KVM: x86: Use gpa_t for cr2/gpa to fix TDP support on 32-bit KVM

Convert a plethora of parameters and variables in the MMU and page fault
flows from type gva_t to gpa_t to properly handle TDP on 32-bit KVM.

Thanks to PSE and PAE paging, 32-bit kernels can access 64-bit physical
addresses.  When TDP is enabled, the fault address is a guest physical
address and thus can be a 64-bit value, even when both KVM and its guest
are using 32-bit virtual addressing, e.g. VMX's VMCS.GUEST_PHYSICAL is a
64-bit field, not a natural width field.

Using a gva_t for the fault address means KVM will incorrectly drop the
upper 32-bits of the GPA.  Ditto for gva_to_gpa() when it is used to
translate L2 GPAs to L1 GPAs.

Opportunistically rename variables and parameters to better reflect the
dual address modes, e.g. use "cr2_or_gpa" for fault addresses and plain
"addr" instead of "vaddr" when the address may be either a GVA or an L2
GPA.  Similarly, use "gpa" in the nonpaging_page_fault() flows to avoid
a confusing "gpa_t gva" declaration; this also sets the stage for a
future patch to combing nonpaging_page_fault() and tdp_page_fault() with
minimal churn.

Sprinkle in a few comments to document flows where an address is known
to be a GVA and thus can be safely truncated to a 32-bit value.  Add
WARNs in kvm_handle_page_fault() and FNAME(gva_to_gpa_nested)() to help
document such cases and detect bugs.

Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 19 insertions, 21 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 25aac4c81b12..93bbbce67a03 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6379,11 +6379,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 	return 1;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
@@ -6397,7 +6397,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry
@@ -6454,10 +6454,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;
@@ -6486,14 +6486,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
@@ -6639,11 +6639,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -6689,8 +6686,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 				kvm_queue_exception(vcpu, UD_VECTOR);
 				return 1;
 			}
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return 1;
 			if (ctxt->have_exception) {
 				/*
@@ -6724,7 +6722,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		return 1;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it
@@ -6736,7 +6734,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 
@@ -6744,7 +6742,7 @@ restart:
 		return 1;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return 1;
 
@@ -10025,7 +10023,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -10138,7 +10136,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (kvm_can_deliver_async_pf(vcpu) &&
@@ -10173,7 +10171,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {