summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/kvm/include
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/kvm/include')
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/arch_timer.h142
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/delay.h25
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic.h47
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic_v3.h82
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h232
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/spinlock.h13
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/ucall.h20
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/vgic.h36
-rw-r--r--tools/testing/selftests/kvm/include/guest_modes.h21
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h13
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util_base.h935
-rw-r--r--tools/testing/selftests/kvm/include/memstress.h83
-rw-r--r--tools/testing/selftests/kvm/include/numaif.h55
-rw-r--r--tools/testing/selftests/kvm/include/riscv/processor.h122
-rw-r--r--tools/testing/selftests/kvm/include/riscv/ucall.h20
-rw-r--r--tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h13
-rw-r--r--tools/testing/selftests/kvm/include/s390x/processor.h30
-rw-r--r--tools/testing/selftests/kvm/include/s390x/ucall.h19
-rw-r--r--tools/testing/selftests/kvm/include/sparsebit.h73
-rw-r--r--tools/testing/selftests/kvm/include/test_util.h193
-rw-r--r--tools/testing/selftests/kvm/include/ucall_common.h104
-rw-r--r--tools/testing/selftests/kvm/include/userfaultfd_util.h45
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/apic.h93
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/evmcs.h1279
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/hyperv.h346
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/mce.h25
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h1259
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm.h326
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm_util.h65
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/ucall.h13
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h577
31 files changed, 6306 insertions, 0 deletions
diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
new file mode 100644
index 0000000000..b3e97525cb
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Timer specific interface
+ */
+
+#ifndef SELFTEST_KVM_ARCH_TIMER_H
+#define SELFTEST_KVM_ARCH_TIMER_H
+
+#include "processor.h"
+
+enum arch_timer {
+ VIRTUAL,
+ PHYSICAL,
+};
+
+#define CTL_ENABLE (1 << 0)
+#define CTL_IMASK (1 << 1)
+#define CTL_ISTATUS (1 << 2)
+
+#define msec_to_cycles(msec) \
+ (timer_get_cntfrq() * (uint64_t)(msec) / 1000)
+
+#define usec_to_cycles(usec) \
+ (timer_get_cntfrq() * (uint64_t)(usec) / 1000000)
+
+#define cycles_to_usec(cycles) \
+ ((uint64_t)(cycles) * 1000000 / timer_get_cntfrq())
+
+static inline uint32_t timer_get_cntfrq(void)
+{
+ return read_sysreg(cntfrq_el0);
+}
+
+static inline uint64_t timer_get_cntct(enum arch_timer timer)
+{
+ isb();
+
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntvct_el0);
+ case PHYSICAL:
+ return read_sysreg(cntpct_el0);
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_cval(enum arch_timer timer, uint64_t cval)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(cval, cntv_cval_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(cval, cntp_cval_el0);
+ break;
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ isb();
+}
+
+static inline uint64_t timer_get_cval(enum arch_timer timer)
+{
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntv_cval_el0);
+ case PHYSICAL:
+ return read_sysreg(cntp_cval_el0);
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_tval(enum arch_timer timer, uint32_t tval)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(tval, cntv_tval_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(tval, cntp_tval_el0);
+ break;
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ isb();
+}
+
+static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(ctl, cntv_ctl_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(ctl, cntp_ctl_el0);
+ break;
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ isb();
+}
+
+static inline uint32_t timer_get_ctl(enum arch_timer timer)
+{
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntv_ctl_el0);
+ case PHYSICAL:
+ return read_sysreg(cntp_ctl_el0);
+ default:
+ GUEST_FAIL("Unexpected timer type = %u", timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_next_cval_ms(enum arch_timer timer, uint32_t msec)
+{
+ uint64_t now_ct = timer_get_cntct(timer);
+ uint64_t next_ct = now_ct + msec_to_cycles(msec);
+
+ timer_set_cval(timer, next_ct);
+}
+
+static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec)
+{
+ timer_set_tval(timer, msec_to_cycles(msec));
+}
+
+#endif /* SELFTEST_KVM_ARCH_TIMER_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/delay.h b/tools/testing/selftests/kvm/include/aarch64/delay.h
new file mode 100644
index 0000000000..329e4f5079
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/delay.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM simple delay routines
+ */
+
+#ifndef SELFTEST_KVM_ARM_DELAY_H
+#define SELFTEST_KVM_ARM_DELAY_H
+
+#include "arch_timer.h"
+
+static inline void __delay(uint64_t cycles)
+{
+ enum arch_timer timer = VIRTUAL;
+ uint64_t start = timer_get_cntct(timer);
+
+ while ((timer_get_cntct(timer) - start) < cycles)
+ cpu_relax();
+}
+
+static inline void udelay(unsigned long usec)
+{
+ __delay(usec_to_cycles(usec));
+}
+
+#endif /* SELFTEST_KVM_ARM_DELAY_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h
new file mode 100644
index 0000000000..b217ea17ca
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/gic.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) specific defines
+ */
+
+#ifndef SELFTEST_KVM_GIC_H
+#define SELFTEST_KVM_GIC_H
+
+enum gic_type {
+ GIC_V3,
+ GIC_TYPE_MAX,
+};
+
+#define MIN_SGI 0
+#define MIN_PPI 16
+#define MIN_SPI 32
+#define MAX_SPI 1019
+#define IAR_SPURIOUS 1023
+
+#define INTID_IS_SGI(intid) (0 <= (intid) && (intid) < MIN_PPI)
+#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI)
+#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI)
+
+void gic_init(enum gic_type type, unsigned int nr_cpus,
+ void *dist_base, void *redist_base);
+void gic_irq_enable(unsigned int intid);
+void gic_irq_disable(unsigned int intid);
+unsigned int gic_get_and_ack_irq(void);
+void gic_set_eoi(unsigned int intid);
+void gic_set_dir(unsigned int intid);
+
+/*
+ * Sets the EOI mode. When split is false, EOI just drops the priority. When
+ * split is true, EOI drops the priority and deactivates the interrupt.
+ */
+void gic_set_eoi_split(bool split);
+void gic_set_priority_mask(uint64_t mask);
+void gic_set_priority(uint32_t intid, uint32_t prio);
+void gic_irq_set_active(unsigned int intid);
+void gic_irq_clear_active(unsigned int intid);
+bool gic_irq_get_active(unsigned int intid);
+void gic_irq_set_pending(unsigned int intid);
+void gic_irq_clear_pending(unsigned int intid);
+bool gic_irq_get_pending(unsigned int intid);
+void gic_irq_set_config(unsigned int intid, bool is_edge);
+
+#endif /* SELFTEST_KVM_GIC_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
new file mode 100644
index 0000000000..ba0886e8a2
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 specific defines
+ */
+
+#ifndef SELFTEST_KVM_GICV3_H
+#define SELFTEST_KVM_GICV3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers
+ */
+#define GICD_CTLR 0x0000
+#define GICD_TYPER 0x0004
+#define GICD_IGROUPR 0x0080
+#define GICD_ISENABLER 0x0100
+#define GICD_ICENABLER 0x0180
+#define GICD_ISPENDR 0x0200
+#define GICD_ICPENDR 0x0280
+#define GICD_ICACTIVER 0x0380
+#define GICD_ISACTIVER 0x0300
+#define GICD_IPRIORITYR 0x0400
+#define GICD_ICFGR 0x0C00
+
+/*
+ * The assumption is that the guest runs in a non-secure mode.
+ * The following bits of GICD_CTLR are defined accordingly.
+ */
+#define GICD_CTLR_RWP (1U << 31)
+#define GICD_CTLR_nASSGIreq (1U << 8)
+#define GICD_CTLR_ARE_NS (1U << 4)
+#define GICD_CTLR_ENABLE_G1A (1U << 1)
+#define GICD_CTLR_ENABLE_G1 (1U << 0)
+
+#define GICD_TYPER_SPIS(typer) ((((typer) & 0x1f) + 1) * 32)
+#define GICD_INT_DEF_PRI_X4 0xa0a0a0a0
+
+/*
+ * Redistributor registers
+ */
+#define GICR_CTLR 0x000
+#define GICR_WAKER 0x014
+
+#define GICR_CTLR_RWP (1U << 3)
+
+#define GICR_WAKER_ProcessorSleep (1U << 1)
+#define GICR_WAKER_ChildrenAsleep (1U << 2)
+
+/*
+ * Redistributor registers, offsets from SGI base
+ */
+#define GICR_IGROUPR0 GICD_IGROUPR
+#define GICR_ISENABLER0 GICD_ISENABLER
+#define GICR_ICENABLER0 GICD_ICENABLER
+#define GICR_ISPENDR0 GICD_ISPENDR
+#define GICR_ISACTIVER0 GICD_ISACTIVER
+#define GICR_ICACTIVER0 GICD_ICACTIVER
+#define GICR_ICENABLER GICD_ICENABLER
+#define GICR_ICACTIVER GICD_ICACTIVER
+#define GICR_IPRIORITYR0 GICD_IPRIORITYR
+
+/* CPU interface registers */
+#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
+#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
+#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+
+#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0)
+
+#define ICC_PMR_DEF_PRIO 0xf0
+
+#define ICC_SRE_EL1_SRE (1U << 0)
+
+#define ICC_IGRPEN1_EL1_ENABLE (1U << 0)
+
+#define GICV3_MAX_CPUS 512
+
+#endif /* SELFTEST_KVM_GICV3_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
new file mode 100644
index 0000000000..cb537253a6
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch64 processor specific defines
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <asm/sysreg.h>
+
+
+#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
+
+/*
+ * KVM_ARM64_SYS_REG(sys_reg_id): Helper macro to convert
+ * SYS_* register definitions in asm/sysreg.h to use in KVM
+ * calls such as vcpu_get_reg() and vcpu_set_reg().
+ */
+#define KVM_ARM64_SYS_REG(sys_reg_id) \
+ ARM64_SYS_REG(sys_reg_Op0(sys_reg_id), \
+ sys_reg_Op1(sys_reg_id), \
+ sys_reg_CRn(sys_reg_id), \
+ sys_reg_CRm(sys_reg_id), \
+ sys_reg_Op2(sys_reg_id))
+
+/*
+ * Default MAIR
+ * index attribute
+ * DEVICE_nGnRnE 0 0000:0000
+ * DEVICE_nGnRE 1 0000:0100
+ * DEVICE_GRE 2 0000:1100
+ * NORMAL_NC 3 0100:0100
+ * NORMAL 4 1111:1111
+ * NORMAL_WT 5 1011:1011
+ */
+
+/* Linux doesn't use these memory types, so let's define them. */
+#define MAIR_ATTR_DEVICE_GRE UL(0x0c)
+#define MAIR_ATTR_NORMAL_WT UL(0xbb)
+
+#define MT_DEVICE_nGnRnE 0
+#define MT_DEVICE_nGnRE 1
+#define MT_DEVICE_GRE 2
+#define MT_NORMAL_NC 3
+#define MT_NORMAL 4
+#define MT_NORMAL_WT 5
+
+#define DEFAULT_MAIR_EL1 \
+ (MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) | \
+ MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) | \
+ MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) | \
+ MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) | \
+ MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \
+ MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
+
+#define MPIDR_HWID_BITMASK (0xff00fffffful)
+
+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);
+
+struct ex_regs {
+ u64 regs[31];
+ u64 sp;
+ u64 pc;
+ u64 pstate;
+};
+
+#define VECTOR_NUM 16
+
+enum {
+ VECTOR_SYNC_CURRENT_SP0,
+ VECTOR_IRQ_CURRENT_SP0,
+ VECTOR_FIQ_CURRENT_SP0,
+ VECTOR_ERROR_CURRENT_SP0,
+
+ VECTOR_SYNC_CURRENT,
+ VECTOR_IRQ_CURRENT,
+ VECTOR_FIQ_CURRENT,
+ VECTOR_ERROR_CURRENT,
+
+ VECTOR_SYNC_LOWER_64,
+ VECTOR_IRQ_LOWER_64,
+ VECTOR_FIQ_LOWER_64,
+ VECTOR_ERROR_LOWER_64,
+
+ VECTOR_SYNC_LOWER_32,
+ VECTOR_IRQ_LOWER_32,
+ VECTOR_FIQ_LOWER_32,
+ VECTOR_ERROR_LOWER_32,
+};
+
+#define VECTOR_IS_SYNC(v) ((v) == VECTOR_SYNC_CURRENT_SP0 || \
+ (v) == VECTOR_SYNC_CURRENT || \
+ (v) == VECTOR_SYNC_LOWER_64 || \
+ (v) == VECTOR_SYNC_LOWER_32)
+
+#define ESR_EC_NUM 64
+#define ESR_EC_SHIFT 26
+#define ESR_EC_MASK (ESR_EC_NUM - 1)
+
+#define ESR_EC_SVC64 0x15
+#define ESR_EC_IABT 0x21
+#define ESR_EC_DABT 0x25
+#define ESR_EC_HW_BP_CURRENT 0x31
+#define ESR_EC_SSTEP_CURRENT 0x33
+#define ESR_EC_WP_CURRENT 0x35
+#define ESR_EC_BRK_INS 0x3c
+
+/* 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,
+ bool *ps4k, bool *ps16k, bool *ps64k);
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
+
+typedef void(*handler_fn)(struct ex_regs *);
+void vm_install_exception_handler(struct kvm_vm *vm,
+ int vector, handler_fn handler);
+void vm_install_sync_handler(struct kvm_vm *vm,
+ int vector, int ec, handler_fn handler);
+
+uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva);
+
+static inline void cpu_relax(void)
+{
+ asm volatile("yield" ::: "memory");
+}
+
+#define isb() asm volatile("isb" : : : "memory")
+#define dsb(opt) asm volatile("dsb " #opt : : : "memory")
+#define dmb(opt) asm volatile("dmb " #opt : : : "memory")
+
+#define dma_wmb() dmb(oshst)
+#define __iowmb() dma_wmb()
+
+#define dma_rmb() dmb(oshld)
+
+#define __iormb(v) \
+({ \
+ unsigned long tmp; \
+ \
+ dma_rmb(); \
+ \
+ /* \
+ * Courtesy of arch/arm64/include/asm/io.h: \
+ * Create a dummy control dependency from the IO read to any \
+ * later instructions. This ensures that a subsequent call \
+ * to udelay() will be ordered due to the ISB in __delay(). \
+ */ \
+ asm volatile("eor %0, %1, %1\n" \
+ "cbnz %0, ." \
+ : "=r" (tmp) : "r" ((unsigned long)(v)) \
+ : "memory"); \
+})
+
+static __always_inline void __raw_writel(u32 val, volatile void *addr)
+{
+ asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+static __always_inline u32 __raw_readl(const volatile void *addr)
+{
+ u32 val;
+ asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+
+#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c));})
+#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; })
+
+static inline void local_irq_enable(void)
+{
+ asm volatile("msr daifclr, #3" : : : "memory");
+}
+
+static inline void local_irq_disable(void)
+{
+ asm volatile("msr daifset, #3" : : : "memory");
+}
+
+/**
+ * struct arm_smccc_res - Result from SMC/HVC call
+ * @a0-a3 result values from registers 0 to 3
+ */
+struct arm_smccc_res {
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+};
+
+/**
+ * smccc_hvc - Invoke a SMCCC function using the hvc conduit
+ * @function_id: the SMCCC function to be called
+ * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7
+ * @res: pointer to write the return values from registers x0-x3
+ *
+ */
+void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
+ uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
+ uint64_t arg6, struct arm_smccc_res *res);
+
+/**
+ * smccc_smc - Invoke a SMCCC function using the smc conduit
+ * @function_id: the SMCCC function to be called
+ * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7
+ * @res: pointer to write the return values from registers x0-x3
+ *
+ */
+void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
+ uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
+ uint64_t arg6, struct arm_smccc_res *res);
+
+
+
+uint32_t guest_get_vcpuid(void);
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/spinlock.h b/tools/testing/selftests/kvm/include/aarch64/spinlock.h
new file mode 100644
index 0000000000..cf0984106d
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/spinlock.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef SELFTEST_KVM_ARM64_SPINLOCK_H
+#define SELFTEST_KVM_ARM64_SPINLOCK_H
+
+struct spinlock {
+ int v;
+};
+
+extern void spin_lock(struct spinlock *lock);
+extern void spin_unlock(struct spinlock *lock);
+
+#endif /* SELFTEST_KVM_ARM64_SPINLOCK_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h
new file mode 100644
index 0000000000..4b68f37efd
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+#define UCALL_EXIT_REASON KVM_EXIT_MMIO
+
+/*
+ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each
+ * VM), it must not be accessed from host code.
+ */
+extern vm_vaddr_t *ucall_exit_mmio_addr;
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+ WRITE_ONCE(*ucall_exit_mmio_addr, uc);
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h
new file mode 100644
index 0000000000..0ac6f05c63
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) host specific defines
+ */
+
+#ifndef SELFTEST_KVM_VGIC_H
+#define SELFTEST_KVM_VGIC_H
+
+#include <linux/kvm.h>
+
+#include "kvm_util.h"
+
+#define REDIST_REGION_ATTR_ADDR(count, base, flags, index) \
+ (((uint64_t)(count) << 52) | \
+ ((uint64_t)((base) >> 16) << 16) | \
+ ((uint64_t)(flags) << 12) | \
+ index)
+
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
+ uint64_t gicd_base_gpa, uint64_t gicr_base_gpa);
+
+#define VGIC_MAX_RESERVED 1023
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+
+/* The vcpu arg only applies to private interrupts. */
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu);
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu);
+
+#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
+
+#endif // SELFTEST_KVM_VGIC_H
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
new file mode 100644
index 0000000000..b691df33e6
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+
+extern struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_append(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+void guest_modes_append_default(void);
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg);
+void guest_modes_help(void);
+void guest_modes_cmdline(const char *arg);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
new file mode 100644
index 0000000000..c9286811a4
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UTIL_H
+#define SELFTEST_KVM_UTIL_H
+
+#include "kvm_util_base.h"
+#include "ucall_common.h"
+
+#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
new file mode 100644
index 0000000000..a18db6a7b3
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -0,0 +1,935 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util_base.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UTIL_BASE_H
+#define SELFTEST_KVM_UTIL_BASE_H
+
+#include "test_util.h"
+
+#include <linux/compiler.h>
+#include "linux/hashtable.h"
+#include "linux/list.h"
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include "linux/rbtree.h"
+#include <linux/types.h>
+
+#include <asm/atomic.h>
+
+#include <sys/ioctl.h>
+
+#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
+
+#define NSEC_PER_SEC 1000000000L
+
+typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
+typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
+
+struct userspace_mem_region {
+ struct kvm_userspace_memory_region region;
+ struct sparsebit *unused_phy_pages;
+ int fd;
+ off_t offset;
+ enum vm_mem_backing_src_type backing_src_type;
+ void *host_mem;
+ void *host_alias;
+ void *mmap_start;
+ void *mmap_alias;
+ size_t mmap_size;
+ struct rb_node gpa_node;
+ struct rb_node hva_node;
+ struct hlist_node slot_node;
+};
+
+struct kvm_vcpu {
+ struct list_head list;
+ uint32_t id;
+ int fd;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+#ifdef __x86_64__
+ struct kvm_cpuid2 *cpuid;
+#endif
+ struct kvm_dirty_gfn *dirty_gfns;
+ uint32_t fetch_index;
+ uint32_t dirty_gfns_count;
+};
+
+struct userspace_mem_regions {
+ struct rb_root gpa_tree;
+ struct rb_root hva_tree;
+ DECLARE_HASHTABLE(slot_hash, 9);
+};
+
+enum kvm_mem_region_type {
+ MEM_REGION_CODE,
+ MEM_REGION_DATA,
+ MEM_REGION_PT,
+ MEM_REGION_TEST_DATA,
+ NR_MEM_REGIONS,
+};
+
+struct kvm_vm {
+ int mode;
+ unsigned long type;
+ int kvm_fd;
+ int fd;
+ unsigned int pgtable_levels;
+ unsigned int page_size;
+ unsigned int page_shift;
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ uint64_t max_gfn;
+ struct list_head vcpus;
+ struct userspace_mem_regions regions;
+ struct sparsebit *vpages_valid;
+ struct sparsebit *vpages_mapped;
+ bool has_irqchip;
+ bool pgd_created;
+ vm_paddr_t ucall_mmio_addr;
+ vm_paddr_t pgd;
+ vm_vaddr_t gdt;
+ vm_vaddr_t tss;
+ vm_vaddr_t idt;
+ vm_vaddr_t handlers;
+ uint32_t dirty_ring_size;
+
+ /* Cache of information for binary stats interface */
+ int stats_fd;
+ struct kvm_stats_header stats_header;
+ struct kvm_stats_desc *stats_desc;
+
+ /*
+ * KVM region slots. These are the default memslots used by page
+ * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE]
+ * memslot.
+ */
+ uint32_t memslots[NR_MEM_REGIONS];
+};
+
+struct vcpu_reg_sublist {
+ const char *name;
+ long capability;
+ int feature;
+ bool finalize;
+ __u64 *regs;
+ __u64 regs_n;
+ __u64 *rejects_set;
+ __u64 rejects_set_n;
+ __u64 *skips_set;
+ __u64 skips_set_n;
+};
+
+struct vcpu_reg_list {
+ char *name;
+ struct vcpu_reg_sublist sublists[];
+};
+
+#define for_each_sublist(c, s) \
+ for ((s) = &(c)->sublists[0]; (s)->regs; ++(s))
+
+#define kvm_for_each_vcpu(vm, i, vcpu) \
+ for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \
+ if (!((vcpu) = vm->vcpus[i])) \
+ continue; \
+ else
+
+struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot);
+
+static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm,
+ enum kvm_mem_region_type type)
+{
+ assert(type < NR_MEM_REGIONS);
+ return memslot2region(vm, vm->memslots[type]);
+}
+
+/* Minimum allocated guest virtual and physical addresses */
+#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
+#define DEFAULT_STACK_PGS 5
+
+enum vm_guest_mode {
+ VM_MODE_P52V48_4K,
+ VM_MODE_P52V48_64K,
+ VM_MODE_P48V48_4K,
+ VM_MODE_P48V48_16K,
+ VM_MODE_P48V48_64K,
+ VM_MODE_P40V48_4K,
+ VM_MODE_P40V48_16K,
+ VM_MODE_P40V48_64K,
+ VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
+ VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
+ VM_MODE_P36V48_4K,
+ VM_MODE_P36V48_16K,
+ VM_MODE_P36V48_64K,
+ VM_MODE_P36V47_16K,
+ NUM_VM_MODES,
+};
+
+#if defined(__aarch64__)
+
+extern enum vm_guest_mode vm_mode_default;
+
+#define VM_MODE_DEFAULT vm_mode_default
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__x86_64__)
+
+#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__s390x__)
+
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 16)
+
+#elif defined(__riscv)
+
+#if __riscv_xlen == 32
+#error "RISC-V 32-bit kvm selftests not supported"
+#endif
+
+#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#endif
+
+#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
+#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
+
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+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);
+
+unsigned int kvm_check_cap(long cap);
+
+static inline bool kvm_has_cap(long cap)
+{
+ return kvm_check_cap(cap);
+}
+
+#define __KVM_SYSCALL_ERROR(_name, _ret) \
+ "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
+
+#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret)
+#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret)
+
+#define kvm_do_ioctl(fd, cmd, arg) \
+({ \
+ kvm_static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd)); \
+ ioctl(fd, cmd, arg); \
+})
+
+#define __kvm_ioctl(kvm_fd, cmd, arg) \
+ kvm_do_ioctl(kvm_fd, cmd, arg)
+
+
+#define _kvm_ioctl(kvm_fd, cmd, name, arg) \
+({ \
+ int ret = __kvm_ioctl(kvm_fd, cmd, arg); \
+ \
+ TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+})
+
+#define kvm_ioctl(kvm_fd, cmd, arg) \
+ _kvm_ioctl(kvm_fd, cmd, #cmd, arg)
+
+static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
+
+#define __vm_ioctl(vm, cmd, arg) \
+({ \
+ static_assert_is_vm(vm); \
+ kvm_do_ioctl((vm)->fd, cmd, arg); \
+})
+
+#define _vm_ioctl(vm, cmd, name, arg) \
+({ \
+ int ret = __vm_ioctl(vm, cmd, arg); \
+ \
+ TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+})
+
+#define vm_ioctl(vm, cmd, arg) \
+ _vm_ioctl(vm, cmd, #cmd, arg)
+
+
+static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
+
+#define __vcpu_ioctl(vcpu, cmd, arg) \
+({ \
+ static_assert_is_vcpu(vcpu); \
+ kvm_do_ioctl((vcpu)->fd, cmd, arg); \
+})
+
+#define _vcpu_ioctl(vcpu, cmd, name, arg) \
+({ \
+ int ret = __vcpu_ioctl(vcpu, cmd, arg); \
+ \
+ TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+})
+
+#define vcpu_ioctl(vcpu, cmd, arg) \
+ _vcpu_ioctl(vcpu, cmd, #cmd, arg)
+
+/*
+ * Looks up and returns the value corresponding to the capability
+ * (KVM_CAP_*) given by cap.
+ */
+static inline int vm_check_cap(struct kvm_vm *vm, long cap)
+{
+ int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap);
+
+ TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret));
+ return ret;
+}
+
+static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
+{
+ struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } };
+
+ return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
+}
+static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0)
+{
+ struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } };
+
+ vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
+}
+
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
+const char *vm_guest_mode_string(uint32_t i);
+
+void kvm_vm_free(struct kvm_vm *vmp);
+void kvm_vm_restart(struct kvm_vm *vmp);
+void kvm_vm_release(struct kvm_vm *vmp);
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+ size_t len);
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
+int kvm_memfd_alloc(size_t size, bool hugepages);
+
+void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
+{
+ struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot };
+
+ vm_ioctl(vm, KVM_GET_DIRTY_LOG, &args);
+}
+
+static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+ uint64_t first_page, uint32_t num_pages)
+{
+ struct kvm_clear_dirty_log args = {
+ .dirty_bitmap = log,
+ .slot = slot,
+ .first_page = first_page,
+ .num_pages = num_pages
+ };
+
+ vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args);
+}
+
+static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
+{
+ return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL);
+}
+
+static inline int vm_get_stats_fd(struct kvm_vm *vm)
+{
+ int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL);
+
+ TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+ return fd;
+}
+
+static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header)
+{
+ ssize_t ret;
+
+ ret = pread(stats_fd, header, sizeof(*header), 0);
+ TEST_ASSERT(ret == sizeof(*header),
+ "Failed to read '%lu' header bytes, ret = '%ld'",
+ sizeof(*header), ret);
+}
+
+struct kvm_stats_desc *read_stats_descriptors(int stats_fd,
+ struct kvm_stats_header *header);
+
+static inline ssize_t get_stats_descriptor_size(struct kvm_stats_header *header)
+{
+ /*
+ * The base size of the descriptor is defined by KVM's ABI, but the
+ * size of the name field is variable, as far as KVM's ABI is
+ * concerned. For a given instance of KVM, the name field is the same
+ * size for all stats and is provided in the overall stats header.
+ */
+ return sizeof(struct kvm_stats_desc) + header->name_size;
+}
+
+static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc *stats,
+ int index,
+ struct kvm_stats_header *header)
+{
+ /*
+ * Note, size_desc includes the size of the name field, which is
+ * variable. i.e. this is NOT equivalent to &stats_desc[i].
+ */
+ return (void *)stats + index * get_stats_descriptor_size(header);
+}
+
+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);
+
+static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name)
+{
+ uint64_t data;
+
+ __vm_get_stat(vm, stat_name, &data, 1);
+ return data;
+}
+
+void vm_create_irqchip(struct kvm_vm *vm);
+
+void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+ uint64_t gpa, uint64_t size, void *hva);
+int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+ uint64_t gpa, uint64_t size, void *hva);
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+ enum vm_mem_backing_src_type src_type,
+ uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+ uint32_t flags);
+
+void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
+void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
+struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
+void vm_populate_vaddr_bitmap(struct kvm_vm *vm);
+vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+ enum kvm_mem_region_type type);
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
+vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm,
+ enum kvm_mem_region_type type);
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
+
+void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ unsigned int npages);
+void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
+void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
+vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
+
+void vcpu_run(struct kvm_vcpu *vcpu);
+int _vcpu_run(struct kvm_vcpu *vcpu);
+
+static inline int __vcpu_run(struct kvm_vcpu *vcpu)
+{
+ return __vcpu_ioctl(vcpu, KVM_RUN, NULL);
+}
+
+void vcpu_run_complete_io(struct kvm_vcpu *vcpu);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu);
+
+static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap,
+ uint64_t arg0)
+{
+ struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } };
+
+ vcpu_ioctl(vcpu, KVM_ENABLE_CAP, &enable_cap);
+}
+
+static inline void vcpu_guest_debug_set(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *debug)
+{
+ vcpu_ioctl(vcpu, KVM_SET_GUEST_DEBUG, debug);
+}
+
+static inline void vcpu_mp_state_get(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_ioctl(vcpu, KVM_GET_MP_STATE, mp_state);
+}
+static inline void vcpu_mp_state_set(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_ioctl(vcpu, KVM_SET_MP_STATE, mp_state);
+}
+
+static inline void vcpu_regs_get(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_ioctl(vcpu, KVM_GET_REGS, regs);
+}
+
+static inline void vcpu_regs_set(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_ioctl(vcpu, KVM_SET_REGS, regs);
+}
+static inline void vcpu_sregs_get(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ vcpu_ioctl(vcpu, KVM_GET_SREGS, sregs);
+
+}
+static inline void vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs);
+}
+static inline int _vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ return __vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs);
+}
+static inline void vcpu_fpu_get(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ vcpu_ioctl(vcpu, KVM_GET_FPU, fpu);
+}
+static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ vcpu_ioctl(vcpu, KVM_SET_FPU, fpu);
+}
+
+static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr)
+{
+ struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr };
+
+ return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, &reg);
+}
+static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val)
+{
+ struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val };
+
+ return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
+}
+static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr)
+{
+ struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr };
+
+ vcpu_ioctl(vcpu, KVM_GET_ONE_REG, &reg);
+}
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val)
+{
+ struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val };
+
+ vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
+}
+
+#ifdef __KVM_HAVE_VCPU_EVENTS
+static inline void vcpu_events_get(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu_events *events)
+{
+ vcpu_ioctl(vcpu, KVM_GET_VCPU_EVENTS, events);
+}
+static inline void vcpu_events_set(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu_events *events)
+{
+ vcpu_ioctl(vcpu, KVM_SET_VCPU_EVENTS, events);
+}
+#endif
+#ifdef __x86_64__
+static inline void vcpu_nested_state_get(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state *state)
+{
+ vcpu_ioctl(vcpu, KVM_GET_NESTED_STATE, state);
+}
+static inline int __vcpu_nested_state_set(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state *state)
+{
+ return __vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state);
+}
+
+static inline void vcpu_nested_state_set(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state *state)
+{
+ vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state);
+}
+#endif
+static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu)
+{
+ int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL);
+
+ TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+ return fd;
+}
+
+int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr);
+
+static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr)
+{
+ int ret = __kvm_has_device_attr(dev_fd, group, attr);
+
+ TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno);
+}
+
+int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val);
+
+static inline void kvm_device_attr_get(int dev_fd, uint32_t group,
+ uint64_t attr, void *val)
+{
+ int ret = __kvm_device_attr_get(dev_fd, group, attr, val);
+
+ TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret));
+}
+
+int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val);
+
+static inline void kvm_device_attr_set(int dev_fd, uint32_t group,
+ uint64_t attr, void *val)
+{
+ int ret = __kvm_device_attr_set(dev_fd, group, attr, val);
+
+ TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret));
+}
+
+static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr)
+{
+ return __kvm_has_device_attr(vcpu->fd, group, attr);
+}
+
+static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr)
+{
+ kvm_has_device_attr(vcpu->fd, group, attr);
+}
+
+static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr, void *val)
+{
+ return __kvm_device_attr_get(vcpu->fd, group, attr, val);
+}
+
+static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr, void *val)
+{
+ kvm_device_attr_get(vcpu->fd, group, attr, val);
+}
+
+static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr, void *val)
+{
+ return __kvm_device_attr_set(vcpu->fd, group, attr, val);
+}
+
+static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group,
+ uint64_t attr, void *val)
+{
+ kvm_device_attr_set(vcpu->fd, group, attr, val);
+}
+
+int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type);
+int __kvm_create_device(struct kvm_vm *vm, uint64_t type);
+
+static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type)
+{
+ int fd = __kvm_create_device(vm, type);
+
+ TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_DEVICE, fd));
+ return fd;
+}
+
+void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu);
+
+/*
+ * VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first @num input parameters for the function at @vcpu's entry point,
+ * per the C calling convention of the architecture, to the values given as
+ * variable args. Each of the variable args is expected to be of type uint64_t.
+ * The maximum @num can be is specific to the architecture.
+ */
+void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...);
+
+void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+
+#define KVM_MAX_IRQ_ROUTES 4096
+
+struct kvm_irq_routing *kvm_gsi_routing_create(void);
+void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
+ uint32_t gsi, uint32_t pin);
+int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+
+const char *exit_reason_str(unsigned int exit_reason);
+
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+ uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+ vm_paddr_t paddr_min, uint32_t memslot);
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
+
+/*
+ * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also
+ * loads the test binary into guest memory and creates an IRQ chip (x86 only).
+ * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
+ * calculate the amount of memory needed for per-vCPU data, e.g. stacks.
+ */
+struct kvm_vm *____vm_create(enum vm_guest_mode mode);
+struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+ uint64_t nr_extra_pages);
+
+static inline struct kvm_vm *vm_create_barebones(void)
+{
+ return ____vm_create(VM_MODE_DEFAULT);
+}
+
+static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
+{
+ return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0);
+}
+
+struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+ uint64_t extra_mem_pages,
+ void *guest_code, struct kvm_vcpu *vcpus[]);
+
+static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus,
+ void *guest_code,
+ struct kvm_vcpu *vcpus[])
+{
+ return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0,
+ guest_code, vcpus);
+}
+
+/*
+ * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages
+ * additional pages of guest memory. Returns the VM and vCPU (via out param).
+ */
+struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+ uint64_t extra_mem_pages,
+ void *guest_code);
+
+static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+ void *guest_code)
+{
+ return __vm_create_with_one_vcpu(vcpu, 0, guest_code);
+}
+
+struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
+
+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[],
+ int nr_vcpus);
+
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
+unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
+unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
+static inline unsigned int
+vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+ unsigned int n;
+ n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
+#ifdef __s390x__
+ /* s390 requires 1M aligned guest sizes */
+ n = (n + 255) & ~255;
+#endif
+ return n;
+}
+
+struct kvm_userspace_memory_region *
+kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
+ uint64_t end);
+
+#define sync_global_to_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(_p, &(g), sizeof(g)); \
+})
+
+#define sync_global_from_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(&(g), _p, sizeof(g)); \
+})
+
+/*
+ * Write a global value, but only in the VM's (guest's) domain. Primarily used
+ * for "globals" that hold per-VM values (VMs always duplicate code and global
+ * data into their own region of physical memory), but can be used anytime it's
+ * undesirable to change the host's copy of the global.
+ */
+#define write_guest_global(vm, g, val) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ typeof(g) _val = val; \
+ \
+ memcpy(_p, &(_val), sizeof(g)); \
+})
+
+void assert_on_unhandled_exception(struct kvm_vcpu *vcpu);
+
+void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu,
+ uint8_t indent);
+
+static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu,
+ uint8_t indent)
+{
+ vcpu_arch_dump(stream, vcpu, indent);
+}
+
+/*
+ * Adds a vCPU with reasonable defaults (e.g. a stack)
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpu_id - The id of the VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ */
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+ void *guest_code);
+
+static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+ void *guest_code)
+{
+ return vm_arch_vcpu_add(vm, vcpu_id, guest_code);
+}
+
+/* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */
+struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id);
+
+static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm,
+ uint32_t vcpu_id)
+{
+ return vm_arch_vcpu_recreate(vm, vcpu_id);
+}
+
+void vcpu_arch_free(struct kvm_vcpu *vcpu);
+
+void virt_arch_pgd_alloc(struct kvm_vm *vm);
+
+static inline void virt_pgd_alloc(struct kvm_vm *vm)
+{
+ virt_arch_pgd_alloc(vm);
+}
+
+/*
+ * VM Virtual Page Map
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vaddr - VM Virtual Address
+ * paddr - VM Physical Address
+ * memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within @vm, creates a virtual translation for the page starting
+ * at @vaddr to the page starting at @paddr.
+ */
+void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
+
+static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
+{
+ virt_arch_pg_map(vm, vaddr, paddr);
+}
+
+
+/*
+ * Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Returns the VM physical address of the translated VM virtual
+ * address given by @gva.
+ */
+vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
+
+static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ return addr_arch_gva2gpa(vm, gva);
+}
+
+/*
+ * Virtual Translation Tables Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * vm - Virtual Machine
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by @stream, the contents of all the
+ * virtual translation tables for the VM given by @vm.
+ */
+void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ virt_arch_dump(stream, vm, indent);
+}
+
+
+static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm)
+{
+ return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0);
+}
+
+/*
+ * Arch hook that is invoked via a constructor, i.e. before exeucting main(),
+ * to allow for arch-specific setup that is common to all tests, e.g. computing
+ * the default guest "mode".
+ */
+void kvm_selftest_arch_init(void);
+
+void kvm_arch_vm_post_create(struct kvm_vm *vm);
+
+#endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h
new file mode 100644
index 0000000000..ce4e603050
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/memstress.h
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/memstress.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_MEMSTRESS_H
+#define SELFTEST_KVM_MEMSTRESS_H
+
+#include <pthread.h>
+
+#include "kvm_util.h"
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM 0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
+
+#define MEMSTRESS_MEM_SLOT_INDEX 1
+
+struct memstress_vcpu_args {
+ uint64_t gpa;
+ uint64_t gva;
+ uint64_t pages;
+
+ /* Only used by the host userspace part of the vCPU thread */
+ struct kvm_vcpu *vcpu;
+ int vcpu_idx;
+};
+
+struct memstress_args {
+ struct kvm_vm *vm;
+ /* The starting address and size of the guest test region. */
+ uint64_t gpa;
+ uint64_t size;
+ uint64_t guest_page_size;
+ uint32_t random_seed;
+ uint32_t write_percent;
+
+ /* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+ bool nested;
+ /* Randomize which pages are accessed by the guest. */
+ bool random_access;
+ /* True if all vCPUs are pinned to pCPUs */
+ bool pin_vcpus;
+ /* The vCPU=>pCPU pinning map. Only valid if pin_vcpus is true. */
+ uint32_t vcpu_to_pcpu[KVM_MAX_VCPUS];
+
+ /* Test is done, stop running vCPUs. */
+ bool stop_vcpus;
+
+ struct memstress_vcpu_args vcpu_args[KVM_MAX_VCPUS];
+};
+
+extern struct memstress_args memstress_args;
+
+struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
+ uint64_t vcpu_memory_bytes, int slots,
+ enum vm_mem_backing_src_type backing_src,
+ bool partition_vcpu_memory_access);
+void memstress_destroy_vm(struct kvm_vm *vm);
+
+void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent);
+void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed);
+void memstress_set_random_access(struct kvm_vm *vm, bool random_access);
+
+void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *));
+void memstress_join_vcpu_threads(int vcpus);
+void memstress_guest_code(uint32_t vcpu_id);
+
+uint64_t memstress_nested_pages(int nr_vcpus);
+void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]);
+
+void memstress_enable_dirty_logging(struct kvm_vm *vm, int slots);
+void memstress_disable_dirty_logging(struct kvm_vm *vm, int slots);
+void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots);
+void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
+ int slots, uint64_t pages_per_slot);
+unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot);
+void memstress_free_bitmaps(unsigned long *bitmaps[], int slots);
+
+#endif /* SELFTEST_KVM_MEMSTRESS_H */
diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
new file mode 100644
index 0000000000..b020547403
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/numaif.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Header file that provides access to NUMA API functions not explicitly
+ * exported to user space.
+ */
+
+#ifndef SELFTEST_KVM_NUMAIF_H
+#define SELFTEST_KVM_NUMAIF_H
+
+#define __NR_get_mempolicy 239
+#define __NR_migrate_pages 256
+
+/* System calls */
+long get_mempolicy(int *policy, const unsigned long *nmask,
+ unsigned long maxnode, void *addr, int flags)
+{
+ return syscall(__NR_get_mempolicy, policy, nmask,
+ maxnode, addr, flags);
+}
+
+long migrate_pages(int pid, unsigned long maxnode,
+ const unsigned long *frommask,
+ const unsigned long *tomask)
+{
+ return syscall(__NR_migrate_pages, pid, maxnode, frommask, tomask);
+}
+
+/* Policies */
+#define MPOL_DEFAULT 0
+#define MPOL_PREFERRED 1
+#define MPOL_BIND 2
+#define MPOL_INTERLEAVE 3
+
+#define MPOL_MAX MPOL_INTERLEAVE
+
+/* Flags for get_mem_policy */
+#define MPOL_F_NODE (1<<0) /* return next il node or node of address */
+ /* Warning: MPOL_F_NODE is unsupported and
+ * subject to change. Don't use.
