Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 389 insertions, 15 deletions

diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6189a4c0d39e..6348307bfa84 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -35,6 +35,25 @@
 
 #include "netdevsim.h"
 
+static unsigned int
+nsim_dev_port_index(enum nsim_dev_port_type type, unsigned int port_index)
+{
+	switch (type) {
+	case NSIM_DEV_PORT_TYPE_VF:
+		port_index = NSIM_DEV_VF_PORT_INDEX_BASE + port_index;
+		break;
+	case NSIM_DEV_PORT_TYPE_PF:
+		break;
+	}
+
+	return port_index;
+}
+
+static inline unsigned int nsim_dev_port_index_to_vf_index(unsigned int port_index)
+{
+	return port_index - NSIM_DEV_VF_PORT_INDEX_BASE;
+}
+
 static struct dentry *nsim_dev_ddir;
 
 #define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32)
@@ -192,9 +211,18 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = {
 	.owner = THIS_MODULE,
 };
 
+static const struct file_operations nsim_dev_max_vfs_fops = {
+	.open = simple_open,
+	.read = nsim_bus_dev_max_vfs_read,
+	.write = nsim_bus_dev_max_vfs_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
 	char dev_ddir_name[sizeof(DRV_NAME) + 10];
+	int err;
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
@@ -231,30 +259,84 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 	debugfs_create_bool("fail_trap_policer_counter_get", 0600,
 			    nsim_dev->ddir,
 			    &nsim_dev->fail_trap_policer_counter_get);
+	nsim_dev->max_vfs = debugfs_create_file("max_vfs",
+						0600,
+						nsim_dev->ddir,
+						nsim_dev->nsim_bus_dev,
+						&nsim_dev_max_vfs_fops);
+	nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir);
+	if (IS_ERR(nsim_dev->nodes_ddir)) {
+		err = PTR_ERR(nsim_dev->nodes_ddir);
+		goto err_out;
+	}
+	debugfs_create_bool("fail_trap_drop_counter_get", 0600,
+			    nsim_dev->ddir,
+			    &nsim_dev->fail_trap_drop_counter_get);
 	nsim_udp_tunnels_debugfs_create(nsim_dev);
 	return 0;
+
+err_out:
+	debugfs_remove_recursive(nsim_dev->ports_ddir);
+	debugfs_remove_recursive(nsim_dev->ddir);
+	return err;
 }
 
 static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
 {
+	debugfs_remove_recursive(nsim_dev->nodes_ddir);
 	debugfs_remove_recursive(nsim_dev->ports_ddir);
 	debugfs_remove_recursive(nsim_dev->ddir);
 }
 
+static ssize_t nsim_dev_rate_parent_read(struct file *file,
+					 char __user *data,
+					 size_t count, loff_t *ppos)
+{
+	char **name_ptr = file->private_data;
+	size_t len;
+
+	if (!*name_ptr)
+		return 0;
+
+	len = strlen(*name_ptr);
+	return simple_read_from_buffer(data, count, ppos, *name_ptr, len);
+}
+
+static const struct file_operations nsim_dev_rate_parent_fops = {
+	.open = simple_open,
+	.read = nsim_dev_rate_parent_read,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
 static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
 				      struct nsim_dev_port *nsim_dev_port)
 {
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	unsigned int port_index = nsim_dev_port->port_index;
 	char port_ddir_name[16];
 	char dev_link_name[32];
 
-	sprintf(port_ddir_name, "%u", nsim_dev_port->port_index);
+	sprintf(port_ddir_name, "%u", port_index);
 	nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name,
 						 nsim_dev->ports_ddir);
 	if (IS_ERR(nsim_dev_port->ddir))
 		return PTR_ERR(nsim_dev_port->ddir);
 
-	sprintf(dev_link_name, "../../../" DRV_NAME "%u",
-		nsim_dev->nsim_bus_dev->dev.id);
+	sprintf(dev_link_name, "../../../" DRV_NAME "%u", nsim_bus_dev->dev.id);
+	if (nsim_dev_port_is_vf(nsim_dev_port)) {
+		unsigned int vf_id = nsim_dev_port_index_to_vf_index(port_index);
+
+		debugfs_create_u16("tx_share", 0400, nsim_dev_port->ddir,
+				   &nsim_bus_dev->vfconfigs[vf_id].min_tx_rate);
+		debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir,
+				   &nsim_bus_dev->vfconfigs[vf_id].max_tx_rate);
+		nsim_dev_port->rate_parent = debugfs_create_file("rate_parent",
+								 0400,
+								 nsim_dev_port->ddir,
+								 &nsim_dev_port->parent_name,
+								 &nsim_dev_rate_parent_fops);
+	}
 	debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name);
 
 	return 0;
@@ -407,6 +489,74 @@ static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev)
 	devlink_region_destroy(nsim_dev->dummy_region);
 }
 
