diff options
Diffstat (limited to 'tools/testing/selftests/kvm/include/x86')
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/apic.h | 29 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/evmcs.h | 22 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/hyperv.h | 28 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/kvm_util_arch.h | 34 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/pmu.h | 33 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/processor.h | 461 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/sev.h | 65 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/smm.h | 16 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/svm.h | 17 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/svm_util.h | 19 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/ucall.h | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/kvm/include/x86/vmx.h | 85 |
12 files changed, 543 insertions, 268 deletions
diff --git a/tools/testing/selftests/kvm/include/x86/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h index 80fe9f69b38d..31887bdc3d6c 100644 --- a/tools/testing/selftests/kvm/include/x86/apic.h +++ b/tools/testing/selftests/kvm/include/x86/apic.h @@ -28,10 +28,13 @@ #define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) #define APIC_TASKPRI 0x80 #define APIC_PROCPRI 0xA0 +#define GET_APIC_PRI(x) (((x) & GENMASK(7, 4)) >> 4) +#define SET_APIC_PRI(x, y) (((x) & ~GENMASK(7, 4)) | (y << 4)) #define APIC_EOI 0xB0 #define APIC_SPIV 0xF0 #define APIC_SPIV_FOCUS_DISABLED (1 << 9) #define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_ISR 0x100 #define APIC_IRR 0x200 #define APIC_ICR 0x300 #define APIC_LVTCMCI 0x2f0 @@ -67,47 +70,51 @@ #define APIC_TMICT 0x380 #define APIC_TMCCT 0x390 #define APIC_TDCR 0x3E0 +#define APIC_SELF_IPI 0x3F0 + +#define APIC_VECTOR_TO_BIT_NUMBER(v) ((unsigned int)(v) % 32) +#define APIC_VECTOR_TO_REG_OFFSET(v) ((unsigned int)(v) / 32 * 0x10) void apic_disable(void); void xapic_enable(void); void x2apic_enable(void); -static inline uint32_t get_bsp_flag(void) +static inline u32 get_bsp_flag(void) { return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; } -static inline uint32_t xapic_read_reg(unsigned int reg) +static inline u32 xapic_read_reg(unsigned int reg) { - return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2]; + return ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2]; } -static inline void xapic_write_reg(unsigned int reg, uint32_t val) +static inline void xapic_write_reg(unsigned int reg, u32 val) { - ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val; + ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2] = val; } -static inline uint64_t x2apic_read_reg(unsigned int reg) +static inline u64 x2apic_read_reg(unsigned int reg) { return rdmsr(APIC_BASE_MSR + (reg >> 4)); } -static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +static inline u8 x2apic_write_reg_safe(unsigned int reg, u64 value) { return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", fault, APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg_fault(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(fault == GP_VECTOR, "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", diff --git a/tools/testing/selftests/kvm/include/x86/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h index 5a74bb30e2f8..be79bda024bf 100644 --- a/tools/testing/selftests/kvm/include/x86/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86/evmcs.h @@ -10,9 +10,9 @@ #include "hyperv.h" #include "vmx.h" -#define u16 uint16_t -#define u32 uint32_t -#define u64 uint64_t +#define u16 u16 +#define u32 u32 +#define u64 u64 #define EVMCS_VERSION 1 @@ -245,7 +245,7 @@ static inline void evmcs_enable(void) enable_evmcs = true; } -static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) +static inline int evmcs_vmptrld(u64 vmcs_pa, void *vmcs) { current_vp_assist->current_nested_vmcs = vmcs_pa; current_vp_assist->enlighten_vmentry = 1; @@ -265,7 +265,7 @@ static inline bool load_evmcs(struct hyperv_test_pages *hv) return true; } -static inline int evmcs_vmptrst(uint64_t *value) +static inline int evmcs_vmptrst(u64 *value) { *value = current_vp_assist->current_nested_vmcs & ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; @@ -273,7 +273,7 @@ static inline int evmcs_vmptrst(uint64_t *value) return 0; } -static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) +static inline int evmcs_vmread(u64 encoding, u64 *value) { switch (encoding) { case GUEST_RIP: @@ -672,7 +672,7 @@ static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) return 0; } -static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) +static inline int evmcs_vmwrite(u64 encoding, u64 value) { switch (encoding) { case GUEST_RIP: @@ -1226,9 +1226,9 @@ static inline int evmcs_vmlaunch(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -1265,9 +1265,9 @@ static inline int evmcs_vmresume(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; diff --git a/tools/testing/selftests/kvm/include/x86/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h index f13e532be240..78003f5a22f3 100644 --- a/tools/testing/selftests/kvm/include/x86/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86/hyperv.h @@ -254,12 +254,12 @@ * 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) +static