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().
  ...

6 files changed, 1112 insertions, 0 deletions

diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
new file mode 100644
index 000000000..c32d04713
--- /dev/null
+++ b/arch/arm/xen/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
new file mode 100644
index 000000000..7d59765ae
--- /dev/null
+++ b/arch/arm/xen/enlighten.c
@@ -0,0 +1,578 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/hvm.h>
+#include <xen/interface/vcpu.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/interface/hvm/params.h>
+#include <xen/features.h>
+#include <xen/platform_pci.h>
+#include <xen/xenbus.h>
+#include <xen/page.h>
+#include <xen/interface/sched.h>
+#include <xen/xen-ops.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include <asm/system_misc.h>
+#include <asm/efi.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/cpuidle.h>
+#include <linux/cpufreq.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/reboot.h>
+#include <linux/time64.h>
+#include <linux/timekeeping.h>
+#include <linux/timekeeper_internal.h>
+#include <linux/acpi.h>
+#include <linux/virtio_anchor.h>
+
+#include <linux/mm.h>
+
+static struct start_info _xen_start_info;
+struct start_info *xen_start_info = &_xen_start_info;
+EXPORT_SYMBOL(xen_start_info);
+
+enum xen_domain_type xen_domain_type = XEN_NATIVE;
+EXPORT_SYMBOL(xen_domain_type);
+
+struct shared_info xen_dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
+
+DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
+static struct vcpu_info __percpu *xen_vcpu_info;
+
+/* Linux <-> Xen vCPU id mapping */
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
+EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
+/* These are unused until we support booting "pre-ballooned" */
+unsigned long xen_released_pages;
+struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
+
+static __read_mostly unsigned int xen_events_irq;
+static __read_mostly phys_addr_t xen_grant_frames;
+
+#define GRANT_TABLE_INDEX   0
+#define EXT_REGION_INDEX    1
+
+uint32_t xen_start_flags;
+EXPORT_SYMBOL(xen_start_flags);
+
+int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
+			       int nr, struct page **pages)
+{
+	return xen_xlate_unmap_gfn_range(vma, nr, pages);
+}
+EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
+
+static void xen_read_wallclock(struct timespec64 *ts)
+{
+	u32 version;
+	struct timespec64 now, ts_monotonic;
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	/* time since system boot */
+	ktime_get_ts64(&ts_monotonic);
+	*ts = timespec64_add(now, ts_monotonic);
+}
+
+static int xen_pvclock_gtod_notify(struct notifier_block *nb,
+				   unsigned long was_set, void *priv)
+{
+	/* Protected by the calling core code serialization */
+	static struct timespec64 next_sync;
+
+	struct xen_platform_op op;
+	struct timespec64 now, system_time;
+	struct timekeeper *tk = priv;
+
+	now.tv_sec = tk->xtime_sec;
+	now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
+	system_time = timespec64_add(now, tk->wall_to_monotonic);
+
+	/*
+	 * We only take the expensive HV call when the clock was set
+	 * or when the 11 minutes RTC synchronization time elapsed.
+	 */
+	if (!was_set && timespec64_compare(&now, &next_sync) < 0)
+		return NOTIFY_OK;
+
+	op.cmd = XENPF_settime64;
+	op.u.settime64.mbz = 0;
+	op.u.settime64.secs = now.tv_sec;
+	op.u.settime64.nsecs = now.tv_nsec;
+	op.u.settime64.system_time = timespec64_to_ns(&system_time);
+	(void)HYPERVISOR_platform_op(&op);
+
+	/*
+	 * Move the next drift compensation time 11 minutes
+	 * ahead. That's emulating the sync_cmos_clock() update for
+	 * the hardware RTC.
+	 */
+	next_sync = now;
+	next_sync.tv_sec += 11 * 60;
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_pvclock_gtod_notifier = {
+	.notifier_call = xen_pvclock_gtod_notify,
+};
+
+static int xen_starting_cpu(unsigned int cpu)
+{
+	struct vcpu_register_vcpu_info info;
+	struct vcpu_info *vcpup;
+	int err;
+
+	/* 
+	 * VCPUOP_register_vcpu_info cannot be called twice for the same
+	 * vcpu, so if vcpu_info is already registered, just get out. This
+	 * can happen with cpu-hotplug.
+	 */
+	if (per_cpu(xen_vcpu, cpu) != NULL)
+		goto after_register_vcpu_info;
+
+	pr_info("Xen: initializing cpu%d\n", cpu);
+	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
+
+	info.mfn = percpu_to_gfn(vcpup);
+	info.offset = xen_offset_in_page(vcpup);
+
+	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+				 &info);
+	BUG_ON(err);
+	per_cpu(xen_vcpu, cpu) = vcpup;
+
+	if (!xen_kernel_unmapped_at_usr())
+		xen_setup_runstate_info(cpu);
+
+after_register_vcpu_info:
+	enable_percpu_irq(xen_events_irq, 0);
+	return 0;
+}
+
+static int xen_dying_cpu(unsigned int cpu)
+{
+	disable_percpu_irq(xen_events_irq);
+	return 0;
+}
+
+void xen_reboot(int reason)
+{
+	struct sched_shutdown r = { .reason = reason };
+	int rc;
+
+	rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+	BUG_ON(rc);
+}
+
+static int xen_restart(struct notifier_block *nb, unsigned long action,
+		       void *data)
+{
+	xen_reboot(SHUTDOWN_reboot);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xen_restart_nb = {
+	.notifier_call = xen_restart,
+	.priority = 192,
+};
+
+static void xen_power_off(void)
+{
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
+static irqreturn_t xen_arm_callback(int irq, void *arg)
+{
+	xen_hvm_evtchn_do_upcall();
+	return IRQ_HANDLED;
+}
+
+static __initdata struct {
+	const char *compat;
+	const char *prefix;
+	const char *version;
+	bool found;
+} hyper_node = {"xen,xen", "xen,xen-", NULL, false};
+
+static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
+				      int depth, void *data)
+{
+	const void *s = NULL;
+	int len;
+
+	if (depth != 1 || strcmp(uname, "hypervisor") != 0)
+		return 0;
+
+	if (of_flat_dt_is_compatible(node, hyper_node.compat))
+		hyper_node.found = true;
+
+	s = of_get_flat_dt_prop(node, "compatible", &len);
+	if (strlen(hyper_node.prefix) + 3  < len &&
+	    !strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
+		hyper_node.version = s + strlen(hyper_node.prefix);
+
+	/*
+	 * Check if Xen supports EFI by checking whether there is the
+	 * "/hypervisor/uefi" node in DT. If so, runtime services are available
+	 * through proxy functions (e.g. in case of Xen dom0 EFI implementation
+	 * they call special hypercall which executes relevant EFI functions)
+	 * and that is why they are always enabled.
+	 */
+	if (IS_ENABLED(CONFIG_XEN_EFI)) {
+		if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
+		    !efi_runtime_disabled())
+			set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+	}
+
+	return 0;
+}
+
+/*
+ * see Documentation/devicetree/bindings/arm/xen.txt for the
+ * documentation of the Xen Device Tree format.
+ */
+void __init xen_early_init(void)
+{
+	of_scan_flat_dt(fdt_find_hyper_node, NULL);
+	if (!hyper_node.found) {
+		pr_debug("No Xen support\n");
+		return;
+	}
+
+	if (hyper_node.version == NULL) {
+		pr_debug("Xen version not found\n");
+		return;
+	}
+
+	pr_info("Xen %s support found\n", hyper_node.version);
+
+	xen_domain_type = XEN_HVM_DOMAIN;
+
+	xen_setup_features();
+
+	if (xen_feature(XENFEAT_dom0))
+		xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
+
+	if (!console_set_on_cmdline && !xen_initial_domain())
+		add_preferred_console("hvc", 0, NULL);
+}
+
+static void __init xen_acpi_guest_init(void)
+{
+#ifdef CONFIG_ACPI
+	struct xen_hvm_param a;
+	int interrupt, trigger, polarity;
+
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+
+	if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
+	    || (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
+		xen_events_irq = 0;
+		return;
+	}
+
+	interrupt = a.value & 0xff;
+	trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
+					 : ACPI_LEVEL_SENSITIVE;
+	polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
+					  : ACPI_ACTIVE_HIGH;
+	xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
+#endif
+}
+
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+/*
+ * A type-less specific Xen resource which contains extended regions
+ * (unused regions of guest physical address space provided by the hypervisor).
