diff options
Diffstat (limited to 'arch/x86')
88 files changed, 3723 insertions, 1363 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 53f2e7797b1d..5edec175b9bf 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -59,6 +59,7 @@ config X86 # select ACPI_LEGACY_TABLES_LOOKUP if ACPI select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE @@ -71,6 +72,7 @@ config X86 select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CPU_PASID if IOMMU_SVA select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -148,6 +150,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_DEVICES select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_ENTRY @@ -1967,6 +1970,11 @@ config INTEL_TDX_HOST depends on CPU_SUP_INTEL depends on X86_64 depends on KVM_INTEL + depends on X86_X2APIC + select ARCH_KEEP_MEMBLOCK + depends on CONTIG_ALLOC + depends on !KEXEC_CORE + depends on X86_MCE help Intel Trust Domain Extensions (TDX) protects guest VMs from malicious host and certain physical attacks. This option enables necessary TDX diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c index 78e413269791..1655aa56a0a5 100644 --- a/arch/x86/coco/tdx/tdx-shared.c +++ b/arch/x86/coco/tdx/tdx-shared.c @@ -22,13 +22,13 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len, */ switch (pg_level) { case PG_LEVEL_4K: - page_size = 0; + page_size = TDX_PS_4K; break; case PG_LEVEL_2M: - page_size = 1; + page_size = TDX_PS_2M; break; case PG_LEVEL_1G: - page_size = 2; + page_size = TDX_PS_1G; break; default: return 0; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index fecc4fe1d68a..f8f9a9b79395 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -23,10 +23,6 @@ static inline void prefill_possible_map(void) {} #endif /* CONFIG_SMP */ -struct x86_cpu { - struct cpu cpu; -}; - #ifdef CONFIG_HOTPLUG_CPU extern void soft_restart_cpu(void); #endif diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 632c26cdeeda..29cb275a219d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -198,6 +198,7 @@ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ @@ -499,6 +500,7 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 26b628d84594..378ed944b849 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags) KVM_X86_OP(get_if_flag) KVM_X86_OP(flush_tlb_all) KVM_X86_OP(flush_tlb_current) +#if IS_ENABLED(CONFIG_HYPERV) KVM_X86_OP_OPTIONAL(flush_remote_tlbs) KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range) +#endif KVM_X86_OP(flush_tlb_gva) KVM_X86_OP(flush_tlb_guest) KVM_X86_OP(vcpu_pre_run) @@ -135,6 +137,7 @@ KVM_X86_OP(msr_filter_changed) KVM_X86_OP(complete_emulated_msr) KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); +KVM_X86_OP_OPTIONAL(get_untagged_addr) #undef KVM_X86_OP #undef KVM_X86_OP_OPTIONAL diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h index 6c98f4bb4228..058bc636356a 100644 --- a/arch/x86/include/asm/kvm-x86-pmu-ops.h +++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h @@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr) KVM_X86_PMU_OP(set_msr) KVM_X86_PMU_OP(refresh) KVM_X86_PMU_OP(init) -KVM_X86_PMU_OP(reset) +KVM_X86_PMU_OP_OPTIONAL(reset) KVM_X86_PMU_OP_OPTIONAL(deliver_pmi) KVM_X86_PMU_OP_OPTIONAL(cleanup) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6711da000bb7..b5b2d0fde579 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -133,7 +133,8 @@ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ - | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP)) + | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ + | X86_CR4_LAM_SUP)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -500,8 +501,23 @@ struct kvm_pmc { u8 idx; bool is_paused; bool intr; + /* + * Base value of the PMC counter, relative to the *consumed* count in + * the associated perf_event. This value includes counter updates from + * the perf_event and emulated_count since the last time the counter + * was reprogrammed, but it is *not* the current value as seen by the + * guest or userspace. + * + * The count is relative to the associated perf_event so that KVM + * doesn't need to reprogram the perf_event every time the guest writes + * to the counter. + */ u64 counter; - u64 prev_counter; + /* + * PMC events triggered by KVM emulation that haven't been fully + * processed, i.e. haven't undergone overflow detection. + */ + u64 emulated_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; @@ -937,8 +953,10 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; +#ifdef CONFIG_KVM_HYPERV bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; +#endif #ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; #endif @@ -1095,6 +1113,7 @@ enum hv_tsc_page_status { HV_TSC_PAGE_BROKEN, }; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; @@ -1125,9 +1144,9 @@ struct kvm_hv { */ unsigned int synic_auto_eoi_used; - struct hv_partition_assist_pg *hv_pa_pg; struct kvm_hv_syndbg hv_syndbg; }; +#endif struct msr_bitmap_range { u32 flags; @@ -1136,6 +1155,7 @@ struct msr_bitmap_range { unsigned long *bitmap; }; +#ifdef CONFIG_KVM_XEN /* Xen emulation context */ struct kvm_xen { struct mutex xen_lock; @@ -1147,6 +1167,7 @@ struct kvm_xen { struct idr evtchn_ports; unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; }; +#endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, @@ -1255,6 +1276,7 @@ enum kvm_apicv_inhibit { }; struct kvm_arch { + unsigned long vm_type; unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; @@ -1347,8 +1369,13 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; +#ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; +#endif + +#ifdef CONFIG_KVM_XEN struct kvm_xen xen; +#endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; @@ -1406,9 +1433,8 @@ struct kvm_arch { * the MMU lock in read mode + RCU or * the MMU lock in write mode * - * For writes, this list is protected by: - * the MMU lock in read mode + the tdp_mmu_pages_lock or - * the MMU lock in write mode + * For writes, this list is protected by tdp_mmu_pages_lock; see + * below for the details. * * Roots will remain in the list until their tdp_mmu_root_count * drops to zero, at which point the thread that decremented the @@ -1425,8 +1451,10 @@ struct kvm_arch { * - possible_nx_huge_pages; * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU - * It is acceptable, but not necessary, to acquire this lock when - * the thread holds the MMU lock in write mode. + * Because the lock is only taken within the MMU lock, strictly + * speaking it is redundant to acquire this lock when the thread + * holds the MMU lock in write mode. However it often simplifies + * the code to do so. */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ @@ -1441,6 +1469,7 @@ struct kvm_arch { #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; + struct hv_partition_assist_pg *hv_pa_pg; #endif /* * VM-scope maximum vCPU ID. Used to determine the size of structures @@ -1613,9 +1642,11 @@ struct kvm_x86_ops { void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); +#if IS_ENABLED(CONFIG_HYPERV) int (*flush_remote_tlbs)(struct kvm *kvm); int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); +#endif /* * Flush any TLB entries associated with the given GVA. @@ -1761,6 +1792,8 @@ struct kvm_x86_ops { * Returns vCPU specific APICv inhibit reasons */ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); + + gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); }; struct kvm_x86_nested_ops { @@ -1824,6 +1857,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void) #define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); +#if IS_ENABLED(CONFIG_HYPERV) #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { @@ -1835,6 +1869,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) } #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, + u64 nr_pages) +{ + if (!kvm_x86_ops.flush_remote_tlbs_range) + return -EOPNOTSUPP; + + return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages); +} +#endif /* CONFIG_HYPERV */ #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) @@ -1848,6 +1891,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot); + void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -2086,6 +2132,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); +#ifdef CONFIG_KVM_PRIVATE_MEM +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM) +#else +#define kvm_arch_has_private_mem(kvm) false +#endif + static inline u16 kvm_read_ldt(void) { u16 ldt; @@ -2133,16 +2185,15 @@ enum { #define HF_SMM_MASK (1 << 1) #define HF_SMM_INSIDE_NMI_MASK (1 << 2) -# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -# define KVM_ADDRESS_SPACE_NUM 2 +# define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif -#define KVM_ARCH_WANT_MMU_NOTIFIER - int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 737a52b89e64..f1bd7b91b3c6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -541,6 +541,9 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* KeyID partitioning between MKTME and TDX */ +#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 + /* * AMD64 MSRs. Not complete. See the architecture manual for a more * complete list. diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index ccce7ebd8677..fdfd41511b02 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -55,6 +55,12 @@ (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15) +/* TDX supported page sizes from the TDX module ABI. */ +#define TDX_PS_4K 0 +#define TDX_PS_2M 1 +#define TDX_PS_1G 2 +#define TDX_PS_NR (TDX_PS_1G + 1) + #ifndef __ASSEMBLY__ #include <linux/compiler_attributes.h> diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index f3d5305a60fc..eba178996d84 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -24,8 +24,16 @@ #define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP) #define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD) +/* + * TDX module SEAMCALL leaf function error codes + */ +#define TDX_SUCCESS 0ULL +#define TDX_RND_NO_ENTROPY 0x8000020300000000ULL + #ifndef __ASSEMBLY__ +#include <uapi/asm/mce.h> + /* * Used by the #VE exception handler to gather the #VE exception * info from the TDX module. This is a software only structure @@ -83,6 +91,36 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, u64 __seamcall(u64 fn, struct tdx_module_args *args); u64 __seamcall_ret(u64 fn, struct tdx_module_args *args); u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args); +void tdx_init(void); + +#include <asm/archrandom.h> + +typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); + +static inline u64 sc_retry(sc_func_t func, u64 fn, + struct tdx_module_args *args) +{ + int retry = RDRAND_RETRY_LOOPS; + u64 ret; + + do { + ret = func(fn, args); + } while (ret == TDX_RND_NO_ENTROPY && --retry); + + return ret; +} + +#define seamcall(_fn, _args) sc_retry(__seamcall, (_fn), (_args)) +#define seamcall_ret(_fn, _args) sc_retry(__seamcall_ret, (_fn), (_args)) +#define seamcall_saved_ret(_fn, _args) sc_retry(__seamcall_saved_ret, (_fn), (_args)) +int tdx_cpu_enable(void); +int tdx_enable(void); +const char *tdx_dump_mce_info(struct mce *m); +#else +static inline void tdx_init(void) { } +static inline int tdx_cpu_enable(void) { return -ENODEV; } +static inline int tdx_enable(void) { return -ENODEV; } +static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; } #endif /* CONFIG_INTEL_TDX_HOST */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 1a6a1f987949..a448d0964fc0 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -562,4 +562,7 @@ struct kvm_pmu_event_filter { /* x86-specific KVM_EXIT_HYPERCALL flags. */ #define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 4feaa670d578..89c0c8a3fc7e 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -259,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) order); } - /* No multi-function device? */ type = read_pci_config_byte(bus, slot, func, PCI_HEADER_TYPE); - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) break; } } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 94bff381ef20..0b97bcde70c6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,7 @@ #include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> +#include <asm/tdx.h> #include "cpu.h" @@ -1986,6 +1987,7 @@ static __init void identify_boot_cpu(void) setup_cr_pinning(); tsx_init(); + tdx_init(); lkgs_init(); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index fd5ce12c4f9a..bc39252bc54f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,6 +53,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/tdx.h> #include "internal.h" @@ -229,12 +230,20 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } +static const char *mce_dump_aux_info(struct mce *m) +{ + if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE)) + return tdx_dump_mce_info(m); + + return NULL; +} + static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) { struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; - struct page *p; + const char *memmsg; /* * Allow instrumentation around external facilities usage. Not that it @@ -285,6 +294,11 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) } if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); + + memmsg = mce_dump_aux_info(final); + if (memmsg) + pr_emerg(HW_ERR "Machine check: %s\n", memmsg); + if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; @@ -297,6 +311,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) */ if (kexec_crash_loaded()) { if (final && (final->status & MCI_STATUS_ADDRV)) { + struct page *p; p = pfn_to_online_page(final->addr >> PAGE_SHIFT); if (p) SetPageHWPoison(p); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index a6c1867fc7aa..59f4aefc6bc1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -779,13 +779,13 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); - if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) { sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); if (sec > num) early_pci_scan_bus(sec); } - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) return -1; return 0; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 8ff2bf921519..a38d0c93a66e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { - if (unlikely(mc146818_get_time(&curr_time) < 0)) { + if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) { pr_err_ratelimited("unable to read current time from RTC\n"); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index a95d0900e8c6..5bb395551c44 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,8 +24,8 @@ static int kvmclock __initdata = 1; static int kvmclock_vsyscall __initdata = 1; -static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; -static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static int msr_kvm_system_time __ro_after_init; +static int msr_kvm_wall_clock __ro_after_init; static u64 kvm_sched_clock_offset __ro_after_init; static int __init parse_no_kvmclock(char *arg) @@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void) void kvmclock_disable(void) { - native_write_msr(msr_kvm_system_time, 0, 0); + if (msr_kvm_system_time) + native_write_msr(msr_kvm_system_time, 0, 0); } static void __init kvmclock_init_mem(void) @@ -294,7 +295,10 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; - } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + } else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; + } else { return; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 1309b9b05338..2e7066980f3e 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - if (mc146818_get_time(&tm)) { + if (mc146818_get_time(&tm, 1000)) { pr_err("Unable to read current time from RTC\n"); now->tv_sec = now->tv_nsec = 0; return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ec2c21a1844e..84201071dfac 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1031,6 +1031,8 @@ void __init setup_arch(char **cmdline_p) * * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. + * + * Note the host kernel TDX also requires the first 1MB being reserved. */ x86_platform.realmode_reserve(); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 0bab03130033..d42c28b8bfd8 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -35,38 +35,9 @@ #include <asm/io_apic.h> #include <asm/cpu.h> -static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); - #ifdef CONFIG_HOTPLUG_CPU -int arch_register_cpu(int cpu) +bool arch_cpu_is_hotpluggable(int cpu) { - struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu); - - xc->cpu.hotpluggable = cpu > 0; - return register_cpu(&xc->cpu, cpu); -} -EXPORT_SYMBOL(arch_register_cpu); - -void arch_unregister_cpu(int num) -{ - unregister_cpu(&per_cpu(cpu_devices, num).cpu); -} -EXPORT_SYMBOL(arch_unregister_cpu); -#else /* CONFIG_HOTPLUG_CPU */ - -int __init arch_register_cpu(int num) -{ - return register_cpu(&per_cpu(cpu_devices, num).cpu, num); + return cpu > 0; } #endif /* CONFIG_HOTPLUG_CPU */ - -static int __init topology_init(void) -{ - int i; - - for_each_present_cpu(i) - arch_register_cpu(i); - - return 0; -} -subsys_initcall(topology_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b0737a15c470..c3b2f863acf0 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -566,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs) */ static bool try_fixup_enqcmd_gp(void) { -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID u32 pasid; /* @@ -592,7 +592,7 @@ static bool try_fixup_enqcmd_gp(void) if (!mm_valid_pasid(current->mm)) return false; - pasid = current->mm->pasid; + pasid = mm_get_enqcmd_pasid(current->mm); /* * Did this thread already have its PASID activated? diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 950c12868d30..87e3da7b0439 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,17 +23,15 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC - select PREEMPT_NOTIFIERS - select MMU_NOTIFIER + select KVM_COMMON + select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_PFNCACHE - select HAVE_KVM_IRQFD select HAVE_KVM_DIRTY_RING_TSO select HAVE_KVM_DIRTY_RING_ACQ_REL select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_EVENTFD select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO @@ -46,7 +44,6 @@ config KVM select KVM_XFER_TO_GUEST_WORK select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO - select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING help @@ -65,18 +62,30 @@ config KVM config KVM_WERROR bool "Compile KVM with -Werror" - # KASAN may cause the build to fail due to larger frames - default y if X86_64 && !KASAN - # We use the dependency on !COMPILE_TEST to not be enabled - # blindly in allmodconfig or allyesconfig configurations - depends on KVM - depends on (X86_64 && !KASAN) || !COMPILE_TEST - depends on EXPERT + # Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against + # randomized configs from selecting KVM_WERROR=y, which doesn't play + # nice with KASAN. KASAN builds generates warnings for the default + # FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning. + # Building KVM with -Werror and KASAN is still doable via enabling + # the kernel-wide WERROR=y. + depends on KVM && EXPERT && !KASAN help Add -Werror to the build flags for KVM. If in doubt, say "N". +config KVM_SW_PROTECTED_VM + bool "Enable support for KVM software-protected VMs" + depends on EXPERT + depends on KVM && X86_64 + select KVM_GENERIC_PRIVATE_MEM + help + Enable support for KVM software-protected VMs. Currently "protected" + means the VM can be backed with memory provided by + KVM_CREATE_GUEST_MEMFD. + + If unsure, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL @@ -129,6 +138,20 @@ config KVM_SMM If unsure, say Y. +config KVM_HYPERV + bool "Support for Microsoft Hyper-V emulation" + depends on KVM + default y + help + Provides KVM support for emulating Microsoft Hyper-V. This allows KVM + to expose a subset of the paravirtualized interfaces defined in the + Hyper-V Hypervisor Top-Level Functional Specification (TLFS): + https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs + These interfaces are required for the correct and performant functioning + of Windows and Hyper-V guests on KVM. + + If unsure, say "Y". + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 80e3fe184d17..475b5fa917a6 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ + debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o -ifdef CONFIG_HYPERV -kvm-y += kvm_onhyperv.o -endif - kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_HYPERV) += hyperv.o kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/hyperv.o vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o + kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ - svm/sev.o svm/hyperv.o + svm/sev.o +kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm_onhyperv.o endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 42d3f47f4c07..adba49afb5fe 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) { +#ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, KVM_CPUID_INDEX_NOT_SIGNIFICANT); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +#else + return false; +#endif } static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) @@ -433,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } +#ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(e2, nent)) { r = kvm_hv_vcpu_init(vcpu); if (r) return r; } +#endif r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -469,7 +475,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent)); + e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e)); if (IS_ERR(e)) return PTR_ERR(e); @@ -513,7 +519,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent)); + e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2)); if (IS_ERR(e2)) return PTR_ERR(e2); } @@ -671,7 +677,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_1_EAX, F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | - F(AMX_FP16) | F(AVX_IFMA) + F(AMX_FP16) | F(AVX_IFMA) | F(LAM) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, @@ -679,6 +685,11 @@ void kvm_set_cpu_caps(void) F(AMX_COMPLEX) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); @@ -960,13 +971,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -976,6 +987,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = 0; entry->ecx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 0b90532b6e26..856e3037e74f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return !