enlighten.c

linux 内核源代码

/*
 * 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 <[e-mail]>, 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 * out of date, but it will never be set early).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);

	/* There's a one instruction preempt window here.  We need to
	   make sure we're don't switch CPUs between getting the vcpu
	   pointer and updating the mask. */
	preempt_disable();
	vcpu = x86_read_percpu(xen_vcpu);
	vcpu->evtchn_upcall_mask = flags;
	preempt_enable_no_resched();

	/* Doesn't matter if we get preempted here, because any
	   pending event will get dealt with anyway. */

	if (flags == 0) {
		preempt_check_resched();
		barrier(); /* unmask then check (avoid races) */
		if (unlikely(vcpu->evtchn_upcall_pending))
			force_evtchn_callback();
	}
}

static void xen_irq_disable(void)
{
	/* There's a one instruction preempt window here.  We need to
	   make sure we're don't switch CPUs between getting the vcpu
	   pointer and updating the mask. */
	preempt_disable();
	x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1;
	preempt_enable_no_resched();
}

static void xen_irq_enable(void)
{
	struct vcpu_info *vcpu;

	/* There's a one instruction preempt window here.  We need to
	   make sure we're don't switch CPUs between getting the vcpu
	   pointer and updating the mask. */
	preempt_disable();
	vcpu = x86_read_percpu(xen_vcpu);
	vcpu->evtchn_upcall_mask = 0;
	preempt_enable_no_resched();

	/* Doesn't matter if we get preempted here, because any
	   pending event will get dealt with anyway. */

	barrier(); /* unmask then check (avoid races) */
	if (unlikely(vcpu->evtchn_upcall_pending))
		force_evtchn_callback();
}

static void xen_safe_halt(void)
{
	/* Blocking includes an implicit local_irq_enable(). */
	if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0)
		BUG();
}

static void xen_halt(void)
{
	if (irqs_disabled())
		HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
	else
		xen_safe_halt();
}

static void xen_leave_lazy(void)
{
	paravirt_leave_lazy(paravirt_get_lazy_mode());
	xen_mc_flush();
}

static unsigned long xen_store_tr(void)
{
	return 0;
}

static void xen_set_ldt(const void *addr, unsigned entries)
{
	unsigned long linear_addr = (unsigned long)addr;
	struct mmuext_op *op;
	struct multicall_space mcs = xen_mc_entry(sizeof(*op));

	op = mcs.args;
	op->cmd = MMUEXT_SET_LDT;
	if (linear_addr) {
		/* ldt my be vmalloced, use arbitrary_virt_to_machine */
		xmaddr_t maddr;
		maddr = arbitrary_virt_to_machine((unsigned long)addr);
		linear_addr = (unsigned long)maddr.maddr;
	}
	op->arg1.linear_addr = linear_addr;
	op->arg2.nr_ents = entries;

	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static void xen_load_gdt(const struct Xgt_desc_struct *dtr)
{
	unsigned long *frames;
	unsigned long va = dtr->address;
	unsigned int size = dtr->size + 1;
	unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
	int f;
	struct multicall_space mcs;

	/* A GDT can be up to 64k in size, which corresponds to 8192
	   8-byte entries, or 16 4k pages.. */

	BUG_ON(size > 65536);
	BUG_ON(va & ~PAGE_MASK);

	mcs = xen_mc_entry(sizeof(*frames) * pages);
	frames = mcs.args;

	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
		frames[f] = virt_to_mfn(va);
		make_lowmem_page_readonly((void *)va);
	}

	MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct));

	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static void load_TLS_descriptor(struct thread_struct *t,
				unsigned int cpu, unsigned int i)
{
	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
	xmaddr_t maddr = virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
	struct multicall_space mc = __xen_mc_entry(0);

	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
}

static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
	xen_mc_batch();

	load_TLS_descriptor(t, cpu, 0);
	load_TLS_descriptor(t, cpu, 1);
	load_TLS_descriptor(t, cpu, 2);

	xen_mc_issue(PARAVIRT_LAZY_CPU);

	/*
	 * XXX sleazy hack: If we're being called in a lazy-cpu zone,
	 * it means we're in a context switch, and %gs has just been
	 * saved.  This means we can zero it out to prevent faults on
	 * exit from the hypervisor if the next process has no %gs.
	 * Either way, it has been saved, and the new value will get
	 * loaded properly.  This will go away as soon as Xen has been
	 * modified to not save/restore %gs for normal hypercalls.
	 */
	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
		loadsegment(gs, 0);
}

static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
				u32 low, u32 high)
{
	unsigned long lp = (unsigned long)&dt[entrynum];
	xmaddr_t mach_lp = virt_to_machine(lp);
	u64 entry = (u64)high << 32 | low;

	preempt_disable();

	xen_mc_flush();
	if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry))
		BUG();

	preempt_enable();
}

static int cvt_gate_to_trap(int vector, u32 low, u32 high,
			    struct trap_info *info)
{
	u8 type, dpl;

	type = (high >> 8) & 0x1f;
	dpl = (high >> 13) & 3;

	if (type != 0xf && type != 0xe)
		return 0;

	info->vector = vector;
	info->address = (high & 0xffff0000) | (low & 0x0000ffff);
	info->cs = low >> 16;
	info->flags = dpl;
	/* interrupt gates clear IF */
	if (type == 0xe)
		info->flags |= 4;

	return 1;
}

/* Locations of each CPU's IDT */
static DEFINE_PER_CPU(struct Xgt_desc_struct, idt_desc);

