x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

6 files changed, 1120 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..25a0ce3b4
--- /dev/null
+++ b/arch/arm/xen/enlighten.c
@@ -0,0 +1,588 @@
+// 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;
+
+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_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 char *s = NULL;
+	int len;
+	size_t prefix_len = strlen(hyper_node.prefix);
+
+	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 (s && len > 0 && strnlen(s, len) < len &&
+	    len > prefix_len + 3 &&
+	    !strncmp(hyper_node.prefix, s, prefix_len))
+		hyper_node.version = s + prefix_len;
+
+	/*
+	 * 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 = kzalloc_objs(*regs, nr_reg);
+	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_obj(*tmp_res);
+		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(sizeof(struct vcpu_info),
+				       1 << fls(sizeof(struct vcpu_info) - 1));
+	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_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 xen_starting_runstate_cpu(unsigned int cpu)
+{
+	xen_setup_runstate_info(cpu);
+	return 0;
+}
+
+static int __init xen_late_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	register_platform_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);
+	}
+
+	if (xen_kernel_unmapped_at_usr())
+		return 0;
+
+	xen_time_setup_guest();
+
+	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
+				 "arm/xen_runstate:starting",
+				 xen_starting_runstate_cpu, NULL);
+}
+late_initcall(xen_late_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..882cd70c7
--- /dev/null
+++ b/arch/arm/xen/mm.c
@@ -0,0 +1,141 @@
+// 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 */
+	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..d911d91d5
--- /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_obj(*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);