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, 709 insertions, 0 deletions

diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
new file mode 100644
index 000000000..c99415a70
--- /dev/null
+++ b/drivers/xen/evtchn.c
@@ -0,0 +1,709 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <xen/xen-ops.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+	struct mutex bind_mutex; /* serialize bind/unbind operations */
+	struct rb_root evtchns;
+	unsigned int nr_evtchns;
+
+	/* Notification ring, accessed via /dev/xen/evtchn. */
+	unsigned int ring_size;
+	evtchn_port_t *ring;
+	unsigned int ring_cons, ring_prod, ring_overflow;
+	struct mutex ring_cons_mutex; /* protect against concurrent readers */
+	spinlock_t ring_prod_lock; /* product against concurrent interrupts */
+
+	/* Processes wait on this queue when ring is empty. */
+	wait_queue_head_t evtchn_wait;
+	struct fasync_struct *evtchn_async_queue;
+	const char *name;
+
+	domid_t restrict_domid;
+};
+
+#define UNRESTRICTED_DOMID ((domid_t)-1)
+
+struct user_evtchn {
+	struct rb_node node;
+	struct per_user_data *user;
+	evtchn_port_t port;
+	bool enabled;
+};
+
+static void evtchn_free_ring(evtchn_port_t *ring)
+{
+	kvfree(ring);
+}
+
+static unsigned int evtchn_ring_offset(struct per_user_data *u,
+				       unsigned int idx)
+{
+	return idx & (u->ring_size - 1);
+}
+
+static evtchn_port_t *evtchn_ring_entry(struct per_user_data *u,
+					unsigned int idx)
+{
+	return u->ring + evtchn_ring_offset(u, idx);
+}
+
+static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
+{
+	struct rb_node **new = &(u->evtchns.rb_node), *parent = NULL;
+
+	u->nr_evtchns++;
+
+	while (*new) {
+		struct user_evtchn *this;
+
+		this = rb_entry(*new, struct user_evtchn, node);
+
+		parent = *new;
+		if (this->port < evtchn->port)
+			new = &((*new)->rb_left);
+		else if (this->port > evtchn->port)
+			new = &((*new)->rb_right);
+		else
+			return -EEXIST;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&evtchn->node, parent, new);
+	rb_insert_color(&evtchn->node, &u->evtchns);
+
+	return 0;
+}
+
+static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
+{
+	u->nr_evtchns--;
+	rb_erase(&evtchn->node, &u->evtchns);
+	kfree(evtchn);
+}
+
+static struct user_evtchn *find_evtchn(struct per_user_data *u,
+				       evtchn_port_t port)
+{
+	struct rb_node *node = u->evtchns.rb_node;
+
+	while (node) {
+		struct user_evtchn *evtchn;
+
+		evtchn = rb_entry(node, struct user_evtchn, node);
+
+		if (evtchn->port < port)
+			node = node->rb_left;
+		else if (evtchn->port > port)
+			node = node->rb_right;
+		else
+			return evtchn;
+	}
+	return NULL;
+}
+
+static irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+	struct user_evtchn *evtchn = data;
+	struct per_user_data *u = evtchn->user;
+	unsigned int prod, cons;
+
+	WARN(!evtchn->enabled,
+	     "Interrupt for port %u, but apparently not enabled; per-user %p\n",
+	     evtchn->port, u);
+
+	evtchn->enabled = false;
+
+	spin_lock(&u->ring_prod_lock);
+
+	prod = READ_ONCE(u->ring_prod);
+	cons = READ_ONCE(u->ring_cons);
+
+	if ((prod - cons) < u->ring_size) {
+		*evtchn_ring_entry(u, prod) = evtchn->port;
+		smp_wmb(); /* Ensure ring contents visible */
+		WRITE_ONCE(u->ring_prod, prod + 1);
+		if (cons == prod) {
+			wake_up_interruptible(&u->evtchn_wait);
+			kill_fasync(&u->evtchn_async_queue,
+				    SIGIO, POLL_IN);
+		}
+	} else
+		u->ring_overflow = 1;
+
