X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fkvm%2Fkvm_main.c;h=33eade7e237c4072f57f4ff0f75f8d3a6607e504;hb=df513e2cdd099822ed32cbc20aaf4ff310372202;hp=dc7a8c78cbf9f31297e922d6b2c4a270ce75d21d;hpb=fbeb1f19229baa9ee80f315e9d24635045455082;p=linux-2.6-omap-h63xx.git diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c index dc7a8c78cbf..33eade7e237 100644 --- a/drivers/kvm/kvm_main.c +++ b/drivers/kvm/kvm_main.c @@ -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) @@ -1177,7 +1193,7 @@ 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 +1217,19 @@ 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); @@ -1442,6 +1467,10 @@ 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 */ @@ -1502,29 +1531,243 @@ 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; + } + + vcpu->run->io_completed = 0; + + 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 (kvm_run->mmio_completed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; + if (kvm_run->io_completed) { + if (vcpu->pio.cur_count) { + r = complete_pio(vcpu); + if (r) + goto out; + } else { + memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + vcpu->mmio_read_completed = 1; + } } 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; } @@ -1665,16 +1908,6 @@ 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); @@ -1697,7 +1930,7 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_arch_ops->decache_cr0_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 +1947,16 @@ 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 +2130,36 @@ 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 +2172,7 @@ 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 +2221,7 @@ 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)) @@ -1961,6 +2236,18 @@ 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; @@ -1990,11 +2277,46 @@ 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; +} + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2003,21 +2325,12 @@ 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)) - goto out; - r = kvm_vcpu_ioctl_run(vcpu, &kvm_run); - if (r < 0 && r != -EINTR) + case KVM_RUN: + r = -EINVAL; + if (arg) 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 +2426,41 @@ 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; + } default: ; } @@ -2248,13 +2596,19 @@ 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 +2638,18 @@ 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 +2665,7 @@ static struct file_operations kvm_chardev_ops = { }; static struct miscdevice kvm_dev = { - MISC_DYNAMIC_MINOR, + KVM_MINOR, "kvm", &kvm_chardev_ops, };