X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fkvm%2Fkvm_main.c;h=721e660023f638011bc02b12f9bf9a8c99ce2ecd;hb=111de5d60c589bca02b49dce076ca588618e0d1c;hp=ec696887b2224c13d030f20e9e44bc1223c76feb;hpb=043405e10001fe7aae60c46a57189515f13a6468;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c index ec69688..721e660 100644 --- a/drivers/kvm/kvm_main.c +++ b/drivers/kvm/kvm_main.c @@ -17,8 +17,6 @@ #include "kvm.h" #include "x86.h" -#include "x86_emulate.h" -#include "segment_descriptor.h" #include "irq.h" #include @@ -42,158 +40,55 @@ #include #include #include +#include #include -#include #include #include #include +#include MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static DEFINE_SPINLOCK(kvm_lock); -static LIST_HEAD(vm_list); +DEFINE_SPINLOCK(kvm_lock); +LIST_HEAD(vm_list); static cpumask_t cpus_hardware_enabled; -struct kvm_x86_ops *kvm_x86_ops; struct kmem_cache *kvm_vcpu_cache; EXPORT_SYMBOL_GPL(kvm_vcpu_cache); static __read_mostly struct preempt_ops kvm_preempt_ops; -#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x) - -static struct kvm_stats_debugfs_item { - const char *name; - int offset; - struct dentry *dentry; -} debugfs_entries[] = { - { "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) }, - { "halt_wakeup", STAT_OFFSET(halt_wakeup) }, - { "request_irq", STAT_OFFSET(request_irq_exits) }, - { "irq_exits", STAT_OFFSET(irq_exits) }, - { "light_exits", STAT_OFFSET(light_exits) }, - { "efer_reload", STAT_OFFSET(efer_reload) }, - { NULL } -}; - static struct dentry *debugfs_dir; -#define MAX_IO_MSRS 256 - -#define CR0_RESERVED_BITS \ - (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ - | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ - | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR4_RESERVED_BITS \ - (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ - | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) - -#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) -#define EFER_RESERVED_BITS 0xfffffffffffff2fe - -#ifdef CONFIG_X86_64 -/* LDT or TSS descriptor in the GDT. 16 bytes. */ -struct segment_descriptor_64 { - struct segment_descriptor s; - u32 base_higher; - u32 pad_zero; -}; - -#endif - static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); -unsigned long segment_base(u16 selector) -{ - struct descriptor_table gdt; - struct segment_descriptor *d; - unsigned long table_base; - unsigned long v; - - if (selector == 0) - return 0; - - asm("sgdt %0" : "=m"(gdt)); - table_base = gdt.base; - - if (selector & 4) { /* from ldt */ - u16 ldt_selector; - - asm("sldt %0" : "=g"(ldt_selector)); - table_base = segment_base(ldt_selector); - } - d = (struct segment_descriptor *)(table_base + (selector & ~7)); - v = d->base_low | ((unsigned long)d->base_mid << 16) | - ((unsigned long)d->base_high << 24); -#ifdef CONFIG_X86_64 - if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long) \ - ((struct segment_descriptor_64 *)d)->base_higher) << 32; -#endif - return v; -} -EXPORT_SYMBOL_GPL(segment_base); - static inline int valid_vcpu(int n) { return likely(n >= 0 && n < KVM_MAX_VCPUS); } -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - if (!vcpu->fpu_active || vcpu->guest_fpu_loaded) - return; - - vcpu->guest_fpu_loaded = 1; - fx_save(&vcpu->host_fx_image); - fx_restore(&vcpu->guest_fx_image); -} -EXPORT_SYMBOL_GPL(kvm_load_guest_fpu); - -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - if (!vcpu->guest_fpu_loaded) - return; - - vcpu->guest_fpu_loaded = 0; - fx_save(&vcpu->guest_fx_image); - fx_restore(&vcpu->host_fx_image); -} -EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); - /* * Switches to specified vcpu, until a matching vcpu_put() */ -static void vcpu_load(struct kvm_vcpu *vcpu) +void vcpu_load(struct kvm_vcpu *vcpu) { int cpu; mutex_lock(&vcpu->mutex); cpu = get_cpu(); preempt_notifier_register(&vcpu->preempt_notifier); - kvm_x86_ops->vcpu_load(vcpu, cpu); + kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); } -static void vcpu_put(struct kvm_vcpu *vcpu) +void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); - kvm_x86_ops->vcpu_put(vcpu); + kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); preempt_enable(); mutex_unlock(&vcpu->mutex); @@ -214,12 +109,15 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) vcpu = kvm->vcpus[i]; if (!vcpu) continue; - if (test_and_set_bit(KVM_TLB_FLUSH, &vcpu->requests)) + if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) continue; cpu = vcpu->cpu; if (cpu != -1 && cpu != raw_smp_processor_id()) cpu_set(cpu, cpus); } + if (cpus_empty(cpus)) + return; + ++kvm->stat.remote_tlb_flush; smp_call_function_mask(cpus, ack_flush, NULL, 1); } @@ -230,13 +128,8 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) mutex_init(&vcpu->mutex); vcpu->cpu = -1; - vcpu->mmu.root_hpa = INVALID_PAGE; vcpu->kvm = kvm; vcpu->vcpu_id = id; - if (!irqchip_in_kernel(kvm) || id == 0) - vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - else - vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED; init_waitqueue_head(&vcpu->wq); page = alloc_page(GFP_KERNEL | __GFP_ZERO); @@ -246,29 +139,11 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) } vcpu->run = page_address(page); - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail_free_run; - } - vcpu->pio_data = page_address(page); - - r = kvm_mmu_create(vcpu); + r = kvm_arch_vcpu_init(vcpu); if (r < 0) - goto fail_free_pio_data; - - if (irqchip_in_kernel(kvm)) { - r = kvm_create_lapic(vcpu); - if (r < 0) - goto fail_mmu_destroy; - } - + goto fail_free_run; return 0; -fail_mmu_destroy: - kvm_mmu_destroy(vcpu); -fail_free_pio_data: - free_page((unsigned long)vcpu->pio_data); fail_free_run: free_page((unsigned long)vcpu->run); fail: @@ -278,78 +153,48 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) { - kvm_free_lapic(vcpu); - kvm_mmu_destroy(vcpu); - free_page((unsigned long)vcpu->pio_data); + kvm_arch_vcpu_uninit(vcpu); free_page((unsigned long)vcpu->run); } EXPORT_SYMBOL_GPL(kvm_vcpu_uninit); static struct kvm *kvm_create_vm(void) { - struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + struct kvm *kvm = kvm_arch_create_vm(); - if (!kvm) - return ERR_PTR(-ENOMEM); + if (IS_ERR(kvm)) + goto out; + kvm->mm = current->mm; + atomic_inc(&kvm->mm->mm_count); kvm_io_bus_init(&kvm->pio_bus); mutex_init(&kvm->lock); - INIT_LIST_HEAD(&kvm->active_mmu_pages); kvm_io_bus_init(&kvm->mmio_bus); spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); +out: return kvm; } -static void kvm_free_userspace_physmem(struct kvm_memory_slot *free) -{ - int i; - - for (i = 0; i < free->npages; ++i) { - if (free->phys_mem[i]) { - if (!PageReserved(free->phys_mem[i])) - SetPageDirty(free->phys_mem[i]); - page_cache_release(free->phys_mem[i]); - } - } -} - -static void kvm_free_kernel_physmem(struct kvm_memory_slot *free) -{ - int i; - - for (i = 0; i < free->npages; ++i) - if (free->phys_mem[i]) - __free_page(free->phys_mem[i]); -} - /* * Free any memory in @free but not in @dont. */ static void kvm_free_physmem_slot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { - if (!dont || free->phys_mem != dont->phys_mem) - if (free->phys_mem) { - if (free->user_alloc) - kvm_free_userspace_physmem(free); - else - kvm_free_kernel_physmem(free); - vfree(free->phys_mem); - } if (!dont || free->rmap != dont->rmap) vfree(free->rmap); if (!dont || free->dirty_bitmap != dont->dirty_bitmap) vfree(free->dirty_bitmap); - free->phys_mem = NULL; free->npages = 0; free->dirty_bitmap = NULL; + free->rmap = NULL; } -static void kvm_free_physmem(struct kvm *kvm) +void kvm_free_physmem(struct kvm *kvm) { int i; @@ -357,55 +202,17 @@ 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 < ARRAY_SIZE(vcpu->pio.guest_pages); ++i) - if (vcpu->pio.guest_pages[i]) { - __free_page(vcpu->pio.guest_pages[i]); - vcpu->pio.guest_pages[i] = NULL; - } -} - -static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) -{ - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); -} - -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - - /* - * Unpin any mmu pages first. - */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i]) - kvm_unload_vcpu_mmu(kvm->vcpus[i]); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_x86_ops->vcpu_free(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - -} - static void kvm_destroy_vm(struct kvm *kvm) { + struct mm_struct *mm = kvm->mm; + spin_lock(&kvm_lock); list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_io_bus_destroy(&kvm->pio_bus); kvm_io_bus_destroy(&kvm->mmio_bus); - kfree(kvm->vpic); - kfree(kvm->vioapic); - kvm_free_vcpus(kvm); - kvm_free_physmem(kvm); - kfree(kvm); + kvm_arch_destroy_vm(kvm); + mmdrop(mm); } static