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, 392 insertions, 0 deletions

diff --git a/include/xen/interface/xen-mca.h b/include/xen/interface/xen-mca.h
new file mode 100644
index 000000000..464aa6b3a
--- /dev/null
+++ b/include/xen/interface/xen-mca.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: MIT */
+/******************************************************************************
+ * arch-x86/mca.h
+ * Guest OS machine check interface to x86 Xen.
+ *
+ * Contributed by Advanced Micro Devices, Inc.
+ * Author: Christoph Egger <Christoph.Egger@amd.com>
+ *
+ * Updated by Intel Corporation
+ * Author: Liu, Jinsong <jinsong.liu@intel.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (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.
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_MCA_H__
+#define __XEN_PUBLIC_ARCH_X86_MCA_H__
+
+/* Hypercall */
+#define __HYPERVISOR_mca __HYPERVISOR_arch_0
+
+#define XEN_MCA_INTERFACE_VERSION	0x01ecc003
+
+/* IN: Dom0 calls hypercall to retrieve nonurgent error log entry */
+#define XEN_MC_NONURGENT	0x1
+/* IN: Dom0 calls hypercall to retrieve urgent error log entry */
+#define XEN_MC_URGENT		0x2
+/* IN: Dom0 acknowledges previosly-fetched error log entry */
+#define XEN_MC_ACK		0x4
+
+/* OUT: All is ok */
+#define XEN_MC_OK		0x0
+/* OUT: Domain could not fetch data. */
+#define XEN_MC_FETCHFAILED	0x1
+/* OUT: There was no machine check data to fetch. */
+#define XEN_MC_NODATA		0x2
+
+#ifndef __ASSEMBLY__
+/* vIRQ injected to Dom0 */
+#define VIRQ_MCA VIRQ_ARCH_0
+
+/*
+ * mc_info entry types
+ * mca machine check info are recorded in mc_info entries.
+ * when fetch mca info, it can use MC_TYPE_... to distinguish
+ * different mca info.
+ */
+#define MC_TYPE_GLOBAL		0
+#define MC_TYPE_BANK		1
+#define MC_TYPE_EXTENDED	2
+#define MC_TYPE_RECOVERY	3
+
+struct mcinfo_common {
+	uint16_t type; /* structure type */
+	uint16_t size; /* size of this struct in bytes */
+};
+
+#define MC_FLAG_CORRECTABLE	(1 << 0)
+#define MC_FLAG_UNCORRECTABLE	(1 << 1)
+#define MC_FLAG_RECOVERABLE	(1 << 2)
+#define MC_FLAG_POLLED		(1 << 3)
+#define MC_FLAG_RESET		(1 << 4)
+#define MC_FLAG_CMCI		(1 << 5)
+#define MC_FLAG_MCE		(1 << 6)
+
+/* contains x86 global mc information */
+struct mcinfo_global {
+	struct mcinfo_common common;
+
+	uint16_t mc_domid; /* running domain at the time in error */
+	uint16_t mc_vcpuid; /* virtual cpu scheduled for mc_domid */
+	uint32_t mc_socketid; /* physical socket of the physical core */
+	uint16_t mc_coreid; /* physical impacted core */
+	uint16_t mc_core_threadid; /* core thread of physical core */
+	uint32_t mc_apicid;
+	uint32_t mc_flags;
+	uint64_t mc_gstatus; /* global status */
+};
+
+/* contains x86 bank mc information */
+struct mcinfo_bank {
+	struct mcinfo_common common;
+
+	uint16_t mc_bank; /* bank nr */
+	uint16_t mc_domid; /* domain referenced by mc_addr if valid */
+	uint64_t mc_status; /* bank status */
+	uint64_t mc_addr; /* bank address */
+	uint64_t mc_misc;
+	uint64_t mc_ctrl2;
+	uint64_t mc_tsc;
+};
+
+struct mcinfo_msr {
+	uint64_t reg; /* MSR */
+	uint64_t value; /* MSR value */
+};
+
+/* contains mc information from other or additional mc MSRs */
+struct mcinfo_extended {
+	struct mcinfo_common common;
+	uint32_t mc_msrs; /* Number of msr with valid values. */
+	/*
+	 * Currently Intel extended MSR (32/64) include all gp registers
+	 * and E(R)FLAGS, E(R)IP, E(R)MISC, up to 11/19 of them might be
+	 * useful at present. So expand this array to 16/32 to leave room.
+	 */
+	struct mcinfo_msr mc_msr[sizeof(void *) * 4];
+};
+
+/* Recovery Action flags. Giving recovery result information to DOM0 */
+
+/* Xen takes successful recovery action, the error is recovered */
+#define REC_ACTION_RECOVERED (0x1 << 0)
+/* No action is performed by XEN */
+#define REC_ACTION_NONE (0x1 << 1)
+/* It's possible DOM0 might take action ownership in some case */
+#define REC_ACTION_NEED_RESET (0x1 << 2)
+
+/*
+ * Different Recovery Action types, if the action is performed successfully,
+ * REC_ACTION_RECOVERED flag will be returned.
+ */
+
+/* Page Offline Action */
+#define MC_ACTION_PAGE_OFFLINE (0x1 << 0)
+/* CPU offline Action */
+#define MC_ACTION_CPU_OFFLINE (0x1 << 1)
+/* L3 cache disable Action */
+#define MC_ACTION_CACHE_SHRINK (0x1 << 2)
+
+/*
+ * Below interface used between XEN/DOM0 for passing XEN's recovery action
+ * information to DOM0.
+ */
+struct page_offline_action {
+	/* Params for passing the offlined page number to DOM0 */
+	uint64_t mfn;
+	uint64_t status;
+};
+
+struct cpu_offline_action {
+	/* Params for passing the identity of the offlined CPU to DOM0 */
+	uint32_t mc_socketid;
+	uint16_t mc_coreid;
+	uint16_t mc_core_threadid;
+};
+
+#define MAX_UNION_SIZE 16
+struct mcinfo_recovery {
+	struct mcinfo_common common;
+	uint16_t mc_bank; /* bank nr */
+	uint8_t action_flags;
+	uint8_t action_types;
+	union {
+		struct page_offline_action page_retire;
+		struct cpu_offline_action cpu_offline;
+		uint8_t pad[MAX_UNION_SIZE];
+	} action_info;
+};
+
+
+#define MCINFO_MAXSIZE 768
+struct mc_info {
+	/* Number of mcinfo_* entries in mi_data */
+	uint32_t mi_nentries;
+	uint32_t flags;
+	uint64_t mi_data[(MCINFO_MAXSIZE - 1) / 8];
+};
+DEFINE_GUEST_HANDLE_STRUCT(mc_info);
+
+#define __MC_MSR_ARRAYSIZE 8
+#define __MC_NMSRS 1
+#define MC_NCAPS 7
+struct mcinfo_logical_cpu {
+	uint32_t mc_cpunr;
+	uint32_t mc_chipid;
+	uint16_t mc_coreid;
+	uint16_t mc_threadid;
+	uint32_t mc_apicid;
+	uint32_t mc_clusterid;
+	uint32_t mc_ncores;
+	uint32_t mc_ncores_active;
+	uint32_t mc_nthreads;
+	uint32_t mc_cpuid_level;
+	uint32_t mc_family;
+	uint32_t mc_vendor;
+	uint32_t mc_model;
+	uint32_t mc_step;
+	char mc_vendorid[16];
+	char mc_brandid[64];
+	uint32_t mc_cpu_caps[MC_NCAPS];
+	uint32_t mc_cache_size;
+	uint32_t mc_cache_alignment;
+	uint32_t mc_nmsrvals;
+	struct mcinfo_msr mc_msrvalues[__MC_MSR_ARRAYSIZE];
+};
+DEFINE_GUEST_HANDLE_STRUCT(mcinfo_logical_cpu);
+
+/*
+ * Prototype:
+ *    uint32_t x86_mcinfo_nentries(struct mc_info *mi);
+ */
+#define x86_mcinfo_nentries(_mi)    \
+	((_mi)->mi_nentries)
+/*
+ * Prototype:
+ *    struct mcinfo_common *x86_mcinfo_first(struct mc_info *mi);
+ */
+#define x86_mcinfo_first(_mi)       \
+	((struct mcinfo_common *)(_mi)->mi_data)
+/*
+ * Prototype:
+ *    struct mcinfo_common *x86_mcinfo_next(struct mcinfo_common *mic);
+ */
+#define x86_mcinfo_next(_mic)       \
+	((struct mcinfo_common *)((uint8_t *)(_mic) + (_mic)->size))
+
+/*
+ * Prototype:
+ *    void x86_mcinfo_lookup(void *ret, struct mc_info *mi, uint16_t type);
+ */
+static inline void x86_mcinfo_lookup(struct mcinfo_common **ret,
+				     struct mc_info *mi, uint16_t type)
+{
+	uint32_t i;
+	struct mcinfo_common *mic;
+	bool found = 0;
+
+	if (!ret || !mi)
+		return;
+
+	mic = x86_mcinfo_first(mi);
+	for (i = 0; i < x86_mcinfo_nentries(mi); i++) {
+		if (mic->type == type) {
+			found = 1;
+			break;
+		}
+		mic = x86_mcinfo_next(mic);
+	}
+
+	*ret = found ? mic : NULL;
+}
+
+/*
+ * Fetch machine check data from hypervisor.
