On Fri, Oct 20, 2017 at 4:25 PM, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
> On x86, struct kvm_vcpu has a usercopy region corresponding to the CPUID
> entries. The area is read and written by the KVM_GET/SET_CPUID2 ioctls.
> Without this patch, KVM is completely broken on x86 with usercopy
> hardening enabled.
>
> Define kvm_init in terms of a more generic function that allows setting
> a usercopy region. Because x86 has separate kvm_init callers for Intel and
> AMD, another variant called kvm_init_x86 passes the region corresponding
> to the cpuid_entries array.
>
> Reported-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: kernel-hardening@xxxxxxxxxxxxxxxxxx
> Cc: Kees Cook <keescook@xxxxxxxxxxxx>
> Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
> Cc: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
> Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
> Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
> Cc: Cornelia Huck <cohuck@xxxxxxxxxx>
> Cc: James Hogan <james.hogan@xxxxxxxxxx>
> Cc: Paul Mackerras <paulus@xxxxxxxxx>
> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> ---
> The patch is on top of linux-next.
>
> arch/x86/include/asm/kvm_host.h | 3 +++
> arch/x86/kvm/svm.c | 4 ++--
> arch/x86/kvm/vmx.c | 4 ++--
> arch/x86/kvm/x86.c | 10 ++++++++++
> include/linux/kvm_host.h | 13 +++++++++++--
> virt/kvm/kvm_main.c | 13 ++++++++-----
> 6 files changed, 36 insertions(+), 11 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 6b8f937ca398..bb8243d413d0 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1420,6 +1420,9 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
>
> static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
>
> +int kvm_init_x86(struct kvm_x86_ops *kvm_x86_ops, unsigned vcpu_size,
> + unsigned vcpu_align, struct module *module);
> +
> static inline int kvm_cpu_get_apicid(int mps_cpu)
> {
> #ifdef CONFIG_X86_LOCAL_APIC
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index ff94552f85d0..457433c3a703 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -5594,8 +5594,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
>
> static int __init svm_init(void)
> {
> - return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm),
> - __alignof__(struct vcpu_svm), THIS_MODULE);
> + return kvm_init_x86(&svm_x86_ops, sizeof(struct vcpu_svm),
> + __alignof__(struct vcpu_svm), THIS_MODULE);
> }
>
> static void __exit svm_exit(void)
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index c460b0b439d3..6e78530df6a8 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -12106,8 +12106,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
>
> static int __init vmx_init(void)
> {
> - int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
> - __alignof__(struct vcpu_vmx), THIS_MODULE);
> + int r = kvm_init_x86(&vmx_x86_ops, sizeof(struct vcpu_vmx),
> + __alignof__(struct vcpu_vmx), THIS_MODULE);
> if (r)
> return r;
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 5669af09b732..415529a78c37 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -8181,6 +8181,16 @@ void kvm_arch_sync_events(struct kvm *kvm)
> kvm_free_pit(kvm);
> }
>
> +int kvm_init_x86(struct kvm_x86_ops *kvm_x86_ops, unsigned vcpu_size,
> + unsigned vcpu_align, struct module *module)
> +{
> + return kvm_init_usercopy(kvm_x86_ops, vcpu_size, vcpu_align,
> + offsetof(struct kvm_vcpu_arch, cpuid_entries),
> + sizeof_field(struct kvm_vcpu_arch, cpuid_entries),
> + module);
> +}
> +EXPORT_SYMBOL_GPL(kvm_init_x86);
> +
> int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
> {
> int i, r;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 6882538eda32..21e19658b086 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -561,8 +561,17 @@ static inline void kvm_irqfd_exit(void)
> {
> }
> #endif
> -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> - struct module *module);
> +
> +int kvm_init_usercopy(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> + unsigned vcpu_usercopy_start, unsigned vcpu_usercopy_size,
> + struct module *module);
> +
> +static inline int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> + struct module *module)
> +{
> + return kvm_init_usercopy(opaque, vcpu_size, vcpu_align, 0, 0, module);
> +}
> +
> void kvm_exit(void);
>
> void kvm_get_kvm(struct kvm *kvm);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 261c782a688f..ac889b28bb54 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -3959,8 +3959,9 @@ static void kvm_sched_out(struct preempt_notifier *pn,
> kvm_arch_vcpu_put(vcpu);
> }
>
> -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> - struct module *module)
> +int kvm_init_usercopy(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> + unsigned vcpu_arch_usercopy_start, unsigned vcpu_arch_usercopy_size,
> + struct module *module)
> {
> int r;
> int cpu;
> @@ -4006,8 +4007,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> /* A kmem cache lets us meet the alignment requirements of fx_save. */
> if (!vcpu_align)
> vcpu_align = __alignof__(struct kvm_vcpu);
> - kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align,
> - SLAB_ACCOUNT, NULL);
> + kvm_vcpu_cache = kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
> + SLAB_ACCOUNT,
> + offsetof(struct kvm_vcpu, arch) + vcpu_arch_usercopy_start,
> + vcpu_arch_usercopy_size, NULL);
I adjusted this hunk for the usercopy tree (SLAB_ACCOUNT got added in
the KVM tree, I think).
-Kees
> if (!kvm_vcpu_cache) {
> r = -ENOMEM;
> goto out_free_3;
> @@ -4065,7 +4068,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
> out_fail:
> return r;
> }
> -EXPORT_SYMBOL_GPL(kvm_init);
> +EXPORT_SYMBOL_GPL(kvm_init_usercopy);
>
> void kvm_exit(void)
> {
> --
> 2.14.2
>
>
--
Kees Cook
Pixel Security