inline u8 __hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address, + u64 *hv_status) { - uint64_t error_code; - uint8_t vector; + u64 error_code; + u8 vector; /* Note both the hypercall and the "asm safe" clobber r9-r11. */ asm volatile("mov %[output_address], %%r8\n\t" @@ -274,11 +274,11 @@ static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, } /* 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) +static inline void hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address) { - uint64_t hv_status; - uint8_t vector; + u64 hv_status; + u8 vector; vector = __hyperv_hypercall(control, input_address, output_address, &hv_status); @@ -327,27 +327,27 @@ struct hv_vp_assist_page { extern struct hv_vp_assist_page *current_vp_assist; -int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist); +int enable_vp_assist(u64 vp_assist_pa, void *vp_assist); struct hyperv_test_pages { /* VP assist page */ void *vp_assist_hva; - uint64_t vp_assist_gpa; + u64 vp_assist_gpa; void *vp_assist; /* Partition assist page */ void *partition_assist_hva; - uint64_t partition_assist_gpa; + u64 partition_assist_gpa; void *partition_assist; /* Enlightened VMCS */ void *enlightened_vmcs_hva; - uint64_t enlightened_vmcs_gpa; + u64 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); + gva_t *p_hv_pages_gva); /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) diff --git a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h index 972bb1c4ab4c..c33ab6e04171 100644 --- a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h @@ -10,13 +10,35 @@ extern bool is_forced_emulation_enabled; +struct pte_masks { + u64 present; + u64 writable; + u64 user; + u64 readable; + u64 executable; + u64 accessed; + u64 dirty; + u64 huge; + u64 nx; + u64 c; + u64 s; + + u64 always_set; +}; + +struct kvm_mmu_arch { + struct pte_masks pte_masks; +}; + +struct kvm_mmu; + struct kvm_vm_arch { - vm_vaddr_t gdt; - vm_vaddr_t tss; - vm_vaddr_t idt; + gva_t gdt; + gva_t tss; + gva_t idt; - uint64_t c_bit; - uint64_t s_bit; + u64 c_bit; + u64 s_bit; int sev_fd; bool is_pt_protected; }; @@ -40,7 +62,7 @@ do { \ : "+m" (mem) \ : "r" (val) : "memory"); \ } else { \ - uint64_t __old = READ_ONCE(mem); \ + u64 __old = READ_ONCE(mem); \ \ __asm__ __volatile__(KVM_FEP LOCK_PREFIX "cmpxchg %[new], %[ptr]" \ : [ptr] "+m" (mem), [old] "+a" (__old) \ diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 3c10c4dc0ae8..98537cc8840d 100644 --- a/tools/testing/selftests/kvm/include/x86/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h @@ -5,7 +5,10 @@ #ifndef SELFTEST_KVM_PMU_H #define SELFTEST_KVM_PMU_H -#include <stdint.h> +#include <stdbool.h> + +#include <linux/types.h> +#include <linux/bits.h> #define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 @@ -61,6 +64,11 @@ #define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00) #define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00) #define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01) +#define INTEL_ARCH_TOPDOWN_BE_BOUND RAW_EVENT(0xa4, 0x02) +#define INTEL_ARCH_TOPDOWN_BAD_SPEC RAW_EVENT(0x73, 0x00) +#define INTEL_ARCH_TOPDOWN_FE_BOUND RAW_EVENT(0x9c, 0x01) +#define INTEL_ARCH_TOPDOWN_RETIRING RAW_EVENT(0xc2, 0x02) +#define INTEL_ARCH_LBR_INSERTS RAW_EVENT(0xe4, 0x01) #define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00) #define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) @@ -80,6 +88,11 @@ enum intel_pmu_architectural_events { INTEL_ARCH_BRANCHES_RETIRED_INDEX, INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX, INTEL_ARCH_TOPDOWN_SLOTS_INDEX, + INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX, + INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_RETIRING_INDEX, + INTEL_ARCH_LBR_INSERTS_INDEX, NR_INTEL_ARCH_EVENTS, }; @@ -91,7 +104,21 @@ enum amd_pmu_zen_events { NR_AMD_ZEN_EVENTS, }; -extern const uint64_t intel_pmu_arch_events[]; -extern const uint64_t amd_pmu_zen_events[]; +extern const u64 intel_pmu_arch_events[]; +extern const u64 amd_pmu_zen_events[]; + +enum pmu_errata { + INSTRUCTIONS_RETIRED_OVERCOUNT, + BRANCHES_RETIRED_OVERCOUNT, +}; + +extern u64 pmu_errata_mask; + +void kvm_init_pmu_errata(void); + +static inline bool this_pmu_has_errata(enum pmu_errata errata) +{ + return pmu_errata_mask & BIT_ULL(errata); +} #endif /* SELFTEST_KVM_PMU_H */ diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index d60da8966772..77f576ee7789 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -21,7 +21,9 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; -extern uint64_t guest_tsc_khz; +extern bool host_cpu_is_hygon; +extern bool host_cpu_is_amd_compatible; +extern u64 guest_tsc_khz; #ifndef MAX_NR_CPUID_ENTRIES #define MAX_NR_CPUID_ENTRIES 100 @@ -34,6 +36,8 @@ extern uint64_t guest_tsc_khz; #define NMI_VECTOR 0x02 +const char *ex_str(int vector); + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -183,6 +187,9 @@ struct kvm_x86_cpu_feature { * Extended Leafs, a.k.a. AMD defined */ #define X86_FEATURE_SVM KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 2) +#define X86_FEATURE_PERFCTR_CORE KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 23) +#define X86_FEATURE_PERFCTR_NB KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 24) +#define X86_FEATURE_PERFCTR_LLC KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 28) #define X86_FEATURE_NX KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 20) #define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) #define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) @@ -196,9 +203,14 @@ struct kvm_x86_cpu_feature { #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_V_VMSAVE_VMLOAD KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 15) #define X86_FEATURE_VGIF KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 16) +#define X86_FEATURE_IDLE_HLT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 30) #define X86_FEATURE_SEV KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1) #define X86_FEATURE_SEV_ES KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3) +#define X86_FEATURE_SEV_SNP KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 4) +#define X86_FEATURE_PERFMON_V2 KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 0) +#define X86_FEATURE_LBR_PMC_FREEZE KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 2) /* * KVM defined paravirt features. @@ -258,7 +270,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) #define X86_PROPERTY_PMU_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_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 12) #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) @@ -285,6 +297,8 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_GUEST_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23) #define X86_PROPERTY_SEV_C_BIT KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) +#define X86_PROPERTY_NR_PERFCTR_CORE KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 0, 3) +#define X86_PROPERTY_NR_PERFCTR_NB KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 10, 15) #define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) @@ -323,6 +337,11 @@ struct kvm_x86_pmu_feature { #define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5) #define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6) #define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7) +#define X86_PMU_FEATURE_TOPDOWN_BE_BOUND KVM_X86_PMU_FEATURE(EBX, 8) +#define X86_PMU_FEATURE_TOPDOWN_BAD_SPEC KVM_X86_PMU_FEATURE(EBX, 9) +#define X86_PMU_FEATURE_TOPDOWN_FE_BOUND KVM_X86_PMU_FEATURE(EBX, 10) +#define X86_PMU_FEATURE_TOPDOWN_RETIRING KVM_X86_PMU_FEATURE(EBX, 11) +#define X86_PMU_FEATURE_LBR_INSERTS KVM_X86_PMU_FEATURE(EBX, 12) #define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0) #define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1) @@ -346,16 +365,6 @@ 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 @@ -390,17 +399,17 @@ struct gpr64_regs { }; struct desc64 { - uint16_t limit0; - uint16_t base0; + u16 limit0; + u16 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; + u32 base3; + u32 zero1; } __attribute__((packed)); struct desc_ptr { - uint16_t size; - uint64_t address; + u16 size; + u64 address; } __attribute__((packed)); struct kvm_x86_state { @@ -418,16 +427,18 @@ struct kvm_x86_state { struct kvm_msrs msrs; }; -static inline uint64_t get_desc64_base(const struct desc64 *desc) +static inline u64 get_desc64_base(const struct desc64 *desc) { - return ((uint64_t)desc->base3 << 32) | - (desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); + return (u64)desc->base3 << 32 | + (u64)desc->base2 << 24 | + (u64)desc->base1 << 16 | + (u64)desc->base0; } -static inline uint64_t rdtsc(void) +static inline u64 rdtsc(void) { - uint32_t eax, edx; - uint64_t tsc_val; + u32 eax, edx; + u64 tsc_val; /* * The lfence is to wait (on Intel CPUs) until all previous * instructions have been executed. If software requires RDTSC to be @@ -435,39 +446,39 @@ static inline uint64_t rdtsc(void) * execute LFENCE immediately after RDTSC */ __asm__ __volatile__("lfence; rdtsc; lfence" : "=a"(eax), "=d"(edx)); - tsc_val = ((uint64_t)edx) << 32 | eax; + tsc_val = ((u64)edx) << 32 | eax; return tsc_val; } -static inline uint64_t rdtscp(uint32_t *aux) +static inline u64 rdtscp(u32 *aux) { - uint32_t eax, edx; + u32 eax, edx; __asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux)); - return ((uint64_t)edx) << 32 | eax; + return ((u64)edx) << 32 | eax; } -static inline uint64_t rdmsr(uint32_t msr) +static inline u64 rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; __asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } -static inline void wrmsr(uint32_t msr, uint64_t value) +static inline void wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; __asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory"); } -static inline uint16_t inw(uint16_t port) +static inline u16 inw(u16 port) { - uint16_t tmp; + u16 tmp; __asm__ __volatile__("in %%dx, %%ax" : /* output */ "=a" (tmp) @@ -476,101 +487,124 @@ static inline uint16_t inw(uint16_t port) return tmp; } -static inline uint16_t get_es(void) +static inline u16 get_es(void) { - uint16_t es; + u16 es; __asm__ __volatile__("mov %%es, %[es]" : /* output */ [es]"=rm"(es)); return es; } -static inline uint16_t get_cs(void) +static inline u16 get_cs(void) { - uint16_t cs; + u16 cs; __asm__ __volatile__("mov %%cs, %[cs]" : /* output */ [cs]"=rm"(cs)); return cs; } -static inline uint16_t get_ss(void) +static inline u16 get_ss(void) { - uint16_t ss; + u16 ss; __asm__ __volatile__("mov %%ss, %[ss]" : /* output */ [ss]"=rm"(ss)); return ss; } -static inline uint16_t get_ds(void) +static inline u16 get_ds(void) { - uint16_t ds; + u16 ds; __asm__ __volatile__("mov %%ds, %[ds]" : /* output */ [ds]"=rm"(ds)); return ds; } -static inline uint16_t get_fs(void) +static inline u16 get_fs(void) { - uint16_t fs; + u16 fs; __asm__ __volatile__("mov %%fs, %[fs]" : /* output */ [fs]"=rm"(fs)); return fs; } -static inline uint16_t get_gs(void) +static inline u16 get_gs(void) { - uint16_t gs; + u16 gs; __asm__ __volatile__("mov %%gs, %[gs]" : /* output */ [gs]"=rm"(gs)); return gs; } -static inline uint16_t get_tr(void) +static inline u16 get_tr(void) { - uint16_t tr; + u16 tr; __asm__ __volatile__("str %[tr]" : /* output */ [tr]"=rm"(tr)); return tr; } -static inline uint64_t get_cr0(void) +static inline u64 get_cr0(void) { - uint64_t cr0; + u64 cr0; __asm__ __volatile__("mov %%cr0, %[cr0]" : /* output */ [cr0]"=r"(cr0)); return cr0; } -static inline uint64_t get_cr3(void) +static inline void set_cr0(u64 val) { - uint64_t cr3; + __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); +} + +static inline u64 get_cr3(void) +{ + u64 cr3; __asm__ __volatile__("mov %%cr3, %[cr3]" : /* output */ [cr3]"=r"(cr3)); return cr3; } -static inline uint64_t get_cr4(void) +static inline void set_cr3(u64 val) +{ + __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); +} + +static inline u64 get_cr4(void) { - uint64_t cr4; + u64 cr4; __asm__ __volatile__("mov %%cr4, %[cr4]" : /* output */ [cr4]"=r"(cr4)); return cr4; } -static inline void set_cr4(uint64_t val) +static inline void set_cr4(u64 val) { __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline u64 get_cr8(void) +{ + u64 cr8; + + __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); + return cr8; +} + +static inline void set_cr8(u64 val) +{ + __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); +} + static inline void set_idt(const struct desc_ptr *idt_desc) { __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); @@ -617,14 +651,14 @@ static inline struct desc_ptr get_idt(void) return idt; } -static inline void outl(uint16_t port, uint32_t value) +static inline void outl(u16 port, u32 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) +static inline void __cpuid(u32 function, u32 index, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { *eax = function; *ecx = index; @@ -638,35 +672,35 @@ static inline void __cpuid(uint32_t function, uint32_t index, : "memory"); } -static inline void cpuid(uint32_t function, - uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void cpuid(u32 function, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { return __cpuid(function, 0, eax, ebx, ecx, edx); } -static inline uint32_t this_cpu_fms(void) +static inline u32 this_cpu_fms(void) { - uint32_t eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; cpuid(1, &eax, &ebx, &ecx, &edx); return eax; } -static inline uint32_t this_cpu_family(void) +static inline u32 this_cpu_family(void) { return x86_family(this_cpu_fms()); } -static inline uint32_t this_cpu_model(void) +static inline u32 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; + const u32 *chunk = (const u32 *)vendor; + u32 eax, ebx, ecx, edx; cpuid(0, &eax, &ebx, &ecx, &edx); return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); @@ -685,10 +719,14 @@ 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) +static inline bool this_cpu_is_hygon(void) { - uint32_t gprs[4]; + return this_cpu_vendor_string_is("HygonGenuine"); +} + +static inline u32 __this_cpu_has(u32 function, u32 index, u8 reg, u8 lo, u8 hi) +{ + u32 gprs[4]; __cpuid(function, index, &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX], @@ -703,7 +741,7 @@ static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) feature.reg, feature.bit, feature.bit); } -static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) +static inline u32 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); @@ -711,7 +749,7 @@ static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) { - uint32_t max_leaf; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -731,7 +769,7 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -743,13 +781,13 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || this_cpu_has(feature.f); } -static __always_inline uint64_t this_cpu_supported_xcr0(void) +static __always_inline u64 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); + ((u64)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -828,7 +866,7 @@ static inline void cpu_relax(void) static inline void udelay(unsigned long usec) { - uint64_t start, now, cycles; + u64 start, now, cycles; GUEST_ASSERT(guest_tsc_khz); cycles = guest_tsc_khz / 1000 * usec; @@ -859,8 +897,8 @@ 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); +bool kvm_msr_is_in_save_restore_list(u32 msr_index); +u64 kvm_get_feature_msr(u64 msr_index); static inline void vcpu_msrs_get(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) @@ -915,20 +953,20 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) } const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index); + u32 function, u32 index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -static inline uint32_t kvm_cpu_fms(void) +static inline u32 