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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...

8 files changed, 398 insertions, 4 deletions

diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 16511d97e8dc..09652eabe769 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -152,7 +152,8 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 pcc[16];		/* with MSA4 */
 	__u8 ppno[16];		/* with MSA5 */
 	__u8 kma[16];		/* with MSA8 */
-	__u8 reserved[1808];
+	__u8 kdsa[16];		/* with MSA9 */
+	__u8 reserved[1792];
 };
 
 /* kvm attributes for crypto */
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 2689d1ea6d7a..df1bf9230a74 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,9 +1,14 @@
 /x86_64/cr4_cpuid_sync_test
 /x86_64/evmcs_test
+/x86_64/hyperv_cpuid
+/x86_64/kvm_create_max_vcpus
 /x86_64/platform_info_test
 /x86_64/set_sregs_test
+/x86_64/smm_test
+/x86_64/state_test
 /x86_64/sync_regs_test
 /x86_64/vmx_close_while_nested_test
+/x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
-/x86_64/state_test
+/clear_dirty_log_test
 /dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index f8588cca2bef..79c524395ebe 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -20,6 +20,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/smm_test
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_create_max_vcpus
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 93f99c6b7d79..f50a15c38f9b 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -314,7 +314,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 #ifdef USE_CLEAR_DIRTY_LOG
 	struct kvm_enable_cap cap = {};
 
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT;
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
 	cap.args[0] = 1;
 	vm_enable_cap(vm, &cap);
 #endif
@@ -430,7 +430,7 @@ int main(int argc, char *argv[])
 	int opt, i;
 
 #ifdef USE_CLEAR_DIRTY_LOG
-	if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT)) {
+	if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) {
 		fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n");
 		exit(KSFT_SKIP);
 	}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 07b71ad9734a..8c6b9619797d 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -118,6 +118,10 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_vcpu_events *events);
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_vcpu_events *events);
+void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
+			   struct kvm_nested_state *state);
+int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
+			  struct kvm_nested_state *state, bool ignore_error);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 4ca96b228e46..e9113857f44e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1250,6 +1250,38 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
 		ret, errno);
 }
 
+void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
+			   struct kvm_nested_state *state)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	ret = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, state);
+	TEST_ASSERT(ret == 0,
+		"KVM_SET_NESTED_STATE failed, ret: %i errno: %i",
+		ret, errno);
+}
+
+int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
+			  struct kvm_nested_state *state, bool ignore_error)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	ret = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, state);
+	if (!ignore_error) {
+		TEST_ASSERT(ret == 0,
+			"KVM_SET_NESTED_STATE failed, ret: %i errno: %i",
+			ret, errno);
+	}
+
+	return ret;
+}
+
 /*
  * VM VCPU System Regs Get
  *
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c
new file mode 100644
index 000000000000..50e92996f918
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c
@@ -0,0 +1,70 @@
+/*
+ * kvm_create_max_vcpus
+ *
+ * Copyright (C) 2019, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Test for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_VCPU_ID.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "asm/kvm.h"
+#include "linux/kvm.h"
+
+void test_vcpu_creation(int first_vcpu_id, int num_vcpus)
+{
+	struct kvm_vm *vm;
+	int i;
+
+	printf("Testing creating %d vCPUs, with IDs %d...%d.\n",
+	       num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1);
+
+	vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+	for (i = 0; i < num_vcpus; i++) {
+		int vcpu_id = first_vcpu_id + i;
+
+		/* This asserts that the vCPU was created. */
+		vm_vcpu_add(vm, vcpu_id, 0, 0);
+	}
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
+	int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+
+	printf("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
+	printf("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
+
+	/*
+	 * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
+	 * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID
+	 * in this case.
+	 */
+	if (!kvm_max_vcpu_id)
+		kvm_max_vcpu_id = kvm_max_vcpus;
+
+	TEST_ASSERT(kvm_max_vcpu_id >= kvm_max_vcpus,
+		    "KVM_MAX_VCPU_ID (%d) must be at least as large as KVM_MAX_VCPUS (%d).",
+		    kvm_max_vcpu_id, kvm_max_vcpus);
+
+	test_vcpu_creation(0, kvm_max_vcpus);
+
+	if (kvm_max_vcpu_id > kvm_max_vcpus)
+		test_vcpu_creation(
+			kvm_max_vcpu_id - kvm_max_vcpus, kvm_max_vcpus);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
new file mode 100644
index 000000000000..61a2163cf9f1
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -0,0 +1,280 @@
+/*
+ * vmx_set_nested_state_test
+ *
+ * Copyright (C) 2019, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * This test verifies the integrity of calling the ioctl KVM_SET_NESTED_STATE.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <errno.h>
+#include <linux/kvm.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+/*
+ * Mirror of VMCS12_REVISION in arch/x86/kvm/vmx/vmcs12.h. If that value
+ * changes this should be updated.
+ */
+#define VMCS12_REVISION 0x11e57ed0
+#define VCPU_ID 5
+
+void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state)
+{
+	volatile struct kvm_run *run;
+
+	vcpu_nested_state_set(vm, VCPU_ID, state, false);
+	run = vcpu_state(vm, VCPU_ID);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+		"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
+		run->exit_reason,
+		exit_reason_str(run->exit_reason));
+}
+
+void test_nested_state_expect_errno(struct kvm_vm *vm,
+				    struct kvm_nested_state *state,
+				    int expected_errno)
+{
+	volatile struct kvm_run *run;
+	int rv;
+
+	rv = vcpu_nested_state_set(vm, VCPU_ID, state, true);
+	TEST_ASSERT(rv == -1 && errno == expected_errno,
+		"Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)",
+		strerror(expected_errno), expected_errno, rv, strerror(errno),
+		errno);
+	run = vcpu_state(vm, VCPU_ID);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+		"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
+		run->exit_reason,
+		exit_reason_str(run->exit_reason));
+}
+
+void test_nested_state_expect_einval(struct kvm_vm *vm,
+				     struct kvm_nested_state *state)
+{
+	test_nested_state_expect_errno(vm, state, EINVAL);
+}
+
+void test_nested_state_expect_efault(struct kvm_vm *vm,
+				     struct kvm_nested_state *state)
+{
+	test_nested_state_expect_errno(vm, state, EFAULT);
+}
+
+void set_revision_id_for_vmcs12(struct kvm_nested_state *state,
+				u32 vmcs12_revision)
+{
+	/* Set revision_id in vmcs12 to vmcs12_revision. */
+	*(u32 *)(state->data) = vmcs12_revision;
+}
+
+void set_default_state(struct kvm_nested_state *state)
+{
+	memset(state, 0, sizeof(*state));
+	state->flags = KVM_STATE_NESTED_RUN_PENDING |
+		       KVM_STATE_NESTED_GUEST_MODE;
+	state->format = 0;
+	state->size = sizeof(*state);
+}
+
+void set_default_vmx_state(struct kvm_nested_state *state, int size)
+{
+	memset(state, 0, size);
+	state->flags = KVM_STATE_NESTED_GUEST_MODE  |
+			KVM_STATE_NESTED_RUN_PENDING |
+			KVM_STATE_NESTED_EVMCS;
+	state->format = 0;
+	state->size = size;
+	state->vmx.vmxon_pa = 0x1000;
