mm.c

xen虚拟机源代码安装包

        {
            struct page_info *page = mfn_to_page(m2p_start_mfn + i);
            share_xen_page_with_privileged_guests(page, XENSHARE_readonly);
        }
    }

    for ( v  = RDWR_COMPAT_MPT_VIRT_START;
          v != RDWR_COMPAT_MPT_VIRT_END;
          v += 1 << L2_PAGETABLE_SHIFT )
    {
        l3e = l4e_to_l3e(idle_pg_table[l4_table_offset(v)])[
            l3_table_offset(v)];
        if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
            continue;
        l2e = l3e_to_l2e(l3e)[l2_table_offset(v)];
        if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) )
            continue;
        m2p_start_mfn = l2e_get_pfn(l2e);

        for ( i = 0; i < L1_PAGETABLE_ENTRIES; i++ )
        {
            struct page_info *page = mfn_to_page(m2p_start_mfn + i);
            share_xen_page_with_privileged_guests(page, XENSHARE_readonly);
        }
    }
}

long subarch_memory_op(int op, XEN_GUEST_HANDLE(void) arg)
{
    struct xen_machphys_mfn_list xmml;
    l3_pgentry_t l3e;
    l2_pgentry_t l2e;
    unsigned long v;
    xen_pfn_t mfn;
    unsigned int i;
    long rc = 0;

    switch ( op )
    {
    case XENMEM_machphys_mfn_list:
        if ( copy_from_guest(&xmml, arg, 1) )
            return -EFAULT;

        for ( i = 0, v = RDWR_MPT_VIRT_START;
              (i != xmml.max_extents) && (v != RDWR_MPT_VIRT_END);
              i++, v += 1 << 21 )
        {
            l3e = l4e_to_l3e(idle_pg_table[l4_table_offset(v)])[
                l3_table_offset(v)];
            if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
                break;
            l2e = l3e_to_l2e(l3e)[l2_table_offset(v)];
            if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) )
                break;
            mfn = l2e_get_pfn(l2e) + l1_table_offset(v);
            if ( copy_to_guest_offset(xmml.extent_start, i, &mfn, 1) )
                return -EFAULT;
        }

        xmml.nr_extents = i;
        if ( copy_to_guest(arg, &xmml, 1) )
            return -EFAULT;

        break;

    default:
        rc = -ENOSYS;
        break;
    }

    return rc;
}

long do_stack_switch(unsigned long ss, unsigned long esp)
{
    fixup_guest_stack_selector(current->domain, ss);
    current->arch.guest_context.kernel_ss = ss;
    current->arch.guest_context.kernel_sp = esp;
    return 0;
}

long do_set_segment_base(unsigned int which, unsigned long base)
{
    struct vcpu *v = current;
    long ret = 0;

    switch ( which )
    {
    case SEGBASE_FS:
        if ( wrmsr_safe(MSR_FS_BASE, base, base>>32) )
            ret = -EFAULT;
        else
            v->arch.guest_context.fs_base = base;
        break;

    case SEGBASE_GS_USER:
        if ( wrmsr_safe(MSR_SHADOW_GS_BASE, base, base>>32) )
            ret = -EFAULT;
        else
            v->arch.guest_context.gs_base_user = base;
        break;

    case SEGBASE_GS_KERNEL:
        if ( wrmsr_safe(MSR_GS_BASE, base, base>>32) )
            ret = -EFAULT;
        else
            v->arch.guest_context.gs_base_kernel = base;
        break;

    case SEGBASE_GS_USER_SEL:
        __asm__ __volatile__ (
            "     swapgs              \n"
            "1:   movl %k0,%%gs       \n"
            "    "safe_swapgs"        \n"
            ".section .fixup,\"ax\"   \n"
            "2:   xorl %k0,%k0        \n"
            "     jmp  1b             \n"
            ".previous                \n"
            ".section __ex_table,\"a\"\n"
            "    .align 8             \n"
            "    .quad 1b,2b          \n"
            ".previous                  "
            : : "r" (base&0xffff) );
        break;

    default:
        ret = -EINVAL;
        break;
    }

    return ret;
}


/* Returns TRUE if given descriptor is valid for GDT or LDT. */
int check_descriptor(const struct domain *dom, struct desc_struct *d)
{
    u32 a = d->a, b = d->b;
    u16 cs;
    unsigned int dpl;

