分类: LINUX
2013-02-25 20:46:41
原文地址:linux 半虚拟化接口(paravirt_ops) 作者:micklongen
摘自:linux 2.6.23.13\arch\i386\kernel
struct paravirt_ops paravirt_ops = {
.name = "bare hardware",
.paravirt_enabled = 0,
.kernel_rpl = 0,
.shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
.patch = native_patch,
.banner = default_banner,
.arch_setup = paravirt_nop,
.memory_setup = machine_specific_memory_setup,
.get_wallclock = native_get_wallclock,
.set_wallclock = native_set_wallclock,
.time_init = hpet_time_init,
.init_IRQ = native_init_IRQ,
.cpuid = native_cpuid,
.get_debugreg = native_get_debugreg,
.set_debugreg = native_set_debugreg,
.clts = native_clts,
.read_cr0 = native_read_cr0,
.write_cr0 = native_write_cr0,
.read_cr2 = native_read_cr2,
.write_cr2 = native_write_cr2,
.read_cr3 = native_read_cr3,
.write_cr3 = native_write_cr3,
.read_cr4 = native_read_cr4,
.read_cr4_safe = native_read_cr4_safe,
.write_cr4 = native_write_cr4,
.save_fl = native_save_fl,
.restore_fl = native_restore_fl,
.irq_disable = native_irq_disable,
.irq_enable = native_irq_enable,
.safe_halt = native_safe_halt,
.halt = native_halt,
.wbinvd = native_wbinvd,
.read_msr = native_read_msr_safe,
.write_msr = native_write_msr_safe,
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
.sched_clock = native_sched_clock,
.get_cpu_khz = native_calculate_cpu_khz,
.load_tr_desc = native_load_tr_desc,
.set_ldt = native_set_ldt,
.load_gdt = native_load_gdt,
.load_idt = native_load_idt,
.store_gdt = native_store_gdt,
.store_idt = native_store_idt,
.store_tr = native_store_tr,
.load_tls = native_load_tls,
.write_ldt_entry = write_dt_entry,
.write_gdt_entry = write_dt_entry,
.write_idt_entry = write_dt_entry,
.load_esp0 = native_load_esp0,
.set_iopl_mask = native_set_iopl_mask,
.io_delay = native_io_delay,
#ifdef CONFIG_X86_LOCAL_APIC
.apic_write = native_apic_write,
.apic_write_atomic = native_apic_write_atomic,
.apic_read = native_apic_read,
.setup_boot_clock = setup_boot_APIC_clock,
.setup_secondary_clock = setup_secondary_APIC_clock,
.startup_ipi_hook = paravirt_nop,
#endif
.set_lazy_mode = paravirt_nop,
.pagetable_setup_start = native_pagetable_setup_start,
.pagetable_setup_done = native_pagetable_setup_done,
.flush_tlb_user = native_flush_tlb,
.flush_tlb_kernel = native_flush_tlb_global,
.flush_tlb_single = native_flush_tlb_single,
.flush_tlb_others = native_flush_tlb_others,
.alloc_pt = paravirt_nop,
.alloc_pd = paravirt_nop,
.alloc_pd_clone = paravirt_nop,
.release_pt = paravirt_nop,
.release_pd = paravirt_nop,
.set_pte = native_set_pte,
.set_pte_at = native_set_pte_at,
.set_pmd = native_set_pmd,
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
#ifdef CONFIG_HIGHPTE
.kmap_atomic_pte = kmap_atomic,
#endif
#ifdef CONFIG_X86_PAE
.set_pte_atomic = native_set_pte_atomic,
.set_pte_present = native_set_pte_present,
.set_pud = native_set_pud,
.pte_clear = native_pte_clear,
.pmd_clear = native_pmd_clear,
.pmd_val = native_pmd_val,
.make_pmd = native_make_pmd,
#endif
.pte_val = native_pte_val,
.pgd_val = native_pgd_val,
.make_pte = native_make_pte,
.make_pgd = native_make_pgd,
.irq_enable_sysexit = native_irq_enable_sysexit,
.iret = native_iret,
.dup_mmap = paravirt_nop,
.exit_mmap = paravirt_nop,
.activate_mm = paravirt_nop,
};
摘自:lguest
/*G:030 Once we get to lguest_init(), we know we're a Guest. The paravirt_ops
* structure in the kernel provides a single point for (almost) every routine
* we have to override to avoid privileged instructions. */
__init void lguest_init(void *boot)
{
/* Copy boot parameters first: the Launcher put the physical location
* in %esi, and head.S converted that to a virtual address and handed
* it to us. We use "__memcpy" because "memcpy" sometimes tries to do
* tricky things to go faster, and we're not ready for that. */
__memcpy(&boot_params, boot, PARAM_SIZE);
/* The boot parameters also tell us where the command-line is: save
* that, too. */
__memcpy(boot_command_line, __va(boot_params.hdr.cmd_line_ptr),
COMMAND_LINE_SIZE);
/* We're under lguest, paravirt is enabled, and we're running at
* privilege level 1, not 0 as normal. */
paravirt_ops.name = "lguest";
paravirt_ops.paravirt_enabled = 1;
paravirt_ops.kernel_rpl = 1;
/* We set up all the lguest overrides for sensitive operations. These
* are detailed with the operations themselves. */
paravirt_ops.save_fl = save_fl;
paravirt_ops.restore_fl = restore_fl;
paravirt_ops.irq_disable = irq_disable;
paravirt_ops.irq_enable = irq_enable;
paravirt_ops.load_gdt = lguest_load_gdt;
paravirt_ops.memory_setup = lguest_memory_setup;
paravirt_ops.cpuid = lguest_cpuid;
paravirt_ops.write_cr3 = lguest_write_cr3;
paravirt_ops.flush_tlb_user = lguest_flush_tlb_user;
paravirt_ops.flush_tlb_single = lguest_flush_tlb_single;
paravirt_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
paravirt_ops.set_pte = lguest_set_pte;
paravirt_ops.set_pte_at = lguest_set_pte_at;
paravirt_ops.set_pmd = lguest_set_pmd;
#ifdef CONFIG_X86_LOCAL_APIC
paravirt_ops.apic_write = lguest_apic_write;
paravirt_ops.apic_write_atomic = lguest_apic_write;
paravirt_ops.apic_read = lguest_apic_read;
#endif
paravirt_ops.load_idt = lguest_load_idt;
paravirt_ops.iret = lguest_iret;
paravirt_ops.load_esp0 = lguest_load_esp0;
paravirt_ops.load_tr_desc = lguest_load_tr_desc;
paravirt_ops.set_ldt = lguest_set_ldt;
paravirt_ops.load_tls = lguest_load_tls;
paravirt_ops.set_debugreg = lguest_set_debugreg;
paravirt_ops.clts = lguest_clts;
paravirt_ops.read_cr0 = lguest_read_cr0;
paravirt_ops.write_cr0 = lguest_write_cr0;
paravirt_ops.init_IRQ = lguest_init_IRQ;
paravirt_ops.read_cr2 = lguest_read_cr2;
paravirt_ops.read_cr3 = lguest_read_cr3;
paravirt_ops.read_cr4 = lguest_read_cr4;
paravirt_ops.write_cr4 = lguest_write_cr4;
paravirt_ops.write_gdt_entry = lguest_write_gdt_entry;
paravirt_ops.write_idt_entry = lguest_write_idt_entry;
paravirt_ops.patch = lguest_patch;
paravirt_ops.safe_halt = lguest_safe_halt;
paravirt_ops.get_wallclock = lguest_get_wallclock;
paravirt_ops.time_init = lguest_time_init;
paravirt_ops.set_lazy_mode = lguest_lazy_mode;
paravirt_ops.wbinvd = lguest_wbinvd;
/* Now is a good time to look at the implementations of these functions
* before returning to the rest of lguest_init(). */
/*G:070 Now we've seen all the paravirt_ops, we return to
* lguest_init() where the rest of the fairly chaotic boot setup
* occurs.
*
* The Host expects our first hypercall to tell it where our "struct
* lguest_data" is, so we do that first. */
hcall(LHCALL_LGUEST_INIT, __pa(&lguest_data), 0, 0);
/* The native boot code sets up initial page tables immediately after
* the kernel itself, and sets init_pg_tables_end so they're not
* clobbered. The Launcher places our initial pagetables somewhere at
* the top of our physical memory, so we don't need extra space: set
* init_pg_tables_end to the end of the kernel. */
init_pg_tables_end = __pa(pg0);
/* Load the %fs segment register (the per-cpu segment register) with
* the normal data segment to get through booting. */
asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory");
/* Clear the part of the kernel data which is expected to be zero.
* Normally it will be anyway, but if we're loading from a bzImage with
* CONFIG_RELOCATALE=y, the relocations will be sitting here. */
memset(__bss_start, 0, __bss_stop - __bss_start);
/* The Host uses the top of the Guest's virtual address space for the
* Host<->Guest Switcher, and it tells us how much it needs in
* lguest_data.reserve_mem, set up on the LGUEST_INIT hypercall. */
reserve_top_address(lguest_data.reserve_mem);
/* If we don't initialize the lock dependency checker now, it crashes
* paravirt_disable_iospace. */
lockdep_init();
/* The IDE code spends about 3 seconds probing for disks: if we reserve
* all the I/O ports up front it can't get them and so doesn't probe.
* Other device drivers are similar (but less severe). This cuts the
* kernel boot time on my machine from 4.1 seconds to 0.45 seconds. */
paravirt_disable_iospace();
/* This is messy CPU setup stuff which the native boot code does before
* start_kernel, so we have to do, too: */
cpu_detect(&new_cpu_data);
/* head.S usually sets up the first capability word, so do it here. */
new_cpu_data.x86_capability[0] = cpuid_edx(1);
/* Math is always hard! */
new_cpu_data.hard_math = 1;
#ifdef CONFIG_X86_MCE
mce_disabled = 1;
#endif
#ifdef CONFIG_ACPI
acpi_disabled = 1;
acpi_ht = 0;
#endif
/* We set the perferred console to "hvc". This is the "hypervisor
* virtual console" driver written by the PowerPC people, which we also
* adapted for lguest's use. */
add_preferred_console("hvc", 0, NULL);
/* Last of all, we set the power management poweroff hook to point to
* the Guest routine to power off. */
pm_power_off = lguest_power_off;
/* Now we're set up, call start_kernel() in init/main.c and we proceed
* to boot as normal. It never returns. */
start_kernel();
}
/*
* This marks the end of stage II of our journey, The Guest.
*
* It is now time for us to explore the nooks and crannies of the three Guest
* devices and complete our understanding of the Guest in "make Drivers".
*/