15 files changed, 298 insertions, 123 deletions

diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index f2a96779716a..26556a266021 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -222,7 +222,7 @@ static void *test_vcpu_run(void *arg)
 
 	/* Currently, any exit from guest is an indication of completion */
 	pthread_mutex_lock(&vcpu_done_map_lock);
-	set_bit(vcpu_idx, vcpu_done_map);
+	__set_bit(vcpu_idx, vcpu_done_map);
 	pthread_mutex_unlock(&vcpu_done_map_lock);
 
 	switch (get_ucall(vcpu, &uc)) {
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index 8a3fb212084a..637be796086f 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -375,10 +375,6 @@ static void guest_svc_handler(struct ex_regs *regs)
 	svc_addr = regs->pc;
 }
 
-enum single_step_op {
-	SINGLE_STEP_ENABLE = 0,
-};
-
 static void guest_code_ss(int test_cnt)
 {
 	uint64_t i;
@@ -389,8 +385,16 @@ static void guest_code_ss(int test_cnt)
 		w_bvr = i << 2;
 		w_wvr = i << 2;
 
-		/* Enable Single Step execution */
-		GUEST_SYNC(SINGLE_STEP_ENABLE);
+		/*
+		 * Enable Single Step execution.  Note!  This _must_ be a bare
+		 * ucall as the ucall() path uses atomic operations to manage
+		 * the ucall structures, and the built-in "atomics" are usually
+		 * implemented via exclusive access instructions.  The exlusive
+		 * monitor is cleared on ERET, and so taking debug exceptions
+		 * during a LDREX=>STREX sequence will prevent forward progress
+		 * and hang the guest/test.
+		 */
+		GUEST_UCALL_NONE();
 
 		/*
 		 * The userspace will verify that the pc is as expected during
@@ -484,12 +488,9 @@ void test_single_step_from_userspace(int test_cnt)
 				break;
 			}
 
-			TEST_ASSERT(cmd == UCALL_SYNC,
+			TEST_ASSERT(cmd == UCALL_NONE,
 				    "Unexpected ucall cmd 0x%lx", cmd);
 
-			TEST_ASSERT(uc.args[1] == SINGLE_STEP_ENABLE,
-				    "Unexpected ucall action 0x%lx", uc.args[1]);
-
 			debug.control = KVM_GUESTDBG_ENABLE |
 					KVM_GUESTDBG_SINGLESTEP;
 			ss_enable = true;
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 57a16371e9c2..3c7defd34f56 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -46,6 +46,7 @@
 #include "test_util.h"
 #include "memstress.h"
 #include "guest_modes.h"
+#include "processor.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
 static int iteration;
@@ -177,16 +178,21 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
 	 * access tracking but low enough as to not make the test too brittle
 	 * over time and across architectures.
 	 *
-	 * Note that when run in nested virtualization, this check will trigger
-	 * much more frequently because TLB size is unlimited and since no flush
-	 * happens, much more pages are cached there and guest won't see the
-	 * "idle" bit cleared.
+	 * When running the guest as a nested VM, "warn" instead of asserting
+	 * as the TLB size is effectively unlimited and the KVM doesn't
+	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
+	 * are cached and the guest won't see the "idle" bit cleared.
 	 */
-	if (still_idle < pages / 10)
-		printf("WARNING: vCPU%d: Too many pages still idle (%" PRIu64
-		       "out of %" PRIu64 "), this will affect performance results"
-		       ".\n",
+	if (still_idle >= pages / 10) {
+#ifdef __x86_64__
+		TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR),
+			    "vCPU%d: Too many pages still idle (%lu out of %lu)",
+			    vcpu_idx, still_idle, pages);
+#endif
+		printf("WARNING: vCPU%d: Too many pages still idle (%lu out of %lu), "
+		       "this will affect performance results.\n",
 		       vcpu_idx, still_idle, pages);
+	}
 