+ */
+#define MPOL_F_ADDR (1<<1) /* look up vma using address */
+#define MPOL_F_MEMS_ALLOWED (1<<2) /* query nodes allowed in cpuset */
+
+/* Flags for mbind */
+#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */
+#define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to mapping */
+#define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to mapping */
+
+#endif /* SELFTEST_KVM_NUMAIF_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
new file mode 100644
index 0000000000..5b62a3d2aa
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V processor specific defines
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+#include <linux/stringify.h>
+
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
+ uint64_t size)
+{
+ return KVM_REG_RISCV | type | idx | size;
+}
+
+#if __riscv_xlen == 64
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64
+#else
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32
+#endif
+
+#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \
+ KVM_REG_RISCV_CONFIG_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \
+ KVM_REG_RISCV_CORE_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \
+ KVM_REG_RISCV_CSR_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \
+ KVM_REG_RISCV_TIMER_REG(name), \
+ KVM_REG_SIZE_U64)
+
+#define RISCV_ISA_EXT_REG(idx) __kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \
+ idx, KVM_REG_SIZE_ULONG)
+
+/* L3 index Bit[47:39] */
+#define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL
+#define PGTBL_L3_INDEX_SHIFT 39
+#define PGTBL_L3_BLOCK_SHIFT 39
+#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL
+#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1))
+/* L2 index Bit[38:30] */
+#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL
+#define PGTBL_L2_INDEX_SHIFT 30
+#define PGTBL_L2_BLOCK_SHIFT 30
+#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL
+#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1))
+/* L1 index Bit[29:21] */
+#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL
+#define PGTBL_L1_INDEX_SHIFT 21
+#define PGTBL_L1_BLOCK_SHIFT 21
+#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL
+#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1))
+/* L0 index Bit[20:12] */
+#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL
+#define PGTBL_L0_INDEX_SHIFT 12
+#define PGTBL_L0_BLOCK_SHIFT 12
+#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL
+#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1))
+
+#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL
+#define PGTBL_PTE_ADDR_SHIFT 10
+#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL
+#define PGTBL_PTE_RSW_SHIFT 8
+#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL
+#define PGTBL_PTE_DIRTY_SHIFT 7
+#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL
+#define PGTBL_PTE_ACCESSED_SHIFT 6
+#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL
+#define PGTBL_PTE_GLOBAL_SHIFT 5
+#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL
+#define PGTBL_PTE_USER_SHIFT 4
+#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL
+#define PGTBL_PTE_EXECUTE_SHIFT 3
+#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL
+#define PGTBL_PTE_WRITE_SHIFT 2
+#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL
+#define PGTBL_PTE_READ_SHIFT 1
+#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_ACCESSED_MASK | \
+ PGTBL_PTE_DIRTY_MASK | \
+ PGTBL_PTE_EXECUTE_MASK | \
+ PGTBL_PTE_WRITE_MASK | \
+ PGTBL_PTE_READ_MASK)
+#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL
+#define PGTBL_PTE_VALID_SHIFT 0
+
+#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE
+#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT
+
+#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39 _AC(0x8000000000000000, UL)
+#define SATP_MODE_48 _AC(0x9000000000000000, UL)
+#define SATP_ASID_BITS 16
+#define SATP_ASID_SHIFT 44
+#define SATP_ASID_MASK _AC(0xFFFF, UL)
+
+#define SBI_EXT_EXPERIMENTAL_START 0x08000000
+#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF
+
+#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END
+#define KVM_RISCV_SELFTESTS_SBI_UCALL 0
+#define KVM_RISCV_SELFTESTS_SBI_UNEXP 1
+
+struct sbiret {
+ long error;
+ long value;
+};
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5);
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h
new file mode 100644
index 0000000000..be46eb32ec
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/ucall.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "processor.h"
+
+#define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+ sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT,
+ KVM_RISCV_SELFTESTS_SBI_UCALL,
+ uc, 0, 0, 0, 0, 0);
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h
new file mode 100644
index 0000000000..b0ed713027
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Test handler for the s390x DIAGNOSE 0x0318 instruction.
+ *
+ * Copyright (C) 2020, IBM
+ */
+
+#ifndef SELFTEST_KVM_DIAG318_TEST_HANDLER
+#define SELFTEST_KVM_DIAG318_TEST_HANDLER
+
+uint64_t get_diag318_info(void);
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h
new file mode 100644
index 0000000000..255c9b990f
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/processor.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * s390x processor specific defines
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include <linux/compiler.h>
+
+/* Bits in the region/segment table entry */
+#define REGION_ENTRY_ORIGIN ~0xfffUL /* region/segment table origin */
+#define REGION_ENTRY_PROTECT 0x200 /* region protection bit */
+#define REGION_ENTRY_NOEXEC 0x100 /* region no-execute bit */
+#define REGION_ENTRY_OFFSET 0xc0 /* region table offset */
+#define REGION_ENTRY_INVALID 0x20 /* invalid region table entry */
+#define REGION_ENTRY_TYPE 0x0c /* region/segment table type mask */
+#define REGION_ENTRY_LENGTH 0x03 /* region third length */
+
+/* Bits in the page table entry */
+#define PAGE_INVALID 0x400 /* HW invalid bit */
+#define PAGE_PROTECT 0x200 /* HW read-only bit */
+#define PAGE_NOEXEC 0x100 /* HW no-execute bit */
+
+/* Is there a portable way to do this? */
+static inline void cpu_relax(void)
+{
+ barrier();
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h
new file mode 100644
index 0000000000..b231bf2e49
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/ucall.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+#define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+static inline void ucall_arch_do_ucall(vm_vaddr_t uc)
+{
+ /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */
+ asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory");
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
new file mode 100644
index 0000000000..12a9a4b9ce
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/sparsebit.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * Header file that describes API to the sparsebit library.
+ * This library provides a memory efficient means of storing
+ * the settings of bits indexed via a uint64_t. Memory usage
+ * is reasonable, significantly less than (2^64 / 8) bytes, as
+ * long as bits that are mostly set or mostly cleared are close
+ * to each other. This library is efficient in memory usage
+ * even in the case where most bits are set.
+ */
+
+#ifndef SELFTEST_KVM_SPARSEBIT_H
+#define SELFTEST_KVM_SPARSEBIT_H
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct sparsebit;
+typedef uint64_t sparsebit_idx_t;
+typedef uint64_t sparsebit_num_t;
+
+struct sparsebit *sparsebit_alloc(void);
+void sparsebit_free(struct sparsebit **sbitp);
+void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src);
+
+bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_set_num(struct sparsebit *sbit,
+ sparsebit_idx_t idx, sparsebit_num_t num);
+bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_clear_num(struct sparsebit *sbit,
+ sparsebit_idx_t idx, sparsebit_num_t num);
+sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit);
+bool sparsebit_any_set(struct sparsebit *sbit);
+bool sparsebit_any_clear(struct sparsebit *sbit);
+bool sparsebit_all_set(struct sparsebit *sbit);
+bool sparsebit_all_clear(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit,
+ sparsebit_idx_t start, sparsebit_num_t num);
+sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit,
+ sparsebit_idx_t start, sparsebit_num_t num);
+
+void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx);
+void sparsebit_set_num(struct sparsebit *sbitp, sparsebit_idx_t start,
+ sparsebit_num_t num);
+void sparsebit_set_all(struct sparsebit *sbitp);
+
+void sparsebit_clear(struct sparsebit *sbitp, sparsebit_idx_t idx);
+void sparsebit_clear_num(struct sparsebit *sbitp,
+ sparsebit_idx_t start, sparsebit_num_t num);
+void sparsebit_clear_all(struct sparsebit *sbitp);
+
+void sparsebit_dump(FILE *stream, struct sparsebit *sbit,
+ unsigned int indent);
+void sparsebit_validate_internal(struct sparsebit *sbit);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* SELFTEST_KVM_SPARSEBIT_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
new file mode 100644
index 0000000000..7e614adc6c
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/test_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_TEST_UTIL_H
+#define SELFTEST_KVM_TEST_UTIL_H
+
+#include <stdlib.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <errno.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include "kselftest.h"
+
+static inline int _no_printf(const char *format, ...) { return 0; }
+
+#ifdef DEBUG
+#define pr_debug(...) printf(__VA_ARGS__)
+#else
+#define pr_debug(...) _no_printf(__VA_ARGS__)
+#endif
+#ifndef QUIET
+#define pr_info(...) printf(__VA_ARGS__)
+#else
+#define pr_info(...) _no_printf(__VA_ARGS__)
+#endif
+
+void print_skip(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
+#define __TEST_REQUIRE(f, fmt, ...) \
+do { \
+ if (!(f)) \
+ ksft_exit_skip("- " fmt "\n", ##__VA_ARGS__); \
+} while (0)
+
+#define TEST_REQUIRE(f) __TEST_REQUIRE(f, "Requirement not met: %s", #f)
+
+ssize_t test_write(int fd, const void *buf, size_t count);
+ssize_t test_read(int fd, void *buf, size_t count);
+int test_seq_read(const char *path, char **bufp, size_t *sizep);
+
+void test_assert(bool exp, const char *exp_str,
+ const char *file, unsigned int line, const char *fmt, ...)
+ __attribute__((format(printf, 5, 6)));
+
+#define TEST_ASSERT(e, fmt, ...) \
+ test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
+
+#define TEST_ASSERT_EQ(a, b) \
+do { \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ test_assert(__a == __b, #a " == " #b, __FILE__, __LINE__, \
+ "%#lx != %#lx (%s != %s)", \
+ (unsigned long)(__a), (unsigned long)(__b), #a, #b);\
+} while (0)
+
+#define TEST_ASSERT_KVM_EXIT_REASON(vcpu, expected) do { \
+ __u32 exit_reason = (vcpu)->run->exit_reason; \
+ \
+ TEST_ASSERT(exit_reason == (expected), \
+ "Wanted KVM exit reason: %u (%s), got: %u (%s)", \
+ (expected), exit_reason_str((expected)), \
+ exit_reason, exit_reason_str(exit_reason)); \
+} while (0)
+
+#define TEST_FAIL(fmt, ...) do { \
+ TEST_ASSERT(false, fmt, ##__VA_ARGS__); \
+ __builtin_unreachable(); \
+} while (0)
+
+size_t parse_size(const char *size);
+
+int64_t timespec_to_ns(struct timespec ts);
+struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
+struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_elapsed(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
+
+struct guest_random_state {
+ uint32_t seed;
+};
+
+struct guest_random_state new_guest_random_state(uint32_t seed);
+uint32_t guest_random_u32(struct guest_random_state *state);
+
+enum vm_mem_backing_src_type {
+ VM_MEM_SRC_ANONYMOUS,
+ VM_MEM_SRC_ANONYMOUS_THP,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB,
+ VM_MEM_SRC_SHMEM,
+ VM_MEM_SRC_SHARED_HUGETLB,
+ NUM_SRC_TYPES,
+};
+
+#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS
+
+struct vm_mem_backing_src_alias {
+ const char *name;
+ uint32_t flag;
+};
+
+#define MIN_RUN_DELAY_NS 200000UL
+
+bool thp_configured(void);
+size_t get_trans_hugepagesz(void);
+size_t get_def_hugetlb_pagesz(void);
+const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
+size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
+void backing_src_help(const char *flag);
+enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
+long get_run_delay(void);
+
+/*
+ * Whether or not the given source type is shared memory (as opposed to
+ * anonymous).
+ */
+static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
+{
+ return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
+}
+
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+ uint64_t mask = size - 1;
+
+ TEST_ASSERT(size != 0 && !(size & (size - 1)),
+ "size not a power of 2: %lu", size);
+ return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+ uint64_t x_aligned_up = align_up(x, size);
+
+ if (x == x_aligned_up)
+ return x;
+ else
+ return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+ return (void *)align_up((unsigned long)x, size);
+}
+
+int atoi_paranoid(const char *num_str);
+
+static inline uint32_t atoi_positive(const char *name, const char *num_str)
+{
+ int num = atoi_paranoid(num_str);
+
+ TEST_ASSERT(num > 0, "%s must be greater than 0, got '%s'", name, num_str);
+ return num;
+}
+
+static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
+{
+ int num = atoi_paranoid(num_str);
+
+ TEST_ASSERT(num >= 0, "%s must be non-negative, got '%s'", name, num_str);
+ return num;
+}
+
+int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args);
+int guest_snprintf(char *buf, int n, const char *fmt, ...);
+
+char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
+
+#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
new file mode 100644
index 0000000000..ce33d306c2
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UCALL_COMMON_H
+#define SELFTEST_KVM_UCALL_COMMON_H
+#include "test_util.h"
+#include "ucall.h"
+
+/* Common ucalls */
+enum {
+ UCALL_NONE,
+ UCALL_SYNC,
+ UCALL_ABORT,
+ UCALL_PRINTF,
+ UCALL_DONE,
+ UCALL_UNHANDLED,
+};
+
+#define UCALL_MAX_ARGS 7
+#define UCALL_BUFFER_LEN 1024
+
+struct ucall {
+ uint64_t cmd;
+ uint64_t args[UCALL_MAX_ARGS];
+ char buffer[UCALL_BUFFER_LEN];
+
+ /* Host virtual address of this struct. */
+ struct ucall *hva;
+};
+
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
+void ucall_arch_do_ucall(vm_vaddr_t uc);
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
+
+void ucall(uint64_t cmd, int nargs, ...);
+void ucall_fmt(uint64_t cmd, const char *fmt, ...);
+void ucall_assert(uint64_t cmd, const char *exp, const char *file,
+ unsigned int line, const char *fmt, ...);
+uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
+void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
+int ucall_nr_pages_required(uint64_t page_size);
+
+/*
+ * 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)
+#define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args)
+#define GUEST_DONE() ucall(UCALL_DONE, 0)
+
+#define REPORT_GUEST_PRINTF(ucall) pr_info("%s", (ucall).buffer)
+
+enum guest_assert_builtin_args {
+ GUEST_ERROR_STRING,
+ GUEST_FILE,
+ GUEST_LINE,
+ GUEST_ASSERT_BUILTIN_NARGS
+};
+
+#define ____GUEST_ASSERT(_condition, _exp, _fmt, _args...) \
+do { \
+ if (!(_condition)) \
+ ucall_assert(UCALL_ABORT, _exp, __FILE__, __LINE__, _fmt, ##_args); \
+} while (0)
+
+#define __GUEST_ASSERT(_condition, _fmt, _args...) \
+ ____GUEST_ASSERT(_condition, #_condition, _fmt, ##_args)
+
+#define GUEST_ASSERT(_condition) \
+ __GUEST_ASSERT(_condition, #_condition)
+
+#define GUEST_FAIL(_fmt, _args...) \
+ ucall_assert(UCALL_ABORT, "Unconditional guest failure", \
+ __FILE__, __LINE__, _fmt, ##_args)
+
+#define GUEST_ASSERT_EQ(a, b) \
+do { \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ ____GUEST_ASSERT(__a == __b, #a " == " #b, "%#lx != %#lx (%s != %s)", \
+ (unsigned long)(__a), (unsigned long)(__b), #a, #b); \
+} while (0)
+
+#define GUEST_ASSERT_NE(a, b) \
+do { \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ ____GUEST_ASSERT(__a != __b, #a " != " #b, "%#lx == %#lx (%s == %s)", \
+ (unsigned long)(__a), (unsigned long)(__b), #a, #b); \
+} while (0)
+
+#define REPORT_GUEST_ASSERT(ucall) \
+ test_assert(false, (const char *)(ucall).args[GUEST_ERROR_STRING], \
+ (const char *)(ucall).args[GUEST_FILE], \
+ (ucall).args[GUEST_LINE], "%s", (ucall).buffer)
+
+#endif /* SELFTEST_KVM_UCALL_COMMON_H */
diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h
new file mode 100644
index 0000000000..877449c345
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KVM userfaultfd util
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019-2022 Google LLC
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+
+#include "test_util.h"
+
+typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg);
+
+struct uffd_desc {
+ int uffd_mode;
+ int uffd;
+ int pipefds[2];
+ useconds_t delay;
+ uffd_handler_t handler;
+ pthread_t thread;
+};
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
+ void *hva, uint64_t len,
+ uffd_handler_t handler);
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd);
+
+#ifdef PRINT_PER_PAGE_UPDATES
+#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#ifdef PRINT_PER_VCPU_UPDATES
+#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h
new file mode 100644
index 0000000000..bed316fdec
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/apic.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/apic.h
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_APIC_H
+#define SELFTEST_KVM_APIC_H
+
+#include <stdint.h>
+
+#include "processor.h"
+
+#define APIC_DEFAULT_GPA 0xfee00000ULL
+
+/* APIC base address MSR and fields */
+#define MSR_IA32_APICBASE 0x0000001b
+#define MSR_IA32_APICBASE_BSP (1<<8)
+#define MSR_IA32_APICBASE_EXTD (1<<10)
+#define MSR_IA32_APICBASE_ENABLE (1<<11)
+#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+#define GET_APIC_BASE(x) (((x) >> 12) << 12)
+
+#define APIC_BASE_MSR 0x800
+#define X2APIC_ENABLE (1UL << 10)
+#define APIC_ID 0x20
+#define APIC_LVR 0x30
+#define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF)
+#define APIC_TASKPRI 0x80
+#define APIC_PROCPRI 0xA0
+#define APIC_EOI 0xB0
+#define APIC_SPIV 0xF0
+#define APIC_SPIV_FOCUS_DISABLED (1 << 9)
+#define APIC_SPIV_APIC_ENABLED (1 << 8)
+#define APIC_IRR 0x200
+#define APIC_ICR 0x300
+#define APIC_LVTCMCI 0x2f0
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DEST_PHYSICAL 0x00000
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+#define SET_APIC_DEST_FIELD(x) ((x) << 24)
+
+void apic_disable(void);
+void xapic_enable(void);
+void x2apic_enable(void);
+
+static inline uint32_t get_bsp_flag(void)
+{
+ return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP;
+}
+
+static inline uint32_t xapic_read_reg(unsigned int reg)
+{
+ return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2];
+}
+
+static inline void xapic_write_reg(unsigned int reg, uint32_t val)
+{
+ ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val;
+}
+
+static inline uint64_t x2apic_read_reg(unsigned int reg)
+{
+ return rdmsr(APIC_BASE_MSR + (reg >> 4));
+}
+
+static inline void x2apic_write_reg(unsigned int reg, uint64_t value)
+{
+ wrmsr(APIC_BASE_MSR + (reg >> 4), value);
+}
+
+#endif /* SELFTEST_KVM_APIC_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
new file mode 100644
index 0000000000..901caf0e09
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
@@ -0,0 +1,1279 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/evmcs.h
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_EVMCS_H
+#define SELFTEST_KVM_EVMCS_H
+
+#include <stdint.h>
+#include "hyperv.h"
+#include "vmx.h"
+
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+#define EVMCS_VERSION 1
+
+extern bool enable_evmcs;
+
+struct hv_enlightened_vmcs {
+ u32 revision_id;
+ u32 abort;
+
+ u16 host_es_selector;
+ u16 host_cs_selector;
+ u16 host_ss_selector;
+ u16 host_ds_selector;
+ u16 host_fs_selector;
+ u16 host_gs_selector;
+ u16 host_tr_selector;
+
+ u16 padding16_1;
+
+ u64 host_ia32_pat;
+ u64 host_ia32_efer;
+
+ u64 host_cr0;
+ u64 host_cr3;
+ u64 host_cr4;
+
+ u64 host_ia32_sysenter_esp;
+ u64 host_ia32_sysenter_eip;
+ u64 host_rip;
+ u32 host_ia32_sysenter_cs;
+
+ u32 pin_based_vm_exec_control;
+ u32 vm_exit_controls;
+ u32 secondary_vm_exec_control;
+
+ u64 io_bitmap_a;
+ u64 io_bitmap_b;
+ u64 msr_bitmap;
+
+ u16 guest_es_selector;
+ u16 guest_cs_selector;
+ u16 guest_ss_selector;
+ u16 guest_ds_selector;
+ u16 guest_fs_selector;
+ u16 guest_gs_selector;
+ u16 guest_ldtr_selector;
+ u16 guest_tr_selector;
+
+ u32 guest_es_limit;
+ u32 guest_cs_limit;
+ u32 guest_ss_limit;
+ u32 guest_ds_limit;
+ u32 guest_fs_limit;
+ u32 guest_gs_limit;
+ u32 guest_ldtr_limit;
+ u32 guest_tr_limit;
+ u32 guest_gdtr_limit;
+ u32 guest_idtr_limit;
+
+ u32 guest_es_ar_bytes;
+ u32 guest_cs_ar_bytes;
+ u32 guest_ss_ar_bytes;
+ u32 guest_ds_ar_bytes;
+ u32 guest_fs_ar_bytes;
+ u32 guest_gs_ar_bytes;
+ u32 guest_ldtr_ar_bytes;
+ u32 guest_tr_ar_bytes;
+
+ u64 guest_es_base;
+ u64 guest_cs_base;
+ u64 guest_ss_base;
+ u64 guest_ds_base;
+ u64 guest_fs_base;
+ u64 guest_gs_base;
+ u64 guest_ldtr_base;
+ u64 guest_tr_base;
+ u64 guest_gdtr_base;
+ u64 guest_idtr_base;
+
+ u64 padding64_1[3];
+
+ u64 vm_exit_msr_store_addr;
+ u64 vm_exit_msr_load_addr;
+ u64 vm_entry_msr_load_addr;
+
+ u64 cr3_target_value0;
+ u64 cr3_target_value1;
+ u64 cr3_target_value2;
+ u64 cr3_target_value3;
+
+ u32 page_fault_error_code_mask;
+ u32 page_fault_error_code_match;
+
+ u32 cr3_target_count;
+ u32 vm_exit_msr_store_count;
+ u32 vm_exit_msr_load_count;
+ u32 vm_entry_msr_load_count;
+
+ u64 tsc_offset;
+ u64 virtual_apic_page_addr;
+ u64 vmcs_link_pointer;
+
+ u64 guest_ia32_debugctl;
+ u64 guest_ia32_pat;
+ u64 guest_ia32_efer;
+
+ u64 guest_pdptr0;
+ u64 guest_pdptr1;
+ u64 guest_pdptr2;
+ u64 guest_pdptr3;
+
+ u64 guest_pending_dbg_exceptions;
+ u64 guest_sysenter_esp;
+ u64 guest_sysenter_eip;
+
+ u32 guest_activity_state;
+ u32 guest_sysenter_cs;
+
+ u64 cr0_guest_host_mask;
+ u64 cr4_guest_host_mask;
+ u64 cr0_read_shadow;
+ u64 cr4_read_shadow;
+ u64 guest_cr0;
+ u64 guest_cr3;
+ u64 guest_cr4;
+ u64 guest_dr7;
+
+ u64 host_fs_base;
+ u64 host_gs_base;
+ u64 host_tr_base;
+ u64 host_gdtr_base;
+ u64 host_idtr_base;
+ u64 host_rsp;
+
+ u64 ept_pointer;
+
+ u16 virtual_processor_id;
+ u16 padding16_2[3];
+
+ u64 padding64_2[5];
+ u64 guest_physical_address;
+
+ u32 vm_instruction_error;
+ u32 vm_exit_reason;
+ u32 vm_exit_intr_info;
+ u32 vm_exit_intr_error_code;
+ u32 idt_vectoring_info_field;
+ u32 idt_vectoring_error_code;
+ u32 vm_exit_instruction_len;
+ u32 vmx_instruction_info;
+
+ u64 exit_qualification;
+ u64 exit_io_instruction_ecx;
+ u64 exit_io_instruction_esi;
+ u64 exit_io_instruction_edi;
+ u64 exit_io_instruction_eip;
+
+ u64 guest_linear_address;
+ u64 guest_rsp;
+ u64 guest_rflags;
+
+ u32 guest_interruptibility_info;
+ u32 cpu_based_vm_exec_control;
+ u32 exception_bitmap;
+ u32 vm_entry_controls;
+ u32 vm_entry_intr_info_field;
+ u32 vm_entry_exception_error_code;
+ u32 vm_entry_instruction_len;
+ u32 tpr_threshold;
+
+ u64 guest_rip;
+
+ u32 hv_clean_fields;
+ u32 padding32_1;
+ u32 hv_synthetic_controls;
+ struct {
+ u32 nested_flush_hypercall:1;
+ u32 msr_bitmap:1;
+ u32 reserved:30;
+ } __packed hv_enlightenments_control;
+ u32 hv_vp_id;
+ u32 padding32_2;
+ u64 hv_vm_id;
+ u64 partition_assist_page;
+ u64 padding64_4[4];
+ u64 guest_bndcfgs;
+ u64 guest_ia32_perf_global_ctrl;
+ u64 guest_ia32_s_cet;
+ u64 guest_ssp;
+ u64 guest_ia32_int_ssp_table_addr;
+ u64 guest_ia32_lbr_ctl;
+ u64 padding64_5[2];
+ u64 xss_exit_bitmap;
+ u64 encls_exiting_bitmap;
+ u64 host_ia32_perf_global_ctrl;
+ u64 tsc_multiplier;
+ u64 host_ia32_s_cet;
+ u64 host_ssp;
+ u64 host_ia32_int_ssp_table_addr;
+ u64 padding64_6;
+} __packed;
+
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF
+
+#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031
+
+extern struct hv_enlightened_vmcs *current_evmcs;
+
+int vcpu_enable_evmcs(struct kvm_vcpu *vcpu);
+
+static inline void evmcs_enable(void)
+{
+ enable_evmcs = true;
+}
+
+static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
+{
+ current_vp_assist->current_nested_vmcs = vmcs_pa;
+ current_vp_assist->enlighten_vmentry = 1;
+
+ current_evmcs = vmcs;
+
+ return 0;
+}
+
+static inline bool load_evmcs(struct hyperv_test_pages *hv)
+{
+ if (evmcs_vmptrld(hv->enlightened_vmcs_gpa, hv->enlightened_vmcs))
+ return false;
+
+ current_evmcs->revision_id = EVMCS_VERSION;
+
+ return true;
+}
+
+static inline int evmcs_vmptrst(uint64_t *value)
+{
+ *value = current_vp_assist->current_nested_vmcs &
+ ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+ return 0;
+}
+
+static inline int evmcs_vmread(uint64_t encoding, uint64_t *value)
+{
+ switch (encoding) {
+ case GUEST_RIP:
+ *value = current_evmcs->guest_rip;
+ break;
+ case GUEST_RSP:
+ *value = current_evmcs->guest_rsp;
+ break;
+ case GUEST_RFLAGS:
+ *value = current_evmcs->guest_rflags;
+ break;
+ case HOST_IA32_PAT:
+ *value = current_evmcs->host_ia32_pat;
+ break;
+ case HOST_IA32_EFER:
+ *value = current_evmcs->host_ia32_efer;
+ break;
+ case HOST_CR0:
+ *value = current_evmcs->host_cr0;
+ break;
+ case HOST_CR3:
+ *value = current_evmcs->host_cr3;
+ break;
+ case HOST_CR4:
+ *value = current_evmcs->host_cr4;
+ break;
+ case HOST_IA32_SYSENTER_ESP:
+ *value = current_evmcs->host_ia32_sysenter_esp;
+ break;
+ case HOST_IA32_SYSENTER_EIP:
+ *value = current_evmcs->host_ia32_sysenter_eip;
+ break;
+ case HOST_RIP:
+ *value = current_evmcs->host_rip;
+ break;
+ case IO_BITMAP_A:
+ *value = current_evmcs->io_bitmap_a;
+ break;
+ case IO_BITMAP_B:
+ *value = current_evmcs->io_bitmap_b;
+ break;
+ case MSR_BITMAP:
+ *value = current_evmcs->msr_bitmap;
+ break;
+ case GUEST_ES_BASE:
+ *value = current_evmcs->guest_es_base;
+ break;
+ case GUEST_CS_BASE:
+ *value = current_evmcs->guest_cs_base;
+ break;
+ case GUEST_SS_BASE:
+ *value = current_evmcs->guest_ss_base;
+ break;
+ case GUEST_DS_BASE:
+ *value = current_evmcs->guest_ds_base;
+ break;
+ case GUEST_FS_BASE:
+ *value = current_evmcs->guest_fs_base;
+ break;
+ case GUEST_GS_BASE:
+ *value = current_evmcs->guest_gs_base;
+ break;
+ case GUEST_LDTR_BASE:
+ *value = current_evmcs->guest_ldtr_base;
+ break;
+ case GUEST_TR_BASE:
+ *value = current_evmcs->guest_tr_base;
+ break;
+ case GUEST_GDTR_BASE:
+ *value = current_evmcs->guest_gdtr_base;
+ break;
+ case GUEST_IDTR_BASE:
+ *value = current_evmcs->guest_idtr_base;
+ break;
+ case TSC_OFFSET:
+ *value = current_evmcs->tsc_offset;
+ break;
+ case VIRTUAL_APIC_PAGE_ADDR:
+ *value = current_evmcs->virtual_apic_page_addr;
+ break;
+ case VMCS_LINK_POINTER:
+ *value = current_evmcs->vmcs_link_pointer;
+ break;
+ case GUEST_IA32_DEBUGCTL:
+ *value = current_evmcs->guest_ia32_debugctl;
+ break;
+ case GUEST_IA32_PAT:
+ *value = current_evmcs->guest_ia32_pat;
+ break;
+ case GUEST_IA32_EFER:
+ *value = current_evmcs->guest_ia32_efer;
+ break;
+ case GUEST_PDPTR0:
+ *value = current_evmcs->guest_pdptr0;
+ break;
+ case GUEST_PDPTR1:
+ *value = current_evmcs->guest_pdptr1;
+ break;
+ case GUEST_PDPTR2:
+ *value = current_evmcs->guest_pdptr2;
+ break;
+ case GUEST_PDPTR3:
+ *value = current_evmcs->guest_pdptr3;
+ break;
+ case GUEST_PENDING_DBG_EXCEPTIONS:
+ *value = current_evmcs->guest_pending_dbg_exceptions;
+ break;
+ case GUEST_SYSENTER_ESP:
+ *value = current_evmcs->guest_sysenter_esp;
+ break;
+ case GUEST_SYSENTER_EIP:
+ *value = current_evmcs->guest_sysenter_eip;
+ break;
+ case CR0_GUEST_HOST_MASK:
+ *value = current_evmcs->cr0_guest_host_mask;
+ break;
+ case CR4_GUEST_HOST_MASK:
+ *value = current_evmcs->cr4_guest_host_mask;
+ break;
+ case CR0_READ_SHADOW:
+ *value = current_evmcs->cr0_read_shadow;
+ break;
+ case CR4_READ_SHADOW:
+ *value = current_evmcs->cr4_read_shadow;
+ break;
+ case GUEST_CR0:
+ *value = current_evmcs->guest_cr0;
+ break;
+ case GUEST_CR3:
+ *value = current_evmcs->guest_cr3;
+ break;
+ case GUEST_CR4:
+ *value = current_evmcs->guest_cr4;
+ break;
+ case GUEST_DR7:
+ *value = current_evmcs->guest_dr7;
+ break;
+ case HOST_FS_BASE:
+ *value = current_evmcs->host_fs_base;
+ break;
+ case HOST_GS_BASE:
+ *value = current_evmcs->host_gs_base;
+ break;
+ case HOST_TR_BASE:
+ *value = current_evmcs->host_tr_base;
+ break;
+ case HOST_GDTR_BASE:
+ *value = current_evmcs->host_gdtr_base;
+ break;
+ case HOST_IDTR_BASE:
+ *value = current_evmcs->host_idtr_base;
+ break;
+ case HOST_RSP:
+ *value = current_evmcs->host_rsp;
+ break;
+ case EPT_POINTER:
+ *value = current_evmcs->ept_pointer;
+ break;
+ case GUEST_BNDCFGS:
+ *value = current_evmcs->guest_bndcfgs;
+ break;
+ case XSS_EXIT_BITMAP:
+ *value = current_evmcs->xss_exit_bitmap;
+ break;
+ case GUEST_PHYSICAL_ADDRESS:
+ *value = current_evmcs->guest_physical_address;
+ break;
+ case EXIT_QUALIFICATION:
+ *value = current_evmcs->exit_qualification;
+ break;
+ case GUEST_LINEAR_ADDRESS:
+ *value = current_evmcs->guest_linear_address;
+ break;
+ case VM_EXIT_MSR_STORE_ADDR:
+ *value = current_evmcs->vm_exit_msr_store_addr;
+ break;
+ case VM_EXIT_MSR_LOAD_ADDR:
+ *value = current_evmcs->vm_exit_msr_load_addr;
+ break;
+ case VM_ENTRY_MSR_LOAD_ADDR:
+ *value = current_evmcs->vm_entry_msr_load_addr;
+ break;
+ case CR3_TARGET_VALUE0:
+ *value = current_evmcs->cr3_target_value0;
+ break;
+ case CR3_TARGET_VALUE1:
+ *value = current_evmcs->cr3_target_value1;
+ break;
+ case CR3_TARGET_VALUE2:
+ *value = current_evmcs->cr3_target_value2;
+ break;
+ case CR3_TARGET_VALUE3:
+ *value = current_evmcs->cr3_target_value3;
+ break;
+ case TPR_THRESHOLD:
+ *value = current_evmcs->tpr_threshold;
+ break;
+ case GUEST_INTERRUPTIBILITY_INFO:
+ *value = current_evmcs->guest_interruptibility_info;
+ break;
+ case CPU_BASED_VM_EXEC_CONTROL:
+ *value = current_evmcs->cpu_based_vm_exec_control;
+ break;
+ case EXCEPTION_BITMAP:
+ *value = current_evmcs->exception_bitmap;
+ break;
+ case VM_ENTRY_CONTROLS:
+ *value = current_evmcs->vm_entry_controls;
+ break;
+ case VM_ENTRY_INTR_INFO_FIELD:
+ *value = current_evmcs->vm_entry_intr_info_field;
+ break;
+ case VM_ENTRY_EXCEPTION_ERROR_CODE:
+ *value = current_evmcs->vm_entry_exception_error_code;
+ break;
+ case VM_ENTRY_INSTRUCTION_LEN:
+ *value = current_evmcs->vm_entry_instruction_len;
+ break;
+ case HOST_IA32_SYSENTER_CS:
+ *value = current_evmcs->host_ia32_sysenter_cs;
+ break;
+ case PIN_BASED_VM_EXEC_CONTROL:
+ *value = current_evmcs->pin_based_vm_exec_control;
+ break;
+ case VM_EXIT_CONTROLS:
+ *value = current_evmcs->vm_exit_controls;
+ break;
+ case SECONDARY_VM_EXEC_CONTROL:
+ *value = current_evmcs->secondary_vm_exec_control;
+ break;
+ case GUEST_ES_LIMIT:
+ *value = current_evmcs->guest_es_limit;
+ break;
+ case GUEST_CS_LIMIT:
+ *value = current_evmcs->guest_cs_limit;
+ break;
+ case GUEST_SS_LIMIT:
+ *value = current_evmcs->guest_ss_limit;
+ break;
+ case GUEST_DS_LIMIT:
+ *value = current_evmcs->guest_ds_limit;
+ break;
+ case GUEST_FS_LIMIT:
+ *value = current_evmcs->guest_fs_limit;
+ break;
+ case GUEST_GS_LIMIT:
+ *value = current_evmcs->guest_gs_limit;
+ break;
+ case GUEST_LDTR_LIMIT:
+ *value = current_evmcs->guest_ldtr_limit;
+ break;
+ case GUEST_TR_LIMIT:
+ *value = current_evmcs->guest_tr_limit;
+ break;
+ case GUEST_GDTR_LIMIT:
+ *value = current_evmcs->guest_gdtr_limit;
+ break;
+ case GUEST_IDTR_LIMIT:
+ *value = current_evmcs->guest_idtr_limit;
+ break;
+ case GUEST_ES_AR_BYTES:
+ *value = current_evmcs->guest_es_ar_bytes;
+ break;
+ case GUEST_CS_AR_BYTES:
+ *value = current_evmcs->guest_cs_ar_bytes;
+ break;
+ case GUEST_SS_AR_BYTES:
+ *value = current_evmcs->guest_ss_ar_bytes;
+ break;
+ case GUEST_DS_AR_BYTES:
+ *value = current_evmcs->guest_ds_ar_bytes;
+ break;
+ case GUEST_FS_AR_BYTES:
+ *value = current_evmcs->guest_fs_ar_bytes;
+ break;
+ case GUEST_GS_AR_BYTES:
+ *value = current_evmcs->guest_gs_ar_bytes;
+ break;
+ case GUEST_LDTR_AR_BYTES:
+ *value = current_evmcs->guest_ldtr_ar_bytes;
+ break;
+ case GUEST_TR_AR_BYTES:
+ *value = current_evmcs->guest_tr_ar_bytes;
+ break;
+ case GUEST_ACTIVITY_STATE:
+ *value = current_evmcs->guest_activity_state;
+ break;
+ case GUEST_SYSENTER_CS:
+ *value = current_evmcs->guest_sysenter_cs;
+ break;
+ case VM_INSTRUCTION_ERROR:
+ *value = current_evmcs->vm_instruction_error;
+ break;
+ case VM_EXIT_REASON:
+ *value = current_evmcs->vm_exit_reason;
+ break;
+ case VM_EXIT_INTR_INFO:
+ *value = current_evmcs->vm_exit_intr_info;
+ break;
+ case VM_EXIT_INTR_ERROR_CODE:
+ *value = current_evmcs->vm_exit_intr_error_code;
+ break;
+ case IDT_VECTORING_INFO_FIELD:
+ *value = current_evmcs->idt_vectoring_info_field;
+ break;
+ case IDT_VECTORING_ERROR_CODE:
+ *value = current_evmcs->idt_vectoring_error_code;
+ break;
+ case VM_EXIT_INSTRUCTION_LEN:
+ *value = current_evmcs->vm_exit_instruction_len;
+ break;
+ case VMX_INSTRUCTION_INFO:
+ *value = current_evmcs->vmx_instruction_info;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MASK:
+ *value = current_evmcs->page_fault_error_code_mask;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MATCH:
+ *value = current_evmcs->page_fault_error_code_match;
+ break;
+ case CR3_TARGET_COUNT:
+ *value = current_evmcs->cr3_target_count;
+ break;
+ case VM_EXIT_MSR_STORE_COUNT:
+ *value = current_evmcs->vm_exit_msr_store_count;
+ break;
+ case VM_EXIT_MSR_LOAD_COUNT:
+ *value = current_evmcs->vm_exit_msr_load_count;
+ break;
+ case VM_ENTRY_MSR_LOAD_COUNT:
+ *value = current_evmcs->vm_entry_msr_load_count;
+ break;
+ case HOST_ES_SELECTOR:
+ *value = current_evmcs->host_es_selector;
+ break;
+ case HOST_CS_SELECTOR:
+ *value = current_evmcs->host_cs_selector;
+ break;
+ case HOST_SS_SELECTOR:
+ *value = current_evmcs->host_ss_selector;
+ break;
+ case HOST_DS_SELECTOR:
+ *value = current_evmcs->host_ds_selector;
+ break;
+ case HOST_FS_SELECTOR:
+ *value = current_evmcs->host_fs_selector;
+ break;
+ case HOST_GS_SELECTOR:
+ *value = current_evmcs->host_gs_selector;
+ break;
+ case HOST_TR_SELECTOR:
+ *value = current_evmcs->host_tr_selector;
+ break;
+ case GUEST_ES_SELECTOR:
+ *value = current_evmcs->guest_es_selector;
+ break;
+ case GUEST_CS_SELECTOR:
+ *value = current_evmcs->guest_cs_selector;
+ break;
+ case GUEST_SS_SELECTOR:
+ *value = current_evmcs->guest_ss_selector;
+ break;
+ case GUEST_DS_SELECTOR:
+ *value = current_evmcs->guest_ds_selector;
+ break;
+ case GUEST_FS_SELECTOR:
+ *value = current_evmcs->guest_fs_selector;
+ break;
+ case GUEST_GS_SELECTOR:
+ *value = current_evmcs->guest_gs_selector;
+ break;
+ case GUEST_LDTR_SELECTOR:
+ *value = current_evmcs->guest_ldtr_selector;
+ break;
+ case GUEST_TR_SELECTOR:
+ *value = current_evmcs->guest_tr_selector;
+ break;
+ case VIRTUAL_PROCESSOR_ID:
+ *value = current_evmcs->virtual_processor_id;
+ break;
+ case HOST_IA32_PERF_GLOBAL_CTRL:
+ *value = current_evmcs->host_ia32_perf_global_ctrl;
+ break;
+ case GUEST_IA32_PERF_GLOBAL_CTRL:
+ *value = current_evmcs->guest_ia32_perf_global_ctrl;
+ break;
+ case ENCLS_EXITING_BITMAP:
+ *value = current_evmcs->encls_exiting_bitmap;
+ break;
+ case TSC_MULTIPLIER:
+ *value = current_evmcs->tsc_multiplier;
+ break;
+ default: return 1;
+ }
+
+ return 0;
+}
+
+static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
+{
+ switch (encoding) {
+ case GUEST_RIP:
+ current_evmcs->guest_rip = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case GUEST_RSP:
+ current_evmcs->guest_rsp = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
+ break;
+ case GUEST_RFLAGS:
+ current_evmcs->guest_rflags = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
+ break;
+ case HOST_IA32_PAT:
+ current_evmcs->host_ia32_pat = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_IA32_EFER:
+ current_evmcs->host_ia32_efer = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_CR0:
+ current_evmcs->host_cr0 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_CR3:
+ current_evmcs->host_cr3 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_CR4:
+ current_evmcs->host_cr4 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_IA32_SYSENTER_ESP:
+ current_evmcs->host_ia32_sysenter_esp = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_IA32_SYSENTER_EIP:
+ current_evmcs->host_ia32_sysenter_eip = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_RIP:
+ current_evmcs->host_rip = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case IO_BITMAP_A:
+ current_evmcs->io_bitmap_a = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP;
+ break;
+ case IO_BITMAP_B:
+ current_evmcs->io_bitmap_b = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP;
+ break;
+ case MSR_BITMAP:
+ current_evmcs->msr_bitmap = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+ break;
+ case GUEST_ES_BASE:
+ current_evmcs->guest_es_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_CS_BASE:
+ current_evmcs->guest_cs_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_SS_BASE:
+ current_evmcs->guest_ss_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_DS_BASE:
+ current_evmcs->guest_ds_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_FS_BASE:
+ current_evmcs->guest_fs_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GS_BASE:
+ current_evmcs->guest_gs_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_LDTR_BASE:
+ current_evmcs->guest_ldtr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_TR_BASE:
+ current_evmcs->guest_tr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GDTR_BASE:
+ current_evmcs->guest_gdtr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_IDTR_BASE:
+ current_evmcs->guest_idtr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case TSC_OFFSET:
+ current_evmcs->tsc_offset = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ case VIRTUAL_APIC_PAGE_ADDR:
+ current_evmcs->virtual_apic_page_addr = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ case VMCS_LINK_POINTER:
+ current_evmcs->vmcs_link_pointer = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_IA32_DEBUGCTL:
+ current_evmcs->guest_ia32_debugctl = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_IA32_PAT:
+ current_evmcs->guest_ia32_pat = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_IA32_EFER:
+ current_evmcs->guest_ia32_efer = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_PDPTR0:
+ current_evmcs->guest_pdptr0 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_PDPTR1:
+ current_evmcs->guest_pdptr1 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_PDPTR2:
+ current_evmcs->guest_pdptr2 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_PDPTR3:
+ current_evmcs->guest_pdptr3 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_PENDING_DBG_EXCEPTIONS:
+ current_evmcs->guest_pending_dbg_exceptions = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_SYSENTER_ESP:
+ current_evmcs->guest_sysenter_esp = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_SYSENTER_EIP:
+ current_evmcs->guest_sysenter_eip = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case CR0_GUEST_HOST_MASK:
+ current_evmcs->cr0_guest_host_mask = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case CR4_GUEST_HOST_MASK:
+ current_evmcs->cr4_guest_host_mask = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case CR0_READ_SHADOW:
+ current_evmcs->cr0_read_shadow = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case CR4_READ_SHADOW:
+ current_evmcs->cr4_read_shadow = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case GUEST_CR0:
+ current_evmcs->guest_cr0 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case GUEST_CR3:
+ current_evmcs->guest_cr3 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case GUEST_CR4:
+ current_evmcs->guest_cr4 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case GUEST_DR7:
+ current_evmcs->guest_dr7 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
+ break;
+ case HOST_FS_BASE:
+ current_evmcs->host_fs_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case HOST_GS_BASE:
+ current_evmcs->host_gs_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case HOST_TR_BASE:
+ current_evmcs->host_tr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case HOST_GDTR_BASE:
+ current_evmcs->host_gdtr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case HOST_IDTR_BASE:
+ current_evmcs->host_idtr_base = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case HOST_RSP:
+ current_evmcs->host_rsp = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+ break;
+ case EPT_POINTER:
+ current_evmcs->ept_pointer = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT;
+ break;
+ case GUEST_BNDCFGS:
+ current_evmcs->guest_bndcfgs = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case XSS_EXIT_BITMAP:
+ current_evmcs->xss_exit_bitmap = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ case GUEST_PHYSICAL_ADDRESS:
+ current_evmcs->guest_physical_address = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case EXIT_QUALIFICATION:
+ current_evmcs->exit_qualification = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case GUEST_LINEAR_ADDRESS:
+ current_evmcs->guest_linear_address = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VM_EXIT_MSR_STORE_ADDR:
+ current_evmcs->vm_exit_msr_store_addr = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case VM_EXIT_MSR_LOAD_ADDR:
+ current_evmcs->vm_exit_msr_load_addr = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case VM_ENTRY_MSR_LOAD_ADDR:
+ current_evmcs->vm_entry_msr_load_addr = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case CR3_TARGET_VALUE0:
+ current_evmcs->cr3_target_value0 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case CR3_TARGET_VALUE1:
+ current_evmcs->cr3_target_value1 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case CR3_TARGET_VALUE2:
+ current_evmcs->cr3_target_value2 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case CR3_TARGET_VALUE3:
+ current_evmcs->cr3_target_value3 = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case TPR_THRESHOLD:
+ current_evmcs->tpr_threshold = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case GUEST_INTERRUPTIBILITY_INFO:
+ current_evmcs->guest_interruptibility_info = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
+ break;
+ case CPU_BASED_VM_EXEC_CONTROL:
+ current_evmcs->cpu_based_vm_exec_control = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC;
+ break;
+ case EXCEPTION_BITMAP:
+ current_evmcs->exception_bitmap = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN;
+ break;
+ case VM_ENTRY_CONTROLS:
+ current_evmcs->vm_entry_controls = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY;
+ break;
+ case VM_ENTRY_INTR_INFO_FIELD:
+ current_evmcs->vm_entry_intr_info_field = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
+ break;
+ case VM_ENTRY_EXCEPTION_ERROR_CODE:
+ current_evmcs->vm_entry_exception_error_code = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
+ break;
+ case VM_ENTRY_INSTRUCTION_LEN:
+ current_evmcs->vm_entry_instruction_len = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
+ break;
+ case HOST_IA32_SYSENTER_CS:
+ current_evmcs->host_ia32_sysenter_cs = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case PIN_BASED_VM_EXEC_CONTROL:
+ current_evmcs->pin_based_vm_exec_control = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
+ break;
+ case VM_EXIT_CONTROLS:
+ current_evmcs->vm_exit_controls = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
+ break;
+ case SECONDARY_VM_EXEC_CONTROL:
+ current_evmcs->secondary_vm_exec_control = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
+ break;
+ case GUEST_ES_LIMIT:
+ current_evmcs->guest_es_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_CS_LIMIT:
