Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Not much excitement - a handful of large patchsets (devmem among them)
  did not make it in time.

  Core & protocols:

   - Use local_lock in addition to local_bh_disable() to protect per-CPU
     resources in networking, a step closer for local_bh_disable() not
     to act as a big lock on PREEMPT_RT

   - Use flex array for netdevice priv area, ensure its cache alignment

   - Add a sysctl knob to allow user to specify a default rto_min at
     socket init time. Bit of a big hammer but multiple companies were
     independently carrying such patch downstream so clearly it's useful

   - Support scheduling transmission of packets based on CLOCK_TAI

   - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned
     off using cpusets

   - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address

   - Allow configuration of multipath hash seed, to both allow
     synchronizing hashing of two routers, and preventing partial
     accidental sync

   - Improve TCP compliance with RFC 9293 for simultaneous connect()

   - Support sending NAT keepalives in IPsec ESP in UDP states.
     Userspace IKE daemon had to do this before, but the kernel can
     better keep track of it

   - Support sending supervision HSR frames with MAC addresses stored in
     ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled

   - Introduce IPPROTO_SMC for selecting SMC when socket is created

   - Allow UDP GSO transmit from devices with no checksum offload

   - openvswitch: add packet sampling via psample, separating the
     sampled traffic from "upcall" packets sent to user space for
     forwarding

   - nf_tables: shrink memory consumption for transaction objects

  Things we sprinkled into general kernel code:

   - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for
     QCA6390)           [ Already merged separately - Linus ]

   - Add IRQ information in sysfs for auxiliary bus

   - Introduce guard definition for local_lock

   - Add aligned flavor of __cacheline_group_{begin, end}() markings for
     grouping fields in structures

  BPF:

   - Notify user space (via epoll) when a struct_ops object is getting
     detached/unregistered

   - Add new kfuncs for a generic, open-coded bits iterator

   - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and
     bpf_list_head

   - Support resilient split BTF which cuts down on duplication and
     makes BTF as compact as possible WRT BTF from modules

   - Add support for dumping kfunc prototypes from BTF which enables
     both detecting as well as dumping compilable prototypes for kfuncs

   - riscv64 BPF JIT improvements in particular to add 12-argument
     support for BPF trampolines and to utilize bpf_prog_pack for the
     latter

   - Add the capability to offload the netfilter flowtable in XDP layer
     through kfuncs

  Driver API:

   - Allow users to configure IRQ tresholds between which automatic IRQ
     moderation can choose

   - Expand Power Sourcing (PoE) status with power, class and failure
     reason. Support setting power limits

   - Track additional RSS contexts in the core, make sure configuration
     changes don't break them

   - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated
     ESP data paths

   - Support updating firmware on SFP modules

  Tests and tooling:

   - mptcp: use net/lib.sh to manage netns

   - TCP-AO and TCP-MD5: replace debug prints used by tests with
     tracepoints

   - openvswitch: make test self-contained (don't depend on OvS CLI
     tools)

  Drivers:

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - increase the max total outstanding PTP TX packets to 4
         - add timestamping statistics support
         - implement netdev_queue_mgmt_ops
         - support new RSS context API
      - Intel (100G, ice, idpf):
         - implement FEC statistics and dumping signal quality indicators
         - support E825C products (with 56Gbps PHYs)
      - nVidia/Mellanox:
         - support HW-GRO
         - mlx4/mlx5: support per-queue statistics via netlink
         - obey the max number of EQs setting in sub-functions
      - AMD/Solarflare:
         - support new RSS context API
      - AMD/Pensando:
         - ionic: rework fix for doorbell miss to lower overhead and
           skip it on new HW
      - Wangxun:
         - txgbe: support Flow Director perfect filters

   - Ethernet NICs consumer, embedded and virtual:
      - Add driver for Tehuti Networks TN40xx chips
      - Add driver for Meta's internal NIC chips
      - Add driver for Ethernet MAC on Airoha EN7581 SoCs
      - Add driver for Renesas Ethernet-TSN devices
      - Google cloud vNIC:
         - flow steering support
      - Microsoft vNIC:
         - support page sizes other than 4KB on ARM64
      - vmware vNIC:
         - support latency measurement (update to version 9)
      - VirtIO net:
         - support for Byte Queue Limits
         - support configuring thresholds for automatic IRQ moderation
         - support for AF_XDP Rx zero-copy
      - Synopsys (stmmac):
         - support for STM32MP13 SoC
         - let platforms select the right PCS implementation
      - TI:
         - icssg-prueth: add multicast filtering support
         - icssg-prueth: enable PTP timestamping and PPS
      - Renesas:
         - ravb: improve Rx performance 30-400% by using page pool,
           theaded NAPI and timer-based IRQ coalescing
         - ravb: add MII support for R-Car V4M
      - Cadence (macb):
         - macb: add ARP support to Wake-On-LAN
      - Cortina:
         - use phylib for RX and TX pause configuration

   - Ethernet switches:
      - nVidia/Mellanox:
         - support configuration of multipath hash seed
         - report more accurate max MTU
         - use page_pool to improve Rx performance
      - MediaTek:
         - mt7530: add support for bridge port isolation
      - Qualcomm:
         - qca8k: add support for bridge port isolation
      - Microchip:
         - lan9371/2: add 100BaseTX PHY support
      - NXP:
         - vsc73xx: implement VLAN operations

   - Ethernet PHYs:
      - aquantia: enable support for aqr115c
      - aquantia: add support for PHY LEDs
      - realtek: add support for rtl8224 2.5Gbps PHY
      - xpcs: add memory-mapped device support
      - add BroadR-Reach link mode and support in Broadcom's PHY driver

   - CAN:
      - add document for ISO 15765-2 protocol support
      - mcp251xfd: workaround for erratum DS80000789E, use timestamps to
        catch when device returns incorrect FIFO status