 	close(page_idle_fd);
 	close(pagemap_fd);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index c33e89012ae6..e9d6d1aecf89 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -398,7 +398,7 @@ static void help(char *name)
 	printf(" -x: Split the memory region into this number of memslots.\n"
 	       "     (default: 1)\n");
 	printf(" -w: specify the percentage of pages which should be written to\n"
-	       "     as an integer from 0-100 inclusive. This is probabalistic,\n"
+	       "     as an integer from 0-100 inclusive. This is probabilistic,\n"
 	       "     so -w X means each page has an X%% chance of writing\n"
 	       "     and a (100-X)%% chance of reading.\n"
 	       "     (default: 100 i.e. all pages are written to.)\n");
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 9d4c50c4e72e..936f3a8d1b83 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -47,20 +47,20 @@
 # define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
 # define test_bit_le(nr, addr) \
 	test_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
-# define set_bit_le(nr, addr) \
-	set_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
-# define clear_bit_le(nr, addr) \
-	clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
-# define test_and_set_bit_le(nr, addr) \
-	test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
-# define test_and_clear_bit_le(nr, addr) \
-	test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
+# define __set_bit_le(nr, addr) \
+	__set_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
+# define __clear_bit_le(nr, addr) \
+	__clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
+# define __test_and_set_bit_le(nr, addr) \
+	__test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
+# define __test_and_clear_bit_le(nr, addr) \
+	__test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, addr)
 #else
-# define test_bit_le		test_bit
-# define set_bit_le		set_bit
-# define clear_bit_le		clear_bit
-# define test_and_set_bit_le	test_and_set_bit
-# define test_and_clear_bit_le	test_and_clear_bit
+# define test_bit_le			test_bit
+# define __set_bit_le			__set_bit
+# define __clear_bit_le			__clear_bit
+# define __test_and_set_bit_le		__test_and_set_bit
+# define __test_and_clear_bit_le	__test_and_clear_bit
 #endif
 
 #define TEST_DIRTY_RING_COUNT		65536
@@ -328,7 +328,7 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
 		TEST_ASSERT(cur->offset < num_pages, "Offset overflow: "
 			    "0x%llx >= 0x%x", cur->offset, num_pages);
 		//pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset);
-		set_bit_le(cur->offset, bitmap);
+		__set_bit_le(cur->offset, bitmap);
 		dirty_ring_last_page = cur->offset;
 		dirty_gfn_set_collected(cur);
 		(*fetch_index)++;
@@ -585,7 +585,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 		value_ptr = host_test_mem + page * host_page_size;
 
 		/* If this is a special page that we were tracking... */
-		if (test_and_clear_bit_le(page, host_bmap_track)) {
+		if (__test_and_clear_bit_le(page, host_bmap_track)) {
 			host_track_next_count++;
 			TEST_ASSERT(test_bit_le(page, bmap),
 				    "Page %"PRIu64" should have its dirty bit "
@@ -593,7 +593,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 				    page);
 		}
 
-		if (test_and_clear_bit_le(page, bmap)) {
+		if (__test_and_clear_bit_le(page, bmap)) {
 			bool matched;
 
 			host_dirty_count++;
@@ -686,7 +686,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 				 * should report its dirtyness in the
 				 * next run
 				 */
-				set_bit_le(page, host_bmap_track);
+				__set_bit_le(page, host_bmap_track);
 			}
 		}
 	}
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 2e267cd69288..fbc2a79369b8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -22,6 +22,18 @@
 
 #include "sparsebit.h"
 
+/*
+ * Provide a version of static_assert() that is guaranteed to have an optional
+ * message param.  If _ISOC11_SOURCE is defined, glibc (/usr/include/assert.h)
+ * #undefs and #defines static_assert() as a direct alias to _Static_assert(),
+ * i.e. effectively makes the message mandatory.  Many KVM selftests #define
+ * _GNU_SOURCE for various reasons, and _GNU_SOURCE implies _ISOC11_SOURCE.  As
+ * a result, static_assert() behavior is non-deterministic and may or may not
+ * require a message depending on #include order.
+ */
+#define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg)
+#define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr)
+
 #define KVM_DEV_PATH "/dev/kvm"
 #define KVM_MAX_VCPUS 512
 
@@ -219,7 +231,7 @@ static inline bool kvm_has_cap(long cap)
 
 #define kvm_do_ioctl(fd, cmd, arg)						\
 ({										\
-	static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd), "");	\
+	kvm_static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd));	\
 	ioctl(fd, cmd, arg);							\
 })
 
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index bdd373189a77..1a6aaef5ccae 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -35,6 +35,14 @@ void ucall(uint64_t cmd, int nargs, ...);
 uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
 void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
 
