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>

2 files changed, 56 insertions, 38 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c19f3ccaace3..2cb199817837 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3532,7 +3532,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte)
  * - true: let the vcpu to access on the same address again.
  * - false: let the real page fault path to fix it.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3552,7 +3552,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	do {
 		u64 new_spte;
 
-		for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
+		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
 			if (!is_shadow_present_pte(spte) ||
 			    iterator.level < level)
 				break;
@@ -3630,7 +3630,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 
 	} while (true);
 
-	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
 			      spte, fault_handled);
 	walk_shadow_page_lockless_end(vcpu);
 
@@ -3638,10 +3638,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable);
 static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
 
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
+static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			 gfn_t gfn, bool prefault)
 {
 	int r;
@@ -3667,16 +3668,16 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	}
 
-	if (fast_page_fault(vcpu, v, level, error_code))
+	if (fast_page_fault(vcpu, gpa, level, error_code))
 		return RET_PF_RETRY;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
 		return RET_PF_RETRY;
 
-	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
+	if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
 		return r;
 
 	r = RET_PF_RETRY;
@@ -3687,7 +3688,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
 			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3985,7 +3986,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
 {
 	if (exception)
@@ -3993,7 +3994,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
 	return vaddr;
 }
 
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
 					 u32 access,
 					 struct x86_exception *exception)
 {
@@ -4153,13 +4154,14 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
 				u32 error_code, bool prefault)
 {
-	gfn_t gfn = gva >> PAGE_SHIFT;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int r;
 
-	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
+	/* Note, paging is disabled, ergo gva == gpa. */
+	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
@@ -4171,11 +4173,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 
-	return nonpaging_map(vcpu, gva & PAGE_MASK,
+	return nonpaging_map(vcpu, gpa & PAGE_MASK,
 			     error_code, gfn, prefault);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				   gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4184,11 +4187,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -4208,12 +4213,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 		return false; /* *pfn has correct page already */
 
 	if (!prefault && kvm_can_do_async_pf(vcpu)) {
-		trace_kvm_try_async_get_page(gva, gfn);
+		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
-			trace_kvm_async_pf_doublefault(gva, gfn);
+			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return true;
-		} else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
 			return true;
 	}
 
@@ -4226,6 +4231,12 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 {
 	int r = 1;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
+	if (WARN_ON_ONCE(fault_address >> 32))
+		return -EFAULT;
+#endif
+
 	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
@@ -4263,7 +4274,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
 	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
 }
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			  bool prefault)
 {
 	kvm_pfn_t pfn;
@@ -5520,7 +5531,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
@@ -5529,18 +5540,18 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
 	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
-		vcpu->arch.gpa_val = cr2;
+		vcpu->arch.gpa_val = cr2_or_gpa;
 	}
 
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
 					       lower_32_bits(error_code),
 					       false);
 		WARN_ON(r == RET_PF_INVALID);
@@ -5560,7 +5571,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 */
 	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
 		return 1;
 	}
 
@@ -5575,7 +5586,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 * 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, direct) && !is_guest_mode(vcpu))
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
@@ -5590,7 +5601,7 @@ emulate:
 			return 1;
 	}
 
-	return x86_emulate_instruction(vcpu, cr2, emulation_type, insn,
+	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..c1d7b866a03f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;
@@ -496,7 +496,7 @@ error:
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
@@ -611,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
 			 kvm_pfn_t pfn, bool map_writable, bool prefault,
@@ -765,7 +765,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
@@ -945,18 +945,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
@@ -964,7 +965,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {
@@ -972,6 +974,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {