Skip to content
Snippets Groups Projects
enlighten_pv.c 36.8 KiB
Newer Older
/*
 * 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/memblock.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/highmem.h>
#include <linux/console.h>
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/edd.h>
#include <linux/frame.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/stackprotector.h>
#include <asm/hypervisor.h>
#include <asm/mach_traps.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 void __init xen_banner(void)
{
	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
	struct xen_extraversion extra;
	HYPERVISOR_xen_version(XENVER_extraversion, &extra);

	pr_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)" : "");

#ifdef CONFIG_X86_32
	pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"
		"Support for running as 32-bit PV-guest under Xen will soon be removed\n"
		"from the Linux kernel!\n"
		"Please use either a 64-bit kernel or switch to HVM or PVH mode!\n"
		"WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n");
#endif

static void __init xen_pv_init_platform(void)
{
	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();
}

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
}

/* Check if running on Xen version (major, minor) or later */
bool
xen_running_on_version_or_later(unsigned int major, unsigned int minor)
{
	unsigned int version;

	if (!xen_domain())
		return false;

	version = HYPERVISOR_xen_version(XENVER_version, NULL);
	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
		((version >> 16) > major))
		return true;
	return false;
}

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;
}
STACK_FRAME_NON_STANDARD(xen_cpuid); /* XEN_EMULATE_PREFIX */

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 backwards compatibility; so we will find out directly
	 * from the hardware and hypercall.
	 */
	if (!xen_initial_domain())
		return false;

	/*
	 * When running under platform earlier than Xen4.2, do not expose
	 * mwait, to avoid the risk of loading native acpi pad driver
	 */
	if (!xen_running_on_version_or_later(4, 2))
		return false;

	ax = 1;
	cx = 0;

	native_cpuid(&ax, &bx, &cx, &dx);

	mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
		     (1 << (X86_FEATURE_MWAIT % 32));

	if ((cx & mwait_mask) != mwait_mask)
		return false;

	/* We need to emulate the MWAIT_LEAF and for that we need both
	 * ecx and edx. The hypercall provides only partial information.
	 */

	ax = CPUID_MWAIT_LEAF;
	bx = 0;
	cx = 0;
	dx = 0;

	native_cpuid(&ax, &bx, &cx, &dx);

	/* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
	 * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
	 */
	buf[0] = ACPI_PDC_REVISION_ID;
	buf[1] = 1;
	buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);

	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);

	if ((HYPERVISOR_platform_op(&op) == 0) &&
	    (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
		cpuid_leaf5_ecx_val = cx;
		cpuid_leaf5_edx_val = dx;
	}
	return true;
#else
	return false;
#endif
}

static bool __init xen_check_xsave(void)
{
	unsigned int cx, xsave_mask;
	cx = cpuid_ecx(1);

	xsave_mask = (1 << (X86_FEATURE_XSAVE % 32)) |
		     (1 << (X86_FEATURE_OSXSAVE % 32));

	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
	return (cx & xsave_mask) == xsave_mask;
static void __init xen_init_capabilities(void)
{
	setup_force_cpu_cap(X86_FEATURE_XENPV);
	setup_clear_cpu_cap(X86_FEATURE_DCA);
	setup_clear_cpu_cap(X86_FEATURE_APERFMPERF);
	setup_clear_cpu_cap(X86_FEATURE_MTRR);
	setup_clear_cpu_cap(X86_FEATURE_ACC);
	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
	setup_clear_cpu_cap(X86_FEATURE_SME);
	/*
	 * Xen PV would need some work to support PCID: CR3 handling as well
	 * as xen_flush_tlb_others() would need updating.
	 */
	setup_clear_cpu_cap(X86_FEATURE_PCID);

	if (!xen_initial_domain())
		setup_clear_cpu_cap(X86_FEATURE_ACPI);

	if (xen_check_mwait())
		setup_force_cpu_cap(X86_FEATURE_MWAIT);
	else
		setup_clear_cpu_cap(X86_FEATURE_MWAIT);
	if (!xen_check_xsave()) {
Loading
Loading full blame...