+static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port);
+int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = priv_to_devlink(nsim_dev);
+	struct nsim_dev_port *nsim_dev_port, *tmp;
+
+	devlink_rate_nodes_destroy(devlink);
+	mutex_lock(&nsim_dev->port_list_lock);
+	list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list)
+		if (nsim_dev_port_is_vf(nsim_dev_port))
+			__nsim_dev_port_del(nsim_dev_port);
+	mutex_unlock(&nsim_dev->port_list_lock);
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	return 0;
+}
+
+int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	int i, err;
+
+	for (i = 0; i < nsim_bus_dev->num_vfs; i++) {
+		err = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to initialize VFs' netdevsim ports");
+			pr_err("Failed to initialize VF id=%d. %d.\n", i, err);
+			goto err_port_add_vfs;
+		}
+	}
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+	return 0;
+
+err_port_add_vfs:
+	for (i--; i >= 0; i--)
+		nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+	return err;
+}
+
+static int nsim_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+					 struct netlink_ext_ack *extack)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	int err = 0;
+
+	mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	if (mode == nsim_dev->esw_mode)
+		goto unlock;
+
+	if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		err = nsim_esw_legacy_enable(nsim_dev, extack);
+	else if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		err = nsim_esw_switchdev_enable(nsim_dev, extack);
+	else
+		err = -EINVAL;
+
+unlock:
+	mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	return err;
+}
+
+static int nsim_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+
+	*mode = nsim_dev->esw_mode;
+	return 0;
+}
+
 struct nsim_trap_item {
 	void *trap_ctx;
 	enum devlink_trap_action action;
@@ -416,6 +566,7 @@ struct nsim_trap_data {
 	struct delayed_work trap_report_dw;
 	struct nsim_trap_item *trap_items_arr;
 	u64 *trap_policers_cnt_arr;
+	u64 trap_pkt_cnt;
 	struct nsim_dev *nsim_dev;
 	spinlock_t trap_lock;	/* Protects trap_items_arr */
 };
@@ -892,7 +1043,190 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 	return 0;
 }
 
