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, 655 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/fsl_hcalls.h b/arch/powerpc/include/asm/fsl_hcalls.h
new file mode 100644
index 000000000..b889d1354
--- /dev/null
+++ b/arch/powerpc/include/asm/fsl_hcalls.h
@@ -0,0 +1,655 @@
+/*
+ * Freescale hypervisor call interface
+ *
+ * Copyright 2008-2010 Freescale Semiconductor, Inc.
+ *
+ * Author: Timur Tabi <timur@freescale.com>
+ *
+ * This file is provided under a dual BSD/GPL license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _FSL_HCALLS_H
+#define _FSL_HCALLS_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/byteorder.h>
+#include <asm/epapr_hcalls.h>
+
+#define FH_API_VERSION			1
+
+#define FH_ERR_GET_INFO			1
+#define FH_PARTITION_GET_DTPROP		2
+#define FH_PARTITION_SET_DTPROP		3
+#define FH_PARTITION_RESTART		4
+#define FH_PARTITION_GET_STATUS		5
+#define FH_PARTITION_START		6
+#define FH_PARTITION_STOP		7
+#define FH_PARTITION_MEMCPY		8
+#define FH_DMA_ENABLE			9
+#define FH_DMA_DISABLE			10
+#define FH_SEND_NMI			11
+#define FH_VMPIC_GET_MSIR		12
+#define FH_SYSTEM_RESET			13
+#define FH_GET_CORE_STATE		14
+#define FH_ENTER_NAP			15
+#define FH_EXIT_NAP			16
+#define FH_CLAIM_DEVICE			17
+#define FH_PARTITION_STOP_DMA		18
+
+/* vendor ID: Freescale Semiconductor */
+#define FH_HCALL_TOKEN(num)		_EV_HCALL_TOKEN(EV_FSL_VENDOR_ID, num)
+
+/*
+ * We use "uintptr_t" to define a register because it's guaranteed to be a
+ * 32-bit integer on a 32-bit platform, and a 64-bit integer on a 64-bit
+ * platform.
+ *
+ * All registers are either input/output or output only.  Registers that are
+ * initialized before making the hypercall are input/output.  All
+ * input/output registers are represented with "+r".  Output-only registers
+ * are represented with "=r".  Do not specify any unused registers.  The
+ * clobber list will tell the compiler that the hypercall modifies those
+ * registers, which is good enough.
+ */
+
+/**
+ * fh_send_nmi - send NMI to virtual cpu(s).
+ * @vcpu_mask: send NMI to virtual cpu(s) specified by this mask.
+ *
+ * Returns 0 for success, or EINVAL for invalid vcpu_mask.
+ */
+static inline unsigned int fh_send_nmi(unsigned int vcpu_mask)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_SEND_NMI);
+	r3 = vcpu_mask;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/* Arbitrary limits to avoid excessive memory allocation in hypervisor */
+#define FH_DTPROP_MAX_PATHLEN 4096
+#define FH_DTPROP_MAX_PROPLEN 32768
+
+/**
+ * fh_partition_get_dtprop - get a property from a guest device tree.
+ * @handle: handle of partition whose device tree is to be accessed
+ * @dtpath_addr: physical address of device tree path to access
+ * @propname_addr: physical address of name of property
+ * @propvalue_addr: physical address of property value buffer
+ * @propvalue_len: length of buffer on entry, length of property on return
+ *
+ * Returns zero on success, non-zero on error.
+ */
+static inline unsigned int fh_partition_get_dtprop(int handle,
+						   uint64_t dtpath_addr,
+						   uint64_t propname_addr,
+						   uint64_t propvalue_addr,
+						   uint32_t *propvalue_len)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r7 __asm__("r7");
+	register uintptr_t r8 __asm__("r8");
+	register uintptr_t r9 __asm__("r9");
+	register uintptr_t r10 __asm__("r10");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_GET_DTPROP);
+	r3 = handle;
+
+#ifdef CONFIG_PHYS_64BIT
+	r4 = dtpath_addr >> 32;
+	r6 = propname_addr >> 32;
+	r8 = propvalue_addr >> 32;
+#else
+	r4 = 0;
+	r6 = 0;
+	r8 = 0;
+#endif
+	r5 = (uint32_t)dtpath_addr;
+	r7 = (uint32_t)propname_addr;
+	r9 = (uint32_t)propvalue_addr;
+	r10 = *propvalue_len;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11),
+		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7),
+		  "+r" (r8), "+r" (r9), "+r" (r10)
+		: : EV_HCALL_CLOBBERS8
+	);
+
+	*propvalue_len = r4;
+	return r3;
+}
+
+/**
+ * Set a property in a guest device tree.
+ * @handle: handle of partition whose device tree is to be accessed
+ * @dtpath_addr: physical address of device tree path to access
+ * @propname_addr: physical address of name of property
+ * @propvalue_addr: physical address of property value
+ * @propvalue_len: length of property
+ *
+ * Returns zero on success, non-zero on error.
+ */
+static inline unsigned int fh_partition_set_dtprop(int handle,
+						   uint64_t dtpath_addr,
+						   uint64_t propname_addr,
+						   uint64_t propvalue_addr,
+						   uint32_t propvalue_len)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r8 __asm__("r8");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r7 __asm__("r7");
+	register uintptr_t r9 __asm__("r9");
+	register uintptr_t r10 __asm__("r10");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_SET_DTPROP);
+	r3 = handle;
+
+#ifdef CONFIG_PHYS_64BIT
+	r4 = dtpath_addr >> 32;
+	r6 = propname_addr >> 32;
+	r8 = propvalue_addr >> 32;
+#else
+	r4 = 0;
+	r6 = 0;
+	r8 = 0;
+#endif
+	r5 = (uint32_t)dtpath_addr;
+	r7 = (uint32_t)propname_addr;
+	r9 = (uint32_t)propvalue_addr;
+	r10 = propvalue_len;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11),
+		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7),
+		  "+r" (r8), "+r" (r9), "+r" (r10)
+		: : EV_HCALL_CLOBBERS8
+	);
+
+	return r3;
+}
+
+/**
+ * fh_partition_restart - reboot the current partition
+ * @partition: partition ID
+ *
+ * Returns an error code if reboot failed.  Does not return if it succeeds.
+ */
+static inline unsigned int fh_partition_restart(unsigned int partition)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_RESTART);
+	r3 = partition;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+#define FH_PARTITION_STOPPED	0
+#define FH_PARTITION_RUNNING	1
+#define FH_PARTITION_STARTING	2
+#define FH_PARTITION_STOPPING	3
+#define FH_PARTITION_PAUSING	4
+#define FH_PARTITION_PAUSED	5
+#define FH_PARTITION_RESUMING	6
+
+/**
+ * fh_partition_get_status - gets the status of a partition
+ * @partition: partition ID
+ * @status: returned status code
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_partition_get_status(unsigned int partition,
+	unsigned int *status)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_GET_STATUS);
+	r3 = partition;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	*status = r4;
+
+	return r3;
+}
+
+/**
+ * fh_partition_start - boots and starts execution of the specified partition
+ * @partition: partition ID
+ * @entry_point: guest physical address to start execution
+ *
+ * The hypervisor creates a 1-to-1 virtual/physical IMA mapping, so at boot
+ * time, guest physical address are the same as guest virtual addresses.
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_partition_start(unsigned int partition,
+	uint32_t entry_point, int load)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_START);
+	r3 = partition;
+	r4 = entry_point;
+	r5 = load;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5)
+		: : EV_HCALL_CLOBBERS3
+	);
+
+	return r3;
+}
+
+/**
+ * fh_partition_stop - stops another partition
+ * @partition: partition ID
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_partition_stop(unsigned int partition)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_STOP);
+	r3 = partition;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/**
+ * struct fh_sg_list: definition of the fh_partition_memcpy S/G list
+ * @source: guest physical address to copy from
+ * @target: guest physical address to copy to
+ * @size: number of bytes to copy
+ * @reserved: reserved, must be zero
+ *
+ * The scatter/gather list for fh_partition_memcpy() is an array of these
+ * structures.  The array must be guest physically contiguous.
+ *
+ * This structure must be aligned on 32-byte boundary, so that no single
+ * strucuture can span two pages.