+ */
+static struct resource xen_resource = {
+	.name = "Xen unused space",
+};
+
+int __init arch_xen_unpopulated_init(struct resource **res)
+{
+	struct device_node *np;
+	struct resource *regs, *tmp_res;
+	uint64_t min_gpaddr = -1, max_gpaddr = 0;
+	unsigned int i, nr_reg = 0;
+	int rc;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!acpi_disabled)
+		return -ENODEV;
+
+	np = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (WARN_ON(!np))
+		return -ENODEV;
+
+	/* Skip region 0 which is reserved for grant table space */
+	while (of_get_address(np, nr_reg + EXT_REGION_INDEX, NULL, NULL))
+		nr_reg++;
+
+	if (!nr_reg) {
+		pr_err("No extended regions are found\n");
+		of_node_put(np);
+		return -EINVAL;
+	}
+
+	regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL);
+	if (!regs) {
+		of_node_put(np);
+		return -ENOMEM;
+	}
+
+	/*
+	 * Create resource from extended regions provided by the hypervisor to be
+	 * used as unused address space for Xen scratch pages.
+	 */
+	for (i = 0; i < nr_reg; i++) {
+		rc = of_address_to_resource(np, i + EXT_REGION_INDEX, &regs[i]);
+		if (rc)
+			goto err;
+
+		if (max_gpaddr < regs[i].end)
+			max_gpaddr = regs[i].end;
+		if (min_gpaddr > regs[i].start)
+			min_gpaddr = regs[i].start;
+	}
+
+	xen_resource.start = min_gpaddr;
+	xen_resource.end = max_gpaddr;
+
+	/*
+	 * Mark holes between extended regions as unavailable. The rest of that
+	 * address space will be available for the allocation.
+	 */
+	for (i = 1; i < nr_reg; i++) {
+		resource_size_t start, end;
+
+		/* There is an overlap between regions */
+		if (regs[i - 1].end + 1 > regs[i].start) {
+			rc = -EINVAL;
+			goto err;
+		}
+
+		/* There is no hole between regions */
+		if (regs[i - 1].end + 1 == regs[i].start)
+			continue;
+
+		start = regs[i - 1].end + 1;
+		end = regs[i].start - 1;
+
+		tmp_res = kzalloc(sizeof(*tmp_res), GFP_KERNEL);
+		if (!tmp_res) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		tmp_res->name = "Unavailable space";
+		tmp_res->start = start;
+		tmp_res->end = end;
+
+		rc = insert_resource(&xen_resource, tmp_res);
+		if (rc) {
+			pr_err("Cannot insert resource %pR (%d)\n", tmp_res, rc);
+			kfree(tmp_res);
+			goto err;
+		}
+	}
+
+	*res = &xen_resource;
+
+err:
+	of_node_put(np);
+	kfree(regs);
+	return rc;
+}
+#endif
+
+static void __init xen_dt_guest_init(void)
+{
+	struct device_node *xen_node;
+	struct resource res;
+
+	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (!xen_node) {
+		pr_err("Xen support was detected before, but it has disappeared\n");
+		return;
+	}
+
+	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+
+	if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) {
+		pr_err("Xen grant table region is not found\n");
+		of_node_put(xen_node);
+		return;
+	}
+	of_node_put(xen_node);
+	xen_grant_frames = res.start;
+}
+
+static int __init xen_guest_init(void)
+{
+	struct xen_add_to_physmap xatp;
+	struct shared_info *shared_info_page = NULL;
+	int rc, cpu;
+
+	if (!xen_domain())
+		return 0;
+
+	if (IS_ENABLED(CONFIG_XEN_VIRTIO))
+		virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);
+
+	if (!acpi_disabled)
+		xen_acpi_guest_init();
+	else
+		xen_dt_guest_init();
+
+	if (!xen_events_irq) {
+		pr_err("Xen event channel interrupt not found\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
+	 * parameters are found. Force enable runtime services.
+	 */
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		xen_efi_runtime_setup();
+
+	shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
+
+	if (!shared_info_page) {
+		pr_err("not enough memory\n");
+		return -ENOMEM;
+	}
+	xatp.domid = DOMID_SELF;
+	xatp.idx = 0;
+	xatp.space = XENMAPSPACE_shared_info;
+	xatp.gpfn = virt_to_gfn(shared_info_page);
+	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
+		BUG();
+
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
+
+	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
+	 * page, we use it in the event channel upcall and in some pvclock
+	 * related functions. 
+	 * The shared info contains exactly 1 CPU (the boot CPU). The guest
+	 * is required to use VCPUOP_register_vcpu_info to place vcpu info
+	 * for secondary CPUs as they are brought up.
+	 * For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
+	 */
+	xen_vcpu_info = alloc_percpu(struct vcpu_info);
+	if (xen_vcpu_info == NULL)
+		return -ENOMEM;
+
+	/* Direct vCPU id mapping for ARM guests. */
+	for_each_possible_cpu(cpu)
+		per_cpu(xen_vcpu_id, cpu) = cpu;
+
+	if (!xen_grant_frames) {
+		xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
+		rc = xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
+										   &xen_auto_xlat_grant_frames.vaddr,
+										   xen_auto_xlat_grant_frames.count);
+	} else
+		rc = gnttab_setup_auto_xlat_frames(xen_grant_frames);
+	if (rc) {
+		free_percpu(xen_vcpu_info);
+		return rc;
+	}
+	gnttab_init();
+
+	/*
+	 * Making sure board specific code will not set up ops for
+	 * cpu idle and cpu freq.
+	 */
+	disable_cpuidle();
+	disable_cpufreq();
+
+	xen_init_IRQ();
+
+	if (request_percpu_irq(xen_events_irq, xen_arm_callback,
+			       "events", &xen_vcpu)) {
+		pr_err("Error request IRQ %d\n", xen_events_irq);
+		return -EINVAL;
+	}
+
+	if (!xen_kernel_unmapped_at_usr())
+		xen_time_setup_guest();
+
+	if (xen_initial_domain())
+		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
+
+	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
+				 "arm/xen:starting", xen_starting_cpu,
+				 xen_dying_cpu);
+}
+early_initcall(xen_guest_init);
+
+static int __init xen_pm_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	pm_power_off = xen_power_off;
+	register_restart_handler(&xen_restart_nb);
+	if (!xen_initial_domain()) {
+		struct timespec64 ts;
+		xen_read_wallclock(&ts);
+		do_settimeofday64(&ts);
+	}
+
+	return 0;
+}
+late_initcall(xen_pm_init);
+
+
+/* empty stubs */
+void xen_arch_pre_suspend(void) { }
+void xen_arch_post_suspend(int suspend_cancelled) { }
+void xen_timer_resume(void) { }
+void xen_arch_resume(void) { }
+void xen_arch_suspend(void) { }
+
+
+/* In the hypercall.S file. */
+EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);
+EXPORT_SYMBOL_GPL(HYPERVISOR_console_io);
+EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
+EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
+EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
+EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
+EXPORT_SYMBOL_GPL(privcmd_call);
diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c
new file mode 100644
index 000000000..91cf08ba1
--- /dev/null
+++ b/arch/arm/xen/grant-table.c
@@ -0,0 +1,58 @@
+/******************************************************************************
+ * grant_table.c
+ * ARM specific part
+ *
+ * Granting foreign access to our memory reservation.
+ *
+ * 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.
+ */
+
+#include <xen/interface/xen.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+
+int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   void **__shared)
+{
+	return -ENOSYS;
+}
+
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
+{
+	return;
+}
+
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
+{
+	return -ENOSYS;
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	return 0;
+}
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
new file mode 100644
index 000000000..f794dac98
--- /dev/null
+++ b/arch/arm/xen/hypercall.S
@@ -0,0 +1,121 @@
+/******************************************************************************
+ * hypercall.S
+ *
+ * Xen hypercall wrappers
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ *
+ * 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.
+ */
+
+/*
+ * The Xen hypercall calling convention is very similar to the ARM
+ * procedure calling convention: the first paramter is passed in r0, the
+ * second in r1, the third in r2 and the fourth in r3. Considering that
+ * Xen hypercalls have 5 arguments at most, the fifth paramter is passed
+ * in r4, differently from the procedure calling convention of using the
+ * stack for that case.
