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, 1016 insertions, 0 deletions

diff --git a/net/can/raw.c b/net/can/raw.c
new file mode 100644
index 000000000..f64469b98
--- /dev/null
+++ b/net/can/raw.c
@@ -0,0 +1,1016 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/* raw.c - Raw sockets for protocol family CAN
+ *
+ * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/uio.h>
+#include <linux/net.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+#include <linux/if_arp.h>
+#include <linux/skbuff.h>
+#include <linux/can.h>
+#include <linux/can/core.h>
+#include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */
+#include <linux/can/skb.h>
+#include <linux/can/raw.h>
+#include <net/sock.h>
+#include <net/net_namespace.h>
+
+MODULE_DESCRIPTION("PF_CAN raw protocol");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
+MODULE_ALIAS("can-proto-1");
+
+#define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
+
+#define MASK_ALL 0
+
+/* A raw socket has a list of can_filters attached to it, each receiving
+ * the CAN frames matching that filter.  If the filter list is empty,
+ * no CAN frames will be received by the socket.  The default after
+ * opening the socket, is to have one filter which receives all frames.
+ * The filter list is allocated dynamically with the exception of the
+ * list containing only one item.  This common case is optimized by
+ * storing the single filter in dfilter, to avoid using dynamic memory.
+ */
+
+struct uniqframe {
+	int skbcnt;
+	const struct sk_buff *skb;
+	unsigned int join_rx_count;
+};
+
+struct raw_sock {
+	struct sock sk;
+	int bound;
+	int ifindex;
+	struct list_head notifier;
+	int loopback;
+	int recv_own_msgs;
+	int fd_frames;
+	int xl_frames;
+	int join_filters;
+	int count;                 /* number of active filters */
+	struct can_filter dfilter; /* default/single filter */
+	struct can_filter *filter; /* pointer to filter(s) */
+	can_err_mask_t err_mask;
+	struct uniqframe __percpu *uniq;
+};
+
+static LIST_HEAD(raw_notifier_list);
+static DEFINE_SPINLOCK(raw_notifier_lock);
+static struct raw_sock *raw_busy_notifier;
+
+/* Return pointer to store the extra msg flags for raw_recvmsg().
+ * We use the space of one unsigned int beyond the 'struct sockaddr_can'
+ * in skb->cb.
+ */
+static inline unsigned int *raw_flags(struct sk_buff *skb)
+{
+	sock_skb_cb_check_size(sizeof(struct sockaddr_can) +
+			       sizeof(unsigned int));
+
+	/* return pointer after struct sockaddr_can */
+	return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]);
+}
+
+static inline struct raw_sock *raw_sk(const struct sock *sk)
+{
+	return (struct raw_sock *)sk;
+}
+
+static void raw_rcv(struct sk_buff *oskb, void *data)
+{
+	struct sock *sk = (struct sock *)data;
+	struct raw_sock *ro = raw_sk(sk);
+	struct sockaddr_can *addr;
+	struct sk_buff *skb;
+	unsigned int *pflags;
+
+	/* check the received tx sock reference */
+	if (!ro->recv_own_msgs && oskb->sk == sk)
+		return;
+
+	/* make sure to not pass oversized frames to the socket */
+	if ((!ro->fd_frames && can_is_canfd_skb(oskb)) ||
+	    (!ro->xl_frames && can_is_canxl_skb(oskb)))
+		return;
+
+	/* eliminate multiple filter matches for the same skb */
+	if (this_cpu_ptr(ro->uniq)->skb == oskb &&
+	    this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) {
+		if (!ro->join_filters)
+			return;
+
+		this_cpu_inc(ro->uniq->join_rx_count);
+		/* drop frame until all enabled filters matched */
+		if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count)
+			return;
+	} else {
+		this_cpu_ptr(ro->uniq)->skb = oskb;
+		this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt;
+		this_cpu_ptr(ro->uniq)->join_rx_count = 1;
+		/* drop first frame to check all enabled filters? */
+		if (ro->join_filters && ro->count > 1)
+			return;
+	}
+
+	/* clone the given skb to be able to enqueue it into the rcv queue */
+	skb = skb_clone(oskb, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	/* Put the datagram to the queue so that raw_recvmsg() can get
+	 * it from there. We need to pass the interface index to
+	 * raw_recvmsg(). We pass a whole struct sockaddr_can in
+	 * skb->cb containing the interface index.