+/*
+ * Perform userspace call without any associated data.  This bare call avoids
+ * allocating a ucall struct, which can be useful if the atomic operations in
+ * the full ucall() are problematic and/or unwanted.  Note, this will come out
+ * as UCALL_NONE on the backend.
+ */
+#define GUEST_UCALL_NONE()	ucall_arch_do_ucall((vm_vaddr_t)NULL)
+
 #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4)	\
 				ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
 #define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 5d310abe6c3f..b1a31de7108a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -72,11 +72,11 @@ struct kvm_x86_cpu_feature {
 		.bit = __bit,							\
 	};									\
 										\
-	static_assert((fn & 0xc0000000) == 0 ||					\
-		      (fn & 0xc0000000) == 0x40000000 ||			\
-		      (fn & 0xc0000000) == 0x80000000 ||			\
-		      (fn & 0xc0000000) == 0xc0000000);				\
-	static_assert(idx < BIT(sizeof(feature.index) * BITS_PER_BYTE));	\
+	kvm_static_assert((fn & 0xc0000000) == 0 ||				\
+			  (fn & 0xc0000000) == 0x40000000 ||			\
+			  (fn & 0xc0000000) == 0x80000000 ||			\
+			  (fn & 0xc0000000) == 0xc0000000);			\
+	kvm_static_assert(idx < BIT(sizeof(feature.index) * BITS_PER_BYTE));	\
 	feature;								\
 })
 
@@ -94,6 +94,7 @@ struct kvm_x86_cpu_feature {
 #define	X86_FEATURE_XSAVE		KVM_X86_CPU_FEATURE(0x1, 0, ECX, 26)
 #define	X86_FEATURE_OSXSAVE		KVM_X86_CPU_FEATURE(0x1, 0, ECX, 27)
 #define	X86_FEATURE_RDRAND		KVM_X86_CPU_FEATURE(0x1, 0, ECX, 30)
+#define	X86_FEATURE_HYPERVISOR		KVM_X86_CPU_FEATURE(0x1, 0, ECX, 31)
 #define X86_FEATURE_PAE			KVM_X86_CPU_FEATURE(0x1, 0, EDX, 6)
 #define	X86_FEATURE_MCE			KVM_X86_CPU_FEATURE(0x1, 0, EDX, 7)
 #define	X86_FEATURE_APIC		KVM_X86_CPU_FEATURE(0x1, 0, EDX, 9)
@@ -102,6 +103,7 @@ struct kvm_x86_cpu_feature {
 #define	X86_FEATURE_XMM2		KVM_X86_CPU_FEATURE(0x1, 0, EDX, 26)
 #define	X86_FEATURE_FSGSBASE		KVM_X86_CPU_FEATURE(0x7, 0, EBX, 0)
 #define	X86_FEATURE_TSC_ADJUST		KVM_X86_CPU_FEATURE(0x7, 0, EBX, 1)
+#define	X86_FEATURE_SGX			KVM_X86_CPU_FEATURE(0x7, 0, EBX, 2)
 #define	X86_FEATURE_HLE			KVM_X86_CPU_FEATURE(0x7, 0, EBX, 4)
 #define	X86_FEATURE_SMEP	        KVM_X86_CPU_FEATURE(0x7, 0, EBX, 7)
 #define	X86_FEATURE_INVPCID		KVM_X86_CPU_FEATURE(0x7, 0, EBX, 10)
@@ -115,6 +117,7 @@ struct kvm_x86_cpu_feature {
 #define	X86_FEATURE_PKU			KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3)
 #define	X86_FEATURE_LA57		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 16)
 #define	X86_FEATURE_RDPID		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 22)
+#define	X86_FEATURE_SGX_LC		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 30)
 #define	X86_FEATURE_SHSTK		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 7)
 #define	X86_FEATURE_IBT			KVM_X86_CPU_FEATURE(0x7, 0, EDX, 20)
 #define	X86_FEATURE_AMX_TILE		KVM_X86_CPU_FEATURE(0x7, 0, EDX, 24)
@@ -190,12 +193,12 @@ struct kvm_x86_cpu_property {
 		.hi_bit = high_bit,						\
 	};									\
 										\
-	static_assert(low_bit < high_bit);					\
-	static_assert((fn & 0xc0000000) == 0 ||					\
-		      (fn & 0xc0000000) == 0x40000000 ||			\
-		      (fn & 0xc0000000) == 0x80000000 ||			\
-		      (fn & 0xc0000000) == 0xc0000000);				\
-	static_assert(idx < BIT(sizeof(property.index) * BITS_PER_BYTE));	\
+	kvm_static_assert(low_bit < high_bit);					\
+	kvm_static_assert((fn & 0xc0000000) == 0 ||				\
+			  (fn & 0xc0000000) == 0x40000000 ||			\
+			  (fn & 0xc0000000) == 0x80000000 ||			\
+			  (fn & 0xc0000000) == 0xc0000000);			\
+	kvm_static_assert(idx < BIT(sizeof(property.index) * BITS_PER_BYTE));	\
 	property;								\
 })
 
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 72420171c0d4..0cc0971ce60e 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -44,7 +44,7 @@ static struct ucall *ucall_alloc(void)
 	GUEST_ASSERT(ucall_pool);
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (!atomic_test_and_set_bit(i, ucall_pool->in_use)) {
+		if (!test_and_set_bit(i, ucall_pool->in_use)) {
 			uc = &ucall_pool->ucalls[i];
 			memset(uc->args, 0, sizeof(uc->args));
 			return uc;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index c5c46f5b767c..c4d368d56cfe 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -552,40 +552,6 @@ static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 	vcpu_sregs_set(vcpu, &sregs);
 }
 
-void __vm_xsave_require_permission(int bit, const char *name)
-{
-	int kvm_fd;
-	u64 bitmask;
-	long rc;
-	struct kvm_device_attr attr = {
-		.group = 0,
-		.attr = KVM_X86_XCOMP_GUEST_SUPP,
-		.addr = (unsigned long) &bitmask
-	};
-
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD));
-
-	kvm_fd = open_kvm_dev_path_or_exit();
-	rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr);
-	close(kvm_fd);
-
-	if (rc == -1 && (errno == ENXIO || errno == EINVAL))
-		__TEST_REQUIRE(0, "KVM_X86_XCOMP_GUEST_SUPP not supported");
-
-	TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc);
-
-	__TEST_REQUIRE(bitmask & (1ULL << bit),
-		       "Required XSAVE feature '%s' not supported", name);
-
-	TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit));
-
-	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask);
-	TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc);
-	TEST_ASSERT(bitmask & (1ULL << bit),
-		    "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx",
-		    bitmask);
-}
-
 void kvm_arch_vm_post_create(struct kvm_vm *vm)
 {
 	vm_create_irqchip(vm);
@@ -636,21 +602,24 @@ void vcpu_arch_free(struct kvm_vcpu *vcpu)
 		free(vcpu->cpuid);
 }
 
+/* Do not use kvm_supported_cpuid directly except for validity checks. */
+static void *kvm_supported_cpuid;
+
 const struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
 {
-	static struct kvm_cpuid2 *cpuid;
 	int kvm_fd;
 
-	if (cpuid)
-		return cpuid;
+	if (kvm_supported_cpuid)
+		return kvm_supported_cpuid;
 
-	cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
+	kvm_supported_cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
 	kvm_fd = open_kvm_dev_path_or_exit();
 
-	kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+	kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID,
+		  (struct kvm_cpuid2 *)kvm_supported_cpuid);
 
 	close(kvm_fd);
-	return cpuid;
+	return kvm_supported_cpuid;
 }
 
 static uint32_t __kvm_cpu_has(const struct kvm_cpuid2 *cpuid,
@@ -708,6 +677,41 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index)
 	return buffer.entry.data;
 }
 
+void __vm_xsave_require_permission(int bit, const char *name)
+{
+	int kvm_fd;
+	u64 bitmask;
+	long rc;
+	struct kvm_device_attr attr = {
+		.group = 0,
+		.attr = KVM_X86_XCOMP_GUEST_SUPP,
+		.addr = (unsigned long) &bitmask
+	};
+
+	TEST_ASSERT(!kvm_supported_cpuid,
+		    "kvm_get_supported_cpuid() cannot be used before ARCH_REQ_XCOMP_GUEST_PERM");
+
+	kvm_fd = open_kvm_dev_path_or_exit();
+	rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr);
+	close(kvm_fd);
+
+	if (rc == -1 && (errno == ENXIO || errno == EINVAL))
+		__TEST_REQUIRE(0, "KVM_X86_XCOMP_GUEST_SUPP not supported");
+
+	TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc);
+
+	__TEST_REQUIRE(bitmask & (1ULL << bit),
+		       "Required XSAVE feature '%s' not supported", name);
+
+	TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit));
+
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask);
+	TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc);
+	TEST_ASSERT(bitmask & (1ULL << bit),
+		    "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx",
+		    bitmask);
+}
+
 void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid)
 {
 	TEST_ASSERT(cpuid != vcpu->cpuid, "@cpuid can't be the vCPU's CPUID");
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 21de6ae42086..bd72c6eb3b67 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -249,16 +249,21 @@ int main(int argc, char *argv[])
 	u32 amx_offset;
 	int stage, ret;
 
+	/*
+	 * Note, all off-by-default features must be enabled before anything
+	 * caches KVM_GET_SUPPORTED_CPUID, e.g. before using kvm_cpu_has().
+	 */
 	vm_xsave_require_permission(XSTATE_XTILE_DATA_BIT);
 
-	/* Create VM */
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD));
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE));
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_AMX_TILE));
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG));
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA));
 
+	/* Create VM */
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
 	TEST_ASSERT(kvm_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE),
 		    "KVM should enumerate max XSAVE size when XSAVE is supported");
 	xsave_restore_size = kvm_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
index ba09d300c953..af29e5776d40 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
@@ -142,7 +142,7 @@ void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages,
 	/* Intercept RDMSR 0xc0000100 */
 	vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) |
 		CPU_BASED_USE_MSR_BITMAPS);
-	set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400);
+	__set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400);
 	GUEST_ASSERT(!vmresume());
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
 	current_evmcs->guest_rip += 2; /* rdmsr */
@@ -154,7 +154,7 @@ void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages,
 	current_evmcs->guest_rip += 2; /* rdmsr */
 
 	/* Intercept RDMSR 0xc0000101 without telling KVM about it */
-	set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400);
+	__set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400);
 	/* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */
 	current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
 	GUEST_ASSERT(!vmresume());
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index 3b3cc94ba8e4..68a7d354ea07 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -103,7 +103,7 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm,
 
 	/* Intercept RDMSR 0xc0000100 */
 	vmcb->control.intercept |= 1ULL << INTERCEPT_MSR_PROT;
-	set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800);
+	__set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800);
 	run_guest(vmcb, svm->vmcb_gpa);
 	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
 	vmcb->save.rip += 2; /* rdmsr */
@@ -115,7 +115,7 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm,
 	vmcb->save.rip += 2; /* rdmsr */
 
 	/* Intercept RDMSR 0xc0000101 without telling KVM about it */
-	set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800);
+	__set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800);
 	/* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */
 	vmcb->control.clean |= HV_VMCB_NESTED_ENLIGHTENMENTS;
 	run_guest(vmcb, svm->vmcb_gpa);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c
index 322d561b4260..90720b6205f4 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c
@@ -67,6 +67,52 @@ static void vmx_save_restore_msrs_test(struct kvm_vcpu *vcpu)
 	vmx_fixed1_msr_test(vcpu, MSR_IA32_VMX_VMFUNC, -1ull);
 }
 
+static void __ia32_feature_control_msr_test(struct kvm_vcpu *vcpu,
+					    uint64_t msr_bit,
+					    struct kvm_x86_cpu_feature feature)
+{
+	uint64_t val;
+
+	vcpu_clear_cpuid_feature(vcpu, feature);
+
+	val = vcpu_get_msr(vcpu, MSR_IA32_FEAT_CTL);
+	vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, val | msr_bit | FEAT_CTL_LOCKED);
+	vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, (val & ~msr_bit) | FEAT_CTL_LOCKED);
+	vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, val | msr_bit | FEAT_CTL_LOCKED);
+	vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, (val & ~msr_bit) | FEAT_CTL_LOCKED);
+	vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, val);
+
+	if (!kvm_cpu_has(feature))
+		return;
+
+	vcpu_set_cpuid_feature(vcpu, feature);
+}
+
+static void ia32_feature_control_msr_test(struct kvm_vcpu *vcpu)
+{
+	uint64_t supported_bits = FEAT_CTL_LOCKED |
+				  FEAT_CTL_VMX_ENABLED_INSIDE_SMX |
+				  FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX |
+				  FEAT_CTL_SGX_LC_ENABLED |
+				  FEAT_CTL_SGX_ENABLED |
+				  FEAT_CTL_LMCE_ENABLED;
+	int bit, r;
+
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_VMX_ENABLED_INSIDE_SMX, X86_FEATURE_SMX);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_VMX_ENABLED_INSIDE_SMX, X86_FEATURE_VMX);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX, X86_FEATURE_VMX);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_SGX_LC_ENABLED, X86_FEATURE_SGX_LC);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_SGX_LC_ENABLED, X86_FEATURE_SGX);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_SGX_ENABLED, X86_FEATURE_SGX);
+	__ia32_feature_control_msr_test(vcpu, FEAT_CTL_LMCE_ENABLED, X86_FEATURE_MCE);
+
+	for_each_clear_bit(bit, &supported_bits, 64) {
+		r = _vcpu_set_msr(vcpu, MSR_IA32_FEAT_CTL, BIT(bit));
+		TEST_ASSERT(r == 0,
+			    "Setting reserved bit %d in IA32_FEATURE_CONTROL should fail", bit);
+	}
+}
+
 int main(void)
 {
 	struct kvm_vcpu *vcpu;
@@ -79,6 +125,7 @@ int main(void)
 	vm = vm_create_with_one_vcpu(&vcpu, NULL);
 
 	vmx_save_restore_msrs_test(vcpu);
+	ia32_feature_control_msr_test(vcpu);
 
 	kvm_vm_free(vm);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 2a5727188c8d..721f6a693799 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -26,17 +26,17 @@
 #define SHINFO_REGION_GPA	0xc0000000ULL
 #define SHINFO_REGION_SLOT	10
 
-#define DUMMY_REGION_GPA	(SHINFO_REGION_GPA + (2 * PAGE_SIZE))
+#define DUMMY_REGION_GPA	(SHINFO_REGION_GPA + (3 * PAGE_SIZE))
 #define DUMMY_REGION_SLOT	11
 
 #define SHINFO_ADDR	(SHINFO_REGION_GPA)
-#define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
-#define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
 #define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
+#define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
+#define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + PAGE_SIZE - 15)
 
 #define SHINFO_VADDR	(SHINFO_REGION_GVA)
-#define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
 #define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+#define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + PAGE_SIZE - 15)
 
 #define EVTCHN_VECTOR	0x10
 
@@ -88,14 +88,20 @@ struct pvclock_wall_clock {
 } __attribute__((__packed__));
 
 struct vcpu_runstate_info {
-    uint32_t state;
-    uint64_t state_entry_time;
-    uint64_t time[4];
+	uint32_t state;
+	uint64_t state_entry_time;
+	uint64_t time[5]; /* Extra field for overrun check */
 };
 
+struct compat_vcpu_runstate_info {
+	uint32_t state;
+	uint64_t state_entry_time;
+	uint64_t time[5];
+} __attribute__((__packed__));;
+
 struct arch_vcpu_info {
-    unsigned long cr2;
-    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+	unsigned long cr2;
+	unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
 };
 
 struct vcpu_info {
@@ -440,6 +446,7 @@ int main(int argc, char *argv[])
 	TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO);
 
 	bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
+	bool do_runstate_flag = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG);
 	bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
 	bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
 
@@ -449,8 +456,8 @@ int main(int argc, char *argv[])
 
 	/* Map a region for the shared_info page */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0);
-	virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2);
+				    SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 3, 0);
+	virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 3);
 
 	struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
 
@@ -475,6 +482,19 @@ int main(int argc, char *argv[])
 	};
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &lm);
 
+	if (do_runstate_flag) {
+		struct kvm_xen_hvm_attr ruf = {
+			.type = KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG,
+			.u.runstate_update_flag = 1,
+		};
+		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ruf);
+
+		ruf.u.runstate_update_flag = 0;
+		vm_ioctl(vm, KVM_XEN_HVM_GET_ATTR, &ruf);
+		TEST_ASSERT(ruf.u.runstate_update_flag == 1,
+			    "Failed to read back RUNSTATE_UPDATE_FLAG attr");
+	}
+
 	struct kvm_xen_hvm_attr ha = {
 		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
 		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE,
@@ -999,22 +1019,91 @@ int main(int argc, char *argv[])
 				       runstate_names[i], rs->time[i]);
 			}
 		}
-		TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch");
-		TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time,
-			    "State entry time mismatch");
-		TEST_ASSERT(rs->time[RUNSTATE_running] == rst.u.runstate.time_running,
-			    "Running time mismatch");
-		TEST_ASSERT(rs->time[RUNSTATE_runnable] == rst.u.runstate.time_runnable,
-			    "Runnable time mismatch");
-		TEST_ASSERT(rs->time[RUNSTATE_blocked] == rst.u.runstate.time_blocked,
-			    "Blocked time mismatch");
-		TEST_ASSERT(rs->time[RUNSTATE_offline] == rst.u.runstate.time_offline,
-			    "Offline time mismatch");
-
-		TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-			    rs->time[1] + rs->time[2] + rs->time[3],
-			    "runstate times don't add up");
+
+		/*
+		 * Exercise runstate info at all points across the page boundary, in
+		 * 32-bit and 64-bit mode. In particular, test the case where it is
+		 * configured in 32-bit mode and then switched to 64-bit mode while
+		 * active, which takes it onto the second page.
+		 */
+		unsigned long runstate_addr;
+		struct compat_vcpu_runstate_info *crs;
+		for (runstate_addr = SHINFO_REGION_GPA + PAGE_SIZE + PAGE_SIZE - sizeof(*rs) - 4;
+		     runstate_addr < SHINFO_REGION_GPA + PAGE_SIZE + PAGE_SIZE + 4; runstate_addr++) {
+
+			rs = addr_gpa2hva(vm, runstate_addr);
+			crs = (void *)rs;
+
+			memset(rs, 0xa5, sizeof(*rs));
+
+			/* Set to compatibility mode */
+			lm.u.long_mode = 0;
+			vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &lm);
+
+			/* Set runstate to new address (kernel will write it) */
+			struct kvm_xen_vcpu_attr st = {
+				.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
+				.u.gpa = runstate_addr,
+			};
+			vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &st);
+
+			if (verbose)
+				printf("Compatibility runstate at %08lx\n", runstate_addr);
+
+			TEST_ASSERT(crs->state == rst.u.runstate.state, "Runstate mismatch");
+			TEST_ASSERT(crs->state_entry_time == rst.u.runstate.state_entry_time,
+				    "State entry time mismatch");
+			TEST_ASSERT(crs->time[RUNSTATE_running] == rst.u.runstate.time_running,
+				    "Running time mismatch");
+			TEST_ASSERT(crs->time[RUNSTATE_runnable] == rst.u.runstate.time_runnable,
+				    "Runnable time mismatch");
+			TEST_ASSERT(crs->time[RUNSTATE_blocked] == rst.u.runstate.time_blocked,
+				    "Blocked time mismatch");
+			TEST_ASSERT(crs->time[RUNSTATE_offline] == rst.u.runstate.time_offline,
+				    "Offline time mismatch");
+			TEST_ASSERT(crs->time[RUNSTATE_offline + 1] == 0xa5a5a5a5a5a5a5a5ULL,
+				    "Structure overrun");
+			TEST_ASSERT(crs->state_entry_time == crs->time[0] +
+				    crs->time[1] + crs->time[2] + crs->time[3],
+				    "runstate times don't add up");
+
+
+			/* Now switch to 64-bit mode */
+			lm.u.long_mode = 1;
+			vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &lm);
+
+			memset(rs, 0xa5, sizeof(*rs));
+
+			/* Don't change the address, just trigger a write */
+			struct kvm_xen_vcpu_attr adj = {
+				.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST,
+				.u.runstate.state = (uint64_t)-1
+			};
+			vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &adj);
+
+			if (verbose)
+				printf("64-bit runstate at %08lx\n", runstate_addr);
+
+			TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch");
+			TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time,
+				    "State entry time mismatch");
+			TEST_ASSERT(rs->time[RUNSTATE_running] == rst.u.runstate.time_running,
+				    "Running time mismatch");
+			TEST_ASSERT(rs->time[RUNSTATE_runnable] == rst.u.runstate.time_runnable,
+				    "Runnable time mismatch");
+			TEST_ASSERT(rs->time[RUNSTATE_blocked] == rst.u.runstate.time_blocked,
+				    "Blocked time mismatch");
+			TEST_ASSERT(rs->time[RUNSTATE_offline] == rst.u.runstate.time_offline,
+				    "Offline time mismatch");
+			TEST_ASSERT(rs->time[RUNSTATE_offline + 1] == 0xa5a5a5a5a5a5a5a5ULL,
+				    "Structure overrun");
+
+			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+				    rs->time[1] + rs->time[2] + rs->time[3],
+				    "runstate times don't add up");
+		}
 	}
+
 	kvm_vm_free(vm);
 	return 0;
 }