Merge branch 'udp_tunnel-convert-Intel-drivers-with-shared-tables'

Jakub Kicinski says:

====================
udp_tunnel: convert Intel drivers with shared tables

This set converts Intel drivers which have the ability to spawn
multiple netdevs, but have only one UDP tunnel port table.

Appropriate support is added to the core infra in patch 1,
followed by netdevsim support and a selftest.

The table sharing works by core attaching the same table
structure to all devices sharing the table. This means the
reference count has to accommodate potentially large values.

Once core is ready i40e and ice are converted. These are
complex drivers, but we got a tested-by from Aaron, so we
should be good :)

Compared to v1 I've made sure the selftest is executable.

Other than that patches 8 and 9 are actually from the Mellanox
conversion series were kept out to avoid Mellanox vs Intel
conflicts.

Last patch is new, some docs to let users knows ethtool
can now display UDP tunnel info.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 190 insertions, 435 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ada0e93c38f0..537300e762f0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -35,6 +35,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/udp_tunnel.h>
 #include <net/xdp_sock.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
@@ -133,7 +134,6 @@ enum i40e_state_t {
 	__I40E_PORT_SUSPENDED,
 	__I40E_VF_DISABLE,
 	__I40E_MACVLAN_SYNC_PENDING,
-	__I40E_UDP_FILTER_SYNC_PENDING,
 	__I40E_TEMP_LINK_POLLING,
 	__I40E_CLIENT_SERVICE_REQUESTED,
 	__I40E_CLIENT_L2_CHANGE,
@@ -478,8 +478,8 @@ struct i40e_pf {
 	struct list_head l3_flex_pit_list;
 	struct list_head l4_flex_pit_list;
 
-	struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
-	u16 pending_udp_bitmap;
+	struct udp_tunnel_nic_shared udp_tunnel_shared;
+	struct udp_tunnel_nic_info udp_tunnel_nic;
 
 	struct hlist_head cloud_filter_list;
 	u16 num_cloud_filters;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index cb366daa1ad7..70bd3f47e43a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10386,106 +10386,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	i40e_flush(hw);
 }
 
-static const char *i40e_tunnel_name(u8 type)
-{
-	switch (type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		return "vxlan";
-	case UDP_TUNNEL_TYPE_GENEVE:
-		return "geneve";
-	default:
-		return "unknown";
-	}
-}
-
-/**
- * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters(struct i40e_pf *pf)
-{
-	int i;
-
-	/* loop through and set pending bit for all active UDP filters */
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->udp_ports[i].port)
-			pf->pending_udp_bitmap |= BIT_ULL(i);
-	}
-
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-}
-
-/**
- * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
-{
-	struct i40e_hw *hw = &pf->hw;
-	u8 filter_index, type;
-	u16 port;
-	int i;
-
-	if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state))
-		return;
-
-	/* acquire RTNL to maintain state of flags and port requests */
-	rtnl_lock();
-
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->pending_udp_bitmap & BIT_ULL(i)) {
-			struct i40e_udp_port_config *udp_port;
-			i40e_status ret = 0;
-
-			udp_port = &pf->udp_ports[i];
-			pf->pending_udp_bitmap &= ~BIT_ULL(i);
-
-			port = READ_ONCE(udp_port->port);
-			type = READ_ONCE(udp_port->type);
-			filter_index = READ_ONCE(udp_port->filter_index);
-
-			/* release RTNL while we wait on AQ command */
-			rtnl_unlock();
-
-			if (port)
-				ret = i40e_aq_add_udp_tunnel(hw, port,
-							     type,
-							     &filter_index,
-							     NULL);
-			else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED)
-				ret = i40e_aq_del_udp_tunnel(hw, filter_index,
-							     NULL);
-
-			/* reacquire RTNL so we can update filter_index */
-			rtnl_lock();
-
-			if (ret) {
-				dev_info(&pf->pdev->dev,
-					 "%s %s port %d, index %d failed, err %s aq_err %s\n",
-					 i40e_tunnel_name(type),
-					 port ? "add" : "delete",
-					 port,
-					 filter_index,
-					 i40e_stat_str(&pf->hw, ret),
-					 i40e_aq_str(&pf->hw,
-						     pf->hw.aq.asq_last_status));
-				if (port) {
-					/* failed to add, just reset port,
-					 * drop pending bit for any deletion
-					 */
-					udp_port->port = 0;
-					pf->pending_udp_bitmap &= ~BIT_ULL(i);
-				}
-			} else if (port) {
-				/* record filter index on success */
-				udp_port->filter_index = filter_index;
-			}
-		}
-	}
-
-	rtnl_unlock();
-}
-
 /**
  * i40e_service_task - Run the driver's async subtasks
  * @work: pointer to work_struct containing our data
@@ -10525,7 +10425,6 @@ static void i40e_service_task(struct work_struct *work)
 								pf->vsi[pf->lan_vsi]);
 		}
 		i40e_sync_filters_subtask(pf);
-		i40e_sync_udp_filters_subtask(pf);
 	} else {
 		i40e_reset_subtask(pf);
 	}
@@ -12225,131 +12124,48 @@ static int i40e_set_features(struct net_device *netdev,
 	return 0;
 }
 