+ *
+ * The hypercall number is passed in r12.
+ *
+ * The return value is in r0.
+ *
+ * The hvc ISS is required to be 0xEA1, that is the Xen specific ARM
+ * hypercall tag.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/opcodes-virt.h>
+#include <xen/interface/xen.h>
+
+
+#define XEN_IMM 0xEA1
+
+#define HYPERCALL_SIMPLE(hypercall)		\
+ENTRY(HYPERVISOR_##hypercall)			\
+	mov r12, #__HYPERVISOR_##hypercall;	\
+	__HVC(XEN_IMM);						\
+	ret lr;					\
+ENDPROC(HYPERVISOR_##hypercall)
+
+#define HYPERCALL0 HYPERCALL_SIMPLE
+#define HYPERCALL1 HYPERCALL_SIMPLE
+#define HYPERCALL2 HYPERCALL_SIMPLE
+#define HYPERCALL3 HYPERCALL_SIMPLE
+#define HYPERCALL4 HYPERCALL_SIMPLE
+
+#define HYPERCALL5(hypercall)			\
+ENTRY(HYPERVISOR_##hypercall)			\
+	stmdb sp!, {r4}						\
+	ldr r4, [sp, #4]					\
+	mov r12, #__HYPERVISOR_##hypercall;	\
+	__HVC(XEN_IMM);						\
+	ldm sp!, {r4}						\
+	ret lr					\
+ENDPROC(HYPERVISOR_##hypercall)
+
+                .text
+
+HYPERCALL2(xen_version);
+HYPERCALL3(console_io);
+HYPERCALL3(grant_table_op);
+HYPERCALL2(sched_op);
+HYPERCALL2(event_channel_op);
+HYPERCALL2(hvm_op);
+HYPERCALL2(memory_op);
+HYPERCALL2(physdev_op);
+HYPERCALL3(vcpu_op);
+HYPERCALL1(platform_op_raw);
+HYPERCALL2(multicall);
+HYPERCALL2(vm_assist);
+HYPERCALL3(dm_op);
+
+ENTRY(privcmd_call)
+	stmdb sp!, {r4}
+	mov r12, r0
+	mov r0, r1
+	mov r1, r2
+	mov r2, r3
+	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
+	ldr r4, [sp, #4]
+	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS) is called before.
+	 */
+	uaccess_disable r4
+
+	ldm sp!, {r4}
+	ret lr
+ENDPROC(privcmd_call);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
new file mode 100644
index 000000000..3d826c0b5
--- /dev/null
+++ b/arch/arm/xen/mm.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/cpu.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+
+#include <xen/xen.h>
+#include <xen/interface/grant_table.h>
+#include <xen/interface/memory.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/cacheflush.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
+
+static gfp_t xen_swiotlb_gfp(void)
+{
+	phys_addr_t base;
+	u64 i;
+
+	for_each_mem_range(i, &base, NULL) {
+		if (base < (phys_addr_t)0xffffffff) {
+			if (IS_ENABLED(CONFIG_ZONE_DMA32))
+				return __GFP_DMA32;
+			return __GFP_DMA;
+		}
+	}
+
+	return GFP_KERNEL;
+}
+
+static bool hypercall_cflush = false;
+
+/* buffers in highmem or foreign pages cannot cross page boundaries */
+static void dma_cache_maint(struct device *dev, dma_addr_t handle,
+			    size_t size, u32 op)
+{
+	struct gnttab_cache_flush cflush;
+
+	cflush.offset = xen_offset_in_page(handle);
+	cflush.op = op;
+	handle &= XEN_PAGE_MASK;
+
+	do {
+		cflush.a.dev_bus_addr = dma_to_phys(dev, handle);
+
+		if (size + cflush.offset > XEN_PAGE_SIZE)
+			cflush.length = XEN_PAGE_SIZE - cflush.offset;
+		else
+			cflush.length = size;
+
+		HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
+
+		cflush.offset = 0;
+		handle += cflush.length;
+		size -= cflush.length;
+	} while (size);
+}
+
+/*
+ * Dom0 is mapped 1:1, and while the Linux page can span across multiple Xen
+ * pages, it is not possible for it to contain a mix of local and foreign Xen
+ * pages.  Calling pfn_valid on a foreign mfn will always return false, so if
+ * pfn_valid returns true the pages is local and we can use the native
+ * dma-direct functions, otherwise we call the Xen specific version.