   - WiFi:
      - mac80211/cfg80211:
         - parse Transmit Power Envelope (TPE) data in mac80211 instead
           of in drivers
         - improvements for 6 GHz regulatory flexibility
         - multi-link improvements
         - support multiple radios per wiphy
         - remove DEAUTH_NEED_MGD_TX_PREP flag
      - Intel (iwlwifi):
         - bump FW API to 91 for BZ/SC devices
         - report 64-bit radiotap timestamp
         - enable P2P low latency by default
         - handle Transmit Power Envelope (TPE) advertised by AP
         - remove support for older FW for new devices
         - fast resume (keeping the device configured)
         - mvm: re-enable Multi-Link Operation (MLO)
         - aggregation (A-MSDU) optimizations
      - MediaTek (mt76):
         - mt7925 Multi-Link Operation (MLO) support
      - Qualcomm (ath10k):
         - LED support for various chipsets
      - Qualcomm (ath12k):
         - remove unsupported Tx monitor handling
         - support channel 2 in 6 GHz band
         - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band
         - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID
           Advertisements (EMA)
         - support dynamic VLAN
         - add panic handler for resetting the firmware state
         - DebugFS support for datapath statistics
         - WCN7850: support for Wake on WLAN
      - Microchip (wilc1000):
         - read MAC address during probe to make it visible to user space
         - suspend/resume improvements
      - TI (wl18xx):
         - support newer firmware versions
      - RealTek (rtw89):
         - preparation for RTL8852BE-VT support
         - Wake on WLAN support for WiFi 6 chips
         - 36-bit PCI DMA support
      - RealTek (rtlwifi):
         - RTL8192DU support
      - Broadcom (brcmfmac):
         - Management Frame Protection support (to enable WPA3)

   - Bluetooth:
      - qualcomm: use the power sequencer for QCA6390
      - btusb: mediatek: add ISO data transmission functions
      - hci_bcm4377: add BCM4388 support
      - btintel: add support for BlazarU core
      - btintel: add support for Whale Peak2
      - btnxpuart: add support for AW693 A1 chipset
      - btnxpuart: add support for IW615 chipset
      - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"

* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits)
  eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering"
  tcp: Replace strncpy() with strscpy()
  wifi: ath12k: fix build vs old compiler
  tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child().
  eth: fbnic: Write the TCAM tables used for RSS control and Rx to host
  eth: fbnic: Add L2 address programming
  eth: fbnic: Add basic Rx handling
  eth: fbnic: Add basic Tx handling
  eth: fbnic: Add link detection
  eth: fbnic: Add initial messaging to notify FW of our presence
  eth: fbnic: Implement Rx queue alloc/start/stop/free
  eth: fbnic: Implement Tx queue alloc/start/stop/free
  eth: fbnic: Allocate a netdevice and napi vectors with queues
  eth: fbnic: Add FW communication mechanism
  eth: fbnic: Add message parsing for FW messages
  eth: fbnic: Add register init to set PCIe/Ethernet device config
  eth: fbnic: Allocate core device specific structures and devlink interface
  eth: fbnic: Add scaffolding for Meta's NIC driver
  PCI: Add Meta Platforms vendor ID
  net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK
  ...

20 files changed, 432 insertions, 166 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index a510bf2cff2f..74f7e27b490f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -33,6 +33,7 @@ config MLXSW_CORE_THERMAL
 config MLXSW_PCI
 	tristate "PCI bus implementation for Mellanox Technologies Switch ASICs"
 	depends on PCI && HAS_IOMEM && MLXSW_CORE
+	select PAGE_POOL
 	default m
 	help
 	  This is PCI bus implementation for Mellanox Technologies Switch ASICs.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 6c06b0592760..294e758f1067 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -513,6 +513,63 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page);
 
+int
+mlxsw_env_set_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
+				    u8 slot_index, u8 module,
+				    const struct ethtool_module_eeprom *page,
+				    struct netlink_ext_ack *extack)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	u32 bytes_written = 0;
+	u16 device_addr;
+	int err;
+
+	if (!mlxsw_env_linecard_is_active(mlxsw_env, slot_index)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot write to EEPROM of a module on an inactive line card");
+		return -EIO;
+	}
+
+	err = mlxsw_env_validate_module_type(mlxsw_core, slot_index, module);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "EEPROM is not equipped on port module type");
+		return err;
+	}
+
+	device_addr = page->offset;
+
+	while (bytes_written < page->length) {
+		char mcia_pl[MLXSW_REG_MCIA_LEN];
+		char eeprom_tmp[128] = {};
+		u8 size;
+
+		size = min_t(u8, page->length - bytes_written,
+			     mlxsw_env->max_eeprom_len);
+
+		mlxsw_reg_mcia_pack(mcia_pl, slot_index, module, page->page,
+				    device_addr + bytes_written, size,
+				    page->i2c_address);
+		mlxsw_reg_mcia_bank_number_set(mcia_pl, page->bank);
+		memcpy(eeprom_tmp, page->data + bytes_written, size);
+		mlxsw_reg_mcia_eeprom_memcpy_to(mcia_pl, eeprom_tmp);
+
+		err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to access module's EEPROM");
+			return err;
+		}
+
+		err = mlxsw_env_mcia_status_process(mcia_pl, extack);
+		if (err)
+			return err;
+
+		bytes_written += size;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_set_module_eeprom_by_page);
+
 static int mlxsw_env_module_reset(struct mlxsw_core *mlxsw_core, u8 slot_index,
 				  u8 module)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
index a197e3ae069c..e4ff17869400 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
@@ -28,6 +28,12 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
 				    const struct ethtool_module_eeprom *page,
 				    struct netlink_ext_ack *extack);
 
+int
+mlxsw_env_set_module_eeprom_by_page(struct mlxsw_core *mlxsw_core,
+				    u8 slot_index, u8 module,
+				    const struct ethtool_module_eeprom *page,
+				    struct netlink_ext_ack *extack);
+
 int mlxsw_env_reset_module(struct net_device *netdev,
 			   struct mlxsw_core *mlxsw_core, u8 slot_index,
 			   u8 module, u32 *flags);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 5c511e1a8efa..d61478c0c632 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -100,6 +100,12 @@ static const struct mlxsw_cooling_states default_cooling_states[] = {
 
 struct mlxsw_thermal;
 
+struct mlxsw_thermal_cooling_device {
+	struct mlxsw_thermal *thermal;
+	struct thermal_cooling_device *cdev;
+	unsigned int idx;
+};
+
 struct mlxsw_thermal_module {
 	struct mlxsw_thermal *parent;
 	struct thermal_zone_device *tzdev;
@@ -123,7 +129,7 @@ struct mlxsw_thermal {
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
 	int polling_delay;
-	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
+	struct mlxsw_thermal_cooling_device cdevs[MLXSW_MFCR_PWMS_MAX];
 	struct thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_cooling_states cooling_states[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_thermal_area line_cards[];
@@ -147,7 +153,7 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 	int i;
 
