Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:

 - Allow again loading KVM on 32-bit non-PAE builds

 - Fixes for host SMIs on AMD

 - Fixes for guest SMIs on AMD

 - Fixes for selftests on s390 and ARM

 - Fix memory leak

 - Enforce no-instrumentation area on vmentry when hardware breakpoints
   are in use.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
  KVM: selftests: smm_test: Test SMM enter from L2
  KVM: nSVM: Restore nested control upon leaving SMM
  KVM: nSVM: Fix L1 state corruption upon return from SMM
  KVM: nSVM: Introduce svm_copy_vmrun_state()
  KVM: nSVM: Check that VM_HSAVE_PA MSR was set before VMRUN
  KVM: nSVM: Check the value written to MSR_VM_HSAVE_PA
  KVM: SVM: Fix sev_pin_memory() error checks in SEV migration utilities
  KVM: SVM: Return -EFAULT if copy_to_user() for SEV mig packet header fails
  KVM: SVM: add module param to control the #SMI interception
  KVM: SVM: remove INIT intercept handler
  KVM: SVM: #SMI interception must not skip the instruction
  KVM: VMX: Remove vmx_msr_index from vmx.h
  KVM: X86: Disable hardware breakpoints unconditionally before kvm_x86->run()
  KVM: selftests: Address extra memslot parameters in vm_vaddr_alloc
  kvm: debugfs: fix memory leak in kvm_create_vm_debugfs
  KVM: x86/pmu: Clear anythread deprecated bit when 0xa leaf is unsupported on the SVM
  KVM: mmio: Fix use-after-free Read in kvm_vm_ioctl_unregister_coalesced_mmio
  KVM: SVM: Revert clearing of C-bit on GPA in #NPF handler
  KVM: x86/mmu: Do not apply HPA (memory encryption) mask to GPAs
  KVM: x86: Use kernel's x86_phys_bits to handle reduced MAXPHYADDR
  ...

8 files changed, 92 insertions, 11 deletions

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 615ab254899d..010b59b13917 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -45,6 +45,7 @@ enum vm_guest_mode {
 	VM_MODE_P40V48_64K,
 	VM_MODE_PXXV48_4K,	/* For 48bits VA but ANY bits PA */
 	VM_MODE_P47V64_4K,
+	VM_MODE_P44V64_4K,
 	NUM_VM_MODES,
 };
 
@@ -62,7 +63,7 @@ enum vm_guest_mode {
 
 #elif defined(__s390x__)
 
-#define VM_MODE_DEFAULT			VM_MODE_P47V64_4K
+#define VM_MODE_DEFAULT			VM_MODE_P44V64_4K
 #define MIN_PAGE_SHIFT			12U
 #define ptes_per_page(page_size)	((page_size) / 16)
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 9f49f6caafe5..632b74d6b3ca 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -401,7 +401,7 @@ unexpected_exception:
 void vm_init_descriptor_tables(struct kvm_vm *vm)
 {
 	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
-			vm->page_size, 0, 0);
+			vm->page_size);
 
 	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
 }
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 25bff307c71f..c330f414ef96 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -22,6 +22,22 @@ void guest_modes_append_default(void)
 		}
 	}
 #endif
+#ifdef __s390x__
+	{
+		int kvm_fd, vm_fd;
+		struct kvm_s390_vm_cpu_processor info;
+
+		kvm_fd = open_kvm_dev_path_or_exit();
+		vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0);
+		kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL,
+				  KVM_S390_VM_CPU_PROCESSOR, &info, false);
+		close(vm_fd);
+		close(kvm_fd);
+		/* Starting with z13 we have 47bits of physical address */
+		if (info.ibc >= 0x30)
+			guest_mode_append(VM_MODE_P47V64_4K, true, true);
+	}
+#endif
 }
 
