KVM: x86: Move nEPT exit_qualification field from kvm_vcpu_arch to x86_exception

Move the exit_qualification field that is used to track information about
in-flight nEPT violations from "struct kvm_vcpu_arch" to "x86_exception",
i.e. associate the information with the actual nEPT violation instead of
the vCPU.  To handle bits that are pulled from vmcs.EXIT_QUALIFICATION,
i.e. that are propagated from the "original" EPT violation VM-Exit, simply
grab them from the VMCS on-demand when injecting a nEPT Violation or a PML
Full VM-exit.

Aside from being ugly, having an exit_qualification field in kvm_vcpu_arch
is outright dangerous, e.g. see commit d7f0a00 ("KVM: VMX: Report
up-to-date exit qualification to userspace").

Opportunstically add a comment to call out that PML Full and EPT Violation
VM-Exits use the same bit to report NMI blocking information.

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sean Christopherson <[email protected]>

Author: sean-jc

arch/x86/include/asm/kvm_host.h

@@ -993,9 +993,6 @@ struct kvm_vcpu_arch {
 
 	u64 msr_kvm_poll_control;
 
-	/* set at EPT violation at this point */
-	unsigned long exit_qualification;
-
 	/* pv related host specific info */
 	struct {
 		bool pv_unhalted;

arch/x86/kvm/kvm_emulate.h

@@ -26,6 +26,7 @@ struct x86_exception {
 	bool nested_page_fault;
 	u64 address; /* cr2 or nested page fault gpa */
 	u8 async_page_fault;
+	unsigned long exit_qualification;
 };
 
 /*

arch/x86/kvm/mmu/paging_tmpl.h

@@ -497,21 +497,21 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	 * The other bits are set to 0.
 	 */
 	if (!(errcode & PFERR_RSVD_MASK)) {
-		vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID |
-						  EPT_VIOLATION_GVA_TRANSLATED);
+		walker->fault.exit_qualification = 0;
+
 		if (write_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
 		if (user_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ;
 		if (fetch_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
 
 		/*
 		 * Note, pte_access holds the raw RWX bits from the EPTE, not
 		 * ACC_*_MASK flags!
 		 */
-		vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
-						 EPT_VIOLATION_RWX_SHIFT;
+		walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
+						     EPT_VIOLATION_RWX_SHIFT;
 	}
 #endif
 	walker->fault.address = addr;

arch/x86/kvm/vmx/nested.c

@@ -409,18 +409,28 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qualification;
 	u32 vm_exit_reason;
-	unsigned long exit_qualification = vcpu->arch.exit_qualification;
 
 	if (vmx->nested.pml_full) {
 		vm_exit_reason = EXIT_REASON_PML_FULL;
 		vmx->nested.pml_full = false;
-		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+
+		/*
+		 * PML Full and EPT Violation VM-Exits both use bit 12 to report
+		 * "NMI unblocking due to IRET", i.e. the bit can be propagated
+		 * as-is from the original EXIT_QUALIFICATION.
+		 */
+		exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI;
 	} else {
 		if (fault->error_code & PFERR_RSVD_MASK) {
 			vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
 			exit_qualification = 0;
 		} else {
+			exit_qualification = fault->exit_qualification;
+			exit_qualification |= vmx_get_exit_qual(vcpu) &
+					      (EPT_VIOLATION_GVA_IS_VALID |
+					       EPT_VIOLATION_GVA_TRANSLATED);
 			vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
 		}
 

arch/x86/kvm/vmx/vmx.c

@@ -5768,8 +5768,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ?
 	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 
-	vcpu->arch.exit_qualification = exit_qualification;
-
 	/*
 	 * Check that the GPA doesn't exceed physical memory limits, as that is
 	 * a guest page fault.  We have to emulate the instruction here, because