[RFC PATCH v3 2/5] KVM: x86: Add new hypercall to lock control registers

[Mickaël Salaün <mic@xxxxxxxxxxx>]

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@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Madhavan T. Venkataraman <madvenka@xxxxxxxxxxxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Cc: Wanpeng Li <wanpengli@xxxxxxxxxxx>
Signed-off-by: Mickaël Salaün <mic@xxxxxxxxxxx>
Link: https://lore.kernel.org/r/20240503131910.307630-3-mic@xxxxxxxxxxx
---

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              |  7 +-
 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, 141 insertions(+), 2 deletions(-)

diff --git a/Documentation/virt/kvm/x86/hypercalls.rst 
b/Documentation/virt/kvm/x86/hypercalls.rst
index 10db7924720f..3178576f4c47 100644
--- a/Documentation/virt/kvm/x86/hypercalls.rst
+++ b/Documentation/virt/kvm/x86/hypercalls.rst
@@ -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.
diff --git a/arch/x86/include/uapi/asm/kvm_para.h 
b/arch/x86/include/uapi/asm/kvm_para.h
index a1efa7907a0b..cfc17f3d1877 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -149,4 +149,6 @@ 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 */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 605c26c009c8..69695d9d6e2a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -398,8 +398,11 @@ 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 = X86_CR4_SMEP | X86_CR4_SMAP | 
X86_CR4_UMIP |
-                                            X86_CR4_FSGSBASE | X86_CR4_CET | 
X86_CR4_FRED;
+const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP |
+                                     X86_CR4_UMIP | X86_CR4_FSGSBASE |
+                                     X86_CR4_CET | X86_CR4_FRED;
+EXPORT_SYMBOL_GPL(cr4_pinned_mask);
+
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 22411f4aff53..7ba970b525f7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5453,6 +5453,11 @@ 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);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 91478b769af0..a5f47be59abc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8281,11 +8281,86 @@ 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));
@@ -10142,6 +10217,15 @@ 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;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a8b71803777b..ade7d68ddaff 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -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);
@@ -327,6 +347,8 @@ 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;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 48f31dcd318a..6ff13937929a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -836,6 +836,11 @@ 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
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 960c7e93d1a9..2ed418704603 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -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
-- 
2.45.0