-/**
- * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port
- * @pf: board private structure
- * @port: The UDP port to look up
- *
- * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
- **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
-{
-	u8 i;
-
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		/* Do not report ports with pending deletions as
-		 * being available.
-		 */
-		if (!port && (pf->pending_udp_bitmap & BIT_ULL(i)))
-			continue;
-		if (pf->udp_ports[i].port == port)
-			return i;
-	}
-
-	return i;
-}
-
-/**
- * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_add(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_set_port(struct net_device *netdev,
+				    unsigned int table, unsigned int idx,
+				    struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	u8 next_idx;
-	u8 idx;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "port %d already offloaded\n", port);
-		return;
-	}
-
-	/* Now check if there is space to add the new port */
-	next_idx = i40e_get_udp_port_idx(pf, 0);
+	struct i40e_hw *hw = &np->vsi->back->hw;
+	u8 type, filter_index;
+	i40e_status ret;
 
-	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
-			    port);
-		return;
-	}
+	type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? I40E_AQC_TUNNEL_TYPE_VXLAN :
+						   I40E_AQC_TUNNEL_TYPE_NGE;
 
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		if (!(pf->hw_features & I40E_HW_GENEVE_OFFLOAD_CAPABLE))
-			return;
-		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
-		break;
-	default:
-		return;
+	ret = i40e_aq_add_udp_tunnel(hw, ntohs(ti->port), type, &filter_index,
+				     NULL);
+	if (ret) {
+		netdev_info(netdev, "add UDP port failed, err %s aq_err %s\n",
+			    i40e_stat_str(hw, ret),
+			    i40e_aq_str(hw, hw->aq.asq_last_status));
+		return -EIO;
 	}
 
-	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].port = port;
-	pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED;
-	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
+	udp_tunnel_nic_set_port_priv(netdev, table, idx, filter_index);
+	return 0;
 }
 
-/**
- * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_del(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_unset_port(struct net_device *netdev,
+				      unsigned int table, unsigned int idx,
+				      struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	u8 idx;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS)
-		goto not_found;
+	struct i40e_hw *hw = &np->vsi->back->hw;
+	i40e_status ret;
 
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN)
-			goto not_found;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE)
-			goto not_found;
-		break;
-	default:
-		goto not_found;
+	ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL);
+	if (ret) {
+		netdev_info(netdev, "delete UDP port failed, err %s aq_err %s\n",
+			    i40e_stat_str(hw, ret),
+			    i40e_aq_str(hw, hw->aq.asq_last_status));
+		return -EIO;
 	}
 
-	/* if port exists, set it to 0 (mark for deletion)
-	 * and make it pending
-	 */
-	pf->udp_ports[idx].port = 0;
-
-	/* Toggle pending bit instead of setting it. This way if we are
-	 * deleting a port that has yet to be added we just clear the pending
-	 * bit and don't have to worry about it.
-	 */
-	pf->pending_udp_bitmap ^= BIT_ULL(idx);
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-
-	return;
-not_found:
-	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
-		    port);
+	return 0;
 }
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -12955,8 +12771,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofchk,
 	.ndo_set_vf_trust	= i40e_ndo_set_vf_trust,
-	.ndo_udp_tunnel_add	= i40e_udp_tunnel_add,
-	.ndo_udp_tunnel_del	= i40e_udp_tunnel_del,
+	.ndo_udp_tunnel_add	= udp_tunnel_nic_add_port,
+	.ndo_udp_tunnel_del	= udp_tunnel_nic_del_port,
 	.ndo_get_phys_port_id	= i40e_get_phys_port_id,
 	.ndo_fdb_add		= i40e_ndo_fdb_add,
 	.ndo_features_check	= i40e_features_check,
@@ -13020,6 +12836,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE))
 		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
+	netdev->udp_tunnel_nic_info = &pf->udp_tunnel_nic;
+
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
 	netdev->hw_enc_features |= hw_enc_features;
@@ -14420,7 +14238,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 	i40e_ptp_init(pf);
 