+ */
+void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
+			  size_t size, enum dma_data_direction dir)
+{
+	if (dir != DMA_TO_DEVICE)
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL);
+}
+
+void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
+			     size_t size, enum dma_data_direction dir)
+{
+	if (dir == DMA_FROM_DEVICE)
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL);
+	else
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_CLEAN);
+}
+
+bool xen_arch_need_swiotlb(struct device *dev,
+			   phys_addr_t phys,
+			   dma_addr_t dev_addr)
+{
+	unsigned int xen_pfn = XEN_PFN_DOWN(phys);
+	unsigned int bfn = XEN_PFN_DOWN(dma_to_phys(dev, dev_addr));
+
+	/*
+	 * The swiotlb buffer should be used if
+	 *	- Xen doesn't have the cache flush hypercall
+	 *	- The Linux page refers to foreign memory
+	 *	- The device doesn't support coherent DMA request
+	 *
+	 * The Linux page may be spanned acrros multiple Xen page, although
+	 * it's not possible to have a mix of local and foreign Xen page.
+	 * Furthermore, range_straddles_page_boundary is already checking
+	 * if buffer is physically contiguous in the host RAM.
+	 *
+	 * Therefore we only need to check the first Xen page to know if we
+	 * require a bounce buffer because the device doesn't support coherent
+	 * memory and we are not able to flush the cache.
+	 */
+	return (!hypercall_cflush && (xen_pfn != bfn) &&
+		!dev_is_dma_coherent(dev));
+}
+
+static int __init xen_mm_init(void)
+{
+	struct gnttab_cache_flush cflush;
+	int rc;
+
+	if (!xen_swiotlb_detect())
+		return 0;
+
+	/* we can work with the default swiotlb */
+	if (!io_tlb_default_mem.nslabs) {
+		rc = swiotlb_init_late(swiotlb_size_or_default(),
+				       xen_swiotlb_gfp(), NULL);
+		if (rc < 0)
+			return rc;
+	}
+
+	cflush.op = 0;
+	cflush.a.dev_bus_addr = 0;
+	cflush.offset = 0;
+	cflush.length = 0;
+	if (HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1) != -ENOSYS)
+		hypercall_cflush = true;
+	return 0;
+}
+arch_initcall(xen_mm_init);
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
new file mode 100644
index 000000000..309648c17
--- /dev/null
+++ b/arch/arm/xen/p2m.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/memblock.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+
+#include <xen/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/cacheflush.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
+
+struct xen_p2m_entry {
+	unsigned long pfn;
+	unsigned long mfn;
+	unsigned long nr_pages;
+	struct rb_node rbnode_phys;
+};
+
+static rwlock_t p2m_lock;
+struct rb_root phys_to_mach = RB_ROOT;
+EXPORT_SYMBOL_GPL(phys_to_mach);
+
+static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new)
+{
+	struct rb_node **link = &phys_to_mach.rb_node;
+	struct rb_node *parent = NULL;
+	struct xen_p2m_entry *entry;
+	int rc = 0;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys);
+
+		if (new->pfn == entry->pfn)
+			goto err_out;
+
+		if (new->pfn < entry->pfn)
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+	rb_link_node(&new->rbnode_phys, parent, link);
+	rb_insert_color(&new->rbnode_phys, &phys_to_mach);
+	goto out;
+
+err_out:
+	rc = -EINVAL;
+	pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n",
+			__func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn);
+out:
+	return rc;
+}
+
+unsigned long __pfn_to_mfn(unsigned long pfn)
+{
+	struct rb_node *n;
+	struct xen_p2m_entry *entry;
+	unsigned long irqflags;
+
+	read_lock_irqsave(&p2m_lock, irqflags);
+	n = phys_to_mach.rb_node;
+	while (n) {
+		entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
+		if (entry->pfn <= pfn &&
+				entry->pfn + entry->nr_pages > pfn) {
+			unsigned long mfn = entry->mfn + (pfn - entry->pfn);
+			read_unlock_irqrestore(&p2m_lock, irqflags);
+			return mfn;
+		}
+		if (pfn < entry->pfn)
+			n = n->rb_left;
+		else
+			n = n->rb_right;
+	}
+	read_unlock_irqrestore(&p2m_lock, irqflags);
+
+	return INVALID_P2M_ENTRY;
+}
+EXPORT_SYMBOL_GPL(__pfn_to_mfn);
+
+int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+			    struct gnttab_map_grant_ref *kmap_ops,
+			    struct page **pages, unsigned int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct gnttab_unmap_grant_ref unmap;
+		int rc;
+
+		if (map_ops[i].status)
+			continue;
+		if (likely(set_phys_to_machine(map_ops[i].host_addr >> XEN_PAGE_SHIFT,
+				    map_ops[i].dev_bus_addr >> XEN_PAGE_SHIFT)))
+			continue;
+
+		/*
+		 * Signal an error for this slot. This in turn requires
+		 * immediate unmapping.