+#define NSIM_LINK_SPEED_MAX     5000 /* Mbps */
+#define NSIM_LINK_SPEED_UNIT    125000 /* 1 Mbps given in bytes/sec to avoid
+					* u64 overflow during conversion from
+					* bytes to bits.
+					*/
+
+static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ack *extack)
+{
+	u64 val;
+	u32 rem;
+
+	val = div_u64_rem(*rate, NSIM_LINK_SPEED_UNIT, &rem);
+	if (rem) {
+		pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
+		       name, *rate);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps.");
+		return -EINVAL;
+	}
+
+	if (val > NSIM_LINK_SPEED_MAX) {
+		pr_err("%s rate value %lluMbps exceed link maximum speed 5000Mbps.\n",
+		       name, val);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed 5000Mbps.");
+		return -EINVAL;
+	}
+	*rate = val;
+	return 0;
+}
+
+static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+				  u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv;
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+	int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	nsim_bus_dev->vfconfigs[vf_id].min_tx_rate = tx_share;
+	return 0;
+}
+
+static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+				u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv;
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+	int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	nsim_bus_dev->vfconfigs[vf_id].max_tx_rate = tx_max;
+	return 0;
+}
+
+struct nsim_rate_node {
+	struct dentry *ddir;
+	struct dentry *rate_parent;
+	char *parent_name;
+	u16 tx_share;
+	u16 tx_max;
+};
+
+static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+				  u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	nsim_node->tx_share = tx_share;
+	return 0;
+}
+
+static int nsim_node_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+				u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	nsim_node->tx_max = tx_max;
+	return 0;
+}
+
+static int nsim_rate_node_new(struct devlink_rate *node, void **priv,
+			      struct netlink_ext_ack *extack)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(node->devlink);
+	struct nsim_rate_node *nsim_node;
+
+	if (!nsim_esw_mode_is_switchdev(nsim_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Node creation allowed only in switchdev mode.");
+		return -EOPNOTSUPP;
+	}
+
+	nsim_node = kzalloc(sizeof(*nsim_node), GFP_KERNEL);
+	if (!nsim_node)
+		return -ENOMEM;
+
+	nsim_node->ddir = debugfs_create_dir(node->name, nsim_dev->nodes_ddir);
+
+	debugfs_create_u16("tx_share", 0400, nsim_node->ddir, &nsim_node->tx_share);
+	debugfs_create_u16("tx_max", 0400, nsim_node->ddir, &nsim_node->tx_max);
+	nsim_node->rate_parent = debugfs_create_file("rate_parent", 0400,
+						     nsim_node->ddir,
+						     &nsim_node->parent_name,
+						     &nsim_dev_rate_parent_fops);
+
+	*priv = nsim_node;
+	return 0;
+}
+
+static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
+			      struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+
+	debugfs_remove(nsim_node->rate_parent);
+	debugfs_remove_recursive(nsim_node->ddir);
+	kfree(nsim_node);
+	return 0;
+}
+
+static int nsim_rate_leaf_parent_set(struct devlink_rate *child,
+				     struct devlink_rate *parent,
+				     void *priv_child, void *priv_parent,
+				     struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv_child;
+
+	if (parent)
+		nsim_dev_port->parent_name = parent->name;
+	else
+		nsim_dev_port->parent_name = NULL;
+	return 0;
+}
+
+static int nsim_rate_node_parent_set(struct devlink_rate *child,
+				     struct devlink_rate *parent,
+				     void *priv_child, void *priv_parent,
+				     struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv_child;
+
+	if (parent)
+		nsim_node->parent_name = parent->name;
+	else
+		nsim_node->parent_name = NULL;
+	return 0;
+}
+
+static int
+nsim_dev_devlink_trap_drop_counter_get(struct devlink *devlink,
+				       const struct devlink_trap *trap,
+				       u64 *p_drops)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	u64 *cnt;
+
+	if (nsim_dev->fail_trap_drop_counter_get)
+		return -EINVAL;
+
+	cnt = &nsim_dev->trap_data->trap_pkt_cnt;
+	*p_drops = (*cnt)++;
+
+	return 0;
+}
+
 static const struct devlink_ops nsim_dev_devlink_ops = {
+	.eswitch_mode_set = nsim_devlink_eswitch_mode_set,
+	.eswitch_mode_get = nsim_devlink_eswitch_mode_get,
 	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT |
 					 DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
 	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
@@ -905,32 +1239,52 @@ static const struct devlink_ops nsim_dev_devlink_ops = {
 	.trap_group_set = nsim_dev_devlink_trap_group_set,
 	.trap_policer_set = nsim_dev_devlink_trap_policer_set,
 	.trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get,
+	.rate_leaf_tx_share_set = nsim_leaf_tx_share_set,
+	.rate_leaf_tx_max_set = nsim_leaf_tx_max_set,
+	.rate_node_tx_share_set = nsim_node_tx_share_set,
+	.rate_node_tx_max_set = nsim_node_tx_max_set,
+	.rate_node_new = nsim_rate_node_new,
+	.rate_node_del = nsim_rate_node_del,
+	.rate_leaf_parent_set = nsim_rate_leaf_parent_set,
+	.rate_node_parent_set = nsim_rate_node_parent_set,
+	.trap_drop_counter_get = nsim_dev_devlink_trap_drop_counter_get,
 };
 
 #define NSIM_DEV_MAX_MACS_DEFAULT 32
 #define NSIM_DEV_TEST1_DEFAULT true
 
-static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
+static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
 			       unsigned int port_index)
 {
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
 	struct devlink_port_attrs attrs = {};
 	struct nsim_dev_port *nsim_dev_port;
 	struct devlink_port *devlink_port;
 	int err;
 
