+};
+
+#define ICE_MAX_BST_TCAMS_IN_BUF                                               \
+	ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_boost_tcam_section *)0, \
+					   tcam, 1) -                          \
+				       sizeof(struct ice_boost_tcam_entry),    \
+			       sizeof(struct ice_boost_tcam_entry))
+
+/* package Marker Ptype TCAM entry */
+struct ice_marker_ptype_tcam_entry {
+#define ICE_MARKER_PTYPE_TCAM_ADDR_MAX 1024
+	__le16 addr;
+	__le16 ptype;
+	u8 keys[20];
+};
+
+struct ice_marker_ptype_tcam_section {
+	__le16 count;
+	__le16 reserved;
+	struct ice_marker_ptype_tcam_entry tcam[];
+};
+
+#define ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF                                    \
+	ICE_MAX_ENTRIES_IN_BUF(                                              \
+		struct_size((struct ice_marker_ptype_tcam_section *)0, tcam, \
+			    1) -                                             \
+			sizeof(struct ice_marker_ptype_tcam_entry),          \
+		sizeof(struct ice_marker_ptype_tcam_entry))
+
+struct ice_xlt1_section {
+	__le16 count;
+	__le16 offset;
+	u8 value[];
+};
+
+struct ice_xlt2_section {
+	__le16 count;
+	__le16 offset;
+	__le16 value[];
+};
+
+struct ice_prof_redir_section {
+	__le16 count;
+	__le16 offset;
+	u8 redir_value[];
+};
+
+/* package buffer building */
+
+struct ice_buf_build {
+	struct ice_buf buf;
+	u16 reserved_section_table_entries;
+};
+
+struct ice_pkg_enum {
+	struct ice_buf_table *buf_table;
+	u32 buf_idx;
+
+	u32 type;
+	struct ice_buf_hdr *buf;
+	u32 sect_idx;
+	void *sect;
+	u32 sect_type;
+
+	u32 entry_idx;
+	void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
+};
+
+int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			u16 buf_size, bool last_buf, u32 *error_offset,
+			u32 *error_info, struct ice_sq_cd *cd);
+int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
+			  u16 buf_size, struct ice_sq_cd *cd);
+
+void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size);
+
+enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len);
+
+struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw);
+
+struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
+						struct ice_pkg_hdr *pkg_hdr);
+
+int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count);
+int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count);
+
+int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count);
+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);
+
+struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf);
+
+#endif
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 0fae0186bd85..05f216af8c81 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -371,10 +371,7 @@ out_free_ctx:
 
 /**
  * ice_devlink_reload_empr_start - Start EMP reset to activate new firmware
- * @devlink: pointer to the devlink instance to reload
- * @netns_change: if true, the network namespace is changing
- * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE
- * @limit: limits on what reload should do, such as not resetting
+ * @pf: pointer to the pf instance
  * @extack: netlink extended ACK structure
  *
  * Allow user to activate new Embedded Management Processor firmware by
@@ -387,12 +384,9 @@ out_free_ctx:
  * any source.
  */
 static int
-ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change,
-			      enum devlink_reload_action action,
-			      enum devlink_reload_limit limit,
+ice_devlink_reload_empr_start(struct ice_pf *pf,
 			      struct netlink_ext_ack *extack)
 {
-	struct ice_pf *pf = devlink_priv(devlink);
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	u8 pending;
@@ -431,11 +425,51 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change,
 }
 
 /**
+ * ice_devlink_reload_down - prepare for reload
+ * @devlink: pointer to the devlink instance to reload
+ * @netns_change: if true, the network namespace is changing
+ * @action: the action to perform
+ * @limit: limits on what reload should do, such as not resetting
+ * @extack: netlink extended ACK structure
+ */
+static int
+ice_devlink_reload_down(struct devlink *devlink, bool netns_change,
+			enum devlink_reload_action action,
+			enum devlink_reload_limit limit,
+			struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	switch (action) {
+	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");
+			return -EOPNOTSUPP;
+		}
+		if (ice_is_adq_active(pf)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Turn off ADQ before doing reinit\n");
+			return -EOPNOTSUPP;
+		}
+		if (ice_has_vfs(pf)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Remove all VFs before doing reinit\n");
+			return -EOPNOTSUPP;
+		}
+		ice_unload(pf);
+		return 0;
+	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
+		return ice_devlink_reload_empr_start(pf, extack);
+	default:
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
  * ice_devlink_reload_empr_finish - Wait for EMP reset to finish
- * @devlink: pointer to the devlink instance reloading
- * @action: the action requested
- * @limit: limits imposed by userspace, such as not resetting
- * @actions_performed: on return, indicate what actions actually performed
+ * @pf: pointer to the pf instance
  * @extack: netlink extended ACK structure
  *
  * Wait for driver to finish rebuilding after EMP reset is completed. This
@@ -443,17 +477,11 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change,
  * for the driver's rebuild to complete.
  */
 static int
-ice_devlink_reload_empr_finish(struct devlink *devlink,
-			       enum devlink_reload_action action,
-			       enum devlink_reload_limit limit,
-			       u32 *actions_performed,
+ice_devlink_reload_empr_finish(struct ice_pf *pf,
 			       struct netlink_ext_ack *extack)
 {
-	struct ice_pf *pf = devlink_priv(devlink);
 	int err;
 
-	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
-
 	err = ice_wait_for_reset(pf, 60 * HZ);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Device still resetting after 1 minute");
@@ -1192,12 +1220,43 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 	return status;
 }
 
+/**
+ * ice_devlink_reload_up - do reload up after reinit
+ * @devlink: pointer to the devlink instance reloading
+ * @action: the action requested
+ * @limit: limits imposed by userspace, such as not resetting
+ * @actions_performed: on return, indicate what actions actually performed
+ * @extack: netlink extended ACK structure
+ */
+static int
+ice_devlink_reload_up(struct devlink *devlink,
+		      enum devlink_reload_action action,
+		      enum devlink_reload_limit limit,
+		      u32 *actions_performed,
+		      struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	switch (action) {
+	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
+		*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
+		return ice_load(pf);
+	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
+		*actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
+		return ice_devlink_reload_empr_finish(pf, extack);
+	default:
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct devlink_ops ice_devlink_ops = {
 	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
-	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
+			  BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
 	/* The ice driver currently does not support driver reinit */
-	.reload_down = ice_devlink_reload_empr_start,
-	.reload_up = ice_devlink_reload_empr_finish,
+	.reload_down = ice_devlink_reload_down,
+	.reload_up = ice_devlink_reload_up,
 	.port_split = ice_devlink_port_split,
 	.port_unsplit = ice_devlink_port_unsplit,
 	.eswitch_mode_get = ice_eswitch_mode_get,
@@ -1376,7 +1435,6 @@ void ice_devlink_register(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
 
-	devlink_set_features(devlink, DEVLINK_F_RELOAD);
 	devlink_register(devlink);
 }
 
@@ -1411,25 +1469,9 @@ ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid)
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
-	union devlink_param_value value;
-	int err;
 
-	err = devlink_params_register(devlink, ice_devlink_params,
-				      ARRAY_SIZE(ice_devlink_params));
-	if (err)
-		return err;
-
-	value.vbool = false;
-	devlink_param_driverinit_value_set(devlink,
-					   DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP,
-					   value);
-
-	value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags) ? true : false;
-	devlink_param_driverinit_value_set(devlink,
-					   DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-					   value);
-
-	return 0;
+	return devlink_params_register(devlink, ice_devlink_params,
+				       ARRAY_SIZE(ice_devlink_params));
 }
 
 void ice_devlink_unregister_params(struct ice_pf *pf)
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index f9f15acae90a..f6dd3f8fd936 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -71,17 +71,17 @@ void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf)
 	if (!ice_is_switchdev_running(vf->pf))
 		return;
 
-	if (is_valid_ether_addr(vf->hw_lan_addr.addr)) {
+	if (is_valid_ether_addr(vf->hw_lan_addr)) {
 		err = ice_eswitch_add_vf_mac_rule(vf->pf, vf,
-						  vf->hw_lan_addr.addr);
+						  vf->hw_lan_addr);
 		if (err) {
 			dev_err(ice_pf_to_dev(vf->pf), "Failed to add MAC %pM for VF %d\n, error %d\n",
-				vf->hw_lan_addr.addr, vf->vf_id, err);
+				vf->hw_lan_addr, vf->vf_id, err);
 			return;
 		}
 		vf->num_mac++;
 
-		ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr);
+		ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr);
 	}
 }
 
@@ -237,7 +237,7 @@ ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi)
 		ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
 		metadata_dst_free(vf->repr->dst);
 		vf->repr->dst = NULL;
-		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr,
+		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr,
 					       ICE_FWD_TO_VSI);
 
 		netif_napi_del(&vf->repr->q_vector->napi);
@@ -265,14 +265,14 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf)
 						   GFP_KERNEL);
 		if (!vf->repr->dst) {
 			ice_fltr_add_mac_and_broadcast(vsi,
-						       vf->hw_lan_addr.addr,
+						       vf->hw_lan_addr,
 						       ICE_FWD_TO_VSI);
 			goto err;
 		}
 
 		if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) {
 			ice_fltr_add_mac_and_broadcast(vsi,
-						       vf->hw_lan_addr.addr,
+						       vf->hw_lan_addr,
 						       ICE_FWD_TO_VSI);
 			metadata_dst_free(vf->repr->dst);
 			vf->repr->dst = NULL;
@@ -281,7 +281,7 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf)
 
 		if (ice_vsi_add_vlan_zero(vsi)) {
 			ice_fltr_add_mac_and_broadcast(vsi,
-						       vf->hw_lan_addr.addr,
+						       vf->hw_lan_addr,
 						       ICE_FWD_TO_VSI);
 			metadata_dst_free(vf->repr->dst);
 			vf->repr->dst = NULL;
@@ -338,7 +338,7 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi)
 
 	ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof);
 	if (ret) {
-		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI);
+		ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI);
 		dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor",
 			vsi->vf->vf_id);
 	}
@@ -425,7 +425,13 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 static struct ice_vsi *
 ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, NULL, NULL);
+	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);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index a359f1610fc1..b360bd8f1599 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -656,7 +656,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi)
 	if (status)
 		goto err_setup_rx_ring;
 
-	status = ice_vsi_cfg(vsi);
+	status = ice_vsi_cfg_lan(vsi);
 	if (status)
 		goto err_setup_rx_ring;
 
@@ -664,7 +664,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi)
 	if (status)
 		goto err_start_rx_ring;
 
-	return status;
+	return 0;
 
 err_start_rx_ring:
 	ice_vsi_free_rx_rings(vsi);
@@ -1950,8 +1950,7 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 			   ICE_PHY_TYPE_LOW_100G_CAUI4 |
 			   ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC |
 			   ICE_PHY_TYPE_LOW_100G_AUI4 |
-			   ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 |
-			   ICE_PHY_TYPE_LOW_100GBASE_CP2;
+			   ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4;
 	phy_type_mask_hi = ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC |
 			   ICE_PHY_TYPE_HIGH_100G_CAUI2 |
 			   ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC |
@@ -1964,15 +1963,27 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 						100000baseCR4_Full);
 	}
 
-	phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_SR4 |
-			   ICE_PHY_TYPE_LOW_100GBASE_SR2;
-	if (phy_types_low & phy_type_mask_lo) {
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR2_Full);
+		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
+						100000baseCR2_Full);
+	}
+
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100000baseSR4_Full);
 		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
 						100000baseSR4_Full);
 	}
 
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseSR2_Full);
+		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
+						100000baseSR2_Full);
+	}
+
 	phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_LR4 |
 			   ICE_PHY_TYPE_LOW_100GBASE_DR;
 	if (phy_types_low & phy_type_mask_lo) {
@@ -1984,14 +1995,20 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 
 	phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_KR4 |
 			   ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4;
-	phy_type_mask_hi = ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4;
-	if (phy_types_low & phy_type_mask_lo ||
-	    phy_types_high & phy_type_mask_hi) {
+	if (phy_types_low & phy_type_mask_lo) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100000baseKR4_Full);
 		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
 						100000baseKR4_Full);
 	}
+
+	if (phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR2_Full);
+		ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
+						100000baseKR2_Full);
+	}
+
 }
 
 #define TEST_SET_BITS_TIMEOUT	50
@@ -2242,17 +2259,15 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 						  100baseT_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_100MB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
-						  1000baseX_Full))
-		adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB;
-	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  1000baseX_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  1000baseT_Full) ||
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  1000baseKX_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
-						  2500baseT_Full))
-		adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB;
-	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  2500baseT_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  2500baseX_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
@@ -2261,9 +2276,8 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  10000baseT_Full) ||
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
-						  10000baseKR_Full))
-		adv_link_speed |= ICE_AQ_LINK_SPEED_10GB;
-	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  10000baseKR_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  10000baseSR_Full) ||
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  10000baseLR_Full))
@@ -2287,9 +2301,8 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  50000baseCR2_Full) ||
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
-						  50000baseKR2_Full))
-		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
-	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseKR2_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  50000baseSR2_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
@@ -2299,7 +2312,13 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  100000baseLR4_ER4_Full) ||
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
-						  100000baseKR4_Full))
+						  100000baseKR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseCR2_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseSR2_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseKR2_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_100GB;
 
 	return adv_link_speed;
@@ -3027,8 +3046,6 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		/* clone ring and setup updated count */
 		xdp_rings[i] = *vsi->xdp_rings[i];
 		xdp_rings[i].count = new_tx_cnt;
-		xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1;
-		xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1;
 		xdp_rings[i].desc = NULL;
 		xdp_rings[i].tx_buf = NULL;
 		err = ice_setup_tx_ring(&xdp_rings[i]);
@@ -3073,7 +3090,7 @@ process_rx:
 
 		/* allocate Rx buffers */
 		err = ice_alloc_rx_bufs(&rx_rings[i],
-					ICE_DESC_UNUSED(&rx_rings[i]));
+					ICE_RX_DESC_UNUSED(&rx_rings[i]));
 rx_unwind:
 		if (err) {
 			while (i) {
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 4b3bb19e1d06..5ce413965930 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -6,23 +6,6 @@
 #include "ice_flow.h"
 #include "ice.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
- * prefixes will be saved to allow enabling double VLAN mode.
- */
-#define ICE_DVM_PRE	"BOOST_MAC_VLAN_DVM"	/* enable these entries */
-#define ICE_SVM_PRE	"BOOST_MAC_VLAN_SVM"	/* disable these entries */
-
-/* To support tunneling entries by PF, the package will append the PF number to
- * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc.
- */
-#define ICE_TNL_PRE	"TNL_"
-static const struct ice_tunnel_type_scan tnls[] = {
-	{ TNL_VXLAN,		"TNL_VXLAN_PF" },
-	{ TNL_GENEVE,		"TNL_GENEVE_PF" },
-	{ TNL_LAST,		"" }
-};
-
 static const u32 ice_sect_lkup[ICE_BLK_COUNT][ICE_SECT_COUNT] = {
 	/* SWITCH */
 	{
@@ -104,225 +87,6 @@ static u32 ice_sect_id(enum ice_block blk, enum ice_sect sect)
 }
 
 /**
- * ice_pkg_val_buf
- * @buf: pointer to the ice buffer
- *
- * This helper function validates a buffer's header.
- */
-static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf)
-{
-	struct ice_buf_hdr *hdr;
-	u16 section_count;
-	u16 data_end;
-
-	hdr = (struct ice_buf_hdr *)buf->buf;
-	/* verify data */
-	section_count = le16_to_cpu(hdr->section_count);
-	if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT)
-		return NULL;
-
-	data_end = le16_to_cpu(hdr->data_end);
-	if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END)
-		return NULL;
-
-	return hdr;
-}
-
-/**
- * ice_find_buf_table
- * @ice_seg: pointer to the ice segment
- *
- * Returns the address of the buffer table within the ice segment.
- */
-static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg)
-{
-	struct ice_nvm_table *nvms;
-
-	nvms = (struct ice_nvm_table *)
-		(ice_seg->device_table +
-		 le32_to_cpu(ice_seg->device_table_count));
-
-	return (__force struct ice_buf_table *)
-		(nvms->vers + le32_to_cpu(nvms->table_count));
-}
-
-/**
- * ice_pkg_enum_buf
- * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
- * @state: pointer to the enum state
- *
- * This function will enumerate all the buffers in the ice segment. The first
- * call is made with the ice_seg parameter non-NULL; on subsequent calls,
- * ice_seg is set to NULL which continues the enumeration. When the function
- * returns a NULL pointer, then the end of the buffers has been reached, or an
- * unexpected value has been detected (for example an invalid section count or
- * an invalid buffer end value).
- */
-static struct ice_buf_hdr *
-ice_pkg_enum_buf(struct ice_seg *ice_seg, struct ice_pkg_enum *state)
-{
-	if (ice_seg) {
-		state->buf_table = ice_find_buf_table(ice_seg);
-		if (!state->buf_table)
-			return NULL;
-
-		state->buf_idx = 0;
-		return ice_pkg_val_buf(state->buf_table->buf_array);
-	}
-
-	if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count))
-		return ice_pkg_val_buf(state->buf_table->buf_array +
-				       state->buf_idx);
-	else
-		return NULL;
-}
-
-/**
- * ice_pkg_advance_sect
- * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
- * @state: pointer to the enum state
- *
- * This helper function will advance the section within the ice segment,
- * also advancing the buffer if needed.
- */
-static bool
-ice_pkg_advance_sect(struct ice_seg *ice_seg, struct ice_pkg_enum *state)
-{
-	if (!ice_seg && !state->buf)
-		return false;
-
-	if (!ice_seg && state->buf)
-		if (++state->sect_idx < le16_to_cpu(state->buf->section_count))
-			return true;
-
-	state->buf = ice_pkg_enum_buf(ice_seg, state);
-	if (!state->buf)
-		return false;
-
-	/* start of new buffer, reset section index */
-	state->sect_idx = 0;
-	return true;
-}
-
-/**
- * ice_pkg_enum_section
- * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
- * @state: pointer to the enum state
- * @sect_type: section type to enumerate
- *
- * This function will enumerate all the sections of a particular type in the
- * ice segment. The first call is made with the ice_seg parameter non-NULL;
- * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
- * When the function returns a NULL pointer, then the end of the matching
- * sections has been reached.
- */
-static void *
-ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
-		     u32 sect_type)
-{
-	u16 offset, size;
-
-	if (ice_seg)
-		state->type = sect_type;
-
-	if (!ice_pkg_advance_sect(ice_seg, state))
-		return NULL;
-
-	/* scan for next matching section */
-	while (state->buf->section_entry[state->sect_idx].type !=
-	       cpu_to_le32(state->type))
-		if (!ice_pkg_advance_sect(NULL, state))
-			return NULL;
-
-	/* validate section */
-	offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
-	if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF)
-		return NULL;
-
-	size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size);
-	if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ)
-		return NULL;
-
-	/* make sure the section fits in the buffer */
-	if (offset + size > ICE_PKG_BUF_SIZE)
-		return NULL;
-
-	state->sect_type =
-		le32_to_cpu(state->buf->section_entry[state->sect_idx].type);
-
-	/* calc pointer to this section */
-	state->sect = ((u8 *)state->buf) +
-		le16_to_cpu(state->buf->section_entry[state->sect_idx].offset);
-
-	return state->sect;
-}
-
-/**
- * ice_pkg_enum_entry
- * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
- * @state: pointer to the enum state
- * @sect_type: section type to enumerate
- * @offset: pointer to variable that receives the offset in the table (optional)
- * @handler: function that handles access to the entries into the section type
- *
- * This function will enumerate all the entries in particular section type in
- * the ice segment. The first call is made with the ice_seg parameter non-NULL;
- * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
- * When the function returns a NULL pointer, then the end of the entries has
- * been reached.
- *
- * Since each section may have a different header and entry size, the handler
- * function is needed to determine the number and location entries in each
- * section.
- *
- * The offset parameter is optional, but should be used for sections that
- * contain an offset for each section table. For such cases, the section handler
- * function must return the appropriate offset + index to give the absolution
- * offset for each entry. For example, if the base for a section's header
- * indicates a base offset of 10, and the index for the entry is 2, then
- * section handler function should set the offset to 10 + 2 = 12.
- */
-static void *
-ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
-		   u32 sect_type, u32 *offset,
-		   void *(*handler)(u32 sect_type, void *section,
-				    u32 index, u32 *offset))
-{
-	void *entry;
-
-	if (ice_seg) {
-		if (!handler)
-			return NULL;
-
-		if (!ice_pkg_enum_section(ice_seg, state, sect_type))
-			return NULL;
-
-		state->entry_idx = 0;
-		state->handler = handler;
-	} else {
-		state->entry_idx++;
-	}
-
-	if (!state->handler)
-		return NULL;
-
-	/* get entry */
-	entry = state->handler(state->sect_type, state->sect, state->entry_idx,
-			       offset);
-	if (!entry) {
-		/* end of a section, look for another section of this type */
-		if (!ice_pkg_enum_section(NULL, state, 0))
-			return NULL;
-
-		state->entry_idx = 0;
-		entry = state->handler(state->sect_type, state->sect,
-				       state->entry_idx, offset);
-	}
-
-	return entry;
-}
-
-/**
  * ice_hw_ptype_ena - check if the PTYPE is enabled or not
  * @hw: pointer to the HW structure
  * @ptype: the hardware PTYPE
@@ -333,312 +97,6 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype)
 	       test_bit(ptype, hw->hw_ptype);
 }
 
-/**
- * ice_marker_ptype_tcam_handler
- * @sect_type: section type
- * @section: pointer to section
- * @index: index of the Marker PType TCAM entry to be returned
- * @offset: pointer to receive absolute offset, always 0 for ptype TCAM sections
- *
- * This is a callback function that can be passed to ice_pkg_enum_entry.
- * Handles enumeration of individual Marker PType TCAM entries.
- */
-static void *
-ice_marker_ptype_tcam_handler(u32 sect_type, void *section, u32 index,
-			      u32 *offset)
-{
-	struct ice_marker_ptype_tcam_section *marker_ptype;
-
-	if (sect_type != ICE_SID_RXPARSER_MARKER_PTYPE)
-		return NULL;
-
-	if (index > ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF)
-		return NULL;
-
-	if (offset)
-		*offset = 0;
-
-	marker_ptype = section;
-	if (index >= le16_to_cpu(marker_ptype->count))
-		return NULL;
-
-	return marker_ptype->tcam + index;
-}
-
-/**
- * ice_fill_hw_ptype - fill the enabled PTYPE bit information
- * @hw: pointer to the HW structure
- */
-static void ice_fill_hw_ptype(struct ice_hw *hw)
-{
-	struct ice_marker_ptype_tcam_entry *tcam;
-	struct ice_seg *seg = hw->seg;
-	struct ice_pkg_enum state;
-
-	bitmap_zero(hw->hw_ptype, ICE_FLOW_PTYPE_MAX);
-	if (!seg)
-		return;
-
-	memset(&state, 0, sizeof(state));
-
-	do {
-		tcam = ice_pkg_enum_entry(seg, &state,
-					  ICE_SID_RXPARSER_MARKER_PTYPE, NULL,
-					  ice_marker_ptype_tcam_handler);
-		if (tcam &&
-		    le16_to_cpu(tcam->addr) < ICE_MARKER_PTYPE_TCAM_ADDR_MAX &&
-		    le16_to_cpu(tcam->ptype) < ICE_FLOW_PTYPE_MAX)
-			set_bit(le16_to_cpu(tcam->ptype), hw->hw_ptype);
-
-		seg = NULL;
-	} while (tcam);
-}
-
-/**
- * ice_boost_tcam_handler
- * @sect_type: section type
- * @section: pointer to section
- * @index: index of the boost TCAM entry to be returned
- * @offset: pointer to receive absolute offset, always 0 for boost TCAM sections
- *
- * This is a callback function that can be passed to ice_pkg_enum_entry.
- * Handles enumeration of individual boost TCAM entries.
- */
-static void *
-ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, u32 *offset)
-{
-	struct ice_boost_tcam_section *boost;
-
-	if (!section)
-		return NULL;
-
-	if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM)
-		return NULL;
-
-	/* cppcheck-suppress nullPointer */
-	if (index > ICE_MAX_BST_TCAMS_IN_BUF)
-		return NULL;
-
-	if (offset)
-		*offset = 0;
-
-	boost = section;
-	if (index >= le16_to_cpu(boost->count))
-		return NULL;
-
-	return boost->tcam + index;
-}
-
-/**
- * ice_find_boost_entry
- * @ice_seg: pointer to the ice segment (non-NULL)
- * @addr: Boost TCAM address of entry to search for
- * @entry: returns pointer to the entry
- *
- * Finds a particular Boost TCAM entry and returns a pointer to that entry
- * if it is found. The ice_seg parameter must not be NULL since the first call
- * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure.
- */
-static int
-ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr,
-		     struct ice_boost_tcam_entry **entry)
-{
-	struct ice_boost_tcam_entry *tcam;
-	struct ice_pkg_enum state;
-
-	memset(&state, 0, sizeof(state));
-
-	if (!ice_seg)
-		return -EINVAL;
-
-	do {
-		tcam = ice_pkg_enum_entry(ice_seg, &state,
-					  ICE_SID_RXPARSER_BOOST_TCAM, NULL,
-					  ice_boost_tcam_handler);
-		if (tcam && le16_to_cpu(tcam->addr) == addr) {
-			*entry = tcam;
-			return 0;
-		}
-
-		ice_seg = NULL;
-	} while (tcam);
-
-	*entry = NULL;
-	return -EIO;
-}
-
-/**
- * ice_label_enum_handler
- * @sect_type: section type
- * @section: pointer to section
- * @index: index of the label entry to be returned
- * @offset: pointer to receive absolute offset, always zero for label sections
- *
- * This is a callback function that can be passed to ice_pkg_enum_entry.
- * Handles enumeration of individual label entries.
- */
-static void *
-ice_label_enum_handler(u32 __always_unused sect_type, void *section, u32 index,
-		       u32 *offset)
-{
-	struct ice_label_section *labels;
-
-	if (!section)
-		return NULL;
-
-	/* cppcheck-suppress nullPointer */
-	if (index > ICE_MAX_LABELS_IN_BUF)
-		return NULL;
-
-	if (offset)
-		*offset = 0;
-
-	labels = section;
-	if (index >= le16_to_cpu(labels->count))
-		return NULL;
-
-	return labels->label + index;
-}
-
-/**
- * ice_enum_labels
- * @ice_seg: pointer to the ice segment (NULL on subsequent calls)
- * @type: the section type that will contain the label (0 on subsequent calls)
- * @state: ice_pkg_enum structure that will hold the state of the enumeration
- * @value: pointer to a value that will return the label's value if found
- *
- * Enumerates a list of labels in the package. The caller will call
- * ice_enum_labels(ice_seg, type, ...) to start the enumeration, then call
- * ice_enum_labels(NULL, 0, ...) to continue. When the function returns a NULL
- * the end of the list has been reached.
- */
-static char *
-ice_enum_labels(struct ice_seg *ice_seg, u32 type, struct ice_pkg_enum *state,
-		u16 *value)
-{
-	struct ice_label *label;
-
-	/* Check for valid label section on first call */
-	if (type && !(type >= ICE_SID_LBL_FIRST && type <= ICE_SID_LBL_LAST))
-		return NULL;
-
-	label = ice_pkg_enum_entry(ice_seg, state, type, NULL,
-				   ice_label_enum_handler);
-	if (!label)
-		return NULL;
-
-	*value = le16_to_cpu(label->value);
-	return label->name;
-}
-
-/**
- * ice_add_tunnel_hint
- * @hw: pointer to the HW structure
- * @label_name: label text
- * @val: value of the tunnel port boost entry
- */
-static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val)
-{
-	if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) {
-		u16 i;
-
-		for (i = 0; tnls[i].type != TNL_LAST; i++) {
-			size_t len = strlen(tnls[i].label_prefix);
-
-			/* Look for matching label start, before continuing */
-			if (strncmp(label_name, tnls[i].label_prefix, len))
-				continue;
-
-			/* Make sure this label matches our PF. Note that the PF
-			 * character ('0' - '7') will be located where our
-			 * prefix string's null terminator is located.
-			 */
-			if ((label_name[len] - '0') == hw->pf_id) {
-				hw->tnl.tbl[hw->tnl.count].type = tnls[i].type;
-				hw->tnl.tbl[hw->tnl.count].valid = false;
-				hw->tnl.tbl[hw->tnl.count].boost_addr = val;
-				hw->tnl.tbl[hw->tnl.count].port = 0;
-				hw->tnl.count++;
-				break;
-			}
-		}
-	}
-}
-
-/**
- * ice_add_dvm_hint
- * @hw: pointer to the HW structure
- * @val: value of the boost entry
- * @enable: true if entry needs to be enabled, or false if needs to be disabled
- */
-static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable)
-{
-	if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) {
-		hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val;
-		hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable;
-		hw->dvm_upd.count++;
-	}
-}
-
-/**
- * ice_init_pkg_hints
- * @hw: pointer to the HW structure
- * @ice_seg: pointer to the segment of the package scan (non-NULL)
- *
- * This function will scan the package and save off relevant information
- * (hints or metadata) for driver use. The ice_seg parameter must not be NULL
- * since the first call to ice_enum_labels requires a pointer to an actual
- * ice_seg structure.
- */
-static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
-{
-	struct ice_pkg_enum state;
-	char *label_name;
-	u16 val;
-	int i;
-
-	memset(&hw->tnl, 0, sizeof(hw->tnl));
-	memset(&state, 0, sizeof(state));
-
-	if (!ice_seg)
-		return;
-
-	label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state,
-				     &val);
-
-	while (label_name) {
-		if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE)))
-			/* check for a tunnel entry */
-			ice_add_tunnel_hint(hw, label_name, val);
-
-		/* check for a dvm mode entry */
-		else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE)))
-			ice_add_dvm_hint(hw, val, true);
-
-		/* check for a svm mode entry */
-		else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE)))
-			ice_add_dvm_hint(hw, val, false);
-
-		label_name = ice_enum_labels(NULL, 0, &state, &val);
-	}
-
-	/* Cache the appropriate boost TCAM entry pointers for tunnels */
-	for (i = 0; i < hw->tnl.count; i++) {
-		ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr,
-				     &hw->tnl.tbl[i].boost_entry);
-		if (hw->tnl.tbl[i].boost_entry) {
-			hw->tnl.tbl[i].valid = true;
-			if (hw->tnl.tbl[i].type < __TNL_TYPE_CNT)
-				hw->tnl.valid_count[hw->tnl.tbl[i].type]++;
-		}
-	}
-
-	/* Cache the appropriate boost TCAM entry pointers for DVM and SVM */
-	for (i = 0; i < hw->dvm_upd.count; i++)
-		ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr,
-				     &hw->dvm_upd.tbl[i].boost_entry);
-}
-
 /* Key creation */
 
 #define ICE_DC_KEY	0x1	/* don't care */
@@ -810,51 +268,6 @@ ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off,
 }
 
 /**
- * ice_acquire_global_cfg_lock
- * @hw: pointer to the HW structure
- * @access: access type (read or write)
- *
- * This function will request ownership of the global config lock for reading
- * or writing of the package. When attempting to obtain write access, the
- * caller must check for the following two return values:
- *
- * 0         -  Means the caller has acquired the global config lock
- *              and can perform writing of the package.
- * -EALREADY - Indicates another driver has already written the
- *             package or has found that no update was necessary; in
- *             this case, the caller can just skip performing any
- *             update of the package.
- */
-static int
-ice_acquire_global_cfg_lock(struct ice_hw *hw,
-			    enum ice_aq_res_access_type access)
-{
-	int status;
-
-	status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access,
-				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
-
-	if (!status)
-		mutex_lock(&ice_global_cfg_lock_sw);
-	else if (status == -EALREADY)
-		ice_debug(hw, ICE_DBG_PKG, "Global config lock: No work to do\n");
-
-	return status;
-}
-
-/**
- * ice_release_global_cfg_lock
- * @hw: pointer to the HW structure
- *
- * This function will release the global config lock.
- */
-static void ice_release_global_cfg_lock(struct ice_hw *hw)
-{
-	mutex_unlock(&ice_global_cfg_lock_sw);
-	ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID);
-}
-
-/**
  * ice_acquire_change_lock
  * @hw: pointer to the HW structure
  * @access: access type (read or write)
@@ -880,1325 +293,6 @@ void ice_release_change_lock(struct ice_hw *hw)
 }
 
 /**
- * ice_aq_download_pkg
- * @hw: pointer to the hardware structure
- * @pkg_buf: the package buffer to transfer
- * @buf_size: the size of the package buffer
- * @last_buf: last buffer indicator
- * @error_offset: returns error offset
- * @error_info: returns error information
- * @cd: pointer to command details structure or NULL
- *
- * Download Package (0x0C40)
- */
-static int
-ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
-		    u16 buf_size, bool last_buf, u32 *error_offset,
-		    u32 *error_info, struct ice_sq_cd *cd)
-{
-	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
-	int status;
-
-	if (error_offset)
-		*error_offset = 0;
-	if (error_info)
-		*error_info = 0;
-
-	cmd = &desc.params.download_pkg;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	if (last_buf)
-		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
-
-	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
-	if (status == -EIO) {
-		/* Read error from buffer only when the FW returned an error */
-		struct ice_aqc_download_pkg_resp *resp;
-
-		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
-		if (error_offset)
-			*error_offset = le32_to_cpu(resp->error_offset);
-		if (error_info)
-			*error_info = le32_to_cpu(resp->error_info);
-	}
-
-	return status;
-}
-
-/**
- * ice_aq_upload_section
- * @hw: pointer to the hardware structure
- * @pkg_buf: the package buffer which will receive the section
- * @buf_size: the size of the package buffer
- * @cd: pointer to command details structure or NULL
- *
- * Upload Section (0x0C41)
- */
-int
-ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
-		      u16 buf_size, struct ice_sq_cd *cd)
-{
-	struct ice_aq_desc desc;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
-}
-
-/**
- * ice_aq_update_pkg
- * @hw: pointer to the hardware structure
- * @pkg_buf: the package cmd buffer
- * @buf_size: the size of the package cmd buffer
- * @last_buf: last buffer indicator
- * @error_offset: returns error offset
- * @error_info: returns error information
- * @cd: pointer to command details structure or NULL
- *
- * Update Package (0x0C42)
- */
-static int
-ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size,
-		  bool last_buf, u32 *error_offset, u32 *error_info,
-		  struct ice_sq_cd *cd)
-{
-	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
-	int status;
-
-	if (error_offset)
-		*error_offset = 0;
-	if (error_info)
-		*error_info = 0;
-
-	cmd = &desc.params.download_pkg;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	if (last_buf)
-		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
-
-	status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
-	if (status == -EIO) {
-		/* Read error from buffer only when the FW returned an error */
-		struct ice_aqc_download_pkg_resp *resp;
-
-		resp = (struct ice_aqc_download_pkg_resp *)pkg_buf;
-		if (error_offset)
-			*error_offset = le32_to_cpu(resp->error_offset);
-		if (error_info)
-			*error_info = le32_to_cpu(resp->error_info);
-	}
-
-	return status;
-}
-
-/**
- * ice_find_seg_in_pkg
- * @hw: pointer to the hardware structure
- * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK)
- * @pkg_hdr: pointer to the package header to be searched
- *
- * This function searches a package file for a particular segment type. On
- * success it returns a pointer to the segment header, otherwise it will
- * return NULL.
- */
-static struct ice_generic_seg_hdr *
-ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
-		    struct ice_pkg_hdr *pkg_hdr)
-{
-	u32 i;
-
-	ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n",
-		  pkg_hdr->pkg_format_ver.major, pkg_hdr->pkg_format_ver.minor,
-		  pkg_hdr->pkg_format_ver.update,
-		  pkg_hdr->pkg_format_ver.draft);
-
-	/* Search all package segments for the requested segment type */
-	for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) {
-		struct ice_generic_seg_hdr *seg;
-
-		seg = (struct ice_generic_seg_hdr *)
-			((u8 *)pkg_hdr + le32_to_cpu(pkg_hdr->seg_offset[i]));
-
-		if (le32_to_cpu(seg->seg_type) == seg_type)
-			return seg;
-	}
-
-	return NULL;
-}
-
-/**
- * ice_update_pkg_no_lock
- * @hw: pointer to the hardware structure
- * @bufs: pointer to an array of buffers
- * @count: the number of buffers in the array
- */
-static int
-ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
-{
-	int status = 0;
-	u32 i;
-
-	for (i = 0; i < count; i++) {
-		struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i);
-		bool last = ((i + 1) == count);
-		u32 offset, info;
-
-		status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end),
-					   last, &offset, &info, NULL);
-
-		if (status) {
-			ice_debug(hw, ICE_DBG_PKG, "Update pkg failed: err %d off %d inf %d\n",
-				  status, offset, info);
-			break;
-		}
-	}
-
-	return status;
-}
-
-/**
- * ice_update_pkg
- * @hw: pointer to the hardware structure
- * @bufs: pointer to an array of buffers
- * @count: the number of buffers in the array
- *
- * Obtains change lock and updates package.
- */
-static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
-{
-	int status;
-
-	status = ice_acquire_change_lock(hw, ICE_RES_WRITE);
-	if (status)
-		return status;
-
-	status = ice_update_pkg_no_lock(hw, bufs, count);
-
-	ice_release_change_lock(hw);
-
-	return status;
-}
-
-static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err)
-{
-	switch (aq_err) {
-	case ICE_AQ_RC_ENOSEC:
-	case ICE_AQ_RC_EBADSIG:
-		return ICE_DDP_PKG_FILE_SIGNATURE_INVALID;
-	case ICE_AQ_RC_ESVN:
-		return ICE_DDP_PKG_FILE_REVISION_TOO_LOW;
-	case ICE_AQ_RC_EBADMAN:
-	case ICE_AQ_RC_EBADBUF:
-		return ICE_DDP_PKG_LOAD_ERROR;
-	default:
-		return ICE_DDP_PKG_ERR;
-	}
-}
-
-/**
- * ice_dwnld_cfg_bufs
- * @hw: pointer to the hardware structure
- * @bufs: pointer to an array of buffers
- * @count: the number of buffers in the array
- *
- * Obtains global config lock and downloads the package configuration buffers
- * to the firmware. Metadata buffers are skipped, and the first metadata buffer
- * found indicates that the rest of the buffers are all metadata buffers.
- */
-static enum ice_ddp_state
-ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
-{
-	enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS;
-	struct ice_buf_hdr *bh;
-	enum ice_aq_err err;
-	u32 offset, info, i;
-	int status;
-
-	if (!bufs || !count)
-		return ICE_DDP_PKG_ERR;
-
-	/* If the first buffer's first section has its metadata bit set
-	 * then there are no buffers to be downloaded, and the operation is
-	 * considered a success.
-	 */
-	bh = (struct ice_buf_hdr *)bufs;
-	if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
-		return ICE_DDP_PKG_SUCCESS;
-
-	status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
-	if (status) {
-		if (status == -EALREADY)
-			return ICE_DDP_PKG_ALREADY_LOADED;
-		return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status);
-	}
-
-	for (i = 0; i < count; i++) {
-		bool last = ((i + 1) == count);
-
-		if (!last) {
-			/* check next buffer for metadata flag */
-			bh = (struct ice_buf_hdr *)(bufs + i + 1);
-
-			/* A set metadata flag in the next buffer will signal
-			 * that the current buffer will be the last buffer
-			 * downloaded
-			 */
-			if (le16_to_cpu(bh->section_count))
-				if (le32_to_cpu(bh->section_entry[0].type) &
-				    ICE_METADATA_BUF)
-					last = true;
-		}
-
-		bh = (struct ice_buf_hdr *)(bufs + i);
-
-		status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last,
-					     &offset, &info, NULL);
-
-		/* Save AQ status from download package */
-		if (status) {
-			ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n",
-				  status, offset, info);
-			err = hw->adminq.sq_last_status;
-			state = ice_map_aq_err_to_ddp_state(err);
-			break;
-		}
-
-		if (last)
-			break;
-	}
-
-	if (!status) {
-		status = ice_set_vlan_mode(hw);
-		if (status)
-			ice_debug(hw, ICE_DBG_PKG, "Failed to set VLAN mode: err %d\n",
-				  status);
-	}
-
-	ice_release_global_cfg_lock(hw);
-
-	return state;
-}
-
-/**
- * ice_aq_get_pkg_info_list
- * @hw: pointer to the hardware structure
- * @pkg_info: the buffer which will receive the information list
- * @buf_size: the size of the pkg_info information buffer
- * @cd: pointer to command details structure or NULL
- *
- * Get Package Info List (0x0C43)
- */
-static int
-ice_aq_get_pkg_info_list(struct ice_hw *hw,
-			 struct ice_aqc_get_pkg_info_resp *pkg_info,
-			 u16 buf_size, struct ice_sq_cd *cd)
-{
-	struct ice_aq_desc desc;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list);
-
-	return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd);
-}
-
-/**
- * ice_download_pkg
- * @hw: pointer to the hardware structure
- * @ice_seg: pointer to the segment of the package to be downloaded
- *
- * Handles the download of a complete package.
- */
-static enum ice_ddp_state
-ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg)
-{
-	struct ice_buf_table *ice_buf_tbl;
-	int status;
-
-	ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
-		  ice_seg->hdr.seg_format_ver.major,
-		  ice_seg->hdr.seg_format_ver.minor,
-		  ice_seg->hdr.seg_format_ver.update,
-		  ice_seg->hdr.seg_format_ver.draft);
-
-	ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
-		  le32_to_cpu(ice_seg->hdr.seg_type),
-		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
-
-	ice_buf_tbl = ice_find_buf_table(ice_seg);
-
-	ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
-		  le32_to_cpu(ice_buf_tbl->buf_count));
-
-	status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
-				    le32_to_cpu(ice_buf_tbl->buf_count));
-
-	ice_post_pkg_dwnld_vlan_mode_cfg(hw);
-
-	return status;
-}
-
-/**
- * ice_init_pkg_info
- * @hw: pointer to the hardware structure
- * @pkg_hdr: pointer to the driver's package hdr
- *
- * Saves off the package details into the HW structure.
- */
-static enum ice_ddp_state
-ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
-{
-	struct ice_generic_seg_hdr *seg_hdr;
-
-	if (!pkg_hdr)
-		return ICE_DDP_PKG_ERR;
-
-	seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr);
-	if (seg_hdr) {
-		struct ice_meta_sect *meta;
-		struct ice_pkg_enum state;
-
-		memset(&state, 0, sizeof(state));
-
-		/* Get package information from the Metadata Section */
-		meta = ice_pkg_enum_section((struct ice_seg *)seg_hdr, &state,
-					    ICE_SID_METADATA);
-		if (!meta) {
-			ice_debug(hw, ICE_DBG_INIT, "Did not find ice metadata section in package\n");
-			return ICE_DDP_PKG_INVALID_FILE;
-		}
-
-		hw->pkg_ver = meta->ver;
-		memcpy(hw->pkg_name, meta->name, sizeof(meta->name));
-
-		ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n",
-			  meta->ver.major, meta->ver.minor, meta->ver.update,
-			  meta->ver.draft, meta->name);
-
-		hw->ice_seg_fmt_ver = seg_hdr->seg_format_ver;
-		memcpy(hw->ice_seg_id, seg_hdr->seg_id,
-		       sizeof(hw->ice_seg_id));
-
-		ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n",
-			  seg_hdr->seg_format_ver.major,
-			  seg_hdr->seg_format_ver.minor,
-			  seg_hdr->seg_format_ver.update,
-			  seg_hdr->seg_format_ver.draft,
-			  seg_hdr->seg_id);
-	} else {
-		ice_debug(hw, ICE_DBG_INIT, "Did not find ice segment in driver package\n");
-		return ICE_DDP_PKG_INVALID_FILE;
-	}
-
-	return ICE_DDP_PKG_SUCCESS;
-}
-
-/**
- * ice_get_pkg_info
- * @hw: pointer to the hardware structure
- *
- * Store details of the package currently loaded in HW into the HW structure.
- */
-static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw)
-{
-	enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS;
-	struct ice_aqc_get_pkg_info_resp *pkg_info;
-	u16 size;
-	u32 i;
-
-	size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT);
-	pkg_info = kzalloc(size, GFP_KERNEL);
-	if (!pkg_info)
-		return ICE_DDP_PKG_ERR;
-
-	if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) {
-		state = ICE_DDP_PKG_ERR;
-		goto init_pkg_free_alloc;
-	}
-
-	for (i = 0; i < le32_to_cpu(pkg_info->count); i++) {
-#define ICE_PKG_FLAG_COUNT	4
-		char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 };
-		u8 place = 0;
-
-		if (pkg_info->pkg_info[i].is_active) {
-			flags[place++] = 'A';
-			hw->active_pkg_ver = pkg_info->pkg_info[i].ver;
-			hw->active_track_id =
-				le32_to_cpu(pkg_info->pkg_info[i].track_id);
-			memcpy(hw->active_pkg_name,
-			       pkg_info->pkg_info[i].name,
-			       sizeof(pkg_info->pkg_info[i].name));
-			hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm;
-		}
-		if (pkg_info->pkg_info[i].is_active_at_boot)
-			flags[place++] = 'B';
-		if (pkg_info->pkg_info[i].is_modified)
-			flags[place++] = 'M';
-		if (pkg_info->pkg_info[i].is_in_nvm)
-			flags[place++] = 'N';
-
-		ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n",
-			  i, pkg_info->pkg_info[i].ver.major,
-			  pkg_info->pkg_info[i].ver.minor,
-			  pkg_info->pkg_info[i].ver.update,
-			  pkg_info->pkg_info[i].ver.draft,
-			  pkg_info->pkg_info[i].name, flags);
-	}
-
-init_pkg_free_alloc:
-	kfree(pkg_info);
-
-	return state;
-}
-
-/**
- * ice_verify_pkg - verify package
- * @pkg: pointer to the package buffer
- * @len: size of the package buffer
- *
- * Verifies various attributes of the package file, including length, format
- * version, and the requirement of at least one segment.
- */
-static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
-{
-	u32 seg_count;
-	u32 i;
-
-	if (len < struct_size(pkg, seg_offset, 1))
-		return ICE_DDP_PKG_INVALID_FILE;
-
-	if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ ||
-	    pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR ||
-	    pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD ||
-	    pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT)
-		return ICE_DDP_PKG_INVALID_FILE;
-
-	/* pkg must have at least one segment */
-	seg_count = le32_to_cpu(pkg->seg_count);
-	if (seg_count < 1)
-		return ICE_DDP_PKG_INVALID_FILE;
-
-	/* make sure segment array fits in package length */
-	if (len < struct_size(pkg, seg_offset, seg_count))
-		return ICE_DDP_PKG_INVALID_FILE;
-
-	/* all segments must fit within length */
-	for (i = 0; i < seg_count; i++) {
-		u32 off = le32_to_cpu(pkg->seg_offset[i]);
-		struct ice_generic_seg_hdr *seg;
-
-		/* segment header must fit */
-		if (len < off + sizeof(*seg))
-			return ICE_DDP_PKG_INVALID_FILE;
-
-		seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off);
-
-		/* segment body must fit */
-		if (len < off + le32_to_cpu(seg->seg_size))
-			return ICE_DDP_PKG_INVALID_FILE;
-	}
-
-	return ICE_DDP_PKG_SUCCESS;
-}
-
-/**
- * ice_free_seg - free package segment pointer
- * @hw: pointer to the hardware structure
- *
- * Frees the package segment pointer in the proper manner, depending on if the
- * segment was allocated or just the passed in pointer was stored.
- */
-void ice_free_seg(struct ice_hw *hw)
-{
-	if (hw->pkg_copy) {
-		devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy);
-		hw->pkg_copy = NULL;
-		hw->pkg_size = 0;
-	}
-	hw->seg = NULL;
-}
-
-/**
- * ice_init_pkg_regs - initialize additional package registers
- * @hw: pointer to the hardware structure
- */
-static void ice_init_pkg_regs(struct ice_hw *hw)
-{
-#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF
-#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF
-#define ICE_SW_BLK_IDX	0
-
-	/* setup Switch block input mask, which is 48-bits in two parts */
-	wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L);
-	wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H);
-}
-
-/**
- * ice_chk_pkg_version - check package version for compatibility with driver
- * @pkg_ver: pointer to a version structure to check
- *
- * Check to make sure that the package about to be downloaded is compatible with
- * the driver. To be compatible, the major and minor components of the package
- * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR
- * definitions.
- */
-static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver)
-{
-	if (pkg_ver->major > ICE_PKG_SUPP_VER_MAJ ||
-	    (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ &&
-	     pkg_ver->minor > ICE_PKG_SUPP_VER_MNR))
-		return ICE_DDP_PKG_FILE_VERSION_TOO_HIGH;
-	else if (pkg_ver->major < ICE_PKG_SUPP_VER_MAJ ||
-		 (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ &&
-		  pkg_ver->minor < ICE_PKG_SUPP_VER_MNR))
-		return ICE_DDP_PKG_FILE_VERSION_TOO_LOW;
-
-	return ICE_DDP_PKG_SUCCESS;
-}
-
-/**
- * ice_chk_pkg_compat
- * @hw: pointer to the hardware structure
- * @ospkg: pointer to the package hdr
- * @seg: pointer to the package segment hdr
- *
- * This function checks the package version compatibility with driver and NVM
- */
-static enum ice_ddp_state
-ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg,
-		   struct ice_seg **seg)
-{
-	struct ice_aqc_get_pkg_info_resp *pkg;
-	enum ice_ddp_state state;
-	u16 size;
-	u32 i;
-
-	/* Check package version compatibility */
-	state = ice_chk_pkg_version(&hw->pkg_ver);
-	if (state) {
-		ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n");
-		return state;
-	}
-
-	/* find ICE segment in given package */
-	*seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE,
-						     ospkg);
-	if (!*seg) {
-		ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n");
-		return ICE_DDP_PKG_INVALID_FILE;
-	}
-
-	/* Check if FW is compatible with the OS package */
-	size = struct_size(pkg, pkg_info, ICE_PKG_CNT);
-	pkg = kzalloc(size, GFP_KERNEL);
-	if (!pkg)
-		return ICE_DDP_PKG_ERR;
-
-	if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) {
-		state = ICE_DDP_PKG_LOAD_ERROR;
-		goto fw_ddp_compat_free_alloc;
-	}
-
-	for (i = 0; i < le32_to_cpu(pkg->count); i++) {
-		/* loop till we find the NVM package */
-		if (!pkg->pkg_info[i].is_in_nvm)
-			continue;
-		if ((*seg)->hdr.seg_format_ver.major !=
-			pkg->pkg_info[i].ver.major ||
-		    (*seg)->hdr.seg_format_ver.minor >
-			pkg->pkg_info[i].ver.minor) {
-			state = ICE_DDP_PKG_FW_MISMATCH;
-			ice_debug(hw, ICE_DBG_INIT, "OS package is not compatible with NVM.\n");
-		}
-		/* done processing NVM package so break */
-		break;
-	}
-fw_ddp_compat_free_alloc:
-	kfree(pkg);
-	return state;
-}
-
-/**
- * ice_sw_fv_handler
- * @sect_type: section type
- * @section: pointer to section
- * @index: index of the field vector entry to be returned
- * @offset: ptr to variable that receives the offset in the field vector table
- *
- * This is a callback function that can be passed to ice_pkg_enum_entry.
- * This function treats the given section as of type ice_sw_fv_section and
- * enumerates offset field. "offset" is an index into the field vector table.
- */
-static void *
-ice_sw_fv_handler(u32 sect_type, void *section, u32 index, u32 *offset)
-{
-	struct ice_sw_fv_section *fv_section = section;
-
-	if (!section || sect_type != ICE_SID_FLD_VEC_SW)
-		return NULL;
-	if (index >= le16_to_cpu(fv_section->count))
-		return NULL;
-	if (offset)
-		/* "index" passed in to this function is relative to a given
-		 * 4k block. To get to the true index into the field vector
-		 * table need to add the relative index to the base_offset
-		 * field of this section
-		 */
-		*offset = le16_to_cpu(fv_section->base_offset) + index;
-	return fv_section->fv + index;
-}
-
-/**
- * ice_get_prof_index_max - get the max profile index for used profile
- * @hw: pointer to the HW struct
- *
- * Calling this function will get the max profile index for used profile
- * and store the index number in struct ice_switch_info *switch_info
- * in HW for following use.
- */
-static int ice_get_prof_index_max(struct ice_hw *hw)
-{
-	u16 prof_index = 0, j, max_prof_index = 0;
-	struct ice_pkg_enum state;
-	struct ice_seg *ice_seg;
-	bool flag = false;
-	struct ice_fv *fv;
-	u32 offset;
-
-	memset(&state, 0, sizeof(state));
-
-	if (!hw->seg)
-		return -EINVAL;
-
-	ice_seg = hw->seg;
-
-	do {
-		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
-					&offset, ice_sw_fv_handler);
-		if (!fv)
-			break;
-		ice_seg = NULL;
-
-		/* in the profile that not be used, the prot_id is set to 0xff
-		 * and the off is set to 0x1ff for all the field vectors.
-		 */
-		for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++)
-			if (fv->ew[j].prot_id != ICE_PROT_INVALID ||
-			    fv->ew[j].off != ICE_FV_OFFSET_INVAL)
-				flag = true;
-		if (flag && prof_index > max_prof_index)
-			max_prof_index = prof_index;
-
-		prof_index++;
-		flag = false;
-	} while (fv);
-
-	hw->switch_info->max_used_prof_index = max_prof_index;
-
-	return 0;
-}
-
-/**
- * ice_get_ddp_pkg_state - get DDP pkg state after download
- * @hw: pointer to the HW struct
- * @already_loaded: indicates if pkg was already loaded onto the device
- */
-static enum ice_ddp_state
-ice_get_ddp_pkg_state(struct ice_hw *hw, bool already_loaded)
-{
-	if (hw->pkg_ver.major == hw->active_pkg_ver.major &&
-	    hw->pkg_ver.minor == hw->active_pkg_ver.minor &&
-	    hw->pkg_ver.update == hw->active_pkg_ver.update &&
-	    hw->pkg_ver.draft == hw->active_pkg_ver.draft &&
-	    !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) {
-		if (already_loaded)
-			return ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED;
-		else
-			return ICE_DDP_PKG_SUCCESS;
-	} else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ ||
-		   hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) {
-		return ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED;
-	} else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
-		   hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) {
-		return ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED;
-	} else {
-		return ICE_DDP_PKG_ERR;
-	}
-}
-
-/**
- * ice_init_pkg - initialize/download package
- * @hw: pointer to the hardware structure
- * @buf: pointer to the package buffer
- * @len: size of the package buffer
- *
- * This function initializes a package. The package contains HW tables
- * required to do packet processing. First, the function extracts package
- * information such as version. Then it finds the ice configuration segment
- * within the package; this function then saves a copy of the segment pointer
- * within the supplied package buffer. Next, the function will cache any hints
- * from the package, followed by downloading the package itself. Note, that if
- * a previous PF driver has already downloaded the package successfully, then
- * the current driver will not have to download the package again.
- *
- * The local package contents will be used to query default behavior and to
- * update specific sections of the HW's version of the package (e.g. to update
- * the parse graph to understand new protocols).
- *
- * This function stores a pointer to the package buffer memory, and it is
- * expected that the supplied buffer will not be freed immediately. If the
- * package buffer needs to be freed, such as when read from a file, use
- * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this
- * case.
- */
-enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
-{
-	bool already_loaded = false;
-	enum ice_ddp_state state;
-	struct ice_pkg_hdr *pkg;
-	struct ice_seg *seg;
-
-	if (!buf || !len)
-		return ICE_DDP_PKG_ERR;
-
-	pkg = (struct ice_pkg_hdr *)buf;
-	state = ice_verify_pkg(pkg, len);
-	if (state) {
-		ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n",
-			  state);
-		return state;
-	}
-
-	/* initialize package info */
-	state = ice_init_pkg_info(hw, pkg);
-	if (state)
-		return state;
-
-	/* before downloading the package, check package version for
-	 * compatibility with driver
-	 */
-	state = ice_chk_pkg_compat(hw, pkg, &seg);
-	if (state)
-		return state;
-
-	/* initialize package hints and then download package */
-	ice_init_pkg_hints(hw, seg);
-	state = ice_download_pkg(hw, seg);
-	if (state == ICE_DDP_PKG_ALREADY_LOADED) {
-		ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n");
-		already_loaded = true;
-	}
-
-	/* Get information on the package currently loaded in HW, then make sure
-	 * the driver is compatible with this version.
-	 */
-	if (!state || state == ICE_DDP_PKG_ALREADY_LOADED) {
-		state = ice_get_pkg_info(hw);
-		if (!state)
-			state = ice_get_ddp_pkg_state(hw, already_loaded);
-	}
-
-	if (ice_is_init_pkg_successful(state)) {
-		hw->seg = seg;
-		/* on successful package download update other required
-		 * registers to support the package and fill HW tables
-		 * with package content.
-		 */
-		ice_init_pkg_regs(hw);
-		ice_fill_blk_tbls(hw);
-		ice_fill_hw_ptype(hw);
-		ice_get_prof_index_max(hw);
-	} else {
-		ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n",
-			  state);
-	}
-
-	return state;
-}
-
-/**
- * ice_copy_and_init_pkg - initialize/download a copy of the package
- * @hw: pointer to the hardware structure
- * @buf: pointer to the package buffer
- * @len: size of the package buffer
- *
- * This function copies the package buffer, and then calls ice_init_pkg() to
- * initialize the copied package contents.
- *
- * The copying is necessary if the package buffer supplied is constant, or if
- * the memory may disappear shortly after calling this function.
- *
- * If the package buffer resides in the data segment and can be modified, the
- * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg().
- *
- * However, if the package buffer needs to be copied first, such as when being
- * read from a file, the caller should use ice_copy_and_init_pkg().
- *
- * This function will first copy the package buffer, before calling
- * ice_init_pkg(). The caller is free to immediately destroy the original
- * package buffer, as the new copy will be managed by this function and
- * related routines.
- */
-enum ice_ddp_state
-ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len)
-{
-	enum ice_ddp_state state;
-	u8 *buf_copy;
-
-	if (!buf || !len)
-		return ICE_DDP_PKG_ERR;
-
-	buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL);
-
-	state = ice_init_pkg(hw, buf_copy, len);
-	if (!ice_is_init_pkg_successful(state)) {
-		/* Free the copy, since we failed to initialize the package */
-		devm_kfree(ice_hw_to_dev(hw), buf_copy);
-	} else {
-		/* Track the copied pkg so we can free it later */
-		hw->pkg_copy = buf_copy;
-		hw->pkg_size = len;
-	}
-
-	return state;
-}
-
-/**
- * ice_is_init_pkg_successful - check if DDP init was successful
- * @state: state of the DDP pkg after download
- */
-bool ice_is_init_pkg_successful(enum ice_ddp_state state)
-{
-	switch (state) {
-	case ICE_DDP_PKG_SUCCESS:
-	case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED:
-	case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED:
-		return true;
-	default:
-		return false;
-	}
-}
-
-/**
- * ice_pkg_buf_alloc
- * @hw: pointer to the HW structure
- *
- * Allocates a package buffer and returns a pointer to the buffer header.
- * Note: all package contents must be in Little Endian form.
- */
-static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw)
-{
-	struct ice_buf_build *bld;
-	struct ice_buf_hdr *buf;
-
-	bld = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*bld), GFP_KERNEL);
-	if (!bld)
-		return NULL;
-
-	buf = (struct ice_buf_hdr *)bld;
-	buf->data_end = cpu_to_le16(offsetof(struct ice_buf_hdr,
-					     section_entry));
-	return bld;
-}
-
-static bool ice_is_gtp_u_profile(u16 prof_idx)
-{
-	return (prof_idx >= ICE_PROFID_IPV6_GTPU_TEID &&
-		prof_idx <= ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER) ||
-	       prof_idx == ICE_PROFID_IPV4_GTPU_TEID;
-}
-
-static bool ice_is_gtp_c_profile(u16 prof_idx)
-{
-	switch (prof_idx) {
-	case ICE_PROFID_IPV4_GTPC_TEID:
-	case ICE_PROFID_IPV4_GTPC_NO_TEID:
-	case ICE_PROFID_IPV6_GTPC_TEID:
-	case ICE_PROFID_IPV6_GTPC_NO_TEID:
-		return true;
-	default:
-		return false;
-	}
-}
-
-/**
- * ice_get_sw_prof_type - determine switch profile type
- * @hw: pointer to the HW structure
- * @fv: pointer to the switch field vector
- * @prof_idx: profile index to check
- */
-static enum ice_prof_type
-ice_get_sw_prof_type(struct ice_hw *hw, struct ice_fv *fv, u32 prof_idx)
-{
-	u16 i;
-
-	if (ice_is_gtp_c_profile(prof_idx))
-		return ICE_PROF_TUN_GTPC;
-
-	if (ice_is_gtp_u_profile(prof_idx))
-		return ICE_PROF_TUN_GTPU;
-
-	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 &&
-		    fv->ew[i].off == ICE_VNI_OFFSET)
-			return ICE_PROF_TUN_UDP;
-
-		/* GRE tunnel will have GRE protocol */
-		if (fv->ew[i].prot_id == (u8)ICE_PROT_GRE_OF)
-			return ICE_PROF_TUN_GRE;
-	}
-
-	return ICE_PROF_NON_TUN;
-}
-
-/**
- * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type
- * @hw: pointer to hardware structure
- * @req_profs: type of profiles requested
- * @bm: pointer to memory for returning the bitmap of field vectors
- */
-void
-ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs,
-		     unsigned long *bm)
-{
-	struct ice_pkg_enum state;
-	struct ice_seg *ice_seg;
-	struct ice_fv *fv;
-
-	if (req_profs == ICE_PROF_ALL) {
-		bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES);
-		return;
-	}
-
-	memset(&state, 0, sizeof(state));
-	bitmap_zero(bm, ICE_MAX_NUM_PROFILES);
-	ice_seg = hw->seg;
-	do {
-		enum ice_prof_type prof_type;
-		u32 offset;
-
-		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
-					&offset, ice_sw_fv_handler);
-		ice_seg = NULL;
-
-		if (fv) {
-			/* Determine field vector type */
-			prof_type = ice_get_sw_prof_type(hw, fv, offset);
-
-			if (req_profs & prof_type)
-				set_bit((u16)offset, bm);
-		}
-	} while (fv);
-}
-
-/**
- * ice_get_sw_fv_list
- * @hw: pointer to the HW structure
- * @lkups: list of protocol types
- * @bm: bitmap of field vectors to consider
- * @fv_list: Head of a list
- *
- * Finds all the field vector entries from switch block that contain
- * a given protocol ID and offset and returns a list of structures of type
- * "ice_sw_fv_list_entry". Every structure in the list has a field vector
- * definition and profile ID information
- * NOTE: The caller of the function is responsible for freeing the memory
- * allocated for every list entry.
- */
-int
-ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups,
-		   unsigned long *bm, struct list_head *fv_list)
-{
-	struct ice_sw_fv_list_entry *fvl;
-	struct ice_sw_fv_list_entry *tmp;
-	struct ice_pkg_enum state;
-	struct ice_seg *ice_seg;
-	struct ice_fv *fv;
-	u32 offset;
-
-	memset(&state, 0, sizeof(state));
-
-	if (!lkups->n_val_words || !hw->seg)
-		return -EINVAL;
-
-	ice_seg = hw->seg;
-	do {
-		u16 i;
-
-		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
-					&offset, ice_sw_fv_handler);
-		if (!fv)
-			break;
-		ice_seg = NULL;
-
-		/* If field vector is not in the bitmap list, then skip this
-		 * profile.
-		 */
-		if (!test_bit((u16)offset, bm))
-			continue;
-
-		for (i = 0; i < lkups->n_val_words; i++) {
-			int j;
-
-			for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++)
-				if (fv->ew[j].prot_id ==
-				    lkups->fv_words[i].prot_id &&
-				    fv->ew[j].off == lkups->fv_words[i].off)
-					break;
-			if (j >= hw->blk[ICE_BLK_SW].es.fvw)
-				break;
-			if (i + 1 == lkups->n_val_words) {
-				fvl = devm_kzalloc(ice_hw_to_dev(hw),
-						   sizeof(*fvl), GFP_KERNEL);
-				if (!fvl)
-					goto err;
-				fvl->fv_ptr = fv;
-				fvl->profile_id = offset;
-				list_add(&fvl->list_entry, fv_list);
-				break;
-			}
-		}
-	} while (fv);
-	if (list_empty(fv_list)) {
-		dev_warn(ice_hw_to_dev(hw), "Required profiles not found in currently loaded DDP package");
-		return -EIO;
-	}
-
-	return 0;
-
-err:
-	list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) {
-		list_del(&fvl->list_entry);
-		devm_kfree(ice_hw_to_dev(hw), fvl);
-	}
-
-	return -ENOMEM;
-}
-
-/**
- * ice_init_prof_result_bm - Initialize the profile result index bitmap
- * @hw: pointer to hardware structure
- */
-void ice_init_prof_result_bm(struct ice_hw *hw)
-{
-	struct ice_pkg_enum state;
-	struct ice_seg *ice_seg;
-	struct ice_fv *fv;
-
-	memset(&state, 0, sizeof(state));
-
-	if (!hw->seg)
-		return;
-
-	ice_seg = hw->seg;
-	do {
-		u32 off;
-		u16 i;
-
-		fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW,
-					&off, ice_sw_fv_handler);
-		ice_seg = NULL;
-		if (!fv)
-			break;
-
-		bitmap_zero(hw->switch_info->prof_res_bm[off],
-			    ICE_MAX_FV_WORDS);
-
-		/* Determine empty field vector indices, these can be
-		 * used for recipe results. Skip index 0, since it is
-		 * always used for Switch ID.
-		 */
-		for (i = 1; i < ICE_MAX_FV_WORDS; i++)
-			if (fv->ew[i].prot_id == ICE_PROT_INVALID &&
-			    fv->ew[i].off == ICE_FV_OFFSET_INVAL)
-				set_bit(i, hw->switch_info->prof_res_bm[off]);
-	} while (fv);
-}
-
-/**
- * ice_pkg_buf_free
- * @hw: pointer to the HW structure
- * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
- *
- * Frees a package buffer
- */
-void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld)
-{
-	devm_kfree(ice_hw_to_dev(hw), bld);
-}
-
-/**
- * ice_pkg_buf_reserve_section
- * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
- * @count: the number of sections to reserve
- *
- * Reserves one or more section table entries in a package buffer. This routine
- * can be called multiple times as long as they are made before calling
- * ice_pkg_buf_alloc_section(). Once ice_pkg_buf_alloc_section()
- * is called once, the number of sections that can be allocated will not be able
- * to be increased; not using all reserved sections is fine, but this will
- * result in some wasted space in the buffer.
- * Note: all package contents must be in Little Endian form.
- */
-static int
-ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count)
-{
-	struct ice_buf_hdr *buf;
-	u16 section_count;
-	u16 data_end;
-
-	if (!bld)
-		return -EINVAL;
-
-	buf = (struct ice_buf_hdr *)&bld->buf;
-
-	/* already an active section, can't increase table size */
-	section_count = le16_to_cpu(buf->section_count);
-	if (section_count > 0)
-		return -EIO;
-
-	if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT)
-		return -EIO;
-	bld->reserved_section_table_entries += count;
-
-	data_end = le16_to_cpu(buf->data_end) +
-		flex_array_size(buf, section_entry, count);
-	buf->data_end = cpu_to_le16(data_end);
-
-	return 0;
-}
-
-/**
- * ice_pkg_buf_alloc_section
- * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
- * @type: the section type value
- * @size: the size of the section to reserve (in bytes)
- *
- * Reserves memory in the buffer for a section's content and updates the
- * buffers' status accordingly. This routine returns a pointer to the first
- * byte of the section start within the buffer, which is used to fill in the
- * section contents.
- * Note: all package contents must be in Little Endian form.
- */
-static void *
-ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size)
-{
-	struct ice_buf_hdr *buf;
-	u16 sect_count;
-	u16 data_end;
-
-	if (!bld || !type || !size)
-		return NULL;
-
-	buf = (struct ice_buf_hdr *)&bld->buf;
-
-	/* check for enough space left in buffer */
-	data_end = le16_to_cpu(buf->data_end);
-
-	/* section start must align on 4 byte boundary */
-	data_end = ALIGN(data_end, 4);
-
-	if ((data_end + size) > ICE_MAX_S_DATA_END)
-		return NULL;
-
-	/* check for more available section table entries */
-	sect_count = le16_to_cpu(buf->section_count);
-	if (sect_count < bld->reserved_section_table_entries) {
-		void *section_ptr = ((u8 *)buf) + data_end;
-
-		buf->section_entry[sect_count].offset = cpu_to_le16(data_end);
-		buf->section_entry[sect_count].size = cpu_to_le16(size);
-		buf->section_entry[sect_count].type = cpu_to_le32(type);
-
-		data_end += size;
-		buf->data_end = cpu_to_le16(data_end);
-
-		buf->section_count = cpu_to_le16(sect_count + 1);
-		return section_ptr;
-	}
-
-	/* no free section table entries */
-	return NULL;
-}
-
-/**
- * ice_pkg_buf_alloc_single_section
- * @hw: pointer to the HW structure
- * @type: the section type value
- * @size: the size of the section to reserve (in bytes)
- * @section: returns pointer to the section
- *
- * Allocates a package buffer with a single section.
- * Note: all package contents must be in Little Endian form.
- */
-struct ice_buf_build *
-ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size,
-				 void **section)
-{
-	struct ice_buf_build *buf;
-
-	if (!section)
-		return NULL;
-
-	buf = ice_pkg_buf_alloc(hw);
-	if (!buf)
-		return NULL;
-
-	if (ice_pkg_buf_reserve_section(buf, 1))
-		goto ice_pkg_buf_alloc_single_section_err;
-
-	*section = ice_pkg_buf_alloc_section(buf, type, size);
-	if (!*section)
-		goto ice_pkg_buf_alloc_single_section_err;
-
-	return buf;
-
-ice_pkg_buf_alloc_single_section_err:
-	ice_pkg_buf_free(hw, buf);
-	return NULL;
-}
-
-/**
- * ice_pkg_buf_get_active_sections
- * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
- *
- * Returns the number of active sections. Before using the package buffer
- * in an update package command, the caller should make sure that there is at
- * least one active section - otherwise, the buffer is not legal and should
- * not be used.
- * Note: all package contents must be in Little Endian form.
- */
-static u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld)
-{
-	struct ice_buf_hdr *buf;
-
-	if (!bld)
-		return 0;
-
-	buf = (struct ice_buf_hdr *)&bld->buf;
-	return le16_to_cpu(buf->section_count);
-}
-
-/**
- * ice_pkg_buf
- * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc())
- *
- * Return a pointer to the buffer's header
- */
-struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
-{
-	if (!bld)
-		return NULL;
-
-	return &bld->buf;
-}
-
-/**
  * ice_get_open_tunnel_port - retrieve an open tunnel port
  * @hw: pointer to the HW structure
  * @port: returns open port
@@ -2297,10 +391,11 @@ ice_upd_dvm_boost_entry_err:
  */
 int ice_set_dvm_boost_entries(struct ice_hw *hw)
 {
-	int status;
 	u16 i;
 
 	for (i = 0; i < hw->dvm_upd.count; i++) {
+		int status;
+
 		status = ice_upd_dvm_boost_entry(hw, &hw->dvm_upd.tbl[i]);
 		if (status)
 			return status;
@@ -2757,7 +852,6 @@ ice_match_prop_lst(struct list_head *list1, struct list_head *list2)
 		count++;
 	list_for_each_entry(tmp2, list2, list)
 		chk_count++;
-	/* cppcheck-suppress knownConditionTrueFalse */
 	if (!count || count != chk_count)
 		return false;
 
@@ -5102,12 +3196,13 @@ ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig,
 	u16 idx = vsig & ICE_VSIG_IDX_M;
 	struct ice_vsig_vsi *vsi_cur;
 	struct ice_vsig_prof *d, *t;
-	int status;
 
 	/* remove TCAM entries */
 	list_for_each_entry_safe(d, t,
 				 &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
 				 list) {
+		int status;
+
 		status = ice_rem_prof_id(hw, blk, d);
 		if (status)
 			return status;
@@ -5158,12 +3253,13 @@ ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl,
 {
 	u16 idx = vsig & ICE_VSIG_IDX_M;
 	struct ice_vsig_prof *p, *t;
-	int status;
 
 	list_for_each_entry_safe(p, t,
 				 &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst,
 				 list)
 		if (p->profile_cookie == hdl) {
+			int status;
+
 			if (ice_vsig_prof_id_count(hw, blk, vsig) == 1)
 				/* this is the last profile, remove the VSIG */
 				return ice_rem_vsig(hw, blk, vsig, chg);
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 9c530c86703e..7af7c8e9aa4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -6,75 +6,6 @@
 
 #include "ice_type.h"
 
-/* Package minimal version supported */
-#define ICE_PKG_SUPP_VER_MAJ	1
-#define ICE_PKG_SUPP_VER_MNR	3
-
-/* Package format version */
-#define ICE_PKG_FMT_VER_MAJ	1
-#define ICE_PKG_FMT_VER_MNR	0
-#define ICE_PKG_FMT_VER_UPD	0
-#define ICE_PKG_FMT_VER_DFT	0
-
-#define ICE_PKG_CNT 4
-
-enum ice_ddp_state {
-	/* Indicates that this call to ice_init_pkg
-	 * successfully loaded the requested DDP package
-	 */
-	ICE_DDP_PKG_SUCCESS			= 0,
-
-	/* Generic error for already loaded errors, it is mapped later to
-	 * the more specific one (one of the next 3)
-	 */
-	ICE_DDP_PKG_ALREADY_LOADED			= -1,
-
-	/* Indicates that a DDP package of the same version has already been
-	 * loaded onto the device by a previous call or by another PF
-	 */
-	ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED		= -2,
-
-	/* The device has a DDP package that is not supported by the driver */
-	ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED	= -3,
-
-	/* The device has a compatible package
-	 * (but different from the request) already loaded
-	 */
-	ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED		= -4,
-
-	/* The firmware loaded on the device is not compatible with
-	 * the DDP package loaded
-	 */
-	ICE_DDP_PKG_FW_MISMATCH				= -5,
-
-	/* The DDP package file is invalid */
-	ICE_DDP_PKG_INVALID_FILE			= -6,
-
-	/* The version of the DDP package provided is higher than
-	 * the driver supports
-	 */
-	ICE_DDP_PKG_FILE_VERSION_TOO_HIGH		= -7,
-
-	/* The version of the DDP package provided is lower than the
-	 * driver supports
-	 */
-	ICE_DDP_PKG_FILE_VERSION_TOO_LOW		= -8,
-
-	/* The signature of the DDP package file provided is invalid */
-	ICE_DDP_PKG_FILE_SIGNATURE_INVALID		= -9,
-
-	/* The DDP package file security revision is too low and not
-	 * supported by firmware
-	 */
-	ICE_DDP_PKG_FILE_REVISION_TOO_LOW		= -10,
-
-	/* An error occurred in firmware while loading the DDP package */
-	ICE_DDP_PKG_LOAD_ERROR				= -11,
-
-	/* Other errors */
-	ICE_DDP_PKG_ERR					= -12
-};
-
 int
 ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access);
 void ice_release_change_lock(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 974d14a83b2e..4f42e14ed3ae 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -3,205 +3,7 @@
 
 #ifndef _ICE_FLEX_TYPE_H_
 #define _ICE_FLEX_TYPE_H_
-
-#define ICE_FV_OFFSET_INVAL	0x1FF
-
-/* Extraction Sequence (Field Vector) Table */
-struct ice_fv_word {
-	u8 prot_id;
-	u16 off;		/* Offset within the protocol header */
-	u8 resvrd;
-} __packed;
-
-#define ICE_MAX_NUM_PROFILES 256
-
-#define ICE_MAX_FV_WORDS 48
-struct ice_fv {
-	struct ice_fv_word ew[ICE_MAX_FV_WORDS];
-};
-
-/* Package and segment headers and tables */
-struct ice_pkg_hdr {
-	struct ice_pkg_ver pkg_format_ver;
-	__le32 seg_count;
-	__le32 seg_offset[];
-};
-
-/* generic segment */
-struct ice_generic_seg_hdr {
-#define SEGMENT_TYPE_METADATA	0x00000001
-#define SEGMENT_TYPE_ICE	0x00000010
-	__le32 seg_type;
-	struct ice_pkg_ver seg_format_ver;
-	__le32 seg_size;
-	char seg_id[ICE_PKG_NAME_SIZE];
-};
-
-/* ice specific segment */
-
-union ice_device_id {
-	struct {
-		__le16 device_id;
-		__le16 vendor_id;
-	} dev_vend_id;
-	__le32 id;
-};
-
-struct ice_device_id_entry {
-	union ice_device_id device;
-	union ice_device_id sub_device;
-};
-
-struct ice_seg {
-	struct ice_generic_seg_hdr hdr;
-	__le32 device_table_count;
-	struct ice_device_id_entry device_table[];
-};
-
-struct ice_nvm_table {
-	__le32 table_count;
-	__le32 vers[];
-};
-
-struct ice_buf {
-#define ICE_PKG_BUF_SIZE	4096
-	u8 buf[ICE_PKG_BUF_SIZE];
-};
-
-struct ice_buf_table {
-	__le32 buf_count;
-	struct ice_buf buf_array[];
-};
-
-/* global metadata specific segment */
-struct ice_global_metadata_seg {
-	struct ice_generic_seg_hdr hdr;
-	struct ice_pkg_ver pkg_ver;
-	__le32 rsvd;
-	char pkg_name[ICE_PKG_NAME_SIZE];
-};
-
-#define ICE_MIN_S_OFF		12
-#define ICE_MAX_S_OFF		4095
-#define ICE_MIN_S_SZ		1
-#define ICE_MAX_S_SZ		4084
-
-/* section information */
-struct ice_section_entry {
-	__le32 type;
-	__le16 offset;
-	__le16 size;
-};
-
-#define ICE_MIN_S_COUNT		1
-#define ICE_MAX_S_COUNT		511
-#define ICE_MIN_S_DATA_END	12
-#define ICE_MAX_S_DATA_END	4096
-
-#define ICE_METADATA_BUF	0x80000000
-
-struct ice_buf_hdr {
-	__le16 section_count;
-	__le16 data_end;
-	struct ice_section_entry section_entry[];
-};
-
-#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz) ((ICE_PKG_BUF_SIZE - \
-	struct_size((struct ice_buf_hdr *)0, section_entry, 1) - (hd_sz)) /\
-	(ent_sz))
-
-/* ice package section IDs */
-#define ICE_SID_METADATA		1
-#define ICE_SID_XLT0_SW			10
-#define ICE_SID_XLT_KEY_BUILDER_SW	11
-#define ICE_SID_XLT1_SW			12
-#define ICE_SID_XLT2_SW			13
-#define ICE_SID_PROFID_TCAM_SW		14
-#define ICE_SID_PROFID_REDIR_SW		15
-#define ICE_SID_FLD_VEC_SW		16
-#define ICE_SID_CDID_KEY_BUILDER_SW	17
-
-struct ice_meta_sect {
-	struct ice_pkg_ver ver;
-#define ICE_META_SECT_NAME_SIZE	28
-	char name[ICE_META_SECT_NAME_SIZE];
-	__le32 track_id;
-};
-
-#define ICE_SID_CDID_REDIR_SW		18
-
-#define ICE_SID_XLT0_ACL		20
-#define ICE_SID_XLT_KEY_BUILDER_ACL	21
-#define ICE_SID_XLT1_ACL		22
-#define ICE_SID_XLT2_ACL		23
-#define ICE_SID_PROFID_TCAM_ACL		24
-#define ICE_SID_PROFID_REDIR_ACL	25
-#define ICE_SID_FLD_VEC_ACL		26
-#define ICE_SID_CDID_KEY_BUILDER_ACL	27
-#define ICE_SID_CDID_REDIR_ACL		28
-
-#define ICE_SID_XLT0_FD			30
-#define ICE_SID_XLT_KEY_BUILDER_FD	31
-#define ICE_SID_XLT1_FD			32
-#define ICE_SID_XLT2_FD			33
-#define ICE_SID_PROFID_TCAM_FD		34
-#define ICE_SID_PROFID_REDIR_FD		35
-#define ICE_SID_FLD_VEC_FD		36
-#define ICE_SID_CDID_KEY_BUILDER_FD	37
-#define ICE_SID_CDID_REDIR_FD		38
-
-#define ICE_SID_XLT0_RSS		40
-#define ICE_SID_XLT_KEY_BUILDER_RSS	41
-#define ICE_SID_XLT1_RSS		42
-#define ICE_SID_XLT2_RSS		43
-#define ICE_SID_PROFID_TCAM_RSS		44
-#define ICE_SID_PROFID_REDIR_RSS	45
-#define ICE_SID_FLD_VEC_RSS		46
-#define ICE_SID_CDID_KEY_BUILDER_RSS	47
-#define ICE_SID_CDID_REDIR_RSS		48
-
-#define ICE_SID_RXPARSER_MARKER_PTYPE	55
-#define ICE_SID_RXPARSER_BOOST_TCAM	56
-#define ICE_SID_RXPARSER_METADATA_INIT	58
-#define ICE_SID_TXPARSER_BOOST_TCAM	66
-
-#define ICE_SID_XLT0_PE			80
-#define ICE_SID_XLT_KEY_BUILDER_PE	81
-#define ICE_SID_XLT1_PE			82
-#define ICE_SID_XLT2_PE			83
-#define ICE_SID_PROFID_TCAM_PE		84
-#define ICE_SID_PROFID_REDIR_PE		85
-#define ICE_SID_FLD_VEC_PE		86
-#define ICE_SID_CDID_KEY_BUILDER_PE	87
-#define ICE_SID_CDID_REDIR_PE		88
-
-/* Label Metadata section IDs */
-#define ICE_SID_LBL_FIRST		0x80000010
-#define ICE_SID_LBL_RXPARSER_TMEM	0x80000018
-/* The following define MUST be updated to reflect the last label section ID */
-#define ICE_SID_LBL_LAST		0x80000038
-
-enum ice_block {
-	ICE_BLK_SW = 0,
-	ICE_BLK_ACL,
-	ICE_BLK_FD,
-	ICE_BLK_RSS,
-	ICE_BLK_PE,
-	ICE_BLK_COUNT
-};
-
-enum ice_sect {
-	ICE_XLT0 = 0,
-	ICE_XLT_KB,
-	ICE_XLT1,
-	ICE_XLT2,
-	ICE_PROF_TCAM,
-	ICE_PROF_REDIR,
-	ICE_VEC_TBL,
-	ICE_CDID_KB,
-	ICE_CDID_REDIR,
-	ICE_SECT_COUNT
-};
+#include "ice_ddp.h"
 
 /* Packet Type (PTYPE) values */
 #define ICE_PTYPE_MAC_PAY		1
@@ -283,134 +85,6 @@ struct ice_ptype_attributes {
 	enum ice_ptype_attrib_type attrib;
 };
 
-/* package labels */
-struct ice_label {
-	__le16 value;
-#define ICE_PKG_LABEL_SIZE	64
-	char name[ICE_PKG_LABEL_SIZE];
-};
-
-struct ice_label_section {
-	__le16 count;
-	struct ice_label label[];
-};
-
-#define ICE_MAX_LABELS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \
-	struct_size((struct ice_label_section *)0, label, 1) - \
-	sizeof(struct ice_label), sizeof(struct ice_label))
-
-struct ice_sw_fv_section {
-	__le16 count;
-	__le16 base_offset;
-	struct ice_fv fv[];
-};
-
-struct ice_sw_fv_list_entry {
-	struct list_head list_entry;
-	u32 profile_id;
-	struct ice_fv *fv_ptr;
-};
-
-/* The BOOST TCAM stores the match packet header in reverse order, meaning
- * the fields are reversed; in addition, this means that the normally big endian
- * fields of the packet are now little endian.
- */
-struct ice_boost_key_value {
-#define ICE_BOOST_REMAINING_HV_KEY	15
-	u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY];
-	__le16 hv_dst_port_key;
-	__le16 hv_src_port_key;
-	u8 tcam_search_key;
-} __packed;
-
-struct ice_boost_key {
-	struct ice_boost_key_value key;
-	struct ice_boost_key_value key2;
-};
-
-/* package Boost TCAM entry */
-struct ice_boost_tcam_entry {
-	__le16 addr;
-	__le16 reserved;
-	/* break up the 40 bytes of key into different fields */
-	struct ice_boost_key key;
-	u8 boost_hit_index_group;
-	/* The following contains bitfields which are not on byte boundaries.
-	 * These fields are currently unused by driver software.
-	 */
-#define ICE_BOOST_BIT_FIELDS		43
-	u8 bit_fields[ICE_BOOST_BIT_FIELDS];
-};
-
-struct ice_boost_tcam_section {
-	__le16 count;
-	__le16 reserved;
-	struct ice_boost_tcam_entry tcam[];
-};
-
-#define ICE_MAX_BST_TCAMS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \
-	struct_size((struct ice_boost_tcam_section *)0, tcam, 1) - \
-	sizeof(struct ice_boost_tcam_entry), \
-	sizeof(struct ice_boost_tcam_entry))
-
-/* package Marker Ptype TCAM entry */
-struct ice_marker_ptype_tcam_entry {
-#define ICE_MARKER_PTYPE_TCAM_ADDR_MAX	1024
-	__le16 addr;
-	__le16 ptype;
-	u8 keys[20];
-};
-
-struct ice_marker_ptype_tcam_section {
-	__le16 count;
-	__le16 reserved;
-	struct ice_marker_ptype_tcam_entry tcam[];
-};
-
-#define ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF	\
-	ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_marker_ptype_tcam_section *)0, tcam, 1) - \
-	sizeof(struct ice_marker_ptype_tcam_entry), \
-	sizeof(struct ice_marker_ptype_tcam_entry))
-
-struct ice_xlt1_section {
-	__le16 count;
-	__le16 offset;
-	u8 value[];
-};
-
-struct ice_xlt2_section {
-	__le16 count;
-	__le16 offset;
-	__le16 value[];
-};
-
-struct ice_prof_redir_section {
-	__le16 count;
-	__le16 offset;
-	u8 redir_value[];
-};
-
-/* package buffer building */
-
-struct ice_buf_build {
-	struct ice_buf buf;
-	u16 reserved_section_table_entries;
-};
-
-struct ice_pkg_enum {
-	struct ice_buf_table *buf_table;
-	u32 buf_idx;
-
-	u32 type;
-	struct ice_buf_hdr *buf;
-	u32 sect_idx;
-	void *sect;
-	u32 sect_type;
-
-	u32 entry_idx;
-	void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
-};
-
 /* Tunnel enabling */
 
 enum ice_tunnel_type {
diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c
index 40e678cfb507..aff7a141c30d 100644
--- a/drivers/net/ethernet/intel/ice/ice_fltr.c
+++ b/drivers/net/ethernet/intel/ice/ice_fltr.c
@@ -208,6 +208,11 @@ static int ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list)
 void ice_fltr_remove_all(struct ice_vsi *vsi)
 {
 	ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx);
+	/* sync netdev filters if exist */
+	if (vsi->netdev) {
+		__dev_uc_unsync(vsi->netdev, NULL);
+		__dev_mc_unsync(vsi->netdev, NULL);
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index 43e199b5b513..8dec748bb53a 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -3,15 +3,18 @@
 
 #include "ice.h"
 #include "ice_lib.h"
-#include <linux/tty_driver.h>
 
 /**
- * ice_gnss_do_write - Write data to internal GNSS
+ * ice_gnss_do_write - Write data to internal GNSS receiver
  * @pf: board private structure
  * @buf: command buffer
  * @size: command buffer size
  *
  * Write UBX command data to the GNSS receiver
+ *
+ * Return:
+ * * number of bytes written - success
+ * * negative - error code
  */
 static unsigned int
 ice_gnss_do_write(struct ice_pf *pf, unsigned char *buf, unsigned int size)
@@ -82,6 +85,12 @@ static void ice_gnss_write_pending(struct kthread_work *work)
 						write_work);
 	struct ice_pf *pf = gnss->back;
 
+	if (!pf)
+		return;
+
+	if (!test_bit(ICE_FLAG_GNSS, pf->flags))
+		return;
+
 	if (!list_empty(&gnss->queue)) {
 		struct gnss_write_buf *write_buf = NULL;
 		unsigned int bytes;
@@ -102,16 +111,14 @@ static void ice_gnss_write_pending(struct kthread_work *work)
  * ice_gnss_read - Read data from internal GNSS module
  * @work: GNSS read work structure
  *
- * Read the data from internal GNSS receiver, number of bytes read will be
- * returned in *read_data parameter.
+ * Read the data from internal GNSS receiver, write it to gnss_dev.
  */
 static void ice_gnss_read(struct kthread_work *work)
 {
 	struct gnss_serial *gnss = container_of(work, struct gnss_serial,
 						read_work.work);
+	unsigned int i, bytes_read, data_len, count;
 	struct ice_aqc_link_topo_addr link_topo;
-	unsigned int i, bytes_read, data_len;
-	struct tty_port *port;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	__be16 data_len_b;
@@ -120,14 +127,15 @@ static void ice_gnss_read(struct kthread_work *work)
 	int err = 0;
 
 	pf = gnss->back;
-	if (!pf || !gnss->tty || !gnss->tty->port) {
+	if (!pf) {
 		err = -EFAULT;
 		goto exit;
 	}
 
-	hw = &pf->hw;
-	port = gnss->tty->port;
+	if (!test_bit(ICE_FLAG_GNSS, pf->flags))
+		return;
 
+	hw = &pf->hw;
 	buf = (char *)get_zeroed_page(GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
@@ -159,7 +167,6 @@ static void ice_gnss_read(struct kthread_work *work)
 	}
 
 	data_len = min_t(typeof(data_len), data_len, PAGE_SIZE);
-	data_len = tty_buffer_request_room(port, data_len);
 	if (!data_len) {
 		err = -ENOMEM;
 		goto exit_buf;
@@ -179,12 +186,11 @@ static void ice_gnss_read(struct kthread_work *work)
 			goto exit_buf;
 	}
 
-	/* Send the data to the tty layer for users to read. This doesn't
-	 * actually push the data through unless tty->low_latency is set.
-	 */
-	tty_insert_flip_string(port, buf, i);
-	tty_flip_buffer_push(port);
-
+	count = gnss_insert_raw(pf->gnss_dev, buf, i);
+	if (count != i)
+		dev_warn(ice_pf_to_dev(pf),
+			 "gnss_insert_raw ret=%d size=%d\n",
+			 count, i);
 exit_buf:
 	free_page((unsigned long)buf);
 	kthread_queue_delayed_work(gnss->kworker, &gnss->read_work,
@@ -195,11 +201,16 @@ exit:
 }
 
 /**
- * ice_gnss_struct_init - Initialize GNSS structure for the TTY
+ * ice_gnss_struct_init - Initialize GNSS receiver
  * @pf: Board private structure
- * @index: TTY device index
+ *
+ * Initialize GNSS structures and workers.
+ *
+ * Return:
+ * * pointer to initialized gnss_serial struct - success
+ * * NULL - error
  */
-static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index)
+static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct kthread_worker *kworker;
@@ -209,17 +220,12 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index)
 	if (!gnss)
 		return NULL;
 
-	mutex_init(&gnss->gnss_mutex);
-	gnss->open_count = 0;
 	gnss->back = pf;
-	pf->gnss_serial[index] = gnss;
+	pf->gnss_serial = gnss;
 
 	kthread_init_delayed_work(&gnss->read_work, ice_gnss_read);
 	INIT_LIST_HEAD(&gnss->queue);
 	kthread_init_work(&gnss->write_work, ice_gnss_write_pending);
-	/* Allocate a kworker for handling work required for the GNSS TTY
-	 * writes.
-	 */
 	kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev));
 	if (IS_ERR(kworker)) {
 		kfree(gnss);
@@ -232,140 +238,100 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index)
 }
 
 /**
- * ice_gnss_tty_open - Initialize GNSS structures on TTY device open
- * @tty: pointer to the tty_struct
- * @filp: pointer to the file
+ * ice_gnss_open - Open GNSS device
+ * @gdev: pointer to the gnss device struct
+ *
+ * Open GNSS device and start filling the read buffer for consumer.
  *
- * This routine is mandatory. If this routine is not filled in, the attempted
- * open will fail with ENODEV.
+ * Return:
+ * * 0 - success
+ * * negative - error code
  */
-static int ice_gnss_tty_open(struct tty_struct *tty, struct file *filp)
+static int ice_gnss_open(struct gnss_device *gdev)
 {
+	struct ice_pf *pf = gnss_get_drvdata(gdev);
 	struct gnss_serial *gnss;
-	struct ice_pf *pf;
 
-	pf = (struct ice_pf *)tty->driver->driver_state;
 	if (!pf)
 		return -EFAULT;
 
-	/* Clear the pointer in case something fails */
-	tty->driver_data = NULL;
-
-	/* Get the serial object associated with this tty pointer */
-	gnss = pf->gnss_serial[tty->index];
-	if (!gnss) {
-		/* Initialize GNSS struct on the first device open */
-		gnss = ice_gnss_struct_init(pf, tty->index);
-		if (!gnss)
-			return -ENOMEM;
-	}
+	if (!test_bit(ICE_FLAG_GNSS, pf->flags))
+		return -EFAULT;
 
-	mutex_lock(&gnss->gnss_mutex);
+	gnss = pf->gnss_serial;
+	if (!gnss)
+		return -ENODEV;
 
-	/* Save our structure within the tty structure */
-	tty->driver_data = gnss;
-	gnss->tty = tty;
-	gnss->open_count++;
 	kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, 0);
 
-	mutex_unlock(&gnss->gnss_mutex);
-
 	return 0;
 }
 
 /**
- * ice_gnss_tty_close - Cleanup GNSS structures on tty device close
- * @tty: pointer to the tty_struct
- * @filp: pointer to the file
+ * ice_gnss_close - Close GNSS device
+ * @gdev: pointer to the gnss device struct
+ *
+ * Close GNSS device, cancel worker, stop filling the read buffer.
  */
-static void ice_gnss_tty_close(struct tty_struct *tty, struct file *filp)
+static void ice_gnss_close(struct gnss_device *gdev)
 {
-	struct gnss_serial *gnss = tty->driver_data;
-	struct ice_pf *pf;
-
-	if (!gnss)
-		return;
+	struct ice_pf *pf = gnss_get_drvdata(gdev);
+	struct gnss_serial *gnss;
 
-	pf = (struct ice_pf *)tty->driver->driver_state;
 	if (!pf)
 		return;
 
-	mutex_lock(&gnss->gnss_mutex);
-
-	if (!gnss->open_count) {
-		/* Port was never opened */
-		dev_err(ice_pf_to_dev(pf), "GNSS port not opened\n");
-		goto exit;
-	}
+	gnss = pf->gnss_serial;
+	if (!gnss)
+		return;
 
-	gnss->open_count--;
-	if (gnss->open_count <= 0) {
-		/* Port is in shutdown state */
-		kthread_cancel_delayed_work_sync(&gnss->read_work);
-	}
-exit:
-	mutex_unlock(&gnss->gnss_mutex);
+	kthread_cancel_work_sync(&gnss->write_work);
+	kthread_cancel_delayed_work_sync(&gnss->read_work);
 }
 
 /**
- * ice_gnss_tty_write - Write GNSS data
- * @tty: pointer to the tty_struct
+ * ice_gnss_write - Write to GNSS device
+ * @gdev: pointer to the gnss device struct
  * @buf: pointer to the user data
- * @count: the number of characters queued to be sent to the HW
+ * @count: size of the buffer to be sent to the GNSS device
  *
- * The write function call is called by the user when there is data to be sent
- * to the hardware. First the tty core receives the call, and then it passes the
- * data on to the tty driver's write function. The tty core also tells the tty
- * driver the size of the data being sent.
- * If any errors happen during the write call, a negative error value should be
- * returned instead of the number of characters queued to be written.
+ * Return:
+ * * number of written bytes - success
+ * * negative - error code
  */
 static int
-ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf,
+	       size_t count)
 {
+	struct ice_pf *pf = gnss_get_drvdata(gdev);
 	struct gnss_write_buf *write_buf;
 	struct gnss_serial *gnss;
 	unsigned char *cmd_buf;
-	struct ice_pf *pf;
 	int err = count;
 
 	/* We cannot write a single byte using our I2C implementation. */
 	if (count <= 1 || count > ICE_GNSS_TTY_WRITE_BUF)
 		return -EINVAL;
 
-	gnss = tty->driver_data;
-	if (!gnss)
-		return -EFAULT;
-
-	pf = (struct ice_pf *)tty->driver->driver_state;
 	if (!pf)
 		return -EFAULT;
 
-	/* Only allow to write on TTY 0 */
-	if (gnss != pf->gnss_serial[0])
-		return -EIO;
-
-	mutex_lock(&gnss->gnss_mutex);
+	if (!test_bit(ICE_FLAG_GNSS, pf->flags))
+		return -EFAULT;
 
-	if (!gnss->open_count) {
-		err = -EINVAL;
-		goto exit;
-	}
+	gnss = pf->gnss_serial;
+	if (!gnss)
+		return -ENODEV;
 
 	cmd_buf = kcalloc(count, sizeof(*buf), GFP_KERNEL);
-	if (!cmd_buf) {
-		err = -ENOMEM;
-		goto exit;
-	}
+	if (!cmd_buf)
+		return -ENOMEM;
 
 	memcpy(cmd_buf, buf, count);
-
-	/* Send the data out to a hardware port */
 	write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL);
 	if (!write_buf) {
 		kfree(cmd_buf);
-		err = -ENOMEM;
-		goto exit;
+		return -ENOMEM;
 	}
 
 	write_buf->buf = cmd_buf;
@@ -373,141 +339,89 @@ ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
 	INIT_LIST_HEAD(&write_buf->queue);
 	list_add_tail(&write_buf->queue, &gnss->queue);
 	kthread_queue_work(gnss->kworker, &gnss->write_work);
-exit:
-	mutex_unlock(&gnss->gnss_mutex);
+
 	return err;
 }
 
+static const struct gnss_operations ice_gnss_ops = {
+	.open = ice_gnss_open,
+	.close = ice_gnss_close,
+	.write_raw = ice_gnss_write,
+};
+
 /**
- * ice_gnss_tty_write_room - Returns the numbers of characters to be written.
- * @tty: pointer to the tty_struct
+ * ice_gnss_register - Register GNSS receiver
+ * @pf: Board private structure
+ *
+ * Allocate and register GNSS receiver in the Linux GNSS subsystem.
  *
- * This routine returns the numbers of characters the tty driver will accept
- * for queuing to be written or 0 if either the TTY is not open or user
- * tries to write to the TTY other than the first.
+ * Return:
+ * * 0 - success
+ * * negative - error code
  */
-static unsigned int ice_gnss_tty_write_room(struct tty_struct *tty)
+static int ice_gnss_register(struct ice_pf *pf)
 {
-	struct gnss_serial *gnss = tty->driver_data;
-
-	/* Only allow to write on TTY 0 */
-	if (!gnss || gnss != gnss->back->gnss_serial[0])
-		return 0;
-
-	mutex_lock(&gnss->gnss_mutex);
+	struct gnss_device *gdev;
+	int ret;
+
+	gdev = gnss_allocate_device(ice_pf_to_dev(pf));
+	if (!gdev) {
+		dev_err(ice_pf_to_dev(pf),
+			"gnss_allocate_device returns NULL\n");
+		return -ENOMEM;
+	}
 
-	if (!gnss->open_count) {
-		mutex_unlock(&gnss->gnss_mutex);
-		return 0;
+	gdev->ops = &ice_gnss_ops;
+	gdev->type = GNSS_TYPE_UBX;
+	gnss_set_drvdata(gdev, pf);
+	ret = gnss_register_device(gdev);
+	if (ret) {
+		dev_err(ice_pf_to_dev(pf), "gnss_register_device err=%d\n",
+			ret);
+		gnss_put_device(gdev);
+	} else {
+		pf->gnss_dev = gdev;
 	}
 
-	mutex_unlock(&gnss->gnss_mutex);
-	return ICE_GNSS_TTY_WRITE_BUF;
+	return ret;
 }
 
-static const struct tty_operations tty_gps_ops = {
-	.open =		ice_gnss_tty_open,
-	.close =	ice_gnss_tty_close,
-	.write =	ice_gnss_tty_write,
-	.write_room =	ice_gnss_tty_write_room,
-};
-
 /**
- * ice_gnss_create_tty_driver - Create a TTY driver for GNSS
+ * ice_gnss_deregister - Deregister GNSS receiver
  * @pf: Board private structure
+ *
+ * Deregister GNSS receiver from the Linux GNSS subsystem,
+ * release its resources.
  */
-static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf)
+static void ice_gnss_deregister(struct ice_pf *pf)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	const int ICE_TTYDRV_NAME_MAX = 14;
-	struct tty_driver *tty_driver;
-	char *ttydrv_name;
-	unsigned int i;
-	int err;
-
-	tty_driver = tty_alloc_driver(ICE_GNSS_TTY_MINOR_DEVICES,
-				      TTY_DRIVER_REAL_RAW);
-	if (IS_ERR(tty_driver)) {
-		dev_err(dev, "Failed to allocate memory for GNSS TTY\n");
-		return NULL;
-	}
-
-	ttydrv_name = kzalloc(ICE_TTYDRV_NAME_MAX, GFP_KERNEL);
-	if (!ttydrv_name) {
-		tty_driver_kref_put(tty_driver);
-		return NULL;
+	if (pf->gnss_dev) {
+		gnss_deregister_device(pf->gnss_dev);
+		gnss_put_device(pf->gnss_dev);
+		pf->gnss_dev = NULL;
 	}
-
-	snprintf(ttydrv_name, ICE_TTYDRV_NAME_MAX, "ttyGNSS_%02x%02x_",
-		 (u8)pf->pdev->bus->number, (u8)PCI_SLOT(pf->pdev->devfn));
-
-	/* Initialize the tty driver*/
-	tty_driver->owner = THIS_MODULE;
-	tty_driver->driver_name = dev_driver_string(dev);
-	tty_driver->name = (const char *)ttydrv_name;
-	tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
-	tty_driver->subtype = SERIAL_TYPE_NORMAL;
-	tty_driver->init_termios = tty_std_termios;
-	tty_driver->init_termios.c_iflag &= ~INLCR;
-	tty_driver->init_termios.c_iflag |= IGNCR;
-	tty_driver->init_termios.c_oflag &= ~OPOST;
-	tty_driver->init_termios.c_lflag &= ~ICANON;
-	tty_driver->init_termios.c_cflag &= ~(CSIZE | CBAUD | CBAUDEX);
-	/* baud rate 9600 */
-	tty_termios_encode_baud_rate(&tty_driver->init_termios, 9600, 9600);
-	tty_driver->driver_state = pf;
-	tty_set_operations(tty_driver, &tty_gps_ops);
-
-	for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
-		pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]),
-					       GFP_KERNEL);
-		if (!pf->gnss_tty_port[i])
-			goto err_out;
-
-		pf->gnss_serial[i] = NULL;
-
-		tty_port_init(pf->gnss_tty_port[i]);
-		tty_port_link_device(pf->gnss_tty_port[i], tty_driver, i);
-	}
-
-	err = tty_register_driver(tty_driver);
-	if (err) {
-		dev_err(dev, "Failed to register TTY driver err=%d\n", err);
-		goto err_out;
-	}
-
-	for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++)
-		dev_info(dev, "%s%d registered\n", ttydrv_name, i);
-
-	return tty_driver;
-
-err_out:
-	while (i--) {
-		tty_port_destroy(pf->gnss_tty_port[i]);
-		kfree(pf->gnss_tty_port[i]);
-	}
-	kfree(ttydrv_name);
-	tty_driver_kref_put(pf->ice_gnss_tty_driver);
-
-	return NULL;
 }
 
 /**
- * ice_gnss_init - Initialize GNSS TTY support
+ * ice_gnss_init - Initialize GNSS support
  * @pf: Board private structure
  */
 void ice_gnss_init(struct ice_pf *pf)
 {
-	struct tty_driver *tty_driver;
+	int ret;
 
-	tty_driver = ice_gnss_create_tty_driver(pf);
-	if (!tty_driver)
+	pf->gnss_serial = ice_gnss_struct_init(pf);
+	if (!pf->gnss_serial)
 		return;
 
-	pf->ice_gnss_tty_driver = tty_driver;
-
-	set_bit(ICE_FLAG_GNSS, pf->flags);
-	dev_info(ice_pf_to_dev(pf), "GNSS TTY init successful\n");
+	ret = ice_gnss_register(pf);
+	if (!ret) {
+		set_bit(ICE_FLAG_GNSS, pf->flags);
+		dev_info(ice_pf_to_dev(pf), "GNSS init successful\n");
+	} else {
+		ice_gnss_exit(pf);
+		dev_err(ice_pf_to_dev(pf), "GNSS init failure\n");
+	}
 }
 
 /**
@@ -516,31 +430,20 @@ void ice_gnss_init(struct ice_pf *pf)
  */
 void ice_gnss_exit(struct ice_pf *pf)
 {
-	unsigned int i;
+	ice_gnss_deregister(pf);
+	clear_bit(ICE_FLAG_GNSS, pf->flags);
 
-	if (!test_bit(ICE_FLAG_GNSS, pf->flags) || !pf->ice_gnss_tty_driver)
-		return;
-
-	for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
-		if (pf->gnss_tty_port[i]) {
-			tty_port_destroy(pf->gnss_tty_port[i]);
-			kfree(pf->gnss_tty_port[i]);
-		}
+	if (pf->gnss_serial) {
+		struct gnss_serial *gnss = pf->gnss_serial;
 
-		if (pf->gnss_serial[i]) {
-			struct gnss_serial *gnss = pf->gnss_serial[i];
+		kthread_cancel_work_sync(&gnss->write_work);
+		kthread_cancel_delayed_work_sync(&gnss->read_work);
+		kthread_destroy_worker(gnss->kworker);
+		gnss->kworker = NULL;
 
-			kthread_cancel_work_sync(&gnss->write_work);
-			kthread_cancel_delayed_work_sync(&gnss->read_work);
-			kfree(gnss);
-			pf->gnss_serial[i] = NULL;
-		}
+		kfree(gnss);
+		pf->gnss_serial = NULL;
 	}
-
-	tty_unregister_driver(pf->ice_gnss_tty_driver);
-	kfree(pf->ice_gnss_tty_driver->name);
-	tty_driver_kref_put(pf->ice_gnss_tty_driver);
-	pf->ice_gnss_tty_driver = NULL;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h
index f454dd1d9285..31db0701d13f 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.h
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.h
@@ -4,15 +4,8 @@
 #ifndef _ICE_GNSS_H_
 #define _ICE_GNSS_H_
 
-#include <linux/tty.h>
-#include <linux/tty_flip.h>
-
 #define ICE_E810T_GNSS_I2C_BUS		0x2
 #define ICE_GNSS_TIMER_DELAY_TIME	(HZ / 10) /* 0.1 second per message */
-/* Create 2 minor devices, both using the same GNSS module. First one is RW,
- * second one RO.
- */
-#define ICE_GNSS_TTY_MINOR_DEVICES	2
 #define ICE_GNSS_TTY_WRITE_BUF		250
 #define ICE_MAX_I2C_DATA_SIZE		FIELD_MAX(ICE_AQC_I2C_DATA_SIZE_M)
 #define ICE_MAX_I2C_WRITE_BYTES		4
@@ -36,13 +29,9 @@ struct gnss_write_buf {
 	unsigned char *buf;
 };
 
-
 /**
  * struct gnss_serial - data used to initialize GNSS TTY port
  * @back: back pointer to PF
- * @tty: pointer to the tty for this device
- * @open_count: number of times this port has been opened
- * @gnss_mutex: gnss_mutex used to protect GNSS serial operations
  * @kworker: kwork thread for handling periodic work
  * @read_work: read_work function for handling GNSS reads
  * @write_work: write_work function for handling GNSS writes
@@ -50,16 +39,13 @@ struct gnss_write_buf {
  */
 struct gnss_serial {
 	struct ice_pf *back;
-	struct tty_struct *tty;
-	int open_count;
-	struct mutex gnss_mutex; /* protects GNSS serial structure */
 	struct kthread_worker *kworker;
 	struct kthread_delayed_work read_work;
 	struct kthread_work write_work;
 	struct list_head queue;
 };
 
-#if IS_ENABLED(CONFIG_TTY)
+#if IS_ENABLED(CONFIG_ICE_GNSS)
 void ice_gnss_init(struct ice_pf *pf);
 void ice_gnss_exit(struct ice_pf *pf);
 bool ice_gnss_is_gps_present(struct ice_hw *hw);
@@ -70,5 +56,5 @@ static inline bool ice_gnss_is_gps_present(struct ice_hw *hw)
 {
 	return false;
 }
-#endif /* IS_ENABLED(CONFIG_TTY) */
+#endif /* IS_ENABLED(CONFIG_ICE_GNSS) */
 #endif /* _ICE_GNSS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 895c32bcc8b5..e6bc2285071e 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -6,6 +6,8 @@
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
+static DEFINE_XARRAY_ALLOC1(ice_aux_id);
+
 /**
  * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
  * @pf: pointer to PF struct
@@ -246,6 +248,17 @@ static int ice_reserve_rdma_qvector(struct ice_pf *pf)
 }
 
 /**
+ * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
+ * @pf: board private structure to initialize
+ */
+static void ice_free_rdma_qvector(struct ice_pf *pf)
+{
+	pf->num_avail_sw_msix -= pf->num_rdma_msix;
+	ice_free_res(pf->irq_tracker, pf->rdma_base_vector,
+		     ICE_RES_RDMA_VEC_ID);
+}
+
+/**
  * ice_adev_release - function to be mapped to AUX dev's release op
  * @dev: pointer to device to free
  */
@@ -331,12 +344,48 @@ int ice_init_rdma(struct ice_pf *pf)
 	struct device *dev = &pf->pdev->dev;
 	int ret;
 
+	if (!ice_is_rdma_ena(pf)) {
+		dev_warn(dev, "RDMA is not supported on this device\n");
+		return 0;
+	}
+
+	ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX),
+		       GFP_KERNEL);
+	if (ret) {
+		dev_err(dev, "Failed to allocate device ID for AUX driver\n");
+		return -ENOMEM;
+	}
+
 	/* Reserve vector resources */
 	ret = ice_reserve_rdma_qvector(pf);
 	if (ret < 0) {
 		dev_err(dev, "failed to reserve vectors for RDMA\n");
-		return ret;
+		goto err_reserve_rdma_qvector;
 	}
 	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
-	return ice_plug_aux_dev(pf);
+	ret = ice_plug_aux_dev(pf);
+	if (ret)
+		goto err_plug_aux_dev;
+	return 0;
+
+err_plug_aux_dev:
+	ice_free_rdma_qvector(pf);
+err_reserve_rdma_qvector:
+	pf->adev = NULL;
+	xa_erase(&ice_aux_id, pf->aux_idx);
+	return ret;
+}
+
+/**
+ * ice_deinit_rdma - deinitialize RDMA on PF
+ * @pf: ptr to ice_pf
+ */
+void ice_deinit_rdma(struct ice_pf *pf)
+{
+	if (!ice_is_rdma_ena(pf))
+		return;
+
+	ice_unplug_aux_dev(pf);
+	ice_free_rdma_qvector(pf);
+	xa_erase(&ice_aux_id, pf->aux_idx);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a596e07b3ce9..781475480ff2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -166,14 +166,14 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 /**
  * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
  * @vsi: the VSI being configured
- * @vf: the VF associated with this VSI, if any
  *
  * Return 0 on success and a negative value on error
  */
-static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf)
+static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 {
 	enum ice_vsi_type vsi_type = vsi->type;
 	struct ice_pf *pf = vsi->back;
+	struct ice_vf *vf = vsi->vf;
 
 	if (WARN_ON(vsi_type == ICE_VSI_VF && !vf))
 		return;
@@ -282,10 +282,10 @@ static int ice_get_free_slot(void *array, int size, int curr)
 }
 
 /**
- * ice_vsi_delete - delete a VSI from the switch
+ * ice_vsi_delete_from_hw - delete a VSI from the switch
  * @vsi: pointer to VSI being removed
  */
-void ice_vsi_delete(struct ice_vsi *vsi)
+static void ice_vsi_delete_from_hw(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_vsi_ctx *ctxt;
@@ -348,47 +348,144 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 }
 
 /**
- * ice_vsi_clear - clean up and deallocate the provided VSI
+ * ice_vsi_free_stats - Free the ring statistics structures
+ * @vsi: VSI pointer
+ */
+static void ice_vsi_free_stats(struct ice_vsi *vsi)
+{
+	struct ice_vsi_stats *vsi_stat;
+	struct ice_pf *pf = vsi->back;
+	int i;
+
+	if (vsi->type == ICE_VSI_CHNL)
+		return;
+	if (!pf->vsi_stats)
+		return;
+
+	vsi_stat = pf->vsi_stats[vsi->idx];
+	if (!vsi_stat)
+		return;
+
+	ice_for_each_alloc_txq(vsi, i) {
+		if (vsi_stat->tx_ring_stats[i]) {
+			kfree_rcu(vsi_stat->tx_ring_stats[i], rcu);
+			WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL);
+		}
+	}
+
+	ice_for_each_alloc_rxq(vsi, i) {
+		if (vsi_stat->rx_ring_stats[i]) {
+			kfree_rcu(vsi_stat->rx_ring_stats[i], rcu);
+			WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL);
+		}
+	}
+
+	kfree(vsi_stat->tx_ring_stats);
+	kfree(vsi_stat->rx_ring_stats);
+	kfree(vsi_stat);
+	pf->vsi_stats[vsi->idx] = NULL;
+}
+
+/**
+ * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI
+ * @vsi: VSI which is having stats allocated
+ */
+static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi)
+{
+	struct ice_ring_stats **tx_ring_stats;
+	struct ice_ring_stats **rx_ring_stats;
+	struct ice_vsi_stats *vsi_stats;
+	struct ice_pf *pf = vsi->back;
+	u16 i;
+
+	vsi_stats = pf->vsi_stats[vsi->idx];
+	tx_ring_stats = vsi_stats->tx_ring_stats;
+	rx_ring_stats = vsi_stats->rx_ring_stats;
+
+	/* Allocate Tx ring stats */
+	ice_for_each_alloc_txq(vsi, i) {
+		struct ice_ring_stats *ring_stats;
+		struct ice_tx_ring *ring;
+
+		ring = vsi->tx_rings[i];
+		ring_stats = tx_ring_stats[i];
+
+		if (!ring_stats) {
+			ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL);
+			if (!ring_stats)
+				goto err_out;
+
+			WRITE_ONCE(tx_ring_stats[i], ring_stats);
+		}
+
+		ring->ring_stats = ring_stats;
+	}
+
+	/* Allocate Rx ring stats */
+	ice_for_each_alloc_rxq(vsi, i) {
+		struct ice_ring_stats *ring_stats;
+		struct ice_rx_ring *ring;
+
+		ring = vsi->rx_rings[i];
+		ring_stats = rx_ring_stats[i];
+
+		if (!ring_stats) {
+			ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL);
+			if (!ring_stats)
+				goto err_out;
+
+			WRITE_ONCE(rx_ring_stats[i], ring_stats);
+		}
+
+		ring->ring_stats = ring_stats;
+	}
+
+	return 0;
+
+err_out:
+	ice_vsi_free_stats(vsi);
+	return -ENOMEM;
+}
+
+/**
+ * ice_vsi_free - clean up and deallocate the provided VSI
  * @vsi: pointer to VSI being cleared
  *
  * This deallocates the VSI's queue resources, removes it from the PF's
  * VSI array if necessary, and deallocates the VSI
- *
- * Returns 0 on success, negative on failure
  */
-int ice_vsi_clear(struct ice_vsi *vsi)
+static void ice_vsi_free(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = NULL;
 	struct device *dev;
 
-	if (!vsi)
-		return 0;
-
-	if (!vsi->back)
-		return -EINVAL;
+	if (!vsi || !vsi->back)
+		return;
 
 	pf = vsi->back;
 	dev = ice_pf_to_dev(pf);
 
 	if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) {
 		dev_dbg(dev, "vsi does not exist at pf->vsi[%d]\n", vsi->idx);
-		return -EINVAL;
+		return;
 	}
 
 	mutex_lock(&pf->sw_mutex);
 	/* updates the PF for this cleared VSI */
 
 	pf->vsi[vsi->idx] = NULL;
-	if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL)
-		pf->next_vsi = vsi->idx;
-	if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && vsi->vf)
-		pf->next_vsi = vsi->idx;
+	pf->next_vsi = vsi->idx;
 
+	ice_vsi_free_stats(vsi);
 	ice_vsi_free_arrays(vsi);
 	mutex_unlock(&pf->sw_mutex);
 	devm_kfree(dev, vsi);
+}
 
-	return 0;
+void ice_vsi_delete(struct ice_vsi *vsi)
+{
+	ice_vsi_delete_from_hw(vsi);
+	ice_vsi_free(vsi);
 }
 
 /**
@@ -461,6 +558,10 @@ static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi)
 	if (!pf->vsi_stats)
 		return -ENOENT;
 
+	if (pf->vsi_stats[vsi->idx])
+	/* realloc will happen in rebuild path */
+		return 0;
+
 	vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL);
 	if (!vsi_stat)
 		return -ENOMEM;
@@ -491,128 +592,93 @@ err_alloc_tx:
 }
 
 /**
- * ice_vsi_alloc - Allocates the next available struct VSI in the PF
- * @pf: board private structure
- * @vsi_type: type of VSI
+ * ice_vsi_alloc_def - set default values for already allocated VSI
+ * @vsi: ptr to VSI
  * @ch: ptr to channel
- * @vf: VF for ICE_VSI_VF and ICE_VSI_CTRL
- *
- * The VF pointer is used for ICE_VSI_VF and ICE_VSI_CTRL. For ICE_VSI_CTRL,
- * it may be NULL in the case there is no association with a VF. For
- * ICE_VSI_VF the VF pointer *must not* be NULL.
- *
- * returns a pointer to a VSI on success, NULL on failure.
  */
-static struct ice_vsi *
-ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type,
-	      struct ice_channel *ch, struct ice_vf *vf)
+static int
+ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_vsi *vsi = NULL;
-
-	if (WARN_ON(vsi_type == ICE_VSI_VF && !vf))
-		return NULL;
-
-	/* Need to protect the allocation of the VSIs at the PF level */
-	mutex_lock(&pf->sw_mutex);
-
-	/* If we have already allocated our maximum number of VSIs,
-	 * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index
-	 * is available to be populated
-	 */
-	if (pf->next_vsi == ICE_NO_VSI) {
-		dev_dbg(dev, "out of VSI slots!\n");
-		goto unlock_pf;
+	if (vsi->type != ICE_VSI_CHNL) {
+		ice_vsi_set_num_qs(vsi);
+		if (ice_vsi_alloc_arrays(vsi))
+			return -ENOMEM;
 	}
 
-	vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL);
-	if (!vsi)
-		goto unlock_pf;
-
-	vsi->type = vsi_type;
-	vsi->back = pf;
-	set_bit(ICE_VSI_DOWN, vsi->state);
-
-	if (vsi_type == ICE_VSI_VF)
-		ice_vsi_set_num_qs(vsi, vf);
-	else if (vsi_type != ICE_VSI_CHNL)
-		ice_vsi_set_num_qs(vsi, NULL);
-
 	switch (vsi->type) {
 	case ICE_VSI_SWITCHDEV_CTRL:
-		if (ice_vsi_alloc_arrays(vsi))
-			goto err_rings;
-
 		/* Setup eswitch MSIX irq handler for VSI */
 		vsi->irq_handler = ice_eswitch_msix_clean_rings;
 		break;
 	case ICE_VSI_PF:
-		if (ice_vsi_alloc_arrays(vsi))
-			goto err_rings;
-
 		/* Setup default MSIX irq handler for VSI */
 		vsi->irq_handler = ice_msix_clean_rings;
 		break;
 	case ICE_VSI_CTRL:
-		if (ice_vsi_alloc_arrays(vsi))
-			goto err_rings;
-
 		/* Setup ctrl VSI MSIX irq handler */
 		vsi->irq_handler = ice_msix_clean_ctrl_vsi;
-
-		/* For the PF control VSI this is NULL, for the VF control VSI
-		 * this will be the first VF to allocate it.
-		 */
-		vsi->vf = vf;
-		break;
-	case ICE_VSI_VF:
-		if (ice_vsi_alloc_arrays(vsi))
-			goto err_rings;
-		vsi->vf = vf;
 		break;
 	case ICE_VSI_CHNL:
 		if (!ch)
-			goto err_rings;
+			return -EINVAL;
+
 		vsi->num_rxq = ch->num_rxq;
 		vsi->num_txq = ch->num_txq;
 		vsi->next_base_q = ch->base_q;
 		break;
+	case ICE_VSI_VF:
 	case ICE_VSI_LB:
-		if (ice_vsi_alloc_arrays(vsi))
-			goto err_rings;
 		break;
 	default:
-		dev_warn(dev, "Unknown VSI type %d\n", vsi->type);
-		goto unlock_pf;
+		ice_vsi_free_arrays(vsi);
+		return -EINVAL;
 	}
 
-	if (vsi->type == ICE_VSI_CTRL && !vf) {
-		/* Use the last VSI slot as the index for PF control VSI */
-		vsi->idx = pf->num_alloc_vsi - 1;
-		pf->ctrl_vsi_idx = vsi->idx;
-		pf->vsi[vsi->idx] = vsi;
-	} else {
-		/* fill slot and make note of the index */
-		vsi->idx = pf->next_vsi;
-		pf->vsi[pf->next_vsi] = vsi;
+	return 0;
+}
+
+/**
+ * ice_vsi_alloc - Allocates the next available struct VSI in the PF
+ * @pf: board private structure
+ *
+ * Reserves a VSI index from the PF and allocates an empty VSI structure
+ * without a type. The VSI structure must later be initialized by calling
+ * ice_vsi_cfg().
+ *
+ * returns a pointer to a VSI on success, NULL on failure.
+ */
+static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_vsi *vsi = NULL;
 
-		/* prepare pf->next_vsi for next use */
-		pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
-						 pf->next_vsi);
+	/* Need to protect the allocation of the VSIs at the PF level */
+	mutex_lock(&pf->sw_mutex);
+
+	/* If we have already allocated our maximum number of VSIs,
+	 * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index
+	 * is available to be populated
+	 */
+	if (pf->next_vsi == ICE_NO_VSI) {
+		dev_dbg(dev, "out of VSI slots!\n");
+		goto unlock_pf;
 	}
 
-	if (vsi->type == ICE_VSI_CTRL && vf)
-		vf->ctrl_vsi_idx = vsi->idx;
+	vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL);
+	if (!vsi)
+		goto unlock_pf;
 
-	/* allocate memory for Tx/Rx ring stat pointers */
-	if (ice_vsi_alloc_stat_arrays(vsi))
-		goto err_rings;
+	vsi->back = pf;
+	set_bit(ICE_VSI_DOWN, vsi->state);
 
-	goto unlock_pf;
+	/* fill slot and make note of the index */
+	vsi->idx = pf->next_vsi;
+	pf->vsi[pf->next_vsi] = vsi;
+
+	/* prepare pf->next_vsi for next use */
+	pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
+					 pf->next_vsi);
 
-err_rings:
-	devm_kfree(dev, vsi);
-	vsi = NULL;
 unlock_pf:
 	mutex_unlock(&pf->sw_mutex);
 	return vsi;
@@ -1177,12 +1243,15 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 /**
  * ice_vsi_init - Create and initialize a VSI
  * @vsi: the VSI being configured
- * @init_vsi: is this call creating a VSI
+ * @vsi_flags: VSI configuration flags
+ *
+ * Set ICE_FLAG_VSI_INIT to initialize a new VSI context, clear it to
+ * reconfigure an existing context.
  *
  * This initializes a VSI context depending on the VSI type to be added and
  * passes it down to the add_vsi aq command to create a new VSI.
  */
-static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
+static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
@@ -1244,7 +1313,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 		/* if updating VSI context, make sure to set valid_section:
 		 * to indicate which section of VSI context being updated
 		 */
-		if (!init_vsi)
+		if (!(vsi_flags & ICE_VSI_FLAG_INIT))
 			ctxt->info.valid_sections |=
 				cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
 	}
@@ -1257,7 +1326,8 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 		if (ret)
 			goto out;
 
-		if (!init_vsi) /* means VSI being updated */
+		if (!(vsi_flags & ICE_VSI_FLAG_INIT))
+			/* means VSI being updated */
 			/* must to indicate which section of VSI context are
 			 * being modified
 			 */
@@ -1272,7 +1342,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 			cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
 	}
 
-	if (init_vsi) {
+	if (vsi_flags & ICE_VSI_FLAG_INIT) {
 		ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL);
 		if (ret) {
 			dev_err(dev, "Add VSI failed, err %d\n", ret);
@@ -1436,7 +1506,7 @@ static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi)
  * ice_vsi_setup_vector_base - Set up the base vector for the given VSI
  * @vsi: ptr to the VSI
  *
- * This should only be called after ice_vsi_alloc() which allocates the
+ * This should only be called after ice_vsi_alloc_def() which allocates the
  * corresponding SW VSI structure and initializes num_queue_pairs for the
  * newly allocated VSI.
  *
@@ -1584,106 +1654,6 @@ err_out:
 }
 
 /**
- * ice_vsi_free_stats - Free the ring statistics structures
- * @vsi: VSI pointer
- */
-static void ice_vsi_free_stats(struct ice_vsi *vsi)
-{
-	struct ice_vsi_stats *vsi_stat;
-	struct ice_pf *pf = vsi->back;
-	int i;
-
-	if (vsi->type == ICE_VSI_CHNL)
-		return;
-	if (!pf->vsi_stats)
-		return;
-
-	vsi_stat = pf->vsi_stats[vsi->idx];
-	if (!vsi_stat)
-		return;
-
-	ice_for_each_alloc_txq(vsi, i) {
-		if (vsi_stat->tx_ring_stats[i]) {
-			kfree_rcu(vsi_stat->tx_ring_stats[i], rcu);
-			WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL);
-		}
-	}
-
-	ice_for_each_alloc_rxq(vsi, i) {
-		if (vsi_stat->rx_ring_stats[i]) {
-			kfree_rcu(vsi_stat->rx_ring_stats[i], rcu);
-			WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL);
-		}
-	}
-
-	kfree(vsi_stat->tx_ring_stats);
-	kfree(vsi_stat->rx_ring_stats);
-	kfree(vsi_stat);
-	pf->vsi_stats[vsi->idx] = NULL;
-}
-
-/**
- * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI
- * @vsi: VSI which is having stats allocated
- */
-static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi)
-{
-	struct ice_ring_stats **tx_ring_stats;
-	struct ice_ring_stats **rx_ring_stats;
-	struct ice_vsi_stats *vsi_stats;
-	struct ice_pf *pf = vsi->back;
-	u16 i;
-
-	vsi_stats = pf->vsi_stats[vsi->idx];
-	tx_ring_stats = vsi_stats->tx_ring_stats;
-	rx_ring_stats = vsi_stats->rx_ring_stats;
-
-	/* Allocate Tx ring stats */
-	ice_for_each_alloc_txq(vsi, i) {
-		struct ice_ring_stats *ring_stats;
-		struct ice_tx_ring *ring;
-
-		ring = vsi->tx_rings[i];
-		ring_stats = tx_ring_stats[i];
-
-		if (!ring_stats) {
-			ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL);
-			if (!ring_stats)
-				goto err_out;
-
-			WRITE_ONCE(tx_ring_stats[i], ring_stats);
-		}
-
-		ring->ring_stats = ring_stats;
-	}
-
-	/* Allocate Rx ring stats */
-	ice_for_each_alloc_rxq(vsi, i) {
-		struct ice_ring_stats *ring_stats;
-		struct ice_rx_ring *ring;
-
-		ring = vsi->rx_rings[i];
-		ring_stats = rx_ring_stats[i];
-
-		if (!ring_stats) {
-			ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL);
-			if (!ring_stats)
-				goto err_out;
-
-			 WRITE_ONCE(rx_ring_stats[i], ring_stats);
-		}
-
-		ring->ring_stats = ring_stats;
-	}
-
-	return 0;
-
-err_out:
-	ice_vsi_free_stats(vsi);
-	return -ENOMEM;
-}
-
-/**
  * ice_vsi_manage_rss_lut - disable/enable RSS
  * @vsi: the VSI being changed
  * @ena: boolean value indicating if this is an enable or disable request
@@ -1992,8 +1962,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
 void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
 {
 	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) {
-		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
-		vsi->rx_buf_len = ICE_RXBUF_2048;
+		vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX;
+		vsi->rx_buf_len = ICE_RXBUF_1664;
 #if (PAGE_SIZE < 8192)
 	} else if (!ICE_2K_TOO_SMALL_WITH_PADDING &&
 		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
@@ -2002,11 +1972,7 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
 #endif
 	} else {
 		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;
-#if (PAGE_SIZE < 8192)
 		vsi->rx_buf_len = ICE_RXBUF_3072;
-#else
-		vsi->rx_buf_len = ICE_RXBUF_2048;
-#endif
 	}
 }
 
@@ -2645,54 +2611,97 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi)
 }
 
 /**
- * ice_vsi_setup - Set up a VSI by a given type
- * @pf: board private structure
- * @pi: pointer to the port_info instance
- * @vsi_type: VSI type
- * @vf: pointer to VF to which this VSI connects. This field is used primarily
- *      for the ICE_VSI_VF type. Other VSI types should pass NULL.
- * @ch: ptr to channel
- *
- * This allocates the sw VSI structure and its queue resources.
+ * ice_free_vf_ctrl_res - Free the VF control VSI resource
+ * @pf: pointer to PF structure
+ * @vsi: the VSI to free resources for
  *
- * Returns pointer to the successfully allocated and configured VSI sw struct on
- * success, NULL on failure.
+ * Check if the VF control VSI resource is still in use. If no VF is using it
+ * any more, release the VSI resource. Otherwise, leave it to be cleaned up
+ * once no other VF uses it.
  */
-struct ice_vsi *
-ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
-	      enum ice_vsi_type vsi_type, struct ice_vf *vf,
-	      struct ice_channel *ch)
+static void ice_free_vf_ctrl_res(struct ice_pf *pf,  struct ice_vsi *vsi)
+{
+	struct ice_vf *vf;
+	unsigned int bkt;
+
+	rcu_read_lock();
+	ice_for_each_vf_rcu(pf, bkt, vf) {
+		if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+
+	/* No other VFs left that have control VSI. It is now safe to reclaim
+	 * SW interrupts back to the common pool.
+	 */
+	ice_free_res(pf->irq_tracker, vsi->base_vector,
+		     ICE_RES_VF_CTRL_VEC_ID);
+	pf->num_avail_sw_msix += vsi->num_q_vectors;
+}
+
+static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_vsi *vsi;
 	int ret, i;
 
-	if (vsi_type == ICE_VSI_CHNL)
-		vsi = ice_vsi_alloc(pf, vsi_type, ch, NULL);
-	else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL)
-		vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf);
-	else
-		vsi = ice_vsi_alloc(pf, vsi_type, NULL, NULL);
+	/* configure VSI nodes based on number of queues and TC's */
+	ice_for_each_traffic_class(i) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(i)))
+			continue;
 
-	if (!vsi) {
-		dev_err(dev, "could not allocate VSI\n");
-		return NULL;
+		if (vsi->type == ICE_VSI_CHNL) {
+			if (!vsi->alloc_txq && vsi->num_txq)
+				max_txqs[i] = vsi->num_txq;
+			else
+				max_txqs[i] = pf->num_lan_tx;
+		} else {
+			max_txqs[i] = vsi->alloc_txq;
+		}
 	}
 
-	vsi->port_info = pi;
+	dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc);
+	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+			      max_txqs);
+	if (ret) {
+		dev_err(dev, "VSI %d failed lan queue config, error %d\n",
+			vsi->vsi_num, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * 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)
+{
+	struct device *dev = ice_pf_to_dev(vsi->back);
+	struct ice_pf *pf = vsi->back;
+	int ret;
+
 	vsi->vsw = pf->first_sw;
-	if (vsi->type == ICE_VSI_PF)
-		vsi->ethtype = ETH_P_PAUSE;
+
+	ret = ice_vsi_alloc_def(vsi, params->ch);
+	if (ret)
+		return ret;
+
+	/* allocate memory for Tx/Rx ring stat pointers */
+	if (ice_vsi_alloc_stat_arrays(vsi))
+		goto unroll_vsi_alloc;
 
 	ice_alloc_fd_res(vsi);
 
-	if (vsi_type != ICE_VSI_CHNL) {
-		if (ice_vsi_get_qs(vsi)) {
-			dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n",
-				vsi->idx);
-			goto unroll_vsi_alloc;
-		}
+	if (ice_vsi_get_qs(vsi)) {
+		dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n",
+			vsi->idx);
+		goto unroll_vsi_alloc_stat;
 	}
 
 	/* set RSS capabilities */
@@ -2702,7 +2711,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	ice_vsi_set_tc_cfg(vsi);
 
 	/* create the VSI */
-	ret = ice_vsi_init(vsi, true);
+	ret = ice_vsi_init(vsi, params->flags);
 	if (ret)
 		goto unroll_get_qs;
 
@@ -2733,6 +2742,14 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 			goto unroll_vector_base;
 
 		ice_vsi_map_rings_to_vectors(vsi);
+		if (ice_is_xdp_ena_vsi(vsi)) {
+			ret = ice_vsi_determine_xdp_res(vsi);
+			if (ret)
+				goto unroll_vector_base;
+			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog);
+			if (ret)
+				goto unroll_vector_base;
+		}
 
 		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
 		if (vsi->type != ICE_VSI_CTRL)
@@ -2797,30 +2814,156 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		goto unroll_vsi_init;
 	}
 
-	/* configure VSI nodes based on number of queues and TC's */
-	ice_for_each_traffic_class(i) {
-		if (!(vsi->tc_cfg.ena_tc & BIT(i)))
-			continue;
+	return 0;
 
-		if (vsi->type == ICE_VSI_CHNL) {
-			if (!vsi->alloc_txq && vsi->num_txq)
-				max_txqs[i] = vsi->num_txq;
-			else
-				max_txqs[i] = pf->num_lan_tx;
+unroll_vector_base:
+	/* reclaim SW interrupts back to the common pool */
+	ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+	pf->num_avail_sw_msix += vsi->num_q_vectors;
+unroll_alloc_q_vector:
+	ice_vsi_free_q_vectors(vsi);
+unroll_vsi_init:
+	ice_vsi_delete_from_hw(vsi);
+unroll_get_qs:
+	ice_vsi_put_qs(vsi);
+unroll_vsi_alloc_stat:
+	ice_vsi_free_stats(vsi);
+unroll_vsi_alloc:
+	ice_vsi_free_arrays(vsi);
+	return ret;
+}
+
+/**
+ * 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)
+{
+	struct ice_pf *pf = vsi->back;
+	int ret;
+
+	if (WARN_ON(params->type == ICE_VSI_VF && !params->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);
+	if (ret)
+		return ret;
+
+	ret = ice_vsi_cfg_tc_lan(vsi->back, vsi);
+	if (ret)
+		ice_vsi_decfg(vsi);
+
+	if (vsi->type == ICE_VSI_CTRL) {
+		if (vsi->vf) {
+			WARN_ON(vsi->vf->ctrl_vsi_idx != ICE_NO_VSI);
+			vsi->vf->ctrl_vsi_idx = vsi->idx;
 		} else {
-			max_txqs[i] = vsi->alloc_txq;
+			WARN_ON(pf->ctrl_vsi_idx != ICE_NO_VSI);
+			pf->ctrl_vsi_idx = vsi->idx;
 		}
 	}
 
-	dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc);
-	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
-			      max_txqs);
-	if (ret) {
-		dev_err(dev, "VSI %d failed lan queue config, error %d\n",
-			vsi->vsi_num, ret);
-		goto unroll_clear_rings;
+	return ret;
+}
+
+/**
+ * ice_vsi_decfg - remove all VSI configuration
+ * @vsi: pointer to VSI
+ */
+void ice_vsi_decfg(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	/* The Rx rule will only exist to remove if the LLDP FW
+	 * engine is currently stopped
+	 */
+	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+		ice_cfg_sw_lldp(vsi, false, false);
+
+	ice_fltr_remove_all(vsi);
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+	err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
+	if (err)
+		dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
+			vsi->vsi_num, err);
+
+	if (ice_is_xdp_ena_vsi(vsi))
+		/* return value check can be skipped here, it always returns
+		 * 0 if reset is in progress
+		 */
+		ice_destroy_xdp_rings(vsi);
+
+	ice_vsi_clear_rings(vsi);
+	ice_vsi_free_q_vectors(vsi);
+	ice_vsi_put_qs(vsi);
+	ice_vsi_free_arrays(vsi);
+
+	/* SR-IOV determines needed MSIX resources all at once instead of per
+	 * VSI since when VFs are spawned we know how many VFs there are and how
+	 * many interrupts each VF needs. SR-IOV MSIX resources are also
+	 * cleared in the same manner.
+	 */
+	if (vsi->type == ICE_VSI_CTRL && vsi->vf) {
+		ice_free_vf_ctrl_res(pf, vsi);
+	} else if (vsi->type != ICE_VSI_VF) {
+		/* reclaim SW interrupts back to the common pool */
+		ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+		pf->num_avail_sw_msix += vsi->num_q_vectors;
+		vsi->base_vector = 0;
 	}
 
+	if (vsi->type == ICE_VSI_VF &&
+	    vsi->agg_node && vsi->agg_node->valid)
+		vsi->agg_node->num_vsis--;
+	if (vsi->agg_node) {
+		vsi->agg_node->valid = false;
+		vsi->agg_node->agg_id = 0;
+	}
+}
+
+/**
+ * ice_vsi_setup - Set up a VSI by a given type
+ * @pf: board private structure
+ * @params: parameters to use when creating the VSI
+ *
+ * This allocates the sw VSI structure and its queue resources.
+ *
+ * Returns pointer to the successfully allocated and configured VSI sw struct on
+ * success, NULL on failure.
+ */
+struct ice_vsi *
+ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_vsi *vsi;
+	int ret;
+
+	/* ice_vsi_setup can only initialize a new VSI, and we must have
+	 * a port_info structure for it.
+	 */
+	if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) ||
+	    WARN_ON(!params->pi))
+		return NULL;
+
+	vsi = ice_vsi_alloc(pf);
+	if (!vsi) {
+		dev_err(dev, "could not allocate VSI\n");
+		return NULL;
+	}
+
+	ret = ice_vsi_cfg(vsi, params);
+	if (ret)
+		goto err_vsi_cfg;
+
 	/* Add switch rule to drop all Tx Flow Control Frames, of look up
 	 * type ETHERTYPE from VSIs, and restrict malicious VF from sending
 	 * out PAUSE or PFC frames. If enabled, FW can still send FC frames.
@@ -2830,34 +2973,21 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	 * be dropped so that VFs cannot send LLDP packets to reconfig DCB
 	 * settings in the HW.
 	 */
-	if (!ice_is_safe_mode(pf))
-		if (vsi->type == ICE_VSI_PF) {
-			ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
-					 ICE_DROP_PACKET);
-			ice_cfg_sw_lldp(vsi, true, true);
-		}
+	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) {
+		ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
+				 ICE_DROP_PACKET);
+		ice_cfg_sw_lldp(vsi, true, true);
+	}
 
 	if (!vsi->agg_node)
 		ice_set_agg_vsi(vsi);
+
 	return vsi;
 
-unroll_clear_rings:
-	ice_vsi_clear_rings(vsi);
-unroll_vector_base:
-	/* reclaim SW interrupts back to the common pool */
-	ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
-	pf->num_avail_sw_msix += vsi->num_q_vectors;
-unroll_alloc_q_vector:
-	ice_vsi_free_q_vectors(vsi);
-unroll_vsi_init:
-	ice_vsi_free_stats(vsi);
-	ice_vsi_delete(vsi);
-unroll_get_qs:
-	ice_vsi_put_qs(vsi);
-unroll_vsi_alloc:
-	if (vsi_type == ICE_VSI_VF)
+err_vsi_cfg:
+	if (params->type == ICE_VSI_VF)
 		ice_enable_lag(pf->lag);
-	ice_vsi_clear(vsi);
+	ice_vsi_free(vsi);
 
 	return NULL;
 }
@@ -3121,37 +3251,6 @@ void ice_napi_del(struct ice_vsi *vsi)
 }
 
 /**
- * ice_free_vf_ctrl_res - Free the VF control VSI resource
- * @pf: pointer to PF structure
- * @vsi: the VSI to free resources for
- *
- * Check if the VF control VSI resource is still in use. If no VF is using it
- * any more, release the VSI resource. Otherwise, leave it to be cleaned up
- * once no other VF uses it.
- */
-static void ice_free_vf_ctrl_res(struct ice_pf *pf,  struct ice_vsi *vsi)
-{
-	struct ice_vf *vf;
-	unsigned int bkt;
-
-	rcu_read_lock();
-	ice_for_each_vf_rcu(pf, bkt, vf) {
-		if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) {
-			rcu_read_unlock();
-			return;
-		}
-	}
-	rcu_read_unlock();
-
-	/* No other VFs left that have control VSI. It is now safe to reclaim
-	 * SW interrupts back to the common pool.
-	 */
-	ice_free_res(pf->irq_tracker, vsi->base_vector,
-		     ICE_RES_VF_CTRL_VEC_ID);
-	pf->num_avail_sw_msix += vsi->num_q_vectors;
-}
-
-/**
  * ice_vsi_release - Delete a VSI and free its resources
  * @vsi: the VSI being removed
  *
@@ -3160,7 +3259,6 @@ static void ice_free_vf_ctrl_res(struct ice_pf *pf,  struct ice_vsi *vsi)
 int ice_vsi_release(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf;
-	int err;
 
 	if (!vsi->back)
 		return -ENODEV;
@@ -3178,50 +3276,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
 	}
 
+	if (vsi->type == ICE_VSI_PF)
+		ice_devlink_destroy_pf_port(pf);
+
 	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
 		ice_rss_clean(vsi);
 
-	/* Disable VSI and free resources */
-	if (vsi->type != ICE_VSI_LB)
-		ice_vsi_dis_irq(vsi);
 	ice_vsi_close(vsi);
-
-	/* SR-IOV determines needed MSIX resources all at once instead of per
-	 * VSI since when VFs are spawned we know how many VFs there are and how
-	 * many interrupts each VF needs. SR-IOV MSIX resources are also
-	 * cleared in the same manner.
-	 */
-	if (vsi->type == ICE_VSI_CTRL && vsi->vf) {
-		ice_free_vf_ctrl_res(pf, vsi);
-	} else if (vsi->type != ICE_VSI_VF) {
-		/* reclaim SW interrupts back to the common pool */
-		ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
-		pf->num_avail_sw_msix += vsi->num_q_vectors;
-	}
-
-	if (!ice_is_safe_mode(pf)) {
-		if (vsi->type == ICE_VSI_PF) {
-			ice_fltr_remove_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
-					    ICE_DROP_PACKET);
-			ice_cfg_sw_lldp(vsi, true, false);
-			/* The Rx rule will only exist to remove if the LLDP FW
-			 * engine is currently stopped
-			 */
-			if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-				ice_cfg_sw_lldp(vsi, false, false);
-		}
-	}
-
-	if (ice_is_vsi_dflt_vsi(vsi))
-		ice_clear_dflt_vsi(vsi);
-	ice_fltr_remove_all(vsi);
-	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
-	err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
-	if (err)
-		dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
-			vsi->vsi_num, err);
-	ice_vsi_delete(vsi);
-	ice_vsi_free_q_vectors(vsi);
+	ice_vsi_decfg(vsi);
 
 	if (vsi->netdev) {
 		if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) {
@@ -3235,19 +3297,12 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		}
 	}
 
-	if (vsi->type == ICE_VSI_VF &&
-	    vsi->agg_node && vsi->agg_node->valid)
-		vsi->agg_node->num_vsis--;
-	ice_vsi_clear_rings(vsi);
-	ice_vsi_free_stats(vsi);
-	ice_vsi_put_qs(vsi);
-
 	/* retain SW VSI data structure since it is needed to unregister and
 	 * free VSI netdev when PF is not in reset recovery pending state,\
 	 * for ex: during rmmod.
 	 */
 	if (!ice_is_reset_in_progress(pf->state))
-		ice_vsi_clear(vsi);
+		ice_vsi_delete(vsi);
 
 	return 0;
 }
@@ -3372,7 +3427,7 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi,
  * @prev_txq: Number of Tx rings before ring reallocation
  * @prev_rxq: Number of Rx rings before ring reallocation
  */
-static int
+static void
 ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq)
 {
 	struct ice_vsi_stats *vsi_stat;
@@ -3380,9 +3435,9 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq)
 	int i;
 
 	if (!prev_txq || !prev_rxq)
-		return 0;
+		return;
 	if (vsi->type == ICE_VSI_CHNL)
-		return 0;
+		return;
 
 	vsi_stat = pf->vsi_stats[vsi->idx];
 
@@ -3403,36 +3458,36 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq)
 			}
 		}
 	}
-
-	return 0;
 }
 
 /**
  * ice_vsi_rebuild - Rebuild VSI after reset
  * @vsi: VSI to be rebuild
- * @init_vsi: is this an initialization or a reconfigure of the VSI
+ * @vsi_flags: flags used for VSI rebuild flow
+ *
+ * Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or
+ * ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware.
  *
  * Returns 0 on success and negative value on failure
  */
-int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
+int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 {
-	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_vsi_cfg_params params = {};
 	struct ice_coalesce_stored *coalesce;
-	int ret, i, prev_txq, prev_rxq;
+	int ret, prev_txq, prev_rxq;
 	int prev_num_q_vectors = 0;
-	enum ice_vsi_type vtype;
 	struct ice_pf *pf;
 
 	if (!vsi)
 		return -EINVAL;
 
+	params = ice_vsi_to_params(vsi);
+	params.flags = vsi_flags;
+
 	pf = vsi->back;
-	vtype = vsi->type;
-	if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf))
+	if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
-	ice_vsi_init_vlan_ops(vsi);
-
 	coalesce = kcalloc(vsi->num_q_vectors,
 			   sizeof(struct ice_coalesce_stored), GFP_KERNEL);
 	if (!coalesce)
@@ -3443,188 +3498,32 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 	prev_txq = vsi->num_txq;
 	prev_rxq = vsi->num_rxq;
 
-	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
-	ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
+	ice_vsi_decfg(vsi);
+	ret = ice_vsi_cfg_def(vsi, &params);
 	if (ret)
-		dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
-			vsi->vsi_num, ret);
-	ice_vsi_free_q_vectors(vsi);
-
-	/* SR-IOV determines needed MSIX resources all at once instead of per
-	 * VSI since when VFs are spawned we know how many VFs there are and how
-	 * many interrupts each VF needs. SR-IOV MSIX resources are also
-	 * cleared in the same manner.
-	 */
-	if (vtype != ICE_VSI_VF) {
-		/* reclaim SW interrupts back to the common pool */
-		ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
-		pf->num_avail_sw_msix += vsi->num_q_vectors;
-		vsi->base_vector = 0;
-	}
-
-	if (ice_is_xdp_ena_vsi(vsi))
-		/* return value check can be skipped here, it always returns
-		 * 0 if reset is in progress
-		 */
-		ice_destroy_xdp_rings(vsi);
-	ice_vsi_put_qs(vsi);
-	ice_vsi_clear_rings(vsi);
-	ice_vsi_free_arrays(vsi);
-	if (vtype == ICE_VSI_VF)
-		ice_vsi_set_num_qs(vsi, vsi->vf);
-	else
-		ice_vsi_set_num_qs(vsi, NULL);
-
-	ret = ice_vsi_alloc_arrays(vsi);
-	if (ret < 0)
-		goto err_vsi;
-
-	ice_vsi_get_qs(vsi);
-
-	ice_alloc_fd_res(vsi);
-	ice_vsi_set_tc_cfg(vsi);
-
-	/* Initialize VSI struct elements and create VSI in FW */
-	ret = ice_vsi_init(vsi, init_vsi);
-	if (ret < 0)
-		goto err_vsi;
-
-	switch (vtype) {
-	case ICE_VSI_CTRL:
-	case ICE_VSI_SWITCHDEV_CTRL:
-	case ICE_VSI_PF:
-		ret = ice_vsi_alloc_q_vectors(vsi);
-		if (ret)
-			goto err_rings;
-
-		ret = ice_vsi_setup_vector_base(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ret = ice_vsi_alloc_rings(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ret = ice_vsi_alloc_ring_stats(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ice_vsi_map_rings_to_vectors(vsi);
-
-		vsi->stat_offsets_loaded = false;
-		if (ice_is_xdp_ena_vsi(vsi)) {
-			ret = ice_vsi_determine_xdp_res(vsi);
-			if (ret)
-				goto err_vectors;
-			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog);
-			if (ret)
-				goto err_vectors;
-		}
-		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
-		if (vtype != ICE_VSI_CTRL)
-			/* Do not exit if configuring RSS had an issue, at
-			 * least receive traffic on first queue. Hence no
-			 * need to capture return value
-			 */
-			if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
-				ice_vsi_cfg_rss_lut_key(vsi);
-
-		/* disable or enable CRC stripping */
-		if (vsi->netdev)
-			ice_vsi_cfg_crc_strip(vsi, !!(vsi->netdev->features &
-					      NETIF_F_RXFCS));
-
-		break;
-	case ICE_VSI_VF:
-		ret = ice_vsi_alloc_q_vectors(vsi);
-		if (ret)
-			goto err_rings;
-
-		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ret = ice_vsi_alloc_rings(vsi);
-		if (ret)
-			goto err_vectors;
-
-		ret = ice_vsi_alloc_ring_stats(vsi);
-		if (ret)
-			goto err_vectors;
-
-		vsi->stat_offsets_loaded = false;
-		break;
-	case ICE_VSI_CHNL:
-		if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
-			ice_vsi_cfg_rss_lut_key(vsi);
-			ice_vsi_set_rss_flow_fld(vsi);
-		}
-		break;
-	default:
-		break;
-	}
-
-	/* configure VSI nodes based on number of queues and TC's */
-	for (i = 0; i < vsi->tc_cfg.numtc; i++) {
-		/* configure VSI nodes based on number of queues and TC's.
-		 * ADQ creates VSIs for each TC/Channel but doesn't
-		 * allocate queues instead it reconfigures the PF queues
-		 * as per the TC command. So max_txqs should point to the
-		 * PF Tx queues.
-		 */
-		if (vtype == ICE_VSI_CHNL)
-			max_txqs[i] = pf->num_lan_tx;
-		else
-			max_txqs[i] = vsi->alloc_txq;
-
-		if (ice_is_xdp_ena_vsi(vsi))
-			max_txqs[i] += vsi->num_xdp_txq;
-	}
-
-	if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags))
-		/* If MQPRIO is set, means channel code path, hence for main
-		 * VSI's, use TC as 1
-		 */
-		ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs);
-	else
-		ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx,
-				      vsi->tc_cfg.ena_tc, max_txqs);
+		goto err_vsi_cfg;
 
+	ret = ice_vsi_cfg_tc_lan(pf, vsi);
 	if (ret) {
-		dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n",
-			vsi->vsi_num, ret);
-		if (init_vsi) {
+		if (vsi_flags & ICE_VSI_FLAG_INIT) {
 			ret = -EIO;
-			goto err_vectors;
+			goto err_vsi_cfg_tc_lan;
 		} else {
+			kfree(coalesce);
 			return ice_schedule_reset(pf, ICE_RESET_PFR);
 		}
 	}
 
-	if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq))
-		goto err_vectors;
+	ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq);
 
 	ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
 	kfree(coalesce);
 
 	return 0;
 
-err_vectors:
-	ice_vsi_free_q_vectors(vsi);
-err_rings:
-	if (vsi->netdev) {
-		vsi->current_netdev_flags = 0;
-		unregister_netdev(vsi->netdev);
-		free_netdev(vsi->netdev);
-		vsi->netdev = NULL;
-	}
-err_vsi:
-	ice_vsi_clear(vsi);
-	set_bit(ICE_RESET_FAILED, pf->state);
+err_vsi_cfg_tc_lan:
+	ice_vsi_decfg(vsi);
+err_vsi_cfg:
 	kfree(coalesce);
 	return ret;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index dcdf69a693e9..75221478f2dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -7,6 +7,47 @@
 #include "ice.h"
 #include "ice_vlan.h"
 
+/* Flags used for VSI configuration and rebuild */
+#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);
@@ -42,7 +83,6 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
 int ice_set_link(struct ice_vsi *vsi, bool ena);
 
 void ice_vsi_delete(struct ice_vsi *vsi);
-int ice_vsi_clear(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
 
@@ -51,9 +91,7 @@ int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi);
 void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 
 struct ice_vsi *
-ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
-	      enum ice_vsi_type vsi_type, struct ice_vf *vf,
-	      struct ice_channel *ch);
+ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
 void ice_napi_del(struct ice_vsi *vsi);
 
@@ -63,6 +101,7 @@ void ice_vsi_close(struct ice_vsi *vsi);
 
 int ice_ena_vsi(struct ice_vsi *vsi, bool locked);
 
+void ice_vsi_decfg(struct ice_vsi *vsi);
 void ice_dis_vsi(struct ice_vsi *vsi, bool locked);
 
 int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id);
@@ -70,7 +109,8 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id);
 int
 ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id);
 
-int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi);
+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);
 
 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 8ec24f6cf6be..567694bf098b 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -22,6 +22,7 @@
 #include "ice_eswitch.h"
 #include "ice_tc_lib.h"
 #include "ice_vsi_vlan_ops.h"
+#include <net/xdp_sock_drv.h>
 
 #define DRV_SUMMARY	"Intel(R) Ethernet Connection E800 Series Linux Driver"
 static const char ice_driver_string[] = DRV_SUMMARY;
@@ -44,7 +45,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX
 MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 
-static DEFINE_IDA(ice_aux_ida);
 DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key);
 EXPORT_SYMBOL(ice_xdp_locking_key);
 
@@ -564,7 +564,7 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	/* Disable VFs until reset is completed */
 	mutex_lock(&pf->vfs.table_lock);
 	ice_for_each_vf(pf, bkt, vf)
-		ice_set_vf_state_qs_dis(vf);
+		ice_set_vf_state_dis(vf);
 	mutex_unlock(&pf->vfs.table_lock);
 
 	if (ice_is_eswitch_mode_switchdev(pf)) {
@@ -2596,8 +2596,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		xdp_ring->netdev = NULL;
 		xdp_ring->dev = dev;
 		xdp_ring->count = vsi->num_tx_desc;
-		xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1;
-		xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1;
 		WRITE_ONCE(vsi->xdp_rings[i], xdp_ring);
 		if (ice_setup_tx_ring(xdp_ring))
 			goto free_xdp_rings;
@@ -2889,6 +2887,18 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @vsi: Pointer to VSI structure
+ */
+static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
+{
+	if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
+		return ICE_RXBUF_1664;
+	else
+		return ICE_RXBUF_3072;
+}
+
+/**
  * ice_xdp_setup_prog - Add or remove XDP eBPF program
  * @vsi: VSI to setup XDP for
  * @prog: XDP program
@@ -2898,13 +2908,16 @@ static int
 ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		   struct netlink_ext_ack *extack)
 {
-	int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
+	unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
 	bool if_running = netif_running(vsi->netdev);
 	int ret = 0, xdp_ring_err = 0;
 
-	if (frame_size > vsi->rx_buf_len) {
-		NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP");
-		return -EOPNOTSUPP;
+	if (prog && !prog->aux->xdp_has_frags) {
+		if (frame_size > ice_max_xdp_frame_size(vsi)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "MTU is too large for linear frames and XDP prog does not support frags");
+			return -EOPNOTSUPP;
+		}
 	}
 
 	/* need to stop netdev while setting up the program for Rx rings */
@@ -2925,11 +2938,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			if (xdp_ring_err)
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
 		}
+		xdp_features_set_redirect_target(vsi->netdev, true);
 		/* reallocate Rx queues that are used for zero-copy */
 		xdp_ring_err = ice_realloc_zc_buf(vsi, true);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
 	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
+		xdp_features_clear_redirect_target(vsi->netdev);
 		xdp_ring_err = ice_destroy_xdp_rings(vsi);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
@@ -3344,10 +3359,11 @@ static void ice_napi_add(struct ice_vsi *vsi)
 
 /**
  * ice_set_ops - set netdev and ethtools ops for the given netdev
- * @netdev: netdev instance
+ * @vsi: the VSI associated with the new netdev
  */
-static void ice_set_ops(struct net_device *netdev)
+static void ice_set_ops(struct ice_vsi *vsi)
 {
+	struct net_device *netdev = vsi->netdev;
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 
 	if (ice_is_safe_mode(pf)) {
@@ -3359,6 +3375,13 @@ static void ice_set_ops(struct net_device *netdev)
 	netdev->netdev_ops = &ice_netdev_ops;
 	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
 	ice_set_ethtool_ops(netdev);
+
+	if (vsi->type != ICE_VSI_PF)
+		return;
+
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY |
+			       NETDEV_XDP_ACT_RX_SG;
 }
 
 /**
@@ -3447,53 +3470,8 @@ static void ice_set_netdev_features(struct net_device *netdev)
 	 * be changed at runtime
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
-}
-
-/**
- * ice_cfg_netdev - Allocate, configure and register a netdev
- * @vsi: the VSI associated with the new netdev
- *
- * Returns 0 on success, negative value on failure
- */
-static int ice_cfg_netdev(struct ice_vsi *vsi)
-{
-	struct ice_netdev_priv *np;
-	struct net_device *netdev;
-	u8 mac_addr[ETH_ALEN];
-
-	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
-				    vsi->alloc_rxq);
-	if (!netdev)
-		return -ENOMEM;
-
-	set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
-	vsi->netdev = netdev;
-	np = netdev_priv(netdev);
-	np->vsi = vsi;
-
-	ice_set_netdev_features(netdev);
-
-	ice_set_ops(netdev);
 
-	if (vsi->type == ICE_VSI_PF) {
-		SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back));
-		ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
-		eth_hw_addr_set(netdev, mac_addr);
-		ether_addr_copy(netdev->perm_addr, mac_addr);
-	}
-
-	netdev->priv_flags |= IFF_UNICAST_FLT;
-
-	/* Setup netdev TC information */
-	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
-
-	/* setup watchdog timeout value to be 5 second */
-	netdev->watchdog_timeo = 5 * HZ;
-
-	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = ICE_MAX_MTU;
-
-	return 0;
+	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
 /**
@@ -3521,14 +3499,27 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size)
 static struct ice_vsi *
 ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_PF, NULL, NULL);
+	struct ice_vsi_cfg_params params = {};
+
+	params.type = ICE_VSI_PF;
+	params.pi = pi;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	return ice_vsi_setup(pf, &params);
 }
 
 static struct ice_vsi *
 ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		   struct ice_channel *ch)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, NULL, ch);
+	struct ice_vsi_cfg_params params = {};
+
+	params.type = ICE_VSI_CHNL;
+	params.pi = pi;
+	params.ch = ch;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	return ice_vsi_setup(pf, &params);
 }
 
 /**
@@ -3542,7 +3533,13 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 static struct ice_vsi *
 ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, NULL, NULL);
+	struct ice_vsi_cfg_params params = {};
+
+	params.type = ICE_VSI_CTRL;
+	params.pi = pi;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	return ice_vsi_setup(pf, &params);
 }
 
 /**
@@ -3556,7 +3553,13 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 struct ice_vsi *
 ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_LB, NULL, NULL);
+	struct ice_vsi_cfg_params params = {};
+
+	params.type = ICE_VSI_LB;
+	params.pi = pi;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	return ice_vsi_setup(pf, &params);
 }
 
 /**
@@ -3716,20 +3719,6 @@ static void ice_tc_indir_block_unregister(struct ice_vsi *vsi)
 }
 
 /**
- * ice_tc_indir_block_remove - clean indirect TC block notifications
- * @pf: PF structure
- */
-static void ice_tc_indir_block_remove(struct ice_pf *pf)
-{
-	struct ice_vsi *pf_vsi = ice_get_main_vsi(pf);
-
-	if (!pf_vsi)
-		return;
-
-	ice_tc_indir_block_unregister(pf_vsi);
-}
-
-/**
  * ice_tc_indir_block_register - Register TC indirect block notifications
  * @vsi: VSI struct which has the netdev
  *
@@ -3749,78 +3738,6 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi)
 }
 
 /**
- * ice_setup_pf_sw - Setup the HW switch on startup or after reset
- * @pf: board private structure
- *
- * Returns 0 on success, negative value on failure
- */
-static int ice_setup_pf_sw(struct ice_pf *pf)
-{
-	struct device *dev = ice_pf_to_dev(pf);
-	bool dvm = ice_is_dvm_ena(&pf->hw);
-	struct ice_vsi *vsi;
-	int status;
-
-	if (ice_is_reset_in_progress(pf->state))
-		return -EBUSY;
-
-	status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL);
-	if (status)
-		return -EIO;
-
-	vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
-	if (!vsi)
-		return -ENOMEM;
-
-	/* init channel list */
-	INIT_LIST_HEAD(&vsi->ch_list);
-
-	status = ice_cfg_netdev(vsi);
-	if (status)
-		goto unroll_vsi_setup;
-	/* netdev has to be configured before setting frame size */
-	ice_vsi_cfg_frame_size(vsi);
-
-	/* init indirect block notifications */
-	status = ice_tc_indir_block_register(vsi);
-	if (status) {
-		dev_err(dev, "Failed to register netdev notifier\n");
-		goto unroll_cfg_netdev;
-	}
-
-	/* Setup DCB netlink interface */
-	ice_dcbnl_setup(vsi);
-
-	/* registering the NAPI handler requires both the queues and
-	 * netdev to be created, which are done in ice_pf_vsi_setup()
-	 * and ice_cfg_netdev() respectively
-	 */
-	ice_napi_add(vsi);
-
-	status = ice_init_mac_fltr(pf);
-	if (status)
-		goto unroll_napi_add;
-
-	return 0;
-
-unroll_napi_add:
-	ice_tc_indir_block_unregister(vsi);
-unroll_cfg_netdev:
-	if (vsi) {
-		ice_napi_del(vsi);
-		if (vsi->netdev) {
-			clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
-			free_netdev(vsi->netdev);
-			vsi->netdev = NULL;
-		}
-	}
-
-unroll_vsi_setup:
-	ice_vsi_release(vsi);
-	return status;
-}
-
-/**
  * ice_get_avail_q_count - Get count of queues in use
  * @pf_qmap: bitmap to get queue use count from
  * @lock: pointer to a mutex that protects access to pf_qmap
@@ -4249,13 +4166,13 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
 
 	/* set for the next time the netdev is started */
 	if (!netif_running(vsi->netdev)) {
-		ice_vsi_rebuild(vsi, false);
+		ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
 		dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
 		goto done;
 	}
 
 	ice_vsi_close(vsi);
-	ice_vsi_rebuild(vsi, false);
+	ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
 	ice_pf_dcb_recfg(pf, locked);
 	ice_vsi_open(vsi);
 done:
@@ -4518,6 +4435,23 @@ err_vsi_open:
 	return err;
 }
 
+static void ice_deinit_fdir(struct ice_pf *pf)
+{
+	struct ice_vsi *vsi = ice_get_ctrl_vsi(pf);
+
+	if (!vsi)
+		return;
+
+	ice_vsi_manage_fdir(vsi, false);
+	ice_vsi_release(vsi);
+	if (pf->ctrl_vsi_idx != ICE_NO_VSI) {
+		pf->vsi[pf->ctrl_vsi_idx] = NULL;
+		pf->ctrl_vsi_idx = ICE_NO_VSI;
+	}
+
+	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
+}
+
 /**
  * ice_get_opt_fw_name - return optional firmware file name or NULL
  * @pf: pointer to the PF instance
@@ -4618,116 +4552,171 @@ static void ice_print_wake_reason(struct ice_pf *pf)
 
 /**
  * ice_register_netdev - register netdev
- * @pf: pointer to the PF struct
+ * @vsi: pointer to the VSI struct
  */
-static int ice_register_netdev(struct ice_pf *pf)
+static int ice_register_netdev(struct ice_vsi *vsi)
 {
-	struct ice_vsi *vsi;
-	int err = 0;
+	int err;
 
-	vsi = ice_get_main_vsi(pf);
 	if (!vsi || !vsi->netdev)
 		return -EIO;
 
 	err = register_netdev(vsi->netdev);
 	if (err)
-		goto err_register_netdev;
+		return err;
 
 	set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
 	netif_carrier_off(vsi->netdev);
 	netif_tx_stop_all_queues(vsi->netdev);
 
 	return 0;
-err_register_netdev:
-	free_netdev(vsi->netdev);
-	vsi->netdev = NULL;
-	clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
-	return err;
+}
+
+static void ice_unregister_netdev(struct ice_vsi *vsi)
+{
+	if (!vsi || !vsi->netdev)
+		return;
+
+	unregister_netdev(vsi->netdev);
+	clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
 }
 
 /**
- * ice_probe - Device initialization routine
- * @pdev: PCI device information struct
- * @ent: entry in ice_pci_tbl
+ * ice_cfg_netdev - Allocate, configure and register a netdev
+ * @vsi: the VSI associated with the new netdev
  *
- * Returns 0 on success, negative on failure
+ * Returns 0 on success, negative value on failure
  */
-static int
-ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
+static int ice_cfg_netdev(struct ice_vsi *vsi)
 {
-	struct device *dev = &pdev->dev;
-	struct ice_vsi *vsi;
-	struct ice_pf *pf;
-	struct ice_hw *hw;
-	int i, err;
+	struct ice_netdev_priv *np;
+	struct net_device *netdev;
+	u8 mac_addr[ETH_ALEN];
 
-	if (pdev->is_virtfn) {
-		dev_err(dev, "can't probe a virtual function\n");
-		return -EINVAL;
+	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
+				    vsi->alloc_rxq);
+	if (!netdev)
+		return -ENOMEM;
+
+	set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
+	vsi->netdev = netdev;
+	np = netdev_priv(netdev);
+	np->vsi = vsi;
+
+	ice_set_netdev_features(netdev);
+	ice_set_ops(vsi);
+
+	if (vsi->type == ICE_VSI_PF) {
+		SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back));
+		ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
+		eth_hw_addr_set(netdev, mac_addr);
 	}
 
-	/* this driver uses devres, see
-	 * Documentation/driver-api/driver-model/devres.rst
-	 */
-	err = pcim_enable_device(pdev);
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* Setup netdev TC information */
+	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
+
+	netdev->max_mtu = ICE_MAX_MTU;
+
+	return 0;
+}
+
+static void ice_decfg_netdev(struct ice_vsi *vsi)
+{
+	clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
+	free_netdev(vsi->netdev);
+	vsi->netdev = NULL;
+}
+
+static int ice_start_eth(struct ice_vsi *vsi)
+{
+	int err;
+
+	err = ice_init_mac_fltr(vsi->back);
 	if (err)
 		return err;
 
-	err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev));
-	if (err) {
-		dev_err(dev, "BAR0 I/O map error %d\n", err);
-		return err;
-	}
+	rtnl_lock();
+	err = ice_vsi_open(vsi);
+	rtnl_unlock();
 
-	pf = ice_allocate_pf(dev);
-	if (!pf)
-		return -ENOMEM;
+	return err;
+}
 
-	/* initialize Auxiliary index to invalid value */
-	pf->aux_idx = -1;
+static int ice_init_eth(struct ice_pf *pf)
+{
+	struct ice_vsi *vsi = ice_get_main_vsi(pf);
+	int err;
 
-	/* set up for high or low DMA */
-	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_err(dev, "DMA configuration failed: 0x%x\n", err);
+	if (!vsi)
+		return -EINVAL;
+
+	/* init channel list */
+	INIT_LIST_HEAD(&vsi->ch_list);
+
+	err = ice_cfg_netdev(vsi);
+	if (err)
 		return err;
-	}
+	/* Setup DCB netlink interface */
+	ice_dcbnl_setup(vsi);
 
-	pci_enable_pcie_error_reporting(pdev);
-	pci_set_master(pdev);
+	err = ice_init_mac_fltr(pf);
+	if (err)
+		goto err_init_mac_fltr;
 
-	pf->pdev = pdev;
-	pci_set_drvdata(pdev, pf);
-	set_bit(ICE_DOWN, pf->state);
-	/* Disable service task until DOWN bit is cleared */
-	set_bit(ICE_SERVICE_DIS, pf->state);
+	err = ice_devlink_create_pf_port(pf);
+	if (err)
+		goto err_devlink_create_pf_port;
 
-	hw = &pf->hw;
-	hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0];
-	pci_save_state(pdev);
+	SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
 
-	hw->back = pf;
-	hw->vendor_id = pdev->vendor;
-	hw->device_id = pdev->device;
-	pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
-	hw->subsystem_vendor_id = pdev->subsystem_vendor;
-	hw->subsystem_device_id = pdev->subsystem_device;
-	hw->bus.device = PCI_SLOT(pdev->devfn);
-	hw->bus.func = PCI_FUNC(pdev->devfn);
-	ice_set_ctrlq_len(hw);
+	err = ice_register_netdev(vsi);
+	if (err)
+		goto err_register_netdev;
 
-	pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M);
+	err = ice_tc_indir_block_register(vsi);
+	if (err)
+		goto err_tc_indir_block_register;
 
-#ifndef CONFIG_DYNAMIC_DEBUG
-	if (debug < -1)
-		hw->debug_mask = debug;
-#endif
+	ice_napi_add(vsi);
+
+	return 0;
+
+err_tc_indir_block_register:
+	ice_unregister_netdev(vsi);
+err_register_netdev:
+	ice_devlink_destroy_pf_port(pf);
+err_devlink_create_pf_port:
+err_init_mac_fltr:
+	ice_decfg_netdev(vsi);
+	return err;
+}
+
+static void ice_deinit_eth(struct ice_pf *pf)
+{
+	struct ice_vsi *vsi = ice_get_main_vsi(pf);
+
+	if (!vsi)
+		return;
+
+	ice_vsi_close(vsi);
+	ice_unregister_netdev(vsi);
+	ice_devlink_destroy_pf_port(pf);
+	ice_tc_indir_block_unregister(vsi);
+	ice_decfg_netdev(vsi);
+}
+
+static int ice_init_dev(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	int err;
 
 	err = ice_init_hw(hw);
 	if (err) {
 		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		err = -EIO;
-		goto err_exit_unroll;
+		return err;
 	}
 
 	ice_init_feature_support(pf);
@@ -4750,62 +4739,31 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	err = ice_init_pf(pf);
 	if (err) {
 		dev_err(dev, "ice_init_pf failed: %d\n", err);
-		goto err_init_pf_unroll;
+		goto err_init_pf;
 	}
 
-	ice_devlink_init_regions(pf);
-
 	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
 	pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port;
 	pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
 	pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared;
-	i = 0;
 	if (pf->hw.tnl.valid_count[TNL_VXLAN]) {
-		pf->hw.udp_tunnel_nic.tables[i].n_entries =
+		pf->hw.udp_tunnel_nic.tables[0].n_entries =
 			pf->hw.tnl.valid_count[TNL_VXLAN];
-		pf->hw.udp_tunnel_nic.tables[i].tunnel_types =
+		pf->hw.udp_tunnel_nic.tables[0].tunnel_types =
 			UDP_TUNNEL_TYPE_VXLAN;
-		i++;
 	}
 	if (pf->hw.tnl.valid_count[TNL_GENEVE]) {
-		pf->hw.udp_tunnel_nic.tables[i].n_entries =
+		pf->hw.udp_tunnel_nic.tables[1].n_entries =
 			pf->hw.tnl.valid_count[TNL_GENEVE];
-		pf->hw.udp_tunnel_nic.tables[i].tunnel_types =
+		pf->hw.udp_tunnel_nic.tables[1].tunnel_types =
 			UDP_TUNNEL_TYPE_GENEVE;
-		i++;
-	}
-
-	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
-	if (!pf->num_alloc_vsi) {
-		err = -EIO;
-		goto err_init_pf_unroll;
-	}
-	if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) {
-		dev_warn(&pf->pdev->dev,
-			 "limiting the VSI count due to UDP tunnel limitation %d > %d\n",
-			 pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES);
-		pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES;
-	}
-
-	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
-			       GFP_KERNEL);
-	if (!pf->vsi) {
-		err = -ENOMEM;
-		goto err_init_pf_unroll;
-	}
-
-	pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi,
-				     sizeof(*pf->vsi_stats), GFP_KERNEL);
-	if (!pf->vsi_stats) {
-		err = -ENOMEM;
-		goto err_init_vsi_unroll;
 	}
 
 	err = ice_init_interrupt_scheme(pf);
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_vsi_stats_unroll;
+		goto err_init_interrupt_scheme;
 	}
 
 	/* In case of MSIX we are going to setup the misc vector right here
@@ -4816,49 +4774,94 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	err = ice_req_irq_msix_misc(pf);
 	if (err) {
 		dev_err(dev, "setup of misc vector failed: %d\n", err);
-		goto err_init_interrupt_unroll;
+		goto err_req_irq_msix_misc;
 	}
 
-	/* create switch struct for the switch element created by FW on boot */
-	pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL);
-	if (!pf->first_sw) {
-		err = -ENOMEM;
-		goto err_msix_misc_unroll;
-	}
+	return 0;
 
-	if (hw->evb_veb)
-		pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
-	else
-		pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA;
+err_req_irq_msix_misc:
+	ice_clear_interrupt_scheme(pf);
+err_init_interrupt_scheme:
+	ice_deinit_pf(pf);
+err_init_pf:
+	ice_deinit_hw(hw);
+	return err;
+}
 
-	pf->first_sw->pf = pf;
+static void ice_deinit_dev(struct ice_pf *pf)
+{
+	ice_free_irq_msix_misc(pf);
+	ice_clear_interrupt_scheme(pf);
+	ice_deinit_pf(pf);
+	ice_deinit_hw(&pf->hw);
+}
 
-	/* record the sw_id available for later use */
-	pf->first_sw->sw_id = hw->port_info->sw_id;
+static void ice_init_features(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
 
-	err = ice_setup_pf_sw(pf);
-	if (err) {
-		dev_err(dev, "probe failed due to setup PF switch: %d\n", err);
-		goto err_alloc_sw_unroll;
-	}
+	if (ice_is_safe_mode(pf))
+		return;
 
-	clear_bit(ICE_SERVICE_DIS, pf->state);
+	/* initialize DDP driven features */
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_init(pf);
 
-	/* tell the firmware we are up */
-	err = ice_send_version(pf);
-	if (err) {
-		dev_err(dev, "probe failed sending driver version %s. error: %d\n",
-			UTS_RELEASE, err);
-		goto err_send_version_unroll;
+	if (ice_is_feature_supported(pf, ICE_F_GNSS))
+		ice_gnss_init(pf);
+
+	/* Note: Flow director init failure is non-fatal to load */
+	if (ice_init_fdir(pf))
+		dev_err(dev, "could not initialize flow director\n");
+
+	/* Note: DCB init failure is non-fatal to load */
+	if (ice_init_pf_dcb(pf, false)) {
+		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	} else {
+		ice_cfg_lldp_mib_change(&pf->hw, true);
 	}
 
-	/* since everything is good, start the service timer */
-	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
+	if (ice_init_lag(pf))
+		dev_warn(dev, "Failed to init link aggregation support\n");
+}
+
+static void ice_deinit_features(struct ice_pf *pf)
+{
+	ice_deinit_lag(pf);
+	if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags))
+		ice_cfg_lldp_mib_change(&pf->hw, false);
+	ice_deinit_fdir(pf);
+	if (ice_is_feature_supported(pf, ICE_F_GNSS))
+		ice_gnss_exit(pf);
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_release(pf);
+}
+
+static void ice_init_wakeup(struct ice_pf *pf)
+{
+	/* Save wakeup reason register for later use */
+	pf->wakeup_reason = rd32(&pf->hw, PFPM_WUS);
+
+	/* check for a power management event */
+	ice_print_wake_reason(pf);
+
+	/* clear wake status, all bits */
+	wr32(&pf->hw, PFPM_WUS, U32_MAX);
+
+	/* Disable WoL at init, wait for user to enable */
+	device_set_wakeup_enable(ice_pf_to_dev(pf), false);
+}
+
+static int ice_init_link(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
 
 	err = ice_init_link_events(pf->hw.port_info);
 	if (err) {
 		dev_err(dev, "ice_init_link_events failed: %d\n", err);
-		goto err_send_version_unroll;
+		return err;
 	}
 
 	/* not a fatal error if this fails */
@@ -4894,123 +4897,350 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		set_bit(ICE_FLAG_NO_MEDIA, pf->flags);
 	}
 
-	ice_verify_cacheline_size(pf);
+	return err;
+}
 
-	/* Save wakeup reason register for later use */
-	pf->wakeup_reason = rd32(hw, PFPM_WUS);
+static int ice_init_pf_sw(struct ice_pf *pf)
+{
+	bool dvm = ice_is_dvm_ena(&pf->hw);
+	struct ice_vsi *vsi;
+	int err;
 
-	/* check for a power management event */
-	ice_print_wake_reason(pf);
+	/* create switch struct for the switch element created by FW on boot */
+	pf->first_sw = kzalloc(sizeof(*pf->first_sw), GFP_KERNEL);
+	if (!pf->first_sw)
+		return -ENOMEM;
 
-	/* clear wake status, all bits */
-	wr32(hw, PFPM_WUS, U32_MAX);
+	if (pf->hw.evb_veb)
+		pf->first_sw->bridge_mode = BRIDGE_MODE_VEB;
+	else
+		pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA;
 
-	/* Disable WoL at init, wait for user to enable */
-	device_set_wakeup_enable(dev, false);
+	pf->first_sw->pf = pf;
 
-	if (ice_is_safe_mode(pf)) {
-		ice_set_safe_mode_vlan_cfg(pf);
-		goto probe_done;
+	/* record the sw_id available for later use */
+	pf->first_sw->sw_id = pf->hw.port_info->sw_id;
+
+	err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL);
+	if (err)
+		goto err_aq_set_port_params;
+
+	vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
+	if (!vsi) {
+		err = -ENOMEM;
+		goto err_pf_vsi_setup;
 	}
 
-	/* initialize DDP driven features */
-	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
-		ice_ptp_init(pf);
+	return 0;
 
-	if (ice_is_feature_supported(pf, ICE_F_GNSS))
-		ice_gnss_init(pf);
+err_pf_vsi_setup:
+err_aq_set_port_params:
+	kfree(pf->first_sw);
+	return err;
+}
 
-	/* Note: Flow director init failure is non-fatal to load */
-	if (ice_init_fdir(pf))
-		dev_err(dev, "could not initialize flow director\n");
+static void ice_deinit_pf_sw(struct ice_pf *pf)
+{
+	struct ice_vsi *vsi = ice_get_main_vsi(pf);
 
-	/* Note: DCB init failure is non-fatal to load */
-	if (ice_init_pf_dcb(pf, false)) {
-		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
-		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
-	} else {
-		ice_cfg_lldp_mib_change(&pf->hw, true);
+	if (!vsi)
+		return;
+
+	ice_vsi_release(vsi);
+	kfree(pf->first_sw);
+}
+
+static int ice_alloc_vsis(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+
+	pf->num_alloc_vsi = pf->hw.func_caps.guar_num_vsi;
+	if (!pf->num_alloc_vsi)
+		return -EIO;
+
+	if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) {
+		dev_warn(dev,
+			 "limiting the VSI count due to UDP tunnel limitation %d > %d\n",
+			 pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES);
+		pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES;
 	}
 
-	if (ice_init_lag(pf))
-		dev_warn(dev, "Failed to init link aggregation support\n");
+	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
+			       GFP_KERNEL);
+	if (!pf->vsi)
+		return -ENOMEM;
 
-	/* print PCI link speed and width */
-	pcie_print_link_status(pf->pdev);
+	pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi,
+				     sizeof(*pf->vsi_stats), GFP_KERNEL);
+	if (!pf->vsi_stats) {
+		devm_kfree(dev, pf->vsi);
+		return -ENOMEM;
+	}
 
-probe_done:
-	err = ice_devlink_create_pf_port(pf);
+	return 0;
+}
+
+static void ice_dealloc_vsis(struct ice_pf *pf)
+{
+	devm_kfree(ice_pf_to_dev(pf), pf->vsi_stats);
+	pf->vsi_stats = NULL;
+
+	pf->num_alloc_vsi = 0;
+	devm_kfree(ice_pf_to_dev(pf), pf->vsi);
+	pf->vsi = NULL;
+}
+
+static int ice_init_devlink(struct ice_pf *pf)
+{
+	int err;
+
+	err = ice_devlink_register_params(pf);
 	if (err)
-		goto err_create_pf_port;
+		return err;
 
-	vsi = ice_get_main_vsi(pf);
-	if (!vsi || !vsi->netdev) {
-		err = -EINVAL;
-		goto err_netdev_reg;
-	}
+	ice_devlink_init_regions(pf);
+	ice_devlink_register(pf);
 
-	SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
+	return 0;
+}
+
+static void ice_deinit_devlink(struct ice_pf *pf)
+{
+	ice_devlink_unregister(pf);
+	ice_devlink_destroy_regions(pf);
+	ice_devlink_unregister_params(pf);
+}
+
+static int ice_init(struct ice_pf *pf)
+{
+	int err;
 
-	err = ice_register_netdev(pf);
+	err = ice_init_dev(pf);
 	if (err)
-		goto err_netdev_reg;
+		return err;
 
-	err = ice_devlink_register_params(pf);
+	err = ice_alloc_vsis(pf);
+	if (err)
+		goto err_alloc_vsis;
+
+	err = ice_init_pf_sw(pf);
 	if (err)
-		goto err_netdev_reg;
+		goto err_init_pf_sw;
+
+	ice_init_wakeup(pf);
+
+	err = ice_init_link(pf);
+	if (err)
+		goto err_init_link;
+
+	err = ice_send_version(pf);
+	if (err)
+		goto err_init_link;
+
+	ice_verify_cacheline_size(pf);
+
+	if (ice_is_safe_mode(pf))
+		ice_set_safe_mode_vlan_cfg(pf);
+	else
+		/* print PCI link speed and width */
+		pcie_print_link_status(pf->pdev);
 
 	/* ready to go, so clear down state bit */
 	clear_bit(ICE_DOWN, pf->state);
-	if (ice_is_rdma_ena(pf)) {
-		pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL);
-		if (pf->aux_idx < 0) {
-			dev_err(dev, "Failed to allocate device ID for AUX driver\n");
-			err = -ENOMEM;
-			goto err_devlink_reg_param;
-		}
+	clear_bit(ICE_SERVICE_DIS, pf->state);
 
-		err = ice_init_rdma(pf);
-		if (err) {
-			dev_err(dev, "Failed to initialize RDMA: %d\n", err);
-			err = -EIO;
-			goto err_init_aux_unroll;
-		}
-	} else {
-		dev_warn(dev, "RDMA is not supported on this device\n");
-	}
+	/* since everything is good, start the service timer */
+	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
-	ice_devlink_register(pf);
 	return 0;
 
-err_init_aux_unroll:
-	pf->adev = NULL;
-	ida_free(&ice_aux_ida, pf->aux_idx);
-err_devlink_reg_param:
-	ice_devlink_unregister_params(pf);
-err_netdev_reg:
-	ice_devlink_destroy_pf_port(pf);
-err_create_pf_port:
-err_send_version_unroll:
-	ice_vsi_release_all(pf);
-err_alloc_sw_unroll:
+err_init_link:
+	ice_deinit_pf_sw(pf);
+err_init_pf_sw:
+	ice_dealloc_vsis(pf);
+err_alloc_vsis:
+	ice_deinit_dev(pf);
+	return err;
+}
+
+static void ice_deinit(struct ice_pf *pf)
+{
 	set_bit(ICE_SERVICE_DIS, pf->state);
 	set_bit(ICE_DOWN, pf->state);
-	devm_kfree(dev, pf->first_sw);
-err_msix_misc_unroll:
-	ice_free_irq_msix_misc(pf);
-err_init_interrupt_unroll:
-	ice_clear_interrupt_scheme(pf);
-err_init_vsi_stats_unroll:
-	devm_kfree(dev, pf->vsi_stats);
-	pf->vsi_stats = NULL;
-err_init_vsi_unroll:
-	devm_kfree(dev, pf->vsi);
-err_init_pf_unroll:
-	ice_deinit_pf(pf);
-	ice_devlink_destroy_regions(pf);
-	ice_deinit_hw(hw);
-err_exit_unroll:
-	pci_disable_pcie_error_reporting(pdev);
+
+	ice_deinit_pf_sw(pf);
+	ice_dealloc_vsis(pf);
+	ice_deinit_dev(pf);
+}
+
+/**
+ * ice_load - load pf by init hw and starting VSI
+ * @pf: pointer to the pf instance
+ */
+int ice_load(struct ice_pf *pf)
+{
+	struct ice_vsi_cfg_params params = {};
+	struct ice_vsi *vsi;
+	int err;
+
+	err = ice_reset(&pf->hw, ICE_RESET_PFR);
+	if (err)
+		return err;
+
+	err = ice_init_dev(pf);
+	if (err)
+		return err;
+
+	vsi = ice_get_main_vsi(pf);
+
+	params = ice_vsi_to_params(vsi);
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	err = ice_vsi_cfg(vsi, &params);
+	if (err)
+		goto err_vsi_cfg;
+
+	err = ice_start_eth(ice_get_main_vsi(pf));
+	if (err)
+		goto err_start_eth;
+
+	err = ice_init_rdma(pf);
+	if (err)
+		goto err_init_rdma;
+
+	ice_init_features(pf);
+	ice_service_task_restart(pf);
+
+	clear_bit(ICE_DOWN, pf->state);
+
+	return 0;
+
+err_init_rdma:
+	ice_vsi_close(ice_get_main_vsi(pf));
+err_start_eth:
+	ice_vsi_decfg(ice_get_main_vsi(pf));
+err_vsi_cfg:
+	ice_deinit_dev(pf);
+	return err;
+}
+
+/**
+ * ice_unload - unload pf by stopping VSI and deinit hw
+ * @pf: pointer to the pf instance
+ */
+void ice_unload(struct ice_pf *pf)
+{
+	ice_deinit_features(pf);
+	ice_deinit_rdma(pf);
+	ice_vsi_close(ice_get_main_vsi(pf));
+	ice_vsi_decfg(ice_get_main_vsi(pf));
+	ice_deinit_dev(pf);
+}
+
+/**
+ * ice_probe - Device initialization routine
+ * @pdev: PCI device information struct
+ * @ent: entry in ice_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int
+ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int err;
+
+	if (pdev->is_virtfn) {
+		dev_err(dev, "can't probe a virtual function\n");
+		return -EINVAL;
+	}
+
+	/* this driver uses devres, see
+	 * Documentation/driver-api/driver-model/devres.rst
+	 */
+	err = pcim_enable_device(pdev);
+	if (err)
+		return err;
+
+	err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev));
+	if (err) {
+		dev_err(dev, "BAR0 I/O map error %d\n", err);
+		return err;
+	}
+
+	pf = ice_allocate_pf(dev);
+	if (!pf)
+		return -ENOMEM;
+
+	/* initialize Auxiliary index to invalid value */
+	pf->aux_idx = -1;
+
+	/* set up for high or low DMA */
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(dev, "DMA configuration failed: 0x%x\n", err);
+		return err;
+	}
+
+	pci_set_master(pdev);
+
+	pf->pdev = pdev;
+	pci_set_drvdata(pdev, pf);
+	set_bit(ICE_DOWN, pf->state);
+	/* Disable service task until DOWN bit is cleared */
+	set_bit(ICE_SERVICE_DIS, pf->state);
+
+	hw = &pf->hw;
+	hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0];
+	pci_save_state(pdev);
+
+	hw->back = pf;
+	hw->port_info = NULL;
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+	hw->bus.device = PCI_SLOT(pdev->devfn);
+	hw->bus.func = PCI_FUNC(pdev->devfn);
+	ice_set_ctrlq_len(hw);
+
+	pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M);
+
+#ifndef CONFIG_DYNAMIC_DEBUG
+	if (debug < -1)
+		hw->debug_mask = debug;
+#endif
+
+	err = ice_init(pf);
+	if (err)
+		goto err_init;
+
+	err = ice_init_eth(pf);
+	if (err)
+		goto err_init_eth;
+
+	err = ice_init_rdma(pf);
+	if (err)
+		goto err_init_rdma;
+
+	err = ice_init_devlink(pf);
+	if (err)
+		goto err_init_devlink;
+
+	ice_init_features(pf);
+
+	return 0;
+
+err_init_devlink:
+	ice_deinit_rdma(pf);
+err_init_rdma:
+	ice_deinit_eth(pf);
+err_init_eth:
+	ice_deinit(pf);
+err_init:
 	pci_disable_device(pdev);
 	return err;
 }
@@ -5085,52 +5315,33 @@ static void ice_remove(struct pci_dev *pdev)
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 	int i;
 
-	ice_devlink_unregister(pf);
 	for (i = 0; i < ICE_MAX_RESET_WAIT; i++) {
 		if (!ice_is_reset_in_progress(pf->state))
 			break;
 		msleep(100);
 	}
 
-	ice_tc_indir_block_remove(pf);
-
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
 	}
 
 	ice_service_task_stop(pf);
-
 	ice_aq_cancel_waiting_tasks(pf);
-	ice_unplug_aux_dev(pf);
-	if (pf->aux_idx >= 0)
-		ida_free(&ice_aux_ida, pf->aux_idx);
-	ice_devlink_unregister_params(pf);
 	set_bit(ICE_DOWN, pf->state);
 
-	ice_deinit_lag(pf);
-	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
-		ice_ptp_release(pf);
-	if (ice_is_feature_supported(pf, ICE_F_GNSS))
-		ice_gnss_exit(pf);
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
-	ice_setup_mc_magic_wake(pf);
+	ice_deinit_features(pf);
+	ice_deinit_devlink(pf);
+	ice_deinit_rdma(pf);
+	ice_deinit_eth(pf);
+	ice_deinit(pf);
+
 	ice_vsi_release_all(pf);
-	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
-	ice_devlink_destroy_pf_port(pf);
+
+	ice_setup_mc_magic_wake(pf);
 	ice_set_wake(pf);
-	ice_free_irq_msix_misc(pf);
-	ice_for_each_vsi(pf, i) {
-		if (!pf->vsi[i])
-			continue;
-		ice_vsi_free_q_vectors(pf->vsi[i]);
-	}
-	devm_kfree(&pdev->dev, pf->vsi_stats);
-	pf->vsi_stats = NULL;
-	ice_deinit_pf(pf);
-	ice_devlink_destroy_regions(pf);
-	ice_deinit_hw(&pf->hw);
 
 	/* Issue a PFR as part of the prescribed driver unload flow.  Do not
 	 * do it via ice_schedule_reset() since there is no need to rebuild
@@ -5138,8 +5349,6 @@ static void ice_remove(struct pci_dev *pdev)
 	 */
 	ice_reset(&pf->hw, ICE_RESET_PFR);
 	pci_wait_for_pending_transaction(pdev);
-	ice_clear_interrupt_scheme(pf);
-	pci_disable_pcie_error_reporting(pdev);
 	pci_disable_device(pdev);
 }
 
@@ -6173,24 +6382,21 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
 }
 
 /**
- * ice_vsi_cfg - Setup the VSI
+ * ice_vsi_cfg_lan - Setup the VSI lan related config
  * @vsi: the VSI being configured
  *
  * Return 0 on success and negative value on error
  */
-int ice_vsi_cfg(struct ice_vsi *vsi)
+int ice_vsi_cfg_lan(struct ice_vsi *vsi)
 {
 	int err;
 
-	if (vsi->netdev) {
+	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
 		ice_set_rx_mode(vsi->netdev);
 
-		if (vsi->type != ICE_VSI_LB) {
-			err = ice_vsi_vlan_setup(vsi);
-
-			if (err)
-				return err;
-		}
+		err = ice_vsi_vlan_setup(vsi);
+		if (err)
+			return err;
 	}
 	ice_vsi_cfg_dcb_rings(vsi);
 
@@ -6371,7 +6577,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 
 	if (vsi->port_info &&
 	    (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) &&
-	    vsi->netdev) {
+	    vsi->netdev && vsi->type == ICE_VSI_PF) {
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
@@ -6382,7 +6588,9 @@ static int ice_up_complete(struct ice_vsi *vsi)
 	 * set the baseline so counters are ready when interface is up
 	 */
 	ice_update_eth_stats(vsi);
-	ice_service_task_schedule(pf);
+
+	if (vsi->type == ICE_VSI_PF)
+		ice_service_task_schedule(pf);
 
 	return 0;
 }
@@ -6395,7 +6603,7 @@ int ice_up(struct ice_vsi *vsi)
 {
 	int err;
 
-	err = ice_vsi_cfg(vsi);
+	err = ice_vsi_cfg_lan(vsi);
 	if (!err)
 		err = ice_up_complete(vsi);
 
@@ -6963,7 +7171,7 @@ int ice_vsi_open_ctrl(struct ice_vsi *vsi)
 	if (err)
 		goto err_setup_rx;
 
-	err = ice_vsi_cfg(vsi);
+	err = ice_vsi_cfg_lan(vsi);
 	if (err)
 		goto err_setup_rx;
 
@@ -7017,7 +7225,7 @@ int ice_vsi_open(struct ice_vsi *vsi)
 	if (err)
 		goto err_setup_rx;
 
-	err = ice_vsi_cfg(vsi);
+	err = ice_vsi_cfg_lan(vsi);
 	if (err)
 		goto err_setup_rx;
 
@@ -7102,7 +7310,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 			continue;
 
 		/* rebuild the VSI */
-		err = ice_vsi_rebuild(vsi, true);
+		err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT);
 		if (err) {
 			dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n",
 				err, vsi->idx, ice_vsi_type_str(type));
@@ -7358,18 +7566,6 @@ clear_recovery:
 }
 
 /**
- * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP
- * @vsi: Pointer to VSI structure
- */
-static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
-{
-	if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))
-		return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM;
-	else
-		return ICE_RXBUF_3072;
-}
-
-/**
  * ice_change_mtu - NDO callback to change the MTU
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size
@@ -7381,6 +7577,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
+	struct bpf_prog *prog;
 	u8 count = 0;
 	int err = 0;
 
@@ -7389,7 +7586,8 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		return 0;
 	}
 
-	if (ice_is_xdp_ena_vsi(vsi)) {
+	prog = vsi->xdp_prog;
+	if (prog && !prog->aux->xdp_has_frags) {
 		int frame_size = ice_max_xdp_frame_size(vsi);
 
 		if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) {
@@ -7397,6 +7595,12 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 				   frame_size - ICE_ETH_PKT_HDR_PAD);
 			return -EINVAL;
 		}
+	} else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) {
+		if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) {
+			netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n",
+				   ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD);
+			return -EINVAL;
+		}
 	}
 
 	/* if a reset is in progress, wait for some time for it to complete */
@@ -8447,12 +8651,9 @@ static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_fltr)
 		/* clear the VSI from scheduler tree */
 		ice_rm_vsi_lan_cfg(ch->ch_vsi->port_info, ch->ch_vsi->idx);
 
-		/* Delete VSI from FW */
+		/* Delete VSI from FW, PF and HW VSI arrays */
 		ice_vsi_delete(ch->ch_vsi);
 
-		/* Delete VSI from PF and HW VSI arrays */
-		ice_vsi_clear(ch->ch_vsi);
-
 		/* free the channel */
 		kfree(ch);
 	}
@@ -8511,7 +8712,7 @@ static int ice_rebuild_channels(struct ice_pf *pf)
 		type = vsi->type;
 
 		/* rebuild ADQ VSI */
-		err = ice_vsi_rebuild(vsi, true);
+		err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT);
 		if (err) {
 			dev_err(dev, "VSI (type:%s) at index %d rebuild failed, err %d\n",
 				ice_vsi_type_str(type), vsi->idx, err);
@@ -8743,14 +8944,14 @@ config_tcf:
 	cur_rxq = vsi->num_rxq;
 
 	/* proceed with rebuild main VSI using correct number of queues */
-	ret = ice_vsi_rebuild(vsi, false);
+	ret = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
 	if (ret) {
 		/* fallback to current number of queues */
 		dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n");
 		vsi->req_txq = cur_txq;
 		vsi->req_rxq = cur_rxq;
 		clear_bit(ICE_RESET_FAILED, pf->state);
-		if (ice_vsi_rebuild(vsi, false)) {
+		if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) {
 			dev_err(dev, "Rebuild of main VSI failed again\n");
 			return ret;
 		}
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index c262dc886e6a..f6f52a248066 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -662,7 +662,6 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank,
 
 		/* Verify that the simple checksum is zero */
 		for (i = 0; i < sizeof(*tmp); i++)
-			/* cppcheck-suppress objectIndex */
 			sum += ((u8 *)tmp)[i];
 
 		if (sum) {
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index d63161d73eb1..ac6f06f9a2ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -680,6 +680,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	u64 tstamp_ready;
+	bool link_up;
 	int err;
 	u8 idx;
 
@@ -695,11 +696,14 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 	if (err)
 		return false;
 
+	/* Drop packets if the link went down */
+	link_up = ptp_port->link_up;
+
 	for_each_set_bit(idx, tx->in_use, tx->len) {
 		struct skb_shared_hwtstamps shhwtstamps = {};
 		u8 phy_idx = idx + tx->offset;
 		u64 raw_tstamp = 0, tstamp;
-		bool drop_ts = false;
+		bool drop_ts = !link_up;
 		struct sk_buff *skb;
 
 		/* Drop packets which have waited for more than 2 seconds */
@@ -728,7 +732,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 		ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx);
 
 		err = ice_read_phy_tstamp(hw, tx->block, phy_idx, &raw_tstamp);
-		if (err)
+		if (err && !drop_ts)
 			continue;
 
 		ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx);
@@ -1770,6 +1774,38 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info,
 }
 
 /**
+ * ice_ptp_gpio_enable_e823 - Enable/disable ancillary features of PHC
+ * @info: the driver's PTP info structure
+ * @rq: The requested feature to change
+ * @on: Enable/disable flag
+ */
+static int ice_ptp_gpio_enable_e823(struct ptp_clock_info *info,
+				    struct ptp_clock_request *rq, int on)
+{
+	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_perout_channel clk_cfg = {0};
+	int err;
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_PPS:
+		clk_cfg.gpio_pin = PPS_PIN_INDEX;
+		clk_cfg.period = NSEC_PER_SEC;
+		clk_cfg.ena = !!on;
+
+		err = ice_ptp_cfg_clkout(pf, PPS_CLK_GEN_CHAN, &clk_cfg, true);
+		break;
+	case PTP_CLK_REQ_EXTTS:
+		err = ice_ptp_cfg_extts(pf, !!on, rq->extts.index,
+					TIME_SYNC_PIN_INDEX, rq->extts.flags);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+/**
  * ice_ptp_gettimex64 - Get the time of the clock
  * @info: the driver's PTP info structure
  * @ts: timespec64 structure to hold the current time value
@@ -2221,6 +2257,19 @@ ice_ptp_setup_pins_e810(struct ice_pf *pf, struct ptp_clock_info *info)
 }
 
 /**
+ * ice_ptp_setup_pins_e823 - Setup PTP pins in sysfs
+ * @pf: pointer to the PF instance
+ * @info: PTP clock capabilities
+ */
+static void
+ice_ptp_setup_pins_e823(struct ice_pf *pf, struct ptp_clock_info *info)
+{
+	info->pps = 1;
+	info->n_per_out = 0;
+	info->n_ext_ts = 1;
+}
+
+/**
  * ice_ptp_set_funcs_e822 - Set specialized functions for E822 support
  * @pf: Board private structure
  * @info: PTP info to fill
@@ -2258,6 +2307,23 @@ ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info)
 }
 
 /**
+ * ice_ptp_set_funcs_e823 - Set specialized functions for E823 support
+ * @pf: Board private structure
+ * @info: PTP info to fill
+ *
+ * Assign functions to the PTP capabiltiies structure for E823 devices.
+ * Functions which operate across all device families should be set directly
+ * in ice_ptp_set_caps. Only add functions here which are distinct for e823
+ * devices.
+ */
+static void
+ice_ptp_set_funcs_e823(struct ice_pf *pf, struct ptp_clock_info *info)
+{
+	info->enable = ice_ptp_gpio_enable_e823;
+	ice_ptp_setup_pins_e823(pf, info);
+}
+
+/**
  * ice_ptp_set_caps - Set PTP capabilities
  * @pf: Board private structure
  */
@@ -2269,7 +2335,7 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	snprintf(info->name, sizeof(info->name) - 1, "%s-%s-clk",
 		 dev_driver_string(dev), dev_name(dev));
 	info->owner = THIS_MODULE;
-	info->max_adj = 999999999;
+	info->max_adj = 100000000;
 	info->adjtime = ice_ptp_adjtime;
 	info->adjfine = ice_ptp_adjfine;
 	info->gettimex64 = ice_ptp_gettimex64;
@@ -2277,6 +2343,8 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 
 	if (ice_is_e810(&pf->hw))
 		ice_ptp_set_funcs_e810(pf, info);
+	else if (ice_is_e823(&pf->hw))
+		ice_ptp_set_funcs_e823(pf, info);
 	else
 		ice_ptp_set_funcs_e822(pf, info);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 6d08b397df2a..4eca8d195ef0 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1063,7 +1063,6 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 	*num_nodes_added = 0;
 	while (*num_nodes_added < num_nodes) {
 		u16 max_child_nodes, num_added = 0;
-		/* cppcheck-suppress unusedVariable */
 		u32 temp;
 
 		status = ice_sched_add_nodes_to_hw_layer(pi, tc_node, parent,
@@ -1655,12 +1654,13 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 	u32 first_node_teid;
 	u16 num_added = 0;
 	u8 i, qgl, vsil;
-	int status;
 
 	qgl = ice_sched_get_qgrp_layer(hw);
 	vsil = ice_sched_get_vsi_layer(hw);
 	parent = ice_sched_get_vsi_node(pi, tc_node, vsi_handle);
 	for (i = vsil + 1; i <= qgl; i++) {
+		int status;
+
 		if (!parent)
 			return -EIO;
 
@@ -1756,13 +1756,14 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
 	u32 first_node_teid;
 	u16 num_added = 0;
 	u8 i, vsil;
-	int status;
 
 	if (!pi)
 		return -EINVAL;
 
 	vsil = ice_sched_get_vsi_layer(pi->hw);
 	for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) {
+		int status;
+
 		status = ice_sched_add_nodes_to_layer(pi, tc_node, parent,
 						      i, num_nodes[i],
 						      &first_node_teid,
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 3ba1408c56a9..96a64c25e2ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -41,21 +41,6 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 }
 
 /**
- * ice_vf_vsi_release - invalidate the VF's VSI after freeing it
- * @vf: invalidate this VF's VSI after freeing it
- */
-static void ice_vf_vsi_release(struct ice_vf *vf)
-{
-	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
-
-	if (WARN_ON(!vsi))
-		return;
-
-	ice_vsi_release(vsi);
-	ice_vf_invalidate_vsi(vf);
-}
-
-/**
  * ice_free_vf_res - Free a VF's resources
  * @vf: pointer to the VF info
  */
@@ -248,11 +233,16 @@ void ice_free_vfs(struct ice_pf *pf)
  */
 static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf)
 {
-	struct ice_port_info *pi = ice_vf_get_port_info(vf);
+	struct ice_vsi_cfg_params params = {};
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
-	vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf, NULL);
+	params.type = ICE_VSI_VF;
+	params.pi = ice_vf_get_port_info(vf);
+	params.vf = vf;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	vsi = ice_vsi_setup(pf, &params);
 
 	if (!vsi) {
 		dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n");
@@ -583,51 +573,19 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
  */
 static int ice_init_vf_vsi_res(struct ice_vf *vf)
 {
-	struct ice_vsi_vlan_ops *vlan_ops;
 	struct ice_pf *pf = vf->pf;
-	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
-	struct device *dev;
 	int err;
 
 	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
 
-	dev = ice_pf_to_dev(pf);
 	vsi = ice_vf_vsi_setup(vf);
 	if (!vsi)
 		return -ENOMEM;
 
-	err = ice_vsi_add_vlan_zero(vsi);
-	if (err) {
-		dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n",
-			 vf->vf_id);
-		goto release_vsi;
-	}
-
-	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
-	err = vlan_ops->ena_rx_filtering(vsi);
-	if (err) {
-		dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n",
-			 vf->vf_id);
-		goto release_vsi;
-	}
-
-	eth_broadcast_addr(broadcast);
-	err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
-	if (err) {
-		dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n",
-			vf->vf_id, err);
-		goto release_vsi;
-	}
-
-	err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk);
-	if (err) {
-		dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n",
-			 vf->vf_id);
+	err = ice_vf_init_host_cfg(vf, vsi);
+	if (err)
 		goto release_vsi;
-	}
-
-	vf->num_mac = 1;
 
 	return 0;
 
@@ -697,6 +655,21 @@ static void ice_sriov_free_vf(struct ice_vf *vf)
 }
 
 /**
+ * ice_sriov_clear_reset_state - clears VF Reset status register
+ * @vf: the vf to configure
+ */
+static void ice_sriov_clear_reset_state(struct ice_vf *vf)
+{
+	struct ice_hw *hw = &vf->pf->hw;
+
+	/* Clear the reset status register so that VF immediately sees that
+	 * the device is resetting, even if hardware hasn't yet gotten around
+	 * to clearing VFGEN_RSTAT for us.
+	 */
+	wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_INPROGRESS);
+}
+
+/**
  * ice_sriov_clear_mbx_register - clears SRIOV VF's mailbox registers
  * @vf: the vf to configure
  */
@@ -799,23 +772,19 @@ static void ice_sriov_clear_reset_trigger(struct ice_vf *vf)
 }
 
 /**
- * ice_sriov_vsi_rebuild - release and rebuild VF's VSI
- * @vf: VF to release and setup the VSI for
+ * ice_sriov_create_vsi - Create a new VSI for a VF
+ * @vf: VF to create the VSI for
  *
- * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF
- * configuration change, etc.).
+ * This is called by ice_vf_recreate_vsi to create the new VSI after the old
+ * VSI has been released.
  */
-static int ice_sriov_vsi_rebuild(struct ice_vf *vf)
+static int ice_sriov_create_vsi(struct ice_vf *vf)
 {
-	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
 
-	ice_vf_vsi_release(vf);
-	if (!ice_vf_vsi_setup(vf)) {
-		dev_err(ice_pf_to_dev(pf),
-			"Failed to release and setup the VF%u's VSI\n",
-			vf->vf_id);
+	vsi = ice_vf_vsi_setup(vf);
+	if (!vsi)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
@@ -826,8 +795,6 @@ static int ice_sriov_vsi_rebuild(struct ice_vf *vf)
  */
 static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf)
 {
-	ice_vf_rebuild_host_cfg(vf);
-	ice_vf_set_initialized(vf);
 	ice_ena_vf_mappings(vf);
 	wr32(&vf->pf->hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
 }
@@ -835,11 +802,13 @@ static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf)
 static const struct ice_vf_ops ice_sriov_vf_ops = {
 	.reset_type = ICE_VF_RESET,
 	.free = ice_sriov_free_vf,
+	.clear_reset_state = ice_sriov_clear_reset_state,
 	.clear_mbx_register = ice_sriov_clear_mbx_register,
 	.trigger_reset_register = ice_sriov_trigger_reset_register,
 	.poll_reset_status = ice_sriov_poll_reset_status,
 	.clear_reset_trigger = ice_sriov_clear_reset_trigger,
-	.vsi_rebuild = ice_sriov_vsi_rebuild,
+	.irq_close = NULL,
+	.create_vsi = ice_sriov_create_vsi,
 	.post_vsi_rebuild = ice_sriov_post_vsi_rebuild,
 };
 
@@ -879,21 +848,9 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
 		/* set sriov vf ops for VFs created during SRIOV flow */
 		vf->vf_ops = &ice_sriov_vf_ops;
 
-		vf->vf_sw_id = pf->first_sw;
-		/* assign default capabilities */
-		vf->spoofchk = true;
-		vf->num_vf_qs = pf->vfs.num_qps_per;
-		ice_vc_set_default_allowlist(vf);
-
-		/* ctrl_vsi_idx will be set to a valid value only when VF
-		 * creates its first fdir rule.
-		 */
-		ice_vf_ctrl_invalidate_vsi(vf);
-		ice_vf_fdir_init(vf);
-
-		ice_virtchnl_set_dflt_ops(vf);
+		ice_initialize_vf_entry(vf);
 
-		mutex_init(&vf->cfg_lock);
+		vf->vf_sw_id = pf->first_sw;
 
 		hash_add_rcu(vfs->table, &vf->entry, vf_id);
 	}
@@ -1285,7 +1242,7 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
 		goto out_put_vf;
 
 	ivi->vf = vf_id;
-	ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr);
+	ether_addr_copy(ivi->mac, vf->hw_lan_addr);
 
 	/* VF configuration for VLAN and applicable QoS */
 	ivi->vlan = ice_vf_get_port_vlan_id(vf);
@@ -1333,8 +1290,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		return -EINVAL;
 
 	/* nothing left to do, unicast MAC already set */
-	if (ether_addr_equal(vf->dev_lan_addr.addr, mac) &&
-	    ether_addr_equal(vf->hw_lan_addr.addr, mac)) {
+	if (ether_addr_equal(vf->dev_lan_addr, mac) &&
+	    ether_addr_equal(vf->hw_lan_addr, mac)) {
 		ret = 0;
 		goto out_put_vf;
 	}
@@ -1348,8 +1305,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	/* VF is notified of its new MAC via the PF's response to the
 	 * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset
 	 */
-	ether_addr_copy(vf->dev_lan_addr.addr, mac);
-	ether_addr_copy(vf->hw_lan_addr.addr, mac);
+	ether_addr_copy(vf->dev_lan_addr, mac);
+	ether_addr_copy(vf->hw_lan_addr, mac);
 	if (is_zero_ether_addr(mac)) {
 		/* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */
 		vf->pf_set_mac = false;
@@ -1750,7 +1707,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
 
 	dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
 		 vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id,
-		 vf->dev_lan_addr.addr,
+		 vf->dev_lan_addr,
 		 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
 			  ? "on" : "off");
 }
@@ -1794,7 +1751,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf)
 
 			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.addr);
+				 vf->dev_lan_addr);
 		}
 	}
 	mutex_unlock(&pf->vfs.table_lock);
@@ -1884,7 +1841,7 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event,
 
 			if (pf_vsi)
 				dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n",
-					 &vf->dev_lan_addr.addr[0],
+					 &vf->dev_lan_addr[0],
 					 pf_vsi->netdev->dev_addr);
 		}
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 95f392ab9670..6b48cbc049c6 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -792,7 +792,7 @@ static struct ice_vsi *
 ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 {
 	struct ice_rx_ring *ring = NULL;
-	struct ice_vsi *ch_vsi = NULL;
+	struct ice_vsi *dest_vsi = NULL;
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u32 tc_class;
@@ -810,7 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 			return ERR_PTR(-EOPNOTSUPP);
 		}
 		/* Locate ADQ VSI depending on hw_tc number */
-		ch_vsi = vsi->tc_map_vsi[tc_class];
+		dest_vsi = vsi->tc_map_vsi[tc_class];
 		break;
 	case ICE_FWD_TO_Q:
 		/* Locate the Rx queue */
@@ -824,7 +824,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 		/* Determine destination VSI even though the action is
 		 * FWD_TO_QUEUE, because QUEUE is associated with VSI
 		 */
-		ch_vsi = tc_fltr->dest_vsi;
+		dest_vsi = tc_fltr->dest_vsi;
 		break;
 	default:
 		dev_err(dev,
@@ -832,13 +832,13 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 			tc_fltr->action.fltr_act);
 		return ERR_PTR(-EINVAL);
 	}
-	/* Must have valid ch_vsi (it could be main VSI or ADQ VSI) */
-	if (!ch_vsi) {
+	/* Must have valid dest_vsi (it could be main VSI or ADQ VSI) */
+	if (!dest_vsi) {
 		dev_err(dev,
 			"Unable to add filter because specified destination VSI doesn't exist\n");
 		return ERR_PTR(-EINVAL);
 	}
-	return ch_vsi;
+	return dest_vsi;
 }
 