 void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5b56b57b3c20..10a8ed691c66 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -176,6 +176,7 @@ const char *vm_guest_mode_string(uint32_t i)
 		[VM_MODE_P40V48_64K]	= "PA-bits:40,  VA-bits:48, 64K pages",
 		[VM_MODE_PXXV48_4K]	= "PA-bits:ANY, VA-bits:48,  4K pages",
 		[VM_MODE_P47V64_4K]	= "PA-bits:47,  VA-bits:64,  4K pages",
+		[VM_MODE_P44V64_4K]	= "PA-bits:44,  VA-bits:64,  4K pages",
 	};
 	_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
 		       "Missing new mode strings?");
@@ -194,6 +195,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	{ 40, 48, 0x10000, 16 },
 	{  0,  0,  0x1000, 12 },
 	{ 47, 64,  0x1000, 12 },
+	{ 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
@@ -282,6 +284,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	case VM_MODE_P47V64_4K:
 		vm->pgtable_levels = 5;
 		break;
+	case VM_MODE_P44V64_4K:
+		vm->pgtable_levels = 5;
+		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
 	}
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 85b18bb8f762..72a1c9b4882c 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -377,7 +377,8 @@ static void test_add_max_memory_regions(void)
 		(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
 
 	mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
-		   PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		   PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
 	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
 	mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 42bd658f52a8..af27c7e829c1 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -615,7 +615,7 @@ int main(void)
 
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
 
 	pr_info("Testing access to Hyper-V specific MSRs\n");
 	guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index 523371cf8e8f..da2325fcad87 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -71,7 +71,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
 	/* Set up a #PF handler to eat the RSVD #PF and signal all done! */
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_handle_exception(vm, PF_VECTOR, guest_pf_handler);
+	vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
 
 	r = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r);
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index c1f831803ad2..d0fe2fdce58c 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -53,15 +53,28 @@ static inline void sync_with_host(uint64_t phase)
 		     : "+a" (phase));
 }
 
-void self_smi(void)
+static void self_smi(void)
 {
 	x2apic_write_reg(APIC_ICR,
 			 APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
 }
 
-void guest_code(void *arg)
+static void l2_guest_code(void)
 {
+	sync_with_host(8);
+
+	sync_with_host(10);
+
+	vmcall();
+}
+
+static void guest_code(void *arg)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
 	uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+	struct svm_test_data *svm = arg;
+	struct vmx_pages *vmx_pages = arg;
 
 	sync_with_host(1);
 
@@ -74,21 +87,50 @@ void guest_code(void *arg)
 	sync_with_host(4);
 
 	if (arg) {
-		if (cpu_has_svm())
-			generic_svm_setup(arg, NULL, NULL);
-		else
-			GUEST_ASSERT(prepare_for_vmx_operation(arg));
+		if (cpu_has_svm()) {
+			generic_svm_setup(svm, l2_guest_code,
+					  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+		} else {
+			GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+			GUEST_ASSERT(load_vmcs(vmx_pages));
+			prepare_vmcs(vmx_pages, l2_guest_code,
+				     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+		}
 
 		sync_with_host(5);
 
 		self_smi();
 
 		sync_with_host(7);
+
+		if (cpu_has_svm()) {
+			run_guest(svm->vmcb, svm->vmcb_gpa);
+			svm->vmcb->save.rip += 3;
+			run_guest(svm->vmcb, svm->vmcb_gpa);
+		} else {
+			vmlaunch();
+			vmresume();
+		}
+
+		/* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */
+		sync_with_host(12);
 	}
 
 	sync_with_host(DONE);
 }
 
+void inject_smi(struct kvm_vm *vm)
+{
+	struct kvm_vcpu_events events;
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+
+	events.smi.pending = 1;
+	events.flags |= KVM_VCPUEVENT_VALID_SMM;
+
+	vcpu_events_set(vm, VCPU_ID, &events);
+}
+
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t nested_gva = 0;
@@ -147,6 +189,22 @@ int main(int argc, char *argv[])
 			    "Unexpected stage: #%x, got %x",
 			    stage, stage_reported);
 
+		/*
+		 * Enter SMM during L2 execution and check that we correctly
+		 * return from it. Do not perform save/restore while in SMM yet.
+		 */
+		if (stage == 8) {
+			inject_smi(vm);
+			continue;
+		}
+
+		/*
+		 * Perform save/restore while the guest is in SMM triggered
+		 * during L2 execution.
+		 */
+		if (stage == 10)
+			inject_smi(vm);
+
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
 		kvm_vm_restart(vm, O_RDWR);