 	/* repopulate tunnel port filters */
-	i40e_sync_udp_filters(pf);
+	udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev);
 
 	return ret;
 }
@@ -15149,6 +14967,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_switch_setup;
 
+	pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port;
+	pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port;
+	pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
+	pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared;
+	pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS;
+	pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
+						    UDP_TUNNEL_TYPE_GENEVE;
+
 	/* The number of VSIs reported by the FW is the minimum guaranteed
 	 * to us; HW supports far more and we share the remaining pool with
 	 * the other PFs. We allocate space for more than the guarantee with
@@ -15158,6 +14984,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
 	else
 		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+	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;
+	}
 
 	/* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */
 	pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index d7430ce6af26..2d27f66ac853 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1268,8 +1268,7 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input,
 		bool is_tun = tun == ICE_FD_HW_SEG_TUN;
 		int err;
 
-		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, TNL_ALL,
-							&port_num))
+		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num))
 			continue;
 		err = ice_fdir_write_fltr(pf, input, add, is_tun);
 		if (err)
@@ -1647,8 +1646,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	}
 
 	/* return error if not an update and no available filters */
-	fltrs_needed = ice_get_open_tunnel_port(hw, TNL_ALL, &tunnel_port) ?
-		2 : 1;
+	fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1;
 	if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
 	    ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
 		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 6834df14332f..59c0c6a0f8c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -556,7 +556,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 		memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len);
 		loc = pkt;
 	} else {
-		if (!ice_get_open_tunnel_port(hw, TNL_ALL, &tnl_port))
+		if (!ice_get_open_tunnel_port(hw, &tnl_port))
 			return ICE_ERR_DOES_NOT_EXIST;
 		if (!ice_fdir_pkt[idx].tun_pkt)
 			return ICE_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index b17ae3e20157..ac448d223e9a 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -489,8 +489,6 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
 			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].in_use = false;
-				hw->tnl.tbl[hw->tnl.count].marked = false;
 				hw->tnl.tbl[hw->tnl.count].boost_addr = val;
 				hw->tnl.tbl[hw->tnl.count].port = 0;
 				hw->tnl.count++;
@@ -505,8 +503,11 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
 	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)
+		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]++;
+		}
 	}
 }
 
@@ -1626,104 +1627,59 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
 }
 
 /**
- * ice_tunnel_port_in_use_hlpr - helper function to determine tunnel usage
+ * ice_get_open_tunnel_port - retrieve an open tunnel port
  * @hw: pointer to the HW structure
- * @port: port to search for
- * @index: optionally returns index
- *
- * Returns whether a port is already in use as a tunnel, and optionally its
- * index
+ * @port: returns open port
  */
-static bool ice_tunnel_port_in_use_hlpr(struct ice_hw *hw, u16 port, u16 *index)
+bool
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port)
 {
+	bool res = false;
 	u16 i;
 
+	mutex_lock(&hw->tnl_lock);
+
 	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].in_use && hw->tnl.tbl[i].port == port) {
-			if (index)
-				*index = i;
-			return true;
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) {
+			*port = hw->tnl.tbl[i].port;
+			res = true;
+			break;
 		}
 
-	return false;
-}
-
-/**
- * ice_tunnel_port_in_use
- * @hw: pointer to the HW structure
- * @port: port to search for
- * @index: optionally returns index
- *
- * Returns whether a port is already in use as a tunnel, and optionally its
- * index
- */
-bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index)
-{
-	bool res;
-
-	mutex_lock(&hw->tnl_lock);
-	res = ice_tunnel_port_in_use_hlpr(hw, port, index);
 	mutex_unlock(&hw->tnl_lock);
 
 	return res;
 }
 
 /**
- * ice_find_free_tunnel_entry
+ * ice_tunnel_idx_to_entry - convert linear index to the sparse one
  * @hw: pointer to the HW structure
- * @type: tunnel type
- * @index: optionally returns index
+ * @type: type of tunnel
+ * @idx: linear index
  *
- * Returns whether there is a free tunnel entry, and optionally its index
+ * Stack assumes we have 2 linear tables with indexes [0, count_valid),
+ * but really the port table may be sprase, and types are mixed, so convert
+ * the stack index into the device index.
  */
-static bool
-ice_find_free_tunnel_entry(struct ice_hw *hw, enum ice_tunnel_type type,
-			   u16 *index)
+static u16 ice_tunnel_idx_to_entry(struct ice_hw *hw, enum ice_tunnel_type type,
+				   u16 idx)
 {
 	u16 i;
 