+	spin_unlock(&u->ring_prod_lock);
+
+	return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	int rc;
+	unsigned int c, p, bytes1 = 0, bytes2 = 0;
+	struct per_user_data *u = file->private_data;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	if (count == 0)
+		return 0;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	for (;;) {
+		mutex_lock(&u->ring_cons_mutex);
+
+		rc = -EFBIG;
+		if (u->ring_overflow)
+			goto unlock_out;
+
+		c = READ_ONCE(u->ring_cons);
+		p = READ_ONCE(u->ring_prod);
+		if (c != p)
+			break;
+
+		mutex_unlock(&u->ring_cons_mutex);
+
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		rc = wait_event_interruptible(u->evtchn_wait,
+			READ_ONCE(u->ring_cons) != READ_ONCE(u->ring_prod));
+		if (rc)
+			return rc;
+	}
+
+	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+	if (((c ^ p) & u->ring_size) != 0) {
+		bytes1 = (u->ring_size - evtchn_ring_offset(u, c)) *
+			sizeof(evtchn_port_t);
+		bytes2 = evtchn_ring_offset(u, p) * sizeof(evtchn_port_t);
+	} else {
+		bytes1 = (p - c) * sizeof(evtchn_port_t);
+		bytes2 = 0;
+	}
+
+	/* Truncate chunks according to caller's maximum byte count. */
+	if (bytes1 > count) {
+		bytes1 = count;
+		bytes2 = 0;
+	} else if ((bytes1 + bytes2) > count) {
+		bytes2 = count - bytes1;
+	}
+
+	rc = -EFAULT;
+	smp_rmb(); /* Ensure that we see the port before we copy it. */
+	if (copy_to_user(buf, evtchn_ring_entry(u, c), bytes1) ||
+	    ((bytes2 != 0) &&
+	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+		goto unlock_out;
+
+	WRITE_ONCE(u->ring_cons, c + (bytes1 + bytes2) / sizeof(evtchn_port_t));
+	rc = bytes1 + bytes2;
+
+ unlock_out:
+	mutex_unlock(&u->ring_cons_mutex);
+	return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	int rc, i;
+	evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	struct per_user_data *u = file->private_data;
+
+	if (kbuf == NULL)
+		return -ENOMEM;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	rc = 0;
+	if (count == 0)
+		goto out;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	rc = -EFAULT;
+	if (copy_from_user(kbuf, buf, count) != 0)
+		goto out;
+
+	mutex_lock(&u->bind_mutex);
+
+	for (i = 0; i < (count/sizeof(evtchn_port_t)); i++) {
+		evtchn_port_t port = kbuf[i];
+		struct user_evtchn *evtchn;
+
+		evtchn = find_evtchn(u, port);
+		if (evtchn && !evtchn->enabled) {
+			evtchn->enabled = true;
+			xen_irq_lateeoi(irq_from_evtchn(port), 0);
+		}
+	}
+
+	mutex_unlock(&u->bind_mutex);
+
+	rc = count;
+
+ out:
+	free_page((unsigned long)kbuf);
+	return rc;
+}
+
+static int evtchn_resize_ring(struct per_user_data *u)
+{
+	unsigned int new_size;
+	evtchn_port_t *new_ring, *old_ring;
+
+	/*
+	 * Ensure the ring is large enough to capture all possible
+	 * events. i.e., one free slot for each bound event.
+	 */
+	if (u->nr_evtchns <= u->ring_size)
+		return 0;
+
+	if (u->ring_size == 0)
+		new_size = 64;
+	else
+		new_size = 2 * u->ring_size;
+
+	new_ring = kvmalloc_array(new_size, sizeof(*new_ring), GFP_KERNEL);
+	if (!new_ring)
+		return -ENOMEM;
+
+	old_ring = u->ring;
+
+	/*
+	 * Access to the ring contents is serialized by either the
+	 * prod /or/ cons lock so take both when resizing.
+	 */
+	mutex_lock(&u->ring_cons_mutex);
+	spin_lock_irq(&u->ring_prod_lock);
+
+	/*
+	 * Copy the old ring contents to the new ring.
+	 *
+	 * To take care of wrapping, a full ring, and the new index
+	 * pointing into the second half, simply copy the old contents
+	 * twice.
+	 *
+	 * +---------+    +------------------+
+	 * |34567  12| -> |34567  1234567  12|
+	 * +-----p-c-+    +-------c------p---+
+	 */
+	memcpy(new_ring, old_ring, u->ring_size * sizeof(*u->ring));
+	memcpy(new_ring + u->ring_size, old_ring,
+	       u->ring_size * sizeof(*u->ring));
+
+	u->ring = new_ring;
+	u->ring_size = new_size;
+
+	spin_unlock_irq(&u->ring_prod_lock);
+	mutex_unlock(&u->ring_cons_mutex);
+
+	evtchn_free_ring(old_ring);
+
+	return 0;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port)
+{
+	struct user_evtchn *evtchn;
+	struct evtchn_close close;
+	int rc = 0;
+
+	/*
+	 * Ports are never reused, so every caller should pass in a
+	 * unique port.
+	 *
+	 * (Locking not necessary because we haven't registered the
+	 * interrupt handler yet, and our caller has already
+	 * serialized bind operations.)
+	 */
+
+	evtchn = kzalloc(sizeof(*evtchn), GFP_KERNEL);
+	if (!evtchn)
+		return -ENOMEM;
+
+	evtchn->user = u;
+	evtchn->port = port;
+	evtchn->enabled = true; /* start enabled */
+
+	rc = add_evtchn(u, evtchn);
+	if (rc < 0)
+		goto err;
+
+	rc = evtchn_resize_ring(u);
+	if (rc < 0)
+		goto err;
+
+	rc = bind_evtchn_to_irqhandler_lateeoi(port, evtchn_interrupt, 0,
+					       u->name, evtchn);
+	if (rc < 0)
+		goto err;
+
+	rc = evtchn_make_refcounted(port);
+	return rc;
+
+err:
+	/* bind failed, should close the port now */
+	close.port = port;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+	del_evtchn(u, evtchn);
+	return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u,
+				    struct user_evtchn *evtchn)
+{
+	int irq = irq_from_evtchn(evtchn->port);
+
+	BUG_ON(irq < 0);
+
+	unbind_from_irqhandler(irq, evtchn);
+
+	del_evtchn(u, evtchn);
+}
+
+static long evtchn_ioctl(struct file *file,
+			 unsigned int cmd, unsigned long arg)
+{
+	int rc;
+	struct per_user_data *u = file->private_data;
+	void __user *uarg = (void __user *) arg;
+
+	/* Prevent bind from racing with unbind */
+	mutex_lock(&u->bind_mutex);
+
+	switch (cmd) {
+	case IOCTL_EVTCHN_BIND_VIRQ: {
+		struct ioctl_evtchn_bind_virq bind;
+		struct evtchn_bind_virq bind_virq;
+
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_virq.virq = bind.virq;
+		bind_virq.vcpu = xen_vcpu_nr(0);
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						 &bind_virq);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_virq.port);
+		if (rc == 0)
+			rc = bind_virq.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+		struct ioctl_evtchn_bind_interdomain bind;
+		struct evtchn_bind_interdomain bind_interdomain;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID &&
+		    u->restrict_domid != bind.remote_domain)
+			break;
+
+		bind_interdomain.remote_dom  = bind.remote_domain;
+		bind_interdomain.remote_port = bind.remote_port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+						 &bind_interdomain);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+		if (rc == 0)
+			rc = bind_interdomain.local_port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+		struct ioctl_evtchn_bind_unbound_port bind;
+		struct evtchn_alloc_unbound alloc_unbound;
+
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		alloc_unbound.dom        = DOMID_SELF;
+		alloc_unbound.remote_dom = bind.remote_domain;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+						 &alloc_unbound);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, alloc_unbound.port);
+		if (rc == 0)
+			rc = alloc_unbound.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_UNBIND: {
+		struct ioctl_evtchn_unbind unbind;
+		struct user_evtchn *evtchn;
+
+		rc = -EFAULT;
+		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+			break;
+
+		rc = -EINVAL;
+		if (unbind.port >= xen_evtchn_nr_channels())
+			break;
+
+		rc = -ENOTCONN;
+		evtchn = find_evtchn(u, unbind.port);
+		if (!evtchn)
+			break;
+
+		disable_irq(irq_from_evtchn(unbind.port));
+		evtchn_unbind_from_user(u, evtchn);
+		rc = 0;
+		break;
+	}
+
+	case IOCTL_EVTCHN_NOTIFY: {
+		struct ioctl_evtchn_notify notify;
+		struct user_evtchn *evtchn;
+
+		rc = -EFAULT;
+		if (copy_from_user(&notify, uarg, sizeof(notify)))
+			break;
+
+		rc = -ENOTCONN;
+		evtchn = find_evtchn(u, notify.port);
+		if (evtchn) {
+			notify_remote_via_evtchn(notify.port);
+			rc = 0;
+		}
+		break;
+	}
+
+	case IOCTL_EVTCHN_RESET: {
+		/* Initialise the ring to empty. Clear errors. */
+		mutex_lock(&u->ring_cons_mutex);
+		spin_lock_irq(&u->ring_prod_lock);
+		WRITE_ONCE(u->ring_cons, 0);
+		WRITE_ONCE(u->ring_prod, 0);
+		u->ring_overflow = 0;
+		spin_unlock_irq(&u->ring_prod_lock);
+		mutex_unlock(&u->ring_cons_mutex);
+		rc = 0;
+		break;
+	}
+
+	case IOCTL_EVTCHN_RESTRICT_DOMID: {
+		struct ioctl_evtchn_restrict_domid ierd;
+
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
+		rc = -EFAULT;
+		if (copy_from_user(&ierd, uarg, sizeof(ierd)))
+		    break;
+
+		rc = -EINVAL;
+		if (ierd.domid == 0 || ierd.domid >= DOMID_FIRST_RESERVED)
+			break;
+
+		u->restrict_domid = ierd.domid;
+		rc = 0;
+
+		break;
+	}
+
+	default:
+		rc = -ENOSYS;
+		break;
+	}
+	mutex_unlock(&u->bind_mutex);
+
+	return rc;
+}
+
+static __poll_t evtchn_poll(struct file *file, poll_table *wait)
+{
+	__poll_t mask = EPOLLOUT | EPOLLWRNORM;
+	struct per_user_data *u = file->private_data;
+
+	poll_wait(file, &u->evtchn_wait, wait);
+	if (READ_ONCE(u->ring_cons) != READ_ONCE(u->ring_prod))
+		mask |= EPOLLIN | EPOLLRDNORM;
+	if (u->ring_overflow)
+		mask = EPOLLERR;
+	return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+	struct per_user_data *u = filp->private_data;
+	return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+	struct per_user_data *u;
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+	if (u->name == NULL) {
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	init_waitqueue_head(&u->evtchn_wait);
+
+	mutex_init(&u->bind_mutex);
+	mutex_init(&u->ring_cons_mutex);
+	spin_lock_init(&u->ring_prod_lock);
+
+	u->restrict_domid = UNRESTRICTED_DOMID;
+
+	filp->private_data = u;
+
+	return stream_open(inode, filp);
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+	struct per_user_data *u = filp->private_data;
+	struct rb_node *node;
+
+	while ((node = u->evtchns.rb_node)) {
+		struct user_evtchn *evtchn;
+
+		evtchn = rb_entry(node, struct user_evtchn, node);
+		disable_irq(irq_from_evtchn(evtchn->port));
+		evtchn_unbind_from_user(u, evtchn);
+	}
+
+	evtchn_free_ring(u->ring);
+	kfree(u->name);
+	kfree(u);
+
+	return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+	.owner   = THIS_MODULE,
+	.read    = evtchn_read,
+	.write   = evtchn_write,
+	.unlocked_ioctl = evtchn_ioctl,
+	.poll    = evtchn_poll,
+	.fasync  = evtchn_fasync,
+	.open    = evtchn_open,
+	.release = evtchn_release,
+	.llseek	 = no_llseek,
+};
+
+static struct miscdevice evtchn_miscdev = {
+	.minor        = MISC_DYNAMIC_MINOR,
+	.name         = "xen/evtchn",
+	.fops         = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	/* Create '/dev/xen/evtchn'. */
+	err = misc_register(&evtchn_miscdev);
+	if (err != 0) {
+		pr_err("Could not register /dev/xen/evtchn\n");
+		return err;
+	}
+
+	pr_info("Event-channel device installed\n");
+
+	return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+	misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");