path: root/arch/x86/xen/enlighten_pv.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Core of Xen paravirt_ops implementation.
 *
 * This file contains the xen_paravirt_ops structure itself, and the
 * implementations for:
 * - privileged instructions
 * - interrupt flags
 * - segment operations
 * - booting and setup
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/preempt.h>
#include <linux/hardirq.h>
#include <linux/percpu.h>
#include <linux/delay.h>
#include <linux/start_kernel.h>
#include <linux/sched.h>
#include <linux/kprobes.h>
#include <linux/kstrtox.h>
#include <linux/memblock.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/edd.h>
#include <linux/reboot.h>
#include <linux/virtio_anchor.h>
#include <linux/stackprotector.h>

#include <xen/xen.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/version.h>
#include <xen/interface/physdev.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/memory.h>
#include <xen/interface/nmi.h>
#include <xen/interface/xen-mca.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/hvc-console.h>
#include <xen/acpi.h>

#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/page.h>
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/cpuid.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/msr-index.h>
#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
#include <asm/hypervisor.h>
#include <asm/mach_traps.h>
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
#include <asm/cpu.h>
#ifdef CONFIG_X86_IOPL_IOPERM
#include <asm/io_bitmap.h>
#endif

#ifdef CONFIG_ACPI
#include <linux/acpi.h>
#include <asm/acpi.h>
#include <acpi/pdc_intel.h>
#include <acpi/processor.h>
#include <xen/interface/platform.h>
#endif

#include "xen-ops.h"
#include "mmu.h"
#include "smp.h"
#include "multicalls.h"
#include "pmu.h"

#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */

void *xen_initial_gdt;

static int xen_cpu_up_prepare_pv(unsigned int cpu);
static int xen_cpu_dead_pv(unsigned int cpu);

struct tls_descs {
	struct desc_struct desc[3];
};

/*
 * Updating the 3 TLS descriptors in the GDT on every task switch is
 * surprisingly expensive so we avoid updating them if they haven't
 * changed.  Since Xen writes different descriptors than the one
 * passed in the update_descriptor hypercall we keep shadow copies to
 * compare against.
 */
static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);

static __read_mostly bool xen_msr_safe = IS_ENABLED(CONFIG_XEN_PV_MSR_SAFE);

static int __init parse_xen_msr_safe(char *str)
{
	if (str)
		return kstrtobool(str, &xen_msr_safe);
	return -EINVAL;
}
early_param("xen_msr_safe", parse_xen_msr_safe);

/* Get MTRR settings from Xen and put them into mtrr_state. */
static void __init xen_set_mtrr_data(void)
{
#ifdef CONFIG_MTRR
	struct xen_platform_op op = {
		.cmd = XENPF_read_memtype,
		.interface_version = XENPF_INTERFACE_VERSION,
	};
	unsigned int reg;
	unsigned long mask;
	uint32_t eax, width;
	static struct mtrr_var_range var[MTRR_MAX_VAR_RANGES] __initdata;

	/* Get physical address width (only 64-bit cpus supported). */
	width = 36;
	eax = cpuid_eax(0x80000000);
	if ((eax >> 16) == 0x8000 && eax >= 0x80000008) {
		eax = cpuid_eax(0x80000008);
		width = eax & 0xff;
	}

	for (reg = 0; reg < MTRR_MAX_VAR_RANGES; reg++) {
		op.u.read_memtype.reg = reg;
		if (HYPERVISOR_platform_op(&op))
			break;

		/*
		 * Only called in dom0, which has all RAM PFNs mapped at
		 * RAM MFNs, and all PCI space etc. is identity mapped.
		 * This means we can treat MFN == PFN regarding MTRR settings.
		 */
		var[reg].base_lo = op.u.read_memtype.type;
		var[reg].base_lo |= op.u.read_memtype.mfn << PAGE_SHIFT;
		var[reg].base_hi = op.u.read_memtype.mfn >> (32 - PAGE_SHIFT);
		mask = ~((op.u.read_memtype.nr_mfns << PAGE_SHIFT) - 1);
		mask &= (1UL << width) - 1;
		if (mask)
			mask |= MTRR_PHYSMASK_V;
		var[reg].mask_lo = mask;
		var[reg].mask_hi = mask >> 32;
	}

	/* Only overwrite MTRR state if any MTRR could be got from Xen. */
	if (reg)
		mtrr_overwrite_state(var, reg, MTRR_TYPE_UNCACHABLE);
#endif
}

static void __init xen_pv_init_platform(void)
{
	/* PV guests can't operate virtio devices without grants. */
	if (IS_ENABLED(CONFIG_XEN_VIRTIO))
		virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);

	populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP));

	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);

	/* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */
	xen_vcpu_info_reset(0);

	/* pvclock is in shared info area */
	xen_init_time_ops();

	if (xen_initial_domain())
		xen_set_mtrr_data();
	else
		mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
}

static void __init xen_pv_guest_late_init(void)
{
#ifndef CONFIG_SMP
	/* Setup shared vcpu info for non-smp configurations */
	xen_setup_vcpu_info_placement();
#endif
}

static __read_mostly unsigned int cpuid_leaf5_ecx_val;
static __read_mostly unsigned int cpuid_leaf5_edx_val;

static void xen_cpuid(unsigned int *ax, unsigned int *bx,
		      unsigned int *cx, unsigned int *dx)
{
	unsigned maskebx = ~0;

	/*
	 * Mask out inconvenient features, to try and disable as many
	 * unsupported kernel subsystems as possible.
	 */
	switch (*ax) {
	case CPUID_MWAIT_LEAF:
		/* Synthesize the values.. */
		*ax = 0;
		*bx = 0;
		*cx = cpuid_leaf5_ecx_val;
		*dx = cpuid_leaf5_edx_val;
		return;

	case 0xb:
		/* Suppress extended topology stuff */
		maskebx = 0;
		break;
	}

	asm(XEN_EMULATE_PREFIX "cpuid"
		: "=a" (*ax),
		  "=b" (*bx),
		  "=c" (*cx),
		  "=d" (*dx)
		: "0" (*ax), "2" (*cx));

	*bx &= maskebx;
}

static bool __init xen_check_mwait(void)
{
#ifdef CONFIG_ACPI
	struct xen_platform_op op = {
		.cmd			= XENPF_set_processor_pminfo,
		.u.set_pminfo.id	= -1,
		.u.set_pminfo.type	= XEN_PM_PDC,
	};
	uint32_t buf[3];
	unsigned int ax, bx, cx, dx;
	unsigned int mwait_mask;

	/* We need to determine whether it is OK to expose the MWAIT
	 * capability to the kernel to harvest deeper than C3 states from ACPI
	 * _CST using the processor_harvest_xen.c module. For this to work, we
	 * need to gather the MWAIT_LEAF values (which the cstate.c code
	 * checks against). The hypervisor won't expose the MWAIT flag because
	 * it would break