 	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && !hw->tnl.tbl[i].in_use &&
-		    hw->tnl.tbl[i].type == type) {
-			if (index)
-				*index = i;
-			return true;
-		}
+		if (hw->tnl.tbl[i].valid &&
+		    hw->tnl.tbl[i].type == type &&
+		    idx--)
+			return i;
 
-	return false;
-}
-
-/**
- * ice_get_open_tunnel_port - retrieve an open tunnel port
- * @hw: pointer to the HW structure
- * @type: tunnel type (TNL_ALL will return any open port)
- * @port: returns open port
- */
-bool
-ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
-			 u16 *port)
-{
-	bool res = false;
-	u16 i;
-
-	mutex_lock(&hw->tnl_lock);
-
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (type == TNL_ALL || hw->tnl.tbl[i].type == type)) {
-			*port = hw->tnl.tbl[i].port;
-			res = true;
-			break;
-		}
-
-	mutex_unlock(&hw->tnl_lock);
-
-	return res;
+	WARN_ON_ONCE(1);
+	return 0;
 }
 
 /**
  * ice_create_tunnel
  * @hw: pointer to the HW structure
+ * @index: device table entry
  * @type: type of tunnel
  * @port: port of tunnel to create
  *
@@ -1731,27 +1687,16 @@ ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
  * creating a package buffer with the tunnel info and issuing an update package
  * command.
  */
-enum ice_status
-ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
+static enum ice_status
+ice_create_tunnel(struct ice_hw *hw, u16 index,
+		  enum ice_tunnel_type type, u16 port)
 {
 	struct ice_boost_tcam_section *sect_rx, *sect_tx;
 	enum ice_status status = ICE_ERR_MAX_LIMIT;
 	struct ice_buf_build *bld;
-	u16 index;
 
 	mutex_lock(&hw->tnl_lock);
 
-	if (ice_tunnel_port_in_use_hlpr(hw, port, &index)) {
-		hw->tnl.tbl[index].ref++;
-		status = 0;
-		goto ice_create_tunnel_end;
-	}
-
-	if (!ice_find_free_tunnel_entry(hw, type, &index)) {
-		status = ICE_ERR_OUT_OF_RANGE;
-		goto ice_create_tunnel_end;
-	}
-
 	bld = ice_pkg_buf_alloc(hw);
 	if (!bld) {
 		status = ICE_ERR_NO_MEMORY;
@@ -1790,11 +1735,8 @@ ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
 	memcpy(sect_tx->tcam, sect_rx->tcam, sizeof(*sect_tx->tcam));
 
 	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
-	if (!status) {
+	if (!status)
 		hw->tnl.tbl[index].port = port;
-		hw->tnl.tbl[index].in_use = true;
-		hw->tnl.tbl[index].ref = 1;
-	}
 
 ice_create_tunnel_err:
 	ice_pkg_buf_free(hw, bld);
@@ -1808,46 +1750,31 @@ ice_create_tunnel_end:
 /**
  * ice_destroy_tunnel
  * @hw: pointer to the HW structure
+ * @index: device table entry
+ * @type: type of tunnel
  * @port: port of tunnel to destroy (ignored if the all parameter is true)
- * @all: flag that states to destroy all tunnels
  *
  * Destroys a tunnel or all tunnels by creating an update package buffer
  * targeting the specific updates requested and then performing an update
  * package.
  */
-enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
+static enum ice_status
+ice_destroy_tunnel(struct ice_hw *hw, u16 index, enum ice_tunnel_type type,
+		   u16 port)
 {
 	struct ice_boost_tcam_section *sect_rx, *sect_tx;
 	enum ice_status status = ICE_ERR_MAX_LIMIT;
 	struct ice_buf_build *bld;
-	u16 count = 0;
-	u16 index;
-	u16 size;
-	u16 i;
 
 	mutex_lock(&hw->tnl_lock);
 
-	if (!all && ice_tunnel_port_in_use_hlpr(hw, port, &index))
-		if (hw->tnl.tbl[index].ref > 1) {
-			hw->tnl.tbl[index].ref--;
-			status = 0;
-			goto ice_destroy_tunnel_end;
-		}
-
-	/* determine count */
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (all || hw->tnl.tbl[i].port == port))
-			count++;
-
-	if (!count) {
-		status = ICE_ERR_PARAM;
+	if (WARN_ON(!hw->tnl.tbl[index].valid ||
+		    hw->tnl.tbl[index].type != type ||
+		    hw->tnl.tbl[index].port != port)) {
+		status = ICE_ERR_OUT_OF_RANGE;
 		goto ice_destroy_tunnel_end;
 	}
 
-	/* size of section - there is at least one entry */
-	size = struct_size(sect_rx, tcam, count);
-
 	bld = ice_pkg_buf_alloc(hw);
 	if (!bld) {
 		status = ICE_ERR_NO_MEMORY;
@@ -1859,13 +1786,13 @@ enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
 		goto ice_destroy_tunnel_err;
 
 	sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM,
-					    size);
+					    struct_size(sect_rx, tcam, 1));
 	if (!sect_rx)
 		goto ice_destroy_tunnel_err;
 	sect_rx->count = cpu_to_le16(1);
 
 	sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM,
-					    size);
+					    struct_size(sect_tx, tcam, 1));
 	if (!sect_tx)
 		goto ice_destroy_tunnel_err;
 	sect_tx->count = cpu_to_le16(1);
@@ -1873,26 +1800,14 @@ enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
 	/* copy original boost entry to update package buffer, one copy to Rx
 	 * section, another copy to the Tx section
 	 */
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (all || hw->tnl.tbl[i].port == port)) {
-			memcpy(sect_rx->tcam + i, hw->tnl.tbl[i].boost_entry,
-			       sizeof(*sect_rx->tcam));
-			memcpy(sect_tx->tcam + i, hw->tnl.tbl[i].boost_entry,
-			       sizeof(*sect_tx->tcam));
-			hw->tnl.tbl[i].marked = true;
-		}
+	memcpy(sect_rx->tcam, hw->tnl.tbl[index].boost_entry,
+	       sizeof(*sect_rx->tcam));
+	memcpy(sect_tx->tcam, hw->tnl.tbl[index].boost_entry,
+	       sizeof(*sect_tx->tcam));
 
 	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
 	if (!status)
-		for (i = 0; i < hw->tnl.count &&
-		     i < ICE_TUNNEL_MAX_ENTRIES; i++)
-			if (hw->tnl.tbl[i].marked) {
-				hw->tnl.tbl[i].ref = 0;
-				hw->tnl.tbl[i].port = 0;
-				hw->tnl.tbl[i].in_use = false;
-				hw->tnl.tbl[i].marked = false;
-			}
+		hw->tnl.tbl[index].port = 0;
 
 ice_destroy_tunnel_err:
 	ice_pkg_buf_free(hw, bld);
@@ -1903,6 +1818,52 @@ ice_destroy_tunnel_end:
 	return status;
 }
 
+int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
+			    unsigned int idx, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	enum ice_tunnel_type tnl_type;
+	enum ice_status status;
+	u16 index;
+
+	tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE;
+	index = ice_tunnel_idx_to_entry(&pf->hw, idx, tnl_type);
+
+	status = ice_create_tunnel(&pf->hw, index, tnl_type, ntohs(ti->port));
+	if (status) {
+		netdev_err(netdev, "Error adding UDP tunnel - %s\n",
+			   ice_stat_str(status));
+		return -EIO;
+	}
+
+	udp_tunnel_nic_set_port_priv(netdev, table, idx, index);
+	return 0;
+}
+
+int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
+			      unsigned int idx, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	enum ice_tunnel_type tnl_type;
+	enum ice_status status;
+
+	tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE;
+
+	status = ice_destroy_tunnel(&pf->hw, ti->hw_priv, tnl_type,
+				    ntohs(ti->port));
+	if (status) {
+		netdev_err(netdev, "Error removing UDP tunnel - %s\n",
+			   ice_stat_str(status));
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /* PTG Management */
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 568ea519af51..20deddb807c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -19,12 +19,11 @@
 #define ICE_PKG_CNT 4
 
 bool
-ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
-			 u16 *port);
-enum ice_status
-ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port);
-enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all);
-bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index);
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port);
+int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
+			    unsigned int idx, struct udp_tunnel_info *ti);
+int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
+			      unsigned int idx, struct udp_tunnel_info *ti);
 
 enum ice_status
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index c1c99a267a98..24063c1351b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -298,6 +298,7 @@ struct ice_pkg_enum {
 enum ice_tunnel_type {
 	TNL_VXLAN = 0,
 	TNL_GENEVE,
+	__TNL_TYPE_CNT,
 	TNL_LAST = 0xFF,
 	TNL_ALL = 0xFF,
 };
@@ -311,11 +312,8 @@ struct ice_tunnel_entry {
 	enum ice_tunnel_type type;
 	u16 boost_addr;
 	u16 port;
-	u16 ref;
 	struct ice_boost_tcam_entry *boost_entry;
 	u8 valid;
-	u8 in_use;
-	u8 marked;
 };
 
 #define ICE_TUNNEL_MAX_ENTRIES	16
@@ -323,6 +321,7 @@ struct ice_tunnel_entry {
 struct ice_tunnel_table {
 	struct ice_tunnel_entry tbl[ICE_TUNNEL_MAX_ENTRIES];
 	u16 count;
+	u16 valid_count[__TNL_TYPE_CNT];
 };
 
 struct ice_pkg_es {
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2297ee7dba26..ffef4c901ea2 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2873,6 +2873,7 @@ 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);
 }
 
@@ -3978,7 +3979,7 @@ 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;
+	int i, err;
 
 	/* this driver uses devres, see
 	 * Documentation/driver-api/driver-model/devres.rst
@@ -4073,11 +4074,37 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	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.tnl.valid_count[TNL_VXLAN];
+		pf->hw.udp_tunnel_nic.tables[i].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.tnl.valid_count[TNL_GENEVE];
+		pf->hw.udp_tunnel_nic.tables[i].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);
@@ -6575,70 +6602,6 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 }
 
 /**
- * ice_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- */
-static void
-ice_udp_tunnel_add(struct net_device *netdev, struct udp_tunnel_info *ti)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
-	enum ice_tunnel_type tnl_type;
-	u16 port = ntohs(ti->port);
-	enum ice_status status;
-
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		tnl_type = TNL_VXLAN;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		tnl_type = TNL_GENEVE;
-		break;
-	default:
-		netdev_err(netdev, "Unknown tunnel type\n");
-		return;
-	}
-
-	status = ice_create_tunnel(&pf->hw, tnl_type, port);
-	if (status == ICE_ERR_OUT_OF_RANGE)
-		netdev_info(netdev, "Max tunneled UDP ports reached, port %d not added\n",
-			    port);
-	else if (status)
-		netdev_err(netdev, "Error adding UDP tunnel - %s\n",
-			   ice_stat_str(status));
-}
-
-/**
- * ice_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- */
-static void
-ice_udp_tunnel_del(struct net_device *netdev, struct udp_tunnel_info *ti)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	enum ice_status status;
-	bool retval;
-
-	retval = ice_tunnel_port_in_use(&pf->hw, port, NULL);
-	if (!retval) {
-		netdev_info(netdev, "port %d not found in UDP tunnels list\n",
-			    port);
-		return;
-	}
-
-	status = ice_destroy_tunnel(&pf->hw, port, false);
-	if (status)
-		netdev_err(netdev, "error deleting port %d from UDP tunnels list\n",
-			   port);
-}
-
-/**
  * ice_open - Called when a network interface becomes active
  * @netdev: network interface device structure
  *
@@ -6830,6 +6793,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_bpf = ice_xdp,
 	.ndo_xdp_xmit = ice_xdp_xmit,
 	.ndo_xsk_wakeup = ice_xsk_wakeup,
-	.ndo_udp_tunnel_add = ice_udp_tunnel_add,
-	.ndo_udp_tunnel_del = ice_udp_tunnel_del,
+	.ndo_udp_tunnel_add = udp_tunnel_nic_add_port,
+	.ndo_udp_tunnel_del = udp_tunnel_nic_del_port,
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4cdccfadf274..2226a291a394 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -676,6 +676,9 @@ struct ice_hw {
 	struct mutex tnl_lock;
 	struct ice_tunnel_table tnl;
 
+	struct udp_tunnel_nic_shared udp_tunnel_shared;
+	struct udp_tunnel_nic_info udp_tunnel_nic;
+
 	/* HW block tables */
 	struct ice_blk_info blk[ICE_BLK_COUNT];
 	struct mutex fl_profs_locks[ICE_BLK_COUNT];	/* lock fltr profiles */