+ current_evmcs->guest_cs_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_SS_LIMIT:
+ current_evmcs->guest_ss_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_DS_LIMIT:
+ current_evmcs->guest_ds_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_FS_LIMIT:
+ current_evmcs->guest_fs_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GS_LIMIT:
+ current_evmcs->guest_gs_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_LDTR_LIMIT:
+ current_evmcs->guest_ldtr_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_TR_LIMIT:
+ current_evmcs->guest_tr_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GDTR_LIMIT:
+ current_evmcs->guest_gdtr_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_IDTR_LIMIT:
+ current_evmcs->guest_idtr_limit = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_ES_AR_BYTES:
+ current_evmcs->guest_es_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_CS_AR_BYTES:
+ current_evmcs->guest_cs_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_SS_AR_BYTES:
+ current_evmcs->guest_ss_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_DS_AR_BYTES:
+ current_evmcs->guest_ds_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_FS_AR_BYTES:
+ current_evmcs->guest_fs_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GS_AR_BYTES:
+ current_evmcs->guest_gs_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_LDTR_AR_BYTES:
+ current_evmcs->guest_ldtr_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_TR_AR_BYTES:
+ current_evmcs->guest_tr_ar_bytes = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_ACTIVITY_STATE:
+ current_evmcs->guest_activity_state = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case GUEST_SYSENTER_CS:
+ current_evmcs->guest_sysenter_cs = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case VM_INSTRUCTION_ERROR:
+ current_evmcs->vm_instruction_error = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VM_EXIT_REASON:
+ current_evmcs->vm_exit_reason = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VM_EXIT_INTR_INFO:
+ current_evmcs->vm_exit_intr_info = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VM_EXIT_INTR_ERROR_CODE:
+ current_evmcs->vm_exit_intr_error_code = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case IDT_VECTORING_INFO_FIELD:
+ current_evmcs->idt_vectoring_info_field = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case IDT_VECTORING_ERROR_CODE:
+ current_evmcs->idt_vectoring_error_code = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VM_EXIT_INSTRUCTION_LEN:
+ current_evmcs->vm_exit_instruction_len = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case VMX_INSTRUCTION_INFO:
+ current_evmcs->vmx_instruction_info = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MASK:
+ current_evmcs->page_fault_error_code_mask = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MATCH:
+ current_evmcs->page_fault_error_code_match = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case CR3_TARGET_COUNT:
+ current_evmcs->cr3_target_count = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case VM_EXIT_MSR_STORE_COUNT:
+ current_evmcs->vm_exit_msr_store_count = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case VM_EXIT_MSR_LOAD_COUNT:
+ current_evmcs->vm_exit_msr_load_count = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case VM_ENTRY_MSR_LOAD_COUNT:
+ current_evmcs->vm_entry_msr_load_count = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ break;
+ case HOST_ES_SELECTOR:
+ current_evmcs->host_es_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_CS_SELECTOR:
+ current_evmcs->host_cs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_SS_SELECTOR:
+ current_evmcs->host_ss_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_DS_SELECTOR:
+ current_evmcs->host_ds_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_FS_SELECTOR:
+ current_evmcs->host_fs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_GS_SELECTOR:
+ current_evmcs->host_gs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case HOST_TR_SELECTOR:
+ current_evmcs->host_tr_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case GUEST_ES_SELECTOR:
+ current_evmcs->guest_es_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_CS_SELECTOR:
+ current_evmcs->guest_cs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_SS_SELECTOR:
+ current_evmcs->guest_ss_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_DS_SELECTOR:
+ current_evmcs->guest_ds_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_FS_SELECTOR:
+ current_evmcs->guest_fs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_GS_SELECTOR:
+ current_evmcs->guest_gs_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_LDTR_SELECTOR:
+ current_evmcs->guest_ldtr_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case GUEST_TR_SELECTOR:
+ current_evmcs->guest_tr_selector = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
+ break;
+ case VIRTUAL_PROCESSOR_ID:
+ current_evmcs->virtual_processor_id = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT;
+ break;
+ case HOST_IA32_PERF_GLOBAL_CTRL:
+ current_evmcs->host_ia32_perf_global_ctrl = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case GUEST_IA32_PERF_GLOBAL_CTRL:
+ current_evmcs->guest_ia32_perf_global_ctrl = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case ENCLS_EXITING_BITMAP:
+ current_evmcs->encls_exiting_bitmap = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ case TSC_MULTIPLIER:
+ current_evmcs->tsc_multiplier = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ default: return 1;
+ }
+
+ return 0;
+}
+
+static inline int evmcs_vmlaunch(void)
+{
+ int ret;
+
+ current_evmcs->hv_clean_fields = 0;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "mov %%rsp, (%[host_rsp]);"
+ "lea 1f(%%rip), %%rax;"
+ "mov %%rax, (%[host_rip]);"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"
+ ((uint64_t)&current_evmcs->host_rsp),
+ [host_rip]"r"
+ ((uint64_t)&current_evmcs->host_rip)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int evmcs_vmresume(void)
+{
+ int ret;
+
+ /* HOST_RIP */
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ /* HOST_RSP */
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "mov %%rsp, (%[host_rsp]);"
+ "lea 1f(%%rip), %%rax;"
+ "mov %%rax, (%[host_rip]);"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"
+ ((uint64_t)&current_evmcs->host_rsp),
+ [host_rip]"r"
+ ((uint64_t)&current_evmcs->host_rip)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+#endif /* !SELFTEST_KVM_EVMCS_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
new file mode 100644
index 0000000000..fa65b908b1
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
@@ -0,0 +1,346 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/hyperv.h
+ *
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_HYPERV_H
+#define SELFTEST_KVM_HYPERV_H
+
+#include "processor.h"
+
+#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000
+#define HYPERV_CPUID_INTERFACE 0x40000001
+#define HYPERV_CPUID_VERSION 0x40000002
+#define HYPERV_CPUID_FEATURES 0x40000003
+#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004
+#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005
+#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007
+#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A
+#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080
+#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081
+#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082
+
+#define HV_X64_MSR_GUEST_OS_ID 0x40000000
+#define HV_X64_MSR_HYPERCALL 0x40000001
+#define HV_X64_MSR_VP_INDEX 0x40000002
+#define HV_X64_MSR_RESET 0x40000003
+#define HV_X64_MSR_VP_RUNTIME 0x40000010
+#define HV_X64_MSR_TIME_REF_COUNT 0x40000020
+#define HV_X64_MSR_REFERENCE_TSC 0x40000021
+#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
+#define HV_X64_MSR_APIC_FREQUENCY 0x40000023
+#define HV_X64_MSR_EOI 0x40000070
+#define HV_X64_MSR_ICR 0x40000071
+#define HV_X64_MSR_TPR 0x40000072
+#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
+#define HV_X64_MSR_SCONTROL 0x40000080
+#define HV_X64_MSR_SVERSION 0x40000081
+#define HV_X64_MSR_SIEFP 0x40000082
+#define HV_X64_MSR_SIMP 0x40000083
+#define HV_X64_MSR_EOM 0x40000084
+#define HV_X64_MSR_SINT0 0x40000090
+#define HV_X64_MSR_SINT1 0x40000091
+#define HV_X64_MSR_SINT2 0x40000092
+#define HV_X64_MSR_SINT3 0x40000093
+#define HV_X64_MSR_SINT4 0x40000094
+#define HV_X64_MSR_SINT5 0x40000095
+#define HV_X64_MSR_SINT6 0x40000096
+#define HV_X64_MSR_SINT7 0x40000097
+#define HV_X64_MSR_SINT8 0x40000098
+#define HV_X64_MSR_SINT9 0x40000099
+#define HV_X64_MSR_SINT10 0x4000009A
+#define HV_X64_MSR_SINT11 0x4000009B
+#define HV_X64_MSR_SINT12 0x4000009C
+#define HV_X64_MSR_SINT13 0x4000009D
+#define HV_X64_MSR_SINT14 0x4000009E
+#define HV_X64_MSR_SINT15 0x4000009F
+#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0
+#define HV_X64_MSR_STIMER0_COUNT 0x400000B1
+#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2
+#define HV_X64_MSR_STIMER1_COUNT 0x400000B3
+#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4
+#define HV_X64_MSR_STIMER2_COUNT 0x400000B5
+#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6
+#define HV_X64_MSR_STIMER3_COUNT 0x400000B7
+#define HV_X64_MSR_GUEST_IDLE 0x400000F0
+#define HV_X64_MSR_CRASH_P0 0x40000100
+#define HV_X64_MSR_CRASH_P1 0x40000101
+#define HV_X64_MSR_CRASH_P2 0x40000102
+#define HV_X64_MSR_CRASH_P3 0x40000103
+#define HV_X64_MSR_CRASH_P4 0x40000104
+#define HV_X64_MSR_CRASH_CTL 0x40000105
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
+#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108
+#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118
+
+#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1
+#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2
+#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3
+#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4
+#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5
+#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF
+
+/* HYPERV_CPUID_FEATURES.EAX */
+#define HV_MSR_VP_RUNTIME_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 0)
+#define HV_MSR_TIME_REF_COUNT_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 1)
+#define HV_MSR_SYNIC_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 2)
+#define HV_MSR_SYNTIMER_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 3)
+#define HV_MSR_APIC_ACCESS_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 4)
+#define HV_MSR_HYPERCALL_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 5)
+#define HV_MSR_VP_INDEX_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 6)
+#define HV_MSR_RESET_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 7)
+#define HV_MSR_STAT_PAGES_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 8)
+#define HV_MSR_REFERENCE_TSC_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 9)
+#define HV_MSR_GUEST_IDLE_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 10)
+#define HV_ACCESS_FREQUENCY_MSRS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 11)
+#define HV_ACCESS_REENLIGHTENMENT \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 13)
+#define HV_ACCESS_TSC_INVARIANT \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 15)
+
+/* HYPERV_CPUID_FEATURES.EBX */
+#define HV_CREATE_PARTITIONS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 0)
+#define HV_ACCESS_PARTITION_ID \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 1)
+#define HV_ACCESS_MEMORY_POOL \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 2)
+#define HV_ADJUST_MESSAGE_BUFFERS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 3)
+#define HV_POST_MESSAGES \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 4)
+#define HV_SIGNAL_EVENTS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 5)
+#define HV_CREATE_PORT \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 6)
+#define HV_CONNECT_PORT \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 7)
+#define HV_ACCESS_STATS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 8)
+#define HV_DEBUGGING \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 11)
+#define HV_CPU_MANAGEMENT \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 12)
+#define HV_ENABLE_EXTENDED_HYPERCALLS \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 20)
+#define HV_ISOLATION \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 22)
+
+/* HYPERV_CPUID_FEATURES.EDX */
+#define HV_X64_MWAIT_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 0)
+#define HV_X64_GUEST_DEBUGGING_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 1)
+#define HV_X64_PERF_MONITOR_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 2)
+#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 3)
+#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 4)
+#define HV_X64_GUEST_IDLE_STATE_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 5)
+#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 8)
+#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 10)
+#define HV_FEATURE_DEBUG_MSRS_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 11)
+#define HV_STIMER_DIRECT_MODE_AVAILABLE \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 19)
+
+/* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */
+#define HV_X64_AS_SWITCH_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 0)
+#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 1)
+#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 2)
+#define HV_X64_APIC_ACCESS_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 3)
+#define HV_X64_SYSTEM_RESET_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 4)
+#define HV_X64_RELAXED_TIMING_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 5)
+#define HV_DEPRECATING_AEOI_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 9)
+#define HV_X64_CLUSTER_IPI_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 10)
+#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 11)
+#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14)
+
+/* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */
+#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \
+ KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1)
+
+/* Hypercalls */
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
+#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
+#define HVCALL_SEND_IPI 0x000b
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014
+#define HVCALL_SEND_IPI_EX 0x0015
+#define HVCALL_GET_PARTITION_ID 0x0046
+#define HVCALL_DEPOSIT_MEMORY 0x0048
+#define HVCALL_CREATE_VP 0x004e
+#define HVCALL_GET_VP_REGISTERS 0x0050
+#define HVCALL_SET_VP_REGISTERS 0x0051
+#define HVCALL_POST_MESSAGE 0x005c
+#define HVCALL_SIGNAL_EVENT 0x005d
+#define HVCALL_POST_DEBUG_DATA 0x0069
+#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a
+#define HVCALL_RESET_DEBUG_SESSION 0x006b
+#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076
+#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c
+#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d
+#define HVCALL_RETARGET_INTERRUPT 0x007e
+#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
+#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
+
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001
+
+#define HV_FLUSH_ALL_PROCESSORS BIT(0)
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1)
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2)
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3)
+
+/* hypercall status code */
+#define HV_STATUS_SUCCESS 0
+#define HV_STATUS_INVALID_HYPERCALL_CODE 2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT 3
+#define HV_STATUS_INVALID_ALIGNMENT 4
+#define HV_STATUS_INVALID_PARAMETER 5
+#define HV_STATUS_ACCESS_DENIED 6
+#define HV_STATUS_OPERATION_DENIED 8
+#define HV_STATUS_INSUFFICIENT_MEMORY 11
+#define HV_STATUS_INVALID_PORT_ID 17
+#define HV_STATUS_INVALID_CONNECTION_ID 18
+#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+
+/* hypercall options */
+#define HV_HYPERCALL_FAST_BIT BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET 17
+#define HV_HYPERCALL_REP_COMP_OFFSET 32
+
+/*
+ * Issue a Hyper-V hypercall. Returns exception vector raised or 0, 'hv_status'
+ * is set to the hypercall status (if no exception occurred).
+ */
+static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address,
+ vm_vaddr_t output_address,
+ uint64_t *hv_status)
+{
+ uint64_t error_code;
+ uint8_t vector;
+
+ /* Note both the hypercall and the "asm safe" clobber r9-r11. */
+ asm volatile("mov %[output_address], %%r8\n\t"
+ KVM_ASM_SAFE("vmcall")
+ : "=a" (*hv_status),
+ "+c" (control), "+d" (input_address),
+ KVM_ASM_SAFE_OUTPUTS(vector, error_code)
+ : [output_address] "r"(output_address),
+ "a" (-EFAULT)
+ : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS);
+ return vector;
+}
+
+/* Issue a Hyper-V hypercall and assert that it succeeded. */
+static inline void hyperv_hypercall(u64 control, vm_vaddr_t input_address,
+ vm_vaddr_t output_address)
+{
+ uint64_t hv_status;
+ uint8_t vector;
+
+ vector = __hyperv_hypercall(control, input_address, output_address, &hv_status);
+
+ GUEST_ASSERT(!vector);
+ GUEST_ASSERT((hv_status & 0xffff) == 0);
+}
+
+/* Write 'Fast' hypercall input 'data' to the first 'n_sse_regs' SSE regs */
+static inline void hyperv_write_xmm_input(void *data, int n_sse_regs)
+{
+ int i;
+
+ for (i = 0; i < n_sse_regs; i++)
+ write_sse_reg(i, (sse128_t *)(data + sizeof(sse128_t) * i));
+}
+
+/* Proper HV_X64_MSR_GUEST_OS_ID value */
+#define HYPERV_LINUX_OS_ID ((u64)0x8100 << 48)
+
+#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
+ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+struct hv_nested_enlightenments_control {
+ struct {
+ __u32 directhypercall:1;
+ __u32 reserved:31;
+ } features;
+ struct {
+ __u32 reserved;
+ } hypercallControls;
+} __packed;
+
+/* Define virtual processor assist page structure. */
+struct hv_vp_assist_page {
+ __u32 apic_assist;
+ __u32 reserved1;
+ __u64 vtl_control[3];
+ struct hv_nested_enlightenments_control nested_control;
+ __u8 enlighten_vmentry;
+ __u8 reserved2[7];
+ __u64 current_nested_vmcs;
+} __packed;
+
+extern struct hv_vp_assist_page *current_vp_assist;
+
+int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist);
+
+struct hyperv_test_pages {
+ /* VP assist page */
+ void *vp_assist_hva;
+ uint64_t vp_assist_gpa;
+ void *vp_assist;
+
+ /* Partition assist page */
+ void *partition_assist_hva;
+ uint64_t partition_assist_gpa;
+ void *partition_assist;
+
+ /* Enlightened VMCS */
+ void *enlightened_vmcs_hva;
+ uint64_t enlightened_vmcs_gpa;
+ void *enlightened_vmcs;
+};
+
+struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm,
+ vm_vaddr_t *p_hv_pages_gva);
+
+/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */
+#define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0)
+
+#endif /* !SELFTEST_KVM_HYPERV_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/mce.h b/tools/testing/selftests/kvm/include/x86_64/mce.h
new file mode 100644
index 0000000000..6119321f3f
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/mce.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/mce.h
+ *
+ * Copyright (C) 2022, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_MCE_H
+#define SELFTEST_KVM_MCE_H
+
+#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */
+#define MCG_SER_P BIT_ULL(24) /* MCA recovery/new status bits */
+#define MCG_LMCE_P BIT_ULL(27) /* Local machine check supported */
+#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */
+#define KVM_MAX_MCE_BANKS 32
+#define MCG_CAP_BANKS_MASK 0xff /* Bit 0-7 of the MCG_CAP register are #banks */
+#define MCI_STATUS_VAL (1ULL << 63) /* valid error */
+#define MCI_STATUS_UC (1ULL << 61) /* uncorrected error */
+#define MCI_STATUS_EN (1ULL << 60) /* error enabled */
+#define MCI_STATUS_MISCV (1ULL << 59) /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1ULL << 58) /* addr reg. valid */
+#define MCM_ADDR_PHYS 2 /* physical address */
+#define MCI_CTL2_CMCI_EN BIT_ULL(30)
+
+#endif /* SELFTEST_KVM_MCE_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
new file mode 100644
index 0000000000..25bc61dac5
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -0,0 +1,1259 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/processor.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include <assert.h>
+#include <stdint.h>
+#include <syscall.h>
+
+#include <asm/msr-index.h>
+#include <asm/prctl.h>
+
+#include <linux/stringify.h>
+
+#include "../kvm_util.h"
+
+extern bool host_cpu_is_intel;
+extern bool host_cpu_is_amd;
+
+#define NMI_VECTOR 0x02
+
+#define X86_EFLAGS_FIXED (1u << 1)
+
+#define X86_CR4_VME (1ul << 0)
+#define X86_CR4_PVI (1ul << 1)
+#define X86_CR4_TSD (1ul << 2)
+#define X86_CR4_DE (1ul << 3)
+#define X86_CR4_PSE (1ul << 4)
+#define X86_CR4_PAE (1ul << 5)
+#define X86_CR4_MCE (1ul << 6)
+#define X86_CR4_PGE (1ul << 7)
+#define X86_CR4_PCE (1ul << 8)
+#define X86_CR4_OSFXSR (1ul << 9)
+#define X86_CR4_OSXMMEXCPT (1ul << 10)
+#define X86_CR4_UMIP (1ul << 11)
+#define X86_CR4_LA57 (1ul << 12)
+#define X86_CR4_VMXE (1ul << 13)
+#define X86_CR4_SMXE (1ul << 14)
+#define X86_CR4_FSGSBASE (1ul << 16)
+#define X86_CR4_PCIDE (1ul << 17)
+#define X86_CR4_OSXSAVE (1ul << 18)
+#define X86_CR4_SMEP (1ul << 20)
+#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_PT BIT_ULL(8)
+#define XFEATURE_MASK_PKRU BIT_ULL(9)
+#define XFEATURE_MASK_PASID BIT_ULL(10)
+#define XFEATURE_MASK_CET_USER BIT_ULL(11)
+#define XFEATURE_MASK_CET_KERNEL BIT_ULL(12)
+#define XFEATURE_MASK_LBR BIT_ULL(15)
+#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,
+ KVM_CPUID_EBX,
+ KVM_CPUID_ECX,
+ KVM_CPUID_EDX
+};
+
+/*
+ * Pack the information into a 64-bit value so that each X86_FEATURE_XXX can be
+ * passed by value with no overhead.
+ */
+struct kvm_x86_cpu_feature {
+ u32 function;
+ u16 index;
+ u8 reg;
+ u8 bit;
+};
+#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \
+({ \
+ struct kvm_x86_cpu_feature feature = { \
+ .function = fn, \
+ .index = idx, \
+ .reg = KVM_CPUID_##gpr, \
+ .bit = __bit, \
+ }; \
+ \
+ 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; \
+})
+
+/*
+ * Basic Leafs, a.k.a. Intel defined
+ */
+#define X86_FEATURE_MWAIT KVM_X86_CPU_FEATURE(0x1, 0, ECX, 3)
+#define X86_FEATURE_VMX KVM_X86_CPU_FEATURE(0x1, 0, ECX, 5)
+#define X86_FEATURE_SMX KVM_X86_CPU_FEATURE(0x1, 0, ECX, 6)
+#define X86_FEATURE_PDCM KVM_X86_CPU_FEATURE(0x1, 0, ECX, 15)
+#define X86_FEATURE_PCID KVM_X86_CPU_FEATURE(0x1, 0, ECX, 17)
+#define X86_FEATURE_X2APIC KVM_X86_CPU_FEATURE(0x1, 0, ECX, 21)
+#define X86_FEATURE_MOVBE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 22)
+#define X86_FEATURE_TSC_DEADLINE_TIMER KVM_X86_CPU_FEATURE(0x1, 0, ECX, 24)
+#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)
+#define X86_FEATURE_CLFLUSH KVM_X86_CPU_FEATURE(0x1, 0, EDX, 19)
+#define X86_FEATURE_XMM KVM_X86_CPU_FEATURE(0x1, 0, EDX, 25)
+#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)
+#define X86_FEATURE_RTM KVM_X86_CPU_FEATURE(0x7, 0, EBX, 11)
+#define X86_FEATURE_MPX KVM_X86_CPU_FEATURE(0x7, 0, EBX, 14)
+#define X86_FEATURE_SMAP KVM_X86_CPU_FEATURE(0x7, 0, EBX, 20)
+#define X86_FEATURE_PCOMMIT KVM_X86_CPU_FEATURE(0x7, 0, EBX, 22)
+#define X86_FEATURE_CLFLUSHOPT KVM_X86_CPU_FEATURE(0x7, 0, EBX, 23)
+#define X86_FEATURE_CLWB KVM_X86_CPU_FEATURE(0x7, 0, EBX, 24)
+#define X86_FEATURE_UMIP KVM_X86_CPU_FEATURE(0x7, 0, ECX, 2)
+#define X86_FEATURE_PKU KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3)
+#define X86_FEATURE_OSPKE KVM_X86_CPU_FEATURE(0x7, 0, ECX, 4)
+#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)
+#define X86_FEATURE_SPEC_CTRL KVM_X86_CPU_FEATURE(0x7, 0, EDX, 26)
+#define X86_FEATURE_ARCH_CAPABILITIES KVM_X86_CPU_FEATURE(0x7, 0, EDX, 29)
+#define X86_FEATURE_PKS KVM_X86_CPU_FEATURE(0x7, 0, ECX, 31)
+#define X86_FEATURE_XTILECFG KVM_X86_CPU_FEATURE(0xD, 0, EAX, 17)
+#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
+ */
+#define X86_FEATURE_SVM KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 2)
+#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)
+#define X86_FEATURE_LM KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 29)
+#define X86_FEATURE_INVTSC KVM_X86_CPU_FEATURE(0x80000007, 0, EDX, 8)
+#define X86_FEATURE_RDPRU KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 4)
+#define X86_FEATURE_AMD_IBPB KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 12)
+#define X86_FEATURE_NPT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 0)
+#define X86_FEATURE_LBRV KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 1)
+#define X86_FEATURE_NRIPS KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 3)
+#define X86_FEATURE_TSCRATEMSR KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 4)
+#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_SEV KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1)
+#define X86_FEATURE_SEV_ES KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3)
+
+/*
+ * KVM defined paravirt features.
+ */
+#define X86_FEATURE_KVM_CLOCKSOURCE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 0)
+#define X86_FEATURE_KVM_NOP_IO_DELAY KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 1)
+#define X86_FEATURE_KVM_MMU_OP KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 2)
+#define X86_FEATURE_KVM_CLOCKSOURCE2 KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 3)
+#define X86_FEATURE_KVM_ASYNC_PF KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 4)
+#define X86_FEATURE_KVM_STEAL_TIME KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 5)
+#define X86_FEATURE_KVM_PV_EOI KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 6)
+#define X86_FEATURE_KVM_PV_UNHALT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 7)
+/* Bit 8 apparently isn't used?!?! */
+#define X86_FEATURE_KVM_PV_TLB_FLUSH KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 9)
+#define X86_FEATURE_KVM_ASYNC_PF_VMEXIT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 10)
+#define X86_FEATURE_KVM_PV_SEND_IPI KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 11)
+#define X86_FEATURE_KVM_POLL_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 12)
+#define X86_FEATURE_KVM_PV_SCHED_YIELD KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 13)
+#define X86_FEATURE_KVM_ASYNC_PF_INT KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 14)
+#define X86_FEATURE_KVM_MSI_EXT_DEST_ID KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 15)
+#define X86_FEATURE_KVM_HC_MAP_GPA_RANGE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 16)
+#define X86_FEATURE_KVM_MIGRATION_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 17)
+
+/*
+ * Same idea as X86_FEATURE_XXX, but X86_PROPERTY_XXX retrieves a multi-bit
+ * value/property as opposed to a single-bit feature. Again, pack the info
+ * into a 64-bit value to pass by value with no overhead.
+ */
+struct kvm_x86_cpu_property {
+ u32 function;
+ u8 index;
+ u8 reg;
+ u8 lo_bit;
+ u8 hi_bit;
+};
+#define KVM_X86_CPU_PROPERTY(fn, idx, gpr, low_bit, high_bit) \
+({ \
+ struct kvm_x86_cpu_property property = { \
+ .function = fn, \
+ .index = idx, \
+ .reg = KVM_CPUID_##gpr, \
+ .lo_bit = low_bit, \
+ .hi_bit = high_bit, \
+ }; \
+ \
+ 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; \
+})
+
+#define X86_PROPERTY_MAX_BASIC_LEAF KVM_X86_CPU_PROPERTY(0, 0, EAX, 0, 31)
+#define X86_PROPERTY_PMU_VERSION KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 0, 7)
+#define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
+#define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23)
+#define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
+#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7)
+#define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31)
+#define X86_PROPERTY_PMU_NR_FIXED_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4)
+#define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12)
+
+#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)
+#define X86_PROPERTY_AMX_NR_TILE_REGS KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 16, 31)
+#define X86_PROPERTY_AMX_MAX_ROWS KVM_X86_CPU_PROPERTY(0x1d, 1, ECX, 0, 15)
+
+#define X86_PROPERTY_MAX_KVM_LEAF KVM_X86_CPU_PROPERTY(0x40000000, 0, EAX, 0, 31)
+
+#define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31)
+#define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7)
+#define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15)
+#define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11)
+
+#define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31)
+
+/*
+ * Intel's architectural PMU events are bizarre. They have a "feature" bit
+ * that indicates the feature is _not_ supported, and a property that states
+ * the length of the bit mask of unsupported features. A feature is supported
+ * if the size of the bit mask is larger than the "unavailable" bit, and said
+ * bit is not set.
+ *
+ * Wrap the "unavailable" feature to simplify checking whether or not a given
+ * architectural event is supported.
+ */
+struct kvm_x86_pmu_feature {
+ struct kvm_x86_cpu_feature anti_feature;
+};
+#define KVM_X86_PMU_FEATURE(name, __bit) \
+({ \
+ struct kvm_x86_pmu_feature feature = { \
+ .anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit), \
+ }; \
+ \
+ feature; \
+})
+
+#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5)
+
+static inline unsigned int x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+static inline unsigned int x86_model(unsigned int eax)
+{
+ return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
+}
+
+/* Page table bitfield declarations */
+#define PTE_PRESENT_MASK BIT_ULL(0)
+#define PTE_WRITABLE_MASK BIT_ULL(1)
+#define PTE_USER_MASK BIT_ULL(2)
+#define PTE_ACCESSED_MASK BIT_ULL(5)
+#define PTE_DIRTY_MASK BIT_ULL(6)
+#define PTE_LARGE_MASK BIT_ULL(7)
+#define PTE_GLOBAL_MASK BIT_ULL(8)
+#define PTE_NX_MASK BIT_ULL(63)
+
+#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12)
+
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1ULL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1) & PHYSICAL_PAGE_MASK)
+
+#define HUGEPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9))
+#define HUGEPAGE_SIZE(x) (1UL << HUGEPAGE_SHIFT(x))
+#define HUGEPAGE_MASK(x) (~(HUGEPAGE_SIZE(x) - 1) & PHYSICAL_PAGE_MASK)
+
+#define PTE_GET_PA(pte) ((pte) & PHYSICAL_PAGE_MASK)
+#define PTE_GET_PFN(pte) (PTE_GET_PA(pte) >> PAGE_SHIFT)
+
+/* General Registers in 64-Bit Mode */
+struct gpr64_regs {
+ u64 rax;
+ u64 rcx;
+ u64 rdx;
+ u64 rbx;
+ u64 rsp;
+ u64 rbp;
+ u64 rsi;
+ u64 rdi;
+ u64 r8;
+ u64 r9;
+ u64 r10;
+ u64 r11;
+ u64 r12;
+ u64 r13;
+ u64 r14;
+ u64 r15;
+};
+
+struct desc64 {
+ uint16_t limit0;
+ uint16_t base0;
+ unsigned base1:8, type:4, s:1, dpl:2, p:1;
+ unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
+ uint32_t base3;
+ uint32_t zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+ uint16_t size;
+ uint64_t address;
+} __attribute__((packed));
+
+struct kvm_x86_state {
+ struct kvm_xsave *xsave;
+ struct kvm_vcpu_events events;
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ struct kvm_xcrs xcrs;
+ struct kvm_sregs sregs;
+ struct kvm_debugregs debugregs;
+ union {
+ struct kvm_nested_state nested;
+ char nested_[16384];
+ };
+ struct kvm_msrs msrs;
+};
+
+static inline uint64_t get_desc64_base(const struct desc64 *desc)
+{
+ return ((uint64_t)desc->base3 << 32) |
+ (desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
+}
+
+static inline uint64_t rdtsc(void)
+{
+ uint32_t eax, edx;
+ uint64_t tsc_val;
+ /*
+ * The lfence is to wait (on Intel CPUs) until all previous
+ * instructions have been executed. If software requires RDTSC to be
+ * executed prior to execution of any subsequent instruction, it can
+ * execute LFENCE immediately after RDTSC
+ */
+ __asm__ __volatile__("lfence; rdtsc; lfence" : "=a"(eax), "=d"(edx));
+ tsc_val = ((uint64_t)edx) << 32 | eax;
+ return tsc_val;
+}
+
+static inline uint64_t rdtscp(uint32_t *aux)
+{
+ uint32_t eax, edx;
+
+ __asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
+ return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdmsr(uint32_t msr)
+{
+ uint32_t a, d;
+
+ __asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+ return a | ((uint64_t) d << 32);
+}
+
+static inline void wrmsr(uint32_t msr, uint64_t value)
+{
+ uint32_t a = value;
+ uint32_t d = value >> 32;
+
+ __asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+
+static inline uint16_t inw(uint16_t port)
+{
+ uint16_t tmp;
+
+ __asm__ __volatile__("in %%dx, %%ax"
+ : /* output */ "=a" (tmp)
+ : /* input */ "d" (port));
+
+ return tmp;
+}
+
+static inline uint16_t get_es(void)
+{
+ uint16_t es;
+
+ __asm__ __volatile__("mov %%es, %[es]"
+ : /* output */ [es]"=rm"(es));
+ return es;
+}
+
+static inline uint16_t get_cs(void)
+{
+ uint16_t cs;
+
+ __asm__ __volatile__("mov %%cs, %[cs]"
+ : /* output */ [cs]"=rm"(cs));
+ return cs;
+}
+
+static inline uint16_t get_ss(void)
+{
+ uint16_t ss;
+
+ __asm__ __volatile__("mov %%ss, %[ss]"
+ : /* output */ [ss]"=rm"(ss));
+ return ss;
+}
+
+static inline uint16_t get_ds(void)
+{
+ uint16_t ds;
+
+ __asm__ __volatile__("mov %%ds, %[ds]"
+ : /* output */ [ds]"=rm"(ds));
+ return ds;
+}
+
+static inline uint16_t get_fs(void)
+{
+ uint16_t fs;
+
+ __asm__ __volatile__("mov %%fs, %[fs]"
+ : /* output */ [fs]"=rm"(fs));
+ return fs;
+}
+
+static inline uint16_t get_gs(void)
+{
+ uint16_t gs;
+
+ __asm__ __volatile__("mov %%gs, %[gs]"
+ : /* output */ [gs]"=rm"(gs));
+ return gs;
+}
+
+static inline uint16_t get_tr(void)
+{
+ uint16_t tr;
+
+ __asm__ __volatile__("str %[tr]"
+ : /* output */ [tr]"=rm"(tr));
+ return tr;
+}
+
+static inline uint64_t get_cr0(void)
+{
+ uint64_t cr0;
+
+ __asm__ __volatile__("mov %%cr0, %[cr0]"
+ : /* output */ [cr0]"=r"(cr0));
+ return cr0;
+}
+
+static inline uint64_t get_cr3(void)
+{
+ uint64_t cr3;
+
+ __asm__ __volatile__("mov %%cr3, %[cr3]"
+ : /* output */ [cr3]"=r"(cr3));
+ return cr3;
+}
+
+static inline uint64_t get_cr4(void)
+{
+ uint64_t cr4;
+
+ __asm__ __volatile__("mov %%cr4, %[cr4]"
+ : /* output */ [cr4]"=r"(cr4));
+ return cr4;
+}
+
+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 void wrpkru(u32 pkru)
+{
+ /* Note, ECX and EDX are architecturally required to be '0'. */
+ asm volatile(".byte 0x0f,0x01,0xef\n\t"
+ : : "a" (pkru), "c"(0), "d"(0));
+}
+
+static inline struct desc_ptr get_gdt(void)
+{
+ struct desc_ptr gdt;
+ __asm__ __volatile__("sgdt %[gdt]"
+ : /* output */ [gdt]"=m"(gdt));
+ return gdt;
+}
+
+static inline struct desc_ptr get_idt(void)
+{
+ struct desc_ptr idt;
+ __asm__ __volatile__("sidt %[idt]"
+ : /* output */ [idt]"=m"(idt));
+ return idt;
+}
+
+static inline void outl(uint16_t port, uint32_t value)
+{
+ __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
+static inline void __cpuid(uint32_t function, uint32_t index,
+ uint32_t *eax, uint32_t *ebx,
+ uint32_t *ecx, uint32_t *edx)
+{
+ *eax = function;
+ *ecx = index;
+
+ asm volatile("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (*eax), "2" (*ecx)
+ : "memory");
+}
+
+static inline void cpuid(uint32_t function,
+ uint32_t *eax, uint32_t *ebx,
+ uint32_t *ecx, uint32_t *edx)
+{
+ return __cpuid(function, 0, eax, ebx, ecx, edx);
+}
+
+static inline uint32_t this_cpu_fms(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+ return eax;
+}
+
+static inline uint32_t this_cpu_family(void)
+{
+ return x86_family(this_cpu_fms());
+}
+
+static inline uint32_t this_cpu_model(void)
+{
+ return x86_model(this_cpu_fms());
+}
+
+static inline bool this_cpu_vendor_string_is(const char *vendor)
+{
+ const uint32_t *chunk = (const uint32_t *)vendor;
+ uint32_t eax, ebx, ecx, edx;
+
+ cpuid(0, &eax, &ebx, &ecx, &edx);
+ return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
+}
+
+static inline bool this_cpu_is_intel(void)
+{
+ return this_cpu_vendor_string_is("GenuineIntel");
+}
+
+/*
+ * Exclude early K5 samples with a vendor string of "AMDisbetter!"