kvm_cpu_fms(void) { return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax; } -static inline uint32_t kvm_cpu_family(void) +static inline u32 kvm_cpu_family(void) { return x86_family(kvm_cpu_fms()); } -static inline uint32_t kvm_cpu_model(void) +static inline u32 kvm_cpu_model(void) { return x86_model(kvm_cpu_fms()); } @@ -941,17 +979,17 @@ 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); +u32 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) +static inline u32 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; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -971,7 +1009,7 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -983,13 +1021,13 @@ static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || kvm_cpu_has(feature.f); } -static __always_inline uint64_t kvm_cpu_supported_xcr0(void) +static __always_inline u64 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); + ((u64)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } static inline size_t kvm_cpuid2_size(int nr_entries) @@ -1023,8 +1061,8 @@ static inline void vcpu_get_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) + u32 function, + u32 index) { TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first (or equivalent)"); @@ -1035,7 +1073,7 @@ static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *v } static inline struct kvm_cpuid_entry2 *vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, - uint32_t function) + u32 function) { return __vcpu_get_cpuid_entry(vcpu, function, 0); } @@ -1065,10 +1103,10 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, - uint32_t value); -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); + u32 value); +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, u8 maxphyaddr); -void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, u32 function); static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_feature feature) @@ -1096,8 +1134,8 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, 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); +u64 vcpu_get_msr(struct kvm_vcpu *vcpu, u64 msr_index); +int _vcpu_set_msr(struct kvm_vcpu *vcpu, u64 msr_index, u64 msr_value); /* * Assert on an MSR access(es) and pretty print the MSR name when possible. @@ -1122,14 +1160,14 @@ do { \ * 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) +static inline bool is_durable_msr(u32 msr) { return msr != MSR_IA32_TSC; } #define vcpu_set_msr(vcpu, msr, val) \ do { \ - uint64_t r, v = val; \ + u64 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); \ @@ -1141,36 +1179,41 @@ do { \ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); void kvm_init_vm_address_properties(struct kvm_vm *vm); -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; + u64 rax, rcx, rdx, rbx; + u64 rbp, rsi, rdi; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 vector; + u64 error_code; + u64 rip; + u64 cs; + u64 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; + u16 offset0; + u16 selector; + u16 ist : 3; + u16 : 5; + u16 type : 4; + u16 : 1; + u16 dpl : 2; + u16 p : 1; + u16 offset1; + u32 offset2; u32 reserved; }; void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); +/* + * Exception fixup morphs #DE to an arbitrary magic vector so that '0' can be + * used to signal "no expcetion". + */ +#define KVM_MAGIC_DE_VECTOR 0xff + /* If a toddler were to say "abracadabra". */ #define KVM_EXCEPTION_MAGIC 0xabacadabaULL @@ -1218,8 +1261,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ @@ -1230,7 +1273,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1241,10 +1284,10 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_fep(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ - asm volatile(KVM_ASM_SAFE(insn) \ + asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ : inputs \ : KVM_ASM_SAFE_CLOBBERS); \ @@ -1253,7 +1296,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec_fep(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1263,11 +1306,11 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, }) #define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ -static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ +static inline u8 insn##_safe ##_fep(u32 idx, u64 *val) \ { \ - uint64_t error_code; \ - uint8_t vector; \ - uint32_t a, d; \ + u64 error_code; \ + u8 vector; \ + u32 a, d; \ \ asm volatile(KVM_ASM_SAFE##_FEP(#insn) \ : "=a"(a), "=d"(d), \ @@ -1275,7 +1318,7 @@ static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ : "c"(idx) \ : KVM_ASM_SAFE_CLOBBERS); \ \ - *val = (uint64_t)a | ((uint64_t)d << 32); \ + *val = (u64)a | ((u64)d << 32); \ return vector; \ } @@ -1291,12 +1334,12 @@ BUILD_READ_U64_SAFE_HELPERS(rdmsr) BUILD_READ_U64_SAFE_HELPERS(rdpmc) BUILD_READ_U64_SAFE_HELPERS(xgetbv) -static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) +static inline u8 wrmsr_safe(u32 msr, u64 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) +static inline u8 xsetbv_safe(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; @@ -1306,6 +1349,26 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) bool kvm_is_tdp_enabled(void); +static inline bool get_kvm_intel_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_intel", param); +} + +static inline bool get_kvm_amd_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_amd", param); +} + +static inline int get_kvm_intel_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_intel", param); +} + +static inline int get_kvm_amd_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_amd", param); +} + static inline bool kvm_is_pmu_enabled(void) { return get_kvm_param_bool("enable_pmu"); @@ -1316,30 +1379,80 @@ static inline bool kvm_is_forced_emulation_enabled(void) return !!get_kvm_param_integer("force_emulation_prefix"); } -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); +static inline bool kvm_is_unrestricted_guest_enabled(void) +{ + return get_kvm_intel_param_bool("unrestricted_guest"); +} + +static inline bool kvm_is_ignore_msrs(void) +{ + return get_kvm_param_bool("ignore_msrs"); +} + +static inline bool kvm_is_lbrv_enabled(void) +{ + return !!get_kvm_amd_param_integer("lbrv"); +} + +u64 *vm_get_pte(struct kvm_vm *vm, gva_t gva); -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); +u64 kvm_hypercall(u64 nr, u64 a0, u64 a1, u64 a2, u64 a3); +u64 __xen_hypercall(u64 nr, u64 a0, void *a1); +void xen_hypercall(u64 nr, u64 a0, void *a1); -static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa, - uint64_t size, uint64_t flags) +static inline u64 __kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0); } -static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size, - uint64_t flags) +static inline void kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { - uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); + u64 ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); GUEST_ASSERT(!ret); } -void __vm_xsave_require_permission(uint64_t xfeature, const char *name); +/* + * Execute HLT in an STI interrupt shadow to ensure that a pending IRQ that's + * intended to be a wake event arrives *after* HLT is executed. Modern CPUs, + * except for a few oddballs that KVM is unlikely to run on, block IRQs for one + * instruction after STI, *if* RFLAGS.IF=0 before STI. Note, Intel CPUs may + * block other events beyond regular IRQs, e.g. may block NMIs and SMIs too. + */ +static inline void safe_halt(void) +{ + asm volatile("sti; hlt"); +} + +/* + * Enable interrupts and ensure that interrupts are evaluated upon return from + * this function, i.e. execute a nop to consume the STi interrupt shadow. + */ +static inline void sti_nop(void) +{ + asm volatile ("sti; nop"); +} + +/* + * Enable interrupts for one instruction (nop), to allow the CPU to process all + * interrupts that are already pending. + */ +static inline void sti_nop_cli(void) +{ + asm volatile ("sti; nop; cli"); +} + +static inline void sti(void) +{ + asm volatile("sti"); +} + +static inline void cli(void) +{ + asm volatile ("cli"); +} + +void __vm_xsave_require_permission(u64 xfeature, const char *name); #define vm_xsave_require_permission(xfeature) \ __vm_xsave_require_permission(xfeature, #xfeature) @@ -1350,7 +1463,7 @@ enum pg_level { PG_LEVEL_2M, PG_LEVEL_1G, PG_LEVEL_512G, - PG_LEVEL_NUM + PG_LEVEL_256T }; #define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12) @@ -1360,9 +1473,51 @@ enum pg_level { #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); +#define PTE_PRESENT_MASK(mmu) ((mmu)->arch.pte_masks.present) +#define PTE_WRITABLE_MASK(mmu) ((mmu)->arch.pte_masks.writable) +#define PTE_USER_MASK(mmu) ((mmu)->arch.pte_masks.user) +#define PTE_READABLE_MASK(mmu) ((mmu)->arch.pte_masks.readable) +#define PTE_EXECUTABLE_MASK(mmu) ((mmu)->arch.pte_masks.executable) +#define PTE_ACCESSED_MASK(mmu) ((mmu)->arch.pte_masks.accessed) +#define PTE_DIRTY_MASK(mmu) ((mmu)->arch.pte_masks.dirty) +#define PTE_HUGE_MASK(mmu) ((mmu)->arch.pte_masks.huge) +#define PTE_NX_MASK(mmu) ((mmu)->arch.pte_masks.nx) +#define PTE_C_BIT_MASK(mmu) ((mmu)->arch.pte_masks.c) +#define PTE_S_BIT_MASK(mmu) ((mmu)->arch.pte_masks.s) +#define PTE_ALWAYS_SET_MASK(mmu) ((mmu)->arch.pte_masks.always_set) + +/* + * For PTEs without a PRESENT bit (i.e. EPT entries), treat the PTE as present + * if it's executable or readable, as EPT supports execute-only PTEs, but not + * write-only PTEs. + */ +#define is_present_pte(mmu, pte) \ + (PTE_PRESENT_MASK(mmu) ? \ + !!(*(pte) & PTE_PRESENT_MASK(mmu)) : \ + !!(*(pte) & (PTE_READABLE_MASK(mmu) | PTE_EXECUTABLE_MASK(mmu)))) +#define is_executable_pte(mmu, pte) \ + ((*(pte) & (PTE_EXECUTABLE_MASK(mmu) | PTE_NX_MASK(mmu))) == PTE_EXECUTABLE_MASK(mmu)) +#define is_writable_pte(mmu, pte) (!!(*(pte) & PTE_WRITABLE_MASK(mmu))) +#define is_user_pte(mmu, pte) (!!(*(pte) & PTE_USER_MASK(mmu))) +#define is_accessed_pte(mmu, pte) (!!(*(pte) & PTE_ACCESSED_MASK(mmu))) +#define is_dirty_pte(mmu, pte) (!!(*(pte) & PTE_DIRTY_MASK(mmu))) +#define is_huge_pte(mmu, pte) (!!