 /**
@@ -860,7 +860,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	u32 flags = tc_fltr->flags;
-	struct ice_vsi *ch_vsi;
+	struct ice_vsi *dest_vsi;
 	struct device *dev;
 	u16 lkups_cnt = 0;
 	u16 l4_proto = 0;
@@ -883,9 +883,11 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 	}
 
 	/* validate forwarding action VSI and queue */
-	ch_vsi = ice_tc_forward_action(vsi, tc_fltr);
-	if (IS_ERR(ch_vsi))
-		return PTR_ERR(ch_vsi);
+	if (ice_is_forward_action(tc_fltr->action.fltr_act)) {
+		dest_vsi = ice_tc_forward_action(vsi, tc_fltr);
+		if (IS_ERR(dest_vsi))
+			return PTR_ERR(dest_vsi);
+	}
 
 	lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr);
 	list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC);
@@ -904,7 +906,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 
 	switch (tc_fltr->action.fltr_act) {
 	case ICE_FWD_TO_VSI:
-		rule_info.sw_act.vsi_handle = ch_vsi->idx;
+		rule_info.sw_act.vsi_handle = dest_vsi->idx;
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI;
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.rx = true;
@@ -915,7 +917,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 	case ICE_FWD_TO_Q:
 		/* HW queue number in global space */
 		rule_info.sw_act.fwd_id.q_id = tc_fltr->action.fwd.q.hw_queue;
-		rule_info.sw_act.vsi_handle = ch_vsi->idx;
+		rule_info.sw_act.vsi_handle = dest_vsi->idx;
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_QUEUE;
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.rx = true;
@@ -923,14 +925,15 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			tc_fltr->action.fwd.q.queue,
 			tc_fltr->action.fwd.q.hw_queue, lkups_cnt);
 		break;
-	default:
-		rule_info.sw_act.flag |= ICE_FLTR_TX;
-		/* In case of Tx (LOOKUP_TX), src needs to be src VSI */
-		rule_info.sw_act.src = vsi->idx;
-		/* 'Rx' is false, direction of rule(LOOKUPTRX) */
-		rule_info.rx = false;
+	case ICE_DROP_PACKET:
+		rule_info.sw_act.flag |= ICE_FLTR_RX;
+		rule_info.sw_act.src = hw->pf_id;
+		rule_info.rx = true;
 		rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI;
 		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto exit;
 	}
 
 	ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added);
@@ -953,11 +956,11 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 	tc_fltr->dest_vsi_handle = rule_added.vsi_handle;
 	if (tc_fltr->action.fltr_act == ICE_FWD_TO_VSI ||
 	    tc_fltr->action.fltr_act == ICE_FWD_TO_Q) {
-		tc_fltr->dest_vsi = ch_vsi;
+		tc_fltr->dest_vsi = dest_vsi;
 		/* keep track of advanced switch filter for
 		 * destination VSI
 		 */
-		ch_vsi->num_chnl_fltr++;
+		dest_vsi->num_chnl_fltr++;
 
 		/* keeps track of channel filters for PF VSI */
 		if (vsi->type == ICE_VSI_PF &&
@@ -978,6 +981,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi,
 			tc_fltr->action.fwd.q.hw_queue, rule_added.rid,
 			rule_added.rule_id);
 		break;
+	case ICE_DROP_PACKET:
+		dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x), action is drop, rid %u, rule_id %u\n",
+			lkups_cnt, flags, rule_added.rid, rule_added.rule_id);
+		break;
 	default:
 		break;
 	}
@@ -1712,6 +1719,9 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr,
 	case FLOW_ACTION_RX_QUEUE_MAPPING:
 		/* forward to queue */
 		return ice_tc_forward_to_queue(vsi, fltr, act);
+	case FLOW_ACTION_DROP:
+		fltr->action.fltr_act = ICE_DROP_PACKET;
+		return 0;
 	default:
 		NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported TC action");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index d916d1e92aa3..8d5e22ac7023 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -211,4 +211,14 @@ ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower);
 void ice_replay_tc_fltrs(struct ice_pf *pf);
 bool ice_is_tunnel_supported(struct net_device *dev);
 
+static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act)
+{
+	switch (fltr_act) {
+	case ICE_FWD_TO_VSI:
+	case ICE_FWD_TO_Q:
+		return true;
+	default:
+		return false;
+	}
+}
 #endif /* _ICE_TC_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 086f0b3ab68d..dfd22862e926 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -85,7 +85,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 	td_cmd = ICE_TXD_LAST_DESC_CMD | ICE_TX_DESC_CMD_DUMMY |
 		 ICE_TX_DESC_CMD_RE;
 
-	tx_buf->tx_flags = ICE_TX_FLAGS_DUMMY_PKT;
+	tx_buf->type = ICE_TX_BUF_DUMMY;
 	tx_buf->raw_buf = raw_packet;
 
 	tx_desc->cmd_type_offset_bsz =
@@ -112,27 +112,29 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 static void
 ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 {
-	if (tx_buf->skb) {
-		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
-			devm_kfree(ring->dev, tx_buf->raw_buf);
-		else if (ice_ring_is_xdp(ring))
-			page_frag_free(tx_buf->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buf->skb);
-		if (dma_unmap_len(tx_buf, len))
-			dma_unmap_single(ring->dev,
-					 dma_unmap_addr(tx_buf, dma),
-					 dma_unmap_len(tx_buf, len),
-					 DMA_TO_DEVICE);
-	} else if (dma_unmap_len(tx_buf, len)) {
+	if (dma_unmap_len(tx_buf, len))
 		dma_unmap_page(ring->dev,
 			       dma_unmap_addr(tx_buf, dma),
 			       dma_unmap_len(tx_buf, len),
 			       DMA_TO_DEVICE);
+
+	switch (tx_buf->type) {
+	case ICE_TX_BUF_DUMMY:
+		devm_kfree(ring->dev, tx_buf->raw_buf);
+		break;
+	case ICE_TX_BUF_SKB:
+		dev_kfree_skb_any(tx_buf->skb);
+		break;
+	case ICE_TX_BUF_XDP_TX:
+		page_frag_free(tx_buf->raw_buf);
+		break;
+	case ICE_TX_BUF_XDP_XMIT:
+		xdp_return_frame(tx_buf->xdpf);
+		break;
 	}
 
 	tx_buf->next_to_watch = NULL;
-	tx_buf->skb = NULL;
+	tx_buf->type = ICE_TX_BUF_EMPTY;
 	dma_unmap_len_set(tx_buf, len, 0);
 	/* tx_buf must be completely set up in the transmit path */
 }
@@ -174,8 +176,6 @@ tx_skip_free:
 
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
-	tx_ring->next_dd = ICE_RING_QUARTER(tx_ring) - 1;
-	tx_ring->next_rs = ICE_RING_QUARTER(tx_ring) - 1;
 
 	if (!tx_ring->netdev)
 		return;
@@ -267,7 +267,7 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
 				 DMA_TO_DEVICE);
 
 		/* clear tx_buf data */
-		tx_buf->skb = NULL;
+		tx_buf->type = ICE_TX_BUF_EMPTY;
 		dma_unmap_len_set(tx_buf, len, 0);
 
 		/* unmap remaining buffers */
@@ -382,6 +382,7 @@ err:
  */
 void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
+	struct xdp_buff *xdp = &rx_ring->xdp;
 	struct device *dev = rx_ring->dev;
 	u32 size;
 	u16 i;
@@ -390,16 +391,16 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	if (!rx_ring->rx_buf)
 		return;
 
-	if (rx_ring->skb) {
-		dev_kfree_skb(rx_ring->skb);
-		rx_ring->skb = NULL;
-	}
-
 	if (rx_ring->xsk_pool) {
 		ice_xsk_clean_rx_ring(rx_ring);
 		goto rx_skip_free;
 	}
 
+	if (xdp->data) {
+		xdp_return_buff(xdp);
+		xdp->data = NULL;
+	}
+
 	/* Free all the Rx ring sk_buffs */
 	for (i = 0; i < rx_ring->count; i++) {
 		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
@@ -437,6 +438,7 @@ rx_skip_free:
 
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
+	rx_ring->first_desc = 0;
 	rx_ring->next_to_use = 0;
 }
 
@@ -506,6 +508,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 
 	rx_ring->next_to_use = 0;
 	rx_ring->next_to_clean = 0;
+	rx_ring->first_desc = 0;
 
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
@@ -523,8 +526,16 @@ err:
 	return -ENOMEM;
 }
 
+/**
+ * ice_rx_frame_truesize
+ * @rx_ring: ptr to Rx ring
+ * @size: size
+ *
+ * calculate the truesize with taking into the account PAGE_SIZE of
+ * underlying arch
+ */
 static unsigned int
-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused size)
+ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
 {
 	unsigned int truesize;
 
@@ -545,34 +556,39 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused s
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @rx_buf: Rx buffer to store the XDP action
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static int
+static void
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	    struct ice_rx_buf *rx_buf)
 {
-	int err;
+	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
 
+	if (!xdp_prog)
+		goto exit;
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
-		return ICE_XDP_PASS;
+		break;
 	case XDP_TX:
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
-		err = ice_xmit_xdp_ring(xdp->data, xdp->data_end - xdp->data, xdp_ring);
+		ret = __ice_xmit_xdp_ring(xdp, xdp_ring, false);
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_unlock(&xdp_ring->tx_lock);
-		if (err == ICE_XDP_CONSUMED)
+		if (ret == ICE_XDP_CONSUMED)
 			goto out_failure;
-		return err;
+		break;
 	case XDP_REDIRECT:
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		if (err)
+		if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))
 			goto out_failure;
-		return ICE_XDP_REDIR;
+		ret = ICE_XDP_REDIR;
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
@@ -581,8 +597,31 @@ out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
-		return ICE_XDP_CONSUMED;
+		ret = ICE_XDP_CONSUMED;
 	}
+exit:
+	rx_buf->act = ret;
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		ice_set_rx_bufs_act(xdp, rx_ring, ret);
+}
+
+/**
+ * ice_xmit_xdp_ring - submit frame to XDP ring for transmission
+ * @xdpf: XDP frame that will be converted to XDP buff
+ * @xdp_ring: XDP ring for transmission
+ */
+static int ice_xmit_xdp_ring(const struct xdp_frame *xdpf,
+			     struct ice_tx_ring *xdp_ring)
+{
+	struct xdp_buff xdp;
+
+	xdp.data_hard_start = (void *)xdpf;
+	xdp.data = xdpf->data;
+	xdp.data_end = xdp.data + xdpf->len;
+	xdp.frame_sz = xdpf->frame_sz;
+	xdp.flags = xdpf->flags;
+
+	return __ice_xmit_xdp_ring(&xdp, xdp_ring, true);
 }
 
 /**
@@ -605,6 +644,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	unsigned int queue_index = smp_processor_id();
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *xdp_ring;
+	struct ice_tx_buf *tx_buf;
 	int nxmit = 0, i;
 
 	if (test_bit(ICE_VSI_DOWN, vsi->state))
@@ -627,16 +667,18 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdp_ring = vsi->xdp_rings[queue_index];
 	}
 
+	tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];
 	for (i = 0; i < n; i++) {
-		struct xdp_frame *xdpf = frames[i];
+		const struct xdp_frame *xdpf = frames[i];
 		int err;
 
-		err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
+		err = ice_xmit_xdp_ring(xdpf, xdp_ring);
 		if (err != ICE_XDP_TX)
 			break;
 		nxmit++;
 	}
 
+	tx_buf->rs_idx = ice_set_rs_bit(xdp_ring);
 	if (unlikely(flags & XDP_XMIT_FLUSH))
 		ice_xdp_ring_update_tail(xdp_ring);
 
@@ -706,7 +748,7 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
  * buffers. Then bump tail at most one time. Grouping like this lets us avoid
  * multiple tail writes per call.
  */
-bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 cleaned_count)
+bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 {
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
@@ -783,7 +825,6 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
 /**
  * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
  * @rx_buf: buffer containing the page
- * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call
  *
  * If page is reusable, we have a green light for calling ice_reuse_rx_page,
  * which will assign the current buffer to the buffer that next_to_alloc is
@@ -791,7 +832,7 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
  * page freed
  */
 static bool
-ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt)
+ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
 {
 	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
 	struct page *page = rx_buf->page;
@@ -802,7 +843,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt)
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
+	if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
 		return false;
 #else
 #define ICE_LAST_OFFSET \
@@ -824,33 +865,44 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt)
 }
 
 /**
- * ice_add_rx_frag - Add contents of Rx buffer to sk_buff as a frag
+ * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag
  * @rx_ring: Rx descriptor ring to transact packets on
+ * @xdp: xdp buff to place the data into
  * @rx_buf: buffer containing page to add
- * @skb: sk_buff to place the data into
  * @size: packet length from rx_desc
  *
- * This function will add the data contained in rx_buf->page to the skb.
- * It will just attach the page as a frag to the skb.
- * The function will then update the page offset.
+ * This function will add the data contained in rx_buf->page to the xdp buf.
+ * It will just attach the page as a frag.
  */
-static void
-ice_add_rx_frag(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-		struct sk_buff *skb, unsigned int size)
+static int
+ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+		 struct ice_rx_buf *rx_buf, const unsigned int size)
 {
-#if (PAGE_SIZE >= 8192)
-	unsigned int truesize = SKB_DATA_ALIGN(size + rx_ring->rx_offset);
-#else
-	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#endif
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!size)
-		return;
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
-			rx_buf->page_offset, size, truesize);
+		return 0;
+
+	if (!xdp_buff_has_frags(xdp)) {
+		sinfo->nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		xdp_buff_set_frags_flag(xdp);
+	}
 
-	/* page is being used so we must update the page offset */
-	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
+		if (unlikely(xdp_buff_has_frags(xdp)))
+			ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+		return -ENOMEM;
+	}
+
+	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
+				   rx_buf->page_offset, size);
+	sinfo->xdp_frags_size += size;
+
+	if (page_is_pfmemalloc(rx_buf->page))
+		xdp_buff_set_frag_pfmemalloc(xdp);
+
+	return 0;
 }
 
 /**
@@ -886,19 +938,18 @@ ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf)
  * ice_get_rx_buf - 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
- * @rx_buf_pgcnt: rx_buf page refcount
  *
  * This function will pull an Rx buffer from the ring and synchronize it
  * for use by the CPU.
  */
 static struct ice_rx_buf *
 ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
-	       int *rx_buf_pgcnt)
+	       const unsigned int ntc)
 {
 	struct ice_rx_buf *rx_buf;
 
-	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
-	*rx_buf_pgcnt =
+	rx_buf = &rx_ring->rx_buf[ntc];
+	rx_buf->pgcnt =
 #if (PAGE_SIZE < 8192)
 		page_count(rx_buf->page);
 #else
@@ -922,26 +973,25 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 /**
  * ice_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: Rx buffer to pull data from
  * @xdp: xdp_buff pointing to the data
  *
- * This function builds an skb around an existing Rx buffer, taking care
- * to set up the skb correctly and avoid any memcpy overhead.
+ * This function builds an skb around an existing XDP buffer, taking care
+ * to set up the skb correctly and avoid any memcpy overhead. Driver has
+ * already combined frags (if any) to skb_shared_info.
  */
 static struct sk_buff *
-ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-	      struct xdp_buff *xdp)
+ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
 	u8 metasize = xdp->data - xdp->data_meta;
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#else
-	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(xdp->data_end -
-					       xdp->data_hard_start);
-#endif
+	struct skb_shared_info *sinfo = NULL;
+	unsigned int nr_frags;
 	struct sk_buff *skb;
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
+
 	/* Prefetch first cache line of first page. If xdp->data_meta
 	 * is unused, this points exactly as xdp->data, otherwise we
 	 * likely have a consumer accessing first few bytes of meta
@@ -949,7 +999,7 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	 */
 	net_prefetch(xdp->data_meta);
 	/* build an skb around the page buffer */
-	skb = napi_build_skb(xdp->data_hard_start, truesize);
+	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -964,8 +1014,11 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	/* buffer is used by skb, update page_offset */
-	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size,
+					   nr_frags * xdp->frame_sz,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
 
 	return skb;
 }
@@ -981,24 +1034,30 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
  * skb correctly.
  */
 static struct sk_buff *
-ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-		  struct xdp_buff *xdp)
+ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int size = xdp->data_end - xdp->data;
+	struct skb_shared_info *sinfo = NULL;
+	struct ice_rx_buf *rx_buf;
+	unsigned int nr_frags = 0;
 	unsigned int headlen;
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	net_prefetch(xdp->data_meta);
+	net_prefetch(xdp->data);
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       ICE_RX_HDR_SIZE + metasize,
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
+	rx_buf = &rx_ring->rx_buf[rx_ring->first_desc];
 	skb_record_rx_queue(skb, rx_ring->q_index);
 	/* Determine available headroom for copy */
 	headlen = size;
@@ -1006,32 +1065,42 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 		headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta,
-	       ALIGN(headlen + metasize, sizeof(long)));
-
-	if (metasize) {
-		skb_metadata_set(skb, metasize);
-		__skb_pull(skb, metasize);
-	}
+	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
+							 sizeof(long)));
 
 	/* if we exhaust the linear part then add what is left as a frag */
 	size -= headlen;
 	if (size) {
-#if (PAGE_SIZE >= 8192)
-		unsigned int truesize = SKB_DATA_ALIGN(size);
-#else
-		unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#endif
+		/* besides adding here a partial frag, we are going to add
+		 * frags from xdp_buff, make sure there is enough space for
+		 * them
+		 */
+		if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
 		skb_add_rx_frag(skb, 0, rx_buf->page,
-				rx_buf->page_offset + headlen, size, truesize);
-		/* buffer is used by skb, update page_offset */
-		ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+				rx_buf->page_offset + headlen, size,
+				xdp->frame_sz);
 	} else {
-		/* buffer is unused, reset bias back to rx_buf; data was copied
-		 * onto skb's linear part so there's no need for adjusting
-		 * page offset and we can reuse this buffer as-is
+		/* buffer is unused, change the act that should be taken later
+		 * on; data was copied onto skb's linear part so there's no
+		 * need for adjusting page offset and we can reuse this buffer
+		 * as-is
 		 */
-		rx_buf->pagecnt_bias++;
+		rx_buf->act = ICE_SKB_CONSUMED;
+	}
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
+
+		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
+		       sizeof(skb_frag_t) * nr_frags);
+
+		xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags,
+					   sinfo->xdp_frags_size,
+					   nr_frags * xdp->frame_sz,
+					   xdp_buff_is_frag_pfmemalloc(xdp));
 	}
 
 	return skb;
@@ -1041,26 +1110,17 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
  * ice_put_rx_buf - Clean up used buffer and either recycle or free
  * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_buf: Rx buffer to pull data from
- * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect()
  *
- * This function will update next_to_clean and then clean up the contents
- * of the rx_buf. It will either recycle the buffer or unmap it and free
- * the associated resources.
+ * This function will clean up the contents of the rx_buf. It will either
+ * recycle the buffer or unmap it and free the associated resources.
  */
 static void
-ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-	       int rx_buf_pgcnt)
+ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-	u16 ntc = rx_ring->next_to_clean + 1;
-
-	/* fetch, update, and store next to clean */
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-
 	if (!rx_buf)
 		return;
 
-	if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) {
+	if (ice_can_reuse_rx_page(rx_buf)) {
 		/* hand second half of page back to the ring */
 		ice_reuse_rx_page(rx_ring, rx_buf);
 	} else {
@@ -1076,27 +1136,6 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
 }
 
 /**
- * ice_is_non_eop - process handling of non-EOP buffers
- * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- *
- * If the buffer is an EOP buffer, this function exits returning false,
- * otherwise return true indicating that this is in fact a non-EOP buffer.
- */
-static bool
-ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc)
-{
-	/* if we are the last buffer then there is nothing else to do */
-#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)
-	if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF)))
-		return false;
-
-	rx_ring->ring_stats->rx_stats.non_eop_descs++;
-
-	return true;
-}
-
-/**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1110,39 +1149,42 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc)
  */
 int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 {
-	unsigned int total_rx_bytes = 0, total_rx_pkts = 0, frame_sz = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
+	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	unsigned int offset = rx_ring->rx_offset;
+	struct xdp_buff *xdp = &rx_ring->xdp;
 	struct ice_tx_ring *xdp_ring = NULL;
-	unsigned int xdp_res, xdp_xmit = 0;
-	struct sk_buff *skb = rx_ring->skb;
 	struct bpf_prog *xdp_prog = NULL;
-	struct xdp_buff xdp;
+	u32 ntc = rx_ring->next_to_clean;
+	u32 cnt = rx_ring->count;
+	u32 cached_ntc = ntc;
+	u32 xdp_xmit = 0;
+	u32 cached_ntu;
 	bool failure;
+	u32 first;
 
 	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
 #if (PAGE_SIZE < 8192)
-	frame_sz = ice_rx_frame_truesize(rx_ring, 0);
+	xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0);
 #endif
-	xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-	if (xdp_prog)
+	if (xdp_prog) {
 		xdp_ring = rx_ring->xdp_ring;
+		cached_ntu = xdp_ring->next_to_use;
+	}
 
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		struct ice_rx_buf *rx_buf;
-		unsigned char *hard_start;
+		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
-		int rx_buf_pgcnt;
 		u16 vlan_tag = 0;
 		u16 rx_ptype;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
-		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
@@ -1166,8 +1208,8 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			if (rx_desc->wb.rxdid == FDIR_DESC_RXDID &&
 			    ctrl_vsi->vf)
 				ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
-			ice_put_rx_buf(rx_ring, NULL, 0);
-			cleaned_count++;
+			if (++ntc == cnt)
+				ntc = 0;
 			continue;
 		}
 
@@ -1175,65 +1217,56 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			ICE_RX_FLX_DESC_PKT_LEN_M;
 
 		/* retrieve a buffer from the ring */
-		rx_buf = ice_get_rx_buf(rx_ring, size, &rx_buf_pgcnt);
+		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
 
-		if (!size) {
-			xdp.data = NULL;
-			xdp.data_end = NULL;
-			xdp.data_hard_start = NULL;
-			xdp.data_meta = NULL;
-			goto construct_skb;
-		}
+		if (!xdp->data) {
+			void *hard_start;
 
-		hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
-			     offset;
-		xdp_prepare_buff(&xdp, hard_start, offset, size, true);
+			hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
+				     offset;
+			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 #if (PAGE_SIZE > 4096)
-		/* At larger PAGE_SIZE, frame_sz depend on len size */
-		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
+			/* At larger PAGE_SIZE, frame_sz depend on len size */
+			xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size);
 #endif
+			xdp_buff_clear_frags_flag(xdp);
+		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+			break;
+		}
+		if (++ntc == cnt)
+			ntc = 0;
 
-		if (!xdp_prog)
-			goto construct_skb;
+		/* skip if it is NOP desc */
+		if (ice_is_non_eop(rx_ring, rx_desc))
+			continue;
 
-		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog, xdp_ring);
-		if (!xdp_res)
+		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
+		if (rx_buf->act == ICE_XDP_PASS)
 			goto construct_skb;
-		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			xdp_xmit |= xdp_res;
-			ice_rx_buf_adjust_pg_offset(rx_buf, xdp.frame_sz);
-		} else {
-			rx_buf->pagecnt_bias++;
-		}
-		total_rx_bytes += size;
+		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		cleaned_count++;
-		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
+		xdp->data = NULL;
+		rx_ring->first_desc = ntc;
 		continue;
 construct_skb:
-		if (skb) {
-			ice_add_rx_frag(rx_ring, rx_buf, skb, size);
-		} else if (likely(xdp.data)) {
-			if (ice_ring_uses_build_skb(rx_ring))
-				skb = ice_build_skb(rx_ring, rx_buf, &xdp);
-			else
-				skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
-		}
+		if (likely(ice_ring_uses_build_skb(rx_ring)))
+			skb = ice_build_skb(rx_ring, xdp);
+		else
+			skb = ice_construct_skb(rx_ring, xdp);
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
-			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
-			if (rx_buf)
-				rx_buf->pagecnt_bias++;
+			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+			rx_buf->act = ICE_XDP_CONSUMED;
+			if (unlikely(xdp_buff_has_frags(xdp)))
+				ice_set_rx_bufs_act(xdp, rx_ring,
+						    ICE_XDP_CONSUMED);
+			xdp->data = NULL;
+			rx_ring->first_desc = ntc;
 			break;
 		}
-
-		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
-		cleaned_count++;
-
-		/* skip if it is NOP desc */
-		if (ice_is_non_eop(rx_ring, rx_desc))
-			continue;
+		xdp->data = NULL;
+		rx_ring->first_desc = ntc;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
@@ -1245,10 +1278,8 @@ construct_skb:
 		vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
 
 		/* pad the skb if needed, to make a valid ethernet frame */
-		if (eth_skb_pad(skb)) {
-			skb = NULL;
+		if (eth_skb_pad(skb))
 			continue;
-		}
 
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
@@ -1262,18 +1293,34 @@ construct_skb:
 		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */
 		ice_receive_skb(rx_ring, skb, vlan_tag);
-		skb = NULL;
 
 		/* update budget accounting */
 		total_rx_pkts++;
 	}
 
+	first = rx_ring->first_desc;
+	while (cached_ntc != first) {
+		struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
+
+		if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+			xdp_xmit |= buf->act;
+		} else if (buf->act & ICE_XDP_CONSUMED) {
+			buf->pagecnt_bias++;
+		} else if (buf->act == ICE_XDP_PASS) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+		}
+
+		ice_put_rx_buf(rx_ring, buf);
+		if (++cached_ntc >= cnt)
+			cached_ntc = 0;
+	}
+	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
-	failure = ice_alloc_rx_bufs(rx_ring, cleaned_count);
+	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
 
-	if (xdp_prog)
-		ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
-	rx_ring->skb = skb;
+	if (xdp_xmit)
+		ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu);
 
 	if (rx_ring->ring_stats)
 		ice_update_rx_ring_stats(rx_ring, total_rx_pkts,
@@ -1682,6 +1729,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 				       DMA_TO_DEVICE);
 
 		tx_buf = &tx_ring->tx_buf[i];
+		tx_buf->type = ICE_TX_BUF_FRAG;
 	}
 
 	/* record SW timestamp if HW timestamp is not available */
@@ -1996,7 +2044,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	if (err < 0)
 		return err;
 
-	/* cppcheck-suppress unreadVariable */
 	protocol = vlan_get_protocol(skb);
 
 	if (eth_p_mpls(protocol))
@@ -2033,8 +2080,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		}
 
 		/* reset pointers to inner headers */
-
-		/* cppcheck-suppress unreadVariable */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
 
@@ -2300,6 +2345,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	ice_trace(xmit_frame_ring, tx_ring, skb);
 
+	if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto out_drop;
+
 	count = ice_xmit_desc_count(skb);
 	if (ice_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb))
@@ -2328,6 +2376,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buf[tx_ring->next_to_use];
 	first->skb = skb;
+	first->type = ICE_TX_BUF_SKB;
 	first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
 	first->gso_segs = 1;
 	first->tx_flags = 0;
@@ -2500,11 +2549,11 @@ void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring)
 					 dma_unmap_addr(tx_buf, dma),
 					 dma_unmap_len(tx_buf, len),
 					 DMA_TO_DEVICE);
-		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
+		if (tx_buf->type == ICE_TX_BUF_DUMMY)
 			devm_kfree(tx_ring->dev, tx_buf->raw_buf);
 
 		/* clear next_to_watch to prevent false hangs */
-		tx_buf->raw_buf = NULL;
+		tx_buf->type = ICE_TX_BUF_EMPTY;
 		tx_buf->tx_flags = 0;
 		tx_buf->next_to_watch = NULL;
 		dma_unmap_len_set(tx_buf, len, 0);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 4fd0e5d0a313..fff0efe28373 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -9,10 +9,12 @@
 #define ICE_DFLT_IRQ_WORK	256
 #define ICE_RXBUF_3072		3072
 #define ICE_RXBUF_2048		2048
+#define ICE_RXBUF_1664		1664
 #define ICE_RXBUF_1536		1536
 #define ICE_MAX_CHAINED_RX_BUFS	5
 #define ICE_MAX_BUF_TXD		8
 #define ICE_MIN_TX_LEN		17
+#define ICE_MAX_FRAME_LEGACY_RX 8320
 
 /* The size limit for a transmit buffer in a descriptor is (16K - 1).
  * In order to align with the read requests we will align the value to
@@ -110,15 +112,16 @@ static inline int ice_skb_pad(void)
 	(u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
 	      (R)->next_to_clean - (R)->next_to_use - 1)
 
+#define ICE_RX_DESC_UNUSED(R)	\
+	((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \
+	      (R)->first_desc - (R)->next_to_use - 1)
+
 #define ICE_RING_QUARTER(R) ((R)->count >> 2)
 
 #define ICE_TX_FLAGS_TSO	BIT(0)
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
 #define ICE_TX_FLAGS_SW_VLAN	BIT(2)
-/* ICE_TX_FLAGS_DUMMY_PKT is used to mark dummy packets that should be
- * freed instead of returned like skb packets.
- */
-#define ICE_TX_FLAGS_DUMMY_PKT	BIT(3)
+/* Free, was ICE_TX_FLAGS_DUMMY_PKT */
 #define ICE_TX_FLAGS_TSYN	BIT(4)
 #define ICE_TX_FLAGS_IPV4	BIT(5)
 #define ICE_TX_FLAGS_IPV6	BIT(6)
@@ -134,6 +137,7 @@ static inline int ice_skb_pad(void)
 #define ICE_XDP_TX		BIT(1)
 #define ICE_XDP_REDIR		BIT(2)
 #define ICE_XDP_EXIT		BIT(3)
+#define ICE_SKB_CONSUMED	ICE_XDP_CONSUMED
 
 #define ICE_RX_DMA_ATTR \
 	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
@@ -142,15 +146,44 @@ static inline int ice_skb_pad(void)
 
 #define ICE_TXD_LAST_DESC_CMD (ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)
 
+/**
+ * enum ice_tx_buf_type - type of &ice_tx_buf to act on Tx completion
+ * @ICE_TX_BUF_EMPTY: unused OR XSk frame, no action required
+ * @ICE_TX_BUF_DUMMY: dummy Flow Director packet, unmap and kfree()
+ * @ICE_TX_BUF_FRAG: mapped skb OR &xdp_buff frag, only unmap DMA
+ * @ICE_TX_BUF_SKB: &sk_buff, unmap and consume_skb(), update stats
+ * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free(), stats
+ * @ICE_TX_BUF_XDP_XMIT: &xdp_frame, unmap and xdp_return_frame(), stats
+ * @ICE_TX_BUF_XSK_TX: &xdp_buff on XSk queue, xsk_buff_free(), stats
+ */
+enum ice_tx_buf_type {
+	ICE_TX_BUF_EMPTY	= 0U,
+	ICE_TX_BUF_DUMMY,
+	ICE_TX_BUF_FRAG,
+	ICE_TX_BUF_SKB,
+	ICE_TX_BUF_XDP_TX,
+	ICE_TX_BUF_XDP_XMIT,
+	ICE_TX_BUF_XSK_TX,
+};
+
 struct ice_tx_buf {
-	struct ice_tx_desc *next_to_watch;
 	union {
-		struct sk_buff *skb;
-		void *raw_buf; /* used for XDP */
+		struct ice_tx_desc *next_to_watch;
+		u32 rs_idx;
+	};
+	union {
+		void *raw_buf;		/* used for XDP_TX and FDir rules */
+		struct sk_buff *skb;	/* used for .ndo_start_xmit() */
+		struct xdp_frame *xdpf;	/* used for .ndo_xdp_xmit() */
+		struct xdp_buff *xdp;	/* used for XDP_TX ZC */
 	};
 	unsigned int bytecount;
-	unsigned short gso_segs;
-	u32 tx_flags;
+	union {
+		unsigned int gso_segs;
+		unsigned int nr_frags;	/* used for mbuf XDP */
+	};
+	u32 type:16;			/* &ice_tx_buf_type */
+	u32 tx_flags:16;
 	DEFINE_DMA_UNMAP_LEN(len);
 	DEFINE_DMA_UNMAP_ADDR(dma);
 };
@@ -170,7 +203,9 @@ struct ice_rx_buf {
 	dma_addr_t dma;
 	struct page *page;
 	unsigned int page_offset;
-	u16 pagecnt_bias;
+	unsigned int pgcnt;
+	unsigned int act;
+	unsigned int pagecnt_bias;
 };
 
 struct ice_q_stats {
@@ -273,42 +308,44 @@ struct ice_rx_ring {
 	struct ice_vsi *vsi;		/* Backreference to associated VSI */
 	struct ice_q_vector *q_vector;	/* Backreference to associated vector */
 	u8 __iomem *tail;
+	u16 q_index;			/* Queue number of ring */
+
+	u16 count;			/* Number of descriptors */
+	u16 reg_idx;			/* HW register index of the ring */
+	u16 next_to_alloc;
+	/* CL2 - 2nd cacheline starts here */
 	union {
 		struct ice_rx_buf *rx_buf;
 		struct xdp_buff **xdp_buf;
 	};
-	/* CL2 - 2nd cacheline starts here */
-	struct xdp_rxq_info xdp_rxq;
+	struct xdp_buff xdp;
 	/* CL3 - 3rd cacheline starts here */
-	u16 q_index;			/* Queue number of ring */
-
-	u16 count;			/* Number of descriptors */
-	u16 reg_idx;			/* HW register index of the ring */
+	struct bpf_prog *xdp_prog;
+	u16 rx_offset;
 
 	/* used in interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
-	u16 next_to_alloc;
-	u16 rx_offset;
-	u16 rx_buf_len;
+	u16 first_desc;
 
 	/* stats structs */
 	struct ice_ring_stats *ring_stats;
 
 	struct rcu_head rcu;		/* to avoid race on free */
-	/* CL4 - 3rd cacheline starts here */
+	/* CL4 - 4th cacheline starts here */
 	struct ice_channel *ch;
-	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring *xdp_ring;
 	struct xsk_buff_pool *xsk_pool;
-	struct sk_buff *skb;
 	dma_addr_t dma;			/* physical address of ring */
 	u64 cached_phctime;
+	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 ptp_rx;
 #define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 #define ICE_RX_FLAGS_CRC_STRIP_DIS	BIT(2)
 	u8 flags;
+	/* CL5 - 5th cacheline starts here */
+	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_internodealigned_in_smp;
 
 struct ice_tx_ring {
@@ -326,12 +363,11 @@ struct ice_tx_ring {
 	struct xsk_buff_pool *xsk_pool;
 	u16 next_to_use;
 	u16 next_to_clean;
-	u16 next_rs;
-	u16 next_dd;
 	u16 q_handle;			/* Queue handle per TC */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 count;			/* Number of descriptors */
 	u16 q_index;			/* Queue number of ring */
+	u16 xdp_tx_active;
 	/* stats structs */
 	struct ice_ring_stats *ring_stats;
 	/* CL3 - 3rd cacheline starts here */
@@ -342,7 +378,6 @@ struct ice_tx_ring {
 	spinlock_t tx_lock;
 	u32 txq_teid;			/* Added Tx queue TEID */
 	/* CL4 - 4th cacheline starts here */
-	u16 xdp_tx_active;
 #define ICE_TX_FLAGS_RING_XDP		BIT(0)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG1	BIT(1)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
@@ -431,7 +466,7 @@ static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring)
 
 union ice_32b_rx_flex_desc;
 
-bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, u16 cleaned_count);
+bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count);
 netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev);
 u16
 ice_select_queue(struct net_device *dev, struct sk_buff *skb,
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 25f04266c668..7bc5aa340c7d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -221,128 +221,217 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
 }
 
 /**
+ * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
+ * @dev: device for DMA mapping
+ * @tx_buf: Tx buffer to clean
+ * @bq: XDP bulk flush struct
+ */
+static void
+ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf,
+		     struct xdp_frame_bulk *bq)
+{
+	dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma),
+			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buf, len, 0);
+
+	switch (tx_buf->type) {
+	case ICE_TX_BUF_XDP_TX:
+		page_frag_free(tx_buf->raw_buf);
+		break;
+	case ICE_TX_BUF_XDP_XMIT:
+		xdp_return_frame_bulk(tx_buf->xdpf, bq);
+		break;
+	}
+
+	tx_buf->type = ICE_TX_BUF_EMPTY;
+}
+
+/**
  * ice_clean_xdp_irq - Reclaim resources after transmit completes on XDP ring
  * @xdp_ring: XDP ring to clean
  */
-static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
 {
-	unsigned int total_bytes = 0, total_pkts = 0;
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
-	u16 ntc = xdp_ring->next_to_clean;
-	struct ice_tx_desc *next_dd_desc;
-	u16 next_dd = xdp_ring->next_dd;
-	struct ice_tx_buf *tx_buf;
-	int i;
+	int total_bytes = 0, total_pkts = 0;
+	struct device *dev = xdp_ring->dev;
+	u32 ntc = xdp_ring->next_to_clean;
+	struct ice_tx_desc *tx_desc;
+	u32 cnt = xdp_ring->count;
+	struct xdp_frame_bulk bq;
+	u32 frags, xdp_tx = 0;
+	u32 ready_frames = 0;
+	u32 idx;
+	u32 ret;
+
+	idx = xdp_ring->tx_buf[ntc].rs_idx;
+	tx_desc = ICE_TX_DESC(xdp_ring, idx);
+	if (tx_desc->cmd_type_offset_bsz &
+	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)) {
+		if (idx >= ntc)
+			ready_frames = idx - ntc + 1;
+		else
+			ready_frames = idx + cnt - ntc + 1;
+	}
 
-	next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd);
-	if (!(next_dd_desc->cmd_type_offset_bsz &
-	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
-		return;
+	if (unlikely(!ready_frames))
+		return 0;
+	ret = ready_frames;
+
+	xdp_frame_bulk_init(&bq);
+	rcu_read_lock(); /* xdp_return_frame_bulk() */
 
-	for (i = 0; i < tx_thresh; i++) {
-		tx_buf = &xdp_ring->tx_buf[ntc];
+	while (ready_frames) {
+		struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc];
+		struct ice_tx_buf *head = tx_buf;
 
+		/* bytecount holds size of head + frags */
 		total_bytes += tx_buf->bytecount;
-		/* normally tx_buf->gso_segs was taken but at this point
-		 * it's always 1 for us
-		 */
+		frags = tx_buf->nr_frags;
 		total_pkts++;
-
-		page_frag_free(tx_buf->raw_buf);
-		dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
-		dma_unmap_len_set(tx_buf, len, 0);
-		tx_buf->raw_buf = NULL;
+		/* count head + frags */
+		ready_frames -= frags + 1;
+		xdp_tx++;
 
 		ntc++;
-		if (ntc >= xdp_ring->count)
+		if (ntc == cnt)
 			ntc = 0;
+
+		for (int i = 0; i < frags; i++) {
+			tx_buf = &xdp_ring->tx_buf[ntc];
+
+			ice_clean_xdp_tx_buf(dev, tx_buf, &bq);
+			ntc++;
+			if (ntc == cnt)
+				ntc = 0;
+		}
+
+		ice_clean_xdp_tx_buf(dev, head, &bq);
 	}
 
-	next_dd_desc->cmd_type_offset_bsz = 0;
-	xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh;
-	if (xdp_ring->next_dd > xdp_ring->count)
-		xdp_ring->next_dd = tx_thresh - 1;
+	xdp_flush_frame_bulk(&bq);
+	rcu_read_unlock();
+
+	tx_desc->cmd_type_offset_bsz = 0;
 	xdp_ring->next_to_clean = ntc;
+	xdp_ring->xdp_tx_active -= xdp_tx;
 	ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes);
+
+	return ret;
 }
 
 /**
- * ice_xmit_xdp_ring - submit single packet to XDP ring for transmission
- * @data: packet data pointer
- * @size: packet data size
+ * __ice_xmit_xdp_ring - submit frame to XDP ring for transmission
+ * @xdp: XDP buffer to be placed onto Tx descriptors
  * @xdp_ring: XDP ring for transmission
+ * @frame: whether this comes from .ndo_xdp_xmit()
  */
-int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
+int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring,
+			bool frame)
 {
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
-	u16 i = xdp_ring->next_to_use;
+	struct skb_shared_info *sinfo = NULL;
+	u32 size = xdp->data_end - xdp->data;
+	struct device *dev = xdp_ring->dev;
+	u32 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
+	struct ice_tx_buf *tx_head;
 	struct ice_tx_buf *tx_buf;
-	dma_addr_t dma;
+	u32 cnt = xdp_ring->count;
+	void *data = xdp->data;
+	u32 nr_frags = 0;
+	u32 free_space;
+	u32 frag = 0;
+
+	free_space = ICE_DESC_UNUSED(xdp_ring);
+	if (free_space < ICE_RING_QUARTER(xdp_ring))
+		free_space += ice_clean_xdp_irq(xdp_ring);
+
+	if (unlikely(!free_space))
+		goto busy;
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+		if (free_space < nr_frags + 1)
+			goto busy;
+	}
 
-	if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh)
-		ice_clean_xdp_irq(xdp_ring);
+	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+	tx_head = &xdp_ring->tx_buf[ntu];
+	tx_buf = tx_head;
 
-	if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) {
-		xdp_ring->ring_stats->tx_stats.tx_busy++;
-		return ICE_XDP_CONSUMED;
-	}
+	for (;;) {
+		dma_addr_t dma;
 
-	dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
-	if (dma_mapping_error(xdp_ring->dev, dma))
-		return ICE_XDP_CONSUMED;
+		dma = dma_map_single(dev, data, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma))
+			goto dma_unmap;
 
-	tx_buf = &xdp_ring->tx_buf[i];
-	tx_buf->bytecount = size;
-	tx_buf->gso_segs = 1;
-	tx_buf->raw_buf = data;
+		/* record length, and DMA address */
+		dma_unmap_len_set(tx_buf, len, size);
+		dma_unmap_addr_set(tx_buf, dma, dma);
 
-	/* record length, and DMA address */
-	dma_unmap_len_set(tx_buf, len, size);
-	dma_unmap_addr_set(tx_buf, dma, dma);
+		if (frame) {
+			tx_buf->type = ICE_TX_BUF_FRAG;
+		} else {
+			tx_buf->type = ICE_TX_BUF_XDP_TX;
+			tx_buf->raw_buf = data;
+		}
 
-	tx_desc = ICE_TX_DESC(xdp_ring, i);
-	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0,
-						      size, 0);
+		tx_desc->buf_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
 
-	xdp_ring->xdp_tx_active++;
-	i++;
-	if (i == xdp_ring->count) {
-		i = 0;
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs = tx_thresh - 1;
+		ntu++;
+		if (ntu == cnt)
+			ntu = 0;
+
+		if (frag == nr_frags)
+			break;
+
+		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+		tx_buf = &xdp_ring->tx_buf[ntu];
+
+		data = skb_frag_address(&sinfo->frags[frag]);
+		size = skb_frag_size(&sinfo->frags[frag]);
+		frag++;
 	}
-	xdp_ring->next_to_use = i;
 
-	if (i > xdp_ring->next_rs) {
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs += tx_thresh;
+	/* store info about bytecount and frag count in first desc */
+	tx_head->bytecount = xdp_get_buff_len(xdp);
+	tx_head->nr_frags = nr_frags;
+
+	if (frame) {
+		tx_head->type = ICE_TX_BUF_XDP_XMIT;
+		tx_head->xdpf = xdp->data_hard_start;
 	}
 
+	/* update last descriptor from a frame with EOP */
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S);
+
+	xdp_ring->xdp_tx_active++;
+	xdp_ring->next_to_use = ntu;
+
 	return ICE_XDP_TX;
-}
 
-/**
- * ice_xmit_xdp_buff - convert an XDP buffer to an XDP frame and send it
- * @xdp: XDP buffer
- * @xdp_ring: XDP Tx ring
- *
- * Returns negative on failure, 0 on success.
- */
-int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring)
-{
-	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
+dma_unmap:
+	for (;;) {
+		tx_buf = &xdp_ring->tx_buf[ntu];
+		dma_unmap_page(dev, dma_unmap_addr(tx_buf, dma),
+			       dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buf, len, 0);
+		if (tx_buf == tx_head)
+			break;
+
+		if (!ntu)
+			ntu += cnt;
+		ntu--;
+	}
+	return ICE_XDP_CONSUMED;
 
-	if (unlikely(!xdpf))
-		return ICE_XDP_CONSUMED;
+busy:
+	xdp_ring->ring_stats->tx_stats.tx_busy++;
 
-	return ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
+	return ICE_XDP_CONSUMED;
 }
 
 /**
@@ -354,14 +443,21 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring)
  * should be called when a batch of packets has been processed in the
  * napi loop.
  */
-void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res)
+void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
+			 u32 first_idx)
 {
+	struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[first_idx];
+
 	if (xdp_res & ICE_XDP_REDIR)
 		xdp_do_flush_map();
 
 	if (xdp_res & ICE_XDP_TX) {
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
+		/* store index of descriptor with RS bit set in the first
+		 * ice_tx_buf of given NAPI batch
+		 */
+		tx_buf->rs_idx = ice_set_rs_bit(xdp_ring);
 		ice_xdp_ring_update_tail(xdp_ring);
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_unlock(&xdp_ring->tx_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index c7d2954dc9ea..115969ecdf7b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,6 +6,36 @@
 #include "ice.h"
 
 /**
+ * ice_set_rx_bufs_act - propagate Rx buffer action to frags
+ * @xdp: XDP buffer representing frame (linear and frags part)
+ * @rx_ring: Rx ring struct
+ * act: action to store onto Rx buffers related to XDP buffer parts
+ *
+ * Set action that should be taken before putting Rx buffer from first frag
+ * to one before last. Last one is handled by caller of this function as it
+ * is the EOP frag that is currently being processed. This function is
+ * supposed to be called only when XDP buffer contains frags.
+ */
+static inline void
+ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
+		    const unsigned int act)
+{
+	const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 first = rx_ring->first_desc;
+	u32 nr_frags = sinfo->nr_frags;
+	u32 cnt = rx_ring->count;
+	struct ice_rx_buf *buf;
+
+	for (int i = 0; i < nr_frags; i++) {
+		buf = &rx_ring->rx_buf[first];
+		buf->act = act;
+
+		if (++first == cnt)
+			first = 0;
+	}
+}
+
+/**
  * ice_test_staterr - tests bits in Rx descriptor status and error fields
  * @status_err_n: Rx descriptor status_error0 or status_error1 bits
  * @stat_err_bits: value to mask
@@ -21,6 +51,28 @@ ice_test_staterr(__le16 status_err_n, const u16 stat_err_bits)
 	return !!(status_err_n & cpu_to_le16(stat_err_bits));
 }
 
+/**
+ * ice_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ *
+ * If the buffer is an EOP buffer, this function exits returning false,
+ * otherwise return true indicating that this is in fact a non-EOP buffer.
+ */
+static inline bool
+ice_is_non_eop(const struct ice_rx_ring *rx_ring,
+	       const union ice_32b_rx_flex_desc *rx_desc)
+{
+	/* if we are the last buffer then there is nothing else to do */
+#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)
+	if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF)))
+		return false;
+
+	rx_ring->ring_stats->rx_stats.non_eop_descs++;
+
+	return true;
+}
+
 static inline __le64
 ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 {
@@ -70,9 +122,28 @@ static inline void ice_xdp_ring_update_tail(struct ice_tx_ring *xdp_ring)
 	writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
 }
 
-void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res);
+/**
+ * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU)
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ *
+ * returns index of descriptor that had RS bit produced on
+ */
+static inline u32 ice_set_rs_bit(const struct ice_tx_ring *xdp_ring)
+{
+	u32 rs_idx = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+	struct ice_tx_desc *tx_desc;
+
+	tx_desc = ICE_TX_DESC(xdp_ring, rs_idx);
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
+
+	return rs_idx;
+}
+
+void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, u32 first_idx);
 int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring);
-int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring);
+int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring,
+			bool frame);
 void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val);
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 375eb6493f0f..0e57bd1b85fd 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -237,16 +237,49 @@ static void ice_vf_clear_counters(struct ice_vf *vf)
  */
 static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf)
 {
+	/* Close any IRQ mapping now */
+	if (vf->vf_ops->irq_close)
+		vf->vf_ops->irq_close(vf);
+
 	ice_vf_clear_counters(vf);
 	vf->vf_ops->clear_reset_trigger(vf);
 }
 
 /**
+ * ice_vf_recreate_vsi - Release and re-create the VF's VSI
+ * @vf: VF to recreate the VSI for
+ *
+ * This is only called when a single VF is being reset (i.e. VVF, VFLR, host
+ * VF configuration change, etc)
+ *
+ * It releases and then re-creates a new VSI.
+ */
+static int ice_vf_recreate_vsi(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	int err;
+
+	ice_vf_vsi_release(vf);
+
+	err = vf->vf_ops->create_vsi(vf);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf),
+			"Failed to recreate the VF%u's VSI, error %d\n",
+			vf->vf_id, err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
  * ice_vf_rebuild_vsi - rebuild the VF's VSI
  * @vf: VF to rebuild the VSI for
  *
  * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the
  * host, PFR, CORER, etc.).
+ *
+ * It reprograms the VSI configuration back into hardware.
  */
 static int ice_vf_rebuild_vsi(struct ice_vf *vf)
 {
@@ -256,7 +289,7 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf)
 	if (WARN_ON(!vsi))
 		return -EINVAL;
 
-	if (ice_vsi_rebuild(vsi, true)) {
+	if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT)) {
 		dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n",
 			vf->vf_id);
 		return -EIO;
@@ -271,6 +304,21 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf)
 }
 
 /**
+ * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild
+ * @vf: the VF being reset
+ *
+ * Perform reset tasks which must occur after the VSI has been re-created or
+ * rebuilt during a VF reset.
+ */
+static void ice_vf_post_vsi_rebuild(struct ice_vf *vf)
+{
+	ice_vf_rebuild_host_cfg(vf);
+	ice_vf_set_initialized(vf);
+
+	vf->vf_ops->post_vsi_rebuild(vf);
+}
+
+/**
  * ice_is_any_vf_in_unicast_promisc - check if any VF(s)
  * are in unicast promiscuous mode
  * @pf: PF structure for accessing VF(s)
@@ -495,7 +543,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 
 		ice_vf_pre_vsi_rebuild(vf);
 		ice_vf_rebuild_vsi(vf);
-		vf->vf_ops->post_vsi_rebuild(vf);
+		ice_vf_post_vsi_rebuild(vf);
 
 		mutex_unlock(&vf->cfg_lock);
 	}
@@ -639,14 +687,14 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 
 	ice_vf_pre_vsi_rebuild(vf);
 
-	if (vf->vf_ops->vsi_rebuild(vf)) {
+	if (ice_vf_recreate_vsi(vf)) {
 		dev_err(dev, "Failed to release and setup the VF%u's VSI\n",
 			vf->vf_id);
 		err = -EFAULT;
 		goto out_unlock;
 	}
 
-	vf->vf_ops->post_vsi_rebuild(vf);
+	ice_vf_post_vsi_rebuild(vf);
 	vsi = ice_get_vf_vsi(vf);
 	if (WARN_ON(!vsi)) {
 		err = -EINVAL;
@@ -673,7 +721,7 @@ out_unlock:
  * ice_set_vf_state_qs_dis - Set VF queues state to disabled
  * @vf: pointer to the VF structure
  */
-void ice_set_vf_state_qs_dis(struct ice_vf *vf)
+static void ice_set_vf_state_qs_dis(struct ice_vf *vf)
 {
 	/* Clear Rx/Tx enabled queues flag */
 	bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF);
@@ -681,9 +729,45 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf)
 	clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states);
 }
 
+/**
+ * ice_set_vf_state_dis - Set VF state to disabled
+ * @vf: pointer to the VF structure
+ */
+void ice_set_vf_state_dis(struct ice_vf *vf)
+{
+	ice_set_vf_state_qs_dis(vf);
+	vf->vf_ops->clear_reset_state(vf);
+}
+
 /* Private functions only accessed from other virtualization files */
 
 /**
+ * ice_initialize_vf_entry - Initialize a VF entry
+ * @vf: pointer to the VF structure
+ */
+void ice_initialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct ice_vfs *vfs;
+
+	vfs = &pf->vfs;
+
+	/* 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);
+
+	/* ctrl_vsi_idx will be set to a valid value only when iAVF
+	 * creates its first fdir rule.
+	 */
+	ice_vf_ctrl_invalidate_vsi(vf);
+	ice_vf_fdir_init(vf);
+
+	mutex_init(&vf->cfg_lock);
+}
+
+/**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
  */
@@ -924,18 +1008,18 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
 
 	vf->num_mac++;
 
-	if (is_valid_ether_addr(vf->hw_lan_addr.addr)) {
-		status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr,
+	if (is_valid_ether_addr(vf->hw_lan_addr)) {
+		status = ice_fltr_add_mac(vsi, vf->hw_lan_addr,
 					  ICE_FWD_TO_VSI);
 		if (status) {
 			dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n",
-				&vf->hw_lan_addr.addr[0], vf->vf_id,
+				&vf->hw_lan_addr[0], vf->vf_id,
 				status);
 			return status;
 		}
 		vf->num_mac++;
 
-		ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr);
+		ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr);
 	}
 
 	return 0;
@@ -1115,11 +1199,16 @@ void ice_vf_ctrl_vsi_release(struct ice_vf *vf)
  */
 struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf)
 {
-	struct ice_port_info *pi = ice_vf_get_port_info(vf);
+	struct ice_vsi_cfg_params params = {};
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
-	vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf, NULL);
+	params.type = ICE_VSI_CTRL;
+	params.pi = ice_vf_get_port_info(vf);
+	params.vf = vf;
+	params.flags = ICE_VSI_FLAG_INIT;
+
+	vsi = ice_vsi_setup(pf, &params);
 	if (!vsi) {
 		dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n");
 		ice_vf_ctrl_invalidate_vsi(vf);
@@ -1129,6 +1218,60 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf)
 }
 
 /**
+ * ice_vf_init_host_cfg - Initialize host admin configuration
+ * @vf: VF to initialize
+ * @vsi: the VSI created at initialization
+ *
+ * Initialize the VF host configuration. Called during VF creation to setup
+ * VLAN 0, add the VF VSI broadcast filter, and setup spoof checking. It
+ * should only be called during VF creation.
+ */
+int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi)
+{
+	struct ice_vsi_vlan_ops *vlan_ops;
+	struct ice_pf *pf = vf->pf;
+	u8 broadcast[ETH_ALEN];
+	struct device *dev;
+	int err;
+
+	dev = ice_pf_to_dev(pf);
+
+	err = ice_vsi_add_vlan_zero(vsi);
+	if (err) {
+		dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n",
+			 vf->vf_id);
+		return err;
+	}
+
+	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
+	err = vlan_ops->ena_rx_filtering(vsi);
+	if (err) {
+		dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n",
+			 vf->vf_id);
+		return err;
+	}
+
+	eth_broadcast_addr(broadcast);
+	err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
+	if (err) {
+		dev_err(dev, "Failed to add broadcast MAC filter for VF %d, status %d\n",
+			vf->vf_id, err);
+		return err;
+	}
+
+	vf->num_mac = 1;
+
+	err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk);
+	if (err) {
+		dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n",
+			 vf->vf_id);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
  * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access
  * @vf: VF to remove access to VSI for
  */
@@ -1139,6 +1282,24 @@ void ice_vf_invalidate_vsi(struct ice_vf *vf)
 }
 
 /**
+ * ice_vf_vsi_release - Release the VF VSI and invalidate indexes
+ * @vf: pointer to the VF structure
+ *
+ * Release the VF associated with this VSI and then invalidate the VSI
+ * indexes.
+ */
+void ice_vf_vsi_release(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+
+	if (WARN_ON(!vsi))
+		return;
+
+	ice_vsi_release(vsi);
+	ice_vf_invalidate_vsi(vf);
+}
+
+/**
  * ice_vf_set_initialized - VF is ready for VIRTCHNL communication
  * @vf: VF to set in initialized state
  *
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 52bd9a3816bf..ef30f05b5d02 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -56,11 +56,13 @@ struct ice_mdd_vf_events {
 struct ice_vf_ops {
 	enum ice_disq_rst_src reset_type;
 	void (*free)(struct ice_vf *vf);
+	void (*clear_reset_state)(struct ice_vf *vf);
 	void (*clear_mbx_register)(struct ice_vf *vf);
 	void (*trigger_reset_register)(struct ice_vf *vf, bool is_vflr);
 	bool (*poll_reset_status)(struct ice_vf *vf);
 	void (*clear_reset_trigger)(struct ice_vf *vf);
-	int (*vsi_rebuild)(struct ice_vf *vf);
+	void (*irq_close)(struct ice_vf *vf);
+	int (*create_vsi)(struct ice_vf *vf);
 	void (*post_vsi_rebuild)(struct ice_vf *vf);
 };
 
@@ -96,8 +98,8 @@ struct ice_vf {
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
 	u32 driver_caps;		/* reported by VF driver */
-	struct virtchnl_ether_addr dev_lan_addr;
-	struct virtchnl_ether_addr hw_lan_addr;
+	u8 dev_lan_addr[ETH_ALEN];
+	u8 hw_lan_addr[ETH_ALEN];
 	struct ice_time_mac legacy_last_added_umac;
 	DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF);
 	DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF);
@@ -213,7 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf);
 struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf);
 bool ice_is_vf_disabled(struct ice_vf *vf);
 int ice_check_vf_ready_for_cfg(struct ice_vf *vf);
-void ice_set_vf_state_qs_dis(struct ice_vf *vf);
+void ice_set_vf_state_dis(struct ice_vf *vf);
 bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf);
 void
 ice_vf_get_promisc_masks(struct ice_vf *vf, struct ice_vsi *vsi,
@@ -259,7 +261,7 @@ static inline int ice_check_vf_ready_for_cfg(struct ice_vf *vf)
 	return -EOPNOTSUPP;
 }
 
-static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf)
+static inline void ice_set_vf_state_dis(struct ice_vf *vf)
 {
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 9c8ef2b01f0f..6f3293b793b5 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -23,6 +23,7 @@
 #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files"
 #endif
 
+void ice_initialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);
@@ -35,7 +36,9 @@ void ice_vf_rebuild_host_cfg(struct ice_vf *vf);
 void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf);
 void ice_vf_ctrl_vsi_release(struct ice_vf *vf);
 struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf);
+int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi);
 void ice_vf_invalidate_vsi(struct ice_vf *vf);
+void ice_vf_vsi_release(struct ice_vf *vf);
 void ice_vf_set_initialized(struct ice_vf *vf);
 
 #endif /* _ICE_VF_LIB_PRIVATE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index dab3cd5d300e..e24e3f5017ca 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -507,7 +507,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV;
 	vfres->vsi_res[0].num_queue_pairs = vsi->num_txq;
 	ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
-			vf->hw_lan_addr.addr);
+			vf->hw_lan_addr);
 
 	/* match guest capabilities */
 	vf->driver_caps = vfres->vf_cap_flags;
@@ -1802,10 +1802,10 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
 	 * was correctly specified over VIRTCHNL
 	 */
 	if ((ice_is_vc_addr_legacy(vc_ether_addr) &&
-	     is_zero_ether_addr(vf->hw_lan_addr.addr)) ||
+	     is_zero_ether_addr(vf->hw_lan_addr)) ||
 	    ice_is_vc_addr_primary(vc_ether_addr)) {
-		ether_addr_copy(vf->dev_lan_addr.addr, mac_addr);
-		ether_addr_copy(vf->hw_lan_addr.addr, mac_addr);
+		ether_addr_copy(vf->dev_lan_addr, mac_addr);
+		ether_addr_copy(vf->hw_lan_addr, mac_addr);
 	}
 
 	/* hardware and device MACs are already set, but its possible that the
@@ -1836,7 +1836,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	int ret;
 
 	/* device MAC already added */
-	if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr))
+	if (ether_addr_equal(mac_addr, vf->dev_lan_addr))
 		return 0;
 
 	if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
@@ -1891,8 +1891,8 @@ ice_update_legacy_cached_mac(struct ice_vf *vf,
 	    ice_is_legacy_umac_expired(&vf->legacy_last_added_umac))
 		return;
 
-	ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr);
-	ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr);
+	ether_addr_copy(vf->dev_lan_addr, vf->legacy_last_added_umac.addr);
+	ether_addr_copy(vf->hw_lan_addr, vf->legacy_last_added_umac.addr);
 }
 
 /**
@@ -1906,15 +1906,15 @@ ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
 	u8 *mac_addr = vc_ether_addr->addr;
 
 	if (!is_valid_ether_addr(mac_addr) ||
-	    !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr))
+	    !ether_addr_equal(vf->dev_lan_addr, mac_addr))
 		return;
 
 	/* allow the device MAC to be repopulated in the add flow and don't
-	 * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant
+	 * clear the hardware MAC (i.e. hw_lan_addr) here as that is meant
 	 * to be persistent on VM reboot and across driver unload/load, which
 	 * won't work if we clear the hardware MAC here
 	 */
-	eth_zero_addr(vf->dev_lan_addr.addr);
+	eth_zero_addr(vf->dev_lan_addr);
 
 	ice_update_legacy_cached_mac(vf, vc_ether_addr);
 }
@@ -1934,7 +1934,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
 	int status;
 
 	if (!ice_can_vf_change_mac(vf) &&
-	    ether_addr_equal(vf->dev_lan_addr.addr, mac_addr))
+	    ether_addr_equal(vf->dev_lan_addr, mac_addr))
 		return 0;
 
 	status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
@@ -3733,7 +3733,7 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
 		int result;
 
 		if (!is_unicast_ether_addr(mac_addr) ||
-		    ether_addr_equal(mac_addr, vf->hw_lan_addr.addr))
+		    ether_addr_equal(mac_addr, vf->hw_lan_addr))
 			continue;
 
 		if (vf->pf_set_mac) {
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index c6a58343d81d..e6ef6b303222 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -113,7 +113,7 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id)
 	if (!ice_vc_isvalid_vsi_id(vf, vsi_id))
 		return -EINVAL;
 
-	if (!pf->vsi[vf->lan_vsi_idx])
+	if (!ice_get_vf_vsi(vf))
 		return -EINVAL;
 
 	return 0;
@@ -494,7 +494,7 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun)
 
 	vf_prof = fdir->fdir_prof[flow];
 
-	vf_vsi = pf->vsi[vf->lan_vsi_idx];
+	vf_vsi = ice_get_vf_vsi(vf);
 	if (!vf_vsi) {
 		dev_dbg(dev, "NULL vf %d vsi pointer\n", vf->vf_id);
 		return;
@@ -572,7 +572,7 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow,
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	hw = &pf->hw;
-	vf_vsi = pf->vsi[vf->lan_vsi_idx];
+	vf_vsi = ice_get_vf_vsi(vf);
 	if (!vf_vsi)
 		return -EINVAL;
 
@@ -1205,7 +1205,7 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf,
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	hw = &pf->hw;
-	vsi = pf->vsi[vf->lan_vsi_idx];
+	vsi = ice_get_vf_vsi(vf);
 	if (!vsi) {
 		dev_dbg(dev, "Invalid vsi for VF %d\n", vf->vf_id);
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 374b7f10b549..31565bbafa22 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -598,6 +598,112 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 }
 
 /**
+ * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
+ * @xdp_ring: XDP Tx ring
+ */
+static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+{
+	u16 ntc = xdp_ring->next_to_clean;
+	struct ice_tx_desc *tx_desc;
+	u16 cnt = xdp_ring->count;
+	struct ice_tx_buf *tx_buf;
+	u16 completed_frames = 0;
+	u16 xsk_frames = 0;
+	u16 last_rs;
+	int i;
+
+	last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1;
+	tx_desc = ICE_TX_DESC(xdp_ring, last_rs);
+	if (tx_desc->cmd_type_offset_bsz &
+	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)) {
+		if (last_rs >= ntc)
+			completed_frames = last_rs - ntc + 1;
+		else
+			completed_frames = last_rs + cnt - ntc + 1;
+	}
+
+	if (!completed_frames)
+		return;
+
+	if (likely(!xdp_ring->xdp_tx_active)) {
+		xsk_frames = completed_frames;
+		goto skip;
+	}
+
+	ntc = xdp_ring->next_to_clean;
+	for (i = 0; i < completed_frames; i++) {
+		tx_buf = &xdp_ring->tx_buf[ntc];
+
+		if (tx_buf->type == ICE_TX_BUF_XSK_TX) {
+			tx_buf->type = ICE_TX_BUF_EMPTY;
+			xsk_buff_free(tx_buf->xdp);
+			xdp_ring->xdp_tx_active--;
+		} else {
+			xsk_frames++;
+		}
+
+		ntc++;
+		if (ntc >= xdp_ring->count)
+			ntc = 0;
+	}
+skip:
+	tx_desc->cmd_type_offset_bsz = 0;
+	xdp_ring->next_to_clean += completed_frames;
+	if (xdp_ring->next_to_clean >= cnt)
+		xdp_ring->next_to_clean -= cnt;
+	if (xsk_frames)
+		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+}
+
+/**
+ * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
+ * @xdp: XDP buffer to xmit
+ * @xdp_ring: XDP ring to produce descriptor onto
+ *
+ * note that this function works directly on xdp_buff, no need to convert
+ * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
+ * side will be able to xsk_buff_free() it.
+ *
+ * Returns ICE_XDP_TX for successfully produced desc, ICE_XDP_CONSUMED if there
+ * was not enough space on XDP ring
+ */
+static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
+			      struct ice_tx_ring *xdp_ring)
+{
+	u32 size = xdp->data_end - xdp->data;
+	u32 ntu = xdp_ring->next_to_use;
+	struct ice_tx_desc *tx_desc;
+	struct ice_tx_buf *tx_buf;
+	dma_addr_t dma;
+
+	if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) {
+		ice_clean_xdp_irq_zc(xdp_ring);
+		if (!ICE_DESC_UNUSED(xdp_ring)) {
+			xdp_ring->ring_stats->tx_stats.tx_busy++;
+			return ICE_XDP_CONSUMED;
+		}
+	}
+
+	dma = xsk_buff_xdp_get_dma(xdp);
+	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+
+	tx_buf = &xdp_ring->tx_buf[ntu];
+	tx_buf->xdp = xdp;
+	tx_buf->type = ICE_TX_BUF_XSK_TX;
+	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+	tx_desc->buf_addr = cpu_to_le64(dma);
+	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+						      0, size, 0);
+	xdp_ring->xdp_tx_active++;
+
+	if (++ntu == xdp_ring->count)
+		ntu = 0;
+	xdp_ring->next_to_use = ntu;
+
+	return ICE_XDP_TX;
+}
+
+/**
  * ice_run_xdp_zc - Executes an XDP program in zero-copy path
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
@@ -630,7 +736,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ice_xmit_xdp_buff(xdp, xdp_ring);
+		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
@@ -760,7 +866,7 @@ construct_skb:
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
 		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
 
-	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
+	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
 	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
@@ -776,78 +882,6 @@ construct_skb:
 }
 
 /**
- * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
- * @xdp_ring: XDP Tx ring
- * @tx_buf: Tx buffer to clean
- */
-static void
-ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
-{
-	page_frag_free(tx_buf->raw_buf);
-	xdp_ring->xdp_tx_active--;
-	dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
-			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
-	dma_unmap_len_set(tx_buf, len, 0);
-}
-
-/**
- * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
- * @xdp_ring: XDP Tx ring
- */
-static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
-{
-	u16 ntc = xdp_ring->next_to_clean;
-	struct ice_tx_desc *tx_desc;
-	u16 cnt = xdp_ring->count;
-	struct ice_tx_buf *tx_buf;
-	u16 completed_frames = 0;
-	u16 xsk_frames = 0;
-	u16 last_rs;
-	int i;
-
-	last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1;
-	tx_desc = ICE_TX_DESC(xdp_ring, last_rs);
-	if ((tx_desc->cmd_type_offset_bsz &
-	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) {
-		if (last_rs >= ntc)
-			completed_frames = last_rs - ntc + 1;
-		else
-			completed_frames = last_rs + cnt - ntc + 1;
-	}
-
-	if (!completed_frames)
-		return;
-
-	if (likely(!xdp_ring->xdp_tx_active)) {
-		xsk_frames = completed_frames;
-		goto skip;
-	}
-
-	ntc = xdp_ring->next_to_clean;
-	for (i = 0; i < completed_frames; i++) {
-		tx_buf = &xdp_ring->tx_buf[ntc];
-
-		if (tx_buf->raw_buf) {
-			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
-			tx_buf->raw_buf = NULL;
-		} else {
-			xsk_frames++;
-		}
-
-		ntc++;
-		if (ntc >= xdp_ring->count)
-			ntc = 0;
-	}
-skip:
-	tx_desc->cmd_type_offset_bsz = 0;
-	xdp_ring->next_to_clean += completed_frames;
-	if (xdp_ring->next_to_clean >= cnt)
-		xdp_ring->next_to_clean -= cnt;
-	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
-}
-
-/**
  * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
  * @xdp_ring: XDP ring to produce the HW Tx descriptor on
  * @desc: AF_XDP descriptor to pull the DMA address and length from
@@ -921,20 +955,6 @@ static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *d
 }
 
 /**
- * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU)
- * @xdp_ring: XDP ring to produce the HW Tx descriptors on
- */
-static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring)
-{
-	u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
-	struct ice_tx_desc *tx_desc;
-
-	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
-	tx_desc->cmd_type_offset_bsz |=
-		cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-}
-
-/**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
  *
@@ -1068,12 +1088,12 @@ void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring)
 	while (ntc != ntu) {
 		struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc];
 
-		if (tx_buf->raw_buf)
-			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
-		else
+		if (tx_buf->type == ICE_TX_BUF_XSK_TX) {
+			tx_buf->type = ICE_TX_BUF_EMPTY;
+			xsk_buff_free(tx_buf->xdp);
+		} else {
 			xsk_frames++;
-
-		tx_buf->raw_buf = NULL;
+		}
 
 		ntc++;
 		if (ntc >= xdp_ring->count)