int kvm_vm_release(struct inode *inode, struct file *filp) @@ -416,268 +223,17 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) return 0; } -static void inject_gp(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops->inject_gp(vcpu, 0); -} - -/* - * Load the pae pdptrs. Return true is they are all valid. - */ -static int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; - unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; - int i; - int ret; - u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)]; - - mutex_lock(&vcpu->kvm->lock); - ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, - offset * sizeof(u64), sizeof(pdpte)); - if (ret < 0) { - ret = 0; - goto out; - } - for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { - if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) { - ret = 0; - goto out; - } - } - ret = 1; - - memcpy(vcpu->pdptrs, pdpte, sizeof(vcpu->pdptrs)); -out: - mutex_unlock(&vcpu->kvm->lock); - - return ret; -} - -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - if (cr0 & CR0_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, vcpu->cr0); - inject_gp(vcpu); - return; - } - - if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { - printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); - inject_gp(vcpu); - return; - } - - if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - printk(KERN_DEBUG "set_cr0: #GP, set PG flag " - "and a clear PE flag\n"); - inject_gp(vcpu); - return; - } - - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { -#ifdef CONFIG_X86_64 - if ((vcpu->shadow_efer & EFER_LME)) { - int cs_db, cs_l; - - if (!is_pae(vcpu)) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while PAE is disabled\n"); - inject_gp(vcpu); - return; - } - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while CS.L == 1\n"); - inject_gp(vcpu); - return; - - } - } else -#endif - if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->cr3)) { - printk(KERN_DEBUG "set_cr0: #GP, pdptrs " - "reserved bits\n"); - inject_gp(vcpu); - return; - } - - } - - kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->cr0 = cr0; - - mutex_lock(&vcpu->kvm->lock); - kvm_mmu_reset_context(vcpu); - mutex_unlock(&vcpu->kvm->lock); - return; -} -EXPORT_SYMBOL_GPL(set_cr0); - -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) -{ - set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f)); -} -EXPORT_SYMBOL_GPL(lmsw); - -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & CR4_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - - if (is_long_mode(vcpu)) { - if (!(cr4 & X86_CR4_PAE)) { - printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " - "in long mode\n"); - inject_gp(vcpu); - return; - } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) - && !load_pdptrs(vcpu, vcpu->cr3)) { - printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); - inject_gp(vcpu); - return; - } - - if (cr4 & X86_CR4_VMXE) { - printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); - inject_gp(vcpu); - return; - } - kvm_x86_ops->set_cr4(vcpu, cr4); - vcpu->cr4 = cr4; - mutex_lock(&vcpu->kvm->lock); - kvm_mmu_reset_context(vcpu); - mutex_unlock(&vcpu->kvm->lock); -} -EXPORT_SYMBOL_GPL(set_cr4); - -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - } else { - if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - printk(KERN_DEBUG "set_cr3: #GP, pdptrs " - "reserved bits\n"); - inject_gp(vcpu); - return; - } - } - /* - * We don't check reserved bits in nonpae mode, because - * this isn't enforced, and VMware depends on this. - */ - } - - mutex_lock(&vcpu->kvm->lock); - /* - * Does the new cr3 value map to physical memory? (Note, we - * catch an invalid cr3 even in real-mode, because it would - * cause trouble later on when we turn on paging anyway.) - * - * A real CPU would silently accept an invalid cr3 and would - * attempt to use it - with largely undefined (and often hard - * to debug) behavior on the guest side. - */ - if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) - inject_gp(vcpu); - else { - vcpu->cr3 = cr3; - vcpu->mmu.new_cr3(vcpu); - } - mutex_unlock(&vcpu->kvm->lock); -} -EXPORT_SYMBOL_GPL(set_cr3); - -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) -{ - if (cr8 & CR8_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); - inject_gp(vcpu); - return; - } - if (irqchip_in_kernel(vcpu->kvm)) - kvm_lapic_set_tpr(vcpu, cr8); - else - vcpu->cr8 = cr8; -} -EXPORT_SYMBOL_GPL(set_cr8); - -unsigned long get_cr8(struct kvm_vcpu *vcpu) -{ - if (irqchip_in_kernel(vcpu->kvm)) - return kvm_lapic_get_cr8(vcpu); - else - return vcpu->cr8; -} -EXPORT_SYMBOL_GPL(get_cr8); - -u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) -{ - if (irqchip_in_kernel(vcpu->kvm)) - return vcpu->apic_base; - else - return vcpu->apic_base; -} -EXPORT_SYMBOL_GPL(kvm_get_apic_base); - -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) -{ - /* TODO: reserve bits check */ - if (irqchip_in_kernel(vcpu->kvm)) - kvm_lapic_set_base(vcpu, data); - else - vcpu->apic_base = data; -} -EXPORT_SYMBOL_GPL(kvm_set_apic_base); - -void fx_init(struct kvm_vcpu *vcpu) -{ - unsigned after_mxcsr_mask; - - /* Initialize guest FPU by resetting ours and saving into guest's */ - preempt_disable(); - fx_save(&vcpu->host_fx_image); - fpu_init(); - fx_save(&vcpu->guest_fx_image); - fx_restore(&vcpu->host_fx_image); - preempt_enable(); - - vcpu->cr0 |= X86_CR0_ET; - after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space); - vcpu->guest_fx_image.mxcsr = 0x1f80; - memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask, - 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask); -} -EXPORT_SYMBOL_GPL(fx_init); - /* * Allocate some memory and give it an address in the guest physical address * space. * * Discontiguous memory is allowed, mostly for framebuffers. + * + * Must be called holding kvm->lock. */ -static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct - kvm_userspace_memory_region *mem, - int user_alloc) +int __kvm_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + int user_alloc) { int r; gfn_t base_gfn; @@ -692,7 +248,7 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; - if (mem->slot >= KVM_MEMORY_SLOTS) + if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; @@ -704,8 +260,6 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, if (!npages) mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; - mutex_lock(&kvm->lock); - new = old = *memslot; new.base_gfn = base_gfn; @@ -715,7 +269,7 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, /* Disallow changing a memory slot's size. */ r = -EINVAL; if (npages && old.npages && npages != old.npages) - goto out_unlock; + goto out_free; /* Check for overlaps */ r = -EEXIST; @@ -726,13 +280,9 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, continue; if (!((base_gfn + npages <= s->base_gfn) || (base_gfn >= s->base_gfn + s->npages))) - goto out_unlock; + goto out_free; } - /* Deallocate if slot is being removed */ - if (!npages) - new.phys_mem = NULL; - /* Free page dirty bitmap if unneeded */ if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) new.dirty_bitmap = NULL; @@ -740,41 +290,16 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, r = -ENOMEM; /* Allocate if a slot is being created */ - if (npages && !new.phys_mem) { - new.phys_mem = vmalloc(npages * sizeof(struct page *)); - - if (!new.phys_mem) - goto out_unlock; - + if (npages && !new.rmap) { new.rmap = vmalloc(npages * sizeof(struct page *)); if (!new.rmap) - goto out_unlock; + goto out_free; - memset(new.phys_mem, 0, npages * sizeof(struct page *)); memset(new.rmap, 0, npages * sizeof(*new.rmap)); - if (user_alloc) { - unsigned long pages_num; - - new.user_alloc = 1; - down_read(¤t->mm->mmap_sem); - - pages_num = get_user_pages(current, current->mm, - mem->userspace_addr, - npages, 1, 1, new.phys_mem, - NULL); - - up_read(¤t->mm->mmap_sem); - if (pages_num != npages) - goto out_unlock; - } else { - for (i = 0; i < npages; ++i) { - new.phys_mem[i] = alloc_page(GFP_HIGHUSER - | __GFP_ZERO); - if (!new.phys_mem[i]) - goto out_unlock; - } - } + + new.user_alloc = user_alloc; + new.userspace_addr = mem->userspace_addr; } /* Allocate page dirty bitmap if needed */ @@ -783,81 +308,63 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, new.dirty_bitmap = vmalloc(dirty_bytes); if (!new.dirty_bitmap) - goto out_unlock; + goto out_free; memset(new.dirty_bitmap, 0, dirty_bytes); } if (mem->slot >= kvm->nmemslots) kvm->nmemslots = mem->slot + 1; - if (!kvm->n_requested_mmu_pages) { - unsigned int n_pages; - - if (npages) { - n_pages = npages * KVM_PERMILLE_MMU_PAGES / 1000; - kvm_mmu_change_mmu_pages(kvm, kvm->n_alloc_mmu_pages + - n_pages); - } else { - unsigned int nr_mmu_pages; - - n_pages = old.npages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = kvm->n_alloc_mmu_pages - n_pages; - nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - } - } - *memslot = new; - kvm_mmu_slot_remove_write_access(kvm, mem->slot); - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->lock); + r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc); + if (r) { + *memslot = old; + goto out_free; + } kvm_free_physmem_slot(&old, &new); return 0; -out_unlock: - mutex_unlock(&kvm->lock); +out_free: kvm_free_physmem_slot(&new, &old); out: return r; + } +EXPORT_SYMBOL_GPL(__kvm_set_memory_region); -static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, - u32 kvm_nr_mmu_pages) +int kvm_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + int user_alloc) { - if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) - return -EINVAL; + int r; mutex_lock(&kvm->lock); - - kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); - kvm->n_requested_mmu_pages = kvm_nr_mmu_pages; - + r = __kvm_set_memory_region(kvm, mem, user_alloc); mutex_unlock(&kvm->lock); - return 0; + return r; } +EXPORT_SYMBOL_GPL(kvm_set_memory_region); -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct + kvm_userspace_memory_region *mem, + int user_alloc) { - return kvm->n_alloc_mmu_pages; + if (mem->slot >= KVM_MEMORY_SLOTS) + return -EINVAL; + return kvm_set_memory_region(kvm, mem, user_alloc); } -/* - * Get (and clear) the dirty memory log for a memory slot. - */ -static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log) +int kvm_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log, int *is_dirty) { struct kvm_memory_slot *memslot; int r, i; int n; unsigned long any = 0; - mutex_lock(&kvm->lock); - r = -EINVAL; if (log->slot >= KVM_MEMORY_SLOTS) goto out; @@ -876,138 +383,30 @@ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) goto out; - /* If nothing is dirty, don't bother messing with page tables. */ - if (any) { - kvm_mmu_slot_remove_write_access(kvm, log->slot); - kvm_flush_remote_tlbs(kvm); - memset(memslot->dirty_bitmap, 0, n); - } + if (any) + *is_dirty = 1; r = 0; - -out: - mutex_unlock(&kvm->lock); - return r; -} - -/* - * 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; - - mutex_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; - - kvm_mmu_zap_all(kvm); - - mutex_unlock(&kvm->lock); - - return 0; - out: return r; } -static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +int is_error_page(struct page *page) { - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy(&chip->chip.pic, - &pic_irqchip(kvm)->pics[0], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&chip->chip.pic, - &pic_irqchip(kvm)->pics[1], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); - break; - default: - r = -EINVAL; - break; - } - return r; + return page == bad_page; } +EXPORT_SYMBOL_GPL(is_error_page); -static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +static inline unsigned long bad_hva(void) { - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy(&pic_irqchip(kvm)->pics[0], - &chip->chip.pic, - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&pic_irqchip(kvm)->pics[1], - &chip->chip.pic, - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - break; - default: - r = -EINVAL; - break; - } - kvm_pic_update_irq(pic_irqchip(kvm)); - return r; + return PAGE_OFFSET; } -gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) +int kvm_is_error_hva(unsigned long addr) { - 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; + return addr == bad_hva(); } +EXPORT_SYMBOL_GPL(kvm_is_error_hva); static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { @@ -1029,18 +428,88 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) return __gfn_to_memslot(kvm, gfn); } -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { - struct kvm_memory_slot *slot; + int i; gfn = unalias_gfn(kvm, gfn); - slot = __gfn_to_memslot(kvm, gfn); + for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { + struct kvm_memory_slot *memslot = &kvm->memslots[i]; + + if (gfn >= memslot->base_gfn + && gfn < memslot->base_gfn + memslot->npages) + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); + +static unsigned long gfn_to_hva(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]; + return bad_hva(); + return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); +} + +/* + * Requires current->mm->mmap_sem to be held + */ +static struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + struct page *page[1]; + unsigned long addr; + int npages; + + might_sleep(); + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) { + get_page(bad_page); + return bad_page; + } + + npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page, + NULL); + + if (npages != 1) { + get_page(bad_page); + return bad_page; + } + + return page[0]; +} + +struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + struct page *page; + + down_read(¤t->mm->mmap_sem); + page = __gfn_to_page(kvm, gfn); + up_read(¤t->mm->mmap_sem); + + return page; } + EXPORT_SYMBOL_GPL(gfn_to_page); +void kvm_release_page_clean(struct page *page) +{ + put_page(page); +} +EXPORT_SYMBOL_GPL(kvm_release_page_clean); + +void kvm_release_page_dirty(struct page *page) +{ + if (!PageReserved(page)) + SetPageDirty(page); + put_page(page); +} +EXPORT_SYMBOL_GPL(kvm_release_page_dirty); + static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) @@ -1052,17 +521,15 @@ static int next_segment(unsigned long len, int offset) int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len) { - void *page_virt; - struct page *page; + int r; + unsigned long addr; - page = gfn_to_page(kvm, gfn); - if (!page) + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return -EFAULT; + r = copy_from_user(data, (void __user *)addr + offset, len); + if (r) return -EFAULT; - page_virt = kmap_atomic(page, KM_USER0); - - memcpy(data, page_virt + offset, len); - - kunmap_atomic(page_virt, KM_USER0); return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest_page); @@ -1090,17 +557,15 @@ EXPORT_SYMBOL_GPL(kvm_read_guest); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { - void *page_virt; - struct page *page; + int r; + unsigned long addr; - page = gfn_to_page(kvm, gfn); - if (!page) + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return -EFAULT; + r = copy_to_user((void __user *)addr + offset, data, len); + if (r) return -EFAULT; - page_virt = kmap_atomic(page, KM_USER0); - - memcpy(page_virt + offset, data, len); - - kunmap_atomic(page_virt, KM_USER0); mark_page_dirty(kvm, gfn); return 0; } @@ -1128,18 +593,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len) { - void *page_virt; - struct page *page; - - page = gfn_to_page(kvm, gfn); - if (!page) - return -EFAULT; - page_virt = kmap_atomic(page, KM_USER0); - - memset(page_virt + offset, 0, len); - - kunmap_atomic(page_virt, KM_USER0); - return 0; + return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len); } EXPORT_SYMBOL_GPL(kvm_clear_guest_page); @@ -1162,11 +616,11 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -/* WARNING: Does not work on aliased pages. */ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; + gfn = unalias_gfn(kvm, gfn); memslot = __gfn_to_memslot(kvm, gfn); if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; @@ -1174,1441 +628,42 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) /* avoid RMW */ if (!test_bit(rel_gfn, memslot->dirty_bitmap)) set_bit(rel_gfn, memslot->dirty_bitmap); - } -} - -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - void *data = val; - - while (bytes) { - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); - int ret; - - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; - ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); - if (ret < 0) - return X86EMUL_UNHANDLEABLE; - - bytes -= tocopy; - data += tocopy; - addr += tocopy; - } - - return X86EMUL_CONTINUE; -} -EXPORT_SYMBOL_GPL(emulator_read_std); - -static int emulator_write_std(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes); - return X86EMUL_UNHANDLEABLE; -} - -/* - * Only apic need an MMIO device hook, so shortcut now.. - */ -static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - struct kvm_io_device *dev; - - if (vcpu->apic) { - dev = &vcpu->apic->dev; - if (dev->in_range(dev, addr)) - return dev; - } - return NULL; -} - -static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - struct kvm_io_device *dev; - - dev = vcpu_find_pervcpu_dev(vcpu, addr); - if (dev == NULL) - dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr); - return dev; -} - -static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr); -} - -static int emulator_read_emulated(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - struct kvm_io_device *mmio_dev; - gpa_t gpa; - - if (vcpu->mmio_read_completed) { - memcpy(val, vcpu->mmio_data, bytes); - vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; - } else if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; - - gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; - - /* - * Is this MMIO handled locally? - */ - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_read(mmio_dev, gpa, bytes, val); - return X86EMUL_CONTINUE; - } - - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 0; - - return X86EMUL_UNHANDLEABLE; -} - -static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) -{ - int ret; - - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); - if (ret < 0) - return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes); - return 1; -} - -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - struct kvm_io_device *mmio_dev; - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - - if (gpa == UNMAPPED_GVA) { - kvm_x86_ops->inject_page_fault(vcpu, addr, 2); - return X86EMUL_PROPAGATE_FAULT; - } - - if (emulator_write_phys(vcpu, gpa, val, bytes)) - return X86EMUL_CONTINUE; - - /* - * Is this MMIO handled locally? - */ - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_write(mmio_dev, gpa, bytes, val); - return X86EMUL_CONTINUE; - } - - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 1; - memcpy(vcpu->mmio_data, val, bytes); - - return X86EMUL_CONTINUE; -} - -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - /* Crossing a page boundary? */ - if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { - int rc, now; - - now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; - addr += now; - val += now; - bytes -= now; - } - return emulator_write_emulated_onepage(addr, val, bytes, vcpu); -} -EXPORT_SYMBOL_GPL(emulator_write_emulated); - -static int emulator_cmpxchg_emulated(unsigned long addr, - const void *old, - const void *new, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - static int reported; - - if (!reported) { - reported = 1; - printk(KERN_WARNING "kvm: emulating exchange as write\n"); - } - return emulator_write_emulated(addr, new, bytes, vcpu); -} - -static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - return kvm_x86_ops->get_segment_base(vcpu, seg); -} - -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) -{ - return X86EMUL_CONTINUE; -} - -int emulate_clts(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS); - return X86EMUL_CONTINUE; -} - -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) -{ - struct kvm_vcpu *vcpu = ctxt->vcpu; - - switch (dr) { - case 0 ... 3: - *dest = kvm_x86_ops->get_dr(vcpu, dr); - return X86EMUL_CONTINUE; - default: - pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr); - return X86EMUL_UNHANDLEABLE; - } -} - -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) -{ - unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - int exception; - - kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception); - if (exception) { - /* FIXME: better handling */ - return X86EMUL_UNHANDLEABLE; - } - return X86EMUL_CONTINUE; -} - -void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) -{ - static int reported; - u8 opcodes[4]; - unsigned long rip = vcpu->rip; - unsigned long rip_linear; - - rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - - if (reported) - return; - - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); - - printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", - context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); - reported = 1; -} -EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); - -struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, - .write_std = emulator_write_std, - .read_emulated = emulator_read_emulated, - .write_emulated = emulator_write_emulated, - .cmpxchg_emulated = emulator_cmpxchg_emulated, -}; - -int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long cr2, - u16 error_code, - int no_decode) -{ - int r; - - vcpu->mmio_fault_cr2 = cr2; - kvm_x86_ops->cache_regs(vcpu); - - vcpu->mmio_is_write = 0; - vcpu->pio.string = 0; - - if (!no_decode) { - int cs_db, cs_l; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - - vcpu->emulate_ctxt.vcpu = vcpu; - vcpu->emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); - vcpu->emulate_ctxt.cr2 = cr2; - vcpu->emulate_ctxt.mode = - (vcpu->emulate_ctxt.eflags & X86_EFLAGS_VM) - ? X86EMUL_MODE_REAL : cs_l - ? X86EMUL_MODE_PROT64 : cs_db - ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - - if (vcpu->emulate_ctxt.mode == X86EMUL_MODE_PROT64) { - vcpu->emulate_ctxt.cs_base = 0; - vcpu->emulate_ctxt.ds_base = 0; - vcpu->emulate_ctxt.es_base = 0; - vcpu->emulate_ctxt.ss_base = 0; - } else { - vcpu->emulate_ctxt.cs_base = - get_segment_base(vcpu, VCPU_SREG_CS); - vcpu->emulate_ctxt.ds_base = - get_segment_base(vcpu, VCPU_SREG_DS); - vcpu->emulate_ctxt.es_base = - get_segment_base(vcpu, VCPU_SREG_ES); - vcpu->emulate_ctxt.ss_base = - get_segment_base(vcpu, VCPU_SREG_SS); - } - - vcpu->emulate_ctxt.gs_base = - get_segment_base(vcpu, VCPU_SREG_GS); - vcpu->emulate_ctxt.fs_base = - get_segment_base(vcpu, VCPU_SREG_FS); - - r = x86_decode_insn(&vcpu->emulate_ctxt, &emulate_ops); - if (r) { - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; - return EMULATE_FAIL; - } - } - - r = x86_emulate_insn(&vcpu->emulate_ctxt, &emulate_ops); - - if (vcpu->pio.string) - return EMULATE_DO_MMIO; - - if ((r || vcpu->mmio_is_write) && run) { - run->exit_reason = KVM_EXIT_MMIO; - run->mmio.phys_addr = vcpu->mmio_phys_addr; - memcpy(run->mmio.data, vcpu->mmio_data, 8); - run->mmio.len = vcpu->mmio_size; - run->mmio.is_write = vcpu->mmio_is_write; - } - - if (r) { - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; - if (!vcpu->mmio_needed) { - kvm_report_emulation_failure(vcpu, "mmio"); - return EMULATE_FAIL; - } - return EMULATE_DO_MMIO; - } - - kvm_x86_ops->decache_regs(vcpu); - kvm_x86_ops->set_rflags(vcpu, vcpu->emulate_ctxt.eflags); - - if (vcpu->mmio_is_write) { - vcpu->mmio_needed = 0; - return EMULATE_DO_MMIO; - } - - return EMULATE_DONE; -} -EXPORT_SYMBOL_GPL(emulate_instruction); - -/* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. - */ -static void kvm_vcpu_block(struct kvm_vcpu *vcpu) -{ - DECLARE_WAITQUEUE(wait, current); - - add_wait_queue(&vcpu->wq, &wait); - - /* - * We will block until either an interrupt or a signal wakes us up - */ - while (!kvm_cpu_has_interrupt(vcpu) - && !signal_pending(current) - && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE - && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) { - set_current_state(TASK_INTERRUPTIBLE); - vcpu_put(vcpu); - schedule(); - vcpu_load(vcpu); - } - - __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->wq, &wait); -} - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.halt_exits; - if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->mp_state = VCPU_MP_STATE_HALTED; - kvm_vcpu_block(vcpu); - if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE) - return -EINTR; - return 1; - } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; - return 0; - } -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) -{ - unsigned long nr, a0, a1, a2, a3, ret; - - kvm_x86_ops->cache_regs(vcpu); - - nr = vcpu->regs[VCPU_REGS_RAX]; - a0 = vcpu->regs[VCPU_REGS_RBX]; - a1 = vcpu->regs[VCPU_REGS_RCX]; - a2 = vcpu->regs[VCPU_REGS_RDX]; - a3 = vcpu->regs[VCPU_REGS_RSI]; - - if (!is_long_mode(vcpu)) { - nr &= 0xFFFFFFFF; - a0 &= 0xFFFFFFFF; - a1 &= 0xFFFFFFFF; - a2 &= 0xFFFFFFFF; - a3 &= 0xFFFFFFFF; - } - - switch (nr) { - default: - ret = -KVM_ENOSYS; - break; - } - vcpu->regs[VCPU_REGS_RAX] = ret; - kvm_x86_ops->decache_regs(vcpu); - return 0; -} -EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); - -int kvm_fix_hypercall(struct kvm_vcpu *vcpu) -{ - char instruction[3]; - int ret = 0; - - mutex_lock(&vcpu->kvm->lock); - - /* - * Blow out the MMU to ensure that no other VCPU has an active mapping - * to ensure that the updated hypercall appears atomically across all - * VCPUs. - */ - kvm_mmu_zap_all(vcpu->kvm); - - kvm_x86_ops->cache_regs(vcpu); - kvm_x86_ops->patch_hypercall(vcpu, instruction); - if (emulator_write_emulated(vcpu->rip, instruction, 3, vcpu) - != X86EMUL_CONTINUE) - ret = -EFAULT; - - mutex_unlock(&vcpu->kvm->lock); - - return