@@ -190,3 +190,20 @@ the KVM_CAP_EXIT_HYPERCALL capability. Userspace must enable that capability
before advertising KVM_FEATURE_HC_MAP_GPA_RANGE in the guest CPUID. In
addition, if the guest supports KVM_FEATURE_MIGRATION_CONTROL, userspace
must also set up an MSR filter to process writes to MSR_KVM_MIGRATION_CONTROL.
+
+9. KVM_HC_LOCK_CR_UPDATE
+------------------------
+
+:Architecture: x86
+:Status: active
+:Purpose: Request some control registers to be restricted.
+
+- a0: identify a control register
+- a1: bit mask to make some flags read-only
+- a2: optional KVM_LOCK_CR_UPDATE_VERSION flag that will return the version of
+ this hypercall. Version 1 supports CR0 and CR4 pinning.
+
+The hypercall lets a guest request control register flags to be pinned for
+itself.
+
+Returns 0 on success or a KVM error code otherwise.
@@ -150,4 +150,6 @@ struct kvm_vcpu_pv_apf_data {
#define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
#define KVM_PV_EOI_DISABLED 0x0
+#define KVM_LOCK_CR_UPDATE_VERSION (1 << 0)
+
#endif /* _UAPI_ASM_X86_KVM_PARA_H */
@@ -400,9 +400,11 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
}
/* These bits should not change their value after CPU init is finished. */
-static const unsigned long cr4_pinned_mask =
+const unsigned long cr4_pinned_mask =
X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
X86_CR4_FSGSBASE | X86_CR4_CET;
+EXPORT_SYMBOL_GPL(cr4_pinned_mask);
+
static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
static unsigned long cr4_pinned_bits __ro_after_init;
@@ -5452,6 +5452,11 @@ static int handle_cr(struct kvm_vcpu *vcpu)
case 0: /* mov to cr */
val = kvm_register_read(vcpu, reg);
trace_kvm_cr_write(cr, val);
+
+ ret = heki_check_cr(vcpu, cr, val);
+ if (ret)
+ return ret;
+
switch (cr) {
case 0:
err = handle_set_cr0(vcpu, val);
@@ -8054,11 +8054,86 @@ static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr)
return value;
}
+#ifdef CONFIG_HEKI
+
+#define HEKI_ABI_VERSION 1
+
+static int heki_lock_cr(struct kvm_vcpu *const vcpu, const unsigned long cr,
+ unsigned long pin, unsigned long flags)
+{
+ if (flags) {
+ if ((flags == KVM_LOCK_CR_UPDATE_VERSION) && !cr && !pin)
+ return HEKI_ABI_VERSION;
+ return -KVM_EINVAL;
+ }
+
+ if (!pin)
+ return -KVM_EINVAL;
+
+ switch (cr) {
+ case 0:
+ /* Cf. arch/x86/kernel/cpu/common.c */
+ if (!(pin & X86_CR0_WP))
+ return -KVM_EINVAL;
+
+ if ((pin & read_cr0()) != pin)
+ return -KVM_EINVAL;
+
+ atomic_long_or(pin, &vcpu->kvm->heki_pinned_cr0);
+ return 0;
+ case 4:
+ /* Checks for irrelevant bits. */
+ if ((pin & cr4_pinned_mask) != pin)
+ return -KVM_EINVAL;
+
+ /* Ignores bits not present in host. */
+ pin &= __read_cr4();
+ atomic_long_or(pin, &vcpu->kvm->heki_pinned_cr4);
+ return 0;
+ }
+ return -KVM_EINVAL;
+}
+
+int heki_check_cr(struct kvm_vcpu *const vcpu, const unsigned long cr,
+ const unsigned long val)
+{
+ unsigned long pinned;
+
+ switch (cr) {
+ case 0:
+ pinned = atomic_long_read(&vcpu->kvm->heki_pinned_cr0);
+ if ((val & pinned) != pinned) {
+ pr_warn_ratelimited(
+ "heki: Blocked CR0 update: 0x%lx\n", val);
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ return 0;
+ case 4:
+ pinned = atomic_long_read(&vcpu->kvm->heki_pinned_cr4);
+ if ((val & pinned) != pinned) {
+ pr_warn_ratelimited(
+ "heki: Blocked CR4 update: 0x%lx\n", val);
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ return 0;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(heki_check_cr);
+
+#endif /* CONFIG_HEKI */
+
static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
int res = 0;
+ res = heki_check_cr(vcpu, cr, val);
+ if (res)
+ return res;
+
switch (cr) {
case 0:
res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
@@ -9918,6 +9993,15 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
vcpu->arch.complete_userspace_io = complete_hypercall_exit;
return 0;
}
+#ifdef CONFIG_HEKI
+ case KVM_HC_LOCK_CR_UPDATE:
+ if (a0 > U32_MAX) {
+ ret = -KVM_EINVAL;
+ } else {
+ ret = heki_lock_cr(vcpu, a0, a1, a2);
+ }
+ break;
+#endif /* CONFIG_HEKI */
default:
ret = -KVM_ENOSYS;
break;
@@ -290,6 +290,26 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
return !(kvm->arch.disabled_quirks & quirk);
}
+#ifdef CONFIG_HEKI
+
+int heki_check_cr(struct kvm_vcpu *vcpu, unsigned long cr, unsigned long val);
+
+#else /* CONFIG_HEKI */
+
+static inline int heki_check_cr(struct kvm_vcpu *vcpu, unsigned long cr,
+ unsigned long val)
+{
+ return 0;
+}
+
+static inline int heki_lock_cr(struct kvm_vcpu *const vcpu, unsigned long cr,
+ unsigned long pin)
+{
+ return 0;
+}
+
+#endif /* CONFIG_HEKI */
+
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
u64 get_kvmclock_ns(struct kvm *kvm);
@@ -325,6 +345,8 @@ extern u64 host_xcr0;
extern u64 host_xss;
extern u64 host_arch_capabilities;
+extern const unsigned long cr4_pinned_mask;
+
extern struct kvm_caps kvm_caps;
extern bool enable_pmu;
@@ -835,6 +835,11 @@ struct kvm {
bool vm_bugged;
bool vm_dead;
+#ifdef CONFIG_HEKI
+ atomic_long_t heki_pinned_cr0;
+ atomic_long_t heki_pinned_cr4;
+#endif /* CONFIG_HEKI */
+
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#endif
@@ -30,6 +30,7 @@
#define KVM_HC_SEND_IPI 10
#define KVM_HC_SCHED_YIELD 11
#define KVM_HC_MAP_GPA_RANGE 12
+#define KVM_HC_LOCK_CR_UPDATE 13
/*
* hypercalls use architecture specific
This enables guests to lock their CR0 and CR4 registers with a subset of X86_CR0_WP, X86_CR4_SMEP, X86_CR4_SMAP, X86_CR4_UMIP, X86_CR4_FSGSBASE and X86_CR4_CET flags. The new KVM_HC_LOCK_CR_UPDATE hypercall takes three arguments. The first is to identify the control register, the second is a bit mask to pin (i.e. mark as read-only), and the third is for optional flags. These register flags should already be pinned by Linux guests, but once compromised, this self-protection mechanism could be disabled, which is not the case with this dedicated hypercall. Once the CRs are pinned by the guest, if it attempts to change them, then a general protection fault is sent to the guest. This hypercall may evolve and support new kind of registers or pinning. The optional KVM_LOCK_CR_UPDATE_VERSION flag enables guests to know the supported abilities by mapping the returned version with the related features. Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Wanpeng Li <wanpengli@tencent.com> Signed-off-by: Mickaël Salaün <mic@digikod.net> --- Changes since v1: * Guard KVM_HC_LOCK_CR_UPDATE hypercall with CONFIG_HEKI. * Move extern cr4_pinned_mask to x86.h (suggested by Kees Cook). * Move VMX CR checks from vmx_set_cr*() to handle_cr() to make it possible to return to user space (see next commit). * Change the heki_check_cr()'s first argument to vcpu. * Don't use -KVM_EPERM in heki_check_cr(). * Generate a fault when the guest requests a denied CR update. * Add a flags argument to get the version of this hypercall. Being able to do a preper version check was suggested by Wei Liu. --- Documentation/virt/kvm/x86/hypercalls.rst | 17 +++++ arch/x86/include/uapi/asm/kvm_para.h | 2 + arch/x86/kernel/cpu/common.c | 4 +- arch/x86/kvm/vmx/vmx.c | 5 ++ arch/x86/kvm/x86.c | 84 +++++++++++++++++++++++ arch/x86/kvm/x86.h | 22 ++++++ include/linux/kvm_host.h | 5 ++ include/uapi/linux/kvm_para.h | 1 + 8 files changed, 139 insertions(+), 1 deletion(-)