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i] == cdev)
+		if (thermal->cdevs[i].cdev == cdev)
 			return i;
 
 	/* Allow mlxsw thermal zone binding to an external cooling device */
@@ -352,17 +358,14 @@ static int mlxsw_thermal_get_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long *p_state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int err, idx;
 	u8 duty;
+	int err;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0);
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx, 0);
 	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to query PWM duty\n");
@@ -378,22 +381,19 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int idx;
 	int err;
 
 	if (state > MLXSW_THERMAL_MAX_STATE)
 		return -EINVAL;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
 	/* Normalize the state to the valid speed range. */
 	state = max_t(unsigned long, MLXSW_THERMAL_MIN_STATE, state);
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx,
+			    mlxsw_state_to_duty(state));
 	err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to write PWM duty\n");
@@ -753,17 +753,21 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 	}
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
 		if (pwm_active & BIT(i)) {
+			struct mlxsw_thermal_cooling_device *mlxsw_cdev;
 			struct thermal_cooling_device *cdev;
 
+			mlxsw_cdev = &thermal->cdevs[i];
+			mlxsw_cdev->thermal = thermal;
+			mlxsw_cdev->idx = i;
 			cdev = thermal_cooling_device_register("mlxsw_fan",
-							       thermal,
+							       mlxsw_cdev,
 							       &mlxsw_cooling_ops);
 			if (IS_ERR(cdev)) {
 				err = PTR_ERR(cdev);
 				dev_err(dev, "Failed to register cooling device\n");
 				goto err_thermal_cooling_device_register;
 			}
-			thermal->cdevs[i] = cdev;
+			mlxsw_cdev->cdev = cdev;
 		}
 	}
 
@@ -824,8 +828,7 @@ err_thermal_modules_init:
 err_thermal_zone_device_register:
 err_thermal_cooling_device_register:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i])
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 err_reg_write:
 err_reg_query:
 	kfree(thermal);
@@ -847,12 +850,8 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 		thermal->tzdev = NULL;
 	}
 
-	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
-		if (thermal->cdevs[i]) {
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
-			thermal->cdevs[i] = NULL;
-		}
-	}
+	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 
 	kfree(thermal);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h
index cfafbeb42586..a619a0736bd1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/item.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/item.h
@@ -218,6 +218,10 @@ __mlxsw_item_bit_array_offset(const struct mlxsw_item *item,
 	}
 
 	max_index = (item->size.bytes << 3) / item->element_size - 1;
+	if (WARN_ONCE(index > max_index,
+		      "name=%s,index=%u,max_index=%u\n", item->name, index,
+		      max_index))
+		index = 0;
 	be_index = max_index - index;
 	offset = be_index * item->element_size >> 3;
 	in_byte_index  = index % (BITS_PER_BYTE / item->element_size);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index f0ceb196a6ce..828c65036a4c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -140,6 +140,20 @@ mlxsw_m_get_module_eeprom_by_page(struct net_device *netdev,
 						   page, extack);
 }
 
+static int
+mlxsw_m_set_module_eeprom_by_page(struct net_device *netdev,
+				  const struct ethtool_module_eeprom *page,
+				  struct netlink_ext_ack *extack)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_set_module_eeprom_by_page(core,
+						   mlxsw_m_port->slot_index,
+						   mlxsw_m_port->module,
+						   page, extack);
+}
+
 static int mlxsw_m_reset(struct net_device *netdev, u32 *flags)
 {
 	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
@@ -181,6 +195,7 @@ static const struct ethtool_ops mlxsw_m_port_ethtool_ops = {
 	.get_module_info	= mlxsw_m_get_module_info,
 	.get_module_eeprom	= mlxsw_m_get_module_eeprom,
 	.get_module_eeprom_by_page = mlxsw_m_get_module_eeprom_by_page,
+	.set_module_eeprom_by_page = mlxsw_m_set_module_eeprom_by_page,
 	.reset			= mlxsw_m_reset,
 	.get_module_power_mode	= mlxsw_m_get_module_power_mode,
 	.set_module_power_mode	= mlxsw_m_set_module_power_mode,
@@ -702,8 +717,8 @@ static struct mlxsw_driver mlxsw_m_driver = {
 };
 
 static const struct i2c_device_id mlxsw_m_i2c_id[] = {
-	{ "mlxsw_minimal", 0},
-	{ },
+	{ "mlxsw_minimal" },
+	{ }
 };
 
 static struct i2c_driver mlxsw_m_i2c_driver = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index c0ced4d315f3..060e5b939211 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -13,6 +13,7 @@
 #include <linux/if_vlan.h>
 #include <linux/log2.h>
 #include <linux/string.h>
+#include <net/page_pool/helpers.h>
 
 #include "pci_hw.h"
 #include "pci.h"
@@ -61,15 +62,11 @@ struct mlxsw_pci_mem_item {
 };
 
 struct mlxsw_pci_queue_elem_info {
+	struct page *pages[MLXSW_PCI_WQE_SG_ENTRIES];
 	char *elem; /* pointer to actual dma mapped element mem chunk */
-	union {
-		struct {
-			struct sk_buff *skb;
-		} sdq;
-		struct {
-			struct sk_buff *skb;
-		} rdq;
-	} u;
+	struct {
+		struct sk_buff *skb;
+	} sdq;
 };
 
 struct mlxsw_pci_queue {
@@ -88,10 +85,14 @@ struct mlxsw_pci_queue {
 			enum mlxsw_pci_cqe_v v;
 			struct mlxsw_pci_queue *dq;
 			struct napi_struct napi;
+			struct page_pool *page_pool;
 		} cq;
 		struct {
 			struct tasklet_struct tasklet;
 		} eq;
+		struct {
+			struct mlxsw_pci_queue *cq;
+		} rdq;
 	} u;
 };
 
@@ -110,6 +111,7 @@ struct mlxsw_pci {
 	bool cff_support;
 	enum mlxsw_cmd_mbox_config_profile_lag_mode lag_mode;
 	enum mlxsw_cmd_mbox_config_profile_flood_mode flood_mode;
+	u8 num_sg_entries; /* Number of scatter/gather entries for packets. */
 	struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT];
 	u32 doorbell_offset;
 	struct mlxsw_core *core;
@@ -335,6 +337,29 @@ static void mlxsw_pci_sdq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_sdq(mlxsw_pci->core, q->num);
 }
 
+#define MLXSW_PCI_SKB_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN)
+
+#define MLXSW_PCI_RX_BUF_SW_OVERHEAD		\
+		(MLXSW_PCI_SKB_HEADROOM +	\
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+static void
+mlxsw_pci_wqe_rx_frag_set(struct mlxsw_pci *mlxsw_pci, struct page *page,
+			  char *wqe, int index, size_t frag_len)
+{
+	dma_addr_t mapaddr;
+
+	mapaddr = page_pool_get_dma_addr(page);
+
+	if (index == 0) {
+		mapaddr += MLXSW_PCI_SKB_HEADROOM;
+		frag_len = frag_len - MLXSW_PCI_RX_BUF_SW_OVERHEAD;
+	}
+
+	mlxsw_pci_wqe_address_set(wqe, index, mapaddr);
+	mlxsw_pci_wqe_byte_count_set(wqe, index, frag_len);
+}
+
 static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe,
 				  int index, char *frag_data, size_t frag_len,
 				  int direction)
@@ -364,43 +389,140 @@ static void mlxsw_pci_wqe_frag_unmap(struct mlxsw_pci *mlxsw_pci, char *wqe,
 	dma_unmap_single(&pdev->dev, mapaddr, frag_len, direction);
 }
 
-static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci,
-				   struct mlxsw_pci_queue_elem_info *elem_info,
-				   gfp_t gfp)
+static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[],
+					       u16 byte_count)
 {
-	size_t buf_len = MLXSW_PORT_MAX_MTU;
-	char *wqe = elem_info->elem;
+	unsigned int linear_data_size;
 	struct sk_buff *skb;
-	int err;
+	int page_index = 0;
+	bool linear_only;
+	void *data;
+
+	data = page_address(pages[page_index]);
+	net_prefetch(data);
+
+	skb = napi_build_skb(data, PAGE_SIZE);
+	if (unlikely(!skb))
+		return ERR_PTR(-ENOMEM);
+
+	linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE;
+	linear_data_size = linear_only ? byte_count :
+					 PAGE_SIZE -
+					 MLXSW_PCI_RX_BUF_SW_OVERHEAD;
+
+	skb_reserve(skb, MLXSW_PCI_SKB_HEADROOM);
+	skb_put(skb, linear_data_size);
+
+	if (linear_only)
+		return skb;
+
+	byte_count -= linear_data_size;
+	page_index++;
+
+	while (byte_count > 0) {
+		unsigned int frag_size;
+		struct page *page;
+
+		page = pages[page_index];
+		frag_size = min(byte_count, PAGE_SIZE);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				page, 0, frag_size, PAGE_SIZE);
+		byte_count -= frag_size;
+		page_index++;
+	}
 
-	skb = __netdev_alloc_skb_ip_align(NULL, buf_len, gfp);
-	if (!skb)
+	return skb;
+}
+
+static int mlxsw_pci_rdq_page_alloc(struct mlxsw_pci_queue *q,
+				    struct mlxsw_pci_queue_elem_info *elem_info,
+				    int index)
+{
+	struct mlxsw_pci_queue *cq = q->u.rdq.cq;
+	char *wqe = elem_info->elem;
+	struct page *page;
+
+	page = page_pool_dev_alloc_pages(cq->u.cq.page_pool);
+	if (unlikely(!page))
 		return -ENOMEM;
 
-	err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data,
-				     buf_len, DMA_FROM_DEVICE);
-	if (err)
-		goto err_frag_map;
+	mlxsw_pci_wqe_rx_frag_set(q->pci, page, wqe, index, PAGE_SIZE);
+	elem_info->pages[index] = page;
+	return 0;
+}
+
+static void mlxsw_pci_rdq_page_free(struct mlxsw_pci_queue *q,
+				    struct mlxsw_pci_queue_elem_info *elem_info,
+				    int index)
+{
+	struct mlxsw_pci_queue *cq = q->u.rdq.cq;
+
+	page_pool_put_page(cq->u.cq.page_pool, elem_info->pages[index], -1,
+			   false);
+}
+
+static u8 mlxsw_pci_num_sg_entries_get(u16 byte_count)
+{
+	return DIV_ROUND_UP(byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD,
+			    PAGE_SIZE);
+}
+
+static int
+mlxsw_pci_elem_info_pages_ref_store(const struct mlxsw_pci_queue *q,
+				    const struct mlxsw_pci_queue_elem_info *el,
+				    u16 byte_count, struct page *pages[],
+				    u8 *p_num_sg_entries)
+{
+	u8 num_sg_entries;
+	int i;
+
+	num_sg_entries = mlxsw_pci_num_sg_entries_get(byte_count);
+	if (WARN_ON_ONCE(num_sg_entries > q->pci->num_sg_entries))
+		return -EINVAL;
+
+	for (i = 0; i < num_sg_entries; i++)
+		pages[i] = el->pages[i];
+
+	*p_num_sg_entries = num_sg_entries;
+	return 0;
+}
+
+static int
+mlxsw_pci_rdq_pages_alloc(struct mlxsw_pci_queue *q,
+			  struct mlxsw_pci_queue_elem_info *elem_info,
+			  u8 num_sg_entries)
+{
+	struct page *old_pages[MLXSW_PCI_WQE_SG_ENTRIES];
+	struct mlxsw_pci_queue *cq = q->u.rdq.cq;
+	int i, err;
+
+	for (i = 0; i < num_sg_entries; i++) {
+		old_pages[i] = elem_info->pages[i];
+		err = mlxsw_pci_rdq_page_alloc(q, elem_info, i);
+		if (err) {
+			dev_err_ratelimited(&q->pci->pdev->dev, "Failed to alloc page\n");
+			goto err_page_alloc;
+		}
+	}
 
-	elem_info->u.rdq.skb = skb;
 	return 0;
 
-err_frag_map:
-	dev_kfree_skb_any(skb);
+err_page_alloc:
+	for (i--; i >= 0; i--)
+		page_pool_recycle_direct(cq->u.cq.page_pool, old_pages[i]);
+
 	return err;
 }
 
