traps.c

xen虚拟机源代码安装包

#include <xen/config.h>
#include <xen/version.h>
#include <xen/init.h>
#include <xen/sched.h>
#include <xen/lib.h>
#include <xen/errno.h>
#include <xen/mm.h>
#include <xen/irq.h>
#include <xen/symbols.h>
#include <xen/console.h>
#include <xen/sched.h>
#include <xen/shutdown.h>
#include <xen/nmi.h>
#include <asm/current.h>
#include <asm/flushtlb.h>
#include <asm/msr.h>
#include <asm/page.h>
#include <asm/shared.h>
#include <asm/hvm/hvm.h>
#include <asm/hvm/support.h>
#include <public/callback.h>

asmlinkage void syscall_enter(void);
asmlinkage void sysenter_entry(void);
asmlinkage void compat_hypercall(void);
asmlinkage void int80_direct_trap(void);

static void print_xen_info(void)
{
    char taint_str[TAINT_STRING_MAX_LEN];
    char debug = 'n';

#ifndef NDEBUG
    debug = 'y';
#endif

    printk("----[ Xen-%d.%d%s  x86_64  debug=%c  %s ]----\n",
           xen_major_version(), xen_minor_version(), xen_extra_version(),
           debug, print_tainted(taint_str));
}

enum context { CTXT_hypervisor, CTXT_pv_guest, CTXT_hvm_guest };

static void _show_registers(
    const struct cpu_user_regs *regs, unsigned long crs[8],
    enum context context, const struct vcpu *v)
{
    const static char *context_names[] = {
        [CTXT_hypervisor] = "hypervisor",
        [CTXT_pv_guest]   = "pv guest",
        [CTXT_hvm_guest]  = "hvm guest"
    };

    printk("RIP:    %04x:[<%016lx>]", regs->cs, regs->rip);
    if ( context == CTXT_hypervisor )
        print_symbol(" %s", regs->rip);
    printk("\nRFLAGS: %016lx   ", regs->rflags);
    if ( (context == CTXT_pv_guest) && v && v->vcpu_info )
        printk("EM: %d   ", !!vcpu_info(v, evtchn_upcall_mask));
    printk("CONTEXT: %s\n", context_names[context]);

    printk("rax: %016lx   rbx: %016lx   rcx: %016lx\n",
           regs->rax, regs->rbx, regs->rcx);
    printk("rdx: %016lx   rsi: %016lx   rdi: %016lx\n",
           regs->rdx, regs->rsi, regs->rdi);
    printk("rbp: %016lx   rsp: %016lx   r8:  %016lx\n",
           regs->rbp, regs->rsp, regs->r8);
    printk("r9:  %016lx   r10: %016lx   r11: %016lx\n",
           regs->r9,  regs->r10, regs->r11);
    printk("r12: %016lx   r13: %016lx   r14: %016lx\n",
           regs->r12, regs->r13, regs->r14);
    printk("r15: %016lx   cr0: %016lx   cr4: %016lx\n",
           regs->r15, crs[0], crs[4]);
    printk("cr3: %016lx   cr2: %016lx\n", crs[3], crs[2]);
    printk("ds: %04x   es: %04x   fs: %04x   gs: %04x   "
           "ss: %04x   cs: %04x\n",
           regs->ds, regs->es, regs->fs,
           regs->gs, regs->ss, regs->cs);
}

void show_registers(struct cpu_user_regs *regs)
{
    struct cpu_user_regs fault_regs = *regs;
    unsigned long fault_crs[8];
    enum context context;
    struct vcpu *v = current;

    if ( is_hvm_vcpu(v) && guest_mode(regs) )
    {
        struct segment_register sreg;
        context = CTXT_hvm_guest;
        fault_crs[0] = v->arch.hvm_vcpu.guest_cr[0];
        fault_crs[2] = v->arch.hvm_vcpu.guest_cr[2];
        fault_crs[3] = v->arch.hvm_vcpu.guest_cr[3];
        fault_crs[4] = v->arch.hvm_vcpu.guest_cr[4];
        hvm_get_segment_register(v, x86_seg_cs, &sreg);
        fault_regs.cs = sreg.sel;
        hvm_get_segment_register(v, x86_seg_ds, &sreg);
        fault_regs.ds = sreg.sel;
        hvm_get_segment_register(v, x86_seg_es, &sreg);
        fault_regs.es = sreg.sel;
        hvm_get_segment_register(v, x86_seg_fs, &sreg);
        fault_regs.fs = sreg.sel;
        hvm_get_segment_register(v, x86_seg_gs, &sreg);
        fault_regs.gs = sreg.sel;
        hvm_get_segment_register(v, x86_seg_ss, &sreg);
        fault_regs.ss = sreg.sel;
    }
    else
    {
        if ( guest_mode(regs) )
        {
            context = CTXT_pv_guest;
            fault_crs[2] = arch_get_cr2(v);
        }
        else
        {
            context = CTXT_hypervisor;
            fault_crs[2] = read_cr2();
        }

