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

Pull kvm fixes from Paolo Bonzini:
 "ARM:
   - selftest fix
   - force PTE mapping on device pages provided via VFIO
   - fix detection of cacheable mapping at S2
   - fallback to PMD/PTE mappings for composite huge pages
   - fix accounting of Stage-2 PGD allocation
   - fix AArch32 handling of some of the debug registers
   - simplify host HYP entry
   - fix stray pointer conversion on nVHE TLB invalidation
   - fix initialization of the nVHE code
   - simplify handling of capabilities exposed to HYP
   - nuke VCPUs caught using a forbidden AArch32 EL0

  x86:
   - new nested virtualization selftest
   - miscellaneous fixes
   - make W=1 fixes
   - reserve new CPUID bit in the KVM leaves"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: vmx: remove unused variable
  KVM: selftests: Don't require THP to run tests
  KVM: VMX: eVMCS: make evmcs_sanitize_exec_ctrls() work again
  KVM: selftests: test behavior of unmapped L2 APIC-access address
  KVM: x86: Fix NULL dereference at kvm_msr_ignored_check()
  KVM: x86: replace static const variables with macros
  KVM: arm64: Handle Asymmetric AArch32 systems
  arm64: cpufeature: upgrade hyp caps to final
  arm64: cpufeature: reorder cpus_have_{const, final}_cap()
  KVM: arm64: Factor out is_{vhe,nvhe}_hyp_code()
  KVM: arm64: Force PTE mapping on fault resulting in a device mapping
  KVM: arm64: Use fallback mapping sizes for contiguous huge page sizes
  KVM: arm64: Fix masks in stage2_pte_cacheable()
  KVM: arm64: Fix AArch32 handling of DBGD{CCINT,SCRext} and DBGVCR
  KVM: arm64: Allocate stage-2 pgd pages with GFP_KERNEL_ACCOUNT
  KVM: arm64: Drop useless PAN setting on host EL1 to EL2 transition
  KVM: arm64: Remove leftover kern_hyp_va() in nVHE TLB invalidation
  KVM: arm64: Don't corrupt tpidr_el2 on failed HVC call
  x86/kvm: Reserve KVM_FEATURE_MSI_EXT_DEST_ID

6 files changed, 175 insertions, 7 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 307ceaadbbb9..d2c2d6205008 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -15,6 +15,7 @@
 /x86_64/vmx_preemption_timer_test
 /x86_64/svm_vmcall_test
 /x86_64/sync_regs_test
+/x86_64/vmx_apic_access_test
 /x86_64/vmx_close_while_nested_test
 /x86_64/vmx_dirty_log_test
 /x86_64/vmx_set_nested_state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 7ebe71fbca53..30afbad36cd5 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -49,6 +49,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 54d624dd6c10..e78d7e26ba61 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -573,6 +573,10 @@ struct vmx_pages {
 	void *eptp_hva;
 	uint64_t eptp_gpa;
 	void *eptp;
+
+	void *apic_access_hva;
+	uint64_t apic_access_gpa;
+	void *apic_access;
 };
 
 union vmx_basic {
@@ -615,5 +619,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 			uint32_t memslot, uint32_t eptp_memslot);
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot);
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+				      uint32_t eptp_memslot);
 
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 74776ee228f2..3327cebc1095 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -14,6 +14,7 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <unistd.h>
 #include <linux/kernel.h>
 
 #define KVM_UTIL_PGS_PER_HUGEPG 512
@@ -664,13 +665,21 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 
 	/* As needed perform madvise */
 	if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
-		ret = madvise(region->host_mem, npages * vm->page_size,
-			     src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
-		TEST_ASSERT(ret == 0, "madvise failed,\n"
-			    "  addr: %p\n"
-			    "  length: 0x%lx\n"
-			    "  src_type: %x",
-			    region->host_mem, npages * vm->page_size, src_type);
+		struct stat statbuf;
+
+		ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+		TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
+			    "stat /sys/kernel/mm/transparent_hugepage");
+
+		TEST_ASSERT(ret == 0 || src_type != VM_MEM_SRC_ANONYMOUS_THP,
+			    "VM_MEM_SRC_ANONYMOUS_THP requires THP to be configured in the host kernel");
+
+		if (ret == 0) {
+			ret = madvise(region->host_mem, npages * vm->page_size,
+				      src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+			TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %x",
+				    region->host_mem, npages * vm->page_size, src_type);
+		}
 	}
 
 	region->unused_phy_pages = sparsebit_alloc();
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index f1e00d43eea2..2448b30e8efa 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -542,3 +542,12 @@ void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 	vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
 	vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
 }
+
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+				      uint32_t eptp_memslot)
+{
+	vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						  0x10000, 0, 0);
+	vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access);
+	vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
new file mode 100644
index 000000000000..1f65342d6cb7
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vmx_apic_access_test
+ *
+ * Copyright (C) 2020, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * The first subtest simply checks to see that an L2 guest can be
+ * launched with a valid APIC-access address that is backed by a
+ * page of L1 physical memory.
+ *
+ * The second subtest sets the APIC-access address to a (valid) L1
+ * physical address that is not backed by memory. KVM can't handle
+ * this situation, so resuming L2 should result in a KVM exit for
+ * internal error (emulation). This is not an architectural
+ * requirement. It is just a shortcoming of KVM. The internal error
+ * is unfortunate, but it's better than what used to happen!
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID		0
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void l2_guest_code(void)
+{
+	/* Exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uint32_t control;
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+	control = vmreadz(SECONDARY_VM_EXEC_CONTROL);
+	control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
+	vmwrite(APIC_ACCESS_ADDR, vmx_pages->apic_access_gpa);
+
+	/* Try to launch L2 with the memory-backed APIC-access address. */
+	GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	vmwrite(APIC_ACCESS_ADDR, high_gpa);
+
+	/* Try to resume L2 with the unbacked APIC-access address. */
+	GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long apic_access_addr = ~0ul;
+	unsigned int paddr_width;
+	unsigned int vaddr_width;
+	vm_vaddr_t vmx_pages_gva;
+	unsigned long high_gpa;
+	struct vmx_pages *vmx;
+	bool done = false;
+
+	nested_vmx_check_supported();
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	kvm_get_cpu_address_width(&paddr_width, &vaddr_width);
+	high_gpa = (1ul << paddr_width) - getpagesize();
+	if ((unsigned long)DEFAULT_GUEST_PHY_PAGES * getpagesize() > high_gpa) {
+		print_skip("No unbacked physical page available");
+		exit(KSFT_SKIP);
+	}
+
+	vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	prepare_virtualize_apic_accesses(vmx, vm, 0);
+	vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa);
+
+	while (!done) {
+		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		struct ucall uc;
+
+		vcpu_run(vm, VCPU_ID);
+		if (apic_access_addr == high_gpa) {
+			TEST_ASSERT(run->exit_reason ==
+				    KVM_EXIT_INTERNAL_ERROR,
+				    "Got exit reason other than KVM_EXIT_INTERNAL_ERROR: %u (%s)\n",
+				    run->exit_reason,
+				    exit_reason_str(run->exit_reason));
+			TEST_ASSERT(run->internal.suberror ==
+				    KVM_INTERNAL_ERROR_EMULATION,
+				    "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+				    run->internal.suberror);
+			break;
+		}
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+				  __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			apic_access_addr = uc.args[1];
+			break;
+		case UCALL_DONE:
+			done = true;
+			break;
+		default:
+			TEST_ASSERT(false, "Unknown ucall %lu", uc.cmd);
+		}
+	}
+	kvm_vm_free(vm);
+	return 0;
+}