#include "vmx.h"
#include <linux/kvm.h>
+#include <linux/kvm_para.h>
#define CR0_PE_MASK (1ULL << 0)
#define CR0_TS_MASK (1ULL << 3)
#define UNMAPPED_GVA (~(gpa_t)0)
#define KVM_MAX_VCPUS 1
+#define KVM_ALIAS_SLOTS 4
#define KVM_MEMORY_SLOTS 4
#define KVM_NUM_MMU_PAGES 256
+#define KVM_MIN_FREE_MMU_PAGES 5
+#define KVM_REFILL_PAGES 25
+#define KVM_MAX_CPUID_ENTRIES 40
#define FX_IMAGE_SIZE 512
#define FX_IMAGE_ALIGN 16
#define FX_BUF_SIZE (2 * FX_IMAGE_SIZE + FX_IMAGE_ALIGN)
#define DE_VECTOR 0
+#define NM_VECTOR 7
#define DF_VECTOR 8
#define TS_VECTOR 10
#define NP_VECTOR 11
#define IOPL_SHIFT 12
+#define KVM_PIO_PAGE_OFFSET 1
+
/*
* Address types:
*
typedef u64 hpa_t;
typedef unsigned long hfn_t;
+#define NR_PTE_CHAIN_ENTRIES 5
+
+struct kvm_pte_chain {
+ u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
+ struct hlist_node link;
+};
+
+/*
+ * kvm_mmu_page_role, below, is defined as:
+ *
+ * bits 0:3 - total guest paging levels (2-4, or zero for real mode)
+ * bits 4:7 - page table level for this shadow (1-4)
+ * bits 8:9 - page table quadrant for 2-level guests
+ * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ * bits 17:18 - "access" - the user and writable bits of a huge page pde
+ */
+union kvm_mmu_page_role {
+ unsigned word;
+ struct {
+ unsigned glevels : 4;
+ unsigned level : 4;
+ unsigned quadrant : 2;
+ unsigned pad_for_nice_hex_output : 6;
+ unsigned metaphysical : 1;
+ unsigned hugepage_access : 2;
+ };
+};
+
struct kvm_mmu_page {
struct list_head link;
+ struct hlist_node hash_link;
+
+ /*
+ * The following two entries are used to key the shadow page in the
+ * hash table.
+ */
+ gfn_t gfn;
+ union kvm_mmu_page_role role;
+
hpa_t page_hpa;
unsigned long slot_bitmap; /* One bit set per slot which has memory
* in this shadow page.
*/
- int global; /* Set if all ptes in this page are global */
- u64 *parent_pte;
+ int multimapped; /* More than one parent_pte? */
+ int root_count; /* Currently serving as active root */
+ union {
+ u64 *parent_pte; /* !multimapped */
+ struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
+ };
};
struct vmcs {
struct kvm_mmu {
void (*new_cr3)(struct kvm_vcpu *vcpu);
int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
- void (*inval_page)(struct kvm_vcpu *vcpu, gva_t gva);
void (*free)(struct kvm_vcpu *vcpu);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
hpa_t root_hpa;
int root_level;
int shadow_root_level;
+
+ u64 *pae_root;
};
+#define KVM_NR_MEM_OBJS 20
+
+struct kvm_mmu_memory_cache {
+ int nobjs;
+ void *objects[KVM_NR_MEM_OBJS];
+};
+
+/*
+ * We don't want allocation failures within the mmu code, so we preallocate
+ * enough memory for a single page fault in a cache.
+ */
struct kvm_guest_debug {
int enabled;
unsigned long bp[4];
VCPU_SREG_LDTR,
};
+struct kvm_pio_request {
+ unsigned long count;
+ int cur_count;
+ struct page *guest_pages[2];
+ unsigned guest_page_offset;
+ int in;
+ int size;
+ int string;
+ int down;
+ int rep;
+};
+
+struct kvm_stat {
+ u32 pf_fixed;
+ u32 pf_guest;
+ u32 tlb_flush;
+ u32 invlpg;
+
+ u32 exits;
+ u32 io_exits;
+ u32 mmio_exits;
+ u32 signal_exits;
+ u32 irq_window_exits;
+ u32 halt_exits;
+ u32 request_irq_exits;
+ u32 irq_exits;
+};
+
struct kvm_vcpu {
struct kvm *kvm;
union {
struct mutex mutex;
int cpu;
int launched;
+ u64 host_tsc;
+ struct kvm_run *run;
int interrupt_window_open;
unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
#define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
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;
+ u64 ia32_misc_enable_msr;
int nmsrs;
struct vmx_msr_entry *guest_msrs;
struct vmx_msr_entry *host_msrs;
struct kvm_mmu_page page_header_buf[KVM_NUM_MMU_PAGES];
struct kvm_mmu mmu;
+ struct kvm_mmu_memory_cache mmu_pte_chain_cache;
+ struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
+
+ gfn_t last_pt_write_gfn;
+ int last_pt_write_count;
+
struct kvm_guest_debug guest_debug;
char fx_buf[FX_BUF_SIZE];
char *host_fx_image;
char *guest_fx_image;
+ int fpu_active;
int mmio_needed;
int mmio_read_completed;
int mmio_size;
unsigned char mmio_data[8];
gpa_t mmio_phys_addr;
+ struct kvm_pio_request pio;
+ void *pio_data;
+
+ int sigset_active;
+ sigset_t sigset;
+
+ struct kvm_stat stat;
struct {
int active;
u32 ar;
} tr, es, ds, fs, gs;
} rmode;
+
+ int cpuid_nent;
+ struct kvm_cpuid_entry cpuid_entries[KVM_MAX_CPUID_ENTRIES];
+};
+
+struct kvm_mem_alias {
+ gfn_t base_gfn;
+ unsigned long npages;
+ gfn_t target_gfn;
};
struct kvm_memory_slot {
struct kvm {
spinlock_t lock; /* protects everything except vcpus */
+ int naliases;
+ struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
int nmemslots;
struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS];
+ /*
+ * Hash table of struct kvm_mmu_page.
+ */
struct list_head active_mmu_pages;
+ int n_free_mmu_pages;
+ struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct kvm_vcpu vcpus[KVM_MAX_VCPUS];
int memory_config_version;
int busy;
unsigned long rmap_overflow;
-};
-
-struct kvm_stat {
- u32 pf_fixed;
- u32 pf_guest;
- u32 tlb_flush;
- u32 invlpg;
-
- u32 exits;
- u32 io_exits;
- u32 mmio_exits;
- u32 signal_exits;
- u32 irq_window_exits;
- u32 halt_exits;
- u32 request_irq_exits;
- u32 irq_exits;
+ struct list_head vm_list;
+ struct file *filp;
};
struct descriptor_table {
int (*vcpu_create)(struct kvm_vcpu *vcpu);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
- struct kvm_vcpu *(*vcpu_load)(struct kvm_vcpu *vcpu);
+ void (*vcpu_load)(struct kvm_vcpu *vcpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
+ void (*vcpu_decache)(struct kvm_vcpu *vcpu);
int (*set_guest_debug)(struct kvm_vcpu *vcpu,
struct kvm_debug_guest *dbg);
void (*set_segment)(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg);
void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
- void (*decache_cr0_cr4_guest_bits)(struct kvm_vcpu *vcpu);
+ void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
- void (*set_cr0_no_modeswitch)(struct kvm_vcpu *vcpu,
- unsigned long cr0);
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
int (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
int (*vcpu_setup)(struct kvm_vcpu *vcpu);
void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+ void (*patch_hypercall)(struct kvm_vcpu *vcpu,
+ unsigned char *hypercall_addr);
};
-extern struct kvm_stat kvm_stat;
extern struct kvm_arch_ops *kvm_arch_ops;
#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module);
void kvm_exit_arch(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);
int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
+void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot);
+void kvm_mmu_zap_all(struct kvm_vcpu *vcpu);
hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, 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);
void kvm_emulator_want_group7_invlpg(void);
extern hpa_t bad_page_address;
-static inline struct page *gfn_to_page(struct kvm_memory_slot *slot, gfn_t gfn)
-{
- return slot->phys_mem[gfn - slot->base_gfn];
-}
-
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
struct x86_emulate_ctxt;
+int kvm_setup_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+ int size, unsigned long count, int string, int down,
+ gva_t address, int rep, unsigned port);
+void kvm_emulate_cpuid(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,
unsigned long segment_base(u16 selector);
-static inline struct page *_gfn_to_page(struct kvm *kvm, gfn_t gfn)
+void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
+void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
+
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+ u32 error_code)
{
- struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
- return (slot) ? slot->phys_mem[gfn - slot->base_gfn] : NULL;
+ if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
+ kvm_mmu_free_some_pages(vcpu);
+ return vcpu->mmu.page_fault(vcpu, gva, error_code);
}
static inline int is_long_mode(struct kvm_vcpu *vcpu)
{
struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
- return (struct kvm_mmu_page *)page->private;
+ return (struct kvm_mmu_page *)page_private(page);
}
static inline u16 read_fs(void)
#ifndef load_ldt
static inline void load_ldt(u16 sel)
{
- asm ("lldt %0" : : "g"(sel));
+ asm ("lldt %0" : : "rm"(sel));
}
#endif
#define TSS_REDIRECTION_SIZE (256 / 8)
#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
-#ifdef CONFIG_X86_64
-
-/*
- * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64. Therefore
- * we need to allocate shadow page tables in the first 4GB of memory, which
- * happens to fit the DMA32 zone.
- */
-#define GFP_KVM_MMU (GFP_KERNEL | __GFP_DMA32)
-
-#else
-
-#define GFP_KVM_MMU GFP_KERNEL
-
-#endif
-
#endif