Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2025-11-06 (i40, ice, iavf)

Mohammad Heib introduces a new devlink parameter, max_mac_per_vf, for
controlling the maximum number of MAC address filters allowed by a VF. This
allows administrators to control the VF behavior in a more nuanced manner.

Aleksandr and Przemek add support for Receive Side Scaling of GTP to iAVF
for VFs running on E800 series ice hardware. This improves performance and
scalability for virtualized network functions in 5G and LTE deployments.

* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  iavf: add RSS support for GTP protocol via ethtool
  ice: Extend PTYPE bitmap coverage for GTP encapsulated flows
  ice: improve TCAM priority handling for RSS profiles
  ice: implement GTP RSS context tracking and configuration
  ice: add virtchnl definitions and static data for GTP RSS
  ice: add flow parsing for GTP and new protocol field support
  i40e: support generic devlink param "max_mac_per_vf"
  devlink: Add new "max_mac_per_vf" generic device param
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/networking/devlink/devlink-params.rst

@@ -151,3 +151,7 @@ own name.
    * - ``num_doorbells``
      - u32
      - Controls the number of doorbells used by the device.
+   * - ``max_mac_per_vf``
+     - u32
+     - Controls the maximum number of MAC address filters that can be assigned
+       to a Virtual Function (VF).

Documentation/networking/devlink/i40e.rst

@@ -7,6 +7,40 @@ i40e devlink support
 This document describes the devlink features implemented by the ``i40e``
 device driver.
 
+Parameters
+==========
+
+.. list-table:: Generic parameters implemented
+    :widths: 5 5 90
+
+    * - Name
+      - Mode
+      - Notes
+    * - ``max_mac_per_vf``
+      - runtime
+      - Controls the maximum number of MAC addresses a VF can use
+        on i40e devices.
+
+        By default (``0``), the driver enforces its internally calculated per-VF
+        MAC filter limit, which is based on the number of allocated VFS.
+
+        If set to a non-zero value, this parameter acts as a strict cap:
+        the driver will use the user-provided value instead of its internal
+        calculation.
+
+        **Important notes:**
+
+        - This value **must be set before enabling SR-IOV**.
+          Attempting to change it while SR-IOV is enabled will return an error.
+        - MAC filters are a **shared hardware resource** across all VFs.
+          Setting a high value may cause other VFs to be starved of filters.
+        - This value is a **Administrative policy**. The hardware may return
+          errors when its absolute limit is reached, regardless of the value
+          set here.
+
+        The default value is ``0`` (internal calculation is used).
+
+
 Info versions
 =============
 

drivers/net/ethernet/intel/i40e/i40e.h

@@ -574,6 +574,10 @@ struct i40e_pf {
 	struct i40e_vf *vf;
 	int num_alloc_vfs;	/* actual number of VFs allocated */
 	u32 vf_aq_requests;
+	/* If set to non-zero, the device uses this value
+	 * as maximum number of MAC filters per VF.
+	 */
+	u32 max_mac_per_vf;
 	u32 arq_overflows;	/* Not fatal, possibly indicative of problems */
 	struct ratelimit_state mdd_message_rate_limit;
 	/* DCBx/DCBNL capability for PF that indicates

drivers/net/ethernet/intel/i40e/i40e_devlink.c

@@ -5,6 +5,41 @@
 #include "i40e.h"
 #include "i40e_devlink.h"
 
+static int i40e_max_mac_per_vf_set(struct devlink *devlink,
+				   u32 id,
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	if (pf->num_alloc_vfs > 0) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot change max_mac_per_vf while SR-IOV is enabled");
+		return -EBUSY;
+	}
+
+	pf->max_mac_per_vf = ctx->val.vu32;
+	return 0;
+}
+
+static int i40e_max_mac_per_vf_get(struct devlink *devlink,
+				   u32 id,
+				   struct devlink_param_gset_ctx *ctx)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	ctx->val.vu32 = pf->max_mac_per_vf;
+	return 0;
+}
+
+static const struct devlink_param i40e_dl_params[] = {
+	DEVLINK_PARAM_GENERIC(MAX_MAC_PER_VF,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			      i40e_max_mac_per_vf_get,
+			      i40e_max_mac_per_vf_set,
+			      NULL),
+};
+
 static void i40e_info_get_dsn(struct i40e_pf *pf, char *buf, size_t len)
 {
 	u8 dsn[8];
@@ -165,7 +200,18 @@ void i40e_free_pf(struct i40e_pf *pf)
  **/
 void i40e_devlink_register(struct i40e_pf *pf)
 {
-	devlink_register(priv_to_devlink(pf));
+	struct devlink *dl = priv_to_devlink(pf);
+	struct device *dev = &pf->pdev->dev;
+	int err;
+
+	err = devlink_params_register(dl, i40e_dl_params,
+				      ARRAY_SIZE(i40e_dl_params));
+	if (err)
+		dev_err(dev,
+			"devlink params register failed with error %d", err);
+
+	devlink_register(dl);
+
 }
 
 /**
@@ -176,7 +222,11 @@ void i40e_devlink_register(struct i40e_pf *pf)
  **/
 void i40e_devlink_unregister(struct i40e_pf *pf)
 {
-	devlink_unregister(priv_to_devlink(pf));
+	struct devlink *dl = priv_to_devlink(pf);
+
+	devlink_unregister(dl);
+	devlink_params_unregister(dl, i40e_dl_params,
+				  ARRAY_SIZE(i40e_dl_params));
 }
 
 /**

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -2935,33 +2935,48 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		if (!f)
 			++mac_add_cnt;
 	}
-
-	/* If this VF is not privileged, then we can't add more than a limited
-	 * number of addresses.
+	/* Determine the maximum number of MAC addresses this VF may use.
+	 *
+	 * - For untrusted VFs: use a fixed small limit.
+	 *
+	 * - For trusted VFs: limit is calculated by dividing total MAC
+	 *  filter pool across all VFs/ports.
 	 *
-	 * If this VF is trusted, it can use more resources than untrusted.
-	 * However to ensure that every trusted VF has appropriate number of
-	 * resources, divide whole pool of resources per port and then across
-	 * all VFs.
+	 * - User can override this by devlink param "max_mac_per_vf".
+	 *   If set its value is used as a strict cap for both trusted and
+	 *   untrusted VFs.
+	 *   Note:
+	 *    even when overridden, this is a theoretical maximum; hardware
+	 *    may reject additional MACs if the absolute HW limit is reached.
 	 */
 	if (!vf_trusted)
 		mac_add_max = I40E_VC_MAX_MAC_ADDR_PER_VF;
 	else
 		mac_add_max = I40E_VC_MAX_MACVLAN_PER_TRUSTED_VF(pf->num_alloc_vfs, hw->num_ports);
 
+	if (pf->max_mac_per_vf > 0)
+		mac_add_max = pf->max_mac_per_vf;
+
 	/* VF can replace all its filters in one step, in this case mac_add_max
 	 * will be added as active and another mac_add_max will be in
 	 * a to-be-removed state. Account for that.
 	 */
 	if ((i40e_count_active_filters(vsi) + mac_add_cnt) > mac_add_max ||
 	    (i40e_count_all_filters(vsi) + mac_add_cnt) > 2 * mac_add_max) {
+		if (pf->max_mac_per_vf == mac_add_max && mac_add_max > 0) {
+			dev_err(&pf->pdev->dev,
+				"Cannot add more MAC addresses: VF reached its maximum allowed limit (%d)\n",
+				mac_add_max);
+				return -EPERM;
+		}
 		if (!vf_trusted) {
 			dev_err(&pf->pdev->dev,
 				"Cannot add more MAC addresses, VF is not trusted, switch the VF to trusted to add more functionality\n");
 			return -EPERM;
 		} else {
 			dev_err(&pf->pdev->dev,
-				"Cannot add more MAC addresses, trusted VF exhausted it's resources\n");
+				"Cannot add more MAC addresses: trusted VF reached its maximum allowed limit (%d)\n",
+				mac_add_max);
 			return -EPERM;
 		}
 	}

drivers/net/ethernet/intel/iavf/iavf_adv_rss.c

@@ -90,6 +90,55 @@ iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds)
 		VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, DST_PORT);
 }
 
+/**
+ * iavf_fill_adv_rss_gtp_hdr - Fill GTP-related RSS protocol headers
+ * @proto_hdrs: pointer to the virtchnl protocol headers structure to populate
+ * @packet_hdrs: bitmask of packet header types to configure
+ * @hash_flds: RSS hash field configuration
+ *
+ * This function populates the virtchnl protocol header structure with
+ * appropriate GTP-related header types based on the specified packet_hdrs.
+ * It supports GTPC, GTPU with extension headers, and uplink/downlink PDU
+ * types. For certain GTPU types, it also appends an IPv4 header to enable
+ * hashing on the destination IP address.
+ *
+ * Return: 0 on success or -EOPNOTSUPP if the packet_hdrs value is unsupported.
+ */
+static int
+iavf_fill_adv_rss_gtp_hdr(struct virtchnl_proto_hdrs *proto_hdrs,
+			  u32 packet_hdrs, u64 hash_flds)
+{
+	struct virtchnl_proto_hdr *hdr;
+
+	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1];
+
+	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) {
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID:
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPC);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_UP);
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA);
+		break;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN:
+		VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_DWN);
+		fallthrough;
+	case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP:
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 /**
  * iavf_fill_adv_rss_cfg_msg - fill the RSS configuration into virtchnl message
  * @rss_cfg: the virtchnl message to be filled with RSS configuration setting
@@ -103,6 +152,8 @@ int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
 			  u32 packet_hdrs, u64 hash_flds, bool symm)
 {
+	const u32 packet_l3_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3;
+	const u32 packet_l4_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4;
 	struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs;
 	struct virtchnl_proto_hdr *hdr;
 
@@ -113,31 +164,41 @@ iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
 
 	proto_hdrs->tunnel_level = 0;	/* always outer layer */
 
-	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
-	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3) {
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4:
-		iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6:
-		iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds);
-		break;
-	default:
-		return -EINVAL;
+	if (packet_l3_hdrs) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		switch (packet_l3_hdrs) {
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4:
+			iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6:
+			iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds);
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
-	hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
-	switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4) {
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP:
-		iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP:
-		iavf_fill_adv_rss_udp_hdr(hdr, hash_flds);
-		break;
-	case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP:
-		iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds);
-		break;
-	default:
-		return -EINVAL;
+	if (packet_l4_hdrs) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		switch (packet_l4_hdrs) {
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP:
+			iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP:
+			iavf_fill_adv_rss_udp_hdr(hdr, hash_flds);
+			break;
+		case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP:
+			iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) {
+		hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++];
+		if (iavf_fill_adv_rss_gtp_hdr(proto_hdrs, packet_hdrs, hash_flds))
+			return -EINVAL;
 	}
 
 	return 0;
@@ -186,6 +247,8 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss,
 		proto = "UDP";
 	else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP)
 		proto = "SCTP";
+	else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP)
+		proto = "GTP";
 	else
 		return;
 
@@ -211,6 +274,16 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss,
 			 IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT |
 			 IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT))
 		strcat(hash_opt, "dst port,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPC_TEID)
+		strcat(hash_opt, "gtp-c,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID)
+		strcat(hash_opt, "gtp-u ip,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID)
+		strcat(hash_opt, "gtp-u ext,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID)
+		strcat(hash_opt, "gtp-u ul,");
+	if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID)
+		strcat(hash_opt, "gtp-u dl,");
 
 	if (!action)
 		action = "";