KVM: x86/mmu: Trigger unprotect logic only on write-protection page faults

Trigger KVM's various "unprotect gfn" paths if and only if the page fault
was a write to a write-protected gfn.  To do so, add a new page fault
return code, RET_PF_WRITE_PROTECTED, to explicitly and precisely track
such page faults.

If a page fault requires emulation for any MMIO (or any reason besides
write-protection), trying to unprotect the gfn is pointless and risks
putting the vCPU into an infinite loop.  E.g. KVM will put the vCPU into
an infinite loop if the vCPU manages to trigger MMIO on a page table walk.

Fixes: 147277540bbc ("kvm: svm: Add support for additional SVM NPF error codes")
Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20240831001538.336683-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 43 insertions, 32 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1eedd1932e5f..d8deed29091b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2896,10 +2896,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 		trace_kvm_mmu_set_spte(level, gfn, sptep);
 	}
 
-	if (wrprot) {
-		if (write_fault)
-			ret = RET_PF_EMULATE;
-	}
+	if (wrprot && write_fault)
+		ret = RET_PF_WRITE_PROTECTED;
 
 	if (flush)
 		kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
@@ -4531,7 +4529,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		return RET_PF_RETRY;
 
 	if (page_fault_handle_page_track(vcpu, fault))
-		return RET_PF_EMULATE;
+		return RET_PF_WRITE_PROTECTED;
 
 	r = fast_page_fault(vcpu, fault);
 	if (r != RET_PF_INVALID)
@@ -4624,7 +4622,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu,
 	int r;
 
 	if (page_fault_handle_page_track(vcpu, fault))
-		return RET_PF_EMULATE;
+		return RET_PF_WRITE_PROTECTED;
 
 	r = fast_page_fault(vcpu, fault);
 	if (r != RET_PF_INVALID)
@@ -4703,6 +4701,7 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
 	switch (r) {
 	case RET_PF_FIXED:
 	case RET_PF_SPURIOUS:
+	case RET_PF_WRITE_PROTECTED:
 		return 0;
 
 	case RET_PF_EMULATE:
@@ -5952,6 +5951,40 @@ static bool is_write_to_guest_page_table(u64 error_code)
 	return (error_code & mask) == mask;
 }
 
+static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				       u64 error_code, int *emulation_type)
+{
+	bool direct = vcpu->arch.mmu->root_role.direct;
+
+	/*
+	 * Before emulating the instruction, check if the error code
+	 * was due to a RO violation while translating the guest page.
+	 * This can occur when using nested virtualization with nested
+	 * paging in both guests. If true, we simply unprotect the page
+	 * and resume the guest.
+	 */
+	if (direct && is_write_to_guest_page_table(error_code)) {
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
+		return RET_PF_RETRY;
+	}
+
+	/*
+	 * The gfn is write-protected, but if emulation fails we can still
+	 * optimistically try to just unprotect the page and let the processor
+	 * re-execute the instruction that caused the page fault.  Do not allow
+	 * retrying MMIO emulation, as it's not only pointless but could also
+	 * cause us to enter an infinite loop because the processor will keep
+	 * faulting on the non-existent MMIO address.  Retrying an instruction
+	 * from a nested guest is also pointless and dangerous as we are only
+	 * explicitly shadowing L1's page tables, i.e. unprotecting something
+	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
+	 */
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
+		*emulation_type |= EMULTYPE_ALLOW_RETRY_PF;
+
+	return RET_PF_EMULATE;
+}
+
 int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
@@ -5997,6 +6030,10 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	if (r < 0)
 		return r;
 
+	if (r == RET_PF_WRITE_PROTECTED)
+		r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code,
+						&emulation_type);
+
 	if (r == RET_PF_FIXED)
 		vcpu->stat.pf_fixed++;
 	else if (r == RET_PF_EMULATE)
@@ -6007,32 +6044,6 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	if (r != RET_PF_EMULATE)
 		return 1;
 
-	/*
-	 * Before emulating the instruction, check if the error code
-	 * was due to a RO violation while translating the guest page.
-	 * This can occur when using nested virtualization with nested
-	 * paging in both guests. If true, we simply unprotect the page
-	 * and resume the guest.
-	 */
-	if (vcpu->arch.mmu->root_role.direct &&
-	    is_write_to_guest_page_table(error_code)) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
-		return 1;
-	}
-
-	/*
-	 * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still
-	 * optimistically try to just unprotect the page and let the processor
-	 * re-execute the instruction that caused the page fault.  Do not allow
-	 * retrying MMIO emulation, as it's not only pointless but could also
-	 * cause us to enter an infinite loop because the processor will keep
-	 * faulting on the non-existent MMIO address.  Retrying an instruction
-	 * from a nested guest is also pointless and dangerous as we are only
-	 * explicitly shadowing L1's page tables, i.e. unprotecting something
-	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
-	 */
-	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
-		emulation_type |= EMULTYPE_ALLOW_RETRY_PF;
 emulate:
 	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);