-static void mlxsw_pci_rdq_skb_free(struct mlxsw_pci *mlxsw_pci,
-				   struct mlxsw_pci_queue_elem_info *elem_info)
+static void
+mlxsw_pci_rdq_pages_recycle(struct mlxsw_pci_queue *q, struct page *pages[],
+			    u8 num_sg_entries)
 {
-	struct sk_buff *skb;
-	char *wqe;
-
-	skb = elem_info->u.rdq.skb;
-	wqe = elem_info->elem;
+	struct mlxsw_pci_queue *cq = q->u.rdq.cq;
+	int i;
 
-	mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
-	dev_kfree_skb_any(skb);
+	for (i = 0; i < num_sg_entries; i++)
+		page_pool_recycle_direct(cq->u.cq.page_pool, pages[i]);
 }
 
 static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
@@ -410,7 +532,7 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	u8 sdq_count = mlxsw_pci->num_sdqs;
 	struct mlxsw_pci_queue *cq;
 	u8 cq_num;
-	int i;
+	int i, j;
 	int err;
 
 	q->producer_counter = 0;
@@ -434,15 +556,19 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 
 	cq = mlxsw_pci_cq_get(mlxsw_pci, cq_num);
 	cq->u.cq.dq = q;
+	q->u.rdq.cq = cq;
 
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
 
 	for (i = 0; i < q->count; i++) {
 		elem_info = mlxsw_pci_queue_elem_info_producer_get(q);
 		BUG_ON(!elem_info);
-		err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info, GFP_KERNEL);
-		if (err)
-			goto rollback;
+
+		for (j = 0; j < mlxsw_pci->num_sg_entries; j++) {
+			err = mlxsw_pci_rdq_page_alloc(q, elem_info, j);
+			if (err)
+				goto rollback;
+		}
 		/* Everything is set up, ring doorbell to pass elem to HW */
 		q->producer_counter++;
 		mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
@@ -453,8 +579,11 @@ static int mlxsw_pci_rdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 rollback:
 	for (i--; i >= 0; i--) {
 		elem_info = mlxsw_pci_queue_elem_info_get(q, i);
-		mlxsw_pci_rdq_skb_free(mlxsw_pci, elem_info);
+		for (j--; j >= 0; j--)
+			mlxsw_pci_rdq_page_free(q, elem_info, j);
+		j = mlxsw_pci->num_sg_entries;
 	}
+	q->u.rdq.cq = NULL;
 	cq->u.cq.dq = NULL;
 	mlxsw_cmd_hw2sw_rdq(mlxsw_pci->core, q->num);
 
@@ -465,12 +594,13 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci,
 			       struct mlxsw_pci_queue *q)
 {
 	struct mlxsw_pci_queue_elem_info *elem_info;
-	int i;
+	int i, j;
 
 	mlxsw_cmd_hw2sw_rdq(mlxsw_pci->core, q->num);
 	for (i = 0; i < q->count; i++) {
 		elem_info = mlxsw_pci_queue_elem_info_get(q, i);
-		mlxsw_pci_rdq_skb_free(mlxsw_pci, elem_info);
+		for (j = 0; j < mlxsw_pci->num_sg_entries; j++)
+			mlxsw_pci_rdq_page_free(q, elem_info, j);
 	}
 }
 
@@ -515,7 +645,7 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 				     struct mlxsw_pci_queue *q,
 				     u16 consumer_counter_limit,
 				     enum mlxsw_pci_cqe_v cqe_v,
-				     char *cqe)
+				     char *cqe, int budget)
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_elem_info *elem_info;
@@ -526,8 +656,8 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 
 	spin_lock(&q->lock);
 	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
-	tx_info = mlxsw_skb_cb(elem_info->u.sdq.skb)->tx_info;
-	skb = elem_info->u.sdq.skb;
+	tx_info = mlxsw_skb_cb(elem_info->sdq.skb)->tx_info;
+	skb = elem_info->sdq.skb;
 	wqe = elem_info->elem;
 	for (i = 0; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, i, DMA_TO_DEVICE);
@@ -541,8 +671,8 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 	}
 
 	if (skb)
-		dev_kfree_skb_any(skb);
-	elem_info->u.sdq.skb = NULL;
+		napi_consume_skb(skb, budget);
+	elem_info->sdq.skb = NULL;
 
 	if (q->consumer_counter++ != consumer_counter_limit)
 		dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in SDQ\n");
@@ -604,27 +734,40 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 				     enum mlxsw_pci_cqe_v cqe_v, char *cqe)
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
+	struct page *pages[MLXSW_PCI_WQE_SG_ENTRIES];
 	struct mlxsw_pci_queue_elem_info *elem_info;
 	struct mlxsw_rx_info rx_info = {};
-	char wqe[MLXSW_PCI_WQE_SIZE];
 	struct sk_buff *skb;
+	u8 num_sg_entries;
 	u16 byte_count;
 	int err;
 
 	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
-	skb = elem_info->u.rdq.skb;
-	memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE);
 
 	if (q->consumer_counter++ != consumer_counter_limit)
 		dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
 
-	err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info, GFP_ATOMIC);
-	if (err) {
-		dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+	byte_count = mlxsw_pci_cqe_byte_count_get(cqe);
+	if (mlxsw_pci_cqe_crc_get(cqe_v, cqe))
+		byte_count -= ETH_FCS_LEN;
+
+	err = mlxsw_pci_elem_info_pages_ref_store(q, elem_info, byte_count,
+						  pages, &num_sg_entries);
+	if (err)
+		goto out;
+
+	err = mlxsw_pci_rdq_pages_alloc(q, elem_info, num_sg_entries);
+	if (err)
+		goto out;
+
+	skb = mlxsw_pci_rdq_build_skb(pages, byte_count);
+	if (IS_ERR(skb)) {
+		dev_err_ratelimited(&pdev->dev, "Failed to build skb for RDQ\n");
+		mlxsw_pci_rdq_pages_recycle(q, pages, num_sg_entries);
 		goto out;
 	}
 
-	mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+	skb_mark_for_recycle(skb);
 
 	if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
 		rx_info.is_lag = true;
@@ -657,10 +800,6 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 
 	mlxsw_pci_skb_cb_ts_set(mlxsw_pci, skb, cqe_v, cqe);
 
