*/
#include <linux/types.h>
+#include <linux/hardirq.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#define KVM_MAX_VCPUS 4
#define KVM_ALIAS_SLOTS 4
#define KVM_MEMORY_SLOTS 8
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_PERMILLE_MMU_PAGES 20
+#define KVM_MIN_ALLOC_MMU_PAGES 64
#define KVM_NUM_MMU_PAGES 1024
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40
#define DE_VECTOR 0
+#define UD_VECTOR 6
#define NM_VECTOR 7
#define DF_VECTOR 8
#define TS_VECTOR 10
/*
* vcpu->requests bit members
*/
-#define KVM_TLB_FLUSH 0
+#define KVM_REQ_TLB_FLUSH 0
/*
* Address types:
union kvm_mmu_page_role role;
u64 *spt;
+ /* hold the gfn of each spte inside spt */
+ gfn_t *gfns;
unsigned long slot_bitmap; /* One bit set per slot which has memory
* in this shadow page.
*/
int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
void (*free)(struct kvm_vcpu *vcpu);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
+ void (*prefetch_page)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *page);
hpa_t root_hpa;
int root_level;
int shadow_root_level;
u64 *pae_root;
};
-#define KVM_NR_MEM_OBJS 20
+#define KVM_NR_MEM_OBJS 40
struct kvm_mmu_memory_cache {
int nobjs;
VCPU_SREG_LDTR,
};
+#include "x86_emulate.h"
+
struct kvm_pio_request {
unsigned long count;
int cur_count;
u32 halt_wakeup;
u32 request_irq_exits;
u32 irq_exits;
- u32 light_exits;
+ u32 host_state_reload;
u32 efer_reload;
+ u32 fpu_reload;
};
struct kvm_io_device {
void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
struct kvm_io_device *dev);
-struct kvm_vcpu {
- struct kvm *kvm;
- struct preempt_notifier preempt_notifier;
- int vcpu_id;
- struct mutex mutex;
- int cpu;
- u64 host_tsc;
- struct kvm_run *run;
- int interrupt_window_open;
- int guest_mode;
- unsigned long requests;
- unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
- DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
- unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */
- unsigned long rip; /* needs vcpu_load_rsp_rip() */
-
- unsigned long cr0;
- unsigned long cr2;
- unsigned long cr3;
- gpa_t para_state_gpa;
- struct page *para_state_page;
- gpa_t hypercall_gpa;
- unsigned long cr4;
- unsigned long cr8;
- u64 pdptrs[4]; /* pae */
- u64 shadow_efer;
- u64 apic_base;
- struct kvm_lapic *apic; /* kernel irqchip context */
-#define VCPU_MP_STATE_RUNNABLE 0
-#define VCPU_MP_STATE_UNINITIALIZED 1
-#define VCPU_MP_STATE_INIT_RECEIVED 2
-#define VCPU_MP_STATE_SIPI_RECEIVED 3
-#define VCPU_MP_STATE_HALTED 4
- int mp_state;
- int sipi_vector;
- u64 ia32_misc_enable_msr;
-
- struct kvm_mmu mmu;
-
- struct kvm_mmu_memory_cache mmu_pte_chain_cache;
- struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
- struct kvm_mmu_memory_cache mmu_page_cache;
- struct kvm_mmu_memory_cache mmu_page_header_cache;
-
- gfn_t last_pt_write_gfn;
- int last_pt_write_count;
-
- struct kvm_guest_debug guest_debug;
-
- struct i387_fxsave_struct host_fx_image;
- struct i387_fxsave_struct guest_fx_image;
- int fpu_active;
- int guest_fpu_loaded;
-
- int mmio_needed;
- int mmio_read_completed;
- int mmio_is_write;
- int mmio_size;
- unsigned char mmio_data[8];
+#ifdef CONFIG_HAS_IOMEM
+#define KVM_VCPU_MMIO \
+ int mmio_needed; \
+ int mmio_read_completed; \
+ int mmio_is_write; \
+ int mmio_size; \
+ unsigned char mmio_data[8]; \
gpa_t mmio_phys_addr;
- gva_t mmio_fault_cr2;
- struct kvm_pio_request pio;
- void *pio_data;
- wait_queue_head_t wq;
- int sigset_active;
- sigset_t sigset;
+#else
+#define KVM_VCPU_MMIO
- struct kvm_stat stat;
+#endif
- struct {
- int active;
- u8 save_iopl;
- struct kvm_save_segment {
- u16 selector;
- unsigned long base;
- u32 limit;
- u32 ar;
- } tr, es, ds, fs, gs;
- } rmode;
- int halt_request; /* real mode on Intel only */
-
- int cpuid_nent;
- struct kvm_cpuid_entry cpuid_entries[KVM_MAX_CPUID_ENTRIES];
-};
+#define KVM_VCPU_COMM \
+ struct kvm *kvm; \
+ struct preempt_notifier preempt_notifier; \
+ int vcpu_id; \
+ struct mutex mutex; \
+ int cpu; \
+ struct kvm_run *run; \
+ int guest_mode; \
+ unsigned long requests; \
+ struct kvm_guest_debug guest_debug; \
+ int fpu_active; \
+ int guest_fpu_loaded; \
+ wait_queue_head_t wq; \
+ int sigset_active; \
+ sigset_t sigset; \
+ struct kvm_stat stat; \
+ KVM_VCPU_MMIO
struct kvm_mem_alias {
gfn_t base_gfn;
gfn_t base_gfn;
unsigned long npages;
unsigned long flags;
- struct page **phys_mem;
+ unsigned long *rmap;
unsigned long *dirty_bitmap;
+ unsigned long userspace_addr;
+ int user_alloc;
};
struct kvm {
int naliases;
struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
int nmemslots;
- struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS];
+ struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
+ KVM_PRIVATE_MEM_SLOTS];
/*
* Hash table of struct kvm_mmu_page.
*/
struct list_head active_mmu_pages;
- int n_free_mmu_pages;
+ unsigned int n_free_mmu_pages;
+ unsigned int n_requested_mmu_pages;
+ unsigned int n_alloc_mmu_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
unsigned long rmap_overflow;
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
int round_robin_prev_vcpu;
+ unsigned int tss_addr;
+ struct page *apic_access_page;
};
static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
static inline int irqchip_in_kernel(struct kvm *kvm)
{
- return pic_irqchip(kvm) != 0;
+ return pic_irqchip(kvm) != NULL;
}
struct descriptor_table {
/* Create, but do not attach this VCPU */
struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
- void (*vcpu_reset)(struct kvm_vcpu *vcpu);
+ int (*vcpu_reset)(struct kvm_vcpu *vcpu);
void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
struct kvm_run *run);
+
+ int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
};
extern struct kvm_x86_ops *kvm_x86_ops;
if (printk_ratelimit()) \
printk(KERN_ERR "kvm: %i: cpu%i " fmt, \
current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__); \
- } while(0)
+ } while (0)
#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
-int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size,
+void vcpu_load(struct kvm_vcpu *vcpu);
+void vcpu_put(struct kvm_vcpu *vcpu);
+
+void decache_vcpus_on_cpu(int cpu);
+
+
+int kvm_init(void *opaque, unsigned int vcpu_size,
struct module *module);
-void kvm_exit_x86(void);
+void kvm_exit(void);
int kvm_mmu_module_init(void);
void kvm_mmu_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
int kvm_mmu_setup(struct kvm_vcpu *vcpu);
+void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
void kvm_mmu_zap_all(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
-hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa);
+hpa_t gpa_to_hpa(struct kvm *kvm, gpa_t gpa);
#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva);
struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva);
-extern hpa_t bad_page_address;
-
+extern struct page *bad_page;
+
+int is_error_page(struct page *page);
+int kvm_is_error_hva(unsigned long addr);
+int kvm_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ int user_alloc);
+int __kvm_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ int user_alloc);
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
+void kvm_release_page(struct page *page);
+int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
+ int len);
+int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
+int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
+ int offset, int len);
+int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
+ unsigned long len);
+int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
+int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
+int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
enum emulation_result {
};
int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
- unsigned long cr2, u16 error_code);
+ unsigned long cr2, u16 error_code, int no_decode);
void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
struct x86_emulate_ctxt;
-int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
int size, unsigned port);
int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
int size, unsigned long count, int down,
int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
int emulate_clts(struct kvm_vcpu *vcpu);
-int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr,
+int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
unsigned long *dest);
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
unsigned long value);
void fx_init(struct kvm_vcpu *vcpu);
+void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_flush_remote_tlbs(struct kvm *kvm);
int emulator_read_std(unsigned long addr,
- void *val,
+ void *val,
unsigned int bytes,
struct kvm_vcpu *vcpu);
int emulator_write_emulated(unsigned long addr,
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
-int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
-static inline void kvm_guest_enter(void)
-{
- current->flags |= PF_VCPU;
-}
+int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
-static inline void kvm_guest_exit(void)
-{
- current->flags &= ~PF_VCPU;
-}
+long kvm_arch_dev_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg);
