Merge tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Introduce a config option to tweak MAX_SKB_FRAGS. Increasing the
     default value allows for better BIG TCP performances

   - Reduce compound page head access for zero-copy data transfers

   - RPS/RFS improvements, avoiding unneeded NET_RX_SOFTIRQ when
     possible

   - Threaded NAPI improvements, adding defer skb free support and
     unneeded softirq avoidance

   - Address dst_entry reference count scalability issues, via false
     sharing avoidance and optimize refcount tracking

   - Add lockless accesses annotation to sk_err[_soft]

   - Optimize again the skb struct layout

   - Extends the skb drop reasons to make it usable by multiple
     subsystems

   - Better const qualifier awareness for socket casts

  BPF:

   - Add skb and XDP typed dynptrs which allow BPF programs for more
     ergonomic and less brittle iteration through data and
     variable-sized accesses

   - Add a new BPF netfilter program type and minimal support to hook
     BPF programs to netfilter hooks such as prerouting or forward

   - Add more precise memory usage reporting for all BPF map types

   - Adds support for using {FOU,GUE} encap with an ipip device
     operating in collect_md mode and add a set of BPF kfuncs for
     controlling encap params

   - Allow BPF programs to detect at load time whether a particular
     kfunc exists or not, and also add support for this in light
     skeleton

   - Bigger batch of BPF verifier improvements to prepare for upcoming
     BPF open-coded iterators allowing for less restrictive looping
     capabilities

   - Rework RCU enforcement in the verifier, add kptr_rcu and enforce
     BPF programs to NULL-check before passing such pointers into kfunc

   - Add support for kptrs in percpu hashmaps, percpu LRU hashmaps and
     in local storage maps

   - Enable RCU semantics for task BPF kptrs and allow referenced kptr
     tasks to be stored in BPF maps

   - Add support for refcounted local kptrs to the verifier for allowing
     shared ownership, useful for adding a node to both the BPF list and
     rbtree

   - Add BPF verifier support for ST instructions in
     convert_ctx_access() which will help new -mcpu=v4 clang flag to
     start emitting them

   - Add ARM32 USDT support to libbpf

   - Improve bpftool's visual program dump which produces the control
     flow graph in a DOT format by adding C source inline annotations

  Protocols:

   - IPv4: Allow adding to IPv4 address a 'protocol' tag. Such value
     indicates the provenance of the IP address

   - IPv6: optimize route lookup, dropping unneeded R/W lock acquisition

   - Add the handshake upcall mechanism, allowing the user-space to
     implement generic TLS handshake on kernel's behalf

   - Bridge: support per-{Port, VLAN} neighbor suppression, increasing
     resilience to nodes failures

   - SCTP: add support for Fair Capacity and Weighted Fair Queueing
     schedulers

   - MPTCP: delay first subflow allocation up to its first usage. This
     will allow for later better LSM interaction

   - xfrm: Remove inner/outer modes from input/output path. These are
     not needed anymore

   - WiFi:
      - reduced neighbor report (RNR) handling for AP mode
      - HW timestamping support
      - support for randomized auth/deauth TA for PASN privacy
      - per-link debugfs for multi-link
      - TC offload support for mac80211 drivers
      - mac80211 mesh fast-xmit and fast-rx support
      - enable Wi-Fi 7 (EHT) mesh support

  Netfilter:

   - Add nf_tables 'brouting' support, to force a packet to be routed
     instead of being bridged

   - Update bridge netfilter and ovs conntrack helpers to handle IPv6
     Jumbo packets properly, i.e. fetch the packet length from
     hop-by-hop extension header. This is needed for BIT TCP support

   - The iptables 32bit compat interface isn't compiled in by default
     anymore

   - Move ip(6)tables builtin icmp matches to the udptcp one. This has
     the advantage that icmp/icmpv6 match doesn't load the
     iptables/ip6tables modules anymore when iptables-nft is used

   - Extended netlink error report for netdevice in flowtables and
     netdev/chains. Allow for incrementally add/delete devices to netdev
     basechain. Allow to create netdev chain without device

  Driver API:

   - Remove redundant Device Control Error Reporting Enable, as PCI core
     has already error reporting enabled at enumeration time

   - Move Multicast DB netlink handlers to core, allowing devices other
     then bridge to use them

   - Allow the page_pool to directly recycle the pages from safely
     localized NAPI