+	 */
+
+	sock_skb_cb_check_size(sizeof(struct sockaddr_can));
+	addr = (struct sockaddr_can *)skb->cb;
+	memset(addr, 0, sizeof(*addr));
+	addr->can_family = AF_CAN;
+	addr->can_ifindex = skb->dev->ifindex;
+
+	/* add CAN specific message flags for raw_recvmsg() */
+	pflags = raw_flags(skb);
+	*pflags = 0;
+	if (oskb->sk)
+		*pflags |= MSG_DONTROUTE;
+	if (oskb->sk == sk)
+		*pflags |= MSG_CONFIRM;
+
+	if (sock_queue_rcv_skb(sk, skb) < 0)
+		kfree_skb(skb);
+}
+
+static int raw_enable_filters(struct net *net, struct net_device *dev,
+			      struct sock *sk, struct can_filter *filter,
+			      int count)
+{
+	int err = 0;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		err = can_rx_register(net, dev, filter[i].can_id,
+				      filter[i].can_mask,
+				      raw_rcv, sk, "raw", sk);
+		if (err) {
+			/* clean up successfully registered filters */
+			while (--i >= 0)
+				can_rx_unregister(net, dev, filter[i].can_id,
+						  filter[i].can_mask,
+						  raw_rcv, sk);
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int raw_enable_errfilter(struct net *net, struct net_device *dev,
+				struct sock *sk, can_err_mask_t err_mask)
+{
+	int err = 0;
+
+	if (err_mask)
+		err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG,
+				      raw_rcv, sk, "raw", sk);
+
+	return err;
+}
+
+static void raw_disable_filters(struct net *net, struct net_device *dev,
+				struct sock *sk, struct can_filter *filter,
+				int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		can_rx_unregister(net, dev, filter[i].can_id,
+				  filter[i].can_mask, raw_rcv, sk);
+}
+
+static inline void raw_disable_errfilter(struct net *net,
+					 struct net_device *dev,
+					 struct sock *sk,
+					 can_err_mask_t err_mask)
+
+{
+	if (err_mask)
+		can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG,
+				  raw_rcv, sk);
+}
+
+static inline void raw_disable_allfilters(struct net *net,
+					  struct net_device *dev,
+					  struct sock *sk)
+{
+	struct raw_sock *ro = raw_sk(sk);
+
+	raw_disable_filters(net, dev, sk, ro->filter, ro->count);
+	raw_disable_errfilter(net, dev, sk, ro->err_mask);
+}
+
+static int raw_enable_allfilters(struct net *net, struct net_device *dev,
+				 struct sock *sk)
+{
+	struct raw_sock *ro = raw_sk(sk);
+	int err;
+
+	err = raw_enable_filters(net, dev, sk, ro->filter, ro->count);
+	if (!err) {
+		err = raw_enable_errfilter(net, dev, sk, ro->err_mask);
+		if (err)
+			raw_disable_filters(net, dev, sk, ro->filter,
+					    ro->count);
+	}
+
+	return err;
+}
+
+static void raw_notify(struct raw_sock *ro, unsigned long msg,
+		       struct net_device *dev)
+{
+	struct sock *sk = &ro->sk;
+
+	if (!net_eq(dev_net(dev), sock_net(sk)))
+		return;
+
+	if (ro->ifindex != dev->ifindex)
+		return;
+
+	switch (msg) {
+	case NETDEV_UNREGISTER:
+		lock_sock(sk);
+		/* remove current filters & unregister */
+		if (ro->bound)
+			raw_disable_allfilters(dev_net(dev), dev, sk);
+
+		if (ro->count > 1)
+			kfree(ro->filter);
+
+		ro->ifindex = 0;
+		ro->bound = 0;
+		ro->count = 0;
+		release_sock(sk);
+
+		sk->sk_err = ENODEV;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk_error_report(sk);
+		break;
+
+	case NETDEV_DOWN:
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk_error_report(sk);
+		break;
+	}
+}
+
+static int raw_notifier(struct notifier_block *nb, unsigned long msg,
+			void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (dev->type != ARPHRD_CAN)
+		return NOTIFY_DONE;
+	if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN)
+		return NOTIFY_DONE;
+	if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */
+		return NOTIFY_DONE;
+
+	spin_lock(&raw_notifier_lock);
