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, 427 insertions, 0 deletions

diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c
new file mode 100644
index 000000000..e9ac3b8c4
--- /dev/null
+++ b/drivers/xen/mcelog.c
@@ -0,0 +1,427 @@
+/******************************************************************************
+ * mcelog.c
+ * Driver for receiving and transferring machine check error infomation
+ *
+ * Copyright (c) 2012 Intel Corporation
+ * Author: Liu, Jinsong <jinsong.liu@intel.com>
+ * Author: Jiang, Yunhong <yunhong.jiang@intel.com>
+ * Author: Ke, Liping <liping.ke@intel.com>
+ *
+ * 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_mcelog: " fmt
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/capability.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+
+#include <xen/interface/xen.h>
+#include <xen/events.h>
+#include <xen/interface/vcpu.h>
+#include <xen/xen.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+static struct mc_info g_mi;
+static struct mcinfo_logical_cpu *g_physinfo;
+static uint32_t ncpus;
+
+static DEFINE_MUTEX(mcelog_lock);
+
+static struct xen_mce_log xen_mcelog = {
+	.signature	= XEN_MCE_LOG_SIGNATURE,
+	.len		= XEN_MCE_LOG_LEN,
+	.recordlen	= sizeof(struct xen_mce),
+};
+
+static DEFINE_SPINLOCK(xen_mce_chrdev_state_lock);
+static int xen_mce_chrdev_open_count;	/* #times opened */
+static int xen_mce_chrdev_open_exclu;	/* already open exclusive? */
+
+static DECLARE_WAIT_QUEUE_HEAD(xen_mce_chrdev_wait);
+
+static int xen_mce_chrdev_open(struct inode *inode, struct file *file)
+{
+	spin_lock(&xen_mce_chrdev_state_lock);
+
+	if (xen_mce_chrdev_open_exclu ||
+	    (xen_mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&xen_mce_chrdev_state_lock);
+
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		xen_mce_chrdev_open_exclu = 1;
+	xen_mce_chrdev_open_count++;
+
+	spin_unlock(&xen_mce_chrdev_state_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int xen_mce_chrdev_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&xen_mce_chrdev_state_lock);
+
+	xen_mce_chrdev_open_count--;
+	xen_mce_chrdev_open_exclu = 0;
+
+	spin_unlock(&xen_mce_chrdev_state_lock);
+
+	return 0;
+}
+
+static ssize_t xen_mce_chrdev_read(struct file *filp, char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	char __user *buf = ubuf;
+	unsigned num;
+	int i, err;
+
+	mutex_lock(&mcelog_lock);
+
+	num = xen_mcelog.next;
+
+	/* Only supports full reads right now */
+	err = -EINVAL;
+	if (*off != 0 || usize < XEN_MCE_LOG_LEN*sizeof(struct xen_mce))
+		goto out;
+
+	err = 0;
+	for (i = 0; i < num; i++) {
+		struct xen_mce *m = &xen_mcelog.entry[i];
+
+		err |= copy_to_user(buf, m, sizeof(*m));
+		buf += sizeof(*m);
+	}
+
+	memset(xen_mcelog.entry, 0, num * sizeof(struct xen_mce));
+	xen_mcelog.next = 0;
+
+	if (err)
+		err = -EFAULT;
+
+out:
+	mutex_unlock(&mcelog_lock);
+
+	return err ? err : buf - ubuf;
+}
+
+static __poll_t xen_mce_chrdev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &xen_mce_chrdev_wait, wait);
+
+	if (xen_mcelog.next)
+		return EPOLLIN | EPOLLRDNORM;
+
+	return 0;
+}
+
+static long xen_mce_chrdev_ioctl(struct file *f, unsigned int cmd,
+				unsigned long arg)
+{
+	int __user *p = (int __user *)arg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (cmd) {
+	case MCE_GET_RECORD_LEN:
+		return put_user(sizeof(struct xen_mce), p);
+	case MCE_GET_LOG_LEN:
+		return put_user(XEN_MCE_LOG_LEN, p);
+	case MCE_GETCLEAR_FLAGS: {
+		unsigned flags;
+
+		do {
+			flags = xen_mcelog.flags;
+		} while (cmpxchg(&xen_mcelog.flags, flags, 0) != flags);
+
+		return put_user(flags, p);
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations xen_mce_chrdev_ops = {
+	.open			= xen_mce_chrdev_open,
+	.release		= xen_mce_chrdev_release,
+	.read			= xen_mce_chrdev_read,
+	.poll			= xen_mce_chrdev_poll,
+	.unlocked_ioctl		= xen_mce_chrdev_ioctl,
+	.llseek			= no_llseek,
+};
+
+static struct miscdevice xen_mce_chrdev_device = {
+	MISC_MCELOG_MINOR,
+	"mcelog",
+	&xen_mce_chrdev_ops,
+};
+
+/*
+ * Caller should hold the mcelog_lock
+ */
+static void xen_mce_log(struct xen_mce *mce)
+{
+	unsigned entry;
+
+	entry = xen_mcelog.next;
+
+	/*
+	 * When the buffer fills up discard new entries.
