core.c

来自「linux 内核源代码」· C语言 代码 · 共 582 行 · 第 1/2 页

/*
 * Copyright (C) 2006, Rusty Russell <[e-mail]> IBM Corporation.
 * Copyright (C) 2007, Jes Sorensen <[e-mail]> SGI.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 * NON INFRINGEMENT.  See the GNU General Public License for more
 * details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
#include <linux/kernel.h>
#include <linux/start_kernel.h>
#include <linux/string.h>
#include <linux/console.h>
#include <linux/screen_info.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
#include <linux/cpu.h>
#include <linux/lguest.h>
#include <linux/lguest_launcher.h>
#include <asm/paravirt.h>
#include <asm/param.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/setup.h>
#include <asm/lguest.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
#include "../lg.h"

static int cpu_had_pge;

static struct {
	unsigned long offset;
	unsigned short segment;
} lguest_entry;

/* Offset from where switcher.S was compiled to where we've copied it */
static unsigned long switcher_offset(void)
{
	return SWITCHER_ADDR - (unsigned long)start_switcher_text;
}

/* This cpu's struct lguest_pages. */
static struct lguest_pages *lguest_pages(unsigned int cpu)
{
	return &(((struct lguest_pages *)
		  (SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]);
}

static DEFINE_PER_CPU(struct lguest *, last_guest);

/*S:010
 * We approach the Switcher.
 *
 * Remember that each CPU has two pages which are visible to the Guest when it
 * runs on that CPU.  This has to contain the state for that Guest: we copy the
 * state in just before we run the Guest.
 *
 * Each Guest has "changed" flags which indicate what has changed in the Guest
 * since it last ran.  We saw this set in interrupts_and_traps.c and
 * segments.c.
 */
static void copy_in_guest_info(struct lguest *lg, struct lguest_pages *pages)
{
	/* Copying all this data can be quite expensive.  We usually run the
	 * same Guest we ran last time (and that Guest hasn't run anywhere else
	 * meanwhile).  If that's not the case, we pretend everything in the
	 * Guest has changed. */
	if (__get_cpu_var(last_guest) != lg || lg->last_pages != pages) {
		__get_cpu_var(last_guest) = lg;
		lg->last_pages = pages;
		lg->changed = CHANGED_ALL;
	}

	/* These copies are pretty cheap, so we do them unconditionally: */
	/* Save the current Host top-level page directory. */
	pages->state.host_cr3 = __pa(current->mm->pgd);
	/* Set up the Guest's page tables to see this CPU's pages (and no
	 * other CPU's pages). */
	map_switcher_in_guest(lg, pages);
	/* Set up the two "TSS" members which tell the CPU what stack to use
	 * for traps which do directly into the Guest (ie. traps at privilege
	 * level 1). */
	pages->state.guest_tss.esp1 = lg->esp1;
	pages->state.guest_tss.ss1 = lg->ss1;

	/* Copy direct-to-Guest trap entries. */
	if (lg->changed & CHANGED_IDT)
		copy_traps(lg, pages->state.guest_idt, default_idt_entries);

	/* Copy all GDT entries which the Guest can change. */
	if (lg->changed & CHANGED_GDT)
		copy_gdt(lg, pages->state.guest_gdt);
	/* If only the TLS entries have changed, copy them. */
	else if (lg->changed & CHANGED_GDT_TLS)
		copy_gdt_tls(lg, pages->state.guest_gdt);

	/* Mark the Guest as unchanged for next time. */
	lg->changed = 0;
}

/* Finally: the code to actually call into the Switcher to run the Guest. */
static void run_guest_once(struct lguest *lg, struct lguest_pages *pages)
{
	/* This is a dummy value we need for GCC's sake. */
	unsigned int clobber;

	/* Copy the guest-specific information into this CPU's "struct
	 * lguest_pages". */
	copy_in_guest_info(lg, pages);

	/* Set the trap number to 256 (impossible value).  If we fault while
	 * switching to the Guest (bad segment registers or bug), this will
	 * cause us to abort the Guest. */
	lg->regs->trapnum = 256;

	/* Now: we push the "eflags" register on the stack, then do an "lcall".
	 * This is how we change from using the kernel code segment to using
	 * the dedicated lguest code segment, as well as jumping into the
	 * Switcher.
	 *
	 * The lcall also pushes the old code segment (KERNEL_CS) onto the
	 * stack, then the address of this call.  This stack layout happens to
	 * exactly match the stack layout created by an interrupt... */
	asm volatile("pushf; lcall *lguest_entry"
		     /* This is how we tell GCC that %eax ("a") and %ebx ("b")
		      * are changed by this routine.  The "=" means output. */
		     : "=a"(clobber), "=b"(clobber)
		     /* %eax contains the pages pointer.  ("0" refers to the
		      * 0-th argument above, ie "a").  %ebx contains the
		      * physical address of the Guest's top-level page
		      * directory. */
		     : "0"(pages), "1"(__pa(lg->pgdirs[lg->pgdidx].pgdir))
		     /* We tell gcc that all these registers could change,
		      * which means we don't have to save and restore them in
		      * the Switcher. */
		     : "memory", "%edx", "%ecx", "%edi", "%esi");
}
/*:*/