    /* A not-present descriptor will always fault, so is safe. */
    if ( !(b & _SEGMENT_P) ) 
        goto good;

    /* Check and fix up the DPL. */
    dpl = (b >> 13) & 3;
    __fixup_guest_selector(dom, dpl);
    b = (b & ~_SEGMENT_DPL) | (dpl << 13);

    /* All code and data segments are okay. No base/limit checking. */
    if ( (b & _SEGMENT_S) )
    {
        if ( is_pv_32bit_domain(dom) )
        {
            unsigned long base, limit;

            if ( b & _SEGMENT_L )
                goto bad;

            /*
             * Older PAE Linux guests use segments which are limited to
             * 0xf6800000. Extend these to allow access to the larger read-only
             * M2P table available in 32on64 mode.
             */
            base = (b & (0xff << 24)) | ((b & 0xff) << 16) | (a >> 16);

            limit = (b & 0xf0000) | (a & 0xffff);
            limit++; /* We add one because limit is inclusive. */

            if ( (b & _SEGMENT_G) )
                limit <<= 12;

            if ( (base == 0) && (limit > HYPERVISOR_COMPAT_VIRT_START(dom)) )
            {
                a |= 0x0000ffff;
                b |= 0x000f0000;
            }
        }

        goto good;
    }

    /* Invalid type 0 is harmless. It is used for 2nd half of a call gate. */
    if ( (b & _SEGMENT_TYPE) == 0x000 )
        goto good;

    /* Everything but a call gate is discarded here. */
    if ( (b & _SEGMENT_TYPE) != 0xc00 )
        goto bad;

    /* Validate the target code selector. */
    cs = a >> 16;
    if ( !guest_gate_selector_okay(dom, cs) )
        goto bad;
    /*
     * Force DPL to zero, causing a GP fault with its error code indicating
     * the gate in use, allowing emulation. This is necessary because with
     * native guests (kernel in ring 3) call gates cannot be used directly
     * to transition from user to kernel mode (and whether a gate is used
     * to enter the kernel can only be determined when the gate is being
     * used), and with compat guests call gates cannot be used at all as
     * there are only 64-bit ones.
     * Store the original DPL in the selector's RPL field.
     */
    b &= ~_SEGMENT_DPL;
    cs = (cs & ~3) | dpl;
    a = (a & 0xffffU) | (cs << 16);

    /* Reserved bits must be zero. */
    if ( b & (is_pv_32bit_domain(dom) ? 0xe0 : 0xff) )
        goto bad;
        
 good:
    d->a = a;
    d->b = b;
    return 1;
 bad:
    return 0;
}

void domain_set_alloc_bitsize(struct domain *d)
{
    if ( !is_pv_32on64_domain(d) ||
         (MACH2PHYS_COMPAT_NR_ENTRIES(d) >= max_page) ||
         d->arch.physaddr_bitsize > 0 )
        return;
    d->arch.physaddr_bitsize =
        /* 2^n entries can be contained in guest's p2m mapping space */
        fls(MACH2PHYS_COMPAT_NR_ENTRIES(d)) - 1
        /* 2^n pages -> 2^(n+PAGE_SHIFT) bits */
        + PAGE_SHIFT;
}

unsigned int domain_clamp_alloc_bitsize(struct domain *d, unsigned int bits)
{
    if ( (d == NULL) || (d->arch.physaddr_bitsize == 0) )
        return bits;
    return min(d->arch.physaddr_bitsize, bits);
}

#include "compat/mm.c"

/*
 * Local variables:
 * mode: C
 * c-set-style: "BSD"
 * c-basic-offset: 4
 * tab-width: 4
 * indent-tabs-mode: nil
 * End:
 */