paravirt.h

#ifndef __ASM_PARAVIRT_H
#define __ASM_PARAVIRT_H
/* Various instructions on x86 need to be replaced for
 * para-virtualization: those hooks are defined here. */

#ifdef CONFIG_PARAVIRT
#include <asm/page.h>

/* Bitmask of what can be clobbered: usually at least eax. */
#define CLBR_NONE 0x0
#define CLBR_EAX 0x1
#define CLBR_ECX 0x2
#define CLBR_EDX 0x4
#define CLBR_ANY 0x7

#ifndef __ASSEMBLY__
#include <linux/types.h>
#include <linux/cpumask.h>
#include <asm/kmap_types.h>
#include <asm/desc_defs.h>

struct page;
struct thread_struct;
struct desc_ptr;
struct tss_struct;
struct mm_struct;
struct desc_struct;

/* general info */
struct pv_info {
	unsigned int kernel_rpl;
	int shared_kernel_pmd;
	int paravirt_enabled;
	const char *name;
};

struct pv_init_ops {
	/*
	 * Patch may replace one of the defined code sequences with
	 * arbitrary code, subject to the same register constraints.
	 * This generally means the code is not free to clobber any
	 * registers other than EAX.  The patch function should return
	 * the number of bytes of code generated, as we nop pad the
	 * rest in generic code.
	 */
	unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
			  unsigned long addr, unsigned len);

	/* Basic arch-specific setup */
	void (*arch_setup)(void);
	char *(*memory_setup)(void);
	void (*post_allocator_init)(void);

	/* Print a banner to identify the environment */
	void (*banner)(void);
};


struct pv_lazy_ops {
	/* Set deferred update mode, used for batching operations. */
	void (*enter)(void);
	void (*leave)(void);
};

struct pv_time_ops {
	void (*time_init)(void);

	/* Set and set time of day */
	unsigned long (*get_wallclock)(void);
	int (*set_wallclock)(unsigned long);

	unsigned long long (*sched_clock)(void);
	unsigned long (*get_cpu_khz)(void);
};

struct pv_cpu_ops {
	/* hooks for various privileged instructions */
	unsigned long (*get_debugreg)(int regno);
	void (*set_debugreg)(int regno, unsigned long value);

	void (*clts)(void);

	unsigned long (*read_cr0)(void);
	void (*write_cr0)(unsigned long);

	unsigned long (*read_cr4_safe)(void);
	unsigned long (*read_cr4)(void);
	void (*write_cr4)(unsigned long);

	/* Segment descriptor handling */
	void (*load_tr_desc)(void);
	void (*load_gdt)(const struct desc_ptr *);
	void (*load_idt)(const struct desc_ptr *);
	void (*store_gdt)(struct desc_ptr *);
	void (*store_idt)(struct desc_ptr *);
	void (*set_ldt)(const void *desc, unsigned entries);
	unsigned long (*store_tr)(void);
	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
	void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
				const void *desc);
	void (*write_gdt_entry)(struct desc_struct *,
				int entrynum, const void *desc, int size);
	void (*write_idt_entry)(gate_desc *,
				int entrynum, const gate_desc *gate);
	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);

	void (*set_iopl_mask)(unsigned mask);

	void (*wbinvd)(void);
	void (*io_delay)(void);

	/* cpuid emulation, mostly so that caps bits can be disabled */
	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
		      unsigned int *ecx, unsigned int *edx);

	/* MSR, PMC and TSR operations.
	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
	u64 (*read_msr)(unsigned int msr, int *err);
	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);

	u64 (*read_tsc)(void);
	u64 (*read_pmc)(int counter);
	unsigned long long (*read_tscp)(unsigned int *aux);

	/* These two are jmp to, not actually called. */
	void (*irq_enable_syscall_ret)(void);
	void (*iret)(void);

	struct pv_lazy_ops lazy_mode;
};

struct pv_irq_ops {
	void (*init_IRQ)(void);

	/*
	 * Get/set interrupt state.  save_fl and restore_fl are only
	 * expected to use X86_EFLAGS_IF; all other bits
	 * returned from save_fl are undefined, and may be ignored by
	 * restore_fl.
	 */
	unsigned long (*save_fl)(void);
	void (*restore_fl)(unsigned long);
	void (*irq_disable)(void);
	void (*irq_enable)(void);
	void (*safe_halt)(void);
	void (*halt)(void);
};

struct pv_apic_ops {
#ifdef CONFIG_X86_LOCAL_APIC
	/*
	 * Direct APIC operations, principally for VMI.  Ideally
	 * these shouldn't be in this interface.
	 */
	void (*apic_write)(unsigned long reg, u32 v);
	void (*apic_write_atomic)(unsigned long reg, u32 v);
	u32 (*apic_read)(unsigned long reg);
	void (*setup_boot_clock)(void);
	void (*setup_secondary_clock)(void);

	void (*startup_ipi_hook)(int phys_apicid,
				 unsigned long start_eip,
				 unsigned long start_esp);
#endif
};

struct pv_mmu_ops {
	/*
	 * Called before/after init_mm pagetable setup. setup_start
	 * may reset %cr3, and may pre-install parts of the pagetable;
	 * pagetable setup is expected to preserve any existing
	 * mapping.
	 */
	void (*pagetable_setup_start)(pgd_t *pgd_base);
	void (*pagetable_setup_done)(pgd_t *pgd_base);

	unsigned long (*read_cr2)(void);
	void (*write_cr2)(unsigned long);

	unsigned long (*read_cr3)(void);
	void (*write_cr3)(unsigned long);

	/*
	 * Hooks for intercepting the creation/use/destruction of an
	 * mm_struct.
	 */
	void (*activate_mm)(struct mm_struct *prev,
			    struct mm_struct *next);
	void (*dup_mmap)(struct mm_struct *oldmm,
			 struct mm_struct *mm);
	void (*exit_mmap)(struct mm_struct *mm);


	/* TLB operations */
	void (*flush_tlb_user)(void);
	void (*flush_tlb_kernel)(void);
	void (*flush_tlb_single)(unsigned long addr);
	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
				 unsigned long va);