+	 * Assume that the earlier errors are the more
+	 * interesting ones:
+	 */
+	if (entry >= XEN_MCE_LOG_LEN) {
+		set_bit(XEN_MCE_OVERFLOW,
+			(unsigned long *)&xen_mcelog.flags);
+		return;
+	}
+
+	memcpy(xen_mcelog.entry + entry, mce, sizeof(struct xen_mce));
+
+	xen_mcelog.next++;
+}
+
+static int convert_log(struct mc_info *mi)
+{
+	struct mcinfo_common *mic;
+	struct mcinfo_global *mc_global;
+	struct mcinfo_bank *mc_bank;
+	struct xen_mce m;
+	unsigned int i, j;
+
+	mic = NULL;
+	x86_mcinfo_lookup(&mic, mi, MC_TYPE_GLOBAL);
+	if (unlikely(!mic)) {
+		pr_warn("Failed to find global error info\n");
+		return -ENODEV;
+	}
+
+	memset(&m, 0, sizeof(struct xen_mce));
+
+	mc_global = (struct mcinfo_global *)mic;
+	m.mcgstatus = mc_global->mc_gstatus;
+	m.apicid = mc_global->mc_apicid;
+
+	for (i = 0; i < ncpus; i++)
+		if (g_physinfo[i].mc_apicid == m.apicid)
+			break;
+	if (unlikely(i == ncpus)) {
+		pr_warn("Failed to match cpu with apicid %d\n", m.apicid);
+		return -ENODEV;
+	}
+
+	m.socketid = g_physinfo[i].mc_chipid;
+	m.cpu = m.extcpu = g_physinfo[i].mc_cpunr;
+	m.cpuvendor = (__u8)g_physinfo[i].mc_vendor;
+	for (j = 0; j < g_physinfo[i].mc_nmsrvals; ++j)
+		switch (g_physinfo[i].mc_msrvalues[j].reg) {
+		case MSR_IA32_MCG_CAP:
+			m.mcgcap = g_physinfo[i].mc_msrvalues[j].value;
+			break;
+
+		case MSR_PPIN:
+		case MSR_AMD_PPIN:
+			m.ppin = g_physinfo[i].mc_msrvalues[j].value;
+			break;
+		}
+
+	mic = NULL;
+	x86_mcinfo_lookup(&mic, mi, MC_TYPE_BANK);
+	if (unlikely(!mic)) {
+		pr_warn("Fail to find bank error info\n");
+		return -ENODEV;
+	}
+
+	do {
+		if ((!mic) || (mic->size == 0) ||
+		    (mic->type != MC_TYPE_GLOBAL   &&
+		     mic->type != MC_TYPE_BANK     &&
+		     mic->type != MC_TYPE_EXTENDED &&
+		     mic->type != MC_TYPE_RECOVERY))
+			break;
+
+		if (mic->type == MC_TYPE_BANK) {
+			mc_bank = (struct mcinfo_bank *)mic;
+			m.misc = mc_bank->mc_misc;
+			m.status = mc_bank->mc_status;
+			m.addr = mc_bank->mc_addr;
+			m.tsc = mc_bank->mc_tsc;
+			m.bank = mc_bank->mc_bank;
+			m.finished = 1;
+			/*log this record*/
+			xen_mce_log(&m);
+		}
+		mic = x86_mcinfo_next(mic);
+	} while (1);
+
+	return 0;
+}
+
+static int mc_queue_handle(uint32_t flags)
+{
+	struct xen_mc mc_op;
+	int ret = 0;
+
+	mc_op.cmd = XEN_MC_fetch;
+	set_xen_guest_handle(mc_op.u.mc_fetch.data, &g_mi);
+	do {
+		mc_op.u.mc_fetch.flags = flags;
+		ret = HYPERVISOR_mca(&mc_op);
+		if (ret) {
+			pr_err("Failed to fetch %surgent error log\n",
+			       flags == XEN_MC_URGENT ? "" : "non");
+			break;
+		}
+
+		if (mc_op.u.mc_fetch.flags & XEN_MC_NODATA ||
+		    mc_op.u.mc_fetch.flags & XEN_MC_FETCHFAILED)
+			break;
+		else {
+			ret = convert_log(&g_mi);
+			if (ret)
+				pr_warn("Failed to convert this error log, continue acking it anyway\n");
+
+			mc_op.u.mc_fetch.flags = flags | XEN_MC_ACK;
+			ret = HYPERVISOR_mca(&mc_op);
+			if (ret) {
+				pr_err("Failed to ack previous error log\n");
+				break;
+			}
+		}
+	} while (1);
+
+	return ret;
+}
+
+/* virq handler for machine check error info*/
+static void xen_mce_work_fn(struct work_struct *work)
+{
+	int err;
+
+	mutex_lock(&mcelog_lock);
+
+	/* urgent mc_info */
+	err = mc_queue_handle(XEN_MC_URGENT);
+	if (err)
+		pr_err("Failed to handle urgent mc_info queue, continue handling nonurgent mc_info queue anyway\n");
+
+	/* nonurgent mc_info */
+	err = mc_queue_handle(XEN_MC_NONURGENT);
+	if (err)
+		pr_err("Failed to handle nonurgent mc_info queue\n");
+
+	/* wake processes polling /dev/mcelog */
+	wake_up_interruptible(&xen_mce_chrdev_wait);
+
+	mutex_unlock(&mcelog_lock);
+}
+static DECLARE_WORK(xen_mce_work, xen_mce_work_fn);
+
+static irqreturn_t xen_mce_interrupt(int irq, void *dev_id)
+{
+	schedule_work(&xen_mce_work);
+	return IRQ_HANDLED;
+}
+
+static int bind_virq_for_mce(void)
+{
+	int ret;
+	struct xen_mc mc_op;
+
+	memset(&mc_op, 0, sizeof(struct xen_mc));
+
+	/* Fetch physical CPU Numbers */
+	mc_op.cmd = XEN_MC_physcpuinfo;
+	set_xen_guest_handle(mc_op.u.mc_physcpuinfo.info, g_physinfo);
+	ret = HYPERVISOR_mca(&mc_op);
+	if (ret) {
+		pr_err("Failed to get CPU numbers\n");
+		return ret;
+	}
+
+	/* Fetch each CPU Physical Info for later reference*/
+	ncpus = mc_op.u.mc_physcpuinfo.ncpus;
+	g_physinfo = kcalloc(ncpus, sizeof(struct mcinfo_logical_cpu),
+			     GFP_KERNEL);
+	if (!g_physinfo)
+		return -ENOMEM;
+	set_xen_guest_handle(mc_op.u.mc_physcpuinfo.info, g_physinfo);
+	ret = HYPERVISOR_mca(&mc_op);
+	if (ret) {
+		pr_err("Failed to get CPU info\n");
+		kfree(g_physinfo);
+		return ret;
+	}
+
+	ret  = bind_virq_to_irqhandler(VIRQ_MCA, 0,
+				       xen_mce_interrupt, 0, "mce", NULL);
+	if (ret < 0) {
+		pr_err("Failed to bind virq\n");
+		kfree(g_physinfo);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init xen_late_init_mcelog(void)
+{
+	int ret;
+
+	/* Only DOM0 is responsible for MCE logging */
+	if (!xen_initial_domain())
+		return -ENODEV;
+
+	/* register character device /dev/mcelog for xen mcelog */
+	ret = misc_register(&xen_mce_chrdev_device);
+	if (ret)
+		return ret;
+
+	ret = bind_virq_for_mce();
+	if (ret)
+		goto deregister;
+
+	pr_info("/dev/mcelog registered by Xen\n");
+
+	return 0;
+
+deregister:
+	misc_deregister(&xen_mce_chrdev_device);
+	return ret;
+}
+device_initcall(xen_late_init_mcelog);