+	list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) {
+		spin_unlock(&raw_notifier_lock);
+		raw_notify(raw_busy_notifier, msg, dev);
+		spin_lock(&raw_notifier_lock);
+	}
+	raw_busy_notifier = NULL;
+	spin_unlock(&raw_notifier_lock);
+	return NOTIFY_DONE;
+}
+
+static int raw_init(struct sock *sk)
+{
+	struct raw_sock *ro = raw_sk(sk);
+
+	ro->bound            = 0;
+	ro->ifindex          = 0;
+
+	/* set default filter to single entry dfilter */
+	ro->dfilter.can_id   = 0;
+	ro->dfilter.can_mask = MASK_ALL;
+	ro->filter           = &ro->dfilter;
+	ro->count            = 1;
+
+	/* set default loopback behaviour */
+	ro->loopback         = 1;
+	ro->recv_own_msgs    = 0;
+	ro->fd_frames        = 0;
+	ro->xl_frames        = 0;
+	ro->join_filters     = 0;
+
+	/* alloc_percpu provides zero'ed memory */
+	ro->uniq = alloc_percpu(struct uniqframe);
+	if (unlikely(!ro->uniq))
+		return -ENOMEM;
+
+	/* set notifier */
+	spin_lock(&raw_notifier_lock);
+	list_add_tail(&ro->notifier, &raw_notifier_list);
+	spin_unlock(&raw_notifier_lock);
+
+	return 0;
+}
+
+static int raw_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro;
+
+	if (!sk)
+		return 0;
+
+	ro = raw_sk(sk);
+
+	spin_lock(&raw_notifier_lock);
+	while (raw_busy_notifier == ro) {
+		spin_unlock(&raw_notifier_lock);
+		schedule_timeout_uninterruptible(1);
+		spin_lock(&raw_notifier_lock);
+	}
+	list_del(&ro->notifier);
+	spin_unlock(&raw_notifier_lock);
+
+	lock_sock(sk);
+
+	/* remove current filters & unregister */
+	if (ro->bound) {
+		if (ro->ifindex) {
+			struct net_device *dev;
+
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+			if (dev) {
+				raw_disable_allfilters(dev_net(dev), dev, sk);
+				dev_put(dev);
+			}
+		} else {
+			raw_disable_allfilters(sock_net(sk), NULL, sk);
+		}
+	}
+
+	if (ro->count > 1)
+		kfree(ro->filter);
+
+	ro->ifindex = 0;
+	ro->bound = 0;
+	ro->count = 0;
+	free_percpu(ro->uniq);
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	release_sock(sk);
+	sock_put(sk);
+
+	return 0;
+}
+
+static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro = raw_sk(sk);
+	int ifindex;
+	int err = 0;
+	int notify_enetdown = 0;
+
+	if (len < RAW_MIN_NAMELEN)
+		return -EINVAL;
+	if (addr->can_family != AF_CAN)
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	if (ro->bound && addr->can_ifindex == ro->ifindex)
+		goto out;
+
+	if (addr->can_ifindex) {
+		struct net_device *dev;
+
+		dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
+		if (!dev) {
+			err = -ENODEV;
+			goto out;
+		}
+		if (dev->type != ARPHRD_CAN) {
+			dev_put(dev);
+			err = -ENODEV;
+			goto out;
+		}
+		if (!(dev->flags & IFF_UP))
+			notify_enetdown = 1;
+
+		ifindex = dev->ifindex;
+
+		/* filters set by default/setsockopt */
+		err = raw_enable_allfilters(sock_net(sk), dev, sk);
+		dev_put(dev);
+	} else {
+		ifindex = 0;
+
+		/* filters set by default/setsockopt */
+		err = raw_enable_allfilters(sock_net(sk), NULL, sk);
+	}
+
+	if (!err) {
+		if (ro->bound) {
+			/* unregister old filters */
+			if (ro->ifindex) {
+				struct net_device *dev;
+
+				dev = dev_get_by_index(sock_net(sk),
+						       ro->ifindex);
+				if (dev) {
+					raw_disable_allfilters(dev_net(dev),
+							       dev, sk);
+					dev_put(dev);
+				}
+			} else {
+				raw_disable_allfilters(sock_net(sk), NULL, sk);
+			}
+		}
+		ro->ifindex = ifindex;
+		ro->bound = 1;
+	}
+
+ out:
+	release_sock(sk);
+
+	if (notify_enetdown) {
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk_error_report(sk);
+	}
+
+	return err;
+}
+
+static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
+		       int peer)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro = raw_sk(sk);
+
+	if (peer)
+		return -EOPNOTSUPP;
+
+	memset(addr, 0, RAW_MIN_NAMELEN);
+	addr->can_family  = AF_CAN;
+	addr->can_ifindex = ro->ifindex;
+
+	return RAW_MIN_NAMELEN;
+}
+
+static int raw_setsockopt(struct socket *sock, int level, int optname,
+			  sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro = raw_sk(sk);
+	struct can_filter *filter = NULL;  /* dyn. alloc'ed filters */
+	struct can_filter sfilter;         /* single filter */
+	struct net_device *dev = NULL;
+	can_err_mask_t err_mask = 0;
+	int fd_frames;
+	int count = 0;
+	int err = 0;
+
+	if (level != SOL_CAN_RAW)
+		return -EINVAL;
+
+	switch (optname) {
+	case CAN_RAW_FILTER:
+		if (optlen % sizeof(struct can_filter) != 0)
+			return -EINVAL;
+
+		if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter))
+			return -EINVAL;
+
+		count = optlen / sizeof(struct can_filter);
+
+		if (count > 1) {
+			/* filter does not fit into dfilter => alloc space */
+			filter = memdup_sockptr(optval, optlen);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
+		} else if (count == 1) {
+			if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter)))
+				return -EFAULT;
+		}
+
+		rtnl_lock();
+		lock_sock(sk);
+
+		if (ro->bound && ro->ifindex) {
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+			if (!dev) {
+				if (count > 1)
+					kfree(filter);
+				err = -ENODEV;
+				goto out_fil;
+			}
+		}
+
+		if (ro->bound) {
+			/* (try to) register the new filters */
+			if (count == 1)
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 &sfilter, 1);
+			else
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 filter, count);
+			if (err) {
+				if (count > 1)
+					kfree(filter);
+				goto out_fil;
+			}
+
+			/* remove old filter registrations */
+			raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
+					    ro->count);
+		}
+
+		/* remove old filter space */
+		if (ro->count > 1)
+			kfree(ro->filter);
+
+		/* link new filters to the socket */
+		if (count == 1) {
+			/* copy filter data for single filter */
+			ro->dfilter = sfilter;
+			filter = &ro->dfilter;
+		}
+		ro->filter = filter;
+		ro->count  = count;
+
+ out_fil:
+		dev_put(dev);
+		release_sock(sk);
+		rtnl_unlock();
+
+		break;
+
+	case CAN_RAW_ERR_FILTER:
+		if (optlen != sizeof(err_mask))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&err_mask, optval, optlen))
+			return -EFAULT;
+
+		err_mask &= CAN_ERR_MASK;
+
+		rtnl_lock();
+		lock_sock(sk);
+
+		if (ro->bound && ro->ifindex) {
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+			if (!dev) {
+				err = -ENODEV;
+				goto out_err;
+			}
+		}
+
+		/* remove current error mask */
+		if (ro->bound) {
+			/* (try to) register the new err_mask */
+			err = raw_enable_errfilter(sock_net(sk), dev, sk,
+						   err_mask);
+
+			if (err)
+				goto out_err;
+
+			/* remove old err_mask registration */
+			raw_disable_errfilter(sock_net(sk), dev, sk,
+					      ro->err_mask);
+		}
+
+		/* link new err_mask to the socket */
+		ro->err_mask = err_mask;
+
+ out_err:
+		dev_put(dev);
+		release_sock(sk);
+		rtnl_unlock();
+
+		break;
+
+	case CAN_RAW_LOOPBACK:
+		if (optlen != sizeof(ro->loopback))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&ro->loopback, optval, optlen))
+			return -EFAULT;
+
+		break;
+
+	case CAN_RAW_RECV_OWN_MSGS:
+		if (optlen != sizeof(ro->recv_own_msgs))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&ro->recv_own_msgs, optval, optlen))
+			return -EFAULT;
+
+		break;
+
+	case CAN_RAW_FD_FRAMES:
+		if (optlen != sizeof(fd_frames))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&fd_frames, optval, optlen))
+			return -EFAULT;
+
+		/* Enabling CAN XL includes CAN FD */
+		if (ro->xl_frames && !fd_frames)
+			return -EINVAL;
+