+ */
+#define XEN_MC_fetch		1
+struct xen_mc_fetch {
+	/*
+	 * IN: XEN_MC_NONURGENT, XEN_MC_URGENT,
+	 * XEN_MC_ACK if ack'king an earlier fetch
+	 * OUT: XEN_MC_OK, XEN_MC_FETCHAILED, XEN_MC_NODATA
+	 */
+	uint32_t flags;
+	uint32_t _pad0;
+	/* OUT: id for ack, IN: id we are ack'ing */
+	uint64_t fetch_id;
+
+	/* OUT variables. */
+	GUEST_HANDLE(mc_info) data;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc_fetch);
+
+
+/*
+ * This tells the hypervisor to notify a DomU about the machine check error
+ */
+#define XEN_MC_notifydomain	2
+struct xen_mc_notifydomain {
+	/* IN variables */
+	uint16_t mc_domid; /* The unprivileged domain to notify */
+	uint16_t mc_vcpuid; /* The vcpu in mc_domid to notify */
+
+	/* IN/OUT variables */
+	uint32_t flags;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc_notifydomain);
+
+#define XEN_MC_physcpuinfo	3
+struct xen_mc_physcpuinfo {
+	/* IN/OUT */
+	uint32_t ncpus;
+	uint32_t _pad0;
+	/* OUT */
+	GUEST_HANDLE(mcinfo_logical_cpu) info;
+};
+
+#define XEN_MC_msrinject	4
+#define MC_MSRINJ_MAXMSRS	8
+struct xen_mc_msrinject {
+	/* IN */
+	uint32_t mcinj_cpunr; /* target processor id */
+	uint32_t mcinj_flags; /* see MC_MSRINJ_F_* below */
+	uint32_t mcinj_count; /* 0 .. count-1 in array are valid */
+	uint32_t _pad0;
+	struct mcinfo_msr mcinj_msr[MC_MSRINJ_MAXMSRS];
+};
+
+/* Flags for mcinj_flags above; bits 16-31 are reserved */
+#define MC_MSRINJ_F_INTERPOSE	0x1
+
+#define XEN_MC_mceinject	5
+struct xen_mc_mceinject {
+	unsigned int mceinj_cpunr; /* target processor id */
+};
+
+struct xen_mc {
+	uint32_t cmd;
+	uint32_t interface_version; /* XEN_MCA_INTERFACE_VERSION */
+	union {
+		struct xen_mc_fetch        mc_fetch;
+		struct xen_mc_notifydomain mc_notifydomain;
+		struct xen_mc_physcpuinfo  mc_physcpuinfo;
+		struct xen_mc_msrinject    mc_msrinject;
+		struct xen_mc_mceinject    mc_mceinject;
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_mc);
+
+/*
+ * Fields are zero when not available. Also, this struct is shared with
+ * userspace mcelog and thus must keep existing fields at current offsets.
+ * Only add new fields to the end of the structure
+ */
+struct xen_mce {
+	__u64 status;
+	__u64 misc;
+	__u64 addr;
+	__u64 mcgstatus;
+	__u64 ip;
+	__u64 tsc;	/* cpu time stamp counter */
+	__u64 time;	/* wall time_t when error was detected */
+	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
+	__u8  inject_flags;	/* software inject flags */
+	__u16  pad;
+	__u32 cpuid;	/* CPUID 1 EAX */
+	__u8  cs;		/* code segment */
+	__u8  bank;	/* machine check bank */
+	__u8  cpu;	/* cpu number; obsolete; use extcpu now */
+	__u8  finished;   /* entry is valid */
+	__u32 extcpu;	/* linux cpu number that detected the error */
+	__u32 socketid;	/* CPU socket ID */
+	__u32 apicid;	/* CPU initial apic ID */
+	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
+	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
+	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
+	__u64 ppin;	/* Protected Processor Inventory Number */
+};
+
+/*
+ * This structure contains all data related to the MCE log.  Also
+ * carries a signature to make it easier to find from external
+ * debugging tools.  Each entry is only valid when its finished flag
+ * is set.
+ */
+
+#define XEN_MCE_LOG_LEN 32
+
+struct xen_mce_log {
+	char signature[12]; /* "MACHINECHECK" */
+	unsigned len;	    /* = XEN_MCE_LOG_LEN */
+	unsigned next;
+	unsigned flags;
+	unsigned recordlen;	/* length of struct xen_mce */
+	struct xen_mce entry[XEN_MCE_LOG_LEN];
+};
+
+#define XEN_MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
+
+#define XEN_MCE_LOG_SIGNATURE	"MACHINECHECK"
+
+#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
+#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
+#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
+
+#endif /* __ASSEMBLY__ */
+#endif /* __XEN_PUBLIC_ARCH_X86_MCA_H__ */