+ */
+struct fh_sg_list {
+	uint64_t source;   /**< guest physical address to copy from */
+	uint64_t target;   /**< guest physical address to copy to */
+	uint64_t size;     /**< number of bytes to copy */
+	uint64_t reserved; /**< reserved, must be zero */
+} __attribute__ ((aligned(32)));
+
+/**
+ * fh_partition_memcpy - copies data from one guest to another
+ * @source: the ID of the partition to copy from
+ * @target: the ID of the partition to copy to
+ * @sg_list: guest physical address of an array of &fh_sg_list structures
+ * @count: the number of entries in @sg_list
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_partition_memcpy(unsigned int source,
+	unsigned int target, phys_addr_t sg_list, unsigned int count)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r7 __asm__("r7");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_MEMCPY);
+	r3 = source;
+	r4 = target;
+	r5 = (uint32_t) sg_list;
+
+#ifdef CONFIG_PHYS_64BIT
+	r6 = sg_list >> 32;
+#else
+	r6 = 0;
+#endif
+	r7 = count;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11),
+		  "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7)
+		: : EV_HCALL_CLOBBERS5
+	);
+
+	return r3;
+}
+
+/**
+ * fh_dma_enable - enable DMA for the specified device
+ * @liodn: the LIODN of the I/O device for which to enable DMA
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_dma_enable(unsigned int liodn)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_DMA_ENABLE);
+	r3 = liodn;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/**
+ * fh_dma_disable - disable DMA for the specified device
+ * @liodn: the LIODN of the I/O device for which to disable DMA
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_dma_disable(unsigned int liodn)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_DMA_DISABLE);
+	r3 = liodn;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+
+/**
+ * fh_vmpic_get_msir - returns the MPIC-MSI register value
+ * @interrupt: the interrupt number
+ * @msir_val: returned MPIC-MSI register value
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_vmpic_get_msir(unsigned int interrupt,
+	unsigned int *msir_val)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = FH_HCALL_TOKEN(FH_VMPIC_GET_MSIR);
+	r3 = interrupt;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	*msir_val = r4;
+
+	return r3;
+}
+
+/**
+ * fh_system_reset - reset the system
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_system_reset(void)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_SYSTEM_RESET);
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "=r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+
+/**
+ * fh_err_get_info - get platform error information
+ * @queue id:
+ * 0 for guest error event queue
+ * 1 for global error event queue
+ *
+ * @pointer to store the platform error data:
+ * platform error data is returned in registers r4 - r11
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_err_get_info(int queue, uint32_t *bufsize,
+	uint32_t addr_hi, uint32_t addr_lo, int peek)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r7 __asm__("r7");
+
+	r11 = FH_HCALL_TOKEN(FH_ERR_GET_INFO);
+	r3 = queue;
+	r4 = *bufsize;
+	r5 = addr_hi;
+	r6 = addr_lo;
+	r7 = peek;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6),
+		  "+r" (r7)
+		: : EV_HCALL_CLOBBERS5
+	);
+
+	*bufsize = r4;
+
+	return r3;
+}
+
+
+#define FH_VCPU_RUN	0
+#define FH_VCPU_IDLE	1
+#define FH_VCPU_NAP	2
+
+/**
+ * fh_get_core_state - get the state of a vcpu
+ *
+ * @handle: handle of partition containing the vcpu
+ * @vcpu: vcpu number within the partition
+ * @state:the current state of the vcpu, see FH_VCPU_*
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_get_core_state(unsigned int handle,
+	unsigned int vcpu, unsigned int *state)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = FH_HCALL_TOKEN(FH_GET_CORE_STATE);
+	r3 = handle;
+	r4 = vcpu;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	*state = r4;
+	return r3;
+}
+
+/**
+ * fh_enter_nap - enter nap on a vcpu
+ *
+ * Note that though the API supports entering nap on a vcpu other
+ * than the caller, this may not be implmented and may return EINVAL.
+ *
+ * @handle: handle of partition containing the vcpu
+ * @vcpu: vcpu number within the partition
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_enter_nap(unsigned int handle, unsigned int vcpu)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = FH_HCALL_TOKEN(FH_ENTER_NAP);
+	r3 = handle;
+	r4 = vcpu;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	return r3;
+}
+
+/**
+ * fh_exit_nap - exit nap on a vcpu
+ * @handle: handle of partition containing the vcpu
+ * @vcpu: vcpu number within the partition
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_exit_nap(unsigned int handle, unsigned int vcpu)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = FH_HCALL_TOKEN(FH_EXIT_NAP);
+	r3 = handle;
+	r4 = vcpu;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	return r3;
+}
+/**
+ * fh_claim_device - claim a "claimable" shared device
+ * @handle: fsl,hv-device-handle of node to claim
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_claim_device(unsigned int handle)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_CLAIM_DEVICE);
+	r3 = handle;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/**
+ * Run deferred DMA disabling on a partition's private devices
+ *
+ * This applies to devices which a partition owns either privately,
+ * or which are claimable and still actively owned by that partition,
+ * and which do not have the no-dma-disable property.
+ *
+ * @handle: partition (must be stopped) whose DMA is to be disabled
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int fh_partition_stop_dma(unsigned int handle)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = FH_HCALL_TOKEN(FH_PARTITION_STOP_DMA);
+	r3 = handle;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+#endif