diff mbox series

[01/16] KVM: x86/mmu: Exit to userspace with -EFAULT if private fault hits emulation

Message ID 20240228024147.41573-2-seanjc@google.com
State New
Headers
Series KVM: x86/mmu: Page fault and MMIO cleanups |

Commit Message

Sean Christopherson Feb. 28, 2024, 2:41 a.m. UTC 
  Exit to userspace with -EFAULT / KVM_EXIT_MEMORY_FAULT if a private fault
triggers emulation of any kind, as KVM doesn't currently support emulating
access to guest private memory.  Practically speaking, private faults and
emulation are already mutually exclusive, but there are edge cases upon
edge cases where KVM can return RET_PF_EMULATE, and adding one last check
to harden against weird, unexpected combinations is inexpensive.

Suggested-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c          |  8 --------
 arch/x86/kvm/mmu/mmu_internal.h | 13 +++++++++++++
 2 files changed, 13 insertions(+), 8 deletions(-)

Comments

Xiaoyao Li March 1, 2024, 8:48 a.m. UTC | #1 
On 2/28/2024 10:41 AM, Sean Christopherson wrote:
> Exit to userspace with -EFAULT / KVM_EXIT_MEMORY_FAULT if a private fault
> triggers emulation of any kind, as KVM doesn't currently support emulating
> access to guest private memory.  Practically speaking, private faults and
> emulation are already mutually exclusive, but there are edge cases upon
> edge cases where KVM can return RET_PF_EMULATE, and adding one last check
> to harden against weird, unexpected combinations is inexpensive.
> 
> Suggested-by: Yan Zhao <yan.y.zhao@intel.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>   arch/x86/kvm/mmu/mmu.c          |  8 --------
>   arch/x86/kvm/mmu/mmu_internal.h | 13 +++++++++++++
>   2 files changed, 13 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index e4cc7f764980..e2fd74e06ff8 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4309,14 +4309,6 @@ static inline u8 kvm_max_level_for_order(int order)
>   	return PG_LEVEL_4K;
>   }
>   
> -static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
> -					      struct kvm_page_fault *fault)
> -{
> -	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
> -				      PAGE_SIZE, fault->write, fault->exec,
> -				      fault->is_private);
> -}
> -
>   static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
>   				   struct kvm_page_fault *fault)
>   {
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index 0669a8a668ca..0eea6c5a824d 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -279,6 +279,14 @@ enum {
>   	RET_PF_SPURIOUS,
>   };
>   
> +static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
> +						     struct kvm_page_fault *fault)
> +{
> +	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
> +				      PAGE_SIZE, fault->write, fault->exec,
> +				      fault->is_private);
> +}
> +
>   static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>   					u32 err, bool prefetch, int *emulation_type)
>   {
> @@ -320,6 +328,11 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>   	else
>   		r = vcpu->arch.mmu->page_fault(vcpu, &fault);

Beg for some comment to explain the paraniod.

> +	if (r == RET_PF_EMULATE && fault.is_private) {
> +		kvm_mmu_prepare_memory_fault_exit(vcpu, &fault);
> +		return -EFAULT;
> +	}
> +
>   	if (fault.write_fault_to_shadow_pgtable && emulation_type)
>   		*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;
>
diff mbox series

Patch

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e4cc7f764980..e2fd74e06ff8 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4309,14 +4309,6 @@  static inline u8 kvm_max_level_for_order(int order)
 	return PG_LEVEL_4K;
 }
 
-static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
-					      struct kvm_page_fault *fault)
-{
-	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
-				      PAGE_SIZE, fault->write, fault->exec,
-				      fault->is_private);
-}
-
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 				   struct kvm_page_fault *fault)
 {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 0669a8a668ca..0eea6c5a824d 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -279,6 +279,14 @@  enum {
 	RET_PF_SPURIOUS,
 };
 
+static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						     struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
 static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 					u32 err, bool prefetch, int *emulation_type)
 {
@@ -320,6 +328,11 @@  static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	else
 		r = vcpu->arch.mmu->page_fault(vcpu, &fault);
 
+	if (r == RET_PF_EMULATE && fault.is_private) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, &fault);
+		return -EFAULT;
+	}
+
 	if (fault.write_fault_to_shadow_pgtable && emulation_type)
 		*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;