(gpa & vcpu->arch.reserved_gpa_bits); } -static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - return !kvm_vcpu_is_legal_gpa(vcpu, gpa); -} - static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t alignment) { @@ -279,4 +274,12 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu, vcpu->arch.governed_features.enabled); } +static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + if (guest_can_use(vcpu, X86_FEATURE_LAM)) + cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57); + + return kvm_vcpu_is_legal_gpa(vcpu, cr3); +} + #endif diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index eea6ea7f14af..95ea1a1f7403 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) mutex_lock(&kvm->slots_lock); write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { int bkt; slots = __kvm_memslots(kvm, i); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2673cd5c46cb..e223043ef5b2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -687,8 +687,8 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned *max_size, unsigned size, - bool write, bool fetch, - enum x86emul_mode mode, ulong *linear) + enum x86emul_mode mode, ulong *linear, + unsigned int flags) { struct desc_struct desc; bool usable; @@ -701,7 +701,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: - *linear = la; + *linear = la = ctxt->ops->get_untagged_addr(ctxt, la, flags); va_bits = ctxt_virt_addr_bits(ctxt); if (!__is_canonical_address(la, va_bits)) goto bad; @@ -717,11 +717,11 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (!usable) goto bad; /* code segment in protected mode or read-only data segment */ - if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) - || !(desc.type & 2)) && write) + if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) && + (flags & X86EMUL_F_WRITE)) goto bad; /* unreadable code segment */ - if (!fetch && (desc.type & 8) && !(desc.type & 2)) + if (!(flags & X86EMUL_F_FETCH) && (desc.type & 8) && !(desc.type & 2)) goto bad; lim = desc_limit_scaled(&desc); if (!(desc.type & 8) && (desc.type & 4)) { @@ -757,8 +757,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ulong *linear) { unsigned max_size; - return __linearize(ctxt, addr, &max_size, size, write, false, - ctxt->mode, linear); + return __linearize(ctxt, addr, &max_size, size, ctxt->mode, linear, + write ? X86EMUL_F_WRITE : 0); } static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) @@ -771,7 +771,8 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; @@ -907,8 +908,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size) * boundary check itself. Instead, we use max_size to check * against op_size. */ - rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode, - &linear); + rc = __linearize(ctxt, addr, &max_size, 0, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (unlikely(rc != X86EMUL_CONTINUE)) return rc; @@ -3439,8 +3440,10 @@ static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; ulong linear; + unsigned int max_size; - rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear); + rc = __linearize(ctxt, ctxt->src.addr.mem, &max_size, 1, ctxt->mode, + &linear, X86EMUL_F_INVLPG); if (rc == X86EMUL_CONTINUE) ctxt->ops->invlpg(ctxt, linear); /* Disable writeback. */ diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h index 423a73395c10..ad463b1ed4e4 100644 --- a/arch/x86/kvm/governed_features.h +++ b/arch/x86/kvm/governed_features.h @@ -16,6 +16,7 @@ KVM_GOVERNED_X86_FEATURE(PAUSEFILTER) KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD) KVM_GOVERNED_X86_FEATURE(VGIF) KVM_GOVERNED_X86_FEATURE(VNMI) +KVM_GOVERNED_X86_FEATURE(LAM) #undef KVM_GOVERNED_X86_FEATURE #undef KVM_GOVERNED_FEATURE diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index f83b8db72b11..1dc0b6604526 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,6 +24,8 @@ #include <linux/kvm_host.h> #include "x86.h" +#ifdef CONFIG_KVM_HYPERV + /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -105,6 +107,17 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap); +} + +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && + test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap); +} + void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); @@ -236,6 +249,76 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) return kvm_hv_get_assist_page(vcpu); } +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, + bool tdp_enabled) +{ + /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && tdp_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); +} + int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) {} +static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {} +static inline void kvm_hv_init_vm(struct kvm *kvm) {} +static inline void kvm_hv_destroy_vm(struct kvm *kvm) {} +static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {} +static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + return HV_STATUS_ACCESS_DENIED; +} +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} +static inline void kvm_hv_free_pa_page(struct kvm *kvm) {} +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {} +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {} +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {} +#endif /* CONFIG_KVM_HYPERV */ -#endif +#endif /* __ARCH_X86_KVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index b2c397dd2bc6..ad9ca8a60144 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; +#ifdef CONFIG_KVM_XEN if (kvm_xen_has_interrupt(v)) return v->kvm->arch.xen.upcall_vector; +#endif if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 16d076a1b91a..68f3f6c26046 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } - +#ifdef CONFIG_KVM_HYPERV static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); } +#endif int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, int r; switch (e->type) { +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: return kvm_hv_set_sint(e, kvm, irq_source_id, level, line_status); +#endif case KVM_IRQ_ROUTING_MSI: if (kvm_msi_route_invalid(kvm, e)) @@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_msi_route_invalid(kvm, e)) return -EINVAL; break; +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#endif #ifdef CONFIG_KVM_XEN case KVM_IRQ_ROUTING_XEN_EVTCHN: return kvm_xen_setup_evtchn(kvm, e, ue); @@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, void kvm_arch_irq_routing_update(struct kvm *kvm) { +#ifdef CONFIG_KVM_HYPERV kvm_hv_irq_routing_update(kvm); +#endif } diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index be7aeb9b8ea3..e6d149825169 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -88,6 +88,12 @@ struct x86_instruction_info { #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ #define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ +/* x86-specific emulation flags */ +#define X86EMUL_F_WRITE BIT(0) +#define X86EMUL_F_FETCH BIT(1) +#define X86EMUL_F_IMPLICIT BIT(2) +#define X86EMUL_F_INVLPG BIT(3) + struct x86_emulate_ops { void (*vm_bugged)(struct x86_emulate_ctxt *ctxt); /* @@ -224,6 +230,9 @@ struct x86_emulate_ops { int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); + + gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, + unsigned int flags); }; /* Type, address-of, and value of an instruction's operand. */ diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index f9ca3e7432b2..eefab3dc8498 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -10,6 +10,26 @@ int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); +static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu) +{ + /* + * Partition assist page is something which Hyper-V running in L0 + * requires from KVM running in L1 before direct TLB flush for L2 + * guests can be enabled. KVM doesn't currently use the page but to + * comply with TLFS it still needs to be allocated. For now, this + * is a single page shared among all vCPUs. + */ + struct hv_partition_assist_pg **p_hv_pa_pg = + &vcpu->kvm->arch.hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + + if (!*p_hv_pa_pg) + return INVALID_PAGE; + + return __pa(*p_hv_pa_pg); +} #else /* !CONFIG_HYPERV */ static inline int hv_flush_remote_tlbs(struct kvm *kvm) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 245b20973cae..3242f3da2457 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1475,8 +1475,7 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (to_hv_vcpu(apic->vcpu) && - test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap)) + if (kvm_hv_synic_has_vector(apic->vcpu, vector)) kvm_hv_synic_send_eoi(apic->vcpu, vector); kvm_ioapic_send_eoi(apic, vector); @@ -2905,7 +2904,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) */ apic_clear_irr(vector, apic); - if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) { + if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) { /* * For auto-EOI interrupts, there might be another pending * interrupt above PPR, so check whether to raise another diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bb8c86eefac0..60f21bb4c27b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -146,6 +146,14 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } +static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) +{ + if (!guest_can_use(vcpu, X86_FEATURE_LAM)) + return 0; + + return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); +} + static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { u64 root_hpa = vcpu->arch.mmu->root.hpa; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0b1f991b9a31..2d6cdeab1f8a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -271,15 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, static inline bool kvm_available_flush_remote_tlbs_range(void) { +#if IS_ENABLED(CONFIG_HYPERV) return kvm_x86_ops.flush_remote_tlbs_range; -} - -int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) -{ - if (!kvm_x86_ops.flush_remote_tlbs_range) - return -EOPNOTSUPP; - - return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages); +#else + return false; +#endif } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); @@ -795,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +/* + * The most significant bit in disallow_lpage tracks whether or not memory + * attributes are mixed, i.e. not identical for all gfns at the current level. + * The lower order bits are used to refcount other cases where a hugepage is + * disallowed, e.g. if KVM has shadow a page table at the gfn. + */ +#define KVM_LPAGE_MIXED_FLAG BIT(31) + static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; - int i; + int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); + + old = linfo->disallow_lpage; linfo->disallow_lpage += count; - WARN_ON_ONCE(linfo->disallow_lpage < 0); + WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } @@ -1382,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); if (READ_ONCE(eager_page_split)) - kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K); + kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K); kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); @@ -2840,9 +2846,9 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, /* * Recheck after taking the spinlock, a different vCPU * may have since marked the page unsync. A false - * positive on the unprotected check above is not + * negative on the unprotected check above is not * possible as clearing sp->unsync _must_ hold mmu_lock - * for write, i.e. unsync cannot transition from 0->1 + * for write, i.e. unsync cannot transition from 1->0 * while this CPU holds mmu_lock for read (or write). */ if (READ_ONCE(sp->unsync)) @@ -3056,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3137,9 +3143,9 @@ out: return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3151,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3158,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3178,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3556,7 +3576,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, return; if (is_tdp_mmu_page(sp)) - kvm_tdp_mmu_put_root(kvm, sp, false); + kvm_tdp_mmu_put_root(kvm, sp); else if (!--sp->root_count && sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3739,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) kvm_page_track_write_tracking_enabled(kvm)) goto out_success; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* @@ -3782,7 +3802,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) hpa_t root; root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); - root_gfn = root_pgd >> PAGE_SHIFT; + root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT; if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { mmu->root.hpa = kvm_mmu_get_dummy_root(); @@ -4259,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + + return RET_PF_CONTINUE; +} + static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -4291,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -4366,7 +4443,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); + mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -6228,7 +6305,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (!kvm_memslots_have_rmaps(kvm)) return flush; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { @@ -6260,7 +6337,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, 0, -1ul); + kvm_mmu_invalidate_begin(kvm); + + kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6270,7 +6349,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, 0, -1ul); + kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } @@ -6723,7 +6802,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ - gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, @@ -7176,3 +7255,163 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) if (kvm->arch.nx_huge_page_recovery_thread) kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + return kvm_unmap_gfn_range(kvm, range); +} + +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + +static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, int level, unsigned long attrs) +{ + const unsigned long start = gfn; + const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); + + if (level == PG_LEVEL_2M) + return kvm_range_has_memory_attributes(kvm, start, end, attrs); + + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { + if (hugepage_test_mixed(slot, gfn, level - 1) || + attrs != kvm_get_memory_attributes(kvm, gfn)) + return false; + } + return true; +} + +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + unsigned long attrs = range->arg.attributes; + struct kvm_memory_slot *slot = range->slot; + int level; + + lockdep_assert_held_write(&kvm->mmu_lock); + lockdep_assert_held(&kvm->slots_lock); + + /* + * Calculate which ranges can be mapped with hugepages even if the slot + * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over + * a range that has PRIVATE GFNs, and conversely converting a range to + * SHARED may now allow hugepages. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + /* + * The sequence matters here: upper levels consume the result of lower + * level's scanning. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn = gfn_round_for_level(range->start, level); + + /* Process the head page if it straddles the range. */ + if (gfn != range->start || gfn + nr_pages > range->end) { + /* + * Skip mixed tracking if the aligned gfn isn't covered + * by the memslot, KVM can't use a hugepage due to the + * misaligned address regardless of memory attributes. + */ + if (gfn >= slot->base_gfn) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + gfn += nr_pages; + } + + /* + * Pages entirely covered by the range are guaranteed to have + * only the attributes which were just set. + */ + for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) + hugepage_clear_mixed(slot, gfn, level); + + /* + * Process the last tail page if it straddles the range and is + * contained by the memslot. Like the head page, KVM can't + * create a hugepage if the slot size is misaligned. + */ + if (gfn < range->end && + (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } + return false; +} + +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + int level; + + if (!kvm_arch_has_private_mem(kvm)) + return; + + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + /* + * Don't bother tracking mixed attributes for pages that can't + * be huge due to alignment, i.e. process only pages that are + * entirely contained by the memslot. + */ + gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); + gfn_t start = gfn_round_for_level(slot->base_gfn, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn; + + if (start < slot->base_gfn) + start += nr_pages; + + /* + * Unlike setting attributes, every potential hugepage needs to + * be manually checked as the attributes may already be mixed. + */ + for (gfn = start; gfn < end; gfn += nr_pages) { + unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); + + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } +} +#endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index decc1f153669..0669a8a668ca 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -13,6 +13,7 @@ #endif /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */ +#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12) #define __PT_LEVEL_SHIFT(level, bits_per_level) \ (PAGE_SHIFT + ((level) - 1) * (bits_per_level)) #define __PT_INDEX(address, level, bits_per_level) \ @@ -201,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* @@ -296,6 +298,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), }; int r; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index c85255073f67..4d4e98fe4f35 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -62,7 +62,7 @@ #endif /* Common logic, but per-type values. These also need to be undefined. */ -#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) +#define PT_BASE_ADDR_MASK ((pt_element_t)__PT_BASE_ADDR_MASK) #define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6cd4dd631a2f..6ae19b4ee5b1 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -73,11 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared) +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) { - kvm_lockdep_assert_mmu_lock_held(kvm, shared); - if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; @@ -106,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared, bool only_valid) + bool only_valid) { struct kvm_mmu_page *next_root; + /* + * While the roots themselves are RCU-protected, fields such as + * role.invalid are protected by mmu_lock. + */ + lockdep_assert_held(&kvm->mmu_lock); + rcu_read_lock(); if (prev_root) @@ -132,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, rcu_read_unlock(); if (prev_root) - kvm_tdp_mmu_put_root(kvm, prev_root, shared); + kvm_tdp_mmu_put_root(kvm, prev_root); return next_root; } @@ -144,26 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * recent root. (Unless keeping a live reference is desirable.) * * If shared is set, this function is operating under the MMU lock in read - * mode. In the unlikely event that this thread must free a root, the lock - * will be temporarily dropped and reacquired in write mode. + * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (kvm_mmu_page_as_id(_root) != _as_id) { \ } else -#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ - if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ - } else +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -276,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) * * @kvm: kvm instance * @sp: the page to be removed - * @shared: This operation may not be running under the exclusive use of - * the MMU lock and the operation must synchronize with other - * threads that might be adding or removing pages. */ -static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, - bool shared) +static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { tdp_unaccount_mmu_page(kvm, sp); if (!sp->nx_huge_page_disallowed) return; - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp); - - if (shared) - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -326,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) trace_kvm_mmu_prepare_zap_page(sp); - tdp_mmu_unlink_sp(kvm, sp, shared); + tdp_mmu_unlink_sp(kvm, sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { tdp_ptep_t sptep = pt + i; @@ -832,7 +821,8 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -854,7 +844,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) tdp_mmu_zap_root(kvm, root, false); } @@ -868,7 +859,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) read_lock(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) continue; @@ -891,7 +882,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the root must be reachable by mmu_notifiers while it's being * zapped */ - kvm_tdp_mmu_put_root(kvm, root, true); + kvm_tdp_mmu_put_root(kvm, root); } read_unlock(&kvm->mmu_lock); @@ -1125,7 +1116,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1314,7 +1305,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); @@ -1346,6 +1337,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, { struct kvm_mmu_page *sp; + kvm_lockdep_assert_mmu_lock_held(kvm, shared); + /* * Since we are allocating while under the MMU lock we have to be * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct @@ -1496,11 +1489,10 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, int r = 0; kvm_lockdep_assert_mmu_lock_held(kvm, shared); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) { + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) { r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared); if (r) { - kvm_tdp_mmu_put_root(kvm, root, shared); + kvm_tdp_mmu_put_root(kvm, root); break; } } @@ -1522,12 +1514,13 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) continue; - if (!is_shadow_present_pte(iter.old_spte)) + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; KVM_MMU_WARN_ON(kvm_ad_enabled() && @@ -1560,8 +1553,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1695,8 +1687,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) zap_collapsible_spte_range(kvm, root, slot); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 733a3aef3a96..20d97aa46c49 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -17,8 +17,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) return refcount_inc_not_zero(&root->tdp_mmu_root_count); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 9ae07db6f0f6..87cc6c8809ad 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -127,9 +127,9 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; /* - * Ignore overflow events for counters that are scheduled to be - * reprogrammed, e.g. if a PMI for the previous event races with KVM's - * handling of a related guest WRMSR. + * Ignore asynchronous overflow events for counters that are scheduled + * to be reprogrammed, e.g. if a PMI for the previous event races with + * KVM's handling of a related guest WRMSR. */ if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi)) return; @@ -161,6 +161,15 @@ static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) return 1; } +static u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) +{ + u64 sample_period = (-counter_value) & pmc_bitmask(pmc); + + if (!sample_period) + sample_period = pmc_bitmask(pmc) + 1; + return sample_period; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -215,17 +224,30 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, return 0; } -static void pmc_pause_counter(struct kvm_pmc *pmc) +static bool pmc_pause_counter(struct kvm_pmc *pmc) { u64 counter = pmc->counter; - - if (!pmc->perf_event || pmc->is_paused) - return; + u64 prev_counter; /* update counter, reset event value to avoid redundant accumulation */ - counter += perf_event_pause(pmc->perf_event, true); + if (pmc->perf_event && !pmc->is_paused) + counter += perf_event_pause(pmc->perf_event, true); + + /* + * Snapshot the previous counter *after* accumulating state from perf. + * If overflow already happened, hardware (via perf) is responsible for + * generating a PMI. KVM just needs to detect overflow on emulated + * counter events that haven't yet been processed. + */ + prev_counter = counter & pmc_bitmask(pmc); + + counter += pmc->emulated_counter; pmc->counter = counter & pmc_bitmask(pmc); + + pmc->emulated_counter = 0; pmc->is_paused = true; + + return pmc->counter < prev_counter; } static bool pmc_resume_counter(struct kvm_pmc *pmc) @@ -250,6 +272,51 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } +static void pmc_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); + } +} + +static void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + +void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + /* + * Drop any unconsumed accumulated counts, the WRMSR is a write, not a + * read-modify-write. Adjust the counter value so that its value is + * relative to the current count, as reading the current count from + * perf is faster than pausing and repgrogramming the event in order to + * reset it to '0'. Note, this very sneakily offsets the accumulated + * emulated count too, by using pmc_read_counter()! + */ + pmc->emulated_counter = 0; + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); + pmc_update_sample_period(pmc); +} +EXPORT_SYMBOL_GPL(pmc_write_counter); + static int filter_cmp(const void *pa, const void *pb, u64 mask) { u64 a = *(u64 *)pa & mask; @@ -383,14 +450,15 @@ static void reprogram_counter(struct kvm_pmc *pmc) struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; u64 new_config = eventsel; + bool emulate_overflow; u8 fixed_ctr_ctrl; - pmc_pause_counter(pmc); + emulate_overflow = pmc_pause_counter(pmc); if (!pmc_event_is_allowed(pmc)) goto reprogram_complete; - if (pmc->counter < pmc->prev_counter) + if (emulate_overflow) __kvm_perf_overflow(pmc, false); if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) @@ -430,7 +498,6 @@ static void reprogram_counter(struct kvm_pmc *pmc) reprogram_complete: clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); - pmc->prev_counter = 0; } void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) @@ -639,32 +706,60 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -/* refresh PMU settings. This function generally is called when underlying - * settings are changed (such as changes of PMU CPUID by guest VMs), which - * should rarely happen. +static void kvm_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + pmu->need_cleanup = false; + + bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX); + + for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { + pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); + if (!pmc) + continue; + + pmc_stop_counter(pmc); + pmc->counter = 0; + pmc->emulated_counter = 0; + + if (pmc_is_gp(pmc)) + pmc->eventsel = 0; + } + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; + + static_call_cond(kvm_x86_pmu_reset)(vcpu); +} + + +/* + * Refresh the PMU configuration for the vCPU, e.g. if userspace changes CPUID + * and/or PERF_CAPABILITIES. */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) return; + /* + * Stop/release all existing counters/events before realizing the new + * vPMU model. + */ + kvm_pmu_reset(vcpu); + bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); static_call(kvm_x86_pmu_refresh)(vcpu); } -void kvm_pmu_reset(struct kvm_vcpu *vcpu) -{ - static_call(kvm_x86_pmu_reset)(vcpu); -} - void kvm_pmu_init(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - pmu->event_count = 0; - pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } @@ -700,8 +795,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { - pmc->prev_counter = pmc->counter; - pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); + pmc->emulated_counter++; kvm_pmu_request_counter_reprogram(pmc); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 1d64113de488..7caeb3d8d4fd 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -66,7 +66,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) { u64 counter, enabled, running; - counter = pmc->counter; + counter = pmc->counter + pmc->emulated_counter; + if (pmc->perf_event && !pmc->is_paused) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); @@ -74,29 +75,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) -{ - pmc->counter += val - pmc_read_counter(pmc); - pmc->counter &= pmc_bitmask(pmc); -} - -static inline void pmc_release_perf_event(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - pmc->current_config = 0; - pmc_to_pmu(pmc)->event_count--; - } -} - -static inline void pmc_stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); - pmc_release_perf_event(pmc); - } -} +void pmc_write_counter(struct kvm_pmc *pmc, u64 val); static inline bool pmc_is_gp(struct kvm_pmc *pmc) { @@ -146,25 +125,6 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) return NULL; } -static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) -{ - u64 sample_period = (-counter_value) & pmc_bitmask(pmc); - - if (!sample_period) - sample_period = pmc_bitmask(pmc) + 1; - return sample_period; -} - -static inline void pmc_update_sample_period(struct kvm_pmc *pmc) -{ - if (!pmc->perf_event || pmc->is_paused || - !is_sampling_event(pmc->perf_event)) - return; - - perf_event_period(pmc->perf_event, - get_sample_period(pmc, pmc->counter)); -} - static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -261,7 +221,6 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index b81650678375..aadefcaa9561 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs { CPUID_7_1_EDX, CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -106,18 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) - return KVM_X86_FEATURE_SGX_EDECCSSA; - else if (x86_feature == X86_FEATURE_CONSTANT_TSC) - return KVM_X86_FEATURE_CONSTANT_TSC; - else if (x86_feature == X86_FEATURE_PERFMON_V2) - return KVM_X86_FEATURE_PERFMON_V2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA); + KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); + KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 02f4784b5d44..d3f8bfc05832 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -11,6 +11,7 @@ #include "../hyperv.h" #include "svm.h" +#ifdef CONFIG_KVM_HYPERV static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) } void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {} +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_KVM_HYPERV */ #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 3fea8c47679e..dee62362a360 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm) */ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; int i; /* @@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) * - Nested hypervisor (L1) is using Hyper-V emulation interface and * tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!svm->nested.force_msr_bitmap_recalc && - kvm_hv_hypercall_enabled(&svm->vcpu) && - hve->hv_enlightenments_control.msr_bitmap && - (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) - goto set_msrpm_base_pa; +#ifdef CONFIG_KVM_HYPERV + if (!svm->nested.force_msr_bitmap_recalc) { + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + + if (kvm_hv_hypercall_enabled(&svm->vcpu) && + hve->hv_enlightenments_control.msr_bitmap && + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) + goto set_msrpm_base_pa; + } +#endif if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; @@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.force_msr_bitmap_recalc = false; +#ifdef CONFIG_KVM_HYPERV set_msrpm_base_pa: +#endif svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; @@ -247,18 +253,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); } -static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) -{ - /* Nested FLUSHBYASID is not supported yet. */ - switch(tlb_ctl) { - case TLB_CONTROL_DO_NOTHING: - case TLB_CONTROL_FLUSH_ALL_ASID: - return true; - default: - return false; - } -} - static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, struct vmcb_ctrl_area_cached *control) { @@ -278,9 +272,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, IOPM_SIZE))) return false; - if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) - return false; - if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && !vmcb12_is_intercept(control, INTERCEPT_NMI))) { return false; @@ -311,7 +302,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) { if (CC(!(save->cr4 & X86_CR4_PAE)) || CC(!(save->cr0 & X86_CR0_PE)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3))) return false; } @@ -378,12 +369,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, to->msrpm_base_pa &= ~0x0fffULL; to->iopm_base_pa &= ~0x0fffULL; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V extensions (Enlightened VMCB) */ if (kvm_hv_hypercall_enabled(vcpu)) { to->clean = from->clean; memcpy(&to->hv_enlightenments, &from->hv_enlightenments, sizeof(to->hv_enlightenments)); } +#endif } void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, @@ -487,14 +480,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && npt_enabled) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled); /* * TODO: optimize unconditional TLB flush/MMU sync. A partial list of @@ -520,7 +507,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_npt, bool reload_pdptrs) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 373ff6a6687b..b6a7ad4d6914 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -161,7 +161,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ @@ -233,21 +232,6 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) } } -static void amd_pmu_reset(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int i; - - for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - pmu->global_ctrl = pmu->global_status = 0; -} - struct kvm_pmu_ops amd_pmu_ops __initdata = { .hw_event_available = amd_hw_event_available, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, @@ -259,7 +243,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .set_msr = amd_pmu_set_msr, .refresh = amd_pmu_refresh, .init = amd_pmu_init, - .reset = amd_pmu_reset, .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, .MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6ee925d66648..f760106c31f8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2191,10 +2191,13 @@ void __init sev_hardware_setup(void) /* * SEV must obviously be supported in hardware. Sanity check that the * CPU supports decode assists, which is mandatory for SEV guests to - * support instruction emulation. + * support instruction emulation. Ditto for flushing by ASID, as SEV + * guests are bound to a single ASID, i.e. KVM can't rotate to a new + * ASID to effect a TLB flush. */ if (!boot_cpu_has(X86_FEATURE_SEV) || - WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; /* Retrieve SEV CPUID information */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7fb51424fc74..e90b429c84f1 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3563,8 +3563,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - svm->nmi_masked = true; - svm_set_iret_intercept(svm); + /* + * No need to manually track NMI masking when vNMI is enabled, hardware + * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the + * case where software directly injects an NMI. + */ + if (!is_vnmi_enabled(svm)) { + svm->nmi_masked = true; + svm_set_iret_intercept(svm); + } ++vcpu->stat.nmi_injections; } @@ -5079,6 +5086,13 @@ static __init void svm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SVM); kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); + /* + * KVM currently flushes TLBs on *every* nested SVM transition, + * and so for all intents and purposes KVM supports flushing by + * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush. + */ + kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID); + if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index c409f934c377..8ef95139cd24 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -148,7 +148,9 @@ struct vmcb_ctrl_area_cached { u64 virt_ext; u32 clean; union { +#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV) struct hv_vmcb_enlightenments hv_enlightenments; +#endif u8 reserved_sw[32]; }; }; diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 7af8422d3382..3971b3ea5d04 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -18,18 +18,14 @@ int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_vmcb_enlightenments *hve; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); - - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; - hve->partition_assist_page = __pa(*p_hv_pa_pg); + hve->partition_assist_page = partition_assist_page; hve->hv_vm_id = (unsigned long)vcpu->kvm; if (!hve->hv_enlightenments_control.nested_flush_hypercall) { hve->hv_enlightenments_control.nested_flush_hypercall = 1; diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index ef2ebabb059c..9499f9c6b077 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -10: cmpb $0, kvm_rebooting +10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 -30: cmpb $0, kvm_rebooting +30: cmpb $0, _ASM_RIP(kvm_rebooting) jne 4b ud2 -50: cmpb $0, kvm_rebooting +50: cmpb $0, _ASM_RIP(kvm_rebooting) jne 6b ud2 -70: cmpb $0, kvm_rebooting +70: cmpb $0, _ASM_RIP(kvm_rebooting) jne 8b ud2 @@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -3: cmpb $0, kvm_rebooting +3: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 313b8bb5b8a7..fab6a1ad98dc 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,419 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_ENABLE_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - -#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) -#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ - {EVMCS1_OFFSET(name), clean_field} - -const struct evmcs_field vmcs_field_to_evmcs_1[] = { - /* 64 bit rw */ - EVMCS1_FIELD(GUEST_RIP, guest_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_RSP, guest_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR0, host_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR3, host_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR4, host_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_RIP, host_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), - EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(TSC_OFFSET, tsc_offset, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR0, guest_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR3, guest_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR4, guest_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_DR7, guest_dr7, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_RSP, host_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(EPT_POINTER, ept_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), - EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - /* - * Not used by KVM: - * - * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x0000682A, guest_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1A, host_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - */ - - /* 64 bit read only */ - EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - /* - * Not defined in KVM: - * - * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - */ - EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* - * No mask defined in the spec as Hyper-V doesn't currently support - * these. Future proof by resetting the whole clean field mask on - * access. - */ - EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 32 bit rw */ - EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), - EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), - EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), - EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, - vm_entry_exception_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - - /* 32 bit read only */ - EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* No mask defined in the spec (not used) */ - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 16 bit rw */ - EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), -}; -const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); - u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); @@ -608,40 +195,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -/* - * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption - * is: in case a feature has corresponding fields in eVMCS described and it was - * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a - * feature which has no corresponding eVMCS field, this likely means that KVM - * needs to be updated. - */ -#define evmcs_check_vmcs_conf(field, ctrl) \ - do { \ - typeof(vmcs_conf->field) unsupported; \ - \ - unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ - if (unsupported) { \ - pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ - (u64)unsupported); \ - vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ - } \ - } \ - while (0) - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); - evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); - evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); - evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); - evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); - evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); -} -#endif - int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9623fe1651c4..a87407412615 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -2,199 +2,89 @@ #ifndef __KVM_X86_VMX_HYPERV_H #define __KVM_X86_VMX_HYPERV_H -#include <linux/jump_label.h> - -#include <asm/hyperv-tlfs.h> -#include <asm/mshyperv.h> -#include <asm/vmx.h> - -#include "../hyperv.h" - -#include "capabilities.h" -#include "vmcs.h" +#include <linux/kvm_host.h> #include "vmcs12.h" +#include "vmx.h" -struct vmcs_config; - -#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) - -#define KVM_EVMCS_VERSION 1 +#define EVMPTR_INVALID (-1ULL) +#define EVMPTR_MAP_PENDING (-2ULL) -struct evmcs_field { - u16 offset; - u16 clean_field; +enum nested_evmptrld_status { + EVMPTRLD_DISABLED, + EVMPTRLD_SUCCEEDED, + EVMPTRLD_VMFAIL, + EVMPTRLD_ERROR, }; -extern const struct evmcs_field vmcs_field_to_evmcs_1[]; -extern const unsigned int nr_evmcs_1_fields; - -static __always_inline int evmcs_field_offset(unsigned long field, - u16 *clean_field) -{ - unsigned int index = ROL16(field, 6); - const struct evmcs_field *evmcs_field; - - if (unlikely(index >= nr_evmcs_1_fields)) - return -ENOENT; - - evmcs_field = &vmcs_field_to_evmcs_1[index]; - - /* - * Use offset=0 to detect holes in eVMCS. This offset belongs to - * 'revision_id' but this field has no encoding and is supposed to - * be accessed directly. - */ - if (unlikely(!evmcs_field->offset)) - return -ENOENT; - - if (clean_field) - *clean_field = evmcs_field->clean_field; - - return evmcs_field->offset; -} - -static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, - unsigned long field, u16 offset) +#ifdef CONFIG_KVM_HYPERV +static inline bool evmptr_is_valid(u64 evmptr) { - /* - * vmcs12_read_any() doesn't care whether the supplied structure - * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes - * the exact offset of the required field, use it for convenience - * here. - */ - return vmcs12_read_any((void *)evmcs, field, offset); + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; } -#if IS_ENABLED(CONFIG_HYPERV) - -DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -static __always_inline bool kvm_is_using_evmcs(void) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - return static_branch_unlikely(&__kvm_is_using_evmcs); + return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); } -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = evmcs_field_offset(field, clean_field); - - WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); - return offset; + return evmptr != EVMPTR_INVALID; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u64 *)((char *)current_evmcs + offset) = value; - - current_evmcs->hv_clean_fields &= ~clean_field; + return evmptr_is_set(vmx->nested.hv_evmcs_vmptr); } -static __always_inline void evmcs_write32(unsigned long field, u32 value) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u32 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + return vmx->nested.hv_evmcs; } -static __always_inline void evmcs_write16(unsigned long field, u16 value) +static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u16 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + /* + * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and + * eVMCS has been explicitly enabled by userspace. + */ + return vcpu->arch.hyperv_enabled && + to_vmx(vcpu)->nested.enlightened_vmcs_enabled; } -static __always_inline u64 evmcs_read64(unsigned long field) +u64 nested_get_evmptr(struct kvm_vcpu *vcpu); +uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); +int nested_enable_evmcs(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); +int nested_evmcs_check_controls(struct vmcs12 *vmcs12); +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else +static inline bool evmptr_is_valid(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u64 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u32 evmcs_read32(unsigned long field) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u32 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u16 evmcs_read16(unsigned long field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u16 *)((char *)current_evmcs + offset); + return false; } -static inline void evmcs_load(u64 phys_addr) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - struct hv_vp_assist_page *vp_ap = - hv_get_vp_assist_page(smp_processor_id()); - - if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) - vp_ap->nested_control.features.directhypercall = 1; - vp_ap->current_nested_vmcs = phys_addr; - vp_ap->enlighten_vmentry = 1; + return false; } -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); -#else /* !IS_ENABLED(CONFIG_HYPERV) */ -static __always_inline bool kvm_is_using_evmcs(void) { return false; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static __always_inline void evmcs_write32(unsigned long field, u32 value) {} -static __always_inline void evmcs_write16(unsigned long field, u16 value) {} -static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } -static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } -static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } -static inline void evmcs_load(u64 phys_addr) {} -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - -#define EVMPTR_INVALID (-1ULL) -#define EVMPTR_MAP_PENDING (-2ULL) - -static inline bool evmptr_is_valid(u64 evmptr) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; + return NULL; } - -enum nested_evmptrld_status { - EVMPTRLD_DISABLED, - EVMPTRLD_SUCCEEDED, - EVMPTRLD_VMFAIL, - EVMPTRLD_ERROR, -}; - -u64 nested_get_evmptr(struct kvm_vcpu *vcpu); -uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); -int nested_enable_evmcs(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version); -void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); -int nested_evmcs_check_controls(struct vmcs12 *vmcs12); -bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); -void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#endif #endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c new file mode 100644 index 000000000000..904bfcd1519b --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common code for working with Enlightened VMCS which is + * used both by Hyper-V on KVM and KVM on Hyper-V. + */ + +#include "hyperv_evmcs.h" + +#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) +#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ + {EVMCS1_OFFSET(name), clean_field} + +const struct evmcs_field vmcs_field_to_evmcs_1[] = { + /* 64 bit rw */ + EVMCS1_FIELD(GUEST_RIP, guest_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_RSP, guest_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR0, host_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR3, host_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR4, host_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_RIP, host_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), + EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(TSC_OFFSET, tsc_offset, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR0, guest_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR3, guest_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR4, guest_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_DR7, guest_dr7, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_RSP, host_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(EPT_POINTER, ept_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), + EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ + + /* 64 bit read only */ + EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + /* + * Not defined in KVM: + * + * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + */ + EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* + * No mask defined in the spec as Hyper-V doesn't currently support + * these. Future proof by resetting the whole clean field mask on + * access. + */ + EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 32 bit rw */ + EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), + EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), + EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), + EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, + vm_entry_exception_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + + /* 32 bit read only */ + EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* No mask defined in the spec (not used) */ + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 16 bit rw */ + EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), +}; +const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h new file mode 100644 index 000000000000..a543fccfc574 --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains common definitions for working with Enlightened VMCS which + * are used both by Hyper-V on KVM and KVM on Hyper-V. + */ +#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H +#define __KVM_X86_VMX_HYPERV_EVMCS_H + +#include <asm/hyperv-tlfs.h> + +#include "capabilities.h" +#include "vmcs12.h" + +#define KVM_EVMCS_VERSION 1 + +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + +struct evmcs_field { + u16 offset; + u16 clean_field; +}; + +extern const struct evmcs_field vmcs_field_to_evmcs_1[]; +extern const unsigned int nr_evmcs_1_fields; + +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) +{ + const struct evmcs_field *evmcs_field; + unsigned int index = ROL16(field, 6); + + if (unlikely(index >= nr_evmcs_1_fields)) + return -ENOENT; + + evmcs_field = &vmcs_field_to_evmcs_1[index]; + + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + + if (clean_field) + *clean_field = evmcs_field->clean_field; + + return evmcs_field->offset; +} + +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 65826fe23f33..6329a306856b 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -179,7 +179,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all * fields and thus must be synced. */ - if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(to_vmx(vcpu))) to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; return kvm_skip_emulated_instruction(vcpu); @@ -194,7 +194,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * can't be done if there isn't a current VMCS. */ if (vmx->nested.current_vmptr == INVALID_GPA && - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + !nested_vmx_is_evmptr12_valid(vmx)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -226,10 +226,11 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (nested_vmx_is_evmptr12_valid(vmx)) { kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); vmx->nested.hv_evmcs = NULL; } @@ -241,6 +242,34 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) hv_vcpu->nested.vm_id = 0; hv_vcpu->nested.vp_id = 0; } +#endif +} + +static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) +{ +#ifdef CONFIG_KVM_HYPERV + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (!guest_cpuid_has_evmcs(vcpu) || + !evmptr_is_valid(nested_get_evmptr(vcpu))) + return false; + + if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr) + nested_release_evmcs(vcpu); + + return true; +#else + return false; +#endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -572,7 +601,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -588,10 +616,13 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature * and tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!vmx->nested.force_msr_bitmap_recalc && evmcs && - evmcs->hv_enlightenments_control.msr_bitmap && - evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) - return true; + if (!vmx->nested.force_msr_bitmap_recalc) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + } if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -1085,7 +1116,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -1139,14 +1170,8 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && enable_ept) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); /* * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings @@ -1578,8 +1603,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ @@ -1818,12 +1844,16 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields */ return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); /* * Should not be changed by KVM: @@ -1992,6 +2022,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } /* @@ -2001,6 +2034,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { +#ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; @@ -2082,13 +2116,16 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( } return EVMPTRLD_SUCCEEDED; +#else + return EVMPTRLD_DISABLED; +#endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) copy_vmcs12_to_enlightened(vmx); else copy_vmcs12_to_shadow(vmx); @@ -2242,7 +2279,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) prepare_vmcs02_early_rare(vmx, vmcs12); /* @@ -2403,7 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { @@ -2535,15 +2572,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || - !(vmx->nested.hv_evmcs->hv_clean_fields & - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); + load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) || + !