[RFC PATCH v3 06/11] KVM: x86: Introduce PFERR_GUEST_ENC_MASK to indicate fault is private

[isaku . yamahata]

From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

Add two PFERR codes to designate that the page fault is private and that
it requires looking up memory attributes.  The vendor kvm page fault
handler should set PFERR_GUEST_ENC_MASK bit based on their fault
information.  It may or may not use the hardware value directly or
parse the hardware value to set the bit.

For KVM_X86_PROTECTED_VM, ask memory attributes for the fault privateness.

Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

---
Changes v2 -> v3:
- Revive PFERR_GUEST_ENC_MASK
- rename struct kvm_page_fault::is_private => private
- Add check KVM_X86_PROTECTED_VM

Changes v1 -> v2:
- Introduced fault type and replaced is_private with fault_type.
- Add kvm_get_fault_type() to encapsulate the difference.
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 14 +++++++++-----
 arch/x86/kvm/mmu/mmu_internal.h | 16 ++++++++++++++--
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3ca93e75041f..831bfd1e719a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -255,6 +255,7 @@ enum x86_intercept_stage;
 #define PFERR_SGX_BIT 15
 #define PFERR_GUEST_FINAL_BIT 32
 #define PFERR_GUEST_PAGE_BIT 33
+#define PFERR_GUEST_ENC_BIT 34
 #define PFERR_IMPLICIT_ACCESS_BIT 48
 
 #define PFERR_PRESENT_MASK	BIT(PFERR_PRESENT_BIT)
@@ -266,6 +267,7 @@ enum x86_intercept_stage;
 #define PFERR_SGX_MASK		BIT(PFERR_SGX_BIT)
 #define PFERR_GUEST_FINAL_MASK	BIT_ULL(PFERR_GUEST_FINAL_BIT)
 #define PFERR_GUEST_PAGE_MASK	BIT_ULL(PFERR_GUEST_PAGE_BIT)
+#define PFERR_GUEST_ENC_MASK	BIT_ULL(PFERR_GUEST_ENC_BIT)
 #define PFERR_IMPLICIT_ACCESS	BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
 
 #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b8ba7f11c3cb..464c70b35383 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3228,7 +3228,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 */
 	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
 						       fault->gfn, fault->max_level,
-						       fault->is_private);
+						       fault->private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4328,7 +4328,7 @@ static int kvm_do_memory_fault_exit(struct kvm_vcpu *vcpu,
 				    struct kvm_page_fault *fault)
 {
 	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
-	if (fault->is_private)
+	if (fault->private)
 		vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
 	else
 		vcpu->run->memory.flags = 0;
@@ -4386,10 +4386,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
-	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn))
-		return kvm_do_memory_fault_exit(vcpu, fault);
+	if (fault->private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		if (vcpu->kvm->arch.vm_type == KVM_X86_PROTECTED_VM)
+			return RET_PF_RETRY;
+		else
+			return kvm_do_memory_fault_exit(vcpu, fault);
+	}
 
-	if (fault->is_private)
+	if (fault->private)
 		return kvm_faultin_pfn_private(vcpu, fault);
 
 	async = false;
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 7f9ec1e5b136..a6e45b39ca90 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -200,10 +200,10 @@ struct kvm_page_fault {
 	const bool present;
 	const bool rsvd;
 	const bool user;
+	const bool private;
 
 	/* Derived from mmu and global state.  */
 	const bool is_tdp;
-	const bool is_private;
 	const bool nx_huge_page_workaround_enabled;
 
 	/*
@@ -282,6 +282,18 @@ enum {
 	RET_PF_SPURIOUS,
 };
 
+static inline bool kvm_is_fault_private(struct kvm *kvm, gpa_t gpa, u64 error_code)
+{
+	/*
+	 * This is racy with mmu_seq.  If we hit a race, it would result in a
+	 * spurious KVM_EXIT_MEMORY_FAULT.
+	 */
+	if (kvm->arch.vm_type == KVM_X86_PROTECTED_VM)
+		return kvm_mem_is_private(kvm, gpa_to_gfn(gpa));
+
+	return error_code & PFERR_GUEST_ENC_MASK;
+}
+
 static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 					u64 err, bool prefetch, int *emulation_type)
 {
@@ -293,6 +305,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.present = err & PFERR_PRESENT_MASK,
 		.rsvd = err & PFERR_RSVD_MASK,
 		.user = err & PFERR_USER_MASK,
+		.private = kvm_is_fault_private(vcpu->kvm, cr2_or_gpa, err),
 		.prefetch = prefetch,
 		.is_tdp = likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault),
 		.nx_huge_page_workaround_enabled =
@@ -301,7 +314,6 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
-		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
 	};
 	int r;
 
-- 
2.25.1