+	state->vmx.vmcs_pa = 0x2000;
+	state->vmx.smm.flags = 0;
+	set_revision_id_for_vmcs12(state, VMCS12_REVISION);
+}
+
+void test_vmx_nested_state(struct kvm_vm *vm)
+{
+	/* Add a page for VMCS12. */
+	const int state_sz = sizeof(struct kvm_nested_state) + getpagesize();
+	struct kvm_nested_state *state =
+		(struct kvm_nested_state *)malloc(state_sz);
+
+	/* The format must be set to 0. 0 for VMX, 1 for SVM. */
+	set_default_vmx_state(state, state_sz);
+	state->format = 1;
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * We cannot virtualize anything if the guest does not have VMX
+	 * enabled.
+	 */
+	set_default_vmx_state(state, state_sz);
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * We cannot virtualize anything if the guest does not have VMX
+	 * enabled.  We expect KVM_SET_NESTED_STATE to return 0 if vmxon_pa
+	 * is set to -1ull.
+	 */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = -1ull;
+	test_nested_state(vm, state);
+
+	/* Enable VMX in the guest CPUID. */
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = -1ull;
+	state->vmx.smm.flags = 1;
+	test_nested_state_expect_einval(vm, state);
+
+	/* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = -1ull;
+	state->vmx.vmcs_pa = 0;
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without
+	 * setting the nested state.
+	 */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = -1ull;
+	state->vmx.vmcs_pa = -1ull;
+	test_nested_state(vm, state);
+
+	/* It is invalid to have vmxon_pa set to a non-page aligned address. */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = 1;
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * It is invalid to have KVM_STATE_NESTED_SMM_GUEST_MODE and
+	 * KVM_STATE_NESTED_GUEST_MODE set together.
+	 */
+	set_default_vmx_state(state, state_sz);
+	state->flags = KVM_STATE_NESTED_GUEST_MODE  |
+		      KVM_STATE_NESTED_RUN_PENDING;
+	state->vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE;
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * It is invalid to have any of the SMM flags set besides:
+	 *	KVM_STATE_NESTED_SMM_GUEST_MODE
+	 *	KVM_STATE_NESTED_SMM_VMXON
+	 */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.smm.flags = ~(KVM_STATE_NESTED_SMM_GUEST_MODE |
+				KVM_STATE_NESTED_SMM_VMXON);
+	test_nested_state_expect_einval(vm, state);
+
+	/* Outside SMM, SMM flags must be zero. */
+	set_default_vmx_state(state, state_sz);
+	state->flags = 0;
+	state->vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE;
+	test_nested_state_expect_einval(vm, state);
+
+	/* Size must be large enough to fit kvm_nested_state and vmcs12. */
+	set_default_vmx_state(state, state_sz);
+	state->size = sizeof(*state);
+	test_nested_state(vm, state);
+
+	/* vmxon_pa cannot be the same address as vmcs_pa. */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = 0;
+	state->vmx.vmcs_pa = 0;
+	test_nested_state_expect_einval(vm, state);
+
+	/* The revision id for vmcs12 must be VMCS12_REVISION. */
+	set_default_vmx_state(state, state_sz);
+	set_revision_id_for_vmcs12(state, 0);
+	test_nested_state_expect_einval(vm, state);
+
+	/*
+	 * Test that if we leave nesting the state reflects that when we get
+	 * it again.
+	 */
+	set_default_vmx_state(state, state_sz);
+	state->vmx.vmxon_pa = -1ull;
+	state->vmx.vmcs_pa = -1ull;
+	state->flags = 0;
+	test_nested_state(vm, state);
+	vcpu_nested_state_get(vm, VCPU_ID, state);
+	TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz,
+		    "Size must be between %d and %d.  The size returned was %d.",
+		    sizeof(*state), state_sz, state->size);
+	TEST_ASSERT(state->vmx.vmxon_pa == -1ull, "vmxon_pa must be -1ull.");
+	TEST_ASSERT(state->vmx.vmcs_pa == -1ull, "vmcs_pa must be -1ull.");
+
+	free(state);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_nested_state state;
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+		printf("KVM_CAP_NESTED_STATE not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	/*
+	 * AMD currently does not implement set_nested_state, so for now we
+	 * just early out.
+	 */
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, 0);
+
+	/* Passing a NULL kvm_nested_state causes a EFAULT. */
+	test_nested_state_expect_efault(vm, NULL);
+
+	/* 'size' cannot be smaller than sizeof(kvm_nested_state). */
+	set_default_state(&state);
+	state.size = 0;
+	test_nested_state_expect_einval(vm, &state);
+
+	/*
+	 * Setting the flags 0xf fails the flags check.  The only flags that
+	 * can be used are:
+	 *     KVM_STATE_NESTED_GUEST_MODE
+	 *     KVM_STATE_NESTED_RUN_PENDING
+	 *     KVM_STATE_NESTED_EVMCS
+	 */
+	set_default_state(&state);
+	state.flags = 0xf;
+	test_nested_state_expect_einval(vm, &state);
+
+	/*
+	 * If KVM_STATE_NESTED_RUN_PENDING is set then
+	 * KVM_STATE_NESTED_GUEST_MODE has to be set as well.
+	 */
+	set_default_state(&state);
+	state.flags = KVM_STATE_NESTED_RUN_PENDING;
+	test_nested_state_expect_einval(vm, &state);
+
+	/*
+	 * TODO: When SVM support is added for KVM_SET_NESTED_STATE
+	 *       add tests here to support it like VMX.
+	 */
+	if (entry->ecx & CPUID_VMX)
+		test_vmx_nested_state(vm);
+
+	kvm_vm_free(vm);
+	return 0;
+}