(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && @@ -2664,9 +2701,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bits when it changes a field in eVMCS. Mark all fields as clean * here. */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (nested_vmx_is_evmptr12_valid(vmx)) + evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; return 0; } @@ -2717,7 +2753,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) + if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2888,8 +2924,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; +#ifdef CONFIG_KVM_HYPERV if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); +#endif return 0; } @@ -2912,7 +2950,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || @@ -3161,6 +3199,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3188,6 +3227,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) return true; } +#endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { @@ -3279,6 +3319,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV /* * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory @@ -3295,6 +3336,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } +#endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -3538,7 +3580,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3569,7 +3611,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); - if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && + if (CC(!nested_vmx_is_evmptr12_valid(vmx) && vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); @@ -3584,8 +3626,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { - copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); + if (nested_vmx_is_evmptr12_valid(vmx)) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -4329,11 +4373,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); + !nested_vmx_is_evmptr12_valid(vmx); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4732,6 +4776,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map @@ -4741,6 +4786,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, */ (void)nested_get_evmcs_page(vcpu); } +#endif /* Service pending TLB flush requests for L2 before switching to L1. */ kvm_service_local_tlb_flush_requests(vcpu); @@ -4854,7 +4900,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, } if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) + (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ @@ -4980,6 +5026,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, else *ret = off; + *ret = vmx_get_untagged_addr(vcpu, *ret, 0); /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! @@ -5292,18 +5339,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - /* - * When Enlightened VMEntry is enabled on the calling CPU we treat - * memory area pointer by vmptr as Enlightened VMCS (as there's no good - * way to distinguish it from VMCS12) and we must not corrupt it by - * writing to the non-existent 'launch_state' field. The area doesn't - * have to be the currently active EVMCS on the calling CPU and there's - * nothing KVM has to do to transition it from 'active' to 'non-active' - * state. It is possible that the area will stay mapped as - * vmx->nested.hv_evmcs but this shouldn't be a problem. - */ - if (likely(!guest_cpuid_has_evmcs(vcpu) || - !evmptr_is_valid(nested_get_evmptr(vcpu)))) { + if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -5320,8 +5356,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { - nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -5360,7 +5394,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (!nested_vmx_is_evmptr12_valid(vmx)) { /* * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMREAD sets the ALU flags for VMfailInvalid. @@ -5398,7 +5432,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* Read the field, zero-extended to a u64 value */ - value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset); + value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset); } /* @@ -5586,7 +5620,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) return 1; if (vmx->nested.current_vmptr != vmptr) { @@ -5649,7 +5683,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) + if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu)))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5797,6 +5831,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if (!operand.vpid || is_noncanonical_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, @@ -6208,11 +6246,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; +#ifdef CONFIG_KVM_HYPERV case EXIT_REASON_VMCALL: /* Hyper-V L2 TLB flush hypercall is handled by L0 */ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && nested_evmcs_l2_tlb_flush_enabled(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu); +#endif default: break; } @@ -6435,7 +6475,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ - if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(vmx)) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && @@ -6491,7 +6531,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) /* * L1 hypervisor is not obliged to keep eVMCS * clean fields data always up-to-date while @@ -6632,6 +6672,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); +#ifdef CONFIG_KVM_HYPERV } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* * nested_vmx_handle_enlightened_vmptrld() cannot be called @@ -6641,6 +6682,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, */ vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); +#endif } else { return -EINVAL; } @@ -7096,7 +7138,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, +#ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, +#endif }; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b4b9d51438c6..cce4e2aa30fb 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -3,6 +3,7 @@ #define __KVM_X86_VMX_NESTED_H #include "kvm_cache_regs.h" +#include "hyperv.h" #include "vmcs12.h" #include "vmx.h" @@ -57,7 +58,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ return vmx->nested.current_vmptr != -1ull || - vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID; + nested_vmx_is_evmptr12_set(vmx); } static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 820d3e1f6b4f..a6216c874729 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -437,11 +437,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { reserved_bits = pmu->reserved_bits; @@ -632,26 +630,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) static void intel_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc = NULL; - int i; - - for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { - pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { - pmc = &pmu->fixed_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = 0; - } - - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; - intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 3e822e582497..6fef01e0536e 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -37,6 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, if (!IS_ALIGNED(*gva, alignment)) { fault = true; } else if (likely(is_64_bit_mode(vcpu))) { + *gva = vmx_get_untagged_addr(vcpu, *gva, 0); fault = is_noncanonical_address(*gva, vcpu); } else { *gva &= 0xffffffff; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index be275a0410a8..906ecd001511 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -289,7 +289,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) RET .Lfixup: - cmpb $0, kvm_rebooting + cmpb $0, _ASM_RIP(kvm_rebooting) jne .Lvmfail ud2 .Lvmfail: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e0f86f11c345..e262bc2ba4e5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -66,6 +66,7 @@ #include "vmx.h" #include "x86.h" #include "smm.h" +#include "vmx_onhyperv.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -523,22 +524,14 @@ module_param(enlightened_vmcs, bool, 0444); static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); + evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; @@ -2055,6 +2048,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; +#ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V @@ -2065,6 +2059,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); +#endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) @@ -3400,7 +3395,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { - guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu); + guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | + kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) @@ -4833,7 +4829,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; + +#ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; +#endif vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -5782,7 +5781,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6757,10 +6756,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; /* - * Grab the memslot so that the hva lookup for the mmu_notifier retry - * is guaranteed to use the same memslot as the pfn lookup, i.e. rely - * on the pfn lookup's validation of the memslot to ensure a valid hva - * is used for the retry check. + * Explicitly grab the memslot using KVM's internal slot ID to ensure + * KVM doesn't unintentionally grab a userspace memslot. It _should_ + * be impossible for userspace to create a memslot for the APIC when + * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -6785,8 +6784,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; read_lock(&vcpu->kvm->mmu_lock); - if (mmu_invalidate_retry_hva(kvm, mmu_seq, - gfn_to_hva_memslot(slot, gfn))) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); read_unlock(&vcpu->kvm->mmu_lock); goto out; @@ -7674,6 +7672,9 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); + cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); + #undef cr4_fixed1_update } @@ -7760,6 +7761,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); vmx_setup_uret_msrs(vmx); @@ -8206,6 +8208,50 @@ static void vmx_vm_destroy(struct kvm *kvm) free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); } +/* + * Note, the SDM states that the linear address is masked *after* the modified + * canonicality check, whereas KVM masks (untags) the address and then performs + * a "normal" canonicality check. Functionally, the two methods are identical, + * and when the masking occurs relative to the canonicality check isn't visible + * to software, i.e. KVM's behavior doesn't violate the SDM. + */ +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) +{ + int lam_bit; + unsigned long cr3_bits; + + if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) + return gva; + + if (!is_64_bit_mode(vcpu)) + return gva; + + /* + * Bit 63 determines if the address should be treated as user address + * or a supervisor address. + */ + if (!(gva & BIT_ULL(63))) { + cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); + if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) + return gva; + + /* LAM_U48 is ignored if LAM_U57 is set. */ + lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; + } else { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) + return gva; + + lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; + } + + /* + * Untag the address by sign-extending the lam_bit, but NOT to bit 63. + * Bit 63 is retained from the raw virtual address so that untagging + * doesn't change a user access to a supervisor access, and vice versa. + */ + return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); +} + static struct kvm_x86_ops vmx_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -8346,6 +8392,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .complete_emulated_msr = kvm_complete_insn_gp, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, }; static unsigned int vmx_handle_intel_pt_intr(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index c2130d2c8e24..e3b0985bb74a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -241,9 +241,11 @@ struct nested_vmx { bool guest_mode; } smm; +#ifdef CONFIG_KVM_HYPERV gpa_t hv_evmcs_vmptr; struct kvm_host_map hv_evmcs_map; struct hv_enlightened_vmcs *hv_evmcs; +#endif }; struct vcpu_vmx { @@ -420,6 +422,8 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { @@ -745,14 +749,4 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) -{ - /* - * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and - * eVMCS has been explicitly enabled by userspace. - */ - return vcpu->arch.hyperv_enabled && - to_vmx(vcpu)->nested.enlightened_vmcs_enabled; -} - #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c new file mode 100644 index 000000000000..b9a8b91166d0 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "capabilities.h" +#include "vmx_onhyperv.h" + +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h new file mode 100644 index 000000000000..eb48153bfd73 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ +#define __ARCH_X86_KVM_VMX_ONHYPERV_H__ + +#include <asm/hyperv-tlfs.h> +#include <asm/mshyperv.h> + +#include <linux/jump_label.h> + +#include "capabilities.h" +#include "hyperv_evmcs.h" +#include "vmcs12.h" + +#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) + +#if IS_ENABLED(CONFIG_HYPERV) + +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); + return offset; +} + +static __always_inline void evmcs_write64(unsigned long field, u64 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u64 *)((char *)current_evmcs + offset) = value; + + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write32(unsigned long field, u32 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u32 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write16(unsigned long field, u16 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u16 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline u64 evmcs_read64(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u64 *)((char *)current_evmcs + offset); +} + +static __always_inline u32 evmcs_read32(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u32 *)((char *)current_evmcs + offset); +} + +static __always_inline u16 evmcs_read16(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u16 *)((char *)current_evmcs + offset); +} + +static inline void evmcs_load(u64 phys_addr) +{ + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(smp_processor_id()); + + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; + vp_ap->current_nested_vmcs = phys_addr; + vp_ap->enlighten_vmentry = 1; +} + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +#else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } +static inline void evmcs_load(u64 phys_addr) {} +#endif /* IS_ENABLED(CONFIG_HYPERV) */ + +#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 33af7b4c6eb4..f41ce3c24123 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include <asm/vmx.h> -#include "hyperv.h" +#include "vmx_onhyperv.h" #include "vmcs.h" #include "../x86.h" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cec0fc2a4b1c..363b1c080205 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1284,7 +1284,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ - if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) @@ -1504,6 +1504,8 @@ static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, @@ -1521,6 +1523,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, @@ -2510,26 +2513,29 @@ static inline int gtod_is_based_on_tsc(int mode) } #endif -static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 - bool vcpus_matched; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; - vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == - atomic_read(&vcpu->kvm->online_vcpus)); + /* + * To use the masterclock, the host clocksource must be based on TSC + * and all vCPUs must have matching TSCs. Note, the count for matching + * vCPUs doesn't include the reference vCPU, hence "+1". + */ + bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)) && + gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* - * Once the masterclock is enabled, always perform request in - * order to update it. - * - * In order to enable masterclock, the host clocksource must be TSC - * and the vcpus need to have matched TSCs. When that happens, - * perform request to enable masterclock. + * Request a masterclock update if the masterclock needs to be toggled + * on/off, or when starting a new generation and the masterclock is + * enabled (compute_guest_tsc() requires the masterclock snapshot to be + * taken _after_ the new generation is created). */ - if (ka->use_master_clock || - (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) + if ((ka->use_master_clock && new_generation) || + (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -2706,7 +2712,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - kvm_track_tsc_matching(vcpu); + kvm_track_tsc_matching(vcpu, !matched); } static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) @@ -3104,7 +3110,8 @@ u64 get_kvmclock_ns(struct kvm *kvm) static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, - unsigned int offset) + unsigned int offset, + bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; @@ -3141,6 +3148,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + + if (force_tsc_unstable) + guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; + smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; @@ -3161,6 +3172,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + */ + bool xen_pvclock_tsc_unstable = + ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; +#endif kernel_ns = 0; host_tsc = 0; @@ -3239,13 +3260,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); #ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); + offsetof(struct compat_vcpu_info, time), + xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, + xen_pvclock_tsc_unstable); #endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; @@ -4020,6 +4043,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * the need to ignore the workaround. */ break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4032,6 +4056,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -4377,6 +4402,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ msr_info->data = 0x20000000; break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4390,6 +4416,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -4527,6 +4554,7 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +#ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { @@ -4547,6 +4575,14 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +#endif + +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type == KVM_X86_DEFAULT_VM || + (type == KVM_X86_SW_PROTECTED_VM && + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled); +} int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { @@ -4573,9 +4609,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: @@ -4585,6 +4623,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: +#endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4594,7 +4633,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: - case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: @@ -4625,6 +4663,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4638,7 +4677,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; @@ -4704,12 +4744,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; +#endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; @@ -4738,6 +4780,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = BIT(KVM_X86_DEFAULT_VM); + if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM)) + r |= BIT(KVM_X86_SW_PROTECTED_VM); + break; default: break; } @@ -4871,9 +4918,11 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; +#endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; @@ -5699,14 +5748,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { - int r; - uint16_t vmcs_version; - void __user *user_ptr; - if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; @@ -5718,16 +5764,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_ops->enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); - if (!r) { - user_ptr = (void __user *)(uintptr_t)cap->args[0]; - if (copy_to_user(user_ptr, &vmcs_version, - sizeof(vmcs_version))) - r = -EFAULT; + { + int r; + uint16_t vmcs_version; + void __user *user_ptr; + + if (!kvm_x86_ops.nested_ops->enable_evmcs) + return -ENOTTY; + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); + if (!r) { + user_ptr = (void __user *)(uintptr_t)cap->args[0]; + if (copy_to_user(user_ptr, &vmcs_version, + sizeof(vmcs_version))) + r = -EFAULT; + } + return r; } - return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; @@ -5736,6 +5788,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); +#endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -6128,9 +6181,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; @@ -7188,6 +7243,7 @@ set_pit2_out: r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -7197,6 +7253,7 @@ set_pit2_out: r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } +#endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; @@ -8432,6 +8489,15 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) kvm_vm_bugged(kvm); } +static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + if (!kvm_x86_ops.get_untagged_addr) + return addr; + + return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8476,6 +8542,7 @@ static const struct x86_emulate_ops emulate_ops = { .