+	if (type == NSIM_DEV_PORT_TYPE_VF && !nsim_bus_dev->num_vfs)
+		return -EINVAL;
+
 	nsim_dev_port = kzalloc(sizeof(*nsim_dev_port), GFP_KERNEL);
 	if (!nsim_dev_port)
 		return -ENOMEM;
-	nsim_dev_port->port_index = port_index;
+	nsim_dev_port->port_index = nsim_dev_port_index(type, port_index);
+	nsim_dev_port->port_type = type;
 
 	devlink_port = &nsim_dev_port->devlink_port;
-	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-	attrs.phys.port_number = port_index + 1;
+	if (nsim_dev_port_is_pf(nsim_dev_port)) {
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+		attrs.phys.port_number = port_index + 1;
+	} else {
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
+		attrs.pci_vf.pf = 0;
+		attrs.pci_vf.vf = port_index;
+	}
 	memcpy(attrs.switch_id.id, nsim_dev->switch_id.id, nsim_dev->switch_id.id_len);
 	attrs.switch_id.id_len = nsim_dev->switch_id.id_len;
 	devlink_port_attrs_set(devlink_port, &attrs);
 	err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port,
-				    port_index);
+				    nsim_dev_port->port_index);
 	if (err)
 		goto err_port_free;
 
@@ -944,11 +1298,20 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
 		goto err_port_debugfs_exit;
 	}
 
+	if (nsim_dev_port_is_vf(nsim_dev_port)) {
+		err = devlink_rate_leaf_create(&nsim_dev_port->devlink_port,
+					       nsim_dev_port);
+		if (err)
+			goto err_nsim_destroy;
+	}
+
 	devlink_port_type_eth_set(devlink_port, nsim_dev_port->ns->netdev);
 	list_add(&nsim_dev_port->list, &nsim_dev->port_list);
 
 	return 0;
 
+err_nsim_destroy:
+	nsim_destroy(nsim_dev_port->ns);
 err_port_debugfs_exit:
 	nsim_dev_port_debugfs_exit(nsim_dev_port);
 err_dl_port_unregister:
@@ -963,6 +1326,8 @@ static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port)
 	struct devlink_port *devlink_port = &nsim_dev_port->devlink_port;
 
 	list_del(&nsim_dev_port->list);
+	if (nsim_dev_port_is_vf(nsim_dev_port))
+		devlink_rate_leaf_destroy(&nsim_dev_port->devlink_port);
 	devlink_port_type_clear(devlink_port);
 	nsim_destroy(nsim_dev_port->ns);
 	nsim_dev_port_debugfs_exit(nsim_dev_port);
@@ -987,7 +1352,7 @@ static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev,
 	int i, err;
 
 	for (i = 0; i < port_count; i++) {
-		err = __nsim_dev_port_add(nsim_dev, i);
+		err = __nsim_dev_port_add(nsim_dev, NSIM_DEV_PORT_TYPE_PF, i);
 		if (err)
 			goto err_port_del_all;
 	}
@@ -1134,6 +1499,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 
 	devlink_params_publish(devlink);
 	devlink_reload_enable(devlink);
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
 	return 0;
 
 err_psample_exit:
@@ -1169,6 +1535,12 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev)
 	if (devlink_is_reload_failed(devlink))
 		return;
 	debugfs_remove(nsim_dev->take_snapshot);
+
+	mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	if (nsim_dev->nsim_bus_dev->num_vfs)
+		nsim_bus_dev_vfs_disable(nsim_dev->nsim_bus_dev);
+	mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+
 	nsim_dev_port_del_all(nsim_dev);
 	nsim_dev_psample_exit(nsim_dev);
 	nsim_dev_health_exit(nsim_dev);
@@ -1197,32 +1569,34 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev)
 }
 
 static struct nsim_dev_port *
-__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, unsigned int port_index)
+__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
+		       unsigned int port_index)
 {
 	struct nsim_dev_port *nsim_dev_port;
 
+	port_index = nsim_dev_port_index(type, port_index);
 	list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list)
 		if (nsim_dev_port->port_index == port_index)
 			return nsim_dev_port;
 	return NULL;
 }
 
-int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
 		      unsigned int port_index)
 {
 	struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
 	int err;
 
 	mutex_lock(&nsim_dev->port_list_lock);
-	if (__nsim_dev_port_lookup(nsim_dev, port_index))
+	if (__nsim_dev_port_lookup(nsim_dev, type, port_index))
 		err = -EEXIST;
 	else
-		err = __nsim_dev_port_add(nsim_dev, port_index);
+		err = __nsim_dev_port_add(nsim_dev, type, port_index);
 	mutex_unlock(&nsim_dev->port_list_lock);
 	return err;
 }
 
-int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
 		      unsigned int port_index)
 {
 	struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
@@ -1230,7 +1604,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
 	int err = 0;
 
 	mutex_lock(&nsim_dev->port_list_lock);
-	nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, port_index);
+	nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, type, port_index);
 	if (!nsim_dev_port)
 		err = -ENOENT;
 	else