   - Implement lockless TX queue stop/wake combo macros, allowing for
     further code de-duplication and sanitization

   - Add YNL support for user headers and struct attrs

   - Add partial YNL specification for devlink

   - Add partial YNL specification for ethtool

   - Add tc-mqprio and tc-taprio support for preemptible traffic classes

   - Add tx push buf len param to ethtool, specifies the maximum number
     of bytes of a transmitted packet a driver can push directly to the
     underlying device

   - Add basic LED support for switch/phy

   - Add NAPI documentation, stop relaying on external links

   - Convert dsa_master_ioctl() to netdev notifier. This is a
     preparatory work to make the hardware timestamping layer selectable
     by user space

   - Add transceiver support and improve the error messages for CAN-FD
     controllers

  New hardware / drivers:

   - Ethernet:
      - AMD/Pensando core device support
      - MediaTek MT7981 SoC
      - MediaTek MT7988 SoC
      - Broadcom BCM53134 embedded switch
      - Texas Instruments CPSW9G ethernet switch
      - Qualcomm EMAC3 DWMAC ethernet
      - StarFive JH7110 SoC
      - NXP CBTX ethernet PHY

   - WiFi:
      - Apple M1 Pro/Max devices
      - RealTek rtl8710bu/rtl8188gu
      - RealTek rtl8822bs, rtl8822cs and rtl8821cs SDIO chipset

   - Bluetooth:
      - Realtek RTL8821CS, RTL8851B, RTL8852BS
      - Mediatek MT7663, MT7922
      - NXP w8997
      - Actions Semi ATS2851
      - QTI WCN6855
      - Marvell 88W8997

   - Can:
      - STMicroelectronics bxcan stm32f429

  Drivers:

   - Ethernet NICs:
      - Intel (1G, icg):
         - add tracking and reporting of QBV config errors
         - add support for configuring max SDU for each Tx queue
      - Intel (100G, ice):
         - refactor mailbox overflow detection to support Scalable IOV
         - GNSS interface optimization
      - Intel (i40e):
         - support XDP multi-buffer
      - nVidia/Mellanox:
         - add the support for linux bridge multicast offload
         - enable TC offload for egress and engress MACVLAN over bond
         - add support for VxLAN GBP encap/decap flows offload
         - extend packet offload to fully support libreswan
         - support tunnel mode in mlx5 IPsec packet offload
         - extend XDP multi-buffer support
         - support MACsec VLAN offload
         - add support for dynamic msix vectors allocation
         - drop RX page_cache and fully use page_pool
         - implement thermal zone to report NIC temperature
      - Netronome/Corigine:
         - add support for multi-zone conntrack offload
      - Solarflare/Xilinx:
         - support offloading TC VLAN push/pop actions to the MAE
         - support TC decap rules
         - support unicast PTP

   - Other NICs:
      - Broadcom (bnxt): enforce software based freq adjustments only on
        shared PHC NIC
      - RealTek (r8169): refactor to addess ASPM issues during NAPI poll
      - Micrel (lan8841): add support for PTP_PF_PEROUT
      - Cadence (macb): enable PTP unicast
      - Engleder (tsnep): add XDP socket zero-copy support
      - virtio-net: implement exact header length guest feature
      - veth: add page_pool support for page recycling
      - vxlan: add MDB data path support
      - gve: add XDP support for GQI-QPL format
      - geneve: accept every ethertype
      - macvlan: allow some packets to bypass broadcast queue
      - mana: add support for jumbo frame

   - Ethernet high-speed switches:
      - Microchip (sparx5): Add support for TC flower templates

   - Ethernet embedded switches:
      - Broadcom (b54):
         - configure 6318 and 63268 RGMII ports
      - Marvell (mv88e6xxx):
         - faster C45 bus scan
      - Microchip:
         - lan966x:
            - add support for IS1 VCAP
            - better TX/RX from/to CPU performances
         - ksz9477: add ETS Qdisc support
         - ksz8: enhance static MAC table operations and error handling
         - sama7g5: add PTP capability
      - NXP (ocelot):
         - add support for external ports
         - add support for preemptible traffic classes
      - Texas Instruments:
         - add CPSWxG SGMII support for J7200 and J721E