/* Set an IDT entry.  If the entry is part of the current IDT, then
   also update Xen. */
static void xen_write_idt_entry(struct desc_struct *dt, int entrynum,
				u32 low, u32 high)
{
	unsigned long p = (unsigned long)&dt[entrynum];
	unsigned long start, end;

	preempt_disable();

	start = __get_cpu_var(idt_desc).address;
	end = start + __get_cpu_var(idt_desc).size + 1;

	xen_mc_flush();

	write_dt_entry(dt, entrynum, low, high);

	if (p >= start && (p + 8) <= end) {
		struct trap_info info[2];

		info[1].address = 0;

		if (cvt_gate_to_trap(entrynum, low, high, &info[0]))
			if (HYPERVISOR_set_trap_table(info))
				BUG();
	}

	preempt_enable();
}

static void xen_convert_trap_info(const struct Xgt_desc_struct *desc,
				  struct trap_info *traps)
{
	unsigned in, out, count;

	count = (desc->size+1) / 8;
	BUG_ON(count > 256);

	for (in = out = 0; in < count; in++) {
		const u32 *entry = (u32 *)(desc->address + in * 8);

		if (cvt_gate_to_trap(in, entry[0], entry[1], &traps[out]))
			out++;
	}
	traps[out].address = 0;
}

void xen_copy_trap_info(struct trap_info *traps)
{
	const struct Xgt_desc_struct *desc = &__get_cpu_var(idt_desc);

	xen_convert_trap_info(desc, traps);
}

/* Load a new IDT into Xen.  In principle this can be per-CPU, so we
   hold a spinlock to protect the static traps[] array (static because
   it avoids allocation, and saves stack space). */
static void xen_load_idt(const struct Xgt_desc_struct *desc)
{
	static DEFINE_SPINLOCK(lock);
	static struct trap_info traps[257];

	spin_lock(&lock);

	__get_cpu_var(idt_desc) = *desc;

	xen_convert_trap_info(desc, traps);

	xen_mc_flush();
	if (HYPERVISOR_set_trap_table(traps))
		BUG();

	spin_unlock(&lock);
}

/* Write a GDT descriptor entry.  Ignore LDT descriptors, since
   they're handled differently. */
static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
				u32 low, u32 high)
{
	preempt_disable();

	switch ((high >> 8) & 0xff) {
	case DESCTYPE_LDT:
	case DESCTYPE_TSS:
		/* ignore */
		break;

	default: {
		xmaddr_t maddr = virt_to_machine(&dt[entry]);
		u64 desc = (u64)high << 32 | low;

		xen_mc_flush();
		if (HYPERVISOR_update_descriptor(maddr.maddr, desc))
			BUG();
	}

	}

	preempt_enable();
}

static void xen_load_esp0(struct tss_struct *tss,
			  struct thread_struct *thread)
{
	struct multicall_space mcs = xen_mc_entry(0);
	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->esp0);
	xen_mc_issue(PARAVIRT_LAZY_CPU);
}

static void xen_set_iopl_mask(unsigned mask)
{
	struct physdev_set_iopl set_iopl;

	/* Force the change at ring 0. */
	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
}

static void xen_io_delay(void)
{
}

#ifdef CONFIG_X86_LOCAL_APIC
static unsigned long xen_apic_read(unsigned long reg)
{
	return 0;
}

static void xen_apic_write(unsigned long reg, unsigned long val)
{
	/* Warn to see if there's any stray references */
	WARN_ON(1);
}
#endif

static void xen_flush_tlb(void)
{
	struct mmuext_op *op;
	struct multicall_space mcs = xen_mc_entry(sizeof(*op));

	op = mcs.args;
	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);
}

static void xen_flush_tlb_single(unsigned long addr)
{
	struct mmuext_op *op;
	struct multicall_space mcs = xen_mc_entry(sizeof(*op));

	op = mcs.args;
	op->cmd = MMUEXT_INVLPG_LOCAL;
	op->arg1.linear_addr = addr & PAGE_MASK;
	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);
}

static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
				 unsigned long va)
{
	struct {
		struct mmuext_op op;
		cpumask_t mask;
	} *args;
	cpumask_t cpumask = *cpus;
	struct multicall_space mcs;

	/*
	 * A couple of (to be removed) sanity checks:
	 *
	 * - current CPU must not be in mask
	 * - mask must exist :)
	 */
	BUG_ON(cpus_empty(cpumask));
	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
	BUG_ON(!mm);

	/* If a CPU which we ran on has gone down, OK. */
	cpus_and(cpumask, cpumask, cpu_online_map);
	if (cpus_empty(cpumask))
		return;

	mcs = xen_mc_entry(sizeof(*args));
	args = mcs.args;
	args->mask = cpumask;
	args->op.arg2.vcpumask = &args->mask;

	if (va == TLB_FLUSH_ALL) {
		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
	} else {
		args->op.cmd = MMUEXT_INVLPG_MULTI;
		args->op.arg1.linear_addr = va;
	}

	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);