Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 551 insertions, 0 deletions

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
new file mode 100644
index 000000000..0beb44f2f
--- /dev/null
+++ b/net/8021q/vlan_core.c
@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netpoll.h>
+#include <linux/export.h>
+#include <net/gro.h>
+#include "vlan.h"
+
+bool vlan_do_receive(struct sk_buff **skbp)
+{
+	struct sk_buff *skb = *skbp;
+	__be16 vlan_proto = skb->vlan_proto;
+	u16 vlan_id = skb_vlan_tag_get_id(skb);
+	struct net_device *vlan_dev;
+	struct vlan_pcpu_stats *rx_stats;
+
+	vlan_dev = vlan_find_dev(skb->dev, vlan_proto, vlan_id);
+	if (!vlan_dev)
+		return false;
+
+	skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return false;
+
+	if (unlikely(!(vlan_dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		*skbp = NULL;
+		return false;
+	}
+
+	skb->dev = vlan_dev;
+	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
+		/* Our lower layer thinks this is not local, let's make sure.
+		 * This allows the VLAN to have a different MAC than the
+		 * underlying device, and still route correctly. */
+		if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
+			skb->pkt_type = PACKET_HOST;
+	}
+
+	if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR) &&
+	    !netif_is_macvlan_port(vlan_dev) &&
+	    !netif_is_bridge_port(vlan_dev)) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+
+		/*
+		 * vlan_insert_tag expect skb->data pointing to mac header.
+		 * So change skb->data before calling it and change back to
+		 * original position later
+		 */
+		skb_push(skb, offset);
+		skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb->vlan_tci, skb->mac_len);
+		if (!skb)
+			return false;
+		skb_pull(skb, offset + VLAN_HLEN);
+		skb_reset_mac_len(skb);
+	}
+
+	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
+	__vlan_hwaccel_clear_tag(skb);
+
+	rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
+
+	u64_stats_update_begin(&rx_stats->syncp);
+	u64_stats_inc(&rx_stats->rx_packets);
+	u64_stats_add(&rx_stats->rx_bytes, skb->len);
+	if (skb->pkt_type == PACKET_MULTICAST)
+		u64_stats_inc(&rx_stats->rx_multicast);
+	u64_stats_update_end(&rx_stats->syncp);
+
+	return true;
+}
+
+/* Must be invoked with rcu_read_lock. */
+struct net_device *__vlan_find_dev_deep_rcu(struct net_device *dev,
+					__be16 vlan_proto, u16 vlan_id)
+{
+	struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info);
+
+	if (vlan_info) {
+		return vlan_group_get_device(&vlan_info->grp,
+					     vlan_proto, vlan_id);
+	} else {
+		/*
+		 * Lower devices of master uppers (bonding, team) do not have
+		 * grp assigned to themselves. Grp is assigned to upper device
+		 * instead.
+		 */
+		struct net_device *upper_dev;
+
+		upper_dev = netdev_master_upper_dev_get_rcu(dev);
+		if (upper_dev)
+			return __vlan_find_dev_deep_rcu(upper_dev,
+						    vlan_proto, vlan_id);
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(__vlan_find_dev_deep_rcu);
+
+struct net_device *vlan_dev_real_dev(const struct net_device *dev)
+{
+	struct net_device *ret = vlan_dev_priv(dev)->real_dev;
+
+	while (is_vlan_dev(ret))
+		ret = vlan_dev_priv(ret)->real_dev;
+
+	return ret;
+}
+EXPORT_SYMBOL(vlan_dev_real_dev);
+
+u16 vlan_dev_vlan_id(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_id;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_id);
+
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
+/*
+ * vlan info and vid list
+ */
+
+static void vlan_group_free(struct vlan_group *grp)
+{
+	int i, j;
+
+	for (i = 0; i < VLAN_PROTO_NUM; i++)
+		for (j = 0; j < VLAN_GROUP_ARRAY_SPLIT_PARTS; j++)
+			kfree(grp->vlan_devices_arrays[i][j]);
+}
+
+static void vlan_info_free(struct vlan_info *vlan_info)
+{
+	vlan_group_free(&vlan_info->grp);
+	kfree(vlan_info);
+}
+
+static void vlan_info_rcu_free(struct rcu_head *rcu)
+{
+	vlan_info_free(container_of(rcu, struct vlan_info, rcu));
+}
+
+static struct vlan_info *vlan_info_alloc(struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+
+	vlan_info = kzalloc(sizeof(struct vlan_info), GFP_KERNEL);