-	byte_count = mlxsw_pci_cqe_byte_count_get(cqe);
-	if (mlxsw_pci_cqe_crc_get(cqe_v, cqe))
-		byte_count -= ETH_FCS_LEN;
-	skb_put(skb, byte_count);
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
 
 out:
@@ -785,7 +924,7 @@ static int mlxsw_pci_napi_poll_cq_tx(struct napi_struct *napi, int budget)
 		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 
 		mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
-					 wqe_counter, q->u.cq.v, ncqe);
+					 wqe_counter, q->u.cq.v, ncqe, budget);
 
 		work_done++;
 	}
@@ -832,19 +971,51 @@ static void mlxsw_pci_cq_napi_setup(struct mlxsw_pci_queue *q,
 			       mlxsw_pci_napi_poll_cq_rx);
 		break;
 	}
-
-	napi_enable(&q->u.cq.napi);
 }
 
 static void mlxsw_pci_cq_napi_teardown(struct mlxsw_pci_queue *q)
 {
-	napi_disable(&q->u.cq.napi);
 	netif_napi_del(&q->u.cq.napi);
 }
 
+static int mlxsw_pci_cq_page_pool_init(struct mlxsw_pci_queue *q,
+				       enum mlxsw_pci_cq_type cq_type)
+{
+	struct page_pool_params pp_params = {};
+	struct mlxsw_pci *mlxsw_pci = q->pci;
+	struct page_pool *page_pool;
+
+	if (cq_type != MLXSW_PCI_CQ_RDQ)
+		return 0;
+
+	pp_params.flags = PP_FLAG_DMA_MAP;
+	pp_params.pool_size = MLXSW_PCI_WQE_COUNT * mlxsw_pci->num_sg_entries;
+	pp_params.nid = dev_to_node(&mlxsw_pci->pdev->dev);
+	pp_params.dev = &mlxsw_pci->pdev->dev;
+	pp_params.napi = &q->u.cq.napi;
+	pp_params.dma_dir = DMA_FROM_DEVICE;
+
+	page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(page_pool))
+		return PTR_ERR(page_pool);
+
+	q->u.cq.page_pool = page_pool;
+	return 0;
+}
+
+static void mlxsw_pci_cq_page_pool_fini(struct mlxsw_pci_queue *q,
+					enum mlxsw_pci_cq_type cq_type)
+{
+	if (cq_type != MLXSW_PCI_CQ_RDQ)
+		return;
+
+	page_pool_destroy(q->u.cq.page_pool);
+}
+
 static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
+	enum mlxsw_pci_cq_type cq_type = mlxsw_pci_cq_type(mlxsw_pci, q);
 	int i;
 	int err;
 
@@ -874,15 +1045,29 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	err = mlxsw_cmd_sw2hw_cq(mlxsw_pci->core, mbox, q->num);
 	if (err)
 		return err;
-	mlxsw_pci_cq_napi_setup(q, mlxsw_pci_cq_type(mlxsw_pci, q));
+	mlxsw_pci_cq_napi_setup(q, cq_type);
+
+	err = mlxsw_pci_cq_page_pool_init(q, cq_type);
+	if (err)
+		goto err_page_pool_init;
+
+	napi_enable(&q->u.cq.napi);
 	mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 	mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
 	return 0;
+
+err_page_pool_init:
+	mlxsw_pci_cq_napi_teardown(q);
+	return err;
 }
 
 static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
 			      struct mlxsw_pci_queue *q)
 {
+	enum mlxsw_pci_cq_type cq_type = mlxsw_pci_cq_type(mlxsw_pci, q);
+
+	napi_disable(&q->u.cq.napi);
+	mlxsw_pci_cq_page_pool_fini(q, cq_type);
 	mlxsw_pci_cq_napi_teardown(q);
 	mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
 }
@@ -1599,6 +1784,7 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+	struct pci_dev *bridge;
 	int err;
 
 	if (!pci_reset_sbr_supported) {
@@ -1615,6 +1801,9 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
 sbr:
 	device_lock_assert(&pdev->dev);
 
+	bridge = pci_upstream_bridge(pdev);
+	if (bridge)
+		pci_cfg_access_lock(bridge);
 	pci_cfg_access_lock(pdev);
 	pci_save_state(pdev);
 
@@ -1624,6 +1813,8 @@ sbr:
 
 	pci_restore_state(pdev);
 	pci_cfg_access_unlock(pdev);
+	if (bridge)
+		pci_cfg_access_unlock(bridge);
 
 	return err;
 }
@@ -1703,6 +1894,17 @@ static void mlxsw_pci_free_irq_vectors(struct mlxsw_pci *mlxsw_pci)
 	pci_free_irq_vectors(mlxsw_pci->pdev);
 }
 
+static void mlxsw_pci_num_sg_entries_set(struct mlxsw_pci *mlxsw_pci)
+{
+	u8 num_sg_entries;
+
+	num_sg_entries = mlxsw_pci_num_sg_entries_get(MLXSW_PORT_MAX_MTU);
+	mlxsw_pci->num_sg_entries = min(num_sg_entries,
+					MLXSW_PCI_WQE_SG_ENTRIES);
+
+	WARN_ON(num_sg_entries > MLXSW_PCI_WQE_SG_ENTRIES);
+}
+
 static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 			  const struct mlxsw_config_profile *profile,
 			  struct mlxsw_res *res)
@@ -1825,6 +2027,8 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_requery_resources;
 
+	mlxsw_pci_num_sg_entries_set(mlxsw_pci);
+
 	err = mlxsw_pci_napi_devs_init(mlxsw_pci);
 	if (err)
 		goto err_napi_devs_init;
@@ -1931,7 +2135,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 		goto unlock;
 	}
 	mlxsw_skb_cb(skb)->tx_info = *tx_info;
-	elem_info->u.sdq.skb = skb;
+	elem_info->sdq.skb = skb;
 
 	wqe = elem_info->elem;
 	mlxsw_pci_wqe_c_set(wqe, 1); /* always report completion */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index ac4d4ea51597..0a73b1a4526e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -6,7 +6,8 @@
 
 #include <linux/types.h>
 
-#define MLXSW_PORT_MAX_MTU		10000
+#define MLXSW_PORT_MAX_MTU		(10 * 1024)
+#define MLXSW_PORT_ETH_FRAME_HDR	(ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 
 #define MLXSW_PORT_DEFAULT_VID		1
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 030ed71f945d..f064789f3240 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -405,29 +405,12 @@ static int mlxsw_sp_port_dev_addr_init(struct mlxsw_sp_port *mlxsw_sp_port)
 					  mlxsw_sp_port->dev->dev_addr);
 }
 
