Merge tag 'kvm-x86-selftests-6.4' of https://github.com/kvm-x86/linux into HEAD

KVM selftests, and an AMX/XCR0 bugfix, for 6.4:

 - Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if XTILE_DATA is
   not being reported due to userspace not opting in via prctl()

 - Overhaul the AMX selftests to improve coverage and cleanup the test

 - Misc cleanups

Author: bonzini

arch/x86/kvm/cpuid.c

@@ -996,7 +996,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->eax = entry->ebx = entry->ecx = 0;
 		break;
 	case 0xd: {
-		u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
+		u64 permitted_xcr0 = kvm_get_filtered_xcr0();
 		u64 permitted_xss = kvm_caps.supported_xss;
 
 		entry->eax &= permitted_xcr0;

arch/x86/kvm/x86.c

@@ -4593,9 +4593,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = 0;
 		break;
 	case KVM_CAP_XSAVE2: {
-		u64 guest_perm = xstate_get_guest_group_perm();
-
-		r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false);
+		r = xstate_required_size(kvm_get_filtered_xcr0(), false);
 		if (r < sizeof(struct kvm_xsave))
 			r = sizeof(struct kvm_xsave);
 		break;

arch/x86/kvm/x86.h

@@ -3,6 +3,7 @@
 #define ARCH_X86_KVM_X86_H
 
 #include <linux/kvm_host.h>
+#include <asm/fpu/xstate.h>
 #include <asm/mce.h>
 #include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
@@ -328,6 +329,34 @@ extern struct kvm_caps kvm_caps;
 
 extern bool enable_pmu;
 
+/*
+ * Get a filtered version of KVM's supported XCR0 that strips out dynamic
+ * features for which the current process doesn't (yet) have permission to use.
+ * This is intended to be used only when enumerating support to userspace,
+ * e.g. in KVM_GET_SUPPORTED_CPUID and KVM_CAP_XSAVE2, it does NOT need to be
+ * used to check/restrict guest behavior as KVM rejects KVM_SET_CPUID{2} if
+ * userspace attempts to enable unpermitted features.
+ */
+static inline u64 kvm_get_filtered_xcr0(void)
+{
+	u64 permitted_xcr0 = kvm_caps.supported_xcr0;
+
+	BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA);
+
+	if (permitted_xcr0 & XFEATURE_MASK_USER_DYNAMIC) {
+		permitted_xcr0 &= xstate_get_guest_group_perm();
+
+		/*
+		 * Treat XTILE_CFG as unsupported if the current process isn't
+		 * allowed to use XTILE_DATA, as attempting to set XTILE_CFG in
+		 * XCR0 without setting XTILE_DATA is architecturally illegal.
+		 */
+		if (!(permitted_xcr0 & XFEATURE_MASK_XTILE_DATA))
+			permitted_xcr0 &= ~XFEATURE_MASK_XTILE_CFG;
+	}
+	return permitted_xcr0;
+}
+
 static inline bool kvm_mpx_supported(void)
 {
 	return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))

tools/testing/selftests/kvm/Makefile

@@ -105,6 +105,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test
 TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test
 TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test
+TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test

tools/testing/selftests/kvm/demand_paging_test.c

@@ -194,7 +194,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 	pr_info("Overall demand paging rate: %f pgs/sec\n",
 		memstress_args.vcpu_args[0].pages * nr_vcpus /
-		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC));
 
 	memstress_destroy_vm(vm);
 

tools/testing/selftests/kvm/include/kvm_util_base.h

@@ -213,6 +213,7 @@ extern const struct vm_guest_mode_params vm_guest_mode_params[];
 int open_path_or_exit(const char *path, int flags);
 int open_kvm_dev_path_or_exit(void);
 
+bool get_kvm_param_bool(const char *param);
 bool get_kvm_intel_param_bool(const char *param);
 bool get_kvm_amd_param_bool(const char *param);
 

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -48,6 +48,35 @@ extern bool host_cpu_is_amd;
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+struct xstate_header {
+	u64				xstate_bv;
+	u64				xcomp_bv;
+	u64				reserved[6];
+} __attribute__((packed));
+
+struct xstate {
+	u8				i387[512];
+	struct xstate_header		header;
+	u8				extended_state_area[0];
+} __attribute__ ((packed, aligned (64)));
+
+#define XFEATURE_MASK_FP		BIT_ULL(0)
+#define XFEATURE_MASK_SSE		BIT_ULL(1)
+#define XFEATURE_MASK_YMM		BIT_ULL(2)
+#define XFEATURE_MASK_BNDREGS		BIT_ULL(3)
+#define XFEATURE_MASK_BNDCSR		BIT_ULL(4)
+#define XFEATURE_MASK_OPMASK		BIT_ULL(5)
+#define XFEATURE_MASK_ZMM_Hi256		BIT_ULL(6)
+#define XFEATURE_MASK_Hi16_ZMM		BIT_ULL(7)
+#define XFEATURE_MASK_XTILE_CFG		BIT_ULL(17)
+#define XFEATURE_MASK_XTILE_DATA	BIT_ULL(18)
+
+#define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK | \
+					 XFEATURE_MASK_ZMM_Hi256 | \
+					 XFEATURE_MASK_Hi16_ZMM)
+#define XFEATURE_MASK_XTILE		(XFEATURE_MASK_XTILE_DATA | \
+					 XFEATURE_MASK_XTILE_CFG)
+
 /* Note, these are ordered alphabetically to match kvm_cpuid_entry2.  Eww. */
 enum cpuid_output_regs {
 	KVM_CPUID_EAX,
@@ -131,6 +160,7 @@ struct kvm_x86_cpu_feature {
 #define	X86_FEATURE_XTILEDATA		KVM_X86_CPU_FEATURE(0xD, 0, EAX, 18)
 #define	X86_FEATURE_XSAVES		KVM_X86_CPU_FEATURE(0xD, 1, EAX, 3)
 #define	X86_FEATURE_XFD			KVM_X86_CPU_FEATURE(0xD, 1, EAX, 4)
+#define X86_FEATURE_XTILEDATA_XFD	KVM_X86_CPU_FEATURE(0xD, 18, ECX, 2)
 
 /*
  * Extended Leafs, a.k.a. AMD defined
@@ -211,10 +241,14 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_PMU_NR_GP_COUNTERS		KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
 #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH	KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
 
+#define X86_PROPERTY_SUPPORTED_XCR0_LO		KVM_X86_CPU_PROPERTY(0xd,  0, EAX,  0, 31)
 #define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0	KVM_X86_CPU_PROPERTY(0xd,  0, EBX,  0, 31)
 #define X86_PROPERTY_XSTATE_MAX_SIZE		KVM_X86_CPU_PROPERTY(0xd,  0, ECX,  0, 31)
+#define X86_PROPERTY_SUPPORTED_XCR0_HI		KVM_X86_CPU_PROPERTY(0xd,  0, EDX,  0, 31)
+
 #define X86_PROPERTY_XSTATE_TILE_SIZE		KVM_X86_CPU_PROPERTY(0xd, 18, EAX,  0, 31)
 #define X86_PROPERTY_XSTATE_TILE_OFFSET		KVM_X86_CPU_PROPERTY(0xd, 18, EBX,  0, 31)
+#define X86_PROPERTY_AMX_MAX_PALETTE_TABLES	KVM_X86_CPU_PROPERTY(0x1d, 0, EAX,  0, 31)
 #define X86_PROPERTY_AMX_TOTAL_TILE_BYTES	KVM_X86_CPU_PROPERTY(0x1d, 1, EAX,  0, 15)
 #define X86_PROPERTY_AMX_BYTES_PER_TILE		KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 16, 31)
 #define X86_PROPERTY_AMX_BYTES_PER_ROW		KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 0,  15)
@@ -496,6 +530,24 @@ static inline void set_cr4(uint64_t val)
 	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
 }
 
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	__asm__ __volatile__("xgetbv;"
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax | ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	__asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
+}
+
 static inline struct desc_ptr get_gdt(void)
 {
 	struct desc_ptr gdt;
@@ -632,6 +684,15 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature)
 	       !this_cpu_has(feature.anti_feature);
 }
 
+static __always_inline uint64_t this_cpu_supported_xcr0(void)
+{
+	if (!this_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO))
+		return 0;
+
+	return this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) |
+	       ((uint64_t)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32);
+}
+
 typedef u32		__attribute__((vector_size(16))) sse128_t;
 #define __sse128_u	union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; }
 #define sse128_lo(x)	({ __sse128_u t; t.vec = x; t.as_u64[0]; })
@@ -1086,6 +1147,14 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val)
 	return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr));
 }
 
+static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	return kvm_asm_safe("xsetbv", "a" (eax), "d" (edx), "c" (index));
+}
+
 bool kvm_is_tdp_enabled(void);
 
 uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
@@ -1097,10 +1166,10 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 void xen_hypercall(uint64_t nr, uint64_t a0, void *a1);
 
-void __vm_xsave_require_permission(int bit, const char *name);
+void __vm_xsave_require_permission(uint64_t xfeature, const char *name);
 
-#define vm_xsave_require_permission(perm)	\
-	__vm_xsave_require_permission(perm, #perm)
+#define vm_xsave_require_permission(xfeature)	\
+	__vm_xsave_require_permission(xfeature, #xfeature)
 
 enum pg_level {
 	PG_LEVEL_NONE,
@@ -1137,14 +1206,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 #define X86_CR0_CD          (1UL<<30) /* Cache Disable */
 #define X86_CR0_PG          (1UL<<31) /* Paging */
 
-#define XSTATE_XTILE_CFG_BIT		17
-#define XSTATE_XTILE_DATA_BIT		18
-
-#define XSTATE_XTILE_CFG_MASK		(1ULL << XSTATE_XTILE_CFG_BIT)
-#define XSTATE_XTILE_DATA_MASK		(1ULL << XSTATE_XTILE_DATA_BIT)
-#define XFEATURE_XTILE_MASK		(XSTATE_XTILE_CFG_MASK | \
-					XSTATE_XTILE_DATA_MASK)
-
 #define PFERR_PRESENT_BIT 0
 #define PFERR_WRITE_BIT 1
 #define PFERR_USER_BIT 2

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -80,6 +80,11 @@ static bool get_module_param_bool(const char *module_name, const char *param)
 	TEST_FAIL("Unrecognized value '%c' for boolean module param", value);
 }
 
+bool get_kvm_param_bool(const char *param)
+{
+	return get_module_param_bool("kvm", param);
+}
+
 bool get_kvm_intel_param_bool(const char *param)
 {
 	return get_module_param_bool("kvm_intel", param);

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -5,6 +5,7 @@
  * Copyright (C) 2018, Google LLC.
  */
 
+#include "linux/bitmap.h"
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
@@ -573,14 +574,29 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				       DEFAULT_GUEST_STACK_VADDR_MIN,
 				       MEM_REGION_DATA);
 
+	stack_vaddr += DEFAULT_STACK_PGS * getpagesize();
+
+	/*
+	 * Align stack to match calling sequence requirements in section "The
+	 * Stack Frame" of the System V ABI AMD64 Architecture Processor
+	 * Supplement, which requires the value (%rsp + 8) to be a multiple of
+	 * 16 when control is transferred to the function entry point.
+	 *
+	 * If this code is ever used to launch a vCPU with 32-bit entry point it
+	 * may need to subtract 4 bytes instead of 8 bytes.
+	 */
+	TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE),
+		    "__vm_vaddr_alloc() did not provide a page-aligned address");
+	stack_vaddr -= 8;
+
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
 	vcpu_setup(vm, vcpu);
 
 	/* Setup guest general purpose registers */
 	vcpu_regs_get(vcpu, &regs);
 	regs.rflags = regs.rflags | 0x2;
-	regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
+	regs.rsp = stack_vaddr;
 	regs.rip = (unsigned long) guest_code;
 	vcpu_regs_set(vcpu, &regs);
 
@@ -681,20 +697,23 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index)
 	return buffer.entry.data;
 }
 
-void __vm_xsave_require_permission(int bit, const char *name)
+void __vm_xsave_require_permission(uint64_t xfeature, 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
+		.addr = (unsigned long) &bitmask,
 	};
 
 	TEST_ASSERT(!kvm_supported_cpuid,
 		    "kvm_get_supported_cpuid() cannot be used before ARCH_REQ_XCOMP_GUEST_PERM");
 
+	TEST_ASSERT(is_power_of_2(xfeature),
+		    "Dynamic XFeatures must be enabled one at a time");
+
 	kvm_fd = open_kvm_dev_path_or_exit();
 	rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr);
 	close(kvm_fd);
@@ -704,16 +723,16 @@ void __vm_xsave_require_permission(int bit, const char *name)
 
 	TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc);
 
-	__TEST_REQUIRE(bitmask & (1ULL << bit),
+	__TEST_REQUIRE(bitmask & xfeature,
 		       "Required XSAVE feature '%s' not supported", name);
 
-	TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit));
+	TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, ilog2(xfeature)));
 
 	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);
+	TEST_ASSERT(bitmask & xfeature,
+		    "'%s' (0x%lx) not permitted after prctl(ARCH_REQ_XCOMP_GUEST_PERM) permitted=0x%lx",
+		    name, xfeature, bitmask);
 }
 
 void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid)
@@ -954,6 +973,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu)
 	vcpu_run_complete_io(vcpu);
 
 	state = malloc(sizeof(*state) + msr_list->nmsrs * sizeof(state->msrs.entries[0]));
+	TEST_ASSERT(state, "-ENOMEM when allocating kvm state");
 
 	vcpu_events_get(vcpu, &state->events);
 	vcpu_mp_state_get(vcpu, &state->mp_state);