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, 670 insertions, 0 deletions

diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
new file mode 100644
index 000000000..2f880374b
--- /dev/null
+++ b/drivers/xen/sys-hypervisor.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  copyright (c) 2006 IBM Corporation
+ *  Authored by: Mike D. Day <ncmike@us.ibm.com>
+ */
+
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+#include <linux/err.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+#ifdef CONFIG_XEN_HAVE_VPMU
+#include <xen/interface/xenpmu.h>
+#endif
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = __ATTR_RW(_name)
+
+struct hyp_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+	ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+	union {
+		void *hyp_attr_data;
+		unsigned long hyp_attr_value;
+	};
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static ssize_t guest_type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	const char *type;
+
+	switch (xen_domain_type) {
+	case XEN_NATIVE:
+		/* ARM only. */
+		type = "Xen";
+		break;
+	case XEN_PV_DOMAIN:
+		type = "PV";
+		break;
+	case XEN_HVM_DOMAIN:
+		type = xen_pvh_domain() ? "PVH" : "HVM";
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sprintf(buffer, "%s\n", type);
+}
+
+HYPERVISOR_ATTR_RO(guest_type);
+
+static int __init xen_sysfs_guest_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &guest_type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version >> 16);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version & 0xff);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *extra;
+
+	extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+	if (extra) {
+		ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", extra);
+		kfree(extra);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+	&major_attr.attr,
+	&minor_attr.attr,
+	&extra_attr.attr,
+	NULL
+};
+
+static const struct attribute_group version_group = {
+	.name = "version",
+	.attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show_fallback(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	char *vm, *val;
+	int ret;
+	extern int xenstored_ready;
+
+	if (!xenstored_ready)
+		return -EBUSY;
+
+	vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+	if (IS_ERR(vm))
+		return PTR_ERR(vm);
+	val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+	kfree(vm);
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+	ret = sprintf(buffer, "%s\n", val);
+	kfree(val);
+	return ret;
+}
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	xen_domain_handle_t uuid;
+	int ret;
+	ret = HYPERVISOR_xen_version(XENVER_guest_handle, uuid);
+	if (ret)
+		return uuid_show_fallback(attr, buffer);
+	ret = sprintf(buffer, "%pU\n", uuid);
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compiler);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_by);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_date);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+	&compiler_attr.attr,
+	&compiled_by_attr.attr,
+	&compile_date_attr.attr,
+	NULL
+};
+
+static const struct attribute_group xen_compilation_group = {
+	.name = "compilation",
+	.attrs = xen_compile_attrs,
+};
+
+static int __init xen_sysfs_compilation_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *caps;
+
+	caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+	if (caps) {
+		ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", caps);
+		kfree(caps);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *cset;
+
+	cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+	if (cset) {
+		ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", cset);
+		kfree(cset);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_platform_parameters *parms;
+
+	parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+	if (parms) {
+		ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+					     parms);
+		if (!ret)
+			ret = sprintf(buffer, "%"PRI_xen_ulong"\n",