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg);
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
-static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
- u32 error_code)
-{
- return vcpu->mmu.page_fault(vcpu, gva, error_code);
-}
+int kvm_dev_ioctl_check_extension(long ext);
-static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
-{
- if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
- __kvm_mmu_free_some_pages(vcpu);
-}
+int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+ struct
+ kvm_userspace_memory_region *mem,
+ int user_alloc);
+long kvm_arch_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg);
+void kvm_arch_destroy_vm(struct kvm *kvm);
-static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
-{
- if (likely(vcpu->mmu.root_hpa != INVALID_PAGE))
- return 0;
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
- return kvm_mmu_load(vcpu);
-}
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr);
-static inline int is_long_mode(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_X86_64
- return vcpu->shadow_efer & EFER_LME;
-#else
- return 0;
-#endif
-}
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs);
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs);
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+ struct kvm_debug_guest *dbg);
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
-static inline int is_pae(struct kvm_vcpu *vcpu)
-{
- return vcpu->cr4 & X86_CR4_PAE;
-}
+int kvm_arch_init(void *opaque);
+void kvm_arch_exit(void);
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
-static inline int is_pse(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
+void kvm_arch_vcpu_destory(struct kvm_vcpu *vcpu);
+
+int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_arch_hardware_enable(void *garbage);
+void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_setup(void);
+void kvm_arch_hardware_unsetup(void);
+void kvm_arch_check_processor_compat(void *rtn);
+
+void kvm_free_physmem(struct kvm *kvm);
+
+struct kvm *kvm_arch_create_vm(void);
+void kvm_arch_destroy_vm(struct kvm *kvm);
+
+static inline void kvm_guest_enter(void)
{
- return vcpu->cr4 & X86_CR4_PSE;
+ account_system_vtime(current);
+ current->flags |= PF_VCPU;
}
-static inline int is_paging(struct kvm_vcpu *vcpu)
+static inline void kvm_guest_exit(void)
{
- return vcpu->cr0 & X86_CR0_PG;
+ account_system_vtime(current);
+ current->flags &= ~PF_VCPU;
}
static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot)
static inline u16 read_fs(void)
{
u16 seg;
- asm ("mov %%fs, %0" : "=g"(seg));
+ asm("mov %%fs, %0" : "=g"(seg));
return seg;
}
static inline u16 read_gs(void)
{
u16 seg;
- asm ("mov %%gs, %0" : "=g"(seg));
+ asm("mov %%gs, %0" : "=g"(seg));
return seg;
}
static inline u16 read_ldt(void)
{
u16 ldt;
- asm ("sldt %0" : "=g"(ldt));
+ asm("sldt %0" : "=g"(ldt));
return ldt;
}
static inline void load_fs(u16 sel)
{
- asm ("mov %0, %%fs" : : "rm"(sel));
+ asm("mov %0, %%fs" : : "rm"(sel));
}
static inline void load_gs(u16 sel)
{
- asm ("mov %0, %%gs" : : "rm"(sel));
+ asm("mov %0, %%gs" : : "rm"(sel));
}
#ifndef load_ldt
static inline void load_ldt(u16 sel)
{
- asm ("lldt %0" : : "rm"(sel));
+ asm("lldt %0" : : "rm"(sel));
}
#endif
static inline void get_idt(struct descriptor_table *table)
{
- asm ("sidt %0" : "=m"(*table));
+ asm("sidt %0" : "=m"(*table));
}
static inline void get_gdt(struct descriptor_table *table)
{
- asm ("sgdt %0" : "=m"(*table));
+ asm("sgdt %0" : "=m"(*table));
}
static inline unsigned long read_tr_base(void)
{
u16 tr;
- asm ("str %0" : "=g"(tr));
+ asm("str %0" : "=g"(tr));
return segment_base(tr);
}
static inline void fx_save(struct i387_fxsave_struct *image)
{
- asm ("fxsave (%0)":: "r" (image));
+ asm("fxsave (%0)":: "r" (image));
}
static inline void fx_restore(struct i387_fxsave_struct *image)
{
- asm ("fxrstor (%0)":: "r" (image));
+ asm("fxrstor (%0)":: "r" (image));
}
static inline void fpu_init(void)
{
- asm ("finit");
+ asm("finit");
}
static inline u32 get_rdx_init_val(void)
#define TSS_REDIRECTION_SIZE (256 / 8)
#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
+struct kvm_stats_debugfs_item {
+ const char *name;
+ int offset;
+ struct dentry *dentry;
+};
+extern struct kvm_stats_debugfs_item debugfs_entries[];
+
#endif