enlighten.c

/*
 * 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/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/bootmem.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/highmem.h>
#include <linux/console.h>

#include <xen/interface/xen.h>
#include <xen/interface/version.h>
#include <xen/interface/physdev.h>
#include <xen/interface/vcpu.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/hvc-console.h>

#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.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/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
#include <asm/stackprotector.h>

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

EXPORT_SYMBOL_GPL(hypercall_page);

DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);

enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);

struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);

struct shared_info xen_dummy_shared_info;

void *xen_initial_gdt;

/*
 * Point at some empty memory to start with. We map the real shared_info
 * page as soon as fixmap is up and running.
 */
struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;

/*
 * Flag to determine whether vcpu info placement is available on all
 * VCPUs.  We assume it is to start with, and then set it to zero on
 * the first failure.  This is because it can succeed on some VCPUs
 * and not others, since it can involve hypervisor memory allocation,
 * or because the guest failed to guarantee all the appropriate
 * constraints on all VCPUs (ie buffer can't cross a page boundary).
 *
 * Note that any particular CPU may be using a placed vcpu structure,
 * but we can only optimise if the all are.
 *
 * 0: not available, 1: available
 */
static int have_vcpu_info_placement = 1;

static void xen_vcpu_setup(int cpu)
{
	struct vcpu_register_vcpu_info info;
	int err;
	struct vcpu_info *vcpup;

	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
	per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];

	if (!have_vcpu_info_placement)
		return;		/* already tested, not available */

	vcpup = &per_cpu(xen_vcpu_info, cpu);

	info.mfn = arbitrary_virt_to_mfn(vcpup);
	info.offset = offset_in_page(vcpup);

	printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
	       cpu, vcpup, info.mfn, info.offset);

	/* Check to see if the hypervisor will put the vcpu_info
	   structure where we want it, which allows direct access via
	   a percpu-variable. */
	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);

	if (err) {
		printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
		have_vcpu_info_placement = 0;
	} else {
		/* This cpu is using the registered vcpu info, even if
		   later ones fail to. */
		per_cpu(xen_vcpu, cpu) = vcpup;

		printk(KERN_DEBUG "cpu %d using vcpu_info at %p\n",
		       cpu, vcpup);
	}
}

/*
 * On restore, set the vcpu placement up again.
 * If it fails, then we're in a bad state, since
 * we can't back out from using it...
 */
void xen_vcpu_restore(void)
{
	if (have_vcpu_info_placement) {
		int cpu;

		for_each_online_cpu(cpu) {
			bool other_cpu = (cpu != smp_processor_id());

			if (other_cpu &&
			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
				BUG();

			xen_vcpu_setup(cpu);

			if (other_cpu &&
			    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
				BUG();
		}

		BUG_ON(!have_vcpu_info_placement);
	}
}

static void __init xen_banner(void)
{
	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
	struct xen_extraversion extra;
	HYPERVISOR_xen_version(XENVER_extraversion, &extra);

	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
	       pv_info.name);
	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
	       version >> 16, version & 0xffff, extra.extraversion,
	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}

static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;

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

	/*
	 * Mask out inconvenient features, to try and disable as many
	 * unsupported kernel subsystems as possible.
	 */
	switch (*ax) {
	case 1:
		maskecx = cpuid_leaf1_ecx_mask;
		maskedx = cpuid_leaf1_edx_mask;
		break;

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