(*(pte) & PTE_HUGE_MASK(mmu))) +#define is_nx_pte(mmu, pte) (!is_executable_pte(mmu, pte)) + +void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels, + struct pte_masks *pte_masks); + +void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, gva_t gva, + gpa_t gpa, int level); +void virt_map_level(struct kvm_vm *vm, gva_t gva, gpa_t gpa, + u64 nr_bytes, int level); + +void vm_enable_tdp(struct kvm_vm *vm); +bool kvm_cpu_has_tdp(void); +void tdp_map(struct kvm_vm *vm, gpa_t l2_gpa, gpa_t gpa, u64 size); +void tdp_identity_map_default_memslots(struct kvm_vm *vm); +void tdp_identity_map_1g(struct kvm_vm *vm, u64 addr, u64 size); +u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa); /* * Basic CPU control in CR0 diff --git a/tools/testing/selftests/kvm/include/x86/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h index 82c11c81a956..1af44c151d60 100644 --- a/tools/testing/selftests/kvm/include/x86/sev.h +++ b/tools/testing/selftests/kvm/include/x86/sev.h @@ -25,19 +25,51 @@ enum sev_guest_state { #define SEV_POLICY_NO_DBG (1UL << 0) #define SEV_POLICY_ES (1UL << 2) +#define SNP_POLICY_SMT (1ULL << 16) +#define SNP_POLICY_RSVD_MBO (1ULL << 17) +#define SNP_POLICY_DBG (1ULL << 19) + #define GHCB_MSR_TERM_REQ 0x100 -void sev_vm_launch(struct kvm_vm *vm, uint32_t policy); -void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement); +static inline bool is_sev_snp_vm(struct kvm_vm *vm) +{ + return vm->type == KVM_X86_SNP_VM; +} + +static inline bool is_sev_es_vm(struct kvm_vm *vm) +{ + return is_sev_snp_vm(vm) || vm->type == KVM_X86_SEV_ES_VM; +} + +static inline bool is_sev_vm(struct kvm_vm *vm) +{ + return is_sev_es_vm(vm) || vm->type == KVM_X86_SEV_VM; +} + +void sev_vm_launch(struct kvm_vm *vm, u32 policy); +void sev_vm_launch_measure(struct kvm_vm *vm, u8 *measurement); void sev_vm_launch_finish(struct kvm_vm *vm); +void snp_vm_launch_start(struct kvm_vm *vm, u64 policy); +void snp_vm_launch_update(struct kvm_vm *vm); +void snp_vm_launch_finish(struct kvm_vm *vm); -struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, +struct kvm_vm *vm_sev_create_with_one_vcpu(u32 type, void *guest_code, struct kvm_vcpu **cpu); -void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement); +void vm_sev_launch(struct kvm_vm *vm, u64 policy, u8 *measurement); kvm_static_assert(SEV_RET_SUCCESS == 0); /* + * A SEV-SNP VM requires the policy reserved bit to always be set. + * The SMT policy bit is also required to be set based on SMT being + * available and active on the system. + */ +static inline u64 snp_default_policy(void) +{ + return SNP_POLICY_RSVD_MBO | (is_smt_on() ? SNP_POLICY_SMT : 0); +} + +/* * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long" * instead of a proper struct. The size of the parameter is embedded in the * ioctl number, i.e. is ABI and thus immutable. Hack around the mess by @@ -53,7 +85,7 @@ kvm_static_assert(SEV_RET_SUCCESS == 0); unsigned long raw; \ } sev_cmd = { .c = { \ .id = (cmd), \ - .data = (uint64_t)(arg), \ + .data = (u64)(arg), \ .sev_fd = (vm)->arch.sev_fd, \ } }; \ \ @@ -70,6 +102,12 @@ kvm_static_assert(SEV_RET_SUCCESS == 0); void sev_vm_init(struct kvm_vm *vm); void sev_es_vm_init(struct kvm_vm *vm); +void snp_vm_init(struct kvm_vm *vm); + +static inline void vmgexit(void) +{ + __asm__ __volatile__("rep; vmmcall"); +} static inline void sev_register_encrypted_memory(struct kvm_vm *vm, struct userspace_mem_region *region) @@ -82,8 +120,8 @@ static inline void sev_register_encrypted_memory(struct kvm_vm *vm, vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); } -static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, - uint64_t size) +static inline void sev_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 size) { struct kvm_sev_launch_update_data update_data = { .uaddr = (unsigned long)addr_gpa2hva(vm, gpa), @@ -93,4 +131,17 @@ static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data); } +static inline void snp_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 hva, u64 size, u8 type) +{ + struct kvm_sev_snp_launch_update update_data = { + .uaddr = hva, + .gfn_start = gpa >> PAGE_SHIFT, + .len = size, + .type = type, + }; + + vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_UPDATE, &update_data); +} + #endif /* SELFTEST_KVM_SEV_H */ diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h new file mode 100644 index 000000000000..2d1afa09819b --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef SELFTEST_KVM_SMM_H +#define SELFTEST_KVM_SMM_H + +#include "kvm_util.h" + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, u64 smram_gpa, + const void *smi_handler, size_t handler_size); + +void inject_smi(struct kvm_vcpu *vcpu); + +#endif /* SELFTEST_KVM_SMM_H */ diff --git a/tools/testing/selftests/kvm/include/x86/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h index 29cffd0a9181..c8539166270e 100644 --- a/tools/testing/selftests/kvm/include/x86/svm.h +++ b/tools/testing/selftests/kvm/include/x86/svm.h @@ -92,19 +92,18 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 int_vector; u32 int_state; u8 reserved_3[4]; - u32 exit_code; - u32 exit_code_hi; + u64 exit_code; u64 exit_info_1; u64 exit_info_2; u32 exit_int_info; u32 exit_int_info_err; - u64 nested_ctl; + u64 misc_ctl; u64 avic_vapic_bar; u8 reserved_4[8]; u32 event_inj; u32 event_inj_err; u64 nested_cr3; - u64 virt_ext; + u64 misc_ctl2; u32 clean; u32 reserved_5; u64 next_rip; @@ -156,9 +155,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #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 @@ -176,8 +172,11 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #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) +#define SVM_MISC_ENABLE_NP BIT(0) +#define SVM_MISC_ENABLE_SEV BIT(1) + +#define SVM_MISC2_ENABLE_V_LBR BIT_ULL(0) +#define SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE BIT_ULL(1) struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; diff --git a/tools/testing/selftests/kvm/include/x86/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h index b74c6dcddcbd..6c013eb838be 100644 --- a/tools/testing/selftests/kvm/include/x86/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86/svm_util.h @@ -16,17 +16,20 @@ struct svm_test_data { /* VMCB */ struct vmcb *vmcb; /* gva */ void *vmcb_hva; - uint64_t vmcb_gpa; + u64 vmcb_gpa; /* host state-save area */ struct vmcb_save_area *save_area; /* gva */ void *save_area_hva; - uint64_t save_area_gpa; + u64 save_area_gpa; /* MSR-Bitmap */ void *msr; /* gva */ void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; + + /* NPT */ + u64 ncr3_gpa; }; static inline void vmmcall(void) @@ -53,9 +56,15 @@ static inline void vmmcall(void) "clgi\n" \ ) -struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, gva_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); +void run_guest(struct vmcb *vmcb, u64 vmcb_gpa); + +static inline bool kvm_cpu_has_npt(void) +{ + return kvm_cpu_has(X86_FEATURE_NPT); +} +void vm_enable_npt(struct kvm_vm *vm); int open_sev_dev_path_or_exit(void); diff --git a/tools/testing/selftests/kvm/include/x86/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h index d3825dcc3cd9..0e4950041e3e 100644 --- a/tools/testing/selftests/kvm/include/x86/ucall.h +++ b/tools/testing/selftests/kvm/include/x86/ucall.h @@ -6,7 +6,7 @@ #define UCALL_EXIT_REASON KVM_EXIT_IO -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } diff --git a/tools/testing/selftests/kvm/include/x86/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h index edb3c391b982..90fffaf91595 100644 --- a/tools/testing/selftests/kvm/include/x86/vmx.h +++ b/tools/testing/selftests/kvm/include/x86/vmx.h @@ -285,16 +285,16 @@ enum vmcs_field { }; struct vmx_msr_entry { - uint32_t index; - uint32_t reserved; - uint64_t value; + u32 index; + u32 reserved; + u64 value; } __attribute__ ((aligned(16))); #include "evmcs.h" -static inline int vmxon(uint64_t phys) +static inline int vmxon(u64 phys) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -309,9 +309,9 @@ static inline void vmxoff(void) __asm__ __volatile__("vmxoff"); } -static inline int vmclear(uint64_t vmcs_pa) +static inline int vmclear(u64 vmcs_pa) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -321,9 +321,9 @@ static inline int vmclear(uint64_t vmcs_pa) return ret; } -static inline int vmptrld(uint64_t vmcs_pa) +static inline int vmptrld(u64 vmcs_pa) { - uint8_t ret; + u8 ret; if (enable_evmcs) return -1; @@ -336,10 +336,10 @@ static inline int vmptrld(uint64_t vmcs_pa) return ret; } -static inline int vmptrst(uint64_t *value) +static inline int vmptrst(u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmptrst(value); @@ -356,9 +356,9 @@ static inline int vmptrst(uint64_t *value) * A wrapper around vmptrst that ignores errors and returns zero if the * vmptrst instruction fails. */ -static inline uint64_t vmptrstz(void) +static inline u64 vmptrstz(void) { - uint64_t value = 0; + u64 value = 0; vmptrst(&value); return value; } @@ -391,8 +391,8 @@ static inline int vmlaunch(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -426,8 +426,8 @@ static inline int vmresume(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -447,10 +447,10 @@ static inline void vmcall(void) "r10", "r11", "r12", "r13", "r14", "r15"); } -static inline int vmread(uint64_t encoding, uint64_t *value) +static inline int vmread(u64 encoding, u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmread(encoding, value); @@ -468,16 +468,16 @@ static inline int vmread(uint64_t encoding, uint64_t *value) * A wrapper around vmread that ignores errors and returns zero if the * vmread instruction fails. */ -static inline uint64_t vmreadz(uint64_t encoding) +static inline u64 vmreadz(u64 encoding) { - uint64_t value = 0; + u64 value = 0; vmread(encoding, &value); return value; } -static inline int vmwrite(uint64_t encoding, uint64_t value) +static inline int vmwrite(u64 encoding, u64 value) { - uint8_t ret; + u8 ret; if (enable_evmcs) return evmcs_vmwrite(encoding, value); @@ -490,43 +490,41 @@ static inline int vmwrite(uint64_t encoding, uint64_t value) return ret; } -static inline uint32_t vmcs_revision(void) +static inline u32 vmcs_revision(void) { return rdmsr(MSR_IA32_VMX_BASIC); } struct vmx_pages { void *vmxon_hva; - uint64_t vmxon_gpa; + u64 vmxon_gpa; void *vmxon; void *vmcs_hva; - uint64_t vmcs_gpa; + u64 vmcs_gpa; void *vmcs; void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; void *msr; void *shadow_vmcs_hva; - uint64_t shadow_vmcs_gpa; + u64 shadow_vmcs_gpa; void *shadow_vmcs; void *vmread_hva; - uint64_t vmread_gpa; + u64 vmread_gpa; void *vmread; void *vmwrite_hva; - uint64_t vmwrite_gpa; + u64 vmwrite_gpa; void *vmwrite; - void *eptp_hva; - uint64_t eptp_gpa; - void *eptp; - void *apic_access_hva; - uint64_t apic_access_gpa; + u64 apic_access_gpa; void *apic_access; + + u64 eptp_gpa; }; union vmx_basic { @@ -552,24 +550,15 @@ union vmx_ctrl_msr { }; }; -struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); +struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, gva_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 vm_enable_ept(struct kvm_vm *vm); void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm); #endif /* SELFTEST_KVM_VMX_H */ |