ret; -} - -static u64 mk_cr_64(u64 curr_cr, u32 new_val) -{ - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; -} - -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct descriptor_table dt = { limit, base }; - - kvm_x86_ops->set_gdt(vcpu, &dt); -} - -void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct descriptor_table dt = { limit, base }; - - kvm_x86_ops->set_idt(vcpu, &dt); -} - -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); -} - -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) -{ - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - switch (cr) { - case 0: - return vcpu->cr0; - case 2: - return vcpu->cr2; - case 3: - return vcpu->cr3; - case 4: - return vcpu->cr4; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - return 0; - } -} - -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - set_cr0(vcpu, mk_cr_64(vcpu->cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); - break; - case 2: - vcpu->cr2 = val; - break; - case 3: - set_cr3(vcpu, val); - break; - case 4: - set_cr4(vcpu, mk_cr_64(vcpu->cr4, val)); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - } -} - -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data; - - switch (msr) { - case 0xc0010010: /* SYSCFG */ - case 0xc0010015: /* HWCR */ - case MSR_IA32_PLATFORM_ID: - case MSR_IA32_P5_MC_ADDR: - case MSR_IA32_P5_MC_TYPE: - case MSR_IA32_MC0_CTL: - case MSR_IA32_MCG_STATUS: - case MSR_IA32_MCG_CAP: - case MSR_IA32_MC0_MISC: - case MSR_IA32_MC0_MISC+4: - case MSR_IA32_MC0_MISC+8: - case MSR_IA32_MC0_MISC+12: - case MSR_IA32_MC0_MISC+16: - case MSR_IA32_UCODE_REV: - case MSR_IA32_PERF_STATUS: - case MSR_IA32_EBL_CR_POWERON: - /* MTRR registers */ - case 0xfe: - case 0x200 ... 0x2ff: - data = 0; - break; - case 0xcd: /* fsb frequency */ - data = 3; - break; - case MSR_IA32_APICBASE: - data = kvm_get_apic_base(vcpu); - break; - case MSR_IA32_MISC_ENABLE: - data = vcpu->ia32_misc_enable_msr; - break; -#ifdef CONFIG_X86_64 - case MSR_EFER: - data = vcpu->shadow_efer; - break; -#endif - default: - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); - return 1; - } - *pdata = data; - return 0; -} -EXPORT_SYMBOL_GPL(kvm_get_msr_common); - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) -{ - return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); -} - -#ifdef CONFIG_X86_64 - -static void set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - if (efer & EFER_RESERVED_BITS) { - printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", - efer); - inject_gp(vcpu); - return; - } - - if (is_paging(vcpu) - && (vcpu->shadow_efer & EFER_LME) != (efer & EFER_LME)) { - printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); - inject_gp(vcpu); - return; - } - - kvm_x86_ops->set_efer(vcpu, efer); - - efer &= ~EFER_LMA; - efer |= vcpu->shadow_efer & EFER_LMA; - - vcpu->shadow_efer = efer; -} - -#endif - -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - switch (msr) { -#ifdef CONFIG_X86_64 - case MSR_EFER: - set_efer(vcpu, data); - break; -#endif - case MSR_IA32_MC0_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", - __FUNCTION__, data); - break; - case MSR_IA32_MCG_STATUS: - pr_unimpl(vcpu, "%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 */ - break; - case MSR_IA32_APICBASE: - kvm_set_apic_base(vcpu, data); - break; - case MSR_IA32_MISC_ENABLE: - vcpu->ia32_misc_enable_msr = data; - break; - default: - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_set_msr_common); - -/* - * Writes msr value into into the appropriate "register". - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) -{ - return kvm_x86_ops->set_msr(vcpu, msr_index, data); -} - -void kvm_resched(struct kvm_vcpu *vcpu) -{ - if (!need_resched()) - return; - cond_resched(); -} -EXPORT_SYMBOL_GPL(kvm_resched); - -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - int i; - u32 function; - struct kvm_cpuid_entry *e, *best; - - kvm_x86_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_x86_ops->decache_regs(vcpu); - kvm_x86_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; - - q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE, - PAGE_KERNEL); - if (!q) { - 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); - 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_x86_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_x86_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_x86_ops->decache_regs(vcpu); - - io->count -= io->cur_count; - io->cur_count = 0; - - return 0; -} - -static void kernel_pio(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu, - void *pd) -{ - /* TODO: String I/O for in kernel device */ - - mutex_lock(&vcpu->kvm->lock); - if (vcpu->pio.in) - kvm_iodevice_read(pio_dev, vcpu->pio.port, - vcpu->pio.size, - pd); - else - kvm_iodevice_write(pio_dev, vcpu->pio.port, - vcpu->pio.size, - pd); - mutex_unlock(&vcpu->kvm->lock); -} - -static void pio_string_write(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->pio; - void *pd = vcpu->pio_data; - int i; - - mutex_lock(&vcpu->kvm->lock); - for (i = 0; i < io->cur_count; i++) { - kvm_iodevice_write(pio_dev, io->port, - io->size, - pd); - pd += io->size; - } - mutex_unlock(&vcpu->kvm->lock); -} - -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) -{ - struct kvm_io_device *pio_dev; - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = 1; - vcpu->run->io.port = vcpu->pio.port = port; - vcpu->pio.in = in; - vcpu->pio.string = 0; - vcpu->pio.down = 0; - vcpu->pio.guest_page_offset = 0; - vcpu->pio.rep = 0; - - kvm_x86_ops->cache_regs(vcpu); - memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4); - kvm_x86_ops->decache_regs(vcpu); - - kvm_x86_ops->skip_emulated_instruction(vcpu); - - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (pio_dev) { - kernel_pio(pio_dev, vcpu, vcpu->pio_data); - complete_pio(vcpu); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio); - -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port) -{ - unsigned now, in_page; - int i, ret = 0; - int nr_pages = 1; - struct page *page; - struct kvm_io_device *pio_dev; - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = count; - vcpu->run->io.port = vcpu->pio.port = port; - vcpu->pio.in = in; - vcpu->pio.string = 1; - vcpu->pio.down = down; - vcpu->pio.guest_page_offset = offset_in_page(address); - vcpu->pio.rep = rep; - - if (!count) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return 1; - } - - 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. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - inject_gp(vcpu); - return 1; - } - vcpu->run->io.count = now; - vcpu->pio.cur_count = now; - - if (vcpu->pio.cur_count == vcpu->pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); - - for (i = 0; i < nr_pages; ++i) { - mutex_lock(&vcpu->kvm->lock); - page = gva_to_page(vcpu, address + i * PAGE_SIZE); - if (page) - get_page(page); - vcpu->pio.guest_pages[i] = page; - mutex_unlock(&vcpu->kvm->lock); - if (!page) { - inject_gp(vcpu); - free_pio_guest_pages(vcpu); - return 1; - } - } - - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (!vcpu->pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret >= 0 && pio_dev) { - pio_string_write(pio_dev, vcpu); - complete_pio(vcpu); - if (vcpu->pio.count == 0) - ret = 1; - } - } else if (pio_dev) - pr_unimpl(vcpu, "no string pio read support yet, " - "port %x size %d count %ld\n", - port, size, count); - - return ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); - -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - return (!vcpu->irq_summary && - kvm_run->request_interrupt_window && - vcpu->interrupt_window_open && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF)); -} - -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->cr8 = get_cr8(vcpu); - kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = 1; - else - kvm_run->ready_for_interrupt_injection = - (vcpu->interrupt_window_open && - vcpu->irq_summary == 0); -} - -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; - - if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) { - pr_debug("vcpu %d received sipi with vector # %x\n", - vcpu->vcpu_id, vcpu->sipi_vector); - kvm_lapic_reset(vcpu); - kvm_x86_ops->vcpu_reset(vcpu); - vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - } - -preempted: - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); - -again: - r = kvm_mmu_reload(vcpu); - if (unlikely(r)) - goto out; - - preempt_disable(); - - kvm_x86_ops->prepare_guest_switch(vcpu); - kvm_load_guest_fpu(vcpu); - - local_irq_disable(); - - if (signal_pending(current)) { - local_irq_enable(); - preempt_enable(); - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.signal_exits; - goto