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, + .get_untagged_addr = emulator_get_untagged_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -10575,19 +10642,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - u64 eoi_exit_bitmap[4]; - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; +#ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { + u64 eoi_exit_bitmap[4]; + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - +#endif static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } @@ -10678,9 +10746,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); +#endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -10733,6 +10803,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; @@ -10763,6 +10834,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); +#endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) @@ -11081,6 +11153,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -11598,7 +11671,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* @@ -12207,7 +12280,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) } if (!init_event) { - kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; vcpu->arch.msr_misc_features_enables = 0; @@ -12424,7 +12496,9 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_free_vm(struct kvm *kvm) { - kfree(to_kvm_hv(kvm)->hv_pa_pg); +#if IS_ENABLED(CONFIG_HYPERV) + kfree(kvm->arch.hv_pa_pg); +#endif __kvm_arch_free_vm(kvm); } @@ -12434,9 +12508,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + ret = kvm_page_track_init(kvm); if (ret) goto out; @@ -12575,8 +12651,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, hva = slot->userspace_addr; } - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; @@ -12726,6 +12802,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + kvm_mmu_init_memslot_memory_attributes(kvm, slot); +#endif + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; @@ -13536,6 +13616,10 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) switch (type) { case INVPCID_TYPE_INDIV_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if ((!pcid_enabled && (operand.pcid != 0)) || is_noncanonical_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 5184fde1dc54..2f7e19166658 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -530,6 +530,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits |= X86_CR4_VMXE; \ if (!__cpu_has(__c, X86_FEATURE_PCID)) \ __reserved_bits |= X86_CR4_PCIDE; \ + if (!__cpu_has(__c, X86_FEATURE_LAM)) \ + __reserved_bits |= X86_CR4_LAM_SUP; \ __reserved_bits; \ }) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 523bb6df5ac9..4b4e738c6f1b 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) { /* Only some feature flags need to be *enabled* by userspace */ u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + u32 old_flags; if (xhc->flags & ~permitted_flags) return -EINVAL; @@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); + old_flags = kvm->arch.xen_hvm_config.flags; memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); mutex_unlock(&kvm->arch.xen.xen_lock); + + if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + return 0; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index ea2eb2ec90e2..55c4b07ec1f6 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -283,6 +283,9 @@ static int setup_mcfg_map(struct acpi_pci_root_info *ci) info->mcfg_added = false; seg = info->sd.domain; + dev_dbg(dev, "%s(%04x %pR ECAM %pa)\n", __func__, seg, + &root->secondary, &root->mcfg_addr); + /* return success if MMCFG is not in use */ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) return 0; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 4b3efaa82ab7..0cc9520666ef 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* - * mmconfig-shared.c - Low-level direct PCI config space access via - * MMCONFIG - common code between i386 and x86-64. + * Low-level direct PCI config space access via ECAM - common code between + * i386 and x86-64. * * This code does: * - known chipset handling @@ -11,6 +11,8 @@ * themselves. */ +#define pr_fmt(fmt) "PCI: " fmt + #include <linux/acpi.h> #include <linux/efi.h> #include <linux/pci.h> @@ -24,9 +26,7 @@ #include <asm/pci_x86.h> #include <asm/acpi.h> -#define PREFIX "PCI: " - -/* Indicate if the mmcfg resources have been placed into the resource table. */ +/* Indicate if the ECAM resources have been placed into the resource table */ static bool pci_mmcfg_running_state; static bool pci_mmcfg_arch_init_failed; static DEFINE_MUTEX(pci_mmcfg_lock); @@ -90,7 +90,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start, res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN, - "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end); + "PCI ECAM %04x [bus %02x-%02x]", segment, start, end); res->name = new->name; return new; @@ -102,16 +102,15 @@ struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, struct pci_mmcfg_region *new; new = pci_mmconfig_alloc(segment, start, end, addr); - if (new) { - mutex_lock(&pci_mmcfg_lock); - list_add_sorted(new); - mutex_unlock(&pci_mmcfg_lock); + if (!new) + return NULL; - pr_info(PREFIX - "MMCONFIG for domain %04x [bus %02x-%02x] at %pR " - "(base %#lx)\n", - segment, start, end, &new->res, (unsigned long)addr); - } + mutex_lock(&pci_mmcfg_lock); + list_add_sorted(new); + mutex_unlock(&pci_mmcfg_lock); + + pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n", + &new->res, (unsigned long)addr, segment, start, end); return new; } @@ -205,7 +204,7 @@ static const char *__init pci_mmcfg_amd_fam10h(void) msr <<= 32; msr |= low; - /* mmconfig is not enable */ + /* ECAM is not enabled */ if (!(msr & FAM10H_MMIO_CONF_ENABLE)) return NULL; @@ -367,7 +366,7 @@ static int __init pci_mmcfg_check_hostbridge(void) name = pci_mmcfg_probes[i].probe(); if (name) - pr_info(PREFIX "%s with MMCONFIG support\n", name); + pr_info("%s with ECAM support\n", name); } /* some end_bus_number is crazy, fix it */ @@ -443,9 +442,11 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } -static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +static bool is_efi_mmio(struct resource *res) { #ifdef CONFIG_EFI + u64 start = res->start; + u64 end = res->start + resource_size(res); efi_memory_desc_t *md; u64 size, mmio_start, mmio_end; @@ -455,11 +456,6 @@ static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) mmio_start = md->phys_addr; mmio_end = mmio_start + size; - /* - * N.B. Caller supplies (start, start + size), - * so to match, mmio_end is the first address - * *past* the EFI_MEMORY_MAPPED_IO area. - */ if (mmio_start <= start && end <= mmio_end) return true; } @@ -490,11 +486,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved as %s\n", + dev_info(dev, "ECAM %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", - &cfg->res, method); + pr_info("ECAM %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { /* update end_bus */ @@ -503,47 +498,51 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, cfg->res.end = cfg->res.start + PCI_MMCFG_BUS_OFFSET(num_buses) - 1; snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN, - "PCI MMCONFIG %04x [bus %02x-%02x]", + "PCI ECAM %04x [bus %02x-%02x]", cfg->segment, cfg->start_bus, cfg->end_bus); if (dev) - dev_info(dev, - "MMCONFIG " - "at %pR (base %#lx) (size reduced!)\n", - &cfg->res, (unsigned long) cfg->address); + dev_info(dev, "ECAM %pR (base %#lx) (size reduced!)\n", + &cfg->res, (unsigned long) cfg->address); else - pr_info(PREFIX - "MMCONFIG for %04x [bus%02x-%02x] " - "at %pR (base %#lx) (size reduced!)\n", - cfg->segment, cfg->start_bus, cfg->end_bus, - &cfg->res, (unsigned long) cfg->address); + pr_info("ECAM %pR (base %#lx) for %04x [bus%02x-%02x] (size reduced!)\n", + &cfg->res, (unsigned long) cfg->address, + cfg->segment, cfg->start_bus, cfg->end_bus); } return true; } -static bool __ref -pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) +static bool __ref pci_mmcfg_reserved(struct device *dev, + struct pci_mmcfg_region *cfg, int early) { + struct resource *conflict; + if (!early && !acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, "ACPI motherboard resource")) return true; if (dev) - dev_info(dev, FW_INFO - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", + dev_info(dev, FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n", &cfg->res); else - pr_info(FW_INFO PREFIX - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", - &cfg->res); - - if (is_mmconf_reserved(is_efi_mmio, cfg, dev, - "EfiMemoryMappedIO")) + pr_info(FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n", + &cfg->res); + + if (is_efi_mmio(&cfg->res)) { + pr_info("ECAM %pR is EfiMemoryMappedIO; assuming valid\n", + &cfg->res); + conflict = insert_resource_conflict(&iomem_resource, + &cfg->res); + if (conflict) + pr_warn("ECAM %pR conflicts with %s %pR\n", + &cfg->res, conflict->name, conflict); + else + pr_info("ECAM %pR reserved to work around lack of ACPI motherboard _CRS\n", + &cfg->res); return true; + } } /* @@ -569,30 +568,31 @@ static void __init pci_mmcfg_reject_broken(int early) struct pci_mmcfg_region *cfg; list_for_each_entry(cfg, &pci_mmcfg_list, list) { - if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) { - pr_info(PREFIX "not using MMCONFIG\n"); + if (!pci_mmcfg_reserved(NULL, cfg, early)) { + pr_info("not using ECAM (%pR not reserved)\n", + &cfg->res); free_all_mmcfg(); return; } } } -static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, - struct acpi_mcfg_allocation *cfg) +static bool __init acpi_mcfg_valid_entry(struct acpi_table_mcfg *mcfg, + struct acpi_mcfg_allocation *cfg) { if (cfg->address < 0xFFFFFFFF) - return 0; + return true; if (!strncmp(mcfg->header.oem_id, "SGI", 3)) - return 0; + return true; if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010)) - return 0; + return true; - pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx " - "is above 4GB, ignored\n", cfg->pci_segment, - cfg->start_bus_number, cfg->end_bus_number, cfg->address); - return -EINVAL; + pr_err("ECAM at %#llx for %04x [bus %02x-%02x] is above 4GB, ignored\n", + cfg->address, cfg->pci_segment, cfg->start_bus_number, + cfg->end_bus_number); + return false; } static int __init pci_parse_mcfg(struct acpi_table_header *header) @@ -616,21 +616,21 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) i -= sizeof(struct acpi_mcfg_allocation); } if (entries == 0) { - pr_err(PREFIX "MMCONFIG has no entries\n"); + pr_err("MCFG has no entries\n"); return -ENODEV; } cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1]; for (i = 0; i < entries; i++) { cfg = &cfg_table[i]; - if (acpi_mcfg_check_entry(mcfg, cfg)) { + if (!acpi_mcfg_valid_entry(mcfg, cfg)) { free_all_mmcfg(); return -ENODEV; } if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number, cfg->end_bus_number, cfg->address) == NULL) { - pr_warn(PREFIX "no memory for MCFG entries\n"); + pr_warn("no memory for MCFG entries\n"); free_all_mmcfg(); return -ENOMEM; } @@ -667,6 +667,8 @@ static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size, static void __init __pci_mmcfg_init(int early) { + pr_debug("%s(%s)\n", __func__, early ? "early" : "late"); + pci_mmcfg_reject_broken(early); if (list_empty(&pci_mmcfg_list)) return; @@ -693,6 +695,8 @@ static int __initdata known_bridge; void __init pci_mmcfg_early_init(void) { + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + if (pci_probe & PCI_PROBE_MMCONF) { if (pci_mmcfg_check_hostbridge()) known_bridge = 1; @@ -706,14 +710,16 @@ void __init pci_mmcfg_early_init(void) void __init pci_mmcfg_late_init(void) { - /* MMCONFIG disabled */ + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + + /* ECAM disabled */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) return; if (known_bridge) return; - /* MMCONFIG hasn't been enabled yet, try again */ + /* ECAM hasn't been enabled yet, try again */ if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) { acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(0); @@ -726,7 +732,9 @@ static int __init pci_mmcfg_late_insert_resources(void) pci_mmcfg_running_state = true; - /* If we are not using MMCONFIG, don't insert the resources. */ + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + + /* If we are not using ECAM, don't insert the resources. */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) return 1; @@ -735,21 +743,24 @@ static int __init pci_mmcfg_late_insert_resources(void) * marked so it won't cause request errors when __request_region is * called. */ - list_for_each_entry(cfg, &pci_mmcfg_list, list) - if (!cfg->res.parent) + list_for_each_entry(cfg, &pci_mmcfg_list, list) { + if (!cfg->res.parent) { + pr_debug("%s() insert %pR\n", __func__, &cfg->res); insert_resource(&iomem_resource, &cfg->res); + } + } return 0; } /* - * Perform MMCONFIG resource insertion after PCI initialization to allow for + * Perform ECAM resource insertion after PCI initialization to allow for * misprogrammed MCFG tables that state larger sizes but actually conflict * with other system resources. */ late_initcall(pci_mmcfg_late_insert_resources); -/* Add MMCFG information for host bridges */ +/* Add ECAM information for host bridges */ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, phys_addr_t addr) { @@ -757,6 +768,8 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, struct resource *tmp = NULL; struct pci_mmcfg_region *cfg; + dev_dbg(dev, "%s(%04x [bus %02x-%02x])\n", __func__, seg, start, end); + if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed) return -ENODEV; @@ -767,15 +780,17 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, cfg = pci_mmconfig_lookup(seg, start); if (cfg) { if (cfg->end_bus < end) - dev_info(dev, FW_INFO - "MMCONFIG for " - "domain %04x [bus %02x-%02x] " - "only partially covers this bridge\n", - cfg->segment, cfg->start_bus, cfg->end_bus); + dev_info(dev, FW_INFO "ECAM %pR for domain %04x [bus %02x-%02x] only partially covers this bridge\n", + &cfg->res, cfg->segment, cfg->start_bus, + cfg->end_bus); mutex_unlock(&pci_mmcfg_lock); return -EEXIST; } + /* + * Don't move earlier; we must return -EEXIST, not -EINVAL, if + * pci_mmconfig_lookup() finds something + */ if (!addr) { mutex_unlock(&pci_mmcfg_lock); return -EINVAL; @@ -784,10 +799,10 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, rc = -EBUSY; cfg = pci_mmconfig_alloc(seg, start, end, addr); if (cfg == NULL) { - dev_warn(dev, "fail to add MMCONFIG (out of memory)\n"); + dev_warn(dev, "fail to add ECAM (out of memory)\n"); rc = -ENOMEM; - } else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) { - dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n", + } else if (!pci_mmcfg_reserved(dev, cfg, 0)) { + dev_warn(dev, FW_BUG "ECAM %pR isn't reserved\n", &cfg->res); } else { /* Insert resource if it's not in boot stage */ @@ -796,16 +811,13 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, &cfg->res); if (tmp) { - dev_warn(dev, - "MMCONFIG %pR conflicts with " - "%s %pR\n", + dev_warn(dev, "ECAM %pR conflicts with %s %pR\n", &cfg->res, tmp->name, tmp); } else if (pci_mmcfg_arch_map(cfg)) { - dev_warn(dev, "fail to map MMCONFIG %pR.\n", - &cfg->res); + dev_warn(dev, "fail to map ECAM %pR\n", &cfg->res); } else { list_add_sorted(cfg); - dev_info(dev, "MMCONFIG at %pR (base %#lx)\n", + dev_info(dev, "ECAM %pR (base %#lx)\n", &cfg->res, (unsigned long)addr); cfg = NULL; rc = 0; @@ -823,7 +835,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, return rc; } -/* Delete MMCFG information for host bridges */ +/* Delete ECAM information for host bridges */ int pci_mmconfig_delete(u16 seg, u8 start, u8 end) { struct pci_mmcfg_region *cfg; diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index bfa789875322..f9ef97c593cf 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -131,7 +131,7 @@ const struct pci_raw_ops pci_mmcfg = { int __init pci_mmcfg_arch_init(void) { - printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n"); + printk(KERN_INFO "PCI: Using ECAM for extended config space\n"); raw_pci_ext_ops = &pci_mmcfg; return 1; } diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 0c7b6e66c644..cb5aa79a759e 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -6,6 +6,8 @@ * space mapped. This allows lockless config space operation. */ +#define pr_fmt(fmt) "PCI: " fmt + #include <linux/pci.h> #include <linux/init.h> #include <linux/acpi.h> @@ -14,8 +16,6 @@ #include <asm/e820/api.h> #include <asm/pci_x86.h> -#define PREFIX "PCI: " - static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn) { struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus); @@ -111,6 +111,25 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg) return addr; } +int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +{ + cfg->virt = mcfg_ioremap(cfg); + if (!cfg->virt) { + pr_err("can't map ECAM at %pR\n", &cfg->res); + return -ENOMEM; + } + + return 0; +} + +void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) +{ + if (cfg && cfg->virt) { + iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); + cfg->virt = NULL; + } +} + int __init pci_mmcfg_arch_init(void) { struct pci_mmcfg_region *cfg; @@ -133,22 +152,3 @@ void __init pci_mmcfg_arch_free(void) list_for_each_entry(cfg, &pci_mmcfg_list, list) pci_mmcfg_arch_unmap(cfg); } - -int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) -{ - cfg->virt = mcfg_ioremap(cfg); - if (!cfg->virt) { - pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res); - return -ENOMEM; - } - - return 0; -} - -void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) -{ - if (cfg && cfg->virt) { - iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); - cfg->virt = NULL; - } -} diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 4f15280732ed..244c643bb0b5 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -3,6 +3,8 @@ * BIOS32 and PCI BIOS handling. */ +#include <linux/bits.h> +#include <linux/bitfield.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/slab.h> @@ -29,8 +31,19 @@ #define PCIBIOS_HW_TYPE1_SPEC 0x10 #define PCIBIOS_HW_TYPE2_SPEC 0x20 +/* + * Returned in EAX: + * - AH: return code + */ +#define PCIBIOS_RETURN_CODE GENMASK(15, 8) + int pcibios_enabled; +static u8 pcibios_get_return_code(u32 eax) +{ + return FIELD_GET(PCIBIOS_RETURN_CODE, eax); +} + /* According to the BIOS specification at: * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could * restrict the x zone to some pages and make it ro. But this may be @@ -154,7 +167,7 @@ static int __init check_pcibios(void) : "memory"); local_irq_restore(flags); - status = (eax >> 8) & 0xff; + status = pcibios_get_return_code(eax); hw_mech = eax & 0xff; major_ver = (ebx >> 8) & 0xff; minor_ver = ebx & 0xff; @@ -227,7 +240,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, raw_spin_unlock_irqrestore(&pci_config_lock, flags); - return (int)((result & 0xff00) >> 8); + return pcibios_get_return_code(result); } static int pci_bios_write(unsigned int seg, unsigned int bus, @@ -269,7 +282,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, raw_spin_unlock_irqrestore(&pci_config_lock, flags); - return (int)((result & 0xff00) >> 8); + return pcibios_get_return_code(result); } @@ -385,9 +398,10 @@ struct irq_routing_table * pcibios_get_irq_routing_table(void) "m" (opt) : "memory"); DBG("OK ret=%d, size=%d, map=%x\n", ret, opt.size, map); - if (ret & 0xff00) - printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff); - else if (opt.size) { + ret = pcibios_get_return_code(ret); + if (ret) { + printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", ret); + } else if (opt.size) { rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL); if (rt) { memset(rt, 0, sizeof(struct irq_routing_table)); @@ -415,7 +429,7 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq) "b" ((dev->bus->number << 8) | dev->devfn), "c" ((irq << 8) | (pin + 10)), "S" (&pci_indirect)); - return !