4 files changed, 132 insertions, 20 deletions
diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h
index 1e8d0d531fbd..b0fc0f945766 100644
--- a/tools/testing/selftests/kvm/include/arm64/processor.h
+++ b/tools/testing/selftests/kvm/include/arm64/processor.h
@@ -62,6 +62,67 @@
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |				\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
 
+/* TCR_EL1 specific flags */
+#define TCR_T0SZ_OFFSET	0
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+
+#define TCR_IRGN0_SHIFT	8
+#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA	(UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT	10
+#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA	(UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT		12
+#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT		14
+#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_IPS_SHIFT		32
+#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
+#define TCR_IPS_52_BITS	(UL(6) << TCR_IPS_SHIFT)
+#define TCR_IPS_48_BITS	(UL(5) << TCR_IPS_SHIFT)
+#define TCR_IPS_40_BITS	(UL(2) << TCR_IPS_SHIFT)
+#define TCR_IPS_36_BITS	(UL(1) << TCR_IPS_SHIFT)
+
+#define TCR_HA			(UL(1) << 39)
+#define TCR_DS			(UL(1) << 59)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t)	((t) << 2)
+#define PTE_ATTRINDX_MASK	GENMASK(4, 2)
+#define PTE_ATTRINDX_SHIFT	2
+
+#define PTE_VALID		BIT(0)
+#define PGD_TYPE_TABLE		BIT(1)
+#define PUD_TYPE_TABLE		BIT(1)
+#define PMD_TYPE_TABLE		BIT(1)
+#define PTE_TYPE_PAGE		BIT(1)
+
+#define PTE_SHARED		(UL(3) << 8) /* SH[1:0], inner shareable */
+#define PTE_AF			BIT(10)
+
+#define PTE_ADDR_MASK(page_shift)	GENMASK(47, (page_shift))
+#define PTE_ADDR_51_48			GENMASK(15, 12)
+#define PTE_ADDR_51_48_SHIFT		12
+#define PTE_ADDR_MASK_LPA2(page_shift)	GENMASK(49, (page_shift))
+#define PTE_ADDR_51_50_LPA2		GENMASK(9, 8)
+#define PTE_ADDR_51_50_LPA2_SHIFT	8
+
 void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
 struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  struct kvm_vcpu_init *init, void *guest_code);
@@ -102,12 +163,6 @@ enum {
 			   (v) == VECTOR_SYNC_LOWER_64    || \
 			   (v) == VECTOR_SYNC_LOWER_32)
 
-/* Access flag */
-#define PTE_AF			(1ULL << 10)
-
-/* Access flag update enable/disable */
-#define TCR_EL1_HA		(1ULL << 39)
-
 void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 					uint32_t *ipa16k, uint32_t *ipa64k);
 
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 4c4e5a847f67..373912464fb4 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -46,6 +46,12 @@ struct userspace_mem_region {
 	struct hlist_node slot_node;
 };
 
+struct kvm_binary_stats {
+	int fd;
+	struct kvm_stats_header header;
+	struct kvm_stats_desc *desc;
+};
+
 struct kvm_vcpu {
 	struct list_head list;
 	uint32_t id;
@@ -55,6 +61,7 @@ struct kvm_vcpu {
 #ifdef __x86_64__
 	struct kvm_cpuid2 *cpuid;
 #endif
+	struct kvm_binary_stats stats;
 	struct kvm_dirty_gfn *dirty_gfns;
 	uint32_t fetch_index;
 	uint32_t dirty_gfns_count;
@@ -99,10 +106,7 @@ struct kvm_vm {
 
 	struct kvm_vm_arch arch;
 
-	/* Cache of information for binary stats interface */
-	int stats_fd;
-	struct kvm_stats_header stats_header;
-	struct kvm_stats_desc *stats_desc;
+	struct kvm_binary_stats stats;
 
 	/*
 	 * KVM region slots. These are the default memslots used by page
@@ -531,16 +535,19 @@ void read_stat_data(int stats_fd, struct kvm_stats_header *header,
 		    struct kvm_stats_desc *desc, uint64_t *data,
 		    size_t max_elements);
 
-void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
-		   size_t max_elements);
+void kvm_get_stat(struct kvm_binary_stats *stats, const char *name,
+		  uint64_t *data, size_t max_elements);
 
-static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name)
-{
-	uint64_t data;
+#define __get_stat(stats, stat)							\
+({										\
+	uint64_t data;								\
+										\
+	kvm_get_stat(stats, #stat, &data, 1);					\
+	data;									\
+})
 
-	__vm_get_stat(vm, stat_name, &data, 1);
-	return data;
-}
+#define vm_get_stat(vm, stat) __get_stat(&(vm)->stats, stat)
+#define vcpu_get_stat(vcpu, stat) __get_stat(&(vcpu)->stats, stat)
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
@@ -963,6 +970,8 @@ static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape
 
 struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
 
+void kvm_set_files_rlimit(uint32_t nr_vcpus);
+
 void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
 void kvm_print_vcpu_pinning_help(void);
 void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 3e473058849f..77d13d7920cb 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -22,7 +22,7 @@
 
 #define msecs_to_usecs(msec)    ((msec) * 1000ULL)
 
-static inline int _no_printf(const char *format, ...) { return 0; }
+static inline __printf(1, 2) int _no_printf(const char *format, ...) { return 0; }
 
 #ifdef DEBUG
 #define pr_debug(...) printf(__VA_ARGS__)
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index d60da8966772..32ab6ca7ec32 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -183,6 +183,9 @@ struct kvm_x86_cpu_feature {
  * Extended Leafs, a.k.a. AMD defined
  */
 #define	X86_FEATURE_SVM			KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 2)
+#define	X86_FEATURE_PERFCTR_CORE	KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 23)
+#define	X86_FEATURE_PERFCTR_NB		KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 24)
+#define	X86_FEATURE_PERFCTR_LLC		KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 28)
 #define	X86_FEATURE_NX			KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 20)
 #define	X86_FEATURE_GBPAGES		KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26)
 #define	X86_FEATURE_RDTSCP		KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27)
@@ -197,8 +200,11 @@ struct kvm_x86_cpu_feature {
 #define X86_FEATURE_PAUSEFILTER         KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 10)
 #define X86_FEATURE_PFTHRESHOLD         KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 12)
 #define	X86_FEATURE_VGIF		KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 16)
+#define X86_FEATURE_IDLE_HLT		KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 30)
 #define X86_FEATURE_SEV			KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1)
 #define X86_FEATURE_SEV_ES		KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3)
+#define	X86_FEATURE_PERFMON_V2		KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 0)
+#define	X86_FEATURE_LBR_PMC_FREEZE	KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 2)
 
 /*
  * KVM defined paravirt features.
@@ -285,6 +291,8 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_GUEST_MAX_PHY_ADDR		KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23)
 #define X86_PROPERTY_SEV_C_BIT			KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5)
 #define X86_PROPERTY_PHYS_ADDR_REDUCTION	KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11)
+#define X86_PROPERTY_NR_PERFCTR_CORE		KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 0, 3)
+#define X86_PROPERTY_NR_PERFCTR_NB		KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 10, 15)
 
 #define X86_PROPERTY_MAX_CENTAUR_LEAF		KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31)
 
@@ -1244,7 +1252,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 	uint64_t ign_error_code;					\
 	uint8_t vector;							\
 									\
-	asm volatile(KVM_ASM_SAFE(insn)					\
+	asm volatile(KVM_ASM_SAFE_FEP(insn)				\
 		     : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code)	\
 		     : inputs						\
 		     : KVM_ASM_SAFE_CLOBBERS);				\
@@ -1339,6 +1347,46 @@ static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size,
 	GUEST_ASSERT(!ret);
 }
 
+/*
+ * Execute HLT in an STI interrupt shadow to ensure that a pending IRQ that's
+ * intended to be a wake event arrives *after* HLT is executed.  Modern CPUs,
+ * except for a few oddballs that KVM is unlikely to run on, block IRQs for one
+ * instruction after STI, *if* RFLAGS.IF=0 before STI.  Note, Intel CPUs may
+ * block other events beyond regular IRQs, e.g. may block NMIs and SMIs too.
+ */
+static inline void safe_halt(void)
+{
+	asm volatile("sti; hlt");
+}
+
+/*
+ * Enable interrupts and ensure that interrupts are evaluated upon return from
+ * this function, i.e. execute a nop to consume the STi interrupt shadow.
+ */
+static inline void sti_nop(void)
+{
+	asm volatile ("sti; nop");
+}
+
+/*
+ * Enable interrupts for one instruction (nop), to allow the CPU to process all
+ * interrupts that are already pending.
+ */
+static inline void sti_nop_cli(void)
+{
+	asm volatile ("sti; nop; cli");
+}
+
+static inline void sti(void)
+{
+	asm volatile("sti");
+}
+
+static inline void cli(void)
+{
+	asm volatile ("cli");
+}
+
 void __vm_xsave_require_permission(uint64_t xfeature, const char *name);
 
 #define vm_xsave_require_permission(xfeature)	\