/*M:002 There are hooks in the scheduler which we can register to tell when we
 * get kicked off the CPU (preempt_notifier_register()).  This would allow us
 * to lazily disable SYSENTER which would regain some performance, and should
 * also simplify copy_in_guest_info().  Note that we'd still need to restore
 * things when we exit to Launcher userspace, but that's fairly easy.
 *
 * The hooks were designed for KVM, but we can also put them to good use. :*/

/*H:040 This is the i386-specific code to setup and run the Guest.  Interrupts
 * are disabled: we own the CPU. */
void lguest_arch_run_guest(struct lguest *lg)
{
	/* Remember the awfully-named TS bit?  If the Guest has asked to set it
	 * we set it now, so we can trap and pass that trap to the Guest if it
	 * uses the FPU. */
	if (lg->ts)
		lguest_set_ts();

	/* SYSENTER is an optimized way of doing system calls.  We can't allow
	 * it because it always jumps to privilege level 0.  A normal Guest
	 * won't try it because we don't advertise it in CPUID, but a malicious
	 * Guest (or malicious Guest userspace program) could, so we tell the
	 * CPU to disable it before running the Guest. */
	if (boot_cpu_has(X86_FEATURE_SEP))
		wrmsr(MSR_IA32_SYSENTER_CS, 0, 0);

	/* Now we actually run the Guest.  It will return when something
	 * interesting happens, and we can examine its registers to see what it
	 * was doing. */
	run_guest_once(lg, lguest_pages(raw_smp_processor_id()));

	/* Note that the "regs" pointer contains two extra entries which are
	 * not really registers: a trap number which says what interrupt or
	 * trap made the switcher code come back, and an error code which some
	 * traps set.  */

	/* If the Guest page faulted, then the cr2 register will tell us the
	 * bad virtual address.  We have to grab this now, because once we
	 * re-enable interrupts an interrupt could fault and thus overwrite
	 * cr2, or we could even move off to a different CPU. */
	if (lg->regs->trapnum == 14)
		lg->arch.last_pagefault = read_cr2();
	/* Similarly, if we took a trap because the Guest used the FPU,
	 * we have to restore the FPU it expects to see. */
	else if (lg->regs->trapnum == 7)
		math_state_restore();

	/* Restore SYSENTER if it's supposed to be on. */
	if (boot_cpu_has(X86_FEATURE_SEP))
		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
}

/*H:130 Now we've examined the hypercall code; our Guest can make requests.
 * Our Guest is usually so well behaved; it never tries to do things it isn't
 * allowed to, and uses hypercalls instead.  Unfortunately, Linux's paravirtual
 * infrastructure isn't quite complete, because it doesn't contain replacements
 * for the Intel I/O instructions.  As a result, the Guest sometimes fumbles
 * across one during the boot process as it probes for various things which are
 * usually attached to a PC.
 *
 * When the Guest uses one of these instructions, we get a trap (General
 * Protection Fault) and come here.  We see if it's one of those troublesome
 * instructions and skip over it.  We return true if we did. */
static int emulate_insn(struct lguest *lg)
{
	u8 insn;
	unsigned int insnlen = 0, in = 0, shift = 0;
	/* The eip contains the *virtual* address of the Guest's instruction:
	 * guest_pa just subtracts the Guest's page_offset. */
	unsigned long physaddr = guest_pa(lg, lg->regs->eip);

	/* This must be the Guest kernel trying to do something, not userspace!
	 * The bottom two bits of the CS segment register are the privilege
	 * level. */
	if ((lg->regs->cs & 3) != GUEST_PL)
		return 0;

	/* Decoding x86 instructions is icky. */
	insn = lgread(lg, physaddr, u8);

	/* 0x66 is an "operand prefix".  It means it's using the upper 16 bits
	   of the eax register. */
	if (insn == 0x66) {
		shift = 16;
		/* The instruction is 1 byte so far, read the next byte. */
		insnlen = 1;
		insn = lgread(lg, physaddr + insnlen, u8);
	}

	/* We can ignore the lower bit for the moment and decode the 4 opcodes
	 * we need to emulate. */
	switch (insn & 0xFE) {
	case 0xE4: /* in     <next byte>,%al */
		insnlen += 2;
		in = 1;
		break;
	case 0xEC: /* in     (%dx),%al */
		insnlen += 1;
		in = 1;
		break;
	case 0xE6: /* out    %al,<next byte> */
		insnlen += 2;
		break;
	case 0xEE: /* out    %al,(%dx) */
		insnlen += 1;
		break;
	default:
		/* OK, we don't know what this is, can't emulate. */
		return 0;
	}

	/* If it was an "IN" instruction, they expect the result to be read
	 * into %eax, so we change %eax.  We always return all-ones, which
	 * traditionally means "there's nothing there". */
	if (in) {
		/* Lower bit tells is whether it's a 16 or 32 bit access */
		if (insn & 0x1)
			lg->regs->eax = 0xFFFFFFFF;
		else
			lg->regs->eax |= (0xFFFF << shift);
	}
	/* Finally, we've "done" the instruction, so move past it. */
	lg->regs->eip += insnlen;
	/* Success! */
	return 1;
}

/*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */
void lguest_arch_handle_trap(struct lguest *lg)
{
	switch (lg->regs->trapnum) {
	case 13: /* We've intercepted a General Protection Fault. */
		/* Check if this was one of those annoying IN or OUT
		 * instructions which we need to emulate.  If so, we just go
		 * back into the Guest after we've done it. */
		if (lg->regs->errcode == 0) {
			if (emulate_insn(lg))
				return;