+ */
+static inline bool this_cpu_is_amd(void)
+{
+ return this_cpu_vendor_string_is("AuthenticAMD");
+}
+
+static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index,
+ uint8_t reg, uint8_t lo, uint8_t hi)
+{
+ uint32_t gprs[4];
+
+ __cpuid(function, index,
+ &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX],
+ &gprs[KVM_CPUID_ECX], &gprs[KVM_CPUID_EDX]);
+
+ return (gprs[reg] & GENMASK(hi, lo)) >> lo;
+}
+
+static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature)
+{
+ return __this_cpu_has(feature.function, feature.index,
+ feature.reg, feature.bit, feature.bit);
+}
+
+static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property)
+{
+ return __this_cpu_has(property.function, property.index,
+ property.reg, property.lo_bit, property.hi_bit);
+}
+
+static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property)
+{
+ uint32_t max_leaf;
+
+ switch (property.function & 0xc0000000) {
+ case 0:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF);
+ break;
+ case 0x40000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF);
+ break;
+ case 0x80000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_EXT_LEAF);
+ break;
+ case 0xc0000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF);
+ }
+ return max_leaf >= property.function;
+}
+
+static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature)
+{
+ uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+
+ return nr_bits > feature.anti_feature.bit &&
+ !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]; })
+#define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; })
+
+static inline void read_sse_reg(int reg, sse128_t *data)
+{
+ switch (reg) {
+ case 0:
+ asm("movdqa %%xmm0, %0" : "=m"(*data));
+ break;
+ case 1:
+ asm("movdqa %%xmm1, %0" : "=m"(*data));
+ break;
+ case 2:
+ asm("movdqa %%xmm2, %0" : "=m"(*data));
+ break;
+ case 3:
+ asm("movdqa %%xmm3, %0" : "=m"(*data));
+ break;
+ case 4:
+ asm("movdqa %%xmm4, %0" : "=m"(*data));
+ break;
+ case 5:
+ asm("movdqa %%xmm5, %0" : "=m"(*data));
+ break;
+ case 6:
+ asm("movdqa %%xmm6, %0" : "=m"(*data));
+ break;
+ case 7:
+ asm("movdqa %%xmm7, %0" : "=m"(*data));
+ break;
+ default:
+ BUG();
+ }
+}
+
+static inline void write_sse_reg(int reg, const sse128_t *data)
+{
+ switch (reg) {
+ case 0:
+ asm("movdqa %0, %%xmm0" : : "m"(*data));
+ break;
+ case 1:
+ asm("movdqa %0, %%xmm1" : : "m"(*data));
+ break;
+ case 2:
+ asm("movdqa %0, %%xmm2" : : "m"(*data));
+ break;
+ case 3:
+ asm("movdqa %0, %%xmm3" : : "m"(*data));
+ break;
+ case 4:
+ asm("movdqa %0, %%xmm4" : : "m"(*data));
+ break;
+ case 5:
+ asm("movdqa %0, %%xmm5" : : "m"(*data));
+ break;
+ case 6:
+ asm("movdqa %0, %%xmm6" : : "m"(*data));
+ break;
+ case 7:
+ asm("movdqa %0, %%xmm7" : : "m"(*data));
+ break;
+ default:
+ BUG();
+ }
+}
+
+static inline void cpu_relax(void)
+{
+ asm volatile("rep; nop" ::: "memory");
+}
+
+#define ud2() \
+ __asm__ __volatile__( \
+ "ud2\n" \
+ )
+
+#define hlt() \
+ __asm__ __volatile__( \
+ "hlt\n" \
+ )
+
+struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu);
+void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state);
+void kvm_x86_state_cleanup(struct kvm_x86_state *state);
+
+const struct kvm_msr_list *kvm_get_msr_index_list(void);
+const struct kvm_msr_list *kvm_get_feature_msr_index_list(void);
+bool kvm_msr_is_in_save_restore_list(uint32_t msr_index);
+uint64_t kvm_get_feature_msr(uint64_t msr_index);
+
+static inline void vcpu_msrs_get(struct kvm_vcpu *vcpu,
+ struct kvm_msrs *msrs)
+{
+ int r = __vcpu_ioctl(vcpu, KVM_GET_MSRS, msrs);
+
+ TEST_ASSERT(r == msrs->nmsrs,
+ "KVM_GET_MSRS failed, r: %i (failed on MSR %x)",
+ r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index);
+}
+static inline void vcpu_msrs_set(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs)
+{
+ int r = __vcpu_ioctl(vcpu, KVM_SET_MSRS, msrs);
+
+ TEST_ASSERT(r == msrs->nmsrs,
+ "KVM_SET_MSRS failed, r: %i (failed on MSR %x)",
+ r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index);
+}
+static inline void vcpu_debugregs_get(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *debugregs)
+{
+ vcpu_ioctl(vcpu, KVM_GET_DEBUGREGS, debugregs);
+}
+static inline void vcpu_debugregs_set(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *debugregs)
+{
+ vcpu_ioctl(vcpu, KVM_SET_DEBUGREGS, debugregs);
+}
+static inline void vcpu_xsave_get(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *xsave)
+{
+ vcpu_ioctl(vcpu, KVM_GET_XSAVE, xsave);
+}
+static inline void vcpu_xsave2_get(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *xsave)
+{
+ vcpu_ioctl(vcpu, KVM_GET_XSAVE2, xsave);
+}
+static inline void vcpu_xsave_set(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *xsave)
+{
+ vcpu_ioctl(vcpu, KVM_SET_XSAVE, xsave);
+}
+static inline void vcpu_xcrs_get(struct kvm_vcpu *vcpu,
+ struct kvm_xcrs *xcrs)
+{
+ vcpu_ioctl(vcpu, KVM_GET_XCRS, xcrs);
+}
+static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs)
+{
+ vcpu_ioctl(vcpu, KVM_SET_XCRS, xcrs);
+}
+
+const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,
+ uint32_t function, uint32_t index);
+const struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
+const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu);
+
+static inline uint32_t kvm_cpu_fms(void)
+{
+ return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax;
+}
+
+static inline uint32_t kvm_cpu_family(void)
+{
+ return x86_family(kvm_cpu_fms());
+}
+
+static inline uint32_t kvm_cpu_model(void)
+{
+ return x86_model(kvm_cpu_fms());
+}
+
+bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid,
+ struct kvm_x86_cpu_feature feature);
+
+static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature)
+{
+ return kvm_cpuid_has(kvm_get_supported_cpuid(), feature);
+}
+
+uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid,
+ struct kvm_x86_cpu_property property);
+
+static inline uint32_t kvm_cpu_property(struct kvm_x86_cpu_property property)
+{
+ return kvm_cpuid_property(kvm_get_supported_cpuid(), property);
+}
+
+static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property)
+{
+ uint32_t max_leaf;
+
+ switch (property.function & 0xc0000000) {
+ case 0:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF);
+ break;
+ case 0x40000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_KVM_LEAF);
+ break;
+ case 0x80000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_EXT_LEAF);
+ break;
+ case 0xc0000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF);
+ }
+ return max_leaf >= property.function;
+}
+
+static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature)
+{
+ uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+
+ return nr_bits > feature.anti_feature.bit &&
+ !kvm_cpu_has(feature.anti_feature);
+}
+
+static __always_inline uint64_t kvm_cpu_supported_xcr0(void)
+{
+ if (!kvm_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO))
+ return 0;
+
+ return kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) |
+ ((uint64_t)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32);
+}
+
+static inline size_t kvm_cpuid2_size(int nr_entries)
+{
+ return sizeof(struct kvm_cpuid2) +
+ sizeof(struct kvm_cpuid_entry2) * nr_entries;
+}
+
+/*
+ * Allocate a "struct kvm_cpuid2* instance, with the 0-length arrary of
+ * entries sized to hold @nr_entries. The caller is responsible for freeing
+ * the struct.
+ */
+static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries)
+{
+ struct kvm_cpuid2 *cpuid;
+
+ cpuid = malloc(kvm_cpuid2_size(nr_entries));
+ TEST_ASSERT(cpuid, "-ENOMEM when allocating kvm_cpuid2");
+
+ cpuid->nent = nr_entries;
+
+ return cpuid;
+}
+
+void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid);
+void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu);
+
+static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu,
+ uint32_t function,
+ uint32_t index)
+{
+ return (struct kvm_cpuid_entry2 *)get_cpuid_entry(vcpu->cpuid,
+ function, index);
+}
+
+static inline struct kvm_cpuid_entry2 *vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu,
+ uint32_t function)
+{
+ return __vcpu_get_cpuid_entry(vcpu, function, 0);
+}
+
+static inline int __vcpu_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ int r;
+
+ TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first");
+ r = __vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid);
+ if (r)
+ return r;
+
+ /* On success, refresh the cache to pick up adjustments made by KVM. */
+ vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid);
+ return 0;
+}
+
+static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first");
+ vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid);
+
+ /* Refresh the cache to pick up adjustments made by KVM. */
+ vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid);
+}
+
+void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr);
+
+void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function);
+void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu,
+ struct kvm_x86_cpu_feature feature,
+ bool set);
+
+static inline void vcpu_set_cpuid_feature(struct kvm_vcpu *vcpu,
+ struct kvm_x86_cpu_feature feature)
+{
+ vcpu_set_or_clear_cpuid_feature(vcpu, feature, true);
+
+}
+
+static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu,
+ struct kvm_x86_cpu_feature feature)
+{
+ vcpu_set_or_clear_cpuid_feature(vcpu, feature, false);
+}
+
+uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index);
+int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value);
+
+/*
+ * Assert on an MSR access(es) and pretty print the MSR name when possible.
+ * Note, the caller provides the stringified name so that the name of macro is
+ * printed, not the value the macro resolves to (due to macro expansion).
+ */
+#define TEST_ASSERT_MSR(cond, fmt, msr, str, args...) \
+do { \
+ if (__builtin_constant_p(msr)) { \
+ TEST_ASSERT(cond, fmt, str, args); \
+ } else if (!(cond)) { \
+ char buf[16]; \
+ \
+ snprintf(buf, sizeof(buf), "MSR 0x%x", msr); \
+ TEST_ASSERT(cond, fmt, buf, args); \
+ } \
+} while (0)
+
+/*
+ * Returns true if KVM should return the last written value when reading an MSR
+ * from userspace, e.g. the MSR isn't a command MSR, doesn't emulate state that
+ * is changing, etc. This is NOT an exhaustive list! The intent is to filter
+ * out MSRs that are not durable _and_ that a selftest wants to write.
+ */
+static inline bool is_durable_msr(uint32_t msr)
+{
+ return msr != MSR_IA32_TSC;
+}
+
+#define vcpu_set_msr(vcpu, msr, val) \
+do { \
+ uint64_t r, v = val; \
+ \
+ TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \
+ "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \
+ if (!is_durable_msr(msr)) \
+ break; \
+ r = vcpu_get_msr(vcpu, msr); \
+ TEST_ASSERT_MSR(r == v, "Set %s to '0x%lx', got back '0x%lx'", msr, #msr, v, r);\
+} while (0)
+
+void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
+bool vm_is_unrestricted_guest(struct kvm_vm *vm);
+
+struct ex_regs {
+ uint64_t rax, rcx, rdx, rbx;
+ uint64_t rbp, rsi, rdi;
+ uint64_t r8, r9, r10, r11;
+ uint64_t r12, r13, r14, r15;
+ uint64_t vector;
+ uint64_t error_code;
+ uint64_t rip;
+ uint64_t cs;
+ uint64_t rflags;
+};
+
+struct idt_entry {
+ uint16_t offset0;
+ uint16_t selector;
+ uint16_t ist : 3;
+ uint16_t : 5;
+ uint16_t type : 4;
+ uint16_t : 1;
+ uint16_t dpl : 2;
+ uint16_t p : 1;
+ uint16_t offset1;
+ uint32_t offset2; uint32_t reserved;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *));
+
+/* If a toddler were to say "abracadabra". */
+#define KVM_EXCEPTION_MAGIC 0xabacadabaULL
+
+/*
+ * KVM selftest exception fixup uses registers to coordinate with the exception
+ * handler, versus the kernel's in-memory tables and KVM-Unit-Tests's in-memory
+ * per-CPU data. Using only registers avoids having to map memory into the
+ * guest, doesn't require a valid, stable GS.base, and reduces the risk of
+ * for recursive faults when accessing memory in the handler. The downside to
+ * using registers is that it restricts what registers can be used by the actual
+ * instruction. But, selftests are 64-bit only, making register* pressure a
+ * minor concern. Use r9-r11 as they are volatile, i.e. don't need to be saved
+ * by the callee, and except for r11 are not implicit parameters to any
+ * instructions. Ideally, fixup would use r8-r10 and thus avoid implicit
+ * parameters entirely, but Hyper-V's hypercall ABI uses r8 and testing Hyper-V
+ * is higher priority than testing non-faulting SYSCALL/SYSRET.
+ *
+ * Note, the fixup handler deliberately does not handle #DE, i.e. the vector
+ * is guaranteed to be non-zero on fault.
+ *
+ * REGISTER INPUTS:
+ * r9 = MAGIC
+ * r10 = RIP
+ * r11 = new RIP on fault
+ *
+ * REGISTER OUTPUTS:
+ * r9 = exception vector (non-zero)
+ * r10 = error code
+ */
+#define KVM_ASM_SAFE(insn) \
+ "mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \
+ "lea 1f(%%rip), %%r10\n\t" \
+ "lea 2f(%%rip), %%r11\n\t" \
+ "1: " insn "\n\t" \
+ "xor %%r9, %%r9\n\t" \
+ "2:\n\t" \
+ "mov %%r9b, %[vector]\n\t" \
+ "mov %%r10, %[error_code]\n\t"
+
+#define KVM_ASM_SAFE_OUTPUTS(v, ec) [vector] "=qm"(v), [error_code] "=rm"(ec)
+#define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11"
+
+#define kvm_asm_safe(insn, inputs...) \
+({ \
+ uint64_t ign_error_code; \
+ uint8_t vector; \
+ \
+ asm volatile(KVM_ASM_SAFE(insn) \
+ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \
+ : inputs \
+ : KVM_ASM_SAFE_CLOBBERS); \
+ vector; \
+})
+
+#define kvm_asm_safe_ec(insn, error_code, inputs...) \
+({ \
+ uint8_t vector; \
+ \
+ asm volatile(KVM_ASM_SAFE(insn) \
+ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \
+ : inputs \
+ : KVM_ASM_SAFE_CLOBBERS); \
+ vector; \
+})
+
+static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val)
+{
+ uint64_t error_code;
+ uint8_t vector;
+ uint32_t a, d;
+
+ asm volatile(KVM_ASM_SAFE("rdmsr")
+ : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code)
+ : "c"(msr)
+ : KVM_ASM_SAFE_CLOBBERS);
+
+ *val = (uint64_t)a | ((uint64_t)d << 32);
+ return vector;
+}
+
+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,
+ int *level);
+uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3);
+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(uint64_t xfeature, const char *name);
+
+#define vm_xsave_require_permission(xfeature) \
+ __vm_xsave_require_permission(xfeature, #xfeature)
+
+enum pg_level {
+ PG_LEVEL_NONE,
+ PG_LEVEL_4K,
+ PG_LEVEL_2M,
+ PG_LEVEL_1G,
+ PG_LEVEL_512G,
+ PG_LEVEL_NUM
+};
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+#define PG_SIZE_4K PG_LEVEL_SIZE(PG_LEVEL_4K)
+#define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
+#define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
+void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint64_t nr_bytes, int level);
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE (1UL<<0) /* Protection Enable */
+#define X86_CR0_MP (1UL<<1) /* Monitor Coprocessor */
+#define X86_CR0_EM (1UL<<2) /* Emulation */
+#define X86_CR0_TS (1UL<<3) /* Task Switched */
+#define X86_CR0_ET (1UL<<4) /* Extension Type */
+#define X86_CR0_NE (1UL<<5) /* Numeric Error */
+#define X86_CR0_WP (1UL<<16) /* Write Protect */
+#define X86_CR0_AM (1UL<<18) /* Alignment Mask */
+#define X86_CR0_NW (1UL<<29) /* Not Write-through */
+#define X86_CR0_CD (1UL<<30) /* Cache Disable */
+#define X86_CR0_PG (1UL<<31) /* Paging */
+
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+#define PFERR_PK_BIT 5
+#define PFERR_SGX_BIT 15
+#define PFERR_GUEST_FINAL_BIT 32
+#define PFERR_GUEST_PAGE_BIT 33
+#define PFERR_IMPLICIT_ACCESS_BIT 48
+
+#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
+#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
+#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
+#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
+#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h
new file mode 100644
index 0000000000..4803e10560
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm.h
+ * This is a copy of arch/x86/include/asm/svm.h
+ *
+ */
+
+#ifndef SELFTEST_KVM_SVM_H
+#define SELFTEST_KVM_SVM_H
+
+enum {
+ INTERCEPT_INTR,
+ INTERCEPT_NMI,
+ INTERCEPT_SMI,
+ INTERCEPT_INIT,
+ INTERCEPT_VINTR,
+ INTERCEPT_SELECTIVE_CR0,
+ INTERCEPT_STORE_IDTR,
+ INTERCEPT_STORE_GDTR,
+ INTERCEPT_STORE_LDTR,
+ INTERCEPT_STORE_TR,
+ INTERCEPT_LOAD_IDTR,
+ INTERCEPT_LOAD_GDTR,
+ INTERCEPT_LOAD_LDTR,
+ INTERCEPT_LOAD_TR,
+ INTERCEPT_RDTSC,
+ INTERCEPT_RDPMC,
+ INTERCEPT_PUSHF,
+ INTERCEPT_POPF,
+ INTERCEPT_CPUID,
+ INTERCEPT_RSM,
+ INTERCEPT_IRET,
+ INTERCEPT_INTn,
+ INTERCEPT_INVD,
+ INTERCEPT_PAUSE,
+ INTERCEPT_HLT,
+ INTERCEPT_INVLPG,
+ INTERCEPT_INVLPGA,
+ INTERCEPT_IOIO_PROT,
+ INTERCEPT_MSR_PROT,
+ INTERCEPT_TASK_SWITCH,
+ INTERCEPT_FERR_FREEZE,
+ INTERCEPT_SHUTDOWN,
+ INTERCEPT_VMRUN,
+ INTERCEPT_VMMCALL,
+ INTERCEPT_VMLOAD,
+ INTERCEPT_VMSAVE,
+ INTERCEPT_STGI,
+ INTERCEPT_CLGI,
+ INTERCEPT_SKINIT,
+ INTERCEPT_RDTSCP,
+ INTERCEPT_ICEBP,
+ INTERCEPT_WBINVD,
+ INTERCEPT_MONITOR,
+ INTERCEPT_MWAIT,
+ INTERCEPT_MWAIT_COND,
+ INTERCEPT_XSETBV,
+ INTERCEPT_RDPRU,
+};
+
+struct hv_vmcb_enlightenments {
+ struct __packed hv_enlightenments_control {
+ u32 nested_flush_hypercall:1;
+ u32 msr_bitmap:1;
+ u32 enlightened_npt_tlb: 1;
+ u32 reserved:29;
+ } __packed hv_enlightenments_control;
+ u32 hv_vp_id;
+ u64 hv_vm_id;
+ u64 partition_assist_page;
+ u64 reserved;
+} __packed;
+
+/*
+ * Hyper-V uses the software reserved clean bit in VMCB
+ */
+#define HV_VMCB_NESTED_ENLIGHTENMENTS (1U << 31)
+
+/* Synthetic VM-Exit */
+#define HV_SVM_EXITCODE_ENL 0xf0000000
+#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1)
+
+struct __attribute__ ((__packed__)) vmcb_control_area {
+ u32 intercept_cr;
+ u32 intercept_dr;
+ u32 intercept_exceptions;
+ u64 intercept;
+ u8 reserved_1[40];
+ u16 pause_filter_thresh;
+ u16 pause_filter_count;
+ u64 iopm_base_pa;
+ u64 msrpm_base_pa;
+ u64 tsc_offset;
+ u32 asid;
+ u8 tlb_ctl;
+ u8 reserved_2[3];
+ u32 int_ctl;
+ u32 int_vector;
+ u32 int_state;
+ u8 reserved_3[4];
+ u32 exit_code;
+ u32 exit_code_hi;
+ u64 exit_info_1;
+ u64 exit_info_2;
+ u32 exit_int_info;
+ u32 exit_int_info_err;
+ u64 nested_ctl;
+ u64 avic_vapic_bar;
+ u8 reserved_4[8];
+ u32 event_inj;
+ u32 event_inj_err;
+ u64 nested_cr3;
+ u64 virt_ext;
+ u32 clean;
+ u32 reserved_5;
+ u64 next_rip;
+ u8 insn_len;
+ u8 insn_bytes[15];
+ u64 avic_backing_page; /* Offset 0xe0 */
+ u8 reserved_6[8]; /* Offset 0xe8 */
+ u64 avic_logical_id; /* Offset 0xf0 */
+ u64 avic_physical_id; /* Offset 0xf8 */
+ u8 reserved_7[8];
+ u64 vmsa_pa; /* Used for an SEV-ES guest */
+ u8 reserved_8[720];
+ /*
+ * Offset 0x3e0, 32 bytes reserved
+ * for use by hypervisor/software.
