diff options
author | Paul Mackerras <paulus@samba.org> | 2007-05-08 13:37:51 +1000 |
---|---|---|
committer | Paul Mackerras <paulus@samba.org> | 2007-05-08 13:37:51 +1000 |
commit | 02bbc0f09c90cefdb2837605c96a66c5ce4ba2e1 (patch) | |
tree | 04ef573cd4de095c500c9fc3477f4278c0b36300 /drivers/kvm | |
parent | 7487a2245b8841c77ba9db406cf99a483b9334e9 (diff) | |
parent | 5b94f675f57e4ff16c8fda09088d7480a84dcd91 (diff) |
Merge branch 'linux-2.6'
Diffstat (limited to 'drivers/kvm')
-rw-r--r-- | drivers/kvm/kvm.h | 100 | ||||
-rw-r--r-- | drivers/kvm/kvm_main.c | 792 | ||||
-rw-r--r-- | drivers/kvm/kvm_svm.h | 13 | ||||
-rw-r--r-- | drivers/kvm/kvm_vmx.h | 14 | ||||
-rw-r--r-- | drivers/kvm/mmu.c | 154 | ||||
-rw-r--r-- | drivers/kvm/paging_tmpl.h | 12 | ||||
-rw-r--r-- | drivers/kvm/svm.c | 197 | ||||
-rw-r--r-- | drivers/kvm/svm.h | 6 | ||||
-rw-r--r-- | drivers/kvm/vmx.c | 273 | ||||
-rw-r--r-- | drivers/kvm/x86_emulate.c | 51 | ||||
-rw-r--r-- | drivers/kvm/x86_emulate.h | 32 |
11 files changed, 1204 insertions, 440 deletions
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h index 0d122bf889d..41634fde8e1 100644 --- a/drivers/kvm/kvm.h +++ b/drivers/kvm/kvm.h @@ -51,16 +51,19 @@ #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 @@ -73,6 +76,8 @@ #define IOPL_SHIFT 12 +#define KVM_PIO_PAGE_OFFSET 1 + /* * Address types: * @@ -106,6 +111,7 @@ struct kvm_pte_chain { * 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; @@ -115,6 +121,7 @@ union kvm_mmu_page_role { unsigned quadrant : 2; unsigned pad_for_nice_hex_output : 6; unsigned metaphysical : 1; + unsigned hugepage_access : 2; }; }; @@ -133,7 +140,6 @@ struct kvm_mmu_page { 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 */ int multimapped; /* More than one parent_pte? */ int root_count; /* Currently serving as active root */ union { @@ -219,6 +225,34 @@ enum { 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 { @@ -228,6 +262,8 @@ struct kvm_vcpu { 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) @@ -266,6 +302,7 @@ struct kvm_vcpu { char fx_buf[FX_BUF_SIZE]; char *host_fx_image; char *guest_fx_image; + int fpu_active; int mmio_needed; int mmio_read_completed; @@ -273,6 +310,14 @@ struct kvm_vcpu { 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; + + int sigset_active; + sigset_t sigset; + + struct kvm_stat stat; struct { int active; @@ -284,6 +329,15 @@ struct kvm_vcpu { 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 { @@ -296,6 +350,8 @@ 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]; /* @@ -312,22 +368,6 @@ struct kvm { struct file *filp; }; -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 descriptor_table { u16 limit; unsigned long base; @@ -358,10 +398,8 @@ struct kvm_arch_ops { 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); @@ -391,7 +429,6 @@ struct kvm_arch_ops { 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) @@ -400,28 +437,29 @@ extern struct kvm_arch_ops *kvm_arch_ops; 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_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); @@ -444,6 +482,10 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, 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, @@ -493,12 +535,6 @@ static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, return vcpu->mmu.page_fault(vcpu, gva, error_code); } -static inline struct page *_gfn_to_page(struct kvm *kvm, gfn_t gfn) -{ - struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); - return (slot) ? slot->phys_mem[gfn - slot->base_gfn] : NULL; -} - static inline int is_long_mode(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c index dc7a8c78cbf..c8b8cfa332b 100644 --- a/drivers/kvm/kvm_main.c +++ b/drivers/kvm/kvm_main.c @@ -51,27 +51,27 @@ static DEFINE_SPINLOCK(kvm_lock); static LIST_HEAD(vm_list); struct kvm_arch_ops *kvm_arch_ops; -struct kvm_stat kvm_stat; -EXPORT_SYMBOL_GPL(kvm_stat); + +#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x) static struct kvm_stats_debugfs_item { const char *name; - u32 *data; + int offset; struct dentry *dentry; } debugfs_entries[] = { - { "pf_fixed", &kvm_stat.pf_fixed }, - { "pf_guest", &kvm_stat.pf_guest }, - { "tlb_flush", &kvm_stat.tlb_flush }, - { "invlpg", &kvm_stat.invlpg }, - { "exits", &kvm_stat.exits }, - { "io_exits", &kvm_stat.io_exits }, - { "mmio_exits", &kvm_stat.mmio_exits }, - { "signal_exits", &kvm_stat.signal_exits }, - { "irq_window", &kvm_stat.irq_window_exits }, - { "halt_exits", &kvm_stat.halt_exits }, - { "request_irq", &kvm_stat.request_irq_exits }, - { "irq_exits", &kvm_stat.irq_exits }, - { NULL, NULL } + { "pf_fixed", STAT_OFFSET(pf_fixed) }, + { "pf_guest", STAT_OFFSET(pf_guest) }, + { "tlb_flush", STAT_OFFSET(tlb_flush) }, + { "invlpg", STAT_OFFSET(invlpg) }, + { "exits", STAT_OFFSET(exits) }, + { "io_exits", STAT_OFFSET(io_exits) }, + { "mmio_exits", STAT_OFFSET(mmio_exits) }, + { "signal_exits", STAT_OFFSET(signal_exits) }, + { "irq_window", STAT_OFFSET(irq_window_exits) }, + { "halt_exits", STAT_OFFSET(halt_exits) }, + { "request_irq", STAT_OFFSET(request_irq_exits) }, + { "irq_exits", STAT_OFFSET(irq_exits) }, + { NULL } }; static struct dentry *debugfs_dir; @@ -346,6 +346,17 @@ static void kvm_free_physmem(struct kvm *kvm) kvm_free_physmem_slot(&kvm->memslots[i], NULL); } +static void free_pio_guest_pages(struct kvm_vcpu *vcpu) +{ + int i; + + for (i = 0; i < 2; ++i) + if (vcpu->pio.guest_pages[i]) { + __free_page(vcpu->pio.guest_pages[i]); + vcpu->pio.guest_pages[i] = NULL; + } +} + static void kvm_free_vcpu(struct kvm_vcpu *vcpu) { if (!vcpu->vmcs) @@ -355,6 +366,11 @@ static void kvm_free_vcpu(struct kvm_vcpu *vcpu) kvm_mmu_destroy(vcpu); vcpu_put(vcpu); kvm_arch_ops->vcpu_free(vcpu); + free_page((unsigned long)vcpu->run); + vcpu->run = NULL; + free_page((unsigned long)vcpu->pio_data); + vcpu->pio_data = NULL; + free_pio_guest_pages(vcpu); } static void kvm_free_vcpus(struct kvm *kvm) @@ -404,12 +420,12 @@ static int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) u64 pdpte; u64 *pdpt; int ret; - struct kvm_memory_slot *memslot; + struct page *page; spin_lock(&vcpu->kvm->lock); - memslot = gfn_to_memslot(vcpu->kvm, pdpt_gfn); - /* FIXME: !memslot - emulate? 0xff? */ - pdpt = kmap_atomic(gfn_to_page(memslot, pdpt_gfn), KM_USER0); + page = gfn_to_page(vcpu->kvm, pdpt_gfn); + /* FIXME: !page - emulate? 0xff? */ + pdpt = kmap_atomic(page, KM_USER0); ret = 1; for (i = 0; i < 4; ++i) { @@ -494,7 +510,6 @@ EXPORT_SYMBOL_GPL(set_cr0); void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { - kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu); set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f)); } EXPORT_SYMBOL_GPL(lmsw); @@ -830,7 +845,73 @@ out: return r; } -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) +/* + * Set a new alias region. Aliases map a portion of physical memory into + * another portion. This is useful for memory windows, for example the PC + * VGA region. + */ +static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, + struct kvm_memory_alias *alias) +{ + int r, n; + struct kvm_mem_alias *p; + + r = -EINVAL; + /* General sanity checks */ + if (alias->memory_size & (PAGE_SIZE - 1)) + goto out; + if (alias->guest_phys_addr & (PAGE_SIZE - 1)) + goto out; + if (alias->slot >= KVM_ALIAS_SLOTS) + goto out; + if (alias->guest_phys_addr + alias->memory_size + < alias->guest_phys_addr) + goto out; + if (alias->target_phys_addr + alias->memory_size + < alias->target_phys_addr) + goto out; + + spin_lock(&kvm->lock); + + p = &kvm->aliases[alias->slot]; + p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; + p->npages = alias->memory_size >> PAGE_SHIFT; + p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; + + for (n = KVM_ALIAS_SLOTS; n > 0; --n) + if (kvm->aliases[n - 1].npages) + break; + kvm->naliases = n; + + spin_unlock(&kvm->lock); + + vcpu_load(&kvm->vcpus[0]); + spin_lock(&kvm->lock); + kvm_mmu_zap_all(&kvm->vcpus[0]); + spin_unlock(&kvm->lock); + vcpu_put(&kvm->vcpus[0]); + + return 0; + +out: + return r; +} + +static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_mem_alias *alias; + + for (i = 0; i < kvm->naliases; ++i) { + alias = &kvm->aliases[i]; + if (gfn >= alias->base_gfn + && gfn < alias->base_gfn + alias->npages) + return alias->target_gfn + gfn - alias->base_gfn; + } + return gfn; +} + +static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { int i; @@ -843,7 +924,24 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) } return NULL; } -EXPORT_SYMBOL_GPL(gfn_to_memslot); + +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) +{ + gfn = unalias_gfn(kvm, gfn); + return __gfn_to_memslot(kvm, gfn); +} + +struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + + gfn = unalias_gfn(kvm, gfn); + slot = __gfn_to_memslot(kvm, gfn); + if (!slot) + return NULL; + return slot->phys_mem[gfn - slot->base_gfn]; +} +EXPORT_SYMBOL_GPL(gfn_to_page); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { @@ -871,7 +969,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) } static int emulator_read_std(unsigned long addr, - unsigned long *val, + void *val, unsigned int bytes, struct x86_emulate_ctxt *ctxt) { @@ -883,20 +981,20 @@ static int emulator_read_std(unsigned long addr, unsigned offset = addr & (PAGE_SIZE-1); unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); unsigned long pfn; - struct kvm_memory_slot *memslot; - void *page; + struct page *page; + void *page_virt; if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; pfn = gpa >> PAGE_SHIFT; - memslot = gfn_to_memslot(vcpu->kvm, pfn); - if (!memslot) + page = gfn_to_page(vcpu->kvm, pfn); + if (!page) return X86EMUL_UNHANDLEABLE; - page = kmap_atomic(gfn_to_page(memslot, pfn), KM_USER0); + page_virt = kmap_atomic(page, KM_USER0); - memcpy(data, page + offset, tocopy); + memcpy(data, page_virt + offset, tocopy); - kunmap_atomic(page, KM_USER0); + kunmap_atomic(page_virt, KM_USER0); bytes -= tocopy; data += tocopy; @@ -907,7 +1005,7 @@ static int emulator_read_std(unsigned long addr, } static int emulator_write_std(unsigned long addr, - unsigned long val, + const void *val, unsigned int bytes, struct x86_emulate_ctxt *ctxt) { @@ -917,7 +1015,7 @@ static int emulator_write_std(unsigned long addr, } static int emulator_read_emulated(unsigned long addr, - unsigned long *val, + void *val, unsigned int bytes, struct x86_emulate_ctxt *ctxt) { @@ -945,37 +1043,37 @@ static int emulator_read_emulated(unsigned long addr, } static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - unsigned long val, int bytes) + const void *val, int bytes) { - struct kvm_memory_slot *m; struct page *page; void *virt; if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT)) return 0; - m = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!m) + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + if (!page) return 0; - page = gfn_to_page(m, gpa >> PAGE_SHIFT); kvm_mmu_pre_write(vcpu, gpa, bytes); mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); virt = kmap_atomic(page, KM_USER0); - memcpy(virt + offset_in_page(gpa), &val, bytes); + memcpy(virt + offset_in_page(gpa), val, bytes); kunmap_atomic(virt, KM_USER0); kvm_mmu_post_write(vcpu, gpa, bytes); return 1; } static int emulator_write_emulated(unsigned long addr, - unsigned long val, + const void *val, unsigned int bytes, struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - if (gpa == UNMAPPED_GVA) + if (gpa == UNMAPPED_GVA) { + kvm_arch_ops->inject_page_fault(vcpu, addr, 2); return X86EMUL_PROPAGATE_FAULT; + } if (emulator_write_phys(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; @@ -984,14 +1082,14 @@ static int emulator_write_emulated(unsigned long addr, vcpu->mmio_phys_addr = gpa; vcpu->mmio_size = bytes; vcpu->mmio_is_write = 1; - memcpy(vcpu->mmio_data, &val, bytes); + memcpy(vcpu->mmio_data, val, bytes); return X86EMUL_CONTINUE; } static int emulator_cmpxchg_emulated(unsigned long addr, - unsigned long old, - unsigned long new, + const void *old, + const void *new, unsigned int bytes, struct x86_emulate_ctxt *ctxt) { @@ -1004,30 +1102,6 @@ static int emulator_cmpxchg_emulated(unsigned long addr, return emulator_write_emulated(addr, new, bytes, ctxt); } -#ifdef CONFIG_X86_32 - -static int emulator_cmpxchg8b_emulated(unsigned long addr, - unsigned long old_lo, - unsigned long old_hi, - unsigned long new_lo, - unsigned long new_hi, - struct x86_emulate_ctxt *ctxt) -{ - static int reported; - int r; - - if (!reported) { - reported = 1; - printk(KERN_WARNING "kvm: emulating exchange8b as write\n"); - } - r = emulator_write_emulated(addr, new_lo, 4, ctxt); - if (r != X86EMUL_CONTINUE) - return r; - return emulator_write_emulated(addr+4, new_hi, 4, ctxt); -} - -#endif - static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_arch_ops->get_segment_base(vcpu, seg); @@ -1042,7 +1116,6 @@ int emulate_clts(struct kvm_vcpu *vcpu) { unsigned long cr0; - kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu); cr0 = vcpu->cr0 & ~CR0_TS_MASK; kvm_arch_ops->set_cr0(vcpu, cr0); return X86EMUL_CONTINUE; @@ -1102,9 +1175,6 @@ struct x86_emulate_ops emulate_ops = { .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, -#ifdef CONFIG_X86_32 - .cmpxchg8b_emulated = emulator_cmpxchg8b_emulated, -#endif }; int emulate_instruction(struct kvm_vcpu *vcpu, @@ -1116,6 +1186,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, int r; int cs_db, cs_l; + vcpu->mmio_fault_cr2 = cr2; kvm_arch_ops->cache_regs(vcpu); kvm_arch_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); @@ -1166,8 +1237,10 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_arch_ops->decache_regs(vcpu); kvm_arch_ops->set_rflags(vcpu, emulate_ctxt.eflags); - if (vcpu->mmio_is_write) + if (vcpu->mmio_is_write) { + vcpu->mmio_needed = 0; return EMULATE_DO_MMIO; + } return EMULATE_DONE; } @@ -1177,7 +1250,7 @@ int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run) { unsigned long nr, a0, a1, a2, a3, a4, a5, ret; - kvm_arch_ops->decache_regs(vcpu); + kvm_arch_ops->cache_regs(vcpu); ret = -KVM_EINVAL; #ifdef CONFIG_X86_64 if (is_long_mode(vcpu)) { @@ -1201,10 +1274,19 @@ int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run) } switch (nr) { default: - ; + run->hypercall.args[0] = a0; + run->hypercall.args[1] = a1; + run->hypercall.args[2] = a2; + run->hypercall.args[3] = a3; + run->hypercall.args[4] = a4; + run->hypercall.args[5] = a5; + run->hypercall.ret = ret; + run->hypercall.longmode = is_long_mode(vcpu); + kvm_arch_ops->decache_regs(vcpu); + return 0; } vcpu->regs[VCPU_REGS_RAX] = ret; - kvm_arch_ops->cache_regs(vcpu); + kvm_arch_ops->decache_regs(vcpu); return 1; } EXPORT_SYMBOL_GPL(kvm_hypercall); @@ -1237,7 +1319,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) { - kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu); + kvm_arch_ops->decache_cr4_guest_bits(vcpu); switch (cr) { case 0: return vcpu->cr0; @@ -1442,6 +1524,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", __FUNCTION__, data); break; + case MSR_IA32_MCG_STATUS: + printk(KERN_WARNING "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", + __FUNCTION__, data); + break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case 0x200 ... 0x2ff: /* MTRRs */ @@ -1478,6 +1564,8 @@ static int set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) void kvm_resched(struct kvm_vcpu *vcpu) { + if (!need_resched()) + return; vcpu_put(vcpu); cond_resched(); vcpu_load(vcpu); @@ -1502,29 +1590,250 @@ void save_msrs(struct vmx_msr_entry *e, int n) } EXPORT_SYMBOL_GPL(save_msrs); +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + int i; + u32 function; + struct kvm_cpuid_entry *e, *best; + + kvm_arch_ops->cache_regs(vcpu); + function = vcpu->regs[VCPU_REGS_RAX]; + vcpu->regs[VCPU_REGS_RAX] = 0; + vcpu->regs[VCPU_REGS_RBX] = 0; + vcpu->regs[VCPU_REGS_RCX] = 0; + vcpu->regs[VCPU_REGS_RDX] = 0; + best = NULL; + for (i = 0; i < vcpu->cpuid_nent; ++i) { + e = &vcpu->cpuid_entries[i]; + if (e->function == function) { + best = e; + break; + } + /* + * Both basic or both extended? + */ + if (((e->function ^ function) & 0x80000000) == 0) + if (!best || e->function > best->function) + best = e; + } + if (best) { + vcpu->regs[VCPU_REGS_RAX] = best->eax; + vcpu->regs[VCPU_REGS_RBX] = best->ebx; + vcpu->regs[VCPU_REGS_RCX] = best->ecx; + vcpu->regs[VCPU_REGS_RDX] = best->edx; + } + kvm_arch_ops->decache_regs(vcpu); + kvm_arch_ops->skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); + +static int pio_copy_data(struct kvm_vcpu *vcpu) +{ + void *p = vcpu->pio_data; + void *q; + unsigned bytes; + int nr_pages = vcpu->pio.guest_pages[1] ? 2 : 1; + + kvm_arch_ops->vcpu_put(vcpu); + q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE, + PAGE_KERNEL); + if (!q) { + kvm_arch_ops->vcpu_load(vcpu); + free_pio_guest_pages(vcpu); + return -ENOMEM; + } + q += vcpu->pio.guest_page_offset; + bytes = vcpu->pio.size * vcpu->pio.cur_count; + if (vcpu->pio.in) + memcpy(q, p, bytes); + else + memcpy(p, q, bytes); + q -= vcpu->pio.guest_page_offset; + vunmap(q); + kvm_arch_ops->vcpu_load(vcpu); + free_pio_guest_pages(vcpu); + return 0; +} + +static int complete_pio(struct kvm_vcpu *vcpu) +{ + struct kvm_pio_request *io = &vcpu->pio; + long delta; + int r; + + kvm_arch_ops->cache_regs(vcpu); + + if (!io->string) { + if (io->in) + memcpy(&vcpu->regs[VCPU_REGS_RAX], vcpu->pio_data, + io->size); + } else { + if (io->in) { + r = pio_copy_data(vcpu); + if (r) { + kvm_arch_ops->cache_regs(vcpu); + return r; + } + } + + delta = 1; + if (io->rep) { + delta *= io->cur_count; + /* + * The size of the register should really depend on + * current address size. + */ + vcpu->regs[VCPU_REGS_RCX] -= delta; + } + if (io->down) + delta = -delta; + delta *= io->size; + if (io->in) + vcpu->regs[VCPU_REGS_RDI] += delta; + else + vcpu->regs[VCPU_REGS_RSI] += delta; + } + + kvm_arch_ops->decache_regs(vcpu); + + io->count -= io->cur_count; + io->cur_count = 0; + + if (!io->count) + kvm_arch_ops->skip_emulated_instruction(vcpu); + return 0; +} + +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) +{ + unsigned now, in_page; + int i; + int nr_pages = 1; + struct page *page; + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + vcpu->pio.count = count; + vcpu->pio.cur_count = count; + vcpu->pio.size = size; + vcpu->pio.in = in; + vcpu->pio.string = string; + vcpu->pio.down = down; + vcpu->pio.guest_page_offset = offset_in_page(address); + vcpu->pio.rep = rep; + + if (!string) { + kvm_arch_ops->cache_regs(vcpu); + memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4); + kvm_arch_ops->decache_regs(vcpu); + return 0; + } + + if (!count) { + kvm_arch_ops->skip_emulated_instruction(vcpu); + return 1; + } + + now = min(count, PAGE_SIZE / size); + + if (!down) + in_page = PAGE_SIZE - offset_in_page(address); + else + in_page = offset_in_page(address) + size; + now = min(count, (unsigned long)in_page / size); + if (!now) { + /* + * String I/O straddles page boundary. Pin two guest pages + * so that we satisfy atomicity constraints. Do just one + * transaction to avoid complexity. + */ + nr_pages = 2; + now = 1; + } + if (down) { + /* + * String I/O in reverse. Yuck. Kill the guest, fix later. + */ + printk(KERN_ERR "kvm: guest string pio down\n"); + inject_gp(vcpu); + return 1; + } + vcpu->run->io.count = now; + vcpu->pio.cur_count = now; + + for (i = 0; i < nr_pages; ++i) { + spin_lock(&vcpu->kvm->lock); + page = gva_to_page(vcpu, address + i * PAGE_SIZE); + if (page) + get_page(page); + vcpu->pio.guest_pages[i] = page; + spin_unlock(&vcpu->kvm->lock); + if (!page) { + inject_gp(vcpu); + free_pio_guest_pages(vcpu); + return 1; + } + } + + if (!vcpu->pio.in) + return pio_copy_data(vcpu); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_setup_pio); + static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; + sigset_t sigsaved; vcpu_load(vcpu); + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + /* re-sync apic's tpr */ vcpu->cr8 = kvm_run->cr8; - if (kvm_run->emulated) { - kvm_arch_ops->skip_emulated_instruction(vcpu); - kvm_run->emulated = 0; + if (vcpu->pio.cur_count) { + r = complete_pio(vcpu); + if (r) + goto out; } - if (kvm_run->mmio_completed) { + if (vcpu->mmio_needed) { memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; + vcpu->mmio_needed = 0; + r = emulate_instruction(vcpu, kvm_run, + vcpu->mmio_fault_cr2, 0); + if (r == EMULATE_DO_MMIO) { + /* + * Read-modify-write. Back to userspace. + */ + kvm_run->exit_reason = KVM_EXIT_MMIO; + r = 0; + goto out; + } } - vcpu->mmio_needed = 0; + if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { + kvm_arch_ops->cache_regs(vcpu); + vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; + kvm_arch_ops->decache_regs(vcpu); + } r = kvm_arch_ops->run(vcpu, kvm_run); +out: + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + vcpu_put(vcpu); return r; } @@ -1633,7 +1942,7 @@ static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, sregs->gdt.limit = dt.limit; sregs->gdt.base = dt.base; - kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu); + kvm_arch_ops->decache_cr4_guest_bits(vcpu); sregs->cr0 = vcpu->cr0; sregs->cr2 = vcpu->cr2; sregs->cr3 = vcpu->cr3; @@ -1665,16 +1974,6 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, vcpu_load(vcpu); - set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - set_segment(vcpu, &sregs->es, VCPU_SREG_ES); - set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - - set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - dt.limit = sregs->idt.limit; dt.base = sregs->idt.base; kvm_arch_ops->set_idt(vcpu, &dt); @@ -1694,10 +1993,10 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, #endif vcpu->apic_base = sregs->apic_base; - kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu); + kvm_arch_ops->decache_cr4_guest_bits(vcpu); mmu_reset_needed |= vcpu->cr0 != sregs->cr0; - kvm_arch_ops->set_cr0_no_modeswitch(vcpu, sregs->cr0); + kvm_arch_ops->set_cr0(vcpu, sregs->cr0); mmu_reset_needed |= vcpu->cr4 != sregs->cr4; kvm_arch_ops->set_cr4(vcpu, sregs->cr4); @@ -1714,6 +2013,16 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, if (vcpu->irq_pending[i]) __set_bit(i, &vcpu->irq_summary); + set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + set_segment(vcpu, &sregs->es, VCPU_SREG_ES); + set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + + set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + vcpu_put(vcpu); return 0; @@ -1887,6 +2196,36 @@ static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, return r; } +static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma, + unsigned long address, + int *type) +{ + struct kvm_vcpu *vcpu = vma->vm_file->private_data; + unsigned long pgoff; + struct page *page; + + *type = VM_FAULT_MINOR; + pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + if (pgoff == 0) + page = virt_to_page(vcpu->run); + else if (pgoff == KVM_PIO_PAGE_OFFSET) + page = virt_to_page(vcpu->pio_data); + else + return NOPAGE_SIGBUS; + get_page(page); + return page; +} + +static struct vm_operations_struct kvm_vcpu_vm_ops = { + .nopage = kvm_vcpu_nopage, +}; + +static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) +{ + vma->vm_ops = &kvm_vcpu_vm_ops; + return 0; +} + static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; @@ -1899,6 +2238,7 @@ static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .compat_ioctl = kvm_vcpu_ioctl, + .mmap = kvm_vcpu_mmap, }; /* @@ -1947,6 +2287,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n) { int r; struct kvm_vcpu *vcpu; + struct page *page; r = -EINVAL; if (!valid_vcpu(n)) @@ -1961,9 +2302,22 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n) return -EEXIST; } + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + r = -ENOMEM; + if (!page) + goto out_unlock; + vcpu->run = page_address(page); + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + r = -ENOMEM; + if (!page) + goto out_free_run; + vcpu->pio_data = page_address(page); + vcpu->host_fx_image = (char*)ALIGN((hva_t)vcpu->fx_buf, FX_IMAGE_ALIGN); vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE; + vcpu->cr0 = 0x10; r = kvm_arch_ops->vcpu_create(vcpu); if (r < 0) @@ -1990,11 +2344,107 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n) out_free_vcpus: kvm_free_vcpu(vcpu); +out_free_run: + free_page((unsigned long)vcpu->run); + vcpu->run = NULL; +out_unlock: mutex_unlock(&vcpu->mutex); out: return r; } +static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -EFAULT; + if (copy_from_user(&vcpu->cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry))) + goto out; + vcpu->cpuid_nent = cpuid->nent; + return 0; + +out: + return r; +} + +static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) +{ + if (sigset) { + sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); + vcpu->sigset_active = 1; + vcpu->sigset = *sigset; + } else + vcpu->sigset_active = 0; + return 0; +} + +/* + * fxsave fpu state. Taken from x86_64/processor.h. To be killed when + * we have asm/x86/processor.h + */ +struct fxsave { + u16 cwd; + u16 swd; + u16 twd; + u16 fop; + u64 rip; + u64 rdp; + u32 mxcsr; + u32 mxcsr_mask; + u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ +#ifdef CONFIG_X86_64 + u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ +#else + u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ +#endif +}; + +static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image; + + vcpu_load(vcpu); + + memcpy(fpu->fpr, fxsave->st_space, 128); + fpu->fcw = fxsave->cwd; + fpu->fsw = fxsave->swd; + fpu->ftwx = fxsave->twd; + fpu->last_opcode = fxsave->fop; + fpu->last_ip = fxsave->rip; + fpu->last_dp = fxsave->rdp; + memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); + + vcpu_put(vcpu); + + return 0; +} + +static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image; + + vcpu_load(vcpu); + + memcpy(fxsave->st_space, fpu->fpr, 128); + fxsave->cwd = fpu->fcw; + fxsave->swd = fpu->fsw; + fxsave->twd = fpu->ftwx; + fxsave->fop = fpu->last_opcode; + fxsave->rip = fpu->last_ip; + fxsave->rdp = fpu->last_dp; + memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); + + vcpu_put(vcpu); + + return 0; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2003,21 +2453,12 @@ static long kvm_vcpu_ioctl(struct file *filp, int r = -EINVAL; switch (ioctl) { - case KVM_RUN: { - struct kvm_run kvm_run; - - r = -EFAULT; - if (copy_from_user(&kvm_run, argp, sizeof kvm_run)) + case KVM_RUN: + r = -EINVAL; + if (arg) goto out; - r = kvm_vcpu_ioctl_run(vcpu, &kvm_run); - if (r < 0 && r != -EINTR) - goto out; - if (copy_to_user(argp, &kvm_run, sizeof kvm_run)) { - r = -EFAULT; - goto out; - } + r = kvm_vcpu_ioctl_run(vcpu, vcpu->run); break; - } case KVM_GET_REGS: { struct kvm_regs kvm_regs; @@ -2113,6 +2554,66 @@ static long kvm_vcpu_ioctl(struct file *filp, case KVM_SET_MSRS: r = msr_io(vcpu, argp, do_set_msr, 0); break; + case KVM_SET_CPUID: { + struct kvm_cpuid __user *cpuid_arg = argp; + struct kvm_cpuid cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); + if (r) + goto out; + break; + } + case KVM_SET_SIGNAL_MASK: { + struct kvm_signal_mask __user *sigmask_arg = argp; + struct kvm_signal_mask kvm_sigmask; + sigset_t sigset, *p; + + p = NULL; + if (argp) { + r = -EFAULT; + if (copy_from_user(&kvm_sigmask, argp, + sizeof kvm_sigmask)) + goto out; + r = -EINVAL; + if (kvm_sigmask.len != sizeof sigset) + goto out; + r = -EFAULT; + if (copy_from_user(&sigset, sigmask_arg->sigset, + sizeof sigset)) + goto out; + p = &sigset; + } + r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); + break; + } + case KVM_GET_FPU: { + struct kvm_fpu fpu; + + memset(&fpu, 0, sizeof fpu); + r = kvm_vcpu_ioctl_get_fpu(vcpu, &fpu); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &fpu, sizeof fpu)) + goto out; + r = 0; + break; + } + case KVM_SET_FPU: { + struct kvm_fpu fpu; + + r = -EFAULT; + if (copy_from_user(&fpu, argp, sizeof fpu)) + goto out; + r = kvm_vcpu_ioctl_set_fpu(vcpu, &fpu); + if (r) + goto out; + r = 0; + break; + } default: ; } @@ -2155,6 +2656,17 @@ static long kvm_vm_ioctl(struct file *filp, goto out; break; } + case KVM_SET_MEMORY_ALIAS: { + struct kvm_memory_alias alias; + + r = -EFAULT; + if (copy_from_user(&alias, argp, sizeof alias)) + goto out; + r = kvm_vm_ioctl_set_memory_alias(kvm, &alias); + if (r) + goto out; + break; + } default: ; } @@ -2168,15 +2680,11 @@ static struct page *kvm_vm_nopage(struct vm_area_struct *vma, { struct kvm *kvm = vma->vm_file->private_data; unsigned long pgoff; - struct kvm_memory_slot *slot; struct page *page; *type = VM_FAULT_MINOR; pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - slot = gfn_to_memslot(kvm, pgoff); - if (!slot) - return NOPAGE_SIGBUS; - page = gfn_to_page(slot, pgoff); + page = gfn_to_page(kvm, pgoff); if (!page) return NOPAGE_SIGBUS; get_page(page); @@ -2248,13 +2756,19 @@ static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; - int r = -EINVAL; + long r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: + r = -EINVAL; + if (arg) + goto out; r = KVM_API_VERSION; break; case KVM_CREATE_VM: + r = -EINVAL; + if (arg) + goto out; r = kvm_dev_ioctl_create_vm(); break; case KVM_GET_MSR_INDEX_LIST: { @@ -2284,6 +2798,18 @@ static long kvm_dev_ioctl(struct file *filp, r = 0; break; } + case KVM_CHECK_EXTENSION: + /* + * No extensions defined at present. + */ + r = 0; + break; + case KVM_GET_VCPU_MMAP_SIZE: + r = -EINVAL; + if (arg) + goto out; + r = 2 * PAGE_SIZE; + break; default: ; } @@ -2299,7 +2825,7 @@ static struct file_operations kvm_chardev_ops = { }; static struct miscdevice kvm_dev = { - MISC_DYNAMIC_MINOR, + KVM_MINOR, "kvm", &kvm_chardev_ops, }; @@ -2385,14 +2911,39 @@ static struct notifier_block kvm_cpu_notifier = { .priority = 20, /* must be > scheduler priority */ }; +static u64 stat_get(void *_offset) +{ + unsigned offset = (long)_offset; + u64 total = 0; + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i; + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + vcpu = &kvm->vcpus[i]; + total += *(u32 *)((void *)vcpu + offset); + } + spin_unlock(&kvm_lock); + return total; +} + +static void stat_set(void *offset, u64 val) +{ +} + +DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, stat_set, "%llu\n"); + static __init void kvm_init_debug(void) { struct kvm_stats_debugfs_item *p; debugfs_dir = debugfs_create_dir("kvm", NULL); for (p = debugfs_entries; p->name; ++p) - p->dentry = debugfs_create_u32(p->name, 0444, debugfs_dir, - p->data); + p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir, + (void *)(long)p->offset, + &stat_fops); } static void kvm_exit_debug(void) @@ -2522,6 +3073,10 @@ static __init int kvm_init(void) static struct page *bad_page; int r; + r = kvm_mmu_module_init(); + if (r) + goto out4; + r = register_filesystem(&kvm_fs_type); if (r) goto out3; @@ -2550,6 +3105,8 @@ out: out2: unregister_filesystem(&kvm_fs_type); out3: + kvm_mmu_module_exit(); +out4: return r; } @@ -2559,6 +3116,7 @@ static __exit void kvm_exit(void) __free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT)); mntput(kvmfs_mnt); unregister_filesystem(&kvm_fs_type); + kvm_mmu_module_exit(); } module_init(kvm_init) diff --git a/drivers/kvm/kvm_svm.h b/drivers/kvm/kvm_svm.h index 624f1ca4865..a869983d683 100644 --- a/drivers/kvm/kvm_svm.h +++ b/drivers/kvm/kvm_svm.h @@ -9,17 +9,15 @@ #include "svm.h" #include "kvm.h" -static const u32 host_save_msrs[] = { +static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, - MSR_FS_BASE, MSR_GS_BASE, + MSR_FS_BASE, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_IA32_DEBUGCTLMSR, /*MSR_IA32_LASTBRANCHFROMIP, - MSR_IA32_LASTBRANCHTOIP, MSR_IA32_LASTINTFROMIP,MSR_IA32_LASTINTTOIP,*/ }; -#define NR_HOST_SAVE_MSRS ARRAY_SIZE(host_save_msrs) +#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) #define NUM_DB_REGS 4 struct vcpu_svm { @@ -28,13 +26,12 @@ struct vcpu_svm { struct svm_cpu_data *svm_data; uint64_t asid_generation; - unsigned long cr0; - unsigned long cr4; unsigned long db_regs[NUM_DB_REGS]; u64 next_rip; - u64 host_msrs[NR_HOST_SAVE_MSRS]; + u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; + u64 host_gs_base; unsigned long host_cr2; unsigned long host_db_regs[NUM_DB_REGS]; unsigned long host_dr6; diff --git a/drivers/kvm/kvm_vmx.h b/drivers/kvm/kvm_vmx.h deleted file mode 100644 index d139f73fb6e..00000000000 --- a/drivers/kvm/kvm_vmx.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __KVM_VMX_H -#define __KVM_VMX_H - -#ifdef CONFIG_X86_64 -/* - * avoid save/load MSR_SYSCALL_MASK and MSR_LSTAR by std vt - * mechanism (cpu bug AA24) - */ -#define NR_BAD_MSRS 2 -#else -#define NR_BAD_MSRS 0 -#endif - -#endif diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c index cab26f301ea..e8e228118de 100644 --- a/drivers/kvm/mmu.c +++ b/drivers/kvm/mmu.c @@ -52,11 +52,15 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {} static int dbg = 1; #endif +#ifndef MMU_DEBUG +#define ASSERT(x) do { } while (0) +#else #define ASSERT(x) \ if (!(x)) { \ printk(KERN_WARNING "assertion failed %s:%d: %s\n", \ __FILE__, __LINE__, #x); \ } +#endif #define PT64_PT_BITS 9 #define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS) @@ -159,6 +163,9 @@ struct kvm_rmap_desc { struct kvm_rmap_desc *more; }; +static struct kmem_cache *pte_chain_cache; +static struct kmem_cache *rmap_desc_cache; + static int is_write_protection(struct kvm_vcpu *vcpu) { return vcpu->cr0 & CR0_WP_MASK; @@ -196,14 +203,15 @@ static int is_rmap_pte(u64 pte) } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, - size_t objsize, int min) + struct kmem_cache *base_cache, int min, + gfp_t gfp_flags) { void *obj; if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - obj = kzalloc(objsize, GFP_NOWAIT); + obj = kmem_cache_zalloc(base_cache, gfp_flags); if (!obj) return -ENOMEM; cache->objects[cache->nobjs++] = obj; @@ -217,20 +225,35 @@ static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) kfree(mc->objects[--mc->nobjs]); } -static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) +static int __mmu_topup_memory_caches(struct kvm_vcpu *vcpu, gfp_t gfp_flags) { int r; r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache, - sizeof(struct kvm_pte_chain), 4); + pte_chain_cache, 4, gfp_flags); if (r) goto out; r = mmu_topup_memory_cache(&vcpu->mmu_rmap_desc_cache, - sizeof(struct kvm_rmap_desc), 1); + rmap_desc_cache, 1, gfp_flags); out: return r; } +static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) +{ + int r; + + r = __mmu_topup_memory_caches(vcpu, GFP_NOWAIT); + if (r < 0) { + spin_unlock(&vcpu->kvm->lock); + kvm_arch_ops->vcpu_put(vcpu); + r = __mmu_topup_memory_caches(vcpu, GFP_KERNEL); + kvm_arch_ops->vcpu_load(vcpu); + spin_lock(&vcpu->kvm->lock); + } + return r; +} + static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) { mmu_free_memory_cache(&vcpu->mmu_pte_chain_cache); @@ -390,13 +413,11 @@ static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm *kvm = vcpu->kvm; struct page *page; - struct kvm_memory_slot *slot; struct kvm_rmap_desc *desc; u64 *spte; - slot = gfn_to_memslot(kvm, gfn); - BUG_ON(!slot); - page = gfn_to_page(slot, gfn); + page = gfn_to_page(kvm, gfn); + BUG_ON(!page); while (page_private(page)) { if (!(page_private(page) & 1)) @@ -417,6 +438,7 @@ static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) } } +#ifdef MMU_DEBUG static int is_empty_shadow_page(hpa_t page_hpa) { u64 *pos; @@ -431,15 +453,15 @@ static int is_empty_shadow_page(hpa_t page_hpa) } return 1; } +#endif static void kvm_mmu_free_page(struct kvm_vcpu *vcpu, hpa_t page_hpa) { struct kvm_mmu_page *page_head = page_header(page_hpa); ASSERT(is_empty_shadow_page(page_hpa)); - list_del(&page_head->link); page_head->page_hpa = page_hpa; - list_add(&page_head->link, &vcpu->free_pages); + list_move(&page_head->link, &vcpu->free_pages); ++vcpu->kvm->n_free_mmu_pages; } @@ -457,11 +479,9 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, return NULL; page = list_entry(vcpu->free_pages.next, struct kvm_mmu_page, link); - list_del(&page->link); - list_add(&page->link, &vcpu->kvm->active_mmu_pages); + list_move(&page->link, &vcpu->kvm->active_mmu_pages); ASSERT(is_empty_shadow_page(page->page_hpa)); page->slot_bitmap = 0; - page->global = 1; page->multimapped = 0; page->parent_pte = parent_pte; --vcpu->kvm->n_free_mmu_pages; @@ -569,6 +589,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int metaphysical, + unsigned hugepage_access, u64 *parent_pte) { union kvm_mmu_page_role role; @@ -582,6 +603,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role.glevels = vcpu->mmu.root_level; role.level = level; role.metaphysical = metaphysical; + role.hugepage_access = hugepage_access; if (vcpu->mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; @@ -669,10 +691,8 @@ static void kvm_mmu_zap_page(struct kvm_vcpu *vcpu, if (!page->root_count) { hlist_del(&page->hash_link); kvm_mmu_free_page(vcpu, page->page_hpa); - } else { - list_del(&page->link); - list_add(&page->link, &vcpu->kvm->active_mmu_pages); - } + } else + list_move(&page->link, &vcpu->kvm->active_mmu_pages); } static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -714,14 +734,12 @@ hpa_t safe_gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa) hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - struct kvm_memory_slot *slot; struct page *page; ASSERT((gpa & HPA_ERR_MASK) == 0); - slot = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!slot) + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + if (!page) return gpa | HPA_ERR_MASK; - page = gfn_to_page(slot, gpa >> PAGE_SHIFT); return ((hpa_t)page_to_pfn(page) << PAGE_SHIFT) | (gpa & (PAGE_SIZE-1)); } @@ -735,6 +753,15 @@ hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva) return gpa_to_hpa(vcpu, gpa); } +struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva); + + if (gpa == UNMAPPED_GVA) + return NULL; + return pfn_to_page(gpa_to_hpa(vcpu, gpa) >> PAGE_SHIFT); +} + static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } @@ -772,7 +799,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, hpa_t p) >> PAGE_SHIFT; new_table = kvm_mmu_get_page(vcpu, pseudo_gfn, v, level - 1, - 1, &table[index]); + 1, 0, &table[index]); if (!new_table) { pgprintk("nonpaging_map: ENOMEM\n"); return -ENOMEM; @@ -804,10 +831,12 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) for (i = 0; i < 4; ++i) { hpa_t root = vcpu->mmu.pae_root[i]; - ASSERT(VALID_PAGE(root)); - root &= PT64_BASE_ADDR_MASK; - page = page_header(root); - --page->root_count; + if (root) { + ASSERT(VALID_PAGE(root)); + root &= PT64_BASE_ADDR_MASK; + page = page_header(root); + --page->root_count; + } vcpu->mmu.pae_root[i] = INVALID_PAGE; } vcpu->mmu.root_hpa = INVALID_PAGE; @@ -827,7 +856,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); page = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, NULL); + PT64_ROOT_LEVEL, 0, 0, NULL); root = page->page_hpa; ++page->root_count; vcpu->mmu.root_hpa = root; @@ -838,13 +867,17 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->mmu.pae_root[i]; ASSERT(!VALID_PAGE(root)); - if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL) + if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL) { + if (!is_present_pte(vcpu->pdptrs[i])) { + vcpu->mmu.pae_root[i] = 0; + continue; + } root_gfn = vcpu->pdptrs[i] >> PAGE_SHIFT; - else if (vcpu->mmu.root_level == 0) + } else if (vcpu->mmu.root_level == 0) root_gfn = 0; page = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, !is_paging(vcpu), - NULL); + 0, NULL); root = page->page_hpa; ++page->root_count; vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK; @@ -903,7 +936,7 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu) static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - ++kvm_stat.tlb_flush; + ++vcpu->stat.tlb_flush; kvm_arch_ops->tlb_flush(vcpu); } @@ -918,11 +951,6 @@ static void paging_new_cr3(struct kvm_vcpu *vcpu) kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa); } -static void mark_pagetable_nonglobal(void *shadow_pte) -{ - page_header(__pa(shadow_pte))->global = 0; -} - static inline void set_pte_common(struct kvm_vcpu *vcpu, u64 *shadow_pte, gpa_t gaddr, @@ -940,9 +968,6 @@ static inline void set_pte_common(struct kvm_vcpu *vcpu, *shadow_pte |= access_bits; - if (!(*shadow_pte & PT_GLOBAL_MASK)) - mark_pagetable_nonglobal(shadow_pte); - if (is_error_hpa(paddr)) { *shadow_pte |= gaddr; *shadow_pte |= PT_SHADOW_IO_MARK; @@ -1316,6 +1341,51 @@ void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot) } } +void kvm_mmu_zap_all(struct kvm_vcpu *vcpu) +{ + destroy_kvm_mmu(vcpu); + + while (!list_empty(&vcpu->kvm->active_mmu_pages)) { + struct kvm_mmu_page *page; + + page = container_of(vcpu->kvm->active_mmu_pages.next, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(vcpu, page); + } + + mmu_free_memory_caches(vcpu); + kvm_arch_ops->tlb_flush(vcpu); + init_kvm_mmu(vcpu); +} + +void kvm_mmu_module_exit(void) +{ + if (pte_chain_cache) + kmem_cache_destroy(pte_chain_cache); + if (rmap_desc_cache) + kmem_cache_destroy(rmap_desc_cache); +} + +int kvm_mmu_module_init(void) +{ + pte_chain_cache = kmem_cache_create("kvm_pte_chain", + sizeof(struct kvm_pte_chain), + 0, 0, NULL, NULL); + if (!pte_chain_cache) + goto nomem; + rmap_desc_cache = kmem_cache_create("kvm_rmap_desc", + sizeof(struct kvm_rmap_desc), + 0, 0, NULL, NULL); + if (!rmap_desc_cache) + goto nomem; + + return 0; + +nomem: + kvm_mmu_module_exit(); + return -ENOMEM; +} + #ifdef AUDIT static const char *audit_msg; @@ -1338,7 +1408,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) { u64 ent = pt[i]; - if (!ent & PT_PRESENT_MASK) + if (!(ent & PT_PRESENT_MASK)) continue; va = canonicalize(va); @@ -1360,7 +1430,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, static void audit_mappings(struct kvm_vcpu *vcpu) { - int i; + unsigned i; if (vcpu->mmu.root_level == 4) audit_mappings_page(vcpu, vcpu->mmu.root_hpa, 0, 4); diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h index f3bcee90465..73ffbffb109 100644 --- a/drivers/kvm/paging_tmpl.h +++ b/drivers/kvm/paging_tmpl.h @@ -148,8 +148,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, break; } - if (walker->level != 3 || is_long_mode(vcpu)) - walker->inherited_ar &= walker->table[index]; + walker->inherited_ar &= walker->table[index]; table_gfn = (*ptep & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; paddr = safe_gpa_to_hpa(vcpu, *ptep & PT_BASE_ADDR_MASK); kunmap_atomic(walker->table, KM_USER0); @@ -248,6 +247,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, u64 shadow_pte; int metaphysical; gfn_t table_gfn; + unsigned hugepage_access = 0; if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) { if (level == PT_PAGE_TABLE_LEVEL) @@ -277,6 +277,9 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (level - 1 == PT_PAGE_TABLE_LEVEL && walker->level == PT_DIRECTORY_LEVEL) { metaphysical = 1; + hugepage_access = *guest_ent; + hugepage_access &= PT_USER_MASK | PT_WRITABLE_MASK; + hugepage_access >>= PT_WRITABLE_SHIFT; table_gfn = (*guest_ent & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; } else { @@ -284,7 +287,8 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, table_gfn = walker->table_gfn[level - 2]; } shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, - metaphysical, shadow_ent); + metaphysical, hugepage_access, + shadow_ent); shadow_addr = shadow_page->page_hpa; shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; @@ -444,7 +448,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, if (is_io_pte(*shadow_pte)) return 1; - ++kvm_stat.pf_fixed; + ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, "post page fault (fixed)"); return write_pt; diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c index 3d8ea7ac2ec..9c15f32eea1 100644 --- a/drivers/kvm/svm.c +++ b/drivers/kvm/svm.c @@ -44,6 +44,10 @@ MODULE_LICENSE("GPL"); #define KVM_EFER_LMA (1 << 10) #define KVM_EFER_LME (1 << 8) +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_DEATURE_SVML (1 << 2) + unsigned long iopm_base; unsigned long msrpm_base; @@ -59,15 +63,16 @@ struct kvm_ldttss_desc { struct svm_cpu_data { int cpu; - uint64_t asid_generation; - uint32_t max_asid; - uint32_t next_asid; + u64 asid_generation; + u32 max_asid; + u32 next_asid; struct kvm_ldttss_desc *tss_desc; struct page *save_area; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +static uint32_t svm_features; struct svm_init_data { int cpu; @@ -82,6 +87,11 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define MAX_INST_SIZE 15 +static inline u32 svm_has(u32 feat) +{ + return svm_features & feat; +} + static unsigned get_addr_size(struct kvm_vcpu *vcpu) { struct vmcb_save_area *sa = &vcpu->svm->vmcb->save; @@ -203,13 +213,6 @@ static void inject_ud(struct kvm_vcpu *vcpu) UD_VECTOR; } -static void inject_db(struct kvm_vcpu *vcpu) -{ - vcpu->svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | - SVM_EVTINJ_TYPE_EXEPT | - DB_VECTOR; -} - static int is_page_fault(uint32_t info) { info &= SVM_EVTINJ_VEC_MASK | SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; @@ -309,6 +312,7 @@ static void svm_hardware_enable(void *garbage) svm_data->asid_generation = 1; svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; svm_data->next_asid = svm_data->max_asid + 1; + svm_features = cpuid_edx(SVM_CPUID_FUNC); asm volatile ( "sgdt %0" : "=m"(gdt_descr) ); gdt = (struct desc_struct *)gdt_descr.address; @@ -459,7 +463,6 @@ static void init_vmcb(struct vmcb *vmcb) { struct vmcb_control_area *control = &vmcb->control; struct vmcb_save_area *save = &vmcb->save; - u64 tsc; control->intercept_cr_read = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | @@ -511,12 +514,13 @@ static void init_vmcb(struct vmcb *vmcb) (1ULL << INTERCEPT_VMSAVE) | (1ULL << INTERCEPT_STGI) | (1ULL << INTERCEPT_CLGI) | - (1ULL << INTERCEPT_SKINIT); + (1ULL << INTERCEPT_SKINIT) | + (1ULL << INTERCEPT_MONITOR) | + (1ULL << INTERCEPT_MWAIT); control->iopm_base_pa = iopm_base; control->msrpm_base_pa = msrpm_base; - rdtscll(tsc); - control->tsc_offset = -tsc; + control->tsc_offset = 0; control->int_ctl = V_INTR_MASKING_MASK; init_seg(&save->es); @@ -576,12 +580,15 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) vcpu->svm->vmcb = page_address(page); memset(vcpu->svm->vmcb, 0, PAGE_SIZE); vcpu->svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; - vcpu->svm->cr0 = 0x00000010; vcpu->svm->asid_generation = 0; memset(vcpu->svm->db_regs, 0, sizeof(vcpu->svm->db_regs)); init_vmcb(vcpu->svm->vmcb); fx_init(vcpu); + vcpu->fpu_active = 1; + vcpu->apic_base = 0xfee00000 | + /*for vcpu 0*/ MSR_IA32_APICBASE_BSP | + MSR_IA32_APICBASE_ENABLE; return 0; @@ -602,11 +609,34 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) static void svm_vcpu_load(struct kvm_vcpu *vcpu) { - get_cpu(); + int cpu, i; + + cpu = get_cpu(); + if (unlikely(cpu != vcpu->cpu)) { + u64 tsc_this, delta; + + /* + * Make sure that the guest sees a monotonically + * increasing TSC. + */ + rdtscll(tsc_this); + delta = vcpu->host_tsc - tsc_this; + vcpu->svm->vmcb->control.tsc_offset += delta; + vcpu->cpu = cpu; + } + + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + rdmsrl(host_save_user_msrs[i], vcpu->svm->host_user_msrs[i]); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) { + int i; + + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + wrmsrl(host_save_user_msrs[i], vcpu->svm->host_user_msrs[i]); + + rdtscll(vcpu->host_tsc); put_cpu(); } @@ -714,7 +744,7 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) vcpu->svm->vmcb->save.gdtr.base = dt->base ; } -static void svm_decache_cr0_cr4_guest_bits(struct kvm_vcpu *vcpu) +static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } @@ -733,9 +763,15 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } } #endif - vcpu->svm->cr0 = cr0; - vcpu->svm->vmcb->save.cr0 = cr0 | CR0_PG_MASK | CR0_WP_MASK; + if ((vcpu->cr0 & CR0_TS_MASK) && !(cr0 & CR0_TS_MASK)) { + vcpu->svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + vcpu->fpu_active = 1; + } + vcpu->cr0 = cr0; + cr0 |= CR0_PG_MASK | CR0_WP_MASK; + cr0 &= ~(CR0_CD_MASK | CR0_NW_MASK); + vcpu->svm->vmcb->save.cr0 = cr0; } static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -785,18 +821,16 @@ static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) static void load_host_msrs(struct kvm_vcpu *vcpu) { - int i; - - for ( i = 0; i < NR_HOST_SAVE_MSRS; i++) - wrmsrl(host_save_msrs[i], vcpu->svm->host_msrs[i]); +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, vcpu->svm->host_gs_base); +#endif } static void save_host_msrs(struct kvm_vcpu *vcpu) { - int i; - - for ( i = 0; i < NR_HOST_SAVE_MSRS; i++) - rdmsrl(host_save_msrs[i], vcpu->svm->host_msrs[i]); +#ifdef CONFIG_X86_64 + rdmsrl(MSR_GS_BASE, vcpu->svm->host_gs_base); +#endif } static void new_asid(struct kvm_vcpu *vcpu, struct svm_cpu_data *svm_data) @@ -890,7 +924,7 @@ static int pf_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) case EMULATE_DONE: return 1; case EMULATE_DO_MMIO: - ++kvm_stat.mmio_exits; + ++vcpu->stat.mmio_exits; kvm_run->exit_reason = KVM_EXIT_MMIO; return 0; case EMULATE_FAIL: @@ -904,6 +938,16 @@ static int pf_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } +static int nm_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + vcpu->svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + if (!(vcpu->cr0 & CR0_TS_MASK)) + vcpu->svm->vmcb->save.cr0 &= ~CR0_TS_MASK; + vcpu->fpu_active = 1; + + return 1; +} + static int shutdown_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { /* @@ -981,7 +1025,7 @@ static int io_get_override(struct kvm_vcpu *vcpu, return 0; } -static unsigned long io_adress(struct kvm_vcpu *vcpu, int ins, u64 *address) +static unsigned long io_adress(struct kvm_vcpu *vcpu, int ins, gva_t *address) { unsigned long addr_mask; unsigned long *reg; @@ -1025,38 +1069,38 @@ static unsigned long io_adress(struct kvm_vcpu *vcpu, int ins, u64 *address) static int io_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 io_info = vcpu->svm->vmcb->control.exit_info_1; //address size bug? - int _in = io_info & SVM_IOIO_TYPE_MASK; + int size, down, in, string, rep; + unsigned port; + unsigned long count; + gva_t address = 0; - ++kvm_stat.io_exits; + ++vcpu->stat.io_exits; vcpu->svm->next_rip = vcpu->svm->vmcb->control.exit_info_2; - kvm_run->exit_reason = KVM_EXIT_IO; - kvm_run->io.port = io_info >> 16; - kvm_run->io.direction = (_in) ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - kvm_run->io.size = ((io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT); - kvm_run->io.string = (io_info & SVM_IOIO_STR_MASK) != 0; - kvm_run->io.rep = (io_info & SVM_IOIO_REP_MASK) != 0; + in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + port = io_info >> 16; + size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; + string = (io_info & SVM_IOIO_STR_MASK) != 0; + rep = (io_info & SVM_IOIO_REP_MASK) != 0; + count = 1; + down = (vcpu->svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; - if (kvm_run->io.string) { + if (string) { unsigned addr_mask; - addr_mask = io_adress(vcpu, _in, &kvm_run->io.address); + addr_mask = io_adress(vcpu, in, &address); if (!addr_mask) { printk(KERN_DEBUG "%s: get io address failed\n", __FUNCTION__); return 1; } - if (kvm_run->io.rep) { - kvm_run->io.count - = vcpu->regs[VCPU_REGS_RCX] & addr_mask; - kvm_run->io.string_down = (vcpu->svm->vmcb->save.rflags - & X86_EFLAGS_DF) != 0; - } - } else - kvm_run->io.value = vcpu->svm->vmcb->save.rax; - return 0; + if (rep) + count = vcpu->regs[VCPU_REGS_RCX] & addr_mask; + } + return kvm_setup_pio(vcpu, kvm_run, in, size, count, string, down, + address, rep, port); } static int nop_on_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -1072,13 +1116,14 @@ static int halt_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; kvm_run->exit_reason = KVM_EXIT_HLT; - ++kvm_stat.halt_exits; + ++vcpu->stat.halt_exits; return 0; } static int vmmcall_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - vcpu->svm->vmcb->save.rip += 3; + vcpu->svm->next_rip = vcpu->svm->vmcb->save.rip + 3; + skip_emulated_instruction(vcpu); return kvm_hypercall(vcpu, kvm_run); } @@ -1098,8 +1143,8 @@ static int task_switch_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_r static int cpuid_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { vcpu->svm->next_rip = vcpu->svm->vmcb->save.rip + 2; - kvm_run->exit_reason = KVM_EXIT_CPUID; - return 0; + kvm_emulate_cpuid(vcpu); + return 1; } static int emulate_on_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -1239,7 +1284,7 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu, */ if (kvm_run->request_interrupt_window && !vcpu->irq_summary) { - ++kvm_stat.irq_window_exits; + ++vcpu->stat.irq_window_exits; kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; return 0; } @@ -1267,6 +1312,7 @@ static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu, [SVM_EXIT_WRITE_DR5] = emulate_on_interception, [SVM_EXIT_WRITE_DR7] = emulate_on_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_INTR] = nop_on_interception, [SVM_EXIT_NMI] = nop_on_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -1288,6 +1334,8 @@ static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu, [SVM_EXIT_STGI] = invalid_op_interception, [SVM_EXIT_CLGI] = invalid_op_interception, [SVM_EXIT_SKINIT] = invalid_op_interception, + [SVM_EXIT_MONITOR] = invalid_op_interception, + [SVM_EXIT_MWAIT] = invalid_op_interception, }; @@ -1295,8 +1343,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 exit_code = vcpu->svm->vmcb->control.exit_code; - kvm_run->exit_type = KVM_EXIT_TYPE_VM_EXIT; - if (is_external_interrupt(vcpu->svm->vmcb->control.exit_int_info) && exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR) printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " @@ -1307,12 +1353,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || svm_exit_handlers[exit_code] == 0) { kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - printk(KERN_ERR "%s: 0x%x @ 0x%llx cr0 0x%lx rflags 0x%llx\n", - __FUNCTION__, - exit_code, - vcpu->svm->vmcb->save.rip, - vcpu->cr0, - vcpu->svm->vmcb->save.rflags); + kvm_run->hw.hardware_exit_reason = exit_code; return 0; } @@ -1461,8 +1502,10 @@ again: load_db_regs(vcpu->svm->db_regs); } - fx_save(vcpu->host_fx_image); - fx_restore(vcpu->guest_fx_image); + if (vcpu->fpu_active) { + fx_save(vcpu->host_fx_image); + fx_restore(vcpu->guest_fx_image); + } asm volatile ( #ifdef CONFIG_X86_64 @@ -1573,8 +1616,10 @@ again: #endif : "cc", "memory" ); - fx_save(vcpu->guest_fx_image); - fx_restore(vcpu->host_fx_image); + if (vcpu->fpu_active) { + fx_save(vcpu->guest_fx_image); + fx_restore(vcpu->host_fx_image); + } if ((vcpu->svm->vmcb->save.dr7 & 0xff)) load_db_regs(vcpu->svm->host_db_regs); @@ -1606,8 +1651,9 @@ again: vcpu->svm->next_rip = 0; if (vcpu->svm->vmcb->control.exit_code == SVM_EXIT_ERR) { - kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY; - kvm_run->exit_reason = vcpu->svm->vmcb->control.exit_code; + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + kvm_run->fail_entry.hardware_entry_failure_reason + = vcpu->svm->vmcb->control.exit_code; post_kvm_run_save(vcpu, kvm_run); return 0; } @@ -1615,14 +1661,16 @@ again: r = handle_exit(vcpu, kvm_run); if (r > 0) { if (signal_pending(current)) { - ++kvm_stat.signal_exits; + ++vcpu->stat.signal_exits; post_kvm_run_save(vcpu, kvm_run); + kvm_run->exit_reason = KVM_EXIT_INTR; return -EINTR; } if (dm_request_for_irq_injection(vcpu, kvm_run)) { - ++kvm_stat.request_irq_exits; + ++vcpu->stat.request_irq_exits; post_kvm_run_save(vcpu, kvm_run); + kvm_run->exit_reason = KVM_EXIT_INTR; return -EINTR; } kvm_resched(vcpu); @@ -1641,6 +1689,12 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { vcpu->svm->vmcb->save.cr3 = root; force_new_asid(vcpu); + + if (vcpu->fpu_active) { + vcpu->svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + vcpu->svm->vmcb->save.cr0 |= CR0_TS_MASK; + vcpu->fpu_active = 0; + } } static void svm_inject_page_fault(struct kvm_vcpu *vcpu, @@ -1649,7 +1703,7 @@ static void svm_inject_page_fault(struct kvm_vcpu *vcpu, { uint32_t exit_int_info = vcpu->svm->vmcb->control.exit_int_info; - ++kvm_stat.pf_guest; + ++vcpu->stat.pf_guest; if (is_page_fault(exit_int_info)) { @@ -1709,9 +1763,8 @@ static struct kvm_arch_ops svm_arch_ops = { .get_segment = svm_get_segment, .set_segment = svm_set_segment, .get_cs_db_l_bits = svm_get_cs_db_l_bits, - .decache_cr0_cr4_guest_bits = svm_decache_cr0_cr4_guest_bits, + .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, - .set_cr0_no_modeswitch = svm_set_cr0, .set_cr3 = svm_set_cr3, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, diff --git a/drivers/kvm/svm.h b/drivers/kvm/svm.h index df731c3fb58..5e93814400c 100644 --- a/drivers/kvm/svm.h +++ b/drivers/kvm/svm.h @@ -44,6 +44,9 @@ enum { INTERCEPT_RDTSCP, INTERCEPT_ICEBP, INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, }; @@ -298,6 +301,9 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXIT_RDTSCP 0x087 #define SVM_EXIT_ICEBP 0x088 #define SVM_EXIT_WBINVD 0x089 +#define SVM_EXIT_MONITOR 0x08a +#define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_ERR -1 diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c index fbbf9d6b299..724db0027f0 100644 --- a/drivers/kvm/vmx.c +++ b/drivers/kvm/vmx.c @@ -17,7 +17,6 @@ #include "kvm.h" #include "vmx.h" -#include "kvm_vmx.h" #include <linux/module.