-static int mlxsw_sp_port_max_mtu_get(struct mlxsw_sp_port *mlxsw_sp_port, int *p_max_mtu)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char pmtu_pl[MLXSW_REG_PMTU_LEN];
-	int err;
-
-	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
-	if (err)
-		return err;
-
-	*p_max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl);
-	return 0;
-}
-
 static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pmtu_pl[MLXSW_REG_PMTU_LEN];
 
-	mtu += MLXSW_TXHDR_LEN + ETH_HLEN;
-	if (mtu > mlxsw_sp_port->max_mtu)
-		return -EINVAL;
+	mtu += MLXSW_PORT_ETH_FRAME_HDR;
 
 	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sp_port->local_port, mtu);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
@@ -1697,8 +1680,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 			 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
 
-	dev->min_mtu = 0;
-	dev->max_mtu = ETH_MAX_MTU;
+	dev->min_mtu = ETH_MIN_MTU;
+	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
 
 	/* Each packet needs to have a Tx header (metadata) on top all other
 	 * headers.
@@ -1727,13 +1710,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 		goto err_max_speed_get;
 	}
 
-	err = mlxsw_sp_port_max_mtu_get(mlxsw_sp_port, &mlxsw_sp_port->max_mtu);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to get maximum MTU\n",
-			mlxsw_sp_port->local_port);
-		goto err_port_max_mtu_get;
-	}
-
 	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, ETH_DATA_LEN);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set MTU\n",
@@ -1877,7 +1853,6 @@ err_port_ets_init:
 err_port_buffers_init:
 err_port_admin_status_set:
 err_port_mtu_set:
-err_port_max_mtu_get:
 err_max_speed_get:
 err_port_speed_by_width_set:
 err_port_system_port_mapping_set:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 3beb5d0847ab..8d3c61287696 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -238,7 +238,7 @@ struct mlxsw_sp_ptp_ops {
 			    struct hwtstamp_config *config);
 	void (*shaper_work)(struct work_struct *work);
 	int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp,
-			   struct ethtool_ts_info *info);
+			   struct kernel_ethtool_ts_info *info);
 	int (*get_stats_count)(void);
 	void (*get_stats_strings)(u8 **p);
 	void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -359,7 +359,6 @@ struct mlxsw_sp_port {
 		u16 egr_types;
 		struct mlxsw_sp_ptp_port_stats stats;
 	} ptp;
-	int max_mtu;
 	u32 max_speed;
 	struct mlxsw_sp_hdroom *hdroom;
 	u64 module_overheat_initial_val;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 4b713832fdd5..07cb1e26ca3e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -391,7 +391,8 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id);
+	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key,
+					    erp_id);
 	if (IS_ERR(lkey_id))
 		return PTR_ERR(lkey_id);
 	aentry->lkey_id = lkey_id;
@@ -399,7 +400,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
 			     priority, region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -428,7 +429,7 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
 			     region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -457,7 +458,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
 			     priority, region->tcam_region_info,
-			     aentry->enc_key, erp_id,
+			     aentry->ht_key.enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -480,26 +481,23 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->ht_key.full_enc_key, mask);
+			 aentry->ht_key.enc_key, mask);
 
 	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
 	if (IS_ERR(erp_mask))
 		return PTR_ERR(erp_mask);
 	aentry->erp_mask = erp_mask;
 	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
-	memcpy(aentry->enc_key, aentry->ht_key.full_enc_key,
-	       sizeof(aentry->enc_key));
 
 	/* Compute all needed delta information and clear the delta bits
-	 * from the encrypted key.
+	 * from the encoded key.
 	 */
 	delta = mlxsw_sp_acl_erp_delta(aentry->erp_mask);
 	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
 	aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
 	aentry->delta_info.value =
-		mlxsw_sp_acl_erp_delta_value(delta,
-					     aentry->ht_key.full_enc_key);
-	mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key);
+		mlxsw_sp_acl_erp_delta_value(delta, aentry->ht_key.enc_key);
+	mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
 
 	/* Add rule to the list of A-TCAM rules, assuming this
 	 * rule is intended to A-TCAM. In case this rule does
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index 95f63fcf4ba1..a54eedb69a3f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -249,7 +249,7 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 		memcpy(chunk + pad_bytes, &erp_region_id,
 		       sizeof(erp_region_id));
 		memcpy(chunk + key_offset,
-		       &aentry->enc_key[chunk_key_offsets[chunk_index]],
+		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
 		       chunk_key_len);
 		chunk += chunk_len;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index d231f4d2888b..9eee229303cc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj,
 	return err ? false : true;
 }
 
-static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2)
-{
-	const struct mlxsw_sp_acl_erp_key *key1 = obj1;
-	const struct mlxsw_sp_acl_erp_key *key2 = obj2;
-
-	/* For hints purposes, two objects are considered equal
-	 * in case the masks are the same. Does not matter what
-	 * the "ctcam" value is.
-	 */
-	return memcmp(key1->mask, key2->mask, sizeof(key1->mask));
-}
-
 static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
 					   void *obj)
 {
@@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
 static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
 	.obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
 	.delta_check = mlxsw_sp_acl_erp_delta_check,
-	.hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp,
 	.delta_create = mlxsw_sp_acl_erp_delta_create,
 	.delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
 	.root_create = mlxsw_sp_acl_erp_root_create,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 79a1d8606512..010204f73ea4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -167,9 +167,9 @@ struct mlxsw_sp_acl_atcam_region {
 };
 
 struct mlxsw_sp_acl_atcam_entry_ht_key {
-	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded
-								 * key.
-								 */
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, minus
+							    * delta bits.
+							    */
 	u8 erp_id;
 };
 
@@ -181,9 +181,6 @@ struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
 	struct list_head list; /* Member in entries_list */
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
-	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
-							    * minus delta bits.
-							    */
 	struct {
 		u16 start;
 		u8 mask;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index ba090262e27e..2c0cfa79d138 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -399,11 +399,13 @@ void mlxsw_sp_hdroom_bufs_reset_sizes(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct mlxsw_sp_hdroom *hdroom)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	unsigned int max_mtu = mlxsw_sp_port->dev->max_mtu;
 	u16 reserve_cells;
 	int i;
 
