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

#include <xen/interface/xen.h>
#include <xen/interface/physdev.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/sched.h>
#include <xen/features.h>
#include <xen/page.h>

#include <asm/paravirt.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/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.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);

/*
 * Note about cr3 (pagetable base) values:
 *
 * xen_cr3 contains the current logical cr3 value; it contains the
 * last set cr3.  This may not be the current effective cr3, because
 * its update may be being lazily deferred.  However, a vcpu looking
 * at its own cr3 can use this value knowing that it everything will
 * be self-consistent.
 *
 * xen_current_cr3 contains the actual vcpu cr3; it is set once the
 * hypercall to set the vcpu cr3 is complete (so it may be a little
 * out of date, but it will never be set early).  If one vcpu is
 * looking at another vcpu's cr3 value, it should use this variable.
 */
DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */

struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);

static /* __initdata */ struct shared_info dummy_shared_info;

/*
 * 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 *)&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 = 0;

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

	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 = 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);
	}
}

static void __init xen_banner(void)
{
	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
	       pv_info.name);
	printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
}

static void xen_cpuid(unsigned int *eax, unsigned int *ebx,
		      unsigned int *ecx, unsigned int *edx)
{
	unsigned maskedx = ~0;

	/*
	 * Mask out inconvenient features, to try and disable as many
	 * unsupported kernel subsystems as possible.
	 */
	if (*eax == 1)
		maskedx = ~((1 << X86_FEATURE_APIC) |  /* disable APIC */
			    (1 << X86_FEATURE_ACPI) |  /* disable ACPI */
			    (1 << X86_FEATURE_ACC));   /* thermal monitoring */

	asm(XEN_EMULATE_PREFIX "cpuid"
		: "=a" (*eax),
		  "=b" (*ebx),
		  "=c" (*ecx),
		  "=d" (*edx)
		: "0" (*eax), "2" (*ecx));
	*edx &= maskedx;
}

static void xen_set_debugreg(int reg, unsigned long val)
{
	HYPERVISOR_set_debugreg(reg, val);
}

static unsigned long xen_get_debugreg(int reg)
{
	return HYPERVISOR_get_debugreg(reg);
}

static unsigned long xen_save_fl(void)
{
	struct vcpu_info *vcpu;
	unsigned long flags;

	vcpu = x86_read_percpu(xen_vcpu);

	/* flag has opposite sense of mask */
	flags = !vcpu->evtchn_upcall_mask;

	/* convert to IF type flag
	   -0 -> 0x00000000
	   -1 -> 0xffffffff
	*/
	return (-flags) & X86_EFLAGS_IF;
}

static void xen_restore_fl(unsigned long flags)
{
	struct vcpu_info *vcpu;

	/* convert from IF type flag */
	flags = !(flags & X86_EFLAGS_IF);