+ */
+ union {
+ struct hv_vmcb_enlightenments hv_enlightenments;
+ u8 reserved_sw[32];
+ };
+};
+
+
+#define TLB_CONTROL_DO_NOTHING 0
+#define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
+
+#define V_TPR_MASK 0x0f
+
+#define V_IRQ_SHIFT 8
+#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+
+#define V_GIF_SHIFT 9
+#define V_GIF_MASK (1 << V_GIF_SHIFT)
+
+#define V_INTR_PRIO_SHIFT 16
+#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
+
+#define V_IGN_TPR_SHIFT 20
+#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+
+#define V_INTR_MASKING_SHIFT 24
+#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+
+#define V_GIF_ENABLE_SHIFT 25
+#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+
+#define AVIC_ENABLE_SHIFT 31
+#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
+
+#define LBR_CTL_ENABLE_MASK BIT_ULL(0)
+#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
+
+#define SVM_INTERRUPT_SHADOW_MASK 1
+
+#define SVM_IOIO_STR_SHIFT 2
+#define SVM_IOIO_REP_SHIFT 3
+#define SVM_IOIO_SIZE_SHIFT 4
+#define SVM_IOIO_ASIZE_SHIFT 7
+
+#define SVM_IOIO_TYPE_MASK 1
+#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
+#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
+#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
+#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
+
+#define SVM_VM_CR_VALID_MASK 0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+
+#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
+
+struct __attribute__ ((__packed__)) vmcb_seg {
+ u16 selector;
+ u16 attrib;
+ u32 limit;
+ u64 base;
+};
+
+struct __attribute__ ((__packed__)) vmcb_save_area {
+ struct vmcb_seg es;
+ struct vmcb_seg cs;
+ struct vmcb_seg ss;
+ struct vmcb_seg ds;
+ struct vmcb_seg fs;
+ struct vmcb_seg gs;
+ struct vmcb_seg gdtr;
+ struct vmcb_seg ldtr;
+ struct vmcb_seg idtr;
+ struct vmcb_seg tr;
+ u8 reserved_1[43];
+ u8 cpl;
+ u8 reserved_2[4];
+ u64 efer;
+ u8 reserved_3[112];
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u8 reserved_4[88];
+ u64 rsp;
+ u8 reserved_5[24];
+ u64 rax;
+ u64 star;
+ u64 lstar;
+ u64 cstar;
+ u64 sfmask;
+ u64 kernel_gs_base;
+ u64 sysenter_cs;
+ u64 sysenter_esp;
+ u64 sysenter_eip;
+ u64 cr2;
+ u8 reserved_6[32];
+ u64 g_pat;
+ u64 dbgctl;
+ u64 br_from;
+ u64 br_to;
+ u64 last_excp_from;
+ u64 last_excp_to;
+};
+
+struct __attribute__ ((__packed__)) vmcb {
+ struct vmcb_control_area control;
+ struct vmcb_save_area save;
+};
+
+#define SVM_VM_CR_SVM_DISABLE 4
+
+#define SVM_SELECTOR_S_SHIFT 4
+#define SVM_SELECTOR_DPL_SHIFT 5
+#define SVM_SELECTOR_P_SHIFT 7
+#define SVM_SELECTOR_AVL_SHIFT 8
+#define SVM_SELECTOR_L_SHIFT 9
+#define SVM_SELECTOR_DB_SHIFT 10
+#define SVM_SELECTOR_G_SHIFT 11
+
+#define SVM_SELECTOR_TYPE_MASK (0xf)
+#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
+#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
+#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
+#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
+#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
+#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
+#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
+
+#define SVM_SELECTOR_WRITE_MASK (1 << 1)
+#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
+#define SVM_SELECTOR_CODE_MASK (1 << 3)
+
+#define INTERCEPT_CR0_READ 0
+#define INTERCEPT_CR3_READ 3
+#define INTERCEPT_CR4_READ 4
+#define INTERCEPT_CR8_READ 8
+#define INTERCEPT_CR0_WRITE (16 + 0)
+#define INTERCEPT_CR3_WRITE (16 + 3)
+#define INTERCEPT_CR4_WRITE (16 + 4)
+#define INTERCEPT_CR8_WRITE (16 + 8)
+
+#define INTERCEPT_DR0_READ 0
+#define INTERCEPT_DR1_READ 1
+#define INTERCEPT_DR2_READ 2
+#define INTERCEPT_DR3_READ 3
+#define INTERCEPT_DR4_READ 4
+#define INTERCEPT_DR5_READ 5
+#define INTERCEPT_DR6_READ 6
+#define INTERCEPT_DR7_READ 7
+#define INTERCEPT_DR0_WRITE (16 + 0)
+#define INTERCEPT_DR1_WRITE (16 + 1)
+#define INTERCEPT_DR2_WRITE (16 + 2)
+#define INTERCEPT_DR3_WRITE (16 + 3)
+#define INTERCEPT_DR4_WRITE (16 + 4)
+#define INTERCEPT_DR5_WRITE (16 + 5)
+#define INTERCEPT_DR6_WRITE (16 + 6)
+#define INTERCEPT_DR7_WRITE (16 + 7)
+
+#define SVM_EVTINJ_VEC_MASK 0xff
+
+#define SVM_EVTINJ_TYPE_SHIFT 8
+#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_VALID (1 << 31)
+#define SVM_EVTINJ_VALID_ERR (1 << 11)
+
+#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK
+
+#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
+#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
+#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
+#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
+
+#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
+#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
+
+#define SVM_EXITINFO_REG_MASK 0x0F
+
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
+
+#endif /* SELFTEST_KVM_SVM_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
new file mode 100644
index 0000000000..044f0f872b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm_utils.h
+ * Header for nested SVM testing
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#ifndef SELFTEST_KVM_SVM_UTILS_H
+#define SELFTEST_KVM_SVM_UTILS_H
+
+#include <asm/svm.h>
+
+#include <stdint.h>
+#include "svm.h"
+#include "processor.h"
+
+struct svm_test_data {
+ /* VMCB */
+ struct vmcb *vmcb; /* gva */
+ void *vmcb_hva;
+ uint64_t vmcb_gpa;
+
+ /* host state-save area */
+ struct vmcb_save_area *save_area; /* gva */
+ void *save_area_hva;
+ uint64_t save_area_gpa;
+
+ /* MSR-Bitmap */
+ void *msr; /* gva */
+ void *msr_hva;
+ uint64_t msr_gpa;
+};
+
+static inline void vmmcall(void)
+{
+ /*
+ * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle
+ * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended
+ * use of this function is to exit to L1 from L2. Clobber all other
+ * GPRs as L1 doesn't correctly preserve them during vmexits.
+ */
+ __asm__ __volatile__("push %%rbp; vmmcall; pop %%rbp"
+ : : "a"(0xdeadbeef), "c"(0xbeefdead)
+ : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
+}
+
+#define stgi() \
+ __asm__ __volatile__( \
+ "stgi\n" \
+ )
+
+#define clgi() \
+ __asm__ __volatile__( \
+ "clgi\n" \
+ )
+
+struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva);
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp);
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa);
+
+int open_sev_dev_path_or_exit(void);
+
+#endif /* SELFTEST_KVM_SVM_UTILS_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h
new file mode 100644
index 0000000000..06b244bd06
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UCALL_H
+#define SELFTEST_KVM_UCALL_H
+
+#include "kvm_util_base.h"
+
+#define UCALL_EXIT_REASON KVM_EXIT_IO
+
+static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+}
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
new file mode 100644
index 0000000000..5f0c0a29c5
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -0,0 +1,577 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <asm/vmx.h>
+
+#include <stdint.h>
+#include "processor.h"
+#include "apic.h"
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_INTR_WINDOW_EXITING 0x00000004
+#define CPU_BASED_USE_TSC_OFFSETTING 0x00000008
+#define CPU_BASED_HLT_EXITING 0x00000080
+#define CPU_BASED_INVLPG_EXITING 0x00000200
+#define CPU_BASED_MWAIT_EXITING 0x00000400
+#define CPU_BASED_RDPMC_EXITING 0x00000800
+#define CPU_BASED_RDTSC_EXITING 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING 0x00008000
+#define CPU_BASED_CR3_STORE_EXITING 0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING 0x00080000
+#define CPU_BASED_CR8_STORE_EXITING 0x00100000
+#define CPU_BASED_TPR_SHADOW 0x00200000
+#define CPU_BASED_NMI_WINDOW_EXITING 0x00400000
+#define CPU_BASED_MOV_DR_EXITING 0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
+#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP 0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
+#define CPU_BASED_MONITOR_EXITING 0x20000000
+#define CPU_BASED_PAUSE_EXITING 0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
+#define SECONDARY_EXEC_DESC 0x00000004
+#define SECONDARY_EXEC_ENABLE_RDTSCP 0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000
+#define SECONDARY_EXEC_ENABLE_PML 0x00020000
+#define SECONDARY_EPT_VE 0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE 0x00100000
+#define SECONDARY_EXEC_TSC_SCALING 0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK 0x00000001
+#define PIN_BASED_NMI_EXITING 0x00000008
+#define PIN_BASED_VIRTUAL_NMIS 0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER 0x00000040
+#define PIN_BASED_POSTED_INTR 0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
+#define VM_EXIT_SAVE_IA32_PAT 0x00040000
+#define VM_EXIT_LOAD_IA32_PAT 0x00080000
+#define VM_EXIT_SAVE_IA32_EFER 0x00100000
+#define VM_EXIT_LOAD_IA32_EFER 0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000004
+#define VM_ENTRY_IA32E_MODE 0x00000200
+#define VM_ENTRY_SMM 0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT 0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER 0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA 0x00000020
+
+#define VMX_EPT_VPID_CAP_1G_PAGES 0x00020000
+#define VMX_EPT_VPID_CAP_AD_BITS 0x00200000
+
+#define EXIT_REASON_FAILED_VMENTRY 0x80000000
+
+enum vmcs_field {
+ VIRTUAL_PROCESSOR_ID = 0x00000000,
+ POSTED_INTR_NV = 0x00000002,
+ GUEST_ES_SELECTOR = 0x00000800,
+ GUEST_CS_SELECTOR = 0x00000802,
+ GUEST_SS_SELECTOR = 0x00000804,
+ GUEST_DS_SELECTOR = 0x00000806,
+ GUEST_FS_SELECTOR = 0x00000808,
+ GUEST_GS_SELECTOR = 0x0000080a,
+ GUEST_LDTR_SELECTOR = 0x0000080c,
+ GUEST_TR_SELECTOR = 0x0000080e,
+ GUEST_INTR_STATUS = 0x00000810,
+ GUEST_PML_INDEX = 0x00000812,
+ HOST_ES_SELECTOR = 0x00000c00,
+ HOST_CS_SELECTOR = 0x00000c02,
+ HOST_SS_SELECTOR = 0x00000c04,
+ HOST_DS_SELECTOR = 0x00000c06,
+ HOST_FS_SELECTOR = 0x00000c08,
+ HOST_GS_SELECTOR = 0x00000c0a,
+ HOST_TR_SELECTOR = 0x00000c0c,
+ IO_BITMAP_A = 0x00002000,
+ IO_BITMAP_A_HIGH = 0x00002001,
+ IO_BITMAP_B = 0x00002002,
+ IO_BITMAP_B_HIGH = 0x00002003,
+ MSR_BITMAP = 0x00002004,
+ MSR_BITMAP_HIGH = 0x00002005,
+ VM_EXIT_MSR_STORE_ADDR = 0x00002006,
+ VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007,
+ VM_EXIT_MSR_LOAD_ADDR = 0x00002008,
+ VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009,
+ VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a,
+ VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b,
+ PML_ADDRESS = 0x0000200e,
+ PML_ADDRESS_HIGH = 0x0000200f,
+ TSC_OFFSET = 0x00002010,
+ TSC_OFFSET_HIGH = 0x00002011,
+ VIRTUAL_APIC_PAGE_ADDR = 0x00002012,
+ VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013,
+ APIC_ACCESS_ADDR = 0x00002014,
+ APIC_ACCESS_ADDR_HIGH = 0x00002015,
+ POSTED_INTR_DESC_ADDR = 0x00002016,
+ POSTED_INTR_DESC_ADDR_HIGH = 0x00002017,
+ EPT_POINTER = 0x0000201a,
+ EPT_POINTER_HIGH = 0x0000201b,
+ EOI_EXIT_BITMAP0 = 0x0000201c,
+ EOI_EXIT_BITMAP0_HIGH = 0x0000201d,
+ EOI_EXIT_BITMAP1 = 0x0000201e,
+ EOI_EXIT_BITMAP1_HIGH = 0x0000201f,
+ EOI_EXIT_BITMAP2 = 0x00002020,
+ EOI_EXIT_BITMAP2_HIGH = 0x00002021,
+ EOI_EXIT_BITMAP3 = 0x00002022,
+ EOI_EXIT_BITMAP3_HIGH = 0x00002023,
+ VMREAD_BITMAP = 0x00002026,
+ VMREAD_BITMAP_HIGH = 0x00002027,
+ VMWRITE_BITMAP = 0x00002028,
+ VMWRITE_BITMAP_HIGH = 0x00002029,
+ XSS_EXIT_BITMAP = 0x0000202C,
+ XSS_EXIT_BITMAP_HIGH = 0x0000202D,
+ ENCLS_EXITING_BITMAP = 0x0000202E,
+ ENCLS_EXITING_BITMAP_HIGH = 0x0000202F,
+ TSC_MULTIPLIER = 0x00002032,
+ TSC_MULTIPLIER_HIGH = 0x00002033,
+ GUEST_PHYSICAL_ADDRESS = 0x00002400,
+ GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
+ VMCS_LINK_POINTER = 0x00002800,
+ VMCS_LINK_POINTER_HIGH = 0x00002801,
+ GUEST_IA32_DEBUGCTL = 0x00002802,
+ GUEST_IA32_DEBUGCTL_HIGH = 0x00002803,
+ GUEST_IA32_PAT = 0x00002804,
+ GUEST_IA32_PAT_HIGH = 0x00002805,
+ GUEST_IA32_EFER = 0x00002806,
+ GUEST_IA32_EFER_HIGH = 0x00002807,
+ GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+ GUEST_PDPTR0 = 0x0000280a,
+ GUEST_PDPTR0_HIGH = 0x0000280b,
+ GUEST_PDPTR1 = 0x0000280c,
+ GUEST_PDPTR1_HIGH = 0x0000280d,
+ GUEST_PDPTR2 = 0x0000280e,
+ GUEST_PDPTR2_HIGH = 0x0000280f,
+ GUEST_PDPTR3 = 0x00002810,
+ GUEST_PDPTR3_HIGH = 0x00002811,
+ GUEST_BNDCFGS = 0x00002812,
+ GUEST_BNDCFGS_HIGH = 0x00002813,
+ HOST_IA32_PAT = 0x00002c00,
+ HOST_IA32_PAT_HIGH = 0x00002c01,
+ HOST_IA32_EFER = 0x00002c02,
+ HOST_IA32_EFER_HIGH = 0x00002c03,
+ HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ HOST_IA32_PERF_GLOBAL_CTRL_HIGH = 0x00002c05,
+ PIN_BASED_VM_EXEC_CONTROL = 0x00004000,
+ CPU_BASED_VM_EXEC_CONTROL = 0x00004002,
+ EXCEPTION_BITMAP = 0x00004004,
+ PAGE_FAULT_ERROR_CODE_MASK = 0x00004006,
+ PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008,
+ CR3_TARGET_COUNT = 0x0000400a,
+ VM_EXIT_CONTROLS = 0x0000400c,
+ VM_EXIT_MSR_STORE_COUNT = 0x0000400e,
+ VM_EXIT_MSR_LOAD_COUNT = 0x00004010,
+ VM_ENTRY_CONTROLS = 0x00004012,
+ VM_ENTRY_MSR_LOAD_COUNT = 0x00004014,
+ VM_ENTRY_INTR_INFO_FIELD = 0x00004016,
+ VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018,
+ VM_ENTRY_INSTRUCTION_LEN = 0x0000401a,
+ TPR_THRESHOLD = 0x0000401c,
+ SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
+ PLE_GAP = 0x00004020,
+ PLE_WINDOW = 0x00004022,
+ VM_INSTRUCTION_ERROR = 0x00004400,
+ VM_EXIT_REASON = 0x00004402,
+ VM_EXIT_INTR_INFO = 0x00004404,
+ VM_EXIT_INTR_ERROR_CODE = 0x00004406,
+ IDT_VECTORING_INFO_FIELD = 0x00004408,
+ IDT_VECTORING_ERROR_CODE = 0x0000440a,
+ VM_EXIT_INSTRUCTION_LEN = 0x0000440c,
+ VMX_INSTRUCTION_INFO = 0x0000440e,
+ GUEST_ES_LIMIT = 0x00004800,
+ GUEST_CS_LIMIT = 0x00004802,
+ GUEST_SS_LIMIT = 0x00004804,
+ GUEST_DS_LIMIT = 0x00004806,
+ GUEST_FS_LIMIT = 0x00004808,
+ GUEST_GS_LIMIT = 0x0000480a,
+ GUEST_LDTR_LIMIT = 0x0000480c,
+ GUEST_TR_LIMIT = 0x0000480e,
+ GUEST_GDTR_LIMIT = 0x00004810,
+ GUEST_IDTR_LIMIT = 0x00004812,
+ GUEST_ES_AR_BYTES = 0x00004814,
+ GUEST_CS_AR_BYTES = 0x00004816,
+ GUEST_SS_AR_BYTES = 0x00004818,
+ GUEST_DS_AR_BYTES = 0x0000481a,
+ GUEST_FS_AR_BYTES = 0x0000481c,
+ GUEST_GS_AR_BYTES = 0x0000481e,
+ GUEST_LDTR_AR_BYTES = 0x00004820,
+ GUEST_TR_AR_BYTES = 0x00004822,
+ GUEST_INTERRUPTIBILITY_INFO = 0x00004824,
+ GUEST_ACTIVITY_STATE = 0X00004826,
+ GUEST_SYSENTER_CS = 0x0000482A,
+ VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ HOST_IA32_SYSENTER_CS = 0x00004c00,
+ CR0_GUEST_HOST_MASK = 0x00006000,
+ CR4_GUEST_HOST_MASK = 0x00006002,
+ CR0_READ_SHADOW = 0x00006004,
+ CR4_READ_SHADOW = 0x00006006,
+ CR3_TARGET_VALUE0 = 0x00006008,
+ CR3_TARGET_VALUE1 = 0x0000600a,
+ CR3_TARGET_VALUE2 = 0x0000600c,
+ CR3_TARGET_VALUE3 = 0x0000600e,
+ EXIT_QUALIFICATION = 0x00006400,
+ GUEST_LINEAR_ADDRESS = 0x0000640a,
+ GUEST_CR0 = 0x00006800,
+ GUEST_CR3 = 0x00006802,
+ GUEST_CR4 = 0x00006804,
+ GUEST_ES_BASE = 0x00006806,
+ GUEST_CS_BASE = 0x00006808,
+ GUEST_SS_BASE = 0x0000680a,
+ GUEST_DS_BASE = 0x0000680c,
+ GUEST_FS_BASE = 0x0000680e,
+ GUEST_GS_BASE = 0x00006810,
+ GUEST_LDTR_BASE = 0x00006812,
+ GUEST_TR_BASE = 0x00006814,
+ GUEST_GDTR_BASE = 0x00006816,
+ GUEST_IDTR_BASE = 0x00006818,
+ GUEST_DR7 = 0x0000681a,
+ GUEST_RSP = 0x0000681c,
+ GUEST_RIP = 0x0000681e,
+ GUEST_RFLAGS = 0x00006820,
+ GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822,
+ GUEST_SYSENTER_ESP = 0x00006824,
+ GUEST_SYSENTER_EIP = 0x00006826,
+ HOST_CR0 = 0x00006c00,
+ HOST_CR3 = 0x00006c02,
+ HOST_CR4 = 0x00006c04,
+ HOST_FS_BASE = 0x00006c06,
+ HOST_GS_BASE = 0x00006c08,
+ HOST_TR_BASE = 0x00006c0a,
+ HOST_GDTR_BASE = 0x00006c0c,
+ HOST_IDTR_BASE = 0x00006c0e,
+ HOST_IA32_SYSENTER_ESP = 0x00006c10,
+ HOST_IA32_SYSENTER_EIP = 0x00006c12,
+ HOST_RSP = 0x00006c14,
+ HOST_RIP = 0x00006c16,
+};
+
+struct vmx_msr_entry {
+ uint32_t index;
+ uint32_t reserved;
+ uint64_t value;
+} __attribute__ ((aligned(16)));
+
+#include "evmcs.h"
+
+static inline int vmxon(uint64_t phys)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(phys)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline void vmxoff(void)
+{
+ __asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ if (enable_evmcs)
+ return -1;
+
+ __asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline int vmptrst(uint64_t *value)
+{
+ uint64_t tmp;
+ uint8_t ret;
+
+ if (enable_evmcs)
+ return evmcs_vmptrst(value);
+
+ __asm__ __volatile__("vmptrst %[value]; setna %[ret]"
+ : [value]"=m"(tmp), [ret]"=rm"(ret)
+ : : "cc", "memory");
+
+ *value = tmp;
+ return ret;
+}
+
+/*
+ * A wrapper around vmptrst that ignores errors and returns zero if the
+ * vmptrst instruction fails.
+ */
+static inline uint64_t vmptrstz(void)
+{
+ uint64_t value = 0;
+ vmptrst(&value);
+ return value;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+ int ret;
+
+ if (enable_evmcs)
+ return evmcs_vmlaunch();
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+ int ret;
+
+ if (enable_evmcs)
+ return evmcs_vmresume();
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+static inline void vmcall(void)
+{
+ /*
+ * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle
+ * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended
+ * use of this function is to exit to L1 from L2. Clobber all other
+ * GPRs as L1 doesn't correctly preserve them during vmexits.
+ */
+ __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp"
+ : : "a"(0xdeadbeef), "c"(0xbeefdead)
+ : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+ uint64_t tmp;
+ uint8_t ret;
+
+ if (enable_evmcs)
+ return evmcs_vmread(encoding, value);
+
+ __asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+ : [value]"=rm"(tmp), [ret]"=rm"(ret)
+ : [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ *value = tmp;
+ return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+ uint64_t value = 0;
+ vmread(encoding, &value);
+ return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+ uint8_t ret;
+
+ if (enable_evmcs)
+ return evmcs_vmwrite(encoding, value);
+
+ __asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [value]"rm"(value), [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+ return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+struct vmx_pages {
+ void *vmxon_hva;
+ uint64_t vmxon_gpa;
+ void *vmxon;
+
+ void *vmcs_hva;
+ uint64_t vmcs_gpa;
+ void *vmcs;
+
+ void *msr_hva;
+ uint64_t msr_gpa;
+ void *msr;
+
+ void *shadow_vmcs_hva;
+ uint64_t shadow_vmcs_gpa;
+ void *shadow_vmcs;
+
+ void *vmread_hva;
+ uint64_t vmread_gpa;
+ void *vmread;
+
+ void *vmwrite_hva;
+ uint64_t vmwrite_gpa;
+ void *vmwrite;
+
+ void *eptp_hva;
+ uint64_t eptp_gpa;
+ void *eptp;
+
+ void *apic_access_hva;
+ uint64_t apic_access_gpa;
+ void *apic_access;
+};
+
+union vmx_basic {
+ u64 val;
+ struct {
+ u32 revision;
+ u32 size:13,
+ reserved1:3,
+ width:1,
+ dual:1,
+ type:4,
+ insouts:1,
+ ctrl:1,
+ vm_entry_exception_ctrl:1,
+ reserved2:7;
+ };
+};
+
+union vmx_ctrl_msr {
+ u64 val;
+ struct {
+ u32 set, clr;
+ };
+};
+
+struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
+bool prepare_for_vmx_operation(struct vmx_pages *vmx);
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+bool load_vmcs(struct vmx_pages *vmx);
+
+bool ept_1g_pages_supported(void);
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr);
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size);
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t memslot);
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t addr, uint64_t size);
+bool kvm_cpu_has_ept(void);
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot);
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
+
+#endif /* SELFTEST_KVM_VMX_H */