Merge tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Wrap datapath globals into net_aligned_data, to avoid false sharing

   - Preserve MSG_ZEROCOPY in forwarding (e.g. out of a container)

   - Add SO_INQ and SCM_INQ support to AF_UNIX

   - Add SIOCINQ support to AF_VSOCK

   - Add TCP_MAXSEG sockopt to MPTCP

   - Add IPv6 force_forwarding sysctl to enable forwarding per interface

   - Make TCP validation of whether packet fully fits in the receive
     window and the rcv_buf more strict. With increased use of HW
     aggregation a single "packet" can be multiple 100s of kB

   - Add MSG_MORE flag to optimize large TCP transmissions via sockmap,
     improves latency up to 33% for sockmap users

   - Convert TCP send queue handling from tasklet to BH workque

   - Improve BPF iteration over TCP sockets to see each socket exactly
     once

   - Remove obsolete and unused TCP RFC3517/RFC6675 loss recovery code

   - Support enabling kernel threads for NAPI processing on per-NAPI
     instance basis rather than a whole device. Fully stop the kernel
     NAPI thread when threaded NAPI gets disabled. Previously thread
     would stick around until ifdown due to tricky synchronization

   - Allow multicast routing to take effect on locally-generated packets

   - Add output interface argument for End.X in segment routing

   - MCTP: add support for gateway routing, improve bind() handling

   - Don't require rtnl_lock when fetching an IPv6 neighbor over Netlink

   - Add a new neighbor flag ("extern_valid"), which cedes refresh
     responsibilities to userspace. This is needed for EVPN multi-homing
     where a neighbor entry for a multi-homed host needs to be synced
     across all the VTEPs among which the host is multi-homed

   - Support NUD_PERMANENT for proxy neighbor entries

   - Add a new queuing discipline for IETF RFC9332 DualQ Coupled AQM

   - Add sequence numbers to netconsole messages. Unregister
     netconsole's console when all net targets are removed. Code
     refactoring. Add a number of selftests

   - Align IPSec inbound SA lookup to RFC 4301. Only SPI and protocol
     should be used for an inbound SA lookup

   - Support inspecting ref_tracker state via DebugFS

   - Don't force bonding advertisement frames tx to ~333 ms boundaries.
     Add broadcast_neighbor option to send ARP/ND on all bonded links

   - Allow providing upcall pid for the 'execute' command in openvswitch

   - Remove DCCP support from Netfilter's conntrack

   - Disallow multiple packet duplications in the queuing layer

   - Prevent use of deprecated iptables code on PREEMPT_RT

  Driver API:

   - Support RSS and hashing configuration over ethtool Netlink

   - Add dedicated ethtool callbacks for getting and setting hashing
     fields

   - Add support for power budget evaluation strategy in PSE /
     Power-over-Ethernet. Generate Netlink events for overcurrent etc

   - Support DPLL phase offset monitoring across all device inputs.
     Support providing clock reference and SYNC over separate DPLL
     inputs

   - Support traffic classes in devlink rate API for bandwidth
     management

   - Remove rtnl_lock dependency from UDP tunnel port configuration

  Device drivers:

   - Add a new Broadcom driver for 800G Ethernet (bnge)

   - Add a standalone driver for Microchip ZL3073x DPLL

   - Remove IBM's NETIUCV device driver

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - support zero-copy Tx of DMABUF memory
         - take page size into account for page pool recycling rings
      - Intel (100G, ice, idpf):
         - idpf: XDP and AF_XDP support preparations
         - idpf: add flow steering
         - add link_down_events statistic
         - clean up the TSPLL code
         - preparations for live VM migration
      - nVidia/Mellanox:
         - support zero-copy Rx/Tx interfaces (DMABUF and io_uring)
         - optimize context memory usage for matchers
         - expose serial numbers in devlink info
         - support PCIe congestion metrics
      - Meta (fbnic):
         - add 25G, 50G, and 100G link modes to phylink
         - support dumping FW logs
      - Marvell/Cavium:
         - support for CN20K generation of the Octeon chips
      - Amazon:
         - add HW clock (without timestamping, just hypervisor time access)