   - Intel WiFi (iwlwifi):
      - preparation for Wi-Fi 7 EHT and multi-link support
      - EHT (Wi-Fi 7) sniffer support
      - hardware timestamping support for some devices/firwmares
      - TX beacon protection on newer hardware

   - Qualcomm 802.11ax WiFi (ath11k):
      - MU-MIMO parameters support
      - ack signal support for management packets

   - RealTek WiFi (rtw88):
      - SDIO bus support
      - better support for some SDIO devices (e.g. MAC address from
        efuse)

   - RealTek WiFi (rtw89):
      - HW scan support for 8852b
      - better support for 6 GHz scanning
      - support for various newer firmware APIs
      - framework firmware backwards compatibility

   - MediaTek WiFi (mt76):
      - P2P support
      - mesh A-MSDU support
      - EHT (Wi-Fi 7) support
      - coredump support"

* tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2078 commits)
  net: phy: hide the PHYLIB_LEDS knob
  net: phy: marvell-88x2222: remove unnecessary (void*) conversions
  tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp.
  net: amd: Fix link leak when verifying config failed
  net: phy: marvell: Fix inconsistent indenting in led_blink_set
  lan966x: Don't use xdp_frame when action is XDP_TX
  tsnep: Add XDP socket zero-copy TX support
  tsnep: Add XDP socket zero-copy RX support
  tsnep: Move skb receive action to separate function
  tsnep: Add functions for queue enable/disable
  tsnep: Rework TX/RX queue initialization
  tsnep: Replace modulo operation with mask
  net: phy: dp83867: Add led_brightness_set support
  net: phy: Fix reading LED reg property
  drivers: nfc: nfcsim: remove return value check of `dev_dir`
  net: phy: dp83867: Remove unnecessary (void*) conversions
  net: ethtool: coalesce: try to make user settings stick twice
  net: mana: Check if netdev/napi_alloc_frag returns single page
  net: mana: Rename mana_refill_rxoob and remove some empty lines
  net: veth: add page_pool stats
  ...

1 files changed, 210 insertions, 11 deletions

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
index f960727ecaee..47b2f7579dd2 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c
@@ -5,14 +5,34 @@
 #include "vcap_api_client.h"
 #include "vcap_tc.h"
 
-static bool lan966x_tc_is_known_etype(u16 etype)
+static bool lan966x_tc_is_known_etype(struct vcap_tc_flower_parse_usage *st,
+				      u16 etype)
 {
-	switch (etype) {
-	case ETH_P_ALL:
-	case ETH_P_ARP:
-	case ETH_P_IP:
-	case ETH_P_IPV6:
-		return true;
+	switch (st->admin->vtype) {
+	case VCAP_TYPE_IS1:
+		switch (etype) {
+		case ETH_P_ALL:
+		case ETH_P_ARP:
+		case ETH_P_IP:
+		case ETH_P_IPV6:
+			return true;
+		}
+		break;
+	case VCAP_TYPE_IS2:
+		switch (etype) {
+		case ETH_P_ALL:
+		case ETH_P_ARP:
+		case ETH_P_IP:
+		case ETH_P_IPV6:
+		case ETH_P_SNAP:
+		case ETH_P_802_2:
+			return true;
+		}
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(st->fco->common.extack,
+				   "VCAP type not supported");
+		return false;
 	}
 
 	return false;
@@ -69,7 +89,7 @@ lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st)
 	flow_rule_match_basic(st->frule, &match);
 	if (match.mask->n_proto) {
 		st->l3_proto = be16_to_cpu(match.key->n_proto);
-		if (!lan966x_tc_is_known_etype(st->l3_proto)) {
+		if (!lan966x_tc_is_known_etype(st, st->l3_proto)) {
 			err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE,
 						    st->l3_proto, ~0);
 			if (err)
@@ -79,18 +99,61 @@ lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st)
 						    VCAP_BIT_1);
 			if (err)
 				goto out;
+		} else if (st->l3_proto == ETH_P_IPV6 &&
+			   st->admin->vtype == VCAP_TYPE_IS1) {
+			/* Don't set any keys in this case */
+		} else if (st->l3_proto == ETH_P_SNAP &&
+			   st->admin->vtype == VCAP_TYPE_IS1) {
+			err = vcap_rule_add_key_bit(st->vrule,
+						    VCAP_KF_ETYPE_LEN_IS,
+						    VCAP_BIT_0);
+			if (err)
+				goto out;
+
+			err = vcap_rule_add_key_bit(st->vrule,
+						    VCAP_KF_IP_SNAP_IS,
+						    VCAP_BIT_1);
+			if (err)
+				goto out;
+		} else if (st->admin->vtype == VCAP_TYPE_IS1) {
+			err = vcap_rule_add_key_bit(st->vrule,
+						    VCAP_KF_ETYPE_LEN_IS,
+						    VCAP_BIT_1);
+			if (err)
+				goto out;
+
+			err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE,
+						    st->l3_proto, ~0);
+			if (err)
+				goto out;
 		}
 	}
 	if (match.mask->ip_proto) {
 		st->l4_proto = match.key->ip_proto;
 