+		ro->fd_frames = fd_frames;
+		break;
+
+	case CAN_RAW_XL_FRAMES:
+		if (optlen != sizeof(ro->xl_frames))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&ro->xl_frames, optval, optlen))
+			return -EFAULT;
+
+		/* Enabling CAN XL includes CAN FD */
+		if (ro->xl_frames)
+			ro->fd_frames = ro->xl_frames;
+		break;
+
+	case CAN_RAW_JOIN_FILTERS:
+		if (optlen != sizeof(ro->join_filters))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&ro->join_filters, optval, optlen))
+			return -EFAULT;
+
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+	return err;
+}
+
+static int raw_getsockopt(struct socket *sock, int level, int optname,
+			  char __user *optval, int __user *optlen)
+{
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro = raw_sk(sk);
+	int len;
+	void *val;
+	int err = 0;
+
+	if (level != SOL_CAN_RAW)
+		return -EINVAL;
+	if (get_user(len, optlen))
+		return -EFAULT;
+	if (len < 0)
+		return -EINVAL;
+
+	switch (optname) {
+	case CAN_RAW_FILTER:
+		lock_sock(sk);
+		if (ro->count > 0) {
+			int fsize = ro->count * sizeof(struct can_filter);
+
+			/* user space buffer to small for filter list? */
+			if (len < fsize) {
+				/* return -ERANGE and needed space in optlen */
+				err = -ERANGE;
+				if (put_user(fsize, optlen))
+					err = -EFAULT;
+			} else {
+				if (len > fsize)
+					len = fsize;
+				if (copy_to_user(optval, ro->filter, len))
+					err = -EFAULT;
+			}
+		} else {
+			len = 0;
+		}
+		release_sock(sk);
+
+		if (!err)
+			err = put_user(len, optlen);
+		return err;
+
+	case CAN_RAW_ERR_FILTER:
+		if (len > sizeof(can_err_mask_t))
+			len = sizeof(can_err_mask_t);
+		val = &ro->err_mask;
+		break;
+
+	case CAN_RAW_LOOPBACK:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->loopback;
+		break;
+
+	case CAN_RAW_RECV_OWN_MSGS:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->recv_own_msgs;
+		break;
+
+	case CAN_RAW_FD_FRAMES:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->fd_frames;
+		break;
+
+	case CAN_RAW_XL_FRAMES:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->xl_frames;
+		break;
+
+	case CAN_RAW_JOIN_FILTERS:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->join_filters;
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+	if (copy_to_user(optval, val, len))
+		return -EFAULT;
+	return 0;
+}
+
+static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu)
+{
+	/* Classical CAN -> no checks for flags and device capabilities */
+	if (can_is_can_skb(skb))
+		return false;
+
+	/* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */
+	if (ro->fd_frames && can_is_canfd_skb(skb) &&
+	    (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu)))
+		return false;
+
+	/* CAN XL -> needs to be enabled and a CAN XL device */
+	if (ro->xl_frames && can_is_canxl_skb(skb) &&
+	    can_is_canxl_dev_mtu(mtu))
+		return false;
+
+	return true;
+}
+
+static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+{
+	struct sock *sk = sock->sk;
+	struct raw_sock *ro = raw_sk(sk);
+	struct sockcm_cookie sockc;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	int ifindex;
+	int err = -EINVAL;
+
+	/* check for valid CAN frame sizes */
+	if (size < CANXL_HDR_SIZE + CANXL_MIN_DLEN || size > CANXL_MTU)
+		return -EINVAL;
+
+	if (msg->msg_name) {
+		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
+
+		if (msg->msg_namelen < RAW_MIN_NAMELEN)
+			return -EINVAL;
+
+		if (addr->can_family != AF_CAN)
+			return -EINVAL;
+
+		ifindex = addr->can_ifindex;
+	} else {
+		ifindex = ro->ifindex;
+	}
+
+	dev = dev_get_by_index(sock_net(sk), ifindex);
+	if (!dev)
+		return -ENXIO;
+
+	skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv),