+	max_mtu += MLXSW_PORT_ETH_FRAME_HDR;
 	/* Internal buffer. */
-	reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_mtu,
+	reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, max_mtu,
 							 mlxsw_sp_port->max_speed);
 	reserve_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, reserve_cells);
 	hdroom->int_buf.reserve_cells = reserve_cells;
@@ -613,7 +615,9 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	mlxsw_sp_hdroom_bufs_reset_sizes(mlxsw_sp_port, &hdroom);
 
 	/* Buffer 9 is used for control traffic. */
-	size9 = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, mlxsw_sp_port->max_mtu);
+	size9 = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port,
+						 mlxsw_sp_port->dev->max_mtu +
+						 MLXSW_PORT_ETH_FRAME_HDR);
 	hdroom.bufs.buf[9].size_cells = mlxsw_sp_bytes_cells(mlxsw_sp, size9);
 
 	return __mlxsw_sp_hdroom_configure(mlxsw_sp_port, &hdroom, true);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index ca80af06465f..fa6eddd27ecf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -283,7 +283,7 @@ static u64 mlxsw_sp_dpipe_table_erif_size_get(void *priv)
 	return MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_erif_entries_dump,
@@ -734,7 +734,7 @@ static u64 mlxsw_sp_dpipe_table_host4_size_get(void *priv)
 	return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_host4_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_host4_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_host4_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_host_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_host4_entries_dump,
@@ -811,7 +811,7 @@ static u64 mlxsw_sp_dpipe_table_host6_size_get(void *priv)
 	return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET6);
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_host6_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_host6_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_host6_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_host_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_host6_entries_dump,
@@ -1230,7 +1230,7 @@ mlxsw_sp_dpipe_table_adj_size_get(void *priv)
 	return size;
 }
 
-static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
+static const struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = {
 	.matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump,
 	.actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump,
 	.entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index a755b0a901d3..2bed8c86b7cf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1068,7 +1068,21 @@ mlxsw_sp_get_module_eeprom_by_page(struct net_device *dev,
 }
 
 static int
-mlxsw_sp_get_ts_info(struct net_device *netdev, struct ethtool_ts_info *info)
+mlxsw_sp_set_module_eeprom_by_page(struct net_device *dev,
+				   const struct ethtool_module_eeprom *page,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 slot_index = mlxsw_sp_port->mapping.slot_index;
+	u8 module = mlxsw_sp_port->mapping.module;
+
+	return mlxsw_env_set_module_eeprom_by_page(mlxsw_sp->core, slot_index,
+						   module, page, extack);
+}
+
+static int
+mlxsw_sp_get_ts_info(struct net_device *netdev, struct kernel_ethtool_ts_info *info)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -1256,6 +1270,7 @@ const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.get_module_info		= mlxsw_sp_get_module_info,
 	.get_module_eeprom		= mlxsw_sp_get_module_eeprom,
 	.get_module_eeprom_by_page	= mlxsw_sp_get_module_eeprom_by_page,
+	.set_module_eeprom_by_page	= mlxsw_sp_set_module_eeprom_by_page,
 	.get_ts_info			= mlxsw_sp_get_ts_info,
 	.get_eth_phy_stats		= mlxsw_sp_get_eth_phy_stats,
 	.get_eth_mac_stats		= mlxsw_sp_get_eth_mac_stats,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index cbb6c75a6620..5b174cb95eb8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -1276,7 +1276,7 @@ int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-			      struct ethtool_ts_info *info)
+			      struct kernel_ethtool_ts_info *info)
 {
 	info->phc_index = ptp_clock_index(mlxsw_sp->clock->ptp);
 
@@ -1661,7 +1661,7 @@ err_get_message_types:
 }
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-			      struct ethtool_ts_info *info)
+			      struct kernel_ethtool_ts_info *info)
 {
 	info->phc_index = ptp_clock_index(mlxsw_sp->clock->ptp);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index a8b88230959a..769095d4932d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -11,7 +11,7 @@ struct mlxsw_sp;
 struct mlxsw_sp_port;
 struct mlxsw_sp_ptp_clock;
 
-static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct ethtool_ts_info *info)
+static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct kernel_ethtool_ts_info *info)
 {
 	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
 				SOF_TIMESTAMPING_SOFTWARE;
@@ -50,7 +50,7 @@ int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 void mlxsw_sp1_ptp_shaper_work(struct work_struct *work);
 
 int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-			      struct ethtool_ts_info *info);
+			      struct kernel_ethtool_ts_info *info);
 
 int mlxsw_sp1_get_stats_count(void);
 void mlxsw_sp1_get_stats_strings(u8 **p);
@@ -84,7 +84,7 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			       struct hwtstamp_config *config);
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-			      struct ethtool_ts_info *info);
+			      struct kernel_ethtool_ts_info *info);
 
 int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
 				  struct mlxsw_sp_port *mlxsw_sp_port,
@@ -152,7 +152,7 @@ static inline void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
 }
 
 static inline int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-					    struct ethtool_ts_info *info)
+					    struct kernel_ethtool_ts_info *info)
 {
 	return mlxsw_sp_ptp_get_ts_info_noptp(info);
 }
@@ -227,7 +227,7 @@ mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-					    struct ethtool_ts_info *info)
+					    struct kernel_ethtool_ts_info *info)
 {
 	return mlxsw_sp_ptp_get_ts_info_noptp(info);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 40ba314fbc72..800dfb64ec83 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -11450,12 +11450,16 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
 {
 	bool old_inc_parsing_depth, new_inc_parsing_depth;
 	struct mlxsw_sp_mp_hash_config config = {};
+	struct net *net = mlxsw_sp_net(mlxsw_sp);
 	char recr2_pl[MLXSW_REG_RECR2_LEN];
 	unsigned long bit;
 	u32 seed;
 	int err;
 
-	seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);
+	seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).user_seed;
+	if (!seed)
+		seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);
+
 	mlxsw_reg_recr2_pack(recr2_pl, seed);
 	mlxsw_sp_mp4_hash_init(mlxsw_sp, &config);
 	mlxsw_sp_mp6_hash_init(mlxsw_sp, &config);