 		if (st->l4_proto == IPPROTO_TCP) {
+			if (st->admin->vtype == VCAP_TYPE_IS1) {
+				err = vcap_rule_add_key_bit(st->vrule,
+							    VCAP_KF_TCP_UDP_IS,
+							    VCAP_BIT_1);
+				if (err)
+					goto out;
+			}
+
 			err = vcap_rule_add_key_bit(st->vrule,
 						    VCAP_KF_TCP_IS,
 						    VCAP_BIT_1);
 			if (err)
 				goto out;
 		} else if (st->l4_proto == IPPROTO_UDP) {
+			if (st->admin->vtype == VCAP_TYPE_IS1) {
+				err = vcap_rule_add_key_bit(st->vrule,
+							    VCAP_KF_TCP_UDP_IS,
+							    VCAP_BIT_1);
+				if (err)
+					goto out;
+			}
+
 			err = vcap_rule_add_key_bit(st->vrule,
 						    VCAP_KF_TCP_IS,
 						    VCAP_BIT_0);
@@ -113,11 +176,29 @@ out:
 }
 
 static int
+lan966x_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st)
+{
+	if (st->admin->vtype != VCAP_TYPE_IS1) {
+		NL_SET_ERR_MSG_MOD(st->fco->common.extack,
+				   "cvlan not supported in this VCAP");
+		return -EINVAL;
+	}
+
+	return vcap_tc_flower_handler_cvlan_usage(st);
+}
+
+static int
 lan966x_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st)
 {
-	return vcap_tc_flower_handler_vlan_usage(st,
-						 VCAP_KF_8021Q_VID_CLS,
-						 VCAP_KF_8021Q_PCP_CLS);
+	enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS;
+	enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS;
+
+	if (st->admin->vtype == VCAP_TYPE_IS1) {
+		vid_key = VCAP_KF_8021Q_VID0;
+		pcp_key = VCAP_KF_8021Q_PCP0;
+	}
+
+	return vcap_tc_flower_handler_vlan_usage(st, vid_key, pcp_key);
 }
 
 static int
@@ -128,6 +209,7 @@ static int
 	[FLOW_DISSECTOR_KEY_CONTROL] = lan966x_tc_flower_handler_control_usage,
 	[FLOW_DISSECTOR_KEY_PORTS] = vcap_tc_flower_handler_portnum_usage,
 	[FLOW_DISSECTOR_KEY_BASIC] = lan966x_tc_flower_handler_basic_usage,
+	[FLOW_DISSECTOR_KEY_CVLAN] = lan966x_tc_flower_handler_cvlan_usage,
 	[FLOW_DISSECTOR_KEY_VLAN] = lan966x_tc_flower_handler_vlan_usage,
 	[FLOW_DISSECTOR_KEY_TCP] = vcap_tc_flower_handler_tcp_usage,
 	[FLOW_DISSECTOR_KEY_ARP] = vcap_tc_flower_handler_arp_usage,
@@ -143,6 +225,7 @@ static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f,
 		.fco = f,
 		.vrule = vrule,
 		.l3_proto = ETH_P_ALL,
+		.admin = admin,
 	};
 	int err = 0;
 
@@ -221,6 +304,100 @@ static int lan966x_tc_flower_action_check(struct vcap_control *vctrl,
 	return 0;
 }
 
+/* Add the actionset that is the default for the VCAP type */
+static int lan966x_tc_set_actionset(struct vcap_admin *admin,
+				    struct vcap_rule *vrule)
+{
+	enum vcap_actionfield_set aset;
+	int err = 0;
+
+	switch (admin->vtype) {
+	case VCAP_TYPE_IS1:
+		aset = VCAP_AFS_S1;
+		break;
+	case VCAP_TYPE_IS2:
+		aset = VCAP_AFS_BASE_TYPE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Do not overwrite any current actionset */
+	if (vrule->actionset == VCAP_AFS_NO_VALUE)
+		err = vcap_set_rule_set_actionset(vrule, aset);
+
+	return err;
+}
+
+static int lan966x_tc_add_rule_link_target(struct vcap_admin *admin,
+					   struct vcap_rule *vrule,
+					   int target_cid)
+{
+	int link_val = target_cid % VCAP_CID_LOOKUP_SIZE;
+	int err;
+
+	if (!link_val)
+		return 0;
+
+	switch (admin->vtype) {
+	case VCAP_TYPE_IS1:
+		/* Choose IS1 specific NXT_IDX key (for chaining rules from IS1) */
+		err = vcap_rule_add_key_u32(vrule, VCAP_KF_LOOKUP_GEN_IDX_SEL,
+					    1, ~0);
+		if (err)
+			return err;
+
+		return vcap_rule_add_key_u32(vrule, VCAP_KF_LOOKUP_GEN_IDX,
+					     link_val, ~0);
+	case VCAP_TYPE_IS2:
+		/* Add IS2 specific PAG key (for chaining rules from IS1) */
+		return vcap_rule_add_key_u32(vrule, VCAP_KF_LOOKUP_PAG,
+					     link_val, ~0);
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int lan966x_tc_add_rule_link(struct vcap_control *vctrl,
+				    struct vcap_admin *admin,
+				    struct vcap_rule *vrule,
+				    struct flow_cls_offload *f,
+				    int to_cid)
+{
+	struct vcap_admin *to_admin = vcap_find_admin(vctrl, to_cid);
+	int diff, err = 0;
+
+	if (!to_admin) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "Unknown destination chain");
+		return -EINVAL;
+	}
+
+	diff = vcap_chain_offset(vctrl, f->common.chain_index, to_cid);
+	if (!diff)
+		return 0;
+
+	/* Between IS1 and IS2 the PAG value is used */
+	if (admin->vtype == VCAP_TYPE_IS1 && to_admin->vtype == VCAP_TYPE_IS2) {
+		/* This works for IS1->IS2 */
+		err = vcap_rule_add_action_u32(vrule, VCAP_AF_PAG_VAL, diff);
+		if (err)
+			return err;
+
+		err = vcap_rule_add_action_u32(vrule, VCAP_AF_PAG_OVERRIDE_MASK,
+					       0xff);
+		if (err)
+			return err;
+	} else {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "Unsupported chain destination");
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
 static int lan966x_tc_flower_add(struct lan966x_port *port,
 				 struct flow_cls_offload *f,
 				 struct vcap_admin *admin,
@@ -248,11 +425,23 @@ static int lan966x_tc_flower_add(struct lan966x_port *port,
 	if (err)
 		goto out;
 
+	err = lan966x_tc_add_rule_link_target(admin, vrule,
+					      f->common.chain_index);
+	if (err)
+		goto out;
+
 	frule = flow_cls_offload_flow_rule(f);
 
 	flow_action_for_each(idx, act, &frule->action) {
 		switch (act->id) {
 		case FLOW_ACTION_TRAP:
+			if (admin->vtype != VCAP_TYPE_IS2) {
+				NL_SET_ERR_MSG_MOD(f->common.extack,
+						   "Trap action not supported in this VCAP");
+				err = -EOPNOTSUPP;
+				goto out;
+			}
+
 			err = vcap_rule_add_action_bit(vrule,
 						       VCAP_AF_CPU_COPY_ENA,
 						       VCAP_BIT_1);
@@ -266,6 +455,16 @@ static int lan966x_tc_flower_add(struct lan966x_port *port,
 
 			break;
 		case FLOW_ACTION_GOTO:
+			err = lan966x_tc_set_actionset(admin, vrule);
+			if (err)
+				goto out;
+
+			err = lan966x_tc_add_rule_link(port->lan966x->vcap_ctrl,
+						       admin, vrule,
+						       f, act->chain_index);
+			if (err)
+				goto out;
+
 			break;
 		default:
 			NL_SET_ERR_MSG_MOD(f->common.extack,