+				      parms->virt_start);
+		kfree(parms);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+
+	ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+	if (ret > 0)
+		ret = sprintf(buffer, "%x\n", ret);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+	ssize_t ret;
+	struct xen_feature_info info;
+
+	info.submap_idx = index;
+	ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+	if (!ret)
+		ret = sprintf(buffer, "%08x", info.submap);
+
+	return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t len;
+	int i;
+
+	len = 0;
+	for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+		int ret = xen_feature_show(i, buffer + len);
+		if (ret < 0) {
+			if (len == 0)
+				len = ret;
+			break;
+		}
+		len += ret;
+	}
+	if (len > 0)
+		buffer[len++] = '\n';
+
+	return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t ret;
+	struct xen_build_id *buildid;
+
+	ret = HYPERVISOR_xen_version(XENVER_build_id, NULL);
+	if (ret < 0) {
+		if (ret == -EPERM)
+			ret = sprintf(buffer, "<denied>");
+		return ret;
+	}
+
+	buildid = kmalloc(sizeof(*buildid) + ret, GFP_KERNEL);
+	if (!buildid)
+		return -ENOMEM;
+
+	buildid->len = ret;
+	ret = HYPERVISOR_xen_version(XENVER_build_id, buildid);
+	if (ret > 0)
+		ret = sprintf(buffer, "%s", buildid->buf);
+	kfree(buildid);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(buildid);
+
+static struct attribute *xen_properties_attrs[] = {
+	&capabilities_attr.attr,
+	&changeset_attr.attr,
+	&virtual_start_attr.attr,
+	&pagesize_attr.attr,
+	&features_attr.attr,
+	&buildid_attr.attr,
+	NULL
+};
+
+static const struct attribute_group xen_properties_group = {
+	.name = "properties",
+	.attrs = xen_properties_attrs,
+};
+
+static int __init xen_sysfs_properties_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+#define FLAG_UNAME "unknown"
+#define FLAG_UNAME_FMT FLAG_UNAME "%02u"
+#define FLAG_UNAME_MAX sizeof(FLAG_UNAME "XX")
+#define FLAG_COUNT (sizeof(xen_start_flags) * BITS_PER_BYTE)
+static_assert(sizeof(xen_start_flags) <=
+	      sizeof_field(struct hyp_sysfs_attr, hyp_attr_value));
+
+static ssize_t flag_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	char *p = buffer;
+
+	*p++ = '0' + ((xen_start_flags & attr->hyp_attr_value) != 0);
+	*p++ = '\n';
+	return p - buffer;
+}
+
+#define FLAG_NODE(flag, node)				\
+	[ilog2(flag)] = {				\
+		.attr = { .name = #node, .mode = 0444 },\
+		.show = flag_show,			\
+		.hyp_attr_value = flag			\
+	}
+
+/*
+ * Add new, known flags here.  No other changes are required, but
+ * note that each known flag wastes one entry in flag_unames[].
+ * The code/complexity machinations to avoid this isn't worth it
+ * for a few entries, but keep it in mind.
+ */
+static struct hyp_sysfs_attr flag_attrs[FLAG_COUNT] = {
+	FLAG_NODE(SIF_PRIVILEGED, privileged),
+	FLAG_NODE(SIF_INITDOMAIN, initdomain)
+};
+static struct attribute_group xen_flags_group = {
+	.name = "start_flags",
+	.attrs = (struct attribute *[FLAG_COUNT + 1]){}
+};
+static char flag_unames[FLAG_COUNT][FLAG_UNAME_MAX];
+
+static int __init xen_sysfs_flags_init(void)
+{
+	for (unsigned fnum = 0; fnum != FLAG_COUNT; fnum++) {
+		if (likely(flag_attrs[fnum].attr.name == NULL)) {
+			sprintf(flag_unames[fnum], FLAG_UNAME_FMT, fnum);
+			flag_attrs[fnum].attr.name = flag_unames[fnum];
+			flag_attrs[fnum].attr.mode = 0444;
+			flag_attrs[fnum].show = flag_show;
+			flag_attrs[fnum].hyp_attr_value = 1 << fnum;
+		}
+		xen_flags_group.attrs[fnum] = &flag_attrs[fnum].attr;
+	}
+	return sysfs_create_group(hypervisor_kobj, &xen_flags_group);
+}
+
+#ifdef CONFIG_XEN_HAVE_VPMU
+struct pmu_mode {
+	const char *name;
+	uint32_t mode;
+};
+
+static struct pmu_mode pmu_modes[] = {
+	{"off", XENPMU_MODE_OFF},
+	{"self", XENPMU_MODE_SELF},
+	{"hv", XENPMU_MODE_HV},
+	{"all", XENPMU_MODE_ALL}
+};
+
+static ssize_t pmu_mode_store(struct hyp_sysfs_attr *attr,
+			      const char *buffer, size_t len)
+{
+	int ret;