+	if (!vlan_info)
+		return NULL;
+
+	vlan_info->real_dev = dev;
+	INIT_LIST_HEAD(&vlan_info->vid_list);
+	return vlan_info;
+}
+
+struct vlan_vid_info {
+	struct list_head list;
+	__be16 proto;
+	u16 vid;
+	int refcount;
+};
+
+static bool vlan_hw_filter_capable(const struct net_device *dev, __be16 proto)
+{
+	if (proto == htons(ETH_P_8021Q) &&
+	    dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		return true;
+	if (proto == htons(ETH_P_8021AD) &&
+	    dev->features & NETIF_F_HW_VLAN_STAG_FILTER)
+		return true;
+	return false;
+}
+
+static struct vlan_vid_info *vlan_vid_info_get(struct vlan_info *vlan_info,
+					       __be16 proto, u16 vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (vid_info->proto == proto && vid_info->vid == vid)
+			return vid_info;
+	}
+	return NULL;
+}
+
+static struct vlan_vid_info *vlan_vid_info_alloc(__be16 proto, u16 vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	vid_info = kzalloc(sizeof(struct vlan_vid_info), GFP_KERNEL);
+	if (!vid_info)
+		return NULL;
+	vid_info->proto = proto;
+	vid_info->vid = vid;
+
+	return vid_info;
+}
+
+static int vlan_add_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid)
+{
+	if (!vlan_hw_filter_capable(dev, proto))
+		return 0;
+
+	if (netif_device_present(dev))
+		return dev->netdev_ops->ndo_vlan_rx_add_vid(dev, proto, vid);
+	else
+		return -ENODEV;
+}
+
+static int vlan_kill_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid)
+{
+	if (!vlan_hw_filter_capable(dev, proto))
+		return 0;
+
+	if (netif_device_present(dev))
+		return dev->netdev_ops->ndo_vlan_rx_kill_vid(dev, proto, vid);
+	else
+		return -ENODEV;
+}
+
+int vlan_for_each(struct net_device *dev,
+		  int (*action)(struct net_device *dev, int vid, void *arg),
+		  void *arg)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+	struct net_device *vdev;
+	int ret;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return 0;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		vdev = vlan_group_get_device(&vlan_info->grp, vid_info->proto,
+					     vid_info->vid);
+		ret = action(vdev, vid_info->vid, arg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(vlan_for_each);
+
+int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto)
+{
+	struct net_device *real_dev = vlan_info->real_dev;
+	struct vlan_vid_info *vlan_vid_info;
+	int err;
+
+	list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list) {
+		if (vlan_vid_info->proto == proto) {
+			err = vlan_add_rx_filter_info(real_dev, proto,
+						      vlan_vid_info->vid);
+			if (err)
+				goto unwind;
+		}
+	}
+
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(vlan_vid_info,
+					     &vlan_info->vid_list, list) {
+		if (vlan_vid_info->proto == proto)
+			vlan_kill_rx_filter_info(real_dev, proto,
+						 vlan_vid_info->vid);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(vlan_filter_push_vids);
+
+void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto)
+{
+	struct vlan_vid_info *vlan_vid_info;
+
+	list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list)
+		if (vlan_vid_info->proto == proto)
+			vlan_kill_rx_filter_info(vlan_info->real_dev,
+						 vlan_vid_info->proto,
+						 vlan_vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_filter_drop_vids);
+
+static int __vlan_vid_add(struct vlan_info *vlan_info, __be16 proto, u16 vid,
+			  struct vlan_vid_info **pvid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	struct vlan_vid_info *vid_info;
+	int err;
+
+	vid_info = vlan_vid_info_alloc(proto, vid);
+	if (!vid_info)
+		return -ENOMEM;
+
+	err = vlan_add_rx_filter_info(dev, proto, vid);
+	if (err) {
+		kfree(vid_info);
+		return err;
+	}
+
+	list_add(&vid_info->list, &vlan_info->vid_list);
+	vlan_info->nr_vids++;
+	*pvid_info = vid_info;
+	return 0;
+}
+
+int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+	bool vlan_info_created = false;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info) {
+		vlan_info = vlan_info_alloc(dev);
+		if (!vlan_info)
+			return -ENOMEM;
+		vlan_info_created = true;
+	}
+	vid_info = vlan_vid_info_get(vlan_info, proto, vid);
+	if (!vid_info) {
+		err = __vlan_vid_add(vlan_info, proto, vid, &vid_info);
+		if (err)
+			goto out_free_vlan_info;
+	}
+	vid_info->refcount++;
+
+	if (vlan_info_created)
+		rcu_assign_pointer(dev->vlan_info, vlan_info);
+
+	return 0;
+
+out_free_vlan_info:
+	if (vlan_info_created)
+		kfree(vlan_info);
+	return err;
+}
+EXPORT_SYMBOL(vlan_vid_add);
+
+static void __vlan_vid_del(struct vlan_info *vlan_info,
+			   struct vlan_vid_info *vid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	__be16 proto = vid_info->proto;
+	u16 vid = vid_info->vid;
+	int err;
+
+	err = vlan_kill_rx_filter_info(dev, proto, vid);
+	if (err && dev->reg_state != NETREG_UNREGISTERING)
+		netdev_warn(dev, "failed to kill vid %04x/%d\n", proto, vid);
+
+	list_del(&vid_info->list);
+	kfree(vid_info);
+	vlan_info->nr_vids--;
+}
+
+void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	vid_info = vlan_vid_info_get(vlan_info, proto, vid);
+	if (!vid_info)
+		return;
+	vid_info->refcount--;
+	if (vid_info->refcount == 0) {
+		__vlan_vid_del(vlan_info, vid_info);
+		if (vlan_info->nr_vids == 0) {
+			RCU_INIT_POINTER(dev->vlan_info, NULL);
+			call_rcu(&vlan_info->rcu, vlan_info_rcu_free);
+		}
+	}
+}
+EXPORT_SYMBOL(vlan_vid_del);
+
+int vlan_vids_add_by_dev(struct net_device *dev,
+			 const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return 0;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		err = vlan_vid_add(dev, vid_info->proto, vid_info->vid);
+		if (err)
+			goto unwind;
+	}
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(vid_info,
+					     &vlan_info->vid_list,
+					     list) {
+		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(vlan_vids_add_by_dev);
+
+void vlan_vids_del_by_dev(struct net_device *dev,
+			  const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_vids_del_by_dev);
+
+bool vlan_uses_dev(const struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return false;
+	return vlan_info->grp.nr_vlan_devs ? true : false;
+}
+EXPORT_SYMBOL(vlan_uses_dev);
+
+static struct sk_buff *vlan_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
+{
+	const struct packet_offload *ptype;
+	unsigned int hlen, off_vlan;
+	struct sk_buff *pp = NULL;
+	struct vlan_hdr *vhdr;
+	struct sk_buff *p;
+	__be16 type;
+	int flush = 1;
+
+	off_vlan = skb_gro_offset(skb);
+	hlen = off_vlan + sizeof(*vhdr);
+	vhdr = skb_gro_header(skb, hlen, off_vlan);
+	if (unlikely(!vhdr))
+		goto out;
+
+	type = vhdr->h_vlan_encapsulated_proto;
+
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype)
+		goto out;
+
+	flush = 0;
+
+	list_for_each_entry(p, head, list) {
+		struct vlan_hdr *vhdr2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		vhdr2 = (struct vlan_hdr *)(p->data + off_vlan);
+		if (compare_vlan_header(vhdr, vhdr2))
+			NAPI_GRO_CB(p)->same_flow = 0;
+	}
+
+	skb_gro_pull(skb, sizeof(*vhdr));
+	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
+
+	pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
+					    ipv6_gro_receive, inet_gro_receive,
+					    head, skb);
+
+out:
+	skb_gro_flush_final(skb, pp, flush);
+
+	return pp;
+}
+
+static int vlan_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff);
+	__be16 type = vhdr->h_vlan_encapsulated_proto;
+	struct packet_offload *ptype;
+	int err = -ENOENT;
+
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+					 ipv6_gro_complete, inet_gro_complete,
+					 skb, nhoff + sizeof(*vhdr));
+
+	return err;
+}
+
+static struct packet_offload vlan_packet_offloads[] __read_mostly = {
+	{
+		.type = cpu_to_be16(ETH_P_8021Q),
+		.priority = 10,
+		.callbacks = {
+			.gro_receive = vlan_gro_receive,
+			.gro_complete = vlan_gro_complete,
+		},
+	},
+	{
+		.type = cpu_to_be16(ETH_P_8021AD),
+		.priority = 10,
+		.callbacks = {
+			.gro_receive = vlan_gro_receive,
+			.gro_complete = vlan_gro_complete,
+		},
+	},
+};
+
+static int __init vlan_offload_init(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++)
+		dev_add_offload(&vlan_packet_offloads[i]);
+
+	return 0;
+}
+
+fs_initcall(vlan_offload_init);