        fault_crs[0] = read_cr0();
        fault_crs[3] = read_cr3();
        fault_crs[4] = read_cr4();
        fault_regs.ds = read_segment_register(ds);
        fault_regs.es = read_segment_register(es);
        fault_regs.fs = read_segment_register(fs);
        fault_regs.gs = read_segment_register(gs);
    }

    print_xen_info();
    printk("CPU:    %d\n", smp_processor_id());
    _show_registers(&fault_regs, fault_crs, context, v);

    if ( this_cpu(ler_msr) && !guest_mode(regs) )
    {
        u64 from, to;
        rdmsrl(this_cpu(ler_msr), from);
        rdmsrl(this_cpu(ler_msr) + 1, to);
        printk("ler: %016lx -> %016lx\n", from, to);
    }
}

void vcpu_show_registers(const struct vcpu *v)
{
    const struct cpu_user_regs *regs = &v->arch.guest_context.user_regs;
    unsigned long crs[8];

    /* No need to handle HVM for now. */
    if ( is_hvm_vcpu(v) )
        return;

    crs[0] = v->arch.guest_context.ctrlreg[0];
    crs[2] = arch_get_cr2(v);
    crs[3] = pagetable_get_paddr(guest_kernel_mode(v, regs) ?
                                 v->arch.guest_table :
                                 v->arch.guest_table_user);
    crs[4] = v->arch.guest_context.ctrlreg[4];

    _show_registers(regs, crs, CTXT_pv_guest, v);
}

void show_page_walk(unsigned long addr)
{
    unsigned long pfn, mfn = read_cr3() >> PAGE_SHIFT;
    l4_pgentry_t l4e, *l4t;
    l3_pgentry_t l3e, *l3t;
    l2_pgentry_t l2e, *l2t;
    l1_pgentry_t l1e, *l1t;

    printk("Pagetable walk from %016lx:\n", addr);

    l4t = mfn_to_virt(mfn);
    l4e = l4t[l4_table_offset(addr)];
    mfn = l4e_get_pfn(l4e);
    pfn = mfn_valid(mfn) ? get_gpfn_from_mfn(mfn) : INVALID_M2P_ENTRY;
    printk(" L4[0x%03lx] = %"PRIpte" %016lx\n",
           l4_table_offset(addr), l4e_get_intpte(l4e), pfn);
    if ( !(l4e_get_flags(l4e) & _PAGE_PRESENT) )
        return;

    l3t = mfn_to_virt(mfn);
    l3e = l3t[l3_table_offset(addr)];
    mfn = l3e_get_pfn(l3e);
    pfn = mfn_valid(mfn) ? get_gpfn_from_mfn(mfn) : INVALID_M2P_ENTRY;
    printk(" L3[0x%03lx] = %"PRIpte" %016lx%s\n",
           l3_table_offset(addr), l3e_get_intpte(l3e), pfn,
           (l3e_get_flags(l3e) & _PAGE_PSE) ? " (PSE)" : "");
    if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) ||
         (l3e_get_flags(l3e) & _PAGE_PSE) )
        return;

    l2t = mfn_to_virt(mfn);
    l2e = l2t[l2_table_offset(addr)];
    mfn = l2e_get_pfn(l2e);
    pfn = mfn_valid(mfn) ? get_gpfn_from_mfn(mfn) : INVALID_M2P_ENTRY;
    printk(" L2[0x%03lx] = %"PRIpte" %016lx %s\n",
           l2_table_offset(addr), l2e_get_intpte(l2e), pfn,
           (l2e_get_flags(l2e) & _PAGE_PSE) ? "(PSE)" : "");
    if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) ||
         (l2e_get_flags(l2e) & _PAGE_PSE) )
        return;

    l1t = mfn_to_virt(mfn);
    l1e = l1t[l1_table_offset(addr)];
    mfn = l1e_get_pfn(l1e);
    pfn = mfn_valid(mfn) ? get_gpfn_from_mfn(mfn) : INVALID_M2P_ENTRY;
    printk(" L1[0x%03lx] = %"PRIpte" %016lx\n",
           l1_table_offset(addr), l1e_get_intpte(l1e), pfn);
}

asmlinkage void double_fault(void);
asmlinkage void do_double_fault(struct cpu_user_regs *regs)
{
    unsigned int cpu, tr;

    asm volatile ( "str %0" : "=r" (tr) );
    cpu = ((tr >> 3) - __FIRST_TSS_ENTRY) >> 2;

    watchdog_disable();

    console_force_unlock();