+				  msg->msg_flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		goto put_dev;
+
+	can_skb_reserve(skb);
+	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
+
+	/* fill the skb before testing for valid CAN frames */
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
+	if (err < 0)
+		goto free_skb;
+
+	err = -EINVAL;
+	if (raw_bad_txframe(ro, skb, dev->mtu))
+		goto free_skb;
+
+	sockcm_init(&sockc, sk);
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (unlikely(err))
+			goto free_skb;
+	}
+
+	skb->dev = dev;
+	skb->priority = sk->sk_priority;
+	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc.transmit_time;
+
+	skb_setup_tx_timestamp(skb, sockc.tsflags);
+
+	err = can_send(skb, ro->loopback);
+
+	dev_put(dev);
+
+	if (err)
+		goto send_failed;
+
+	return size;
+
+free_skb:
+	kfree_skb(skb);
+put_dev:
+	dev_put(dev);
+send_failed:
+	return err;
+}
+
+static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		       int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	int err = 0;
+
+	if (flags & MSG_ERRQUEUE)
+		return sock_recv_errqueue(sk, msg, size,
+					  SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE);
+
+	skb = skb_recv_datagram(sk, flags, &err);
+	if (!skb)
+		return err;
+
+	if (size < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+	else
+		size = skb->len;
+
+	err = memcpy_to_msg(msg, skb->data, size);
+	if (err < 0) {
+		skb_free_datagram(sk, skb);
+		return err;
+	}
+
+	sock_recv_cmsgs(msg, sk, skb);
+
+	if (msg->msg_name) {
+		__sockaddr_check_size(RAW_MIN_NAMELEN);
+		msg->msg_namelen = RAW_MIN_NAMELEN;
+		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
+	}
+
+	/* assign the flags that have been recorded in raw_rcv() */
+	msg->msg_flags |= *(raw_flags(skb));
+
+	skb_free_datagram(sk, skb);
+
+	return size;
+}
+
+static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd,
+				unsigned long arg)
+{
+	/* no ioctls for socket layer -> hand it down to NIC layer */
+	return -ENOIOCTLCMD;
+}
+
+static const struct proto_ops raw_ops = {
+	.family        = PF_CAN,
+	.release       = raw_release,
+	.bind          = raw_bind,
+	.connect       = sock_no_connect,
+	.socketpair    = sock_no_socketpair,
+	.accept        = sock_no_accept,
+	.getname       = raw_getname,
+	.poll          = datagram_poll,
+	.ioctl         = raw_sock_no_ioctlcmd,
+	.gettstamp     = sock_gettstamp,
+	.listen        = sock_no_listen,
+	.shutdown      = sock_no_shutdown,
+	.setsockopt    = raw_setsockopt,
+	.getsockopt    = raw_getsockopt,
+	.sendmsg       = raw_sendmsg,
+	.recvmsg       = raw_recvmsg,
+	.mmap          = sock_no_mmap,
+	.sendpage      = sock_no_sendpage,
+};
+
+static struct proto raw_proto __read_mostly = {
+	.name       = "CAN_RAW",
+	.owner      = THIS_MODULE,
+	.obj_size   = sizeof(struct raw_sock),
+	.init       = raw_init,
+};
+
+static const struct can_proto raw_can_proto = {
+	.type       = SOCK_RAW,
+	.protocol   = CAN_RAW,
+	.ops        = &raw_ops,
+	.prot       = &raw_proto,
+};
+
+static struct notifier_block canraw_notifier = {
+	.notifier_call = raw_notifier
+};
+
+static __init int raw_module_init(void)
+{
+	int err;
+
+	pr_info("can: raw protocol\n");
+
+	err = register_netdevice_notifier(&canraw_notifier);
+	if (err)
+		return err;
+
+	err = can_proto_register(&raw_can_proto);
+	if (err < 0) {
+		pr_err("can: registration of raw protocol failed\n");
+		goto register_proto_failed;
+	}
+
+	return 0;
+
+register_proto_failed:
+	unregister_netdevice_notifier(&canraw_notifier);
+	return err;
+}
+
+static __exit void raw_module_exit(void)
+{
+	can_proto_unregister(&raw_can_proto);
+	unregister_netdevice_notifier(&canraw_notifier);
+}
+
+module_init(raw_module_init);
+module_exit(raw_module_exit);