+	struct xen_pmu_params xp;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pmu_modes); i++) {
+		if (strncmp(buffer, pmu_modes[i].name, len - 1) == 0) {
+			xp.val = pmu_modes[i].mode;
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(pmu_modes))
+		return -EINVAL;
+
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+	ret = HYPERVISOR_xenpmu_op(XENPMU_mode_set, &xp);
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+static ssize_t pmu_mode_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+	struct xen_pmu_params xp;
+	int i;
+	uint32_t mode;
+
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+	ret = HYPERVISOR_xenpmu_op(XENPMU_mode_get, &xp);
+	if (ret)
+		return ret;
+
+	mode = (uint32_t)xp.val;
+	for (i = 0; i < ARRAY_SIZE(pmu_modes); i++) {
+		if (mode == pmu_modes[i].mode)
+			return sprintf(buffer, "%s\n", pmu_modes[i].name);
+	}
+
+	return -EINVAL;
+}
+HYPERVISOR_ATTR_RW(pmu_mode);
+
+static ssize_t pmu_features_store(struct hyp_sysfs_attr *attr,
+				  const char *buffer, size_t len)
+{
+	int ret;
+	uint32_t features;
+	struct xen_pmu_params xp;
+
+	ret = kstrtou32(buffer, 0, &features);
+	if (ret)
+		return ret;
+
+	xp.val = features;
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+	ret = HYPERVISOR_xenpmu_op(XENPMU_feature_set, &xp);
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+static ssize_t pmu_features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+	struct xen_pmu_params xp;
+
+	xp.version.maj = XENPMU_VER_MAJ;
+	xp.version.min = XENPMU_VER_MIN;
+	ret = HYPERVISOR_xenpmu_op(XENPMU_feature_get, &xp);
+	if (ret)
+		return ret;
+
+	return sprintf(buffer, "0x%x\n", (uint32_t)xp.val);
+}
+HYPERVISOR_ATTR_RW(pmu_features);
+
+static struct attribute *xen_pmu_attrs[] = {
+	&pmu_mode_attr.attr,
+	&pmu_features_attr.attr,
+	NULL
+};
+
+static const struct attribute_group xen_pmu_group = {
+	.name = "pmu",
+	.attrs = xen_pmu_attrs,
+};
+
+static int __init xen_sysfs_pmu_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_pmu_group);
+}
+#endif
+
+static int __init hyper_sysfs_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	ret = xen_sysfs_type_init();
+	if (ret)
+		goto out;
+	ret = xen_sysfs_guest_type_init();
+	if (ret)
+		goto guest_type_out;
+	ret = xen_sysfs_version_init();
+	if (ret)
+		goto version_out;
+	ret = xen_sysfs_compilation_init();
+	if (ret)
+		goto comp_out;
+	ret = xen_sysfs_uuid_init();
+	if (ret)
+		goto uuid_out;
+	ret = xen_sysfs_properties_init();
+	if (ret)
+		goto prop_out;
+	ret = xen_sysfs_flags_init();
+	if (ret)
+		goto flags_out;
+#ifdef CONFIG_XEN_HAVE_VPMU
+	if (xen_initial_domain()) {
+		ret = xen_sysfs_pmu_init();
+		if (ret) {
+			sysfs_remove_group(hypervisor_kobj, &xen_flags_group);
+			goto flags_out;
+		}
+	}
+#endif
+	goto out;
+
+flags_out:
+	sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+prop_out:
+	sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+uuid_out:
+	sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+comp_out:
+	sysfs_remove_group(hypervisor_kobj, &version_group);
+version_out:
+	sysfs_remove_file(hypervisor_kobj, &guest_type_attr.attr);
+guest_type_out:
+	sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+out:
+	return ret;
+}
+device_initcall(hyper_sysfs_init);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+			      struct attribute *attr,
+			      char *buffer)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->show)
+		return hyp_attr->show(hyp_attr, buffer);
+	return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buffer,
+			       size_t len)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->store)
+		return hyp_attr->store(hyp_attr, buffer, len);
+	return 0;
+}
+
+static const struct sysfs_ops hyp_sysfs_ops = {
+	.show = hyp_sysfs_show,
+	.store = hyp_sysfs_store,
+};
+
+static const struct kobj_type hyp_sysfs_kobj_type = {
+	.sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+	return 0;
+}
+device_initcall(hypervisor_subsys_init);