    /* Find information saved during fault and dump it to the console. */
    printk("*** DOUBLE FAULT ***\n");
    print_xen_info();
    printk("CPU:    %d\nRIP:    %04x:[<%016lx>]",
           cpu, regs->cs, regs->rip);
    print_symbol(" %s", regs->rip);
    printk("\nRFLAGS: %016lx\n", regs->rflags);
    printk("rax: %016lx   rbx: %016lx   rcx: %016lx\n",
           regs->rax, regs->rbx, regs->rcx);
    printk("rdx: %016lx   rsi: %016lx   rdi: %016lx\n",
           regs->rdx, regs->rsi, regs->rdi);
    printk("rbp: %016lx   rsp: %016lx   r8:  %016lx\n",
           regs->rbp, regs->rsp, regs->r8);
    printk("r9:  %016lx   r10: %016lx   r11: %016lx\n",
           regs->r9,  regs->r10, regs->r11);
    printk("r12: %016lx   r13: %016lx   r14: %016lx\n",
           regs->r12, regs->r13, regs->r14);
    printk("r15: %016lx    cs: %016lx    ss: %016lx\n",
           regs->r15, (long)regs->cs, (long)regs->ss);
    show_stack_overflow(cpu, regs->rsp);

    panic("DOUBLE FAULT -- system shutdown\n");
}

void toggle_guest_mode(struct vcpu *v)
{
    if ( is_pv_32bit_vcpu(v) )
        return;
    v->arch.flags ^= TF_kernel_mode;
    asm volatile ( "swapgs" );
    update_cr3(v);
#ifdef USER_MAPPINGS_ARE_GLOBAL
    /* Don't flush user global mappings from the TLB. Don't tick TLB clock. */
    asm volatile ( "mov %0, %%cr3" : : "r" (v->arch.cr3) : "memory" );
#else
    write_ptbase(v);
#endif
}

unsigned long do_iret(void)
{
    struct cpu_user_regs *regs = guest_cpu_user_regs();
    struct iret_context iret_saved;
    struct vcpu *v = current;

    if ( unlikely(copy_from_user(&iret_saved, (void *)regs->rsp,
                                 sizeof(iret_saved))) )
    {
        gdprintk(XENLOG_ERR, "Fault while reading IRET context from "
                "guest stack\n");
        goto exit_and_crash;
    }

    /* Returning to user mode? */
    if ( (iret_saved.cs & 3) == 3 )
    {
        if ( unlikely(pagetable_is_null(v->arch.guest_table_user)) )
        {
            gdprintk(XENLOG_ERR, "Guest switching to user mode with no "
                    "user page tables\n");
            goto exit_and_crash;
        }
        toggle_guest_mode(v);
    }

    regs->rip    = iret_saved.rip;
    regs->cs     = iret_saved.cs | 3; /* force guest privilege */
    regs->rflags = (iret_saved.rflags & ~(EF_IOPL|EF_VM)) | EF_IE;
    regs->rsp    = iret_saved.rsp;
    regs->ss     = iret_saved.ss | 3; /* force guest privilege */

    if ( !(iret_saved.flags & VGCF_in_syscall) )
    {
        regs->entry_vector = 0;
        regs->r11 = iret_saved.r11;
        regs->rcx = iret_saved.rcx;
    }

    /* Restore affinity.  */
    if ((v->trap_priority >= VCPU_TRAP_NMI)
       && !cpus_equal(v->cpu_affinity_tmp, v->cpu_affinity))
        vcpu_set_affinity(v, &v->cpu_affinity_tmp);

    /* Restore previous trap priority */
    v->trap_priority = v->old_trap_priority;

    /* Restore upcall mask from supplied EFLAGS.IF. */
    vcpu_info(v, evtchn_upcall_mask) = !(iret_saved.rflags & EF_IE);

    /* Saved %rax gets written back to regs->rax in entry.S. */
    return iret_saved.rax;

 exit_and_crash:
    gdprintk(XENLOG_ERR, "Fatal error\n");