   - Ethernet virtual:
      - VirtIO net:
         - support segmentation of UDP-tunnel-encapsulated packets
      - Google (gve):
         - support packet timestamping and clock synchronization
      - Microsoft vNIC:
         - add handler for device-originated servicing events
         - allow dynamic MSI-X vector allocation
         - support Tx bandwidth clamping

   - Ethernet NICs consumer, and embedded:
      - AMD:
         - amd-xgbe: hardware timestamping and PTP clock support
      - Broadcom integrated MACs (bcmgenet, bcmasp):
         - use napi_complete_done() return value to support NAPI polling
         - add support for re-starting auto-negotiation
      - Broadcom switches (b53):
         - support BCM5325 switches
         - add bcm63xx EPHY power control
      - Synopsys (stmmac):
         - lots of code refactoring and cleanups
      - TI:
         - icssg-prueth: read firmware-names from device tree
         - icssg: PRP offload support
      - Microchip:
         - lan78xx: convert to PHYLINK for improved PHY and MAC management
         - ksz: add KSZ8463 switch support
      - Intel:
         - support similar queue priority scheme in multi-queue and
           time-sensitive networking (taprio)
         - support packet pre-emption in both
      - RealTek (r8169):
         - enable EEE at 5Gbps on RTL8126
      - Airoha:
         - add PPPoE offload support
         - MDIO bus controller for Airoha AN7583

   - Ethernet PHYs:
      - support for the IPQ5018 internal GE PHY
      - micrel KSZ9477 switch-integrated PHYs:
         - add MDI/MDI-X control support
         - add RX error counters
         - add cable test support
         - add Signal Quality Indicator (SQI) reporting
      - dp83tg720: improve reset handling and reduce link recovery time
      - support bcm54811 (and its MII-Lite interface type)
      - air_en8811h: support resume/suspend
      - support PHY counters for QCA807x and QCA808x
      - support WoL for QCA807x

   - CAN drivers:
      - rcar_canfd: support for Transceiver Delay Compensation
      - kvaser: report FW versions via devlink dev info

   - WiFi:
      - extended regulatory info support (6 GHz)
      - add statistics and beacon monitor for Multi-Link Operation (MLO)
      - support S1G aggregation, improve S1G support
      - add Radio Measurement action fields
      - support per-radio RTS threshold
      - some work around how FIPS affects wifi, which was wrong (RC4 is
        used by TKIP, not only WEP)
      - improvements for unsolicited probe response handling

   - WiFi drivers:
      - RealTek (rtw88):
         - IBSS mode for SDIO devices
      - RealTek (rtw89):
         - BT coexistence for MLO/WiFi7
         - concurrent station + P2P support
         - support for USB devices RTL8851BU/RTL8852BU
      - Intel (iwlwifi):
         - use embedded PNVM in (to be released) FW images to fix
           compatibility issues
         - many cleanups (unused FW APIs, PCIe code, WoWLAN)
         - some FIPS interoperability
      - MediaTek (mt76):
         - firmware recovery improvements
         - more MLO work
      - Qualcomm/Atheros (ath12k):
         - fix scan on multi-radio devices
         - more EHT/Wi-Fi 7 features
         - encapsulation/decapsulation offload
      - Broadcom (brcm80211):
         - support SDIO 43751 device

   - Bluetooth:
      - hci_event: add support for handling LE BIG Sync Lost event
      - ISO: add socket option to report packet seqnum via CMSG
      - ISO: support SCM_TIMESTAMPING for ISO TS

   - Bluetooth drivers:
      - intel_pcie: support Function Level Reset
      - nxpuart: add support for 4M baudrate
      - nxpuart: implement powerup sequence, reset, FW dump, and FW loading"

* tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1742 commits)
  dpll: zl3073x: Fix build failure
  selftests: bpf: fix legacy netfilter options
  ipv6: annotate data-races around rt->fib6_nsiblings
  ipv6: fix possible infinite loop in fib6_info_uses_dev()
  ipv6: prevent infinite loop in rt6_nlmsg_size()
  ipv6: add a retry logic in net6_rt_notify()
  vrf: Drop existing dst reference in vrf_ip6_input_dst
  net/sched: taprio: align entry index attr validation with mqprio
  net: fsl_pq_mdio: use dev_err_probe
  selftests: rtnetlink.sh: remove esp4_offload after test
  vsock: remove unnecessary null check in vsock_getname()
  igb: xsk: solve negative overflow of nb_pkts in zerocopy mode
  stmmac: xsk: fix negative overflow of budget in zerocopy mode
  dt-bindings: ieee802154: Convert at86rf230.txt yaml format
  net: dsa: microchip: Disable PTP function of KSZ8463
  net: dsa: microchip: Setup fiber ports for KSZ8463
  net: dsa: microchip: Write switch MAC address differently for KSZ8463
  net: dsa: microchip: Use different registers for KSZ8463
  net: dsa: microchip: Add KSZ8463 switch support to KSZ DSA driver
  dt-bindings: net: dsa: microchip: Add KSZ8463 switch support
  ...

1 files changed, 55 insertions, 17 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f8c5e2fd04df..cc6c50180663 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -186,7 +186,8 @@ struct tun_struct {
 	struct net_device	*dev;
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
-			  NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4)
+			  NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4 | \
+			  NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
 	int			align;
 	int			vnet_hdr_sz;
@@ -925,6 +926,7 @@ static int tun_net_init(struct net_device *dev)
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_STAG_TX;
+	dev->hw_enc_features = dev->hw_features;
 	dev->features = dev->hw_features;
 	dev->vlan_features = dev->features &
 			     ~(NETIF_F_HW_VLAN_CTAG_TX |
@@ -1000,8 +1002,8 @@ static unsigned int run_ebpf_filter(struct tun_struct *tun,
 /* Net device start xmit */
 static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct tun_struct *tun = netdev_priv(dev);
-	enum skb_drop_reason drop_reason;
 	int txq = skb->queue_mapping;
 	struct netdev_queue *queue;
 	struct tun_file *tfile;
@@ -1030,10 +1032,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (tfile->socket.sk->sk_filter &&
-	    sk_filter(tfile->socket.sk, skb)) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	    sk_filter_reason(tfile->socket.sk, skb, &drop_reason))
 		goto drop;
-	}
 
 	len = run_ebpf_filter(tun, skb, len);
 	if (len == 0) {
@@ -1698,7 +1698,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	struct sk_buff *skb;
 	size_t total_len = iov_iter_count(from);
 	size_t len = total_len, align = tun->align, linear;
-	struct virtio_net_hdr gso = { 0 };
+	struct virtio_net_hdr_v1_hash_tunnel hdr;
+	struct virtio_net_hdr *gso;
 	int good_linear;
 	int copylen;
 	int hdr_len = 0;
@@ -1708,6 +1709,15 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
+	netdev_features_t features = 0;
+
+	/*
+	 * Keep it easy and always zero the whole buffer, even if the
+	 * tunnel-related field will be touched only when the feature
+	 * is enabled and the hdr size id compatible.
+	 */
+	memset(&hdr, 0, sizeof(hdr));
+	gso = (struct virtio_net_hdr *)&hdr;
 
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
@@ -1721,7 +1731,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	if (tun->flags & IFF_VNET_HDR) {
 		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
-		hdr_len = tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, from, &gso);
+		features = tun_vnet_hdr_guest_features(vnet_hdr_sz);
+		hdr_len = __tun_vnet_hdr_get(vnet_hdr_sz, tun->flags,
+					     features, from, gso);
 		if (hdr_len < 0)
 			return hdr_len;
 
@@ -1755,7 +1767,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		 * (e.g gso or jumbo packet), we will do it at after
 		 * skb was created with generic XDP routine.
 		 */
-		skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp);
+		skb = tun_build_skb(tun, tfile, from, gso, len, &skb_xdp);
 		err = PTR_ERR_OR_ZERO(skb);
 		if (err)
 			goto drop;
@@ -1799,7 +1811,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		}
 	}
 
-	if (tun_vnet_hdr_to_skb(tun->flags, skb, &gso)) {
+	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
@@ -2050,13 +2062,21 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	if (vnet_hdr_sz) {
-		struct virtio_net_hdr gso;
+		struct virtio_net_hdr_v1_hash_tunnel hdr;
+		struct virtio_net_hdr *gso;
 
-		ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+		ret = tun_vnet_hdr_tnl_from_skb(tun->flags, tun->dev, skb,
+						&hdr);
 		if (ret)
 			return ret;
 
-		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		/*
+		 * Drop the packet if the configured header size is too small
+		 * WRT the enabled offloads.
+		 */
+		gso = (struct virtio_net_hdr *)&hdr;
+		ret = __tun_vnet_hdr_put(vnet_hdr_sz, tun->dev->features,
+					 iter, gso);
 		if (ret)
 			return ret;
 	}
@@ -2356,13 +2376,14 @@ static int tun_xdp_one(struct tun_struct *tun,
 		       struct tun_page *tpage)
 {
 	unsigned int datasize = xdp->data_end - xdp->data;
-	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
-	struct virtio_net_hdr *gso = &hdr->gso;
+	struct virtio_net_hdr *gso = xdp->data_hard_start;
+	struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr;
 	struct bpf_prog *xdp_prog;
 	struct sk_buff *skb = NULL;
 	struct sk_buff_head *queue;
+	netdev_features_t features;
 	u32 rxhash = 0, act;
-	int buflen = hdr->buflen;
+	int buflen = xdp->frame_sz;
 	int metasize = 0;
 	int ret = 0;
 	bool skb_xdp = false;
@@ -2426,7 +2447,9 @@ build:
 	if (metasize > 0)
 		skb_metadata_set(skb, metasize);
 
-	if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) {
+	features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz));
+	tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso;
+	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
@@ -2812,6 +2835,8 @@ static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr)
 
 }
 
+#define PLAIN_GSO (NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6)
+
 /* This is like a cut-down ethtool ops, except done via tun fd so no
  * privs required. */
 static int set_offload(struct tun_struct *tun, unsigned long arg)
@@ -2841,6 +2866,18 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 			features |= NETIF_F_GSO_UDP_L4;
 			arg &= ~(TUN_F_USO4 | TUN_F_USO6);
 		}
+
+		/*
+		 * Tunnel offload is allowed only if some plain offload is
+		 * available, too.
+		 */
+		if (features & PLAIN_GSO && arg & TUN_F_UDP_TUNNEL_GSO) {
+			features |= NETIF_F_GSO_UDP_TUNNEL;
+			if (arg & TUN_F_UDP_TUNNEL_GSO_CSUM)
+				features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+			arg &= ~(TUN_F_UDP_TUNNEL_GSO |
+				 TUN_F_UDP_TUNNEL_GSO_CSUM);
+		}
 	}
 
 	/* This gives the user a way to test for new features in future by
@@ -3186,7 +3223,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	case SIOCGIFHWADDR:
 		/* Get hw address */
-		dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name);
+		netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name);
 		if (copy_to_user(argp, &ifr, ifreq_len))
 			ret = -EFAULT;
 		break;
@@ -3695,3 +3732,4 @@ MODULE_AUTHOR(DRV_COPYRIGHT);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(TUN_MINOR);
 MODULE_ALIAS("devname:net/tun");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");