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

Pull KVM fixes from Paolo Bonzini:
 "A collection of x86 and ARM bugfixes, and some improvements to
  documentation.

  On top of this, a cleanup of kvm_para.h headers, which were exported
  by some architectures even though they not support KVM at all. This is
  responsible for all the Kbuild changes in the diffstat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  Documentation: kvm: clarify KVM_SET_USER_MEMORY_REGION
  KVM: doc: Document the life cycle of a VM and its resources
  KVM: selftests: complete IO before migrating guest state
  KVM: selftests: disable stack protector for all KVM tests
  KVM: selftests: explicitly disable PIE for tests
  KVM: selftests: assert on exit reason in CR4/cpuid sync test
  KVM: x86: update %rip after emulating IO
  x86/kvm/hyper-v: avoid spurious pending stimer on vCPU init
  kvm/x86: Move MSR_IA32_ARCH_CAPABILITIES to array emulated_msrs
  KVM: x86: Emulate MSR_IA32_ARCH_CAPABILITIES on AMD hosts
  kvm: don't redefine flags as something else
  kvm: mmu: Used range based flushing in slot_handle_level_range
  KVM: export <linux/kvm_para.h> and <asm/kvm_para.h> iif KVM is supported
  KVM: x86: remove check on nr_mmu_pages in kvm_arch_commit_memory_region()
  kvm: nVMX: Add a vmentry check for HOST_SYSENTER_ESP and HOST_SYSENTER_EIP fields
  KVM: SVM: Workaround errata#1096 (insn_len maybe zero on SMAP violation)
  KVM: Reject device ioctls from processes other than the VM's creator
  KVM: doc: Fix incorrect word ordering regarding supported use of APIs
  KVM: x86: fix handling of role.cr4_pae and rename it to 'gpte_size'
  KVM: nVMX: Do not inherit quadrant and invalid for the root shadow EPT
  ...

5 files changed, 54 insertions, 20 deletions

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3c1f4bdf9000..7514fcea91a7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -29,8 +29,8 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread
+CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+LDFLAGS += -pthread -no-pie
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a84785b02557..07b71ad9734a 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b52cfdefecbf..efa0aad8b3c6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1121,6 +1121,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	vcpu->state->immediate_exit = 1;
+	ret = ioctl(vcpu->fd, KVM_RUN, NULL);
+	vcpu->state->immediate_exit = 0;
+
+	TEST_ASSERT(ret == -1 && errno == EINTR,
+		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
+		    ret, errno);
+}
+
 /*
  * VM VCPU Set MP State
  *
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index d503a51fad30..7c2c4d4055a8 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -87,22 +87,25 @@ int main(int argc, char *argv[])
 	while (1) {
 		rc = _vcpu_run(vm, VCPU_ID);
 
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			/* emulate hypervisor clearing CR4.OSXSAVE */
+			vcpu_sregs_get(vm, VCPU_ID, &sregs);
+			sregs.cr4 &= ~X86_CR4_OSXSAVE;
+			vcpu_sregs_set(vm, VCPU_ID, &sregs);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4b3f556265f1..30f75856cf39 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -134,6 +134,11 @@ int main(int argc, char *argv[])
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
+	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -156,8 +161,6 @@ int main(int argc, char *argv[])
 			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
 			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
@@ -176,6 +179,17 @@ int main(int argc, char *argv[])
 			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
 			    stage, (ulong)uc.args[1]);
 
+		/*
+		 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+		 * guest state is consistent only after userspace re-enters the
+		 * kernel with KVM_RUN.  Complete IO prior to migrating state
+		 * to a new VM.
+		 */
+		vcpu_run_complete_io(vm, VCPU_ID);
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);