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -70,6 +69,10 @@ static struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +/* + * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it + * away by decrementing the array size. + */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, @@ -78,6 +81,19 @@ static const u32 vmx_msr_index[] = { }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) +#ifdef CONFIG_X86_64 +static unsigned msr_offset_kernel_gs_base; +#define NR_64BIT_MSRS 4 +/* + * avoid save/load MSR_SYSCALL_MASK and MSR_LSTAR by std vt + * mechanism (cpu bug AA24) + */ +#define NR_BAD_MSRS 2 +#else +#define NR_64BIT_MSRS 0 +#define NR_BAD_MSRS 0 +#endif + static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | @@ -85,6 +101,13 @@ static inline int is_page_fault(u32 intr_info) (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } +static inline int is_no_device(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | + INTR_INFO_VALID_MASK)) == + (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); +} + static inline int is_external_interrupt(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) @@ -200,6 +223,16 @@ static void vmcs_write64(unsigned long field, u64 value) #endif } +static void vmcs_clear_bits(unsigned long field, u32 mask) +{ + vmcs_writel(field, vmcs_readl(field) & ~mask); +} + +static void vmcs_set_bits(unsigned long field, u32 mask) +{ + vmcs_writel(field, vmcs_readl(field) | mask); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -297,6 +330,44 @@ static void vmx_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code) } /* + * Set up the vmcs to automatically save and restore system + * msrs. Don't touch the 64-bit msrs if the guest is in legacy + * mode, as fiddling with msrs is very expensive. + */ +static void setup_msrs(struct kvm_vcpu *vcpu) +{ + int nr_skip, nr_good_msrs; + + if (is_long_mode(vcpu)) + nr_skip = NR_BAD_MSRS; + else + nr_skip = NR_64BIT_MSRS; + nr_good_msrs = vcpu->nmsrs - nr_skip; + + /* + * MSR_K6_STAR is only needed on long mode guests, and only + * if efer.sce is enabled. + */ + if (find_msr_entry(vcpu, MSR_K6_STAR)) { + --nr_good_msrs; +#ifdef CONFIG_X86_64 + if (is_long_mode(vcpu) && (vcpu->shadow_efer & EFER_SCE)) + ++nr_good_msrs; +#endif + } + + vmcs_writel(VM_ENTRY_MSR_LOAD_ADDR, + virt_to_phys(vcpu->guest_msrs + nr_skip)); + vmcs_writel(VM_EXIT_MSR_STORE_ADDR, + virt_to_phys(vcpu->guest_msrs + nr_skip)); + vmcs_writel(VM_EXIT_MSR_LOAD_ADDR, + virt_to_phys(vcpu->host_msrs + nr_skip)); + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, nr_good_msrs); /* 22.2.2 */ + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */ + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */ +} + +/* * reads and returns guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset -- 21.3 */ @@ -712,6 +783,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); vmcs_write32(GUEST_CS_LIMIT, 0xffff); + if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) + vmcs_writel(GUEST_CS_BASE, 0xf0000); vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); fix_rmode_seg(VCPU_SREG_ES, &vcpu->rmode.es); @@ -754,11 +827,8 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_decache_cr0_cr4_guest_bits(struct kvm_vcpu *vcpu) +static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { - vcpu->cr0 &= KVM_GUEST_CR0_MASK; - vcpu->cr0 |= vmcs_readl(GUEST_CR0) & ~KVM_GUEST_CR0_MASK; - vcpu->cr4 &= KVM_GUEST_CR4_MASK; vcpu->cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK; } @@ -780,22 +850,11 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif - vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, - (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON); - vcpu->cr0 = cr0; -} - -/* - * Used when restoring the VM to avoid corrupting segment registers - */ -static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - if (!vcpu->rmode.active && !(cr0 & CR0_PE_MASK)) - enter_rmode(vcpu); + if (!(cr0 & CR0_TS_MASK)) { + vcpu->fpu_active = 1; + vmcs_clear_bits(EXCEPTION_BITMAP, CR0_TS_MASK); + } - vcpu->rmode.active = ((cr0 & CR0_PE_MASK) == 0); - update_exception_bitmap(vcpu); vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON); @@ -805,6 +864,12 @@ static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0) static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { vmcs_writel(GUEST_CR3, cr3); + + if (!(vcpu->cr0 & CR0_TS_MASK)) { + vcpu->fpu_active = 0; + vmcs_set_bits(GUEST_CR0, CR0_TS_MASK); + vmcs_set_bits(EXCEPTION_BITMAP, 1 << NM_VECTOR); + } } static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -835,6 +900,7 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) msr->data = efer & ~EFER_LME; } + setup_msrs(vcpu); } #endif @@ -878,7 +944,14 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); - if (var->unusable) + if (vcpu->rmode.active && var->s) { + /* + * Hack real-mode segments into vm86 compatibility. + */ + if (var->base == 0xffff0000 && var->selector == 0xf000) + vmcs_writel(sf->base, 0xf0000); + ar = 0xf3; + } else if (var->unusable) ar = 1 << 16; else { ar = var->type & 15; @@ -933,9 +1006,9 @@ static int init_rmode_tss(struct kvm* kvm) gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT; char *page; - p1 = _gfn_to_page(kvm, fn++); - p2 = _gfn_to_page(kvm, fn++); - p3 = _gfn_to_page(kvm, fn); + p1 = gfn_to_page(kvm, fn++); + p2 = gfn_to_page(kvm, fn++); + p3 = gfn_to_page(kvm, fn); if (!p1 || !p2 || !p3) { kvm_printf(kvm,"%s: gfn_to_page failed\n", __FUNCTION__); @@ -991,7 +1064,6 @@ static int vmx_vcpu_setup(struct kvm_vcpu *vcpu) struct descriptor_table dt; int i; int ret = 0; - int nr_good_msrs; extern asmlinkage void kvm_vmx_return(void); if (!init_rmode_tss(vcpu->kvm)) { @@ -1136,23 +1208,17 @@ static int vmx_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->host_msrs[j].reserved = 0; vcpu->host_msrs[j].data = data; vcpu->guest_msrs[j] = vcpu->host_msrs[j]; +#ifdef CONFIG_X86_64 + if (index == MSR_KERNEL_GS_BASE) + msr_offset_kernel_gs_base = j; +#endif ++vcpu->nmsrs; } - printk(KERN_DEBUG "kvm: msrs: %d\n", vcpu->nmsrs); - nr_good_msrs = vcpu->nmsrs - NR_BAD_MSRS; - vmcs_writel(VM_ENTRY_MSR_LOAD_ADDR, - virt_to_phys(vcpu->guest_msrs + NR_BAD_MSRS)); - vmcs_writel(VM_EXIT_MSR_STORE_ADDR, - virt_to_phys(vcpu->guest_msrs + NR_BAD_MSRS)); - vmcs_writel(VM_EXIT_MSR_LOAD_ADDR, - virt_to_phys(vcpu->host_msrs + NR_BAD_MSRS)); + setup_msrs(vcpu); + vmcs_write32_fixedbits(MSR_IA32_VMX_EXIT_CTLS, VM_EXIT_CONTROLS, (HOST_IS_64 << 9)); /* 22.2,1, 20.7.1 */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, nr_good_msrs); /* 22.2.2 */ - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */ - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */ - /* 22.2.1, 20.8.1 */ vmcs_write32_fixedbits(MSR_IA32_VMX_ENTRY_CTLS, @@ -1164,7 +1230,7 @@ static int vmx_vcpu_setup(struct kvm_vcpu *vcpu) vmcs_writel(TPR_THRESHOLD, 0); #endif - vmcs_writel(CR0_GUEST_HOST_MASK, KVM_GUEST_CR0_MASK); + vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); vcpu->cr0 = 0x60000010; @@ -1190,7 +1256,7 @@ static void inject_rmode_irq(struct kvm_vcpu *vcpu, int irq) u16 sp = vmcs_readl(GUEST_RSP); u32 ss_limit = vmcs_read32(GUEST_SS_LIMIT); - if (sp > ss_limit || sp - 6 > sp) { + if (sp > ss_limit || sp < 6 ) { vcpu_printf(vcpu, "%s: #SS, rsp 0x%lx ss 0x%lx limit 0x%x\n", __FUNCTION__, vmcs_readl(GUEST_RSP), @@ -1330,6 +1396,15 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) asm ("int $2"); return 1; } + + if (is_no_device(intr_info)) { + vcpu->fpu_active = 1; + vmcs_clear_bits(EXCEPTION_BITMAP, 1 << NM_VECTOR); + if (!(vcpu->cr0 & CR0_TS_MASK)) + vmcs_clear_bits(GUEST_CR0, CR0_TS_MASK); + return 1; + } + error_code = 0; rip = vmcs_readl(GUEST_RIP); if (intr_info & INTR_INFO_DELIEVER_CODE_MASK) @@ -1355,7 +1430,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) case EMULATE_DONE: return 1; case EMULATE_DO_MMIO: - ++kvm_stat.mmio_exits; + ++vcpu->stat.mmio_exits; kvm_run->exit_reason = KVM_EXIT_MMIO; return 0; case EMULATE_FAIL: @@ -1384,7 +1459,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) static int handle_external_interrupt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - ++kvm_stat.irq_exits; + ++vcpu->stat.irq_exits; return 1; } @@ -1394,7 +1469,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } -static int get_io_count(struct kvm_vcpu *vcpu, u64 *count) +static int get_io_count(struct kvm_vcpu *vcpu, unsigned long *count) { u64 inst; gva_t rip; @@ -1439,33 +1514,35 @@ static int get_io_count(struct kvm_vcpu *vcpu, u64 *count) done: countr_size *= 8; *count = vcpu->regs[VCPU_REGS_RCX] & (~0ULL >> (64 - countr_size)); + //printk("cx: %lx\n", vcpu->regs[VCPU_REGS_RCX]); return 1; } static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u64 exit_qualification; + int size, down, in, string, rep; + unsigned port; + unsigned long count; + gva_t address; - ++kvm_stat.io_exits; + ++vcpu->stat.io_exits; exit_qualification = vmcs_read64(EXIT_QUALIFICATION); - kvm_run->exit_reason = KVM_EXIT_IO; - if (exit_qualification & 8) - kvm_run->io.direction = KVM_EXIT_IO_IN; - else - kvm_run->io.direction = KVM_EXIT_IO_OUT; - kvm_run->io.size = (exit_qualification & 7) + 1; - kvm_run->io.string = (exit_qualification & 16) != 0; - kvm_run->io.string_down - = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; - kvm_run->io.rep = (exit_qualification & 32) != 0; - kvm_run->io.port = exit_qualification >> 16; - if (kvm_run->io.string) { - if (!get_io_count(vcpu, &kvm_run->io.count)) + in = (exit_qualification & 8) != 0; + size = (exit_qualification & 7) + 1; + string = (exit_qualification & 16) != 0; + down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; + count = 1; + rep = (exit_qualification & 32) != 0; + port = exit_qualification >> 16; + address = 0; + if (string) { + if (rep && !get_io_count(vcpu, &count)) return 1; - kvm_run->io.address = vmcs_readl(GUEST_LINEAR_ADDRESS); - } else - kvm_run->io.value = vcpu->regs[VCPU_REGS_RAX]; /* rax */ - return 0; + address = vmcs_readl(GUEST_LINEAR_ADDRESS); + } + return kvm_setup_pio(vcpu, kvm_run, in, size, count, string, down, + address, rep, port); } static void @@ -1514,6 +1591,15 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; }; break; + case 2: /* clts */ + vcpu_load_rsp_rip(vcpu); + vcpu->fpu_active = 1; + vmcs_clear_bits(EXCEPTION_BITMAP, 1 << NM_VECTOR); + vmcs_clear_bits(GUEST_CR0, CR0_TS_MASK); + vcpu->cr0 &= ~CR0_TS_MASK; + vmcs_writel(CR0_READ_SHADOW, vcpu->cr0); + skip_emulated_instruction(vcpu); + return 1; case 1: /*mov from cr*/ switch (cr) { case 3: @@ -1523,8 +1609,6 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) skip_emulated_instruction(vcpu); return 1; case 8: - printk(KERN_DEBUG "handle_cr: read CR8 " - "cpu erratum AA15\n"); vcpu_load_rsp_rip(vcpu); vcpu->regs[reg] = vcpu->cr8; vcpu_put_rsp_rip(vcpu); @@ -1583,8 +1667,8 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - kvm_run->exit_reason = KVM_EXIT_CPUID; - return 0; + kvm_emulate_cpuid(vcpu); + return 1; } static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -1639,7 +1723,7 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, if (kvm_run->request_interrupt_window && !vcpu->irq_summary) { kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - ++kvm_stat.irq_window_exits; + ++vcpu->stat.irq_window_exits; return 0; } return 1; @@ -1652,13 +1736,13 @@ static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; kvm_run->exit_reason = KVM_EXIT_HLT; - ++kvm_stat.halt_exits; + ++vcpu->stat.halt_exits; return 0; } static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP)+3); + skip_emulated_instruction(vcpu); return kvm_hypercall(vcpu, kvm_run); } @@ -1699,7 +1783,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) exit_reason != EXIT_REASON_EXCEPTION_NMI ) printk(KERN_WARNING "%s: unexpected, valid vectoring info and " "exit reason is 0x%x\n", __FUNCTION__, exit_reason); - kvm_run->instruction_length = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); @@ -1763,11 +1846,21 @@ again: if (vcpu->guest_debug.enabled) kvm_guest_debug_pre(vcpu); - fx_save(vcpu->host_fx_image); - fx_restore(vcpu->guest_fx_image); + if (vcpu->fpu_active) { + fx_save(vcpu->host_fx_image); + fx_restore(vcpu->guest_fx_image); + } + /* + * Loading guest fpu may have cleared host cr0.ts + */ + vmcs_writel(HOST_CR0, read_cr0()); - save_msrs(vcpu->host_msrs, vcpu->nmsrs); - load_msrs(vcpu->guest_msrs, NR_BAD_MSRS); +#ifdef CONFIG_X86_64 + if (is_long_mode(vcpu)) { + save_msrs(vcpu->host_msrs + msr_offset_kernel_gs_base, 1); + load_msrs(vcpu->guest_msrs, NR_BAD_MSRS); + } +#endif asm ( /* Store host registers */ @@ -1909,21 +2002,28 @@ again: reload_tss(); } - ++kvm_stat.exits; + ++vcpu->stat.exits; - save_msrs(vcpu->guest_msrs, NR_BAD_MSRS); - load_msrs(vcpu->host_msrs, NR_BAD_MSRS); +#ifdef CONFIG_X86_64 + if (is_long_mode(vcpu)) { + save_msrs(vcpu->guest_msrs, NR_BAD_MSRS); + load_msrs(vcpu->host_msrs, NR_BAD_MSRS); + } +#endif + + if (vcpu->fpu_active) { + fx_save(vcpu->guest_fx_image); + fx_restore(vcpu->host_fx_image); + } - fx_save(vcpu->guest_fx_image); - fx_restore(vcpu->host_fx_image); vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0; asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS)); - kvm_run->exit_type = 0; if (fail) { - kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY; - kvm_run->exit_reason = vmcs_read32(VM_INSTRUCTION_ERROR); + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + kvm_run->fail_entry.hardware_entry_failure_reason + = vmcs_read32(VM_INSTRUCTION_ERROR); r = 0; } else { /* @@ -1933,19 +2033,20 @@ again: profile_hit(KVM_PROFILING, (void *)vmcs_readl(GUEST_RIP)); vcpu->launched = 1; - kvm_run->exit_type = KVM_EXIT_TYPE_VM_EXIT; r = kvm_handle_exit(kvm_run, vcpu); if (r > 0) { /* Give scheduler a change to reschedule. */ if (signal_pending(current)) { - ++kvm_stat.signal_exits; + ++vcpu->stat.signal_exits; post_kvm_run_save(vcpu, kvm_run); + kvm_run->exit_reason = KVM_EXIT_INTR; return -EINTR; } if (dm_request_for_irq_injection(vcpu, kvm_run)) { - ++kvm_stat.request_irq_exits; + ++vcpu->stat.request_irq_exits; post_kvm_run_save(vcpu, kvm_run); + kvm_run->exit_reason = KVM_EXIT_INTR; return -EINTR; } @@ -1969,7 +2070,7 @@ static void vmx_inject_page_fault(struct kvm_vcpu *vcpu, { u32 vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - ++kvm_stat.pf_guest; + ++vcpu->stat.pf_guest; if (is_page_fault(vect_info)) { printk(KERN_DEBUG "inject_page_fault: " @@ -2026,6 +2127,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmcs_clear(vmcs); vcpu->vmcs = vmcs; vcpu->launched = 0; + vcpu->fpu_active = 1; return 0; @@ -2062,9 +2164,8 @@ static struct kvm_arch_ops vmx_arch_ops = { .get_segment = vmx_get_segment, .set_segment = vmx_set_segment, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_cr4_guest_bits = vmx_decache_cr0_cr4_guest_bits, + .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, - .set_cr0_no_modeswitch = vmx_set_cr0_no_modeswitch, .set_cr3 = vmx_set_cr3, .set_cr4 = vmx_set_cr4, #ifdef CONFIG_X86_64 diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_emulate.c index 7513cddb929..7ade09086aa 100644 --- a/drivers/kvm/x86_emulate.c +++ b/drivers/kvm/x86_emulate.c @@ -833,8 +833,9 @@ done_prefixes: dst.ptr = (unsigned long *)cr2; dst.bytes = (d & ByteOp) ? 1 : op_bytes; if (d & BitOp) { - dst.ptr += src.val / BITS_PER_LONG; - dst.bytes = sizeof(long); + unsigned long mask = ~(dst.bytes * 8 - 1); + + dst.ptr = (void *)dst.ptr + (src.val & mask) / 8; } if (!(d & Mov) && /* optimisation - avoid slow emulated read */ ((rc = ops->read_emulated((unsigned long)dst.ptr, @@ -1044,7 +1045,7 @@ done_prefixes: if ((rc = ops->write_std( register_address(ctxt->ss_base, _regs[VCPU_REGS_RSP]), - dst.val, dst.bytes, ctxt)) != 0) + &dst.val, dst.bytes, ctxt)) != 0) goto done; dst.val = dst.orig_val; /* skanky: disable writeback */ break; @@ -1077,12 +1078,12 @@ writeback: case OP_MEM: if (lock_prefix) rc = ops->cmpxchg_emulated((unsigned long)dst. - ptr, dst.orig_val, - dst.val, dst.bytes, + ptr, &dst.orig_val, + &dst.val, dst.bytes, ctxt); else rc = ops->write_emulated((unsigned long)dst.ptr, - dst.val, dst.bytes, + &dst.val, dst.bytes, ctxt); if (rc != 0) goto done; @@ -1320,36 +1321,8 @@ twobyte_special_insn: realmode_set_cr(ctxt->vcpu, modrm_reg, modrm_val, &_eflags); break; case 0xc7: /* Grp9 (cmpxchg8b) */ -#if defined(__i386__) - { - unsigned long old_lo, old_hi; - if (((rc = ops->read_emulated(cr2 + 0, &old_lo, 4, - ctxt)) != 0) - || ((rc = ops->read_emulated(cr2 + 4, &old_hi, 4, - ctxt)) != 0)) - goto done; - if ((old_lo != _regs[VCPU_REGS_RAX]) - || (old_hi != _regs[VCPU_REGS_RDX])) { - _regs[VCPU_REGS_RAX] = old_lo; - _regs[VCPU_REGS_RDX] = old_hi; - _eflags &= ~EFLG_ZF; - } else if (ops->cmpxchg8b_emulated == NULL) { - rc = X86EMUL_UNHANDLEABLE; - goto done; - } else { - if ((rc = ops->cmpxchg8b_emulated(cr2, old_lo, - old_hi, - _regs[VCPU_REGS_RBX], - _regs[VCPU_REGS_RCX], - ctxt)) != 0) - goto done; - _eflags |= EFLG_ZF; - } - break; - } -#elif defined(CONFIG_X86_64) { - unsigned long old, new; + u64 old, new; if ((rc = ops->read_emulated(cr2, &old, 8, ctxt)) != 0) goto done; if (((u32) (old >> 0) != (u32) _regs[VCPU_REGS_RAX]) || @@ -1358,15 +1331,15 @@ twobyte_special_insn: _regs[VCPU_REGS_RDX] = (u32) (old >> 32); _eflags &= ~EFLG_ZF; } else { - new = (_regs[VCPU_REGS_RCX] << 32) | (u32) _regs[VCPU_REGS_RBX]; - if ((rc = ops->cmpxchg_emulated(cr2, old, - new, 8, ctxt)) != 0) + new = ((u64)_regs[VCPU_REGS_RCX] << 32) + | (u32) _regs[VCPU_REGS_RBX]; + if ((rc = ops->cmpxchg_emulated(cr2, &old, + &new, 8, ctxt)) != 0) goto done; _eflags |= EFLG_ZF; } break; } -#endif } goto writeback; diff --git a/drivers/kvm/x86_emulate.h b/drivers/kvm/x86_emulate.h index 5d41bd55125..ea3407d7fee 100644 --- a/drivers/kvm/x86_emulate.h +++ b/drivers/kvm/x86_emulate.h @@ -59,8 +59,7 @@ struct x86_emulate_ops { * @val: [OUT] Value read from memory, zero-extended to 'u_long'. * @bytes: [IN ] Number of bytes to read from memory. */ - int (*read_std)(unsigned long addr, - unsigned long *val, + int (*read_std)(unsigned long addr, void *val, unsigned int bytes, struct x86_emulate_ctxt * ctxt); /* @@ -71,8 +70,7 @@ struct x86_emulate_ops { * required). * @bytes: [IN ] Number of bytes to write to memory. */ - int (*write_std)(unsigned long addr, - unsigned long val, + int (*write_std)(unsigned long addr, const void *val, unsigned int bytes, struct x86_emulate_ctxt * ctxt); /* @@ -82,7 +80,7 @@ struct x86_emulate_ops { * @bytes: [IN ] Number of bytes to read from memory. */ int (*read_emulated) (unsigned long addr, - unsigned long *val, + void *val, unsigned int bytes, struct x86_emulate_ctxt * ctxt); @@ -94,7 +92,7 @@ struct x86_emulate_ops { * @bytes: [IN ] Number of bytes to write to memory. */ int (*write_emulated) (unsigned long addr, - unsigned long val, + const void *val, unsigned int bytes, struct x86_emulate_ctxt * ctxt); @@ -107,29 +105,11 @@ struct x86_emulate_ops { * @bytes: [IN ] Number of bytes to access using CMPXCHG. */ int (*cmpxchg_emulated) (unsigned long addr, - unsigned long old, - unsigned long new, + const void *old, + const void *new, unsigned int bytes, struct x86_emulate_ctxt * ctxt); - /* - * cmpxchg8b_emulated: Emulate an atomic (LOCKed) CMPXCHG8B operation on an - * emulated/special memory area. - * @addr: [IN ] Linear address to access. - * @old: [IN ] Value expected to be current at @addr. - * @new: [IN ] Value to write to @addr. - * NOTES: - * 1. This function is only ever called when emulating a real CMPXCHG8B. - * 2. This function is *never* called on x86/64 systems. - * 2. Not defining this function (i.e., specifying NULL) is equivalent - * to defining a function that always returns X86EMUL_UNHANDLEABLE. - */ - int (*cmpxchg8b_emulated) (unsigned long addr, - unsigned long old_lo, - unsigned long old_hi, - unsigned long new_lo, - unsigned long new_hi, - struct x86_emulate_ctxt * ctxt); }; struct cpu_user_regs; |