+		 */
+		map_ops[i].status = GNTST_general_error;
+		unmap.host_addr = map_ops[i].host_addr,
+		unmap.handle = map_ops[i].handle;
+		map_ops[i].handle = INVALID_GRANT_HANDLE;
+		if (map_ops[i].flags & GNTMAP_device_map)
+			unmap.dev_bus_addr = map_ops[i].dev_bus_addr;
+		else
+			unmap.dev_bus_addr = 0;
+
+		/*
+		 * Pre-populate the status field, to be recognizable in
+		 * the log message below.
+		 */
+		unmap.status = 1;
+
+		rc = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref,
+					       &unmap, 1);
+		if (rc || unmap.status != GNTST_okay)
+			pr_err_once("gnttab unmap failed: rc=%d st=%d\n",
+				    rc, unmap.status);
+	}
+
+	return 0;
+}
+
+int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
+			      struct gnttab_unmap_grant_ref *kunmap_ops,
+			      struct page **pages, unsigned int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		set_phys_to_machine(unmap_ops[i].host_addr >> XEN_PAGE_SHIFT,
+				    INVALID_P2M_ENTRY);
+	}
+
+	return 0;
+}
+
+bool __set_phys_to_machine_multi(unsigned long pfn,
+		unsigned long mfn, unsigned long nr_pages)
+{
+	int rc;
+	unsigned long irqflags;
+	struct xen_p2m_entry *p2m_entry;
+	struct rb_node *n;
+
+	if (mfn == INVALID_P2M_ENTRY) {
+		write_lock_irqsave(&p2m_lock, irqflags);
+		n = phys_to_mach.rb_node;
+		while (n) {
+			p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
+			if (p2m_entry->pfn <= pfn &&
+					p2m_entry->pfn + p2m_entry->nr_pages > pfn) {
+				rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach);
+				write_unlock_irqrestore(&p2m_lock, irqflags);
+				kfree(p2m_entry);
+				return true;
+			}
+			if (pfn < p2m_entry->pfn)
+				n = n->rb_left;
+			else
+				n = n->rb_right;
+		}
+		write_unlock_irqrestore(&p2m_lock, irqflags);
+		return true;
+	}
+
+	p2m_entry = kzalloc(sizeof(*p2m_entry), GFP_NOWAIT);
+	if (!p2m_entry)
+		return false;
+
+	p2m_entry->pfn = pfn;
+	p2m_entry->nr_pages = nr_pages;
+	p2m_entry->mfn = mfn;
+
+	write_lock_irqsave(&p2m_lock, irqflags);
+	rc = xen_add_phys_to_mach_entry(p2m_entry);
+	if (rc < 0) {
+		write_unlock_irqrestore(&p2m_lock, irqflags);
+		kfree(p2m_entry);
+		return false;
+	}
+	write_unlock_irqrestore(&p2m_lock, irqflags);
+	return true;
+}
+EXPORT_SYMBOL_GPL(__set_phys_to_machine_multi);
+
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	return __set_phys_to_machine_multi(pfn, mfn, 1);
+}
+EXPORT_SYMBOL_GPL(__set_phys_to_machine);
+
+static int p2m_init(void)
+{
+	rwlock_init(&p2m_lock);
+	return 0;
+}
+arch_initcall(p2m_init);