out; - } - - if (irqchip_in_kernel(vcpu->kvm)) - kvm_x86_ops->inject_pending_irq(vcpu); - else if (!vcpu->mmio_read_completed) - kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run); - - vcpu->guest_mode = 1; - kvm_guest_enter(); - - if (vcpu->requests) - if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests)) - kvm_x86_ops->tlb_flush(vcpu); - - kvm_x86_ops->run(vcpu, kvm_run); - - vcpu->guest_mode = 0; - local_irq_enable(); - - ++vcpu->stat.exits; - - /* - * We must have an instruction between local_irq_enable() and - * kvm_guest_exit(), so the timer interrupt isn't delayed by - * the interrupt shadow. The stat.exits increment will do nicely. - * But we need to prevent reordering, hence this barrier(): - */ - barrier(); - - kvm_guest_exit(); - - preempt_enable(); - - /* - * Profile KVM exit RIPs: - */ - if (unlikely(prof_on == KVM_PROFILING)) { - kvm_x86_ops->cache_regs(vcpu); - profile_hit(KVM_PROFILING, (void *)vcpu->rip); - } - - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); - - if (r > 0) { - if (dm_request_for_irq_injection(vcpu, kvm_run)) { - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.request_irq_exits; - goto out; - } - if (!need_resched()) { - ++vcpu->stat.light_exits; - goto again; - } - } - -out: - if (r > 0) { - kvm_resched(vcpu); - goto preempted; - } - - post_kvm_run_save(vcpu, kvm_run); - - return r; -} - - -static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; - sigset_t sigsaved; - - vcpu_load(vcpu); - - if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) { - kvm_vcpu_block(vcpu); - vcpu_put(vcpu); - return -EAGAIN; - } - - if (vcpu->sigset_active) - sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - - /* re-sync apic's tpr */ - if (!irqchip_in_kernel(vcpu->kvm)) - set_cr8(vcpu, kvm_run->cr8); - - if (vcpu->pio.cur_count) { - r = complete_pio(vcpu); - if (r) - goto out; - } - - 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, 1); - if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ - r = 0; - goto out; - } - } - - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { - kvm_x86_ops->cache_regs(vcpu); - vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; - kvm_x86_ops->decache_regs(vcpu); - } - - r = __vcpu_run(vcpu, kvm_run); - -out: - if (vcpu->sigset_active) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - vcpu_put(vcpu); - return r; -} - -static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, - struct kvm_regs *regs) -{ - vcpu_load(vcpu); - - kvm_x86_ops->cache_regs(vcpu); - - regs->rax = vcpu->regs[VCPU_REGS_RAX]; - regs->rbx = vcpu->regs[VCPU_REGS_RBX]; - regs->rcx = vcpu->regs[VCPU_REGS_RCX]; - regs->rdx = vcpu->regs[VCPU_REGS_RDX]; - regs->rsi = vcpu->regs[VCPU_REGS_RSI]; - regs->rdi = vcpu->regs[VCPU_REGS_RDI]; - regs->rsp = vcpu->regs[VCPU_REGS_RSP]; - regs->rbp = vcpu->regs[VCPU_REGS_RBP]; -#ifdef CONFIG_X86_64 - regs->r8 = vcpu->regs[VCPU_REGS_R8]; - regs->r9 = vcpu->regs[VCPU_REGS_R9]; - regs->r10 = vcpu->regs[VCPU_REGS_R10]; - regs->r11 = vcpu->regs[VCPU_REGS_R11]; - regs->r12 = vcpu->regs[VCPU_REGS_R12]; - regs->r13 = vcpu->regs[VCPU_REGS_R13]; - regs->r14 = vcpu->regs[VCPU_REGS_R14]; - regs->r15 = vcpu->regs[VCPU_REGS_R15]; -#endif - - regs->rip = vcpu->rip; - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, - struct kvm_regs *regs) -{ - vcpu_load(vcpu); - - vcpu->regs[VCPU_REGS_RAX] = regs->rax; - vcpu->regs[VCPU_REGS_RBX] = regs->rbx; - vcpu->regs[VCPU_REGS_RCX] = regs->rcx; - vcpu->regs[VCPU_REGS_RDX] = regs->rdx; - vcpu->regs[VCPU_REGS_RSI] = regs->rsi; - vcpu->regs[VCPU_REGS_RDI] = regs->rdi; - vcpu->regs[VCPU_REGS_RSP] = regs->rsp; - vcpu->regs[VCPU_REGS_RBP] = regs->rbp; -#ifdef CONFIG_X86_64 - vcpu->regs[VCPU_REGS_R8] = regs->r8; - vcpu->regs[VCPU_REGS_R9] = regs->r9; - vcpu->regs[VCPU_REGS_R10] = regs->r10; - vcpu->regs[VCPU_REGS_R11] = regs->r11; - vcpu->regs[VCPU_REGS_R12] = regs->r12; - vcpu->regs[VCPU_REGS_R13] = regs->r13; - vcpu->regs[VCPU_REGS_R14] = regs->r14; - vcpu->regs[VCPU_REGS_R15] = regs->r15; -#endif - - vcpu->rip = regs->rip; - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - - kvm_x86_ops->decache_regs(vcpu); - - vcpu_put(vcpu); - - return 0; -} - -static void get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - return kvm_x86_ops->get_segment(vcpu, var, seg); -} - -static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - struct descriptor_table dt; - int pending_vec; - - vcpu_load(vcpu); - - get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - get_segment(vcpu, &sregs->es, VCPU_SREG_ES); - get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - - get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - - kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; - kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; - - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - sregs->cr0 = vcpu->cr0; - sregs->cr2 = vcpu->cr2; - sregs->cr3 = vcpu->cr3; - sregs->cr4 = vcpu->cr4; - sregs->cr8 = get_cr8(vcpu); - sregs->efer = vcpu->shadow_efer; - sregs->apic_base = kvm_get_apic_base(vcpu); - - if (irqchip_in_kernel(vcpu->kvm)) { - memset(sregs->interrupt_bitmap, 0, - sizeof sregs->interrupt_bitmap); - pending_vec = kvm_x86_ops->get_irq(vcpu); - if (pending_vec >= 0) - set_bit(pending_vec, - (unsigned long *)sregs->interrupt_bitmap); - } else - memcpy(sregs->interrupt_bitmap, vcpu->irq_pending, - sizeof sregs->interrupt_bitmap); - - vcpu_put(vcpu); - - return 0; -} - -static void set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - return kvm_x86_ops->set_segment(vcpu, var, seg); -} - -static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - int mmu_reset_needed = 0; - int i, pending_vec, max_bits; - struct descriptor_table dt; - - vcpu_load(vcpu); - - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; - kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; - kvm_x86_ops->set_gdt(vcpu, &dt); - - vcpu->cr2 = sregs->cr2; - mmu_reset_needed |= vcpu->cr3 != sregs->cr3; - vcpu->cr3 = sregs->cr3; - - set_cr8(vcpu, sregs->cr8); - - mmu_reset_needed |= vcpu->shadow_efer != sregs->efer; -#ifdef CONFIG_X86_64 - kvm_x86_ops->set_efer(vcpu, sregs->efer); -#endif - kvm_set_apic_base(vcpu, sregs->apic_base); - - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - - mmu_reset_needed |= vcpu->cr0 != sregs->cr0; - vcpu->cr0 = sregs->cr0; - kvm_x86_ops->set_cr0(vcpu, sregs->cr0); - - mmu_reset_needed |= vcpu->cr4 != sregs->cr4; - kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) - load_pdptrs(vcpu, vcpu->cr3); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); - - if (!irqchip_in_kernel(vcpu->kvm)) { - memcpy(vcpu->irq_pending, sregs->interrupt_bitmap, - sizeof vcpu->irq_pending); - vcpu->irq_summary = 0; - for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i) - if (vcpu->irq_pending[i]) - __set_bit(i, &vcpu->irq_summary); - } else { - max_bits = (sizeof sregs->interrupt_bitmap) << 3; - pending_vec = find_first_bit( - (const unsigned long *)sregs->interrupt_bitmap, - max_bits); - /* Only pending external irq is handled here */ - if (pending_vec < max_bits) { - kvm_x86_ops->set_irq(vcpu, pending_vec); - pr_debug("Set back pending irq %d\n", - pending_vec); - } - } - - 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; -} - -void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - struct kvm_segment cs; - - get_segment(vcpu, &cs, VCPU_SREG_CS); - *db = cs.db; - *l = cs.l; -} -EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); - -/* - * Adapt set_msr() to msr_io()'s calling convention - */ -static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) -{ - return kvm_set_msr(vcpu, index, *data); -} - -/* - * Read or write a bunch of msrs. All parameters are kernel addresses. - * - * @return number of msrs set successfully. - */ -static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, - struct kvm_msr_entry *entries, - int (*do_msr)(struct kvm_vcpu *vcpu, - unsigned index, u64 *data)) -{ - int i; - - vcpu_load(vcpu); - - for (i = 0; i < msrs->nmsrs; ++i) - if (do_msr(vcpu, entries[i].index, &entries[i].data)) - break; - - vcpu_put(vcpu); - - return i; -} - -/* - * Read or write a bunch of msrs. Parameters are user addresses. - * - * @return number of msrs set successfully. - */ -static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, - int (*do_msr)(struct kvm_vcpu *vcpu, - unsigned index, u64 *data), - int writeback) -{ - struct kvm_msrs msrs; - struct kvm_msr_entry *entries; - int r, n; - unsigned size; - - r = -EFAULT; - if (copy_from_user(&msrs, user_msrs, sizeof msrs)) - goto out; - - r = -E2BIG; - if (msrs.nmsrs >= MAX_IO_MSRS) - goto out; - - r = -ENOMEM; - size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = vmalloc(size); - if (!entries) - goto out; - - r = -EFAULT; - if (copy_from_user(entries, user_msrs->entries, size)) - goto out_free; - - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; - - r = -EFAULT; - if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; - -out_free: - vfree(entries); -out: - return r; + } } /* - * Translate a guest virtual address to a guest physical address. + * The vCPU has executed a HLT instruction with in-kernel mode enabled. */ -static int kvm_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, - struct kvm_translation *tr) +void kvm_vcpu_block(struct kvm_vcpu *vcpu) { - unsigned long vaddr = tr->linear_address; - gpa_t gpa; + DECLARE_WAITQUEUE(wait, current); - vcpu_load(vcpu); - mutex_lock(&vcpu->kvm->lock); - gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr); - tr->physical_address = gpa; - tr->valid = gpa != UNMAPPED_GVA; - tr->writeable = 1; - tr->usermode = 0; - mutex_unlock(&vcpu->kvm->lock); - vcpu_put(vcpu); + add_wait_queue(&vcpu->wq, &wait); - return 0; + /* + * We will block until either an interrupt or a signal wakes us up + */ + while (!kvm_cpu_has_interrupt(vcpu) + && !signal_pending(current) + && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE + && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) { + set_current_state(TASK_INTERRUPTIBLE); + vcpu_put(vcpu); + schedule(); + vcpu_load(vcpu); + } + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&vcpu->wq, &wait); +} + +void kvm_resched(struct kvm_vcpu *vcpu) +{ + if (!need_resched()) + return; + cond_resched(); } +EXPORT_SYMBOL_GPL(kvm_resched); static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) @@ -2627,20 +682,6 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return 0; } -static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) -{ - int r; - - vcpu_load(vcpu); - - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); - - vcpu_put(vcpu); - - return r; -} - static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma, unsigned long address, int *type) @@ -2716,26 +757,21 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n) if (!valid_vcpu(n)) return -EINVAL; - vcpu = kvm_x86_ops->vcpu_create(kvm, n); + vcpu = kvm_arch_vcpu_create(kvm, n); if (IS_ERR(vcpu)) return PTR_ERR(vcpu); preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); - /* We do fxsave: this must be aligned. */ - BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF); - - vcpu_load(vcpu); - r = kvm_mmu_setup(vcpu); - vcpu_put(vcpu); - if (r < 0) - goto free_vcpu; + r = kvm_arch_vcpu_setup(vcpu); + if (r) + goto vcpu_destroy; mutex_lock(&kvm->lock); if (kvm->vcpus[n]) { r = -EEXIST; mutex_unlock(&kvm->lock); - goto mmu_unload; + goto vcpu_destroy; } kvm->vcpus[n] = vcpu; mutex_unlock(&kvm->lock); @@ -2750,56 +786,8 @@ unlink: mutex_lock(&kvm->lock); kvm->vcpus[n] = NULL; mutex_unlock(&kvm->lock); - -mmu_unload: - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); - -free_vcpu: - kvm_x86_ops->vcpu_free(vcpu); - return r; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - u64 efer; - int i; - struct kvm_cpuid_entry *e, *entry; - - rdmsrl(MSR_EFER, efer); - entry = NULL; - for (i = 0; i < vcpu->cpuid_nent; ++i) { - e = &vcpu->cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) { - entry->edx &= ~(1 << 20); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - -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; - cpuid_fix_nx_cap(vcpu); - return 0; - -out: +vcpu_destroy: + kvm_arch_vcpu_destroy(vcpu); return r; } @@ -2814,107 +802,27 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) 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 int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) -{ - vcpu_load(vcpu); - memcpy(s->regs, vcpu->apic->regs, sizeof *s); - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) -{ - vcpu_load(vcpu); - memcpy(vcpu->apic->regs, s->regs, sizeof *s); - kvm_apic_post_state_restore(vcpu); - vcpu_put(vcpu); - - return 0; -} - static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r; + if (vcpu->kvm->mm != current->mm) + return -EIO; switch (ioctl) { case KVM_RUN: r = -EINVAL; if (arg) goto out; - r = kvm_vcpu_ioctl_run(vcpu, vcpu->run); + r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); break; case KVM_GET_REGS: { struct kvm_regs kvm_regs; memset(&kvm_regs, 0, sizeof kvm_regs); - r = kvm_vcpu_ioctl_get_regs(vcpu, &kvm_regs); + r = kvm_arch_vcpu_ioctl_get_regs(vcpu, &kvm_regs); if (r) goto out; r = -EFAULT; @@ -2929,7 +837,7 @@ static long kvm_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs)) goto out; - r = kvm_vcpu_ioctl_set_regs(vcpu, &kvm_regs); + r = kvm_arch_vcpu_ioctl_set_regs(vcpu, &kvm_regs); if (r) goto out; r = 0; @@ -2939,7 +847,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_sregs kvm_sregs; memset(&kvm_sregs, 0, sizeof kvm_sregs); - r = kvm_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs); + r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs); if (r) goto out; r = -EFAULT; @@ -2954,7 +862,7 @@ static long kvm_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs)) goto out; - r = kvm_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs); + r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs); if (r) goto out; r = 0; @@ -2966,7 +874,7 @@ static long kvm_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&tr, argp, sizeof tr)) goto out; - r = kvm_vcpu_ioctl_translate(vcpu, &tr); + r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; @@ -2993,30 +901,12 @@ static long kvm_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof dbg)) goto out; - r = kvm_vcpu_ioctl_debug_guest(vcpu, &dbg); + r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg); if (r) goto out; r = 0; break; } - case KVM_GET_MSRS: - r = msr_io(vcpu, argp, kvm_get_msr, 1); - break; - 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; @@ -3044,7 +934,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu fpu; memset(&fpu, 0, sizeof fpu); - r = kvm_vcpu_ioctl_get_fpu(vcpu, &fpu); + r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, &fpu); if (r) goto out; r = -EFAULT; @@ -3059,39 +949,14 @@ static long kvm_vcpu_ioctl(struct file *filp, 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; - } - case KVM_GET_LAPIC: { - struct kvm_lapic_state lapic; - - memset(&lapic, 0, sizeof lapic); - r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &lapic, sizeof lapic)) - goto out; - r = 0; - break; - } - case KVM_SET_LAPIC: { - struct kvm_lapic_state lapic; - - r = -EFAULT; - if (copy_from_user(&lapic, argp, sizeof lapic)) - goto out; - r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);; + r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, &fpu); if (r) goto out; r = 0; break; } default: - ; + r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: return r; @@ -3102,30 +967,16 @@ static long kvm_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r; + if (kvm->mm != current->mm) + return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); if (r < 0) goto out; break; - case KVM_SET_MEMORY_REGION: { - struct kvm_memory_region kvm_mem; - struct kvm_userspace_memory_region kvm_userspace_mem; - - r = -EFAULT; - if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) - goto out; - kvm_userspace_mem.slot = kvm_mem.slot; - kvm_userspace_mem.flags = kvm_mem.flags; - kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr; - kvm_userspace_mem.memory_size = kvm_mem.memory_size; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0); - if (r) - goto out; - break; - } case KVM_SET_USER_MEMORY_REGION: { struct kvm_userspace_memory_region kvm_userspace_mem; @@ -3139,14 +990,6 @@ static long kvm_vm_ioctl(struct file *filp, goto out; break; } - case KVM_SET_NR_MMU_PAGES: - r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); - if (r) - goto out; - break; - case KVM_GET_NR_MMU_PAGES: - r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); - break; case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; @@ -3158,87 +1001,8 @@ 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; - } - case KVM_CREATE_IRQCHIP: - r = -ENOMEM; - kvm->vpic = kvm_create_pic(kvm); - if (kvm->vpic) { - r = kvm_ioapic_init(kvm); - if (r) { - kfree(kvm->vpic); - kvm->vpic = NULL; - goto out; - } - } else - goto out; - break; - case KVM_IRQ_LINE: { - struct kvm_irq_level irq_event; - - r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) - goto out; - if (irqchip_in_kernel(kvm)) { - mutex_lock(&kvm->lock); - if (irq_event.irq < 