(ret & 0xff00); + return pcibios_get_return_code(ret) == PCIBIOS_SUCCESSFUL; } EXPORT_SYMBOL(pcibios_set_irq_routing); diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 6523eb7c3bd1..6052200fe925 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -168,8 +168,8 @@ do { \ (pr_reg)[18] = (_regs)->regs.gp[18]; \ (pr_reg)[19] = (_regs)->regs.gp[19]; \ (pr_reg)[20] = (_regs)->regs.gp[20]; \ - (pr_reg)[21] = current->thread.arch.fs; \ - (pr_reg)[22] = 0; \ + (pr_reg)[21] = (_regs)->regs.gp[21]; \ + (pr_reg)[22] = (_regs)->regs.gp[22]; \ (pr_reg)[23] = 0; \ (pr_reg)[24] = 0; \ (pr_reg)[25] = 0; \ diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 1ef9c21877bc..f90159508936 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -10,13 +10,11 @@ struct arch_thread { unsigned long debugregs[8]; int debugregs_seq; - unsigned long fs; struct faultinfo faultinfo; }; #define INIT_ARCH_THREAD { .debugregs = { [ 0 ... 7 ] = 0 }, \ .debugregs_seq = 0, \ - .fs = 0, \ .faultinfo = { 0, 0, 0 } } #define STACKSLOTS_PER_LINE 4 @@ -28,7 +26,6 @@ static inline void arch_flush_thread(struct arch_thread *thread) static inline void arch_copy_thread(struct arch_thread *from, struct arch_thread *to) { - to->fs = from->fs; } #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; }) diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile index ae169125d03f..5249bbc30dcd 100644 --- a/arch/x86/um/os-Linux/Makefile +++ b/arch/x86/um/os-Linux/Makefile @@ -6,7 +6,6 @@ obj-y = registers.o task_size.o mcontext.o obj-$(CONFIG_X86_32) += tls.o -obj-$(CONFIG_64BIT) += prctl.o USER_OBJS := $(obj-y) diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c deleted file mode 100644 index 8431e87ac333..000000000000 --- a/arch/x86/um/os-Linux/prctl.c +++ /dev/null @@ -1,12 +0,0 @@ -/* - * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com}) - * Licensed under the GPL - */ - -#include <sys/ptrace.h> -#include <asm/ptrace.h> - -int os_arch_prctl(int pid, int option, unsigned long *arg2) -{ - return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option); -} diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index 0bc4b73a9cde..7f1abde2c84b 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -25,30 +25,6 @@ void arch_switch_to(struct task_struct *to) printk(KERN_WARNING "arch_switch_tls failed, errno = EINVAL\n"); } -int is_syscall(unsigned long addr) -{ - unsigned short instr; - int n; - - n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); - if (n) { - /* access_process_vm() grants access to vsyscall and stub, - * while copy_from_user doesn't. Maybe access_process_vm is - * slow, but that doesn't matter, since it will be called only - * in case of singlestepping, if copy_from_user failed. - */ - n = access_process_vm(current, addr, &instr, sizeof(instr), - FOLL_FORCE); - if (n != sizeof(instr)) { - printk(KERN_ERR "is_syscall : failed to read " - "instruction from 0x%lx\n", addr); - return 1; - } - } - /* int 0x80 or sysenter */ - return (instr == 0x80cd) || (instr == 0x340f); -} - /* determines which flags the user has access to. */ /* 1 = access 0 = no access */ #define FLAG_MASK 0x00044dd5 diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index 289d0159b041..aa68d83d3f44 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -188,32 +188,6 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long *) data); } -/* XXX Mostly copied from sys-i386 */ -int is_syscall(unsigned long addr) -{ - unsigned short instr; - int n; - - n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); - if (n) { - /* - * access_process_vm() grants access to vsyscall and stub, - * while copy_from_user doesn't. Maybe access_process_vm is - * slow, but that doesn't matter, since it will be called only - * in case of singlestepping, if copy_from_user failed. - */ - n = access_process_vm(current, addr, &instr, sizeof(instr), - FOLL_FORCE); - if (n != sizeof(instr)) { - printk("is_syscall : failed to read instruction from " - "0x%lx\n", addr); - return 1; - } - } - /* sysenter */ - return instr == 0x050f; -} - static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h index db8478a83a09..0c4989842fbe 100644 --- a/arch/x86/um/shared/sysdep/ptrace_32.h +++ b/arch/x86/um/shared/sysdep/ptrace_32.h @@ -8,10 +8,6 @@ #define MAX_FP_NR HOST_FPX_SIZE -void set_using_sysemu(int value); -int get_using_sysemu(void); -extern int sysemu_supported; - #define UPT_SYSCALL_ARG1(r) UPT_BX(r) #define UPT_SYSCALL_ARG2(r) UPT_CX(r) #define UPT_SYSCALL_ARG3(r) UPT_DX(r) diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h index 44782bbad41e..1d1a824fa652 100644 --- a/arch/x86/um/shared/sysdep/ptrace_user.h +++ b/arch/x86/um/shared/sysdep/ptrace_user.h @@ -15,14 +15,12 @@ #define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE) #else #define FP_SIZE HOST_FP_SIZE +#endif /* - * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though - * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the - * 2.4 name and value for 2.4 host compatibility. + * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum, + * ensure we have a definition by (re-)defining it here. */ -#ifndef PTRACE_OLDSETOPTIONS -#define PTRACE_OLDSETOPTIONS 21 -#endif - +#ifndef PTRACE_SYSEMU_SINGLESTEP +#define PTRACE_SYSEMU_SINGLESTEP 32 #endif diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 38fa894b65d0..ea8b5a2d67af 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -12,72 +12,79 @@ #define STUB_MMAP_NR __NR_mmap2 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT) -static inline long stub_syscall0(long syscall) +static __always_inline long stub_syscall0(long syscall) { long ret; - __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall)); + __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall) + : "memory"); return ret; } -static inline long stub_syscall1(long syscall, long arg1) +static __always_inline long stub_syscall1(long syscall, long arg1) { long ret; - __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1)); + __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1) + : "memory"); return ret; } -static inline long stub_syscall2(long syscall, long arg1, long arg2) +static __always_inline long stub_syscall2(long syscall, long arg1, long arg2) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2)); + "c" (arg2) + : "memory"); return ret; } -static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) +static __always_inline long stub_syscall3(long syscall, long arg1, long arg2, + long arg3) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3)); + "c" (arg2), "d" (arg3) + : "memory"); return ret; } -static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, - long arg4) +static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, + long arg3, long arg4) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3), "S" (arg4)); + "c" (arg2), "d" (arg3), "S" (arg4) + : "memory"); return ret; } -static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, - long arg4, long arg5) +static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)); + "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5) + : "memory"); return ret; } -static inline void trap_myself(void) +static __always_inline void trap_myself(void) { __asm("int3"); } -static inline void remap_stack_and_trap(void) +static __always_inline void remap_stack_and_trap(void) { __asm__ volatile ( "movl %%esp,%%ebx ;" diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 2de1c8f88173..b24168ef0ac4 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -16,7 +16,7 @@ #define __syscall_clobber "r11","rcx","memory" #define __syscall "syscall" -static inline long stub_syscall0(long syscall) +static __always_inline long stub_syscall0(long syscall) { long ret; @@ -27,7 +27,7 @@ static inline long stub_syscall0(long syscall) return ret; } -static inline long stub_syscall2(long syscall, long arg1, long arg2) +static __always_inline long stub_syscall2(long syscall, long arg1, long arg2) { long ret; @@ -38,7 +38,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2) return ret; } -static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) +static __always_inline long stub_syscall3(long syscall, long arg1, long arg2, + long arg3) { long ret; @@ -50,7 +51,7 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) return ret; } -static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, +static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, long arg4) { long ret; @@ -64,8 +65,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, return ret; } -static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, - long arg4, long arg5) +static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5) { long ret; @@ -78,12 +79,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, return ret; } -static inline void trap_myself(void) +static __always_inline void trap_myself(void) { __asm("int3"); } -static inline void remap_stack_and_trap(void) +static __always_inline void remap_stack_and_trap(void) { __asm__ volatile ( "movq %0,%%rax ;" diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index 27b29ae6c471..6a00a28c9cca 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -16,60 +16,24 @@ long arch_prctl(struct task_struct *task, int option, unsigned long __user *arg2) { - unsigned long *ptr = arg2, tmp; - long ret; - int pid = task->mm->context.id.u.pid; - - /* - * With ARCH_SET_FS (and ARCH_SET_GS is treated similarly to - * be safe), we need to call arch_prctl on the host because - * setting %fs may result in something else happening (like a - * GDT or thread.fs being set instead). So, we let the host - * fiddle the registers and thread struct and restore the - * registers afterwards. - * - * So, the saved registers are stored to the process (this - * needed because a stub may have been the last thing to run), - * arch_prctl is run on the host, then the registers are read - * back. - */ - switch (option) { - case ARCH_SET_FS: - case ARCH_SET_GS: - ret = restore_pid_registers(pid, ¤t->thread.regs.regs); - if (ret) - return ret; - break; - case ARCH_GET_FS: - case ARCH_GET_GS: - /* - * With these two, we read to a local pointer and - * put_user it to the userspace pointer that we were - * given. If addr isn't valid (because it hasn't been - * faulted in or is just bogus), we want put_user to - * fault it in (or return -EFAULT) instead of having - * the host return -EFAULT. - */ - ptr = &tmp; - } - - ret = os_arch_prctl(pid, option, ptr); - if (ret) - return ret; + long ret = -EINVAL; switch (option) { case ARCH_SET_FS: - current->thread.arch.fs = (unsigned long) ptr; - ret = save_registers(pid, ¤t->thread.regs.regs); + current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = + (unsigned long) arg2; + ret = 0; break; case ARCH_SET_GS: - ret = save_registers(pid, ¤t->thread.regs.regs); + current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)] = + (unsigned long) arg2; + ret = 0; break; case ARCH_GET_FS: - ret = put_user(tmp, arg2); + ret = put_user(current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)], arg2); break; case ARCH_GET_GS: - ret = put_user(tmp, arg2); + ret = put_user(current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)], arg2); break; } @@ -83,10 +47,10 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) void arch_switch_to(struct task_struct *to) { - if ((to->thread.arch.fs == 0) || (to->mm == NULL)) - return; - - arch_prctl(to, ARCH_SET_FS, (void __user *) to->thread.arch.fs); + /* + * Nothing needs to be done on x86_64. + * The FS_BASE/GS_BASE registers are saved in the ptrace register set. + */ } SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index ebd3855d9b13..c51a613f6f5c 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -12,7 +12,7 @@ int arch_set_tls(struct task_struct *t, unsigned long tls) * If CLONE_SETTLS is set, we need to save the thread id * so it can be set during context switches. */ - t->thread.arch.fs = tls; + t->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = tls; return 0; } diff --git a/arch/x86/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile index 46ef8f73aebb..90da47eb85ee 100644 --- a/arch/x86/virt/vmx/tdx/Makefile +++ b/arch/x86/virt/vmx/tdx/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += seamcall.o +obj-y += seamcall.o tdx.o diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c new file mode 100644 index 000000000000..4d6826a76f78 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -0,0 +1,1492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(c) 2023 Intel Corporation. + * + * Intel Trusted Domain Extensions (TDX) support + */ + +#define pr_fmt(fmt) "virt/tdx: " fmt + +#include <linux/types.h> +#include <linux/cache.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/printk.h> +#include <linux/cpu.h> +#include <linux/spinlock.h> +#include <linux/percpu-defs.h> +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/memory.h> +#include <linux/minmax.h> +#include <linux/sizes.h> +#include <linux/pfn.h> +#include <linux/align.h> +#include <linux/sort.h> +#include <linux/log2.h> +#include <linux/acpi.h> +#include <linux/suspend.h> +#include <linux/acpi.h> +#include <asm/page.h> +#include <asm/special_insns.h> +#include <asm/msr-index.h> +#include <asm/msr.h> +#include <asm/cpufeature.h> +#include <asm/tdx.h> +#include <asm/intel-family.h> +#include <asm/processor.h> +#include <asm/mce.h> +#include "tdx.h" + +static u32 tdx_global_keyid __ro_after_init; +static u32 tdx_guest_keyid_start __ro_after_init; +static u32 tdx_nr_guest_keyids __ro_after_init; + +static DEFINE_PER_CPU(bool, tdx_lp_initialized); + +static struct tdmr_info_list tdx_tdmr_list; + +static enum tdx_module_status_t tdx_module_status; +static DEFINE_MUTEX(tdx_module_lock); + +/* All TDX-usable memory regions. Protected by mem_hotplug_lock. */ +static LIST_HEAD(tdx_memlist); + +typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args); + +static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args) +{ + pr_err("SEAMCALL (0x%016llx) failed: 0x%016llx\n", fn, err); +} + +static inline void seamcall_err_ret(u64 fn, u64 err, + struct tdx_module_args *args) +{ + seamcall_err(fn, err, args); + pr_err("RCX 0x%016llx RDX 0x%016llx R08 0x%016llx\n", + args->rcx, args->rdx, args->r8); + pr_err("R09 0x%016llx R10 0x%016llx R11 0x%016llx\n", + args->r9, args->r10, args->r11); +} + +static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) +{ + u64 sret = sc_retry(func, fn, args); + + if (sret == TDX_SUCCESS) + return 0; + + if (sret == TDX_SEAMCALL_VMFAILINVALID) + return -ENODEV; + + if (sret == TDX_SEAMCALL_GP) + return -EOPNOTSUPP; + + if (sret == TDX_SEAMCALL_UD) + return -EACCES; + + err_func(fn, sret, args); + return -EIO; +} + +#define seamcall_prerr(__fn, __args) \ + sc_retry_prerr(__seamcall, seamcall_err, (__fn), (__args)) + +#define seamcall_prerr_ret(__fn, __args) \ + sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args)) + +/* + * Do the module global initialization once and return its result. + * It can be done on any cpu. It's always called with interrupts + * disabled. + */ +static int try_init_module_global(void) +{ + struct tdx_module_args args = {}; + static DEFINE_RAW_SPINLOCK(sysinit_lock); + static bool sysinit_done; + static int sysinit_ret; + + lockdep_assert_irqs_disabled(); + + raw_spin_lock(&sysinit_lock); + + if (sysinit_done) + goto out; + + /* RCX is module attributes and all bits are reserved */ + args.rcx = 0; + sysinit_ret = seamcall_prerr(TDH_SYS_INIT, &args); + + /* + * The first SEAMCALL also detects the TDX module, thus + * it can fail due to the TDX module is not loaded. + * Dump message to let the user know. + */ + if (sysinit_ret == -ENODEV) + pr_err("module not loaded\n"); + + sysinit_done = true; +out: + raw_spin_unlock(&sysinit_lock); + return sysinit_ret; +} + +/** + * tdx_cpu_enable - Enable TDX on local cpu + * + * Do one-time TDX module per-cpu initialization SEAMCALL (and TDX module + * global initialization SEAMCALL if not done) on local cpu to make this + * cpu be ready to run any other SEAMCALLs. + * + * Always call this function via IPI function calls. + * + * Return 0 on success, otherwise errors. + */ +int tdx_cpu_enable(void) +{ + struct tdx_module_args args = {}; + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_irqs_disabled(); + + if (__this_cpu_read(tdx_lp_initialized)) + return 0; + + /* + * The TDX module global initialization is the very first step + * to enable TDX. Need to do it first (if hasn't been done) + * before the per-cpu initialization. + */ + ret = try_init_module_global(); + if (ret) + return ret; + + ret = seamcall_prerr(TDH_SYS_LP_INIT, &args); + if (ret) + return ret; + + __this_cpu_write(tdx_lp_initialized, true); + + return 0; +} +EXPORT_SYMBOL_GPL(tdx_cpu_enable); + +/* + * Add a memory region as a TDX memory block. The caller must make sure + * all memory regions are added in address ascending order and don't + * overlap. + */ +static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn, + unsigned long end_pfn, int nid) +{ + struct tdx_memblock *tmb; + + tmb = kmalloc(sizeof(*tmb), GFP_KERNEL); + if (!tmb) + return -ENOMEM; + + INIT_LIST_HEAD(&tmb->list); + tmb->start_pfn = start_pfn; + tmb->end_pfn = end_pfn; + tmb->nid = nid; + + /* @tmb_list is protected by mem_hotplug_lock */ + list_add_tail(&tmb->list, tmb_list); + return 0; +} + +static void free_tdx_memlist(struct list_head *tmb_list) +{ + /* @tmb_list is protected by mem_hotplug_lock */ + while (!list_empty(tmb_list)) { + struct tdx_memblock *tmb = list_first_entry(tmb_list, + struct tdx_memblock, list); + + list_del(&tmb->list); + kfree(tmb); + } +} + +/* + * Ensure that all memblock memory regions are convertible to TDX + * memory. Once this has been established, stash the memblock + * ranges off in a secondary structure because memblock is modified + * in memory hotplug while TDX memory regions are fixed. + */ +static int build_tdx_memlist(struct list_head *tmb_list) +{ + unsigned long start_pfn, end_pfn; + int i, nid, ret; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + /* + * The first 1MB is not reported as TDX convertible memory. + * Although the first 1MB is always reserved and won't end up + * to the page allocator, it is still in memblock's memory + * regions. Skip them manually to exclude them as TDX memory. + */ + start_pfn = max(start_pfn, PHYS_PFN(SZ_1M)); + if (start_pfn >= end_pfn) + continue; + + /* + * Add the memory regions as TDX memory. The regions in + * memblock has already guaranteed they are in address + * ascending order and don't overlap. + */ + ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn, nid); + if (ret) + goto err; + } + + return 0; +err: + free_tdx_memlist(tmb_list); + return ret; +} + +static int read_sys_metadata_field(u64 field_id, u64 *data) +{ + struct tdx_module_args args = {}; + int ret; + + /* + * TDH.SYS.RD -- reads one global metadata field + * - RDX (in): the field to read + * - R8 (out): the field data + */ + args.rdx = field_id; + ret = seamcall_prerr_ret(TDH_SYS_RD, &args); + if (ret) + return ret; + + *data = args.r8; + + return 0; +} + +static int read_sys_metadata_field16(u64 field_id, + int offset, + struct tdx_tdmr_sysinfo *ts) +{ + u16 *ts_member = ((void *)ts) + offset; + u64 tmp; + int ret; + + if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) != + MD_FIELD_ID_ELE_SIZE_16BIT)) + return -EINVAL; + + ret = read_sys_metadata_field(field_id, &tmp); + if (ret) + return ret; + + *ts_member = tmp; + + return 0; +} + +struct field_mapping { + u64 field_id; + int offset; +}; + +#define TD_SYSINFO_MAP(_field_id, _offset) \ + { .field_id = MD_FIELD_ID_##_field_id, \ + .offset = offsetof(struct tdx_tdmr_sysinfo, _offset) } + +/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */ +static const struct field_mapping fields[] = { + TD_SYSINFO_MAP(MAX_TDMRS, max_tdmrs), + TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr), + TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE, pamt_entry_size[TDX_PS_4K]), + TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE, pamt_entry_size[TDX_PS_2M]), + TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE, pamt_entry_size[TDX_PS_1G]), +}; + +static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + int i; + + /* Populate 'tdmr_sysinfo' fields using the mapping structure above: */ + for (i = 0; i < ARRAY_SIZE(fields); i++) { + ret = read_sys_metadata_field16(fields[i].field_id, + fields[i].offset, + tdmr_sysinfo); + if (ret) + return ret; + } + + return 0; +} + +/* Calculate the actual TDMR size */ +static int tdmr_size_single(u16 max_reserved_per_tdmr) +{ + int tdmr_sz; + + /* + * The actual size of TDMR depends on the maximum + * number of reserved areas. + */ + tdmr_sz = sizeof(struct tdmr_info); + tdmr_sz += sizeof(struct tdmr_reserved_area) * max_reserved_per_tdmr; + + return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT); +} + +static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + size_t tdmr_sz, tdmr_array_sz; + void *tdmr_array; + + tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr); + tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs; + + /* + * To keep things simple, allocate all TDMRs together. + * The buffer needs to be physically contiguous to make + * sure each TDMR is physically contiguous. + */ + tdmr_array = alloc_pages_exact(tdmr_array_sz, + GFP_KERNEL | __GFP_ZERO); + if (!tdmr_array) + return -ENOMEM; + + tdmr_list->tdmrs = tdmr_array; + + /* + * Keep the size of TDMR to find the target TDMR + * at a given index in the TDMR list. + */ + tdmr_list->tdmr_sz = tdmr_sz; + tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs; + tdmr_list->nr_consumed_tdmrs = 0; + + return 0; +} + +static void free_tdmr_list(struct tdmr_info_list *tdmr_list) +{ + free_pages_exact(tdmr_list->tdmrs, + tdmr_list->max_tdmrs * tdmr_list->tdmr_sz); +} + +/* Get the TDMR from the list at the given index. */ +static struct tdmr_info *tdmr_entry(struct tdmr_info_list *tdmr_list, + int idx) +{ + int tdmr_info_offset = tdmr_list->tdmr_sz * idx; + + return (void *)tdmr_list->tdmrs + tdmr_info_offset; +} + +#define TDMR_ALIGNMENT SZ_1G +#define TDMR_ALIGN_DOWN(_addr) ALIGN_DOWN((_addr), TDMR_ALIGNMENT) +#define TDMR_ALIGN_UP(_addr) ALIGN((_addr), TDMR_ALIGNMENT) + +static inline u64 tdmr_end(struct tdmr_info *tdmr) +{ + return tdmr->base + tdmr->size; +} + +/* + * Take the memory referenced in @tmb_list and populate the + * preallocated @tdmr_list, following all the special alignment + * and size rules for TDMR. + */ +static int fill_out_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list) +{ + struct tdx_memblock *tmb; + int tdmr_idx = 0; + + /* + * Loop over TDX memory regions and fill out TDMRs to cover them. + * To keep it simple, always try to use one TDMR to cover one + * memory region. + * + * In practice TDX supports at least 64 TDMRs. A 2-socket system + * typically only consumes less than 10 of those. This code is + * dumb and simple and may use more TMDRs than is strictly + * required. + */ + list_for_each_entry(tmb, tmb_list, list) { + struct tdmr_info *tdmr = tdmr_entry(tdmr_list, tdmr_idx); + u64 start, end; + + start = TDMR_ALIGN_DOWN(PFN_PHYS(tmb->start_pfn)); + end = TDMR_ALIGN_UP(PFN_PHYS(tmb->end_pfn)); + + /* + * A valid size indicates the current TDMR has already + * been filled out to cover the previous memory region(s). + */ + if (tdmr->size) { + /* + * Loop to the next if the current memory region + * has already been fully covered. + */ + if (end <= tdmr_end(tdmr)) + continue; + + /* Otherwise, skip the already covered part. */ + if (start < tdmr_end(tdmr)) + start = tdmr_end(tdmr); + + /* + * Create a new TDMR to cover the current memory + * region, or the remaining part of it. + */ + tdmr_idx++; + if (tdmr_idx >= tdmr_list->max_tdmrs) { + pr_warn("initialization failed: TDMRs exhausted.\n"); + return -ENOSPC; + } + + tdmr = tdmr_entry(tdmr_list, tdmr_idx); + } + + tdmr->base = start; + tdmr->size = end - start; + } + + /* @tdmr_idx is always the index of the last valid TDMR. */ + tdmr_list->nr_consumed_tdmrs = tdmr_idx + 1; + + /* + * Warn early that kernel is about to run out of TDMRs. + * + * This is an indication that TDMR allocation has to be + * reworked to be smarter to not run into an issue. + */ + if (tdmr_list->max_tdmrs - tdmr_list->nr_consumed_tdmrs < TDMR_NR_WARN) + pr_warn("consumed TDMRs reaching limit: %d used out of %d\n", + tdmr_list->nr_consumed_tdmrs, + tdmr_list->max_tdmrs); + + return 0; +} + +/* + * Calculate PAMT size given a TDMR and a page size. The returned + * PAMT size is always aligned up to 4K page boundary. + */ +static unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz, + u16 pamt_entry_size) +{ + unsigned long pamt_sz, nr_pamt_entries; + + switch (pgsz) { + case TDX_PS_4K: + nr_pamt_entries = tdmr->size >> PAGE_SHIFT; + break; + case TDX_PS_2M: + nr_pamt_entries = tdmr->size >> PMD_SHIFT; + break; + case TDX_PS_1G: + nr_pamt_entries = tdmr->size >> PUD_SHIFT; + break; + default: + WARN_ON_ONCE(1); + return 0; + } + + pamt_sz = nr_pamt_entries * pamt_entry_size; + /* TDX requires PAMT size must be 4K aligned */ + pamt_sz = ALIGN(pamt_sz, PAGE_SIZE); + + return pamt_sz; +} + +/* + * Locate a NUMA node which should hold the allocation of the @tdmr + * PAMT. This node will have some memory covered by the TDMR. The + * relative amount of memory covered is not considered. + */ +static int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_list) +{ + struct tdx_memblock *tmb; + + /* + * A TDMR must cover at least part of one TMB. That TMB will end + * after the TDMR begins. But, that TMB may have started before + * the TDMR. Find the next 'tmb' that _ends_ after this TDMR + * begins. Ignore 'tmb' start addresses. They are irrelevant. + */ + list_for_each_entry(tmb, tmb_list, list) { + if (tmb->end_pfn > PHYS_PFN(tdmr->base)) + return tmb->nid; + } + + /* + * Fall back to allocating the TDMR's metadata from node 0 when + * no TDX memory block can be found. This should never happen + * since TDMRs originate from TDX memory blocks. + */ + pr_warn("TDMR [0x%llx, 0x%llx): unable to find local NUMA node for PAMT allocation, fallback to use node 0.\n", + tdmr->base, tdmr_end(tdmr)); + return 0; +} + +/* + * Allocate PAMTs from the local NUMA node of some memory in @tmb_list + * within @tdmr, and set up PAMTs for @tdmr. + */ +static int tdmr_set_up_pamt(struct tdmr_info *tdmr, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + unsigned long pamt_base[TDX_PS_NR]; + unsigned long pamt_size[TDX_PS_NR]; + unsigned long tdmr_pamt_base; + unsigned long tdmr_pamt_size; + struct page *pamt; + int pgsz, nid; + + nid = tdmr_get_nid(tdmr, tmb_list); + + /* + * Calculate the PAMT size for each TDX supported page size + * and the total PAMT size. + */ + tdmr_pamt_size = 0; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz, + pamt_entry_size[pgsz]); + tdmr_pamt_size += pamt_size[pgsz]; + } + + /* + * Allocate one chunk of physically contiguous memory for all + * PAMTs. This helps minimize the PAMT's use of reserved areas + * in overlapped TDMRs. + */ + pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL, + nid, &node_online_map); + if (!pamt) + return -ENOMEM; + + /* + * Break the contiguous allocation back up into the + * individual PAMTs for each page size. + */ + tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_base[pgsz] = tdmr_pamt_base; + tdmr_pamt_base += pamt_size[pgsz]; + } + + tdmr->pamt_4k_base = pamt_base[TDX_PS_4K]; + tdmr->pamt_4k_size = pamt_size[TDX_PS_4K]; + tdmr->pamt_2m_base = pamt_base[TDX_PS_2M]; + tdmr->pamt_2m_size = pamt_size[TDX_PS_2M]; + tdmr->pamt_1g_base = pamt_base[TDX_PS_1G]; + tdmr->pamt_1g_size = pamt_size[TDX_PS_1G]; + + return 0; +} + +static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base, + unsigned long *pamt_size) +{ + unsigned long pamt_bs, pamt_sz; + + /* + * The PAMT was allocated in one contiguous unit. The 4K PAMT + * should always point to the beginning of that allocation. + */ + pamt_bs = tdmr->pamt_4k_base; + pamt_sz = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size; + + WARN_ON_ONCE((pamt_bs & ~PAGE_MASK) || (pamt_sz & ~PAGE_MASK)); + + *pamt_base = pamt_bs; + *pamt_size = pamt_sz; +} + +static void tdmr_do_pamt_func(struct tdmr_info *tdmr, + void (*pamt_func)(unsigned long base, unsigned long size)) +{ + unsigned long pamt_base, pamt_size; + + tdmr_get_pamt(tdmr, &pamt_base, &pamt_size); + + /* Do nothing if PAMT hasn't been allocated for this TDMR */ + if (!pamt_size) + return; + + if (WARN_ON_ONCE(!pamt_base)) + return; + + pamt_func(pamt_base, pamt_size); +} + +static void free_pamt(unsigned long pamt_base, unsigned long pamt_size) +{ + free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT); +} + +static void tdmr_free_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, free_pamt); +} + +static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_free_pamt(tdmr_entry(tdmr_list, i)); +} + +/* Allocate and set up PAMTs for all TDMRs */ +static int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + int i, ret = 0; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list, + pamt_entry_size); + if (ret) + goto err; + } + + return 0; +err: + tdmrs_free_pamt_all(tdmr_list); + return ret; +} + +/* + * Convert TDX private pages back to normal by using MOVDIR64B to + * clear these pages. Note this function doesn't flush cache of + * these TDX private pages. The caller should make sure of that. + */ +static void reset_tdx_pages(unsigned long base, unsigned long size) +{ + const void *zero_page = (const void *)page_address(ZERO_PAGE(0)); + unsigned long phys, end; + + end = base + size; + for (phys = base; phys < end; phys += 64) + movdir64b(__va(phys), zero_page); + + /* + * MOVDIR64B uses WC protocol. Use memory barrier to + * make sure any later user of these pages sees the + * updated data. + */ + mb(); +} + +static void tdmr_reset_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, reset_tdx_pages); +} + +static void tdmrs_reset_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_reset_pamt(tdmr_entry(tdmr_list, i)); +} + +static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list) +{ + unsigned long pamt_size = 0; + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + pamt_size += size; + } + + return pamt_size / 1024; +} + +static int tdmr_add_rsvd_area(struct tdmr_info *tdmr, int *p_idx, u64 addr, + u64 size, u16 max_reserved_per_tdmr) +{ + struct tdmr_reserved_area *rsvd_areas = tdmr->reserved_areas; + int idx = *p_idx; + + /* Reserved area must be 4K aligned in offset and size */ + if (WARN_ON(addr & ~PAGE_MASK || size & ~PAGE_MASK)) + return -EINVAL; + + if (idx >= max_reserved_per_tdmr) { + pr_warn("initialization failed: TDMR [0x%llx, 0x%llx): reserved areas exhausted.\n", + tdmr->base, tdmr_end(tdmr)); + return -ENOSPC; + } + + /* + * Consume one reserved area per call. Make no effort to + * optimize or reduce the number of reserved areas which are + * consumed by contiguous reserved areas, for instance. + */ + rsvd_areas[idx].offset = addr - tdmr->base; + rsvd_areas[idx].size = size; + + *p_idx = idx + 1; + + return 0; +} + +/* + * Go through @tmb_list to find holes between memory areas. If any of + * those holes fall within @tdmr, set up a TDMR reserved area to cover + * the hole. + */ +static int tdmr_populate_rsvd_holes(struct list_head *tmb_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + struct tdx_memblock *tmb; + u64 prev_end; + int ret; + + /* + * Start looking for reserved blocks at the + * beginning of the TDMR. + */ + prev_end = tdmr->base; + list_for_each_entry(tmb, tmb_list, list) { + u64 start, end; + + start = PFN_PHYS(tmb->start_pfn); + end = PFN_PHYS(tmb->end_pfn); + + /* Break if this region is after the TDMR */ + if (start >= tdmr_end(tdmr)) + break; + + /* Exclude regions before this TDMR */ + if (end < tdmr->base) + continue; + + /* + * Skip over memory areas that + * have already been dealt with. + */ + if (start <= prev_end) { + prev_end = end; + continue; + } + + /* Add the hole before this region */ + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + start - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + + prev_end = end; + } + + /* Add the hole after the last region if it exists. */ + if (prev_end < tdmr_end(tdmr)) { + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + tdmr_end(tdmr) - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Go through @tdmr_list to find all PAMTs. If any of those PAMTs + * overlaps with @tdmr, set up a TDMR reserved area to cover the + * overlapping part. + */ +static int tdmr_populate_rsvd_pamts(struct tdmr_info_list *tdmr_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + int i, ret; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + struct tdmr_info *tmp = tdmr_entry(tdmr_list, i); + unsigned long pamt_base, pamt_size, pamt_end; + + tdmr_get_pamt(tmp, &pamt_base, &pamt_size); + /* Each TDMR must already have PAMT allocated */ + WARN_ON_ONCE(!pamt_size || !pamt_base); + + pamt_end = pamt_base + pamt_size; + /* Skip PAMTs outside of the given TDMR */ + if ((pamt_end <= tdmr->base) || + (pamt_base >= tdmr_end(tdmr))) + continue; + + /* Only mark the part within the TDMR as reserved */ + if (pamt_base < tdmr->base) + pamt_base = tdmr->base; + if (pamt_end > tdmr_end(tdmr)) + pamt_end = tdmr_end(tdmr); + + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, pamt_base, + pamt_end - pamt_base, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* Compare function called by sort() for TDMR reserved areas */ +static int rsvd_area_cmp_func(const void *a, const void *b) +{ + struct tdmr_reserved_area *r1 = (struct tdmr_reserved_area *)a; + struct tdmr_reserved_area *r2 = (struct tdmr_reserved_area *)b; + + if (r1->offset + r1->size <= r2->offset) + return -1; + if (r1->offset >= r2->offset + r2->size) + return 1; + + /* Reserved areas cannot overlap. The caller must guarantee. */ + WARN_ON_ONCE(1); + return -1; +} + +/* + * Populate reserved areas for the given @tdmr, including memory holes + * (via @tmb_list) and PAMTs (via @tdmr_list). + */ +static int tdmr_populate_rsvd_areas(struct tdmr_info *tdmr, + struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + u16 max_reserved_per_tdmr) +{ + int ret, rsvd_idx = 0; + + ret = tdmr_populate_rsvd_holes(tmb_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + ret = tdmr_populate_rsvd_pamts(tdmr_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + /* TDX requires reserved areas listed in address ascending order */ + sort(tdmr->reserved_areas, rsvd_idx, sizeof(struct tdmr_reserved_area), + rsvd_area_cmp_func, NULL); + + return 0; +} + +/* + * Populate reserved areas for all TDMRs in @tdmr_list, including memory + * holes (via @tmb_list) and PAMTs. + */ +static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 max_reserved_per_tdmr) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = tdmr_populate_rsvd_areas(tdmr_entry(tdmr_list, i), + tmb_list, tdmr_list, max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Construct a list of TDMRs on the preallocated space in @tdmr_list + * to cover all TDX memory regions in @tmb_list based on the TDX module + * TDMR global information in @tdmr_sysinfo. + */ +static int construct_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + + ret = fill_out_tdmrs(tmb_list, tdmr_list); + if (ret) + return ret; + + ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, + tdmr_sysinfo->pamt_entry_size); + if (ret) + return ret; + + ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list, + tdmr_sysinfo->max_reserved_per_tdmr); + if (ret) + tdmrs_free_pamt_all(tdmr_list); + + /* + * The tdmr_info_list is read-only from here on out. + * Ensure that these writes are seen by other CPUs. + * Pairs with a smp_rmb() in is_pamt_page(). + */ + smp_wmb(); + + return ret; +} + +static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid) +{ + struct tdx_module_args args = {}; + u64 *tdmr_pa_array; + size_t array_sz; + int i, ret; + + /* + * TDMRs are passed to the TDX module via an array of physical + * addresses of each TDMR. The array itself also has certain + * alignment requirement. + */ + array_sz = tdmr_list->nr_consumed_tdmrs * sizeof(u64); + array_sz = roundup_pow_of_two(array_sz); + if (array_sz < TDMR_INFO_PA_ARRAY_ALIGNMENT) + array_sz = TDMR_INFO_PA_ARRAY_ALIGNMENT; + + tdmr_pa_array = kzalloc(array_sz, GFP_KERNEL); + if (!tdmr_pa_array) + return -ENOMEM; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_pa_array[i] = __pa(tdmr_entry(tdmr_list, i)); + + args.rcx = __pa(tdmr_pa_array); + args.rdx = tdmr_list->nr_consumed_tdmrs; + args.r8 = global_keyid; + ret = seamcall_prerr(TDH_SYS_CONFIG, &args); + + /* Free the array as it is not required anymore. */ + kfree(tdmr_pa_array); + + return ret; +} + +static int do_global_key_config(void *unused) +{ + struct tdx_module_args args = {}; + + return seamcall_prerr(TDH_SYS_KEY_CONFIG, &args); +} + +/* + * Attempt to configure the global KeyID on all physical packages. + * + * This requires running code on at least one CPU in each package. + * TDMR initialization) will fail will fail if any package in the + * system has no online CPUs. + * + * This code takes no affirmative steps to online CPUs. Callers (aka. + * KVM) can ensure success by ensuring sufficient CPUs are online and + * can run SEAMCALLs. + */ +static int config_global_keyid(void) +{ + cpumask_var_t packages; + int cpu, ret = -EINVAL; + + if (!zalloc_cpumask_var(&packages, GFP_KERNEL)) + return -ENOMEM; + + /* + * Hardware doesn't guarantee cache coherency across different + * KeyIDs. The kernel needs to flush PAMT's dirty cachelines + * (associated with KeyID 0) before the TDX module can use the + * global KeyID to access the PAMT. Given PAMTs are potentially + * large (~1/256th of system RAM), just use WBINVD. + */ + wbinvd_on_all_cpus(); + + for_each_online_cpu(cpu) { + /* + * The key configuration only needs to be done once per + * package and will return an error if configured more + * than once. Avoid doing it multiple times per package. + */ + if (cpumask_test_and_set_cpu(topology_physical