16) - kvm_pic_set_irq(pic_irqchip(kvm), - irq_event.irq, - irq_event.level); - kvm_ioapic_set_irq(kvm->vioapic, - irq_event.irq, - irq_event.level); - mutex_unlock(&kvm->lock); - r = 0; - } - break; - } - case KVM_GET_IRQCHIP: { - /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; - - r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) - goto out; - r = -ENXIO; - if (!irqchip_in_kernel(kvm)) - goto out; - r = kvm_vm_ioctl_get_irqchip(kvm, &chip); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &chip, sizeof chip)) - goto out; - r = 0; - break; - } - case KVM_SET_IRQCHIP: { - /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; - - r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) - goto out; - r = -ENXIO; - if (!irqchip_in_kernel(kvm)) - goto out; - r = kvm_vm_ioctl_set_irqchip(kvm, &chip); - if (r) - goto out; - r = 0; - break; - } default: - ; + r = kvm_arch_vm_ioctl(filp, ioctl, arg); } out: return r; @@ -3253,10 +1017,14 @@ static struct page *kvm_vm_nopage(struct vm_area_struct *vma, struct page *page; pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = gfn_to_page(kvm, pgoff); - if (!page) + if (!kvm_is_visible_gfn(kvm, pgoff)) return NOPAGE_SIGBUS; - get_page(page); + /* current->mm->mmap_sem is already held so call lockless version */ + page = __gfn_to_page(kvm, pgoff); + if (is_error_page(page)) { + kvm_release_page_clean(page); + return NOPAGE_SIGBUS; + } if (type != NULL) *type = VM_FAULT_MINOR; @@ -3320,22 +1088,9 @@ static long kvm_dev_ioctl(struct file *filp, goto out; r = kvm_dev_ioctl_create_vm(); break; - case KVM_CHECK_EXTENSION: { - int ext = (long)argp; - - switch (ext) { - case KVM_CAP_IRQCHIP: - case KVM_CAP_HLT: - case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: - case KVM_CAP_USER_MEMORY: - r = 1; - break; - default: - r = 0; - break; - } + case KVM_CHECK_EXTENSION: + r = kvm_dev_ioctl_check_extension((long)argp); break; - } case KVM_GET_VCPU_MMAP_SIZE: r = -EINVAL; if (arg) @@ -3360,41 +1115,6 @@ static struct miscdevice kvm_dev = { &kvm_chardev_ops, }; -/* - * Make sure that a cpu that is being hot-unplugged does not have any vcpus - * cached on it. - */ -static void decache_vcpus_on_cpu(int cpu) -{ - struct kvm *vm; - struct kvm_vcpu *vcpu; - int i; - - spin_lock(&kvm_lock); - list_for_each_entry(vm, &vm_list, vm_list) - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = vm->vcpus[i]; - if (!vcpu) - continue; - /* - * If the vcpu is locked, then it is running on some - * other cpu and therefore it is not cached on the - * cpu in question. - * - * If it's not locked, check the last cpu it executed - * on. - */ - if (mutex_trylock(&vcpu->mutex)) { - if (vcpu->cpu == cpu) { - kvm_x86_ops->vcpu_decache(vcpu); - vcpu->cpu = -1; - } - mutex_unlock(&vcpu->mutex); - } - } - spin_unlock(&kvm_lock); -} - static void hardware_enable(void *junk) { int cpu = raw_smp_processor_id(); @@ -3402,7 +1122,7 @@ static void hardware_enable(void *junk) if (cpu_isset(cpu, cpus_hardware_enabled)) return; cpu_set(cpu, cpus_hardware_enabled); - kvm_x86_ops->hardware_enable(NULL); + kvm_arch_hardware_enable(NULL); } static void hardware_disable(void *junk) @@ -3413,7 +1133,7 @@ static void hardware_disable(void *junk) return; cpu_clear(cpu, cpus_hardware_enabled); decache_vcpus_on_cpu(cpu); - kvm_x86_ops->hardware_disable(NULL); + kvm_arch_hardware_disable(NULL); } static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, @@ -3421,21 +1141,19 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, { int cpu = (long)v; + val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: - case CPU_DYING_FROZEN: printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", cpu); hardware_disable(NULL); break; case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", cpu); smp_call_function_single(cpu, hardware_disable, NULL, 0, 1); break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); smp_call_function_single(cpu, hardware_enable, NULL, 0, 1); @@ -3505,7 +1223,22 @@ static struct notifier_block kvm_cpu_notifier = { .priority = 20, /* must be > scheduler priority */ }; -static u64 stat_get(void *_offset) +static u64 vm_stat_get(void *_offset) +{ + unsigned offset = (long)_offset; + u64 total = 0; + struct kvm *kvm; + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + total += *(u32 *)((void *)kvm + offset); + spin_unlock(&kvm_lock); + return total; +} + +DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n"); + +static u64 vcpu_stat_get(void *_offset) { unsigned offset = (long)_offset; u64 total = 0; @@ -3524,9 +1257,14 @@ static u64 stat_get(void *_offset) return total; } -DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, NULL, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n"); -static __init void kvm_init_debug(void) +static struct file_operations *stat_fops[] = { + [KVM_STAT_VCPU] = &vcpu_stat_fops, + [KVM_STAT_VM] = &vm_stat_fops, +}; + +static void kvm_init_debug(void) { struct kvm_stats_debugfs_item *p; @@ -3534,7 +1272,7 @@ static __init void kvm_init_debug(void) for (p = debugfs_entries; p->name; ++p) p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir, (void *)(long)p->offset, - &stat_fops); + stat_fops[p->kind]); } static void kvm_exit_debug(void) @@ -3569,7 +1307,7 @@ static struct sys_device kvm_sysdev = { .cls = &kvm_sysdev_class, }; -hpa_t bad_page_address; +struct page *bad_page; static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) @@ -3581,7 +1319,7 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - kvm_x86_ops->vcpu_load(vcpu, cpu); + kvm_arch_vcpu_load(vcpu, cpu); } static void kvm_sched_out(struct preempt_notifier *pn, @@ -3589,38 +1327,35 @@ static void kvm_sched_out(struct preempt_notifier *pn, { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - kvm_x86_ops->vcpu_put(vcpu); + kvm_arch_vcpu_put(vcpu); } -int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size, +int kvm_init(void *opaque, unsigned int vcpu_size, struct module *module) { int r; int cpu; - if (kvm_x86_ops) { - printk(KERN_ERR "kvm: already loaded the other module\n"); - return -EEXIST; - } + kvm_init_debug(); - if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); - return -EOPNOTSUPP; - } - if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); - return -EOPNOTSUPP; - } + r = kvm_arch_init(opaque); + if (r) + goto out4; - kvm_x86_ops = ops; + bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + + if (bad_page == NULL) { + r = -ENOMEM; + goto out; + } - r = kvm_x86_ops->hardware_setup(); + r = kvm_arch_hardware_setup(); if (r < 0) goto out; for_each_online_cpu(cpu) { smp_call_function_single(cpu, - kvm_x86_ops->check_processor_compatibility, + kvm_arch_check_processor_compat, &r, 0, 1); if (r < 0) goto out_free_0; @@ -3642,7 +1377,8 @@ int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size, /* A kmem cache lets us meet the alignment requirements of fx_save. */ kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, - __alignof__(struct kvm_vcpu), 0, 0); + __alignof__(struct kvm_vcpu), + 0, NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; goto out_free_4; @@ -3659,8 +1395,6 @@ int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; - kvm_mmu_set_nonpresent_ptes(0ull, 0ull); - return 0; out_free: @@ -3675,14 +1409,16 @@ out_free_2: out_free_1: on_each_cpu(hardware_disable, NULL, 0, 1); out_free_0: - kvm_x86_ops->hardware_unsetup(); + kvm_arch_hardware_unsetup(); out: - kvm_x86_ops = NULL; + kvm_arch_exit(); + kvm_exit_debug(); +out4: return r; } -EXPORT_SYMBOL_GPL(kvm_init_x86); +EXPORT_SYMBOL_GPL(kvm_init); -void kvm_exit_x86(void) +void kvm_exit(void) { misc_deregister(&kvm_dev); kmem_cache_destroy(kvm_vcpu_cache); @@ -3691,49 +1427,9 @@ void kvm_exit_x86(void) unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); on_each_cpu(hardware_disable, NULL, 0, 1); - kvm_x86_ops->hardware_unsetup(); - kvm_x86_ops = NULL; -} -EXPORT_SYMBOL_GPL(kvm_exit_x86); - -static __init int kvm_init(void) -{ - static struct page *bad_page; - int r; - - r = kvm_mmu_module_init(); - if (r) - goto out4; - - kvm_init_debug(); - - kvm_arch_init(); - - bad_page = alloc_page(GFP_KERNEL); - - if (bad_page == NULL) { - r = -ENOMEM; - goto out; - } - - bad_page_address = page_to_pfn(bad_page) << PAGE_SHIFT; - memset(__va(bad_page_address), 0, PAGE_SIZE); - - return 0; - -out: - kvm_exit_debug(); - kvm_mmu_module_exit(); -out4: - return r; -} - -static __exit void kvm_exit(void) -{ + kvm_arch_hardware_unsetup(); + kvm_arch_exit(); kvm_exit_debug(); - __free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT)); - kvm_mmu_module_exit(); + __free_page(bad_page); } - -module_init(kvm_init) -module_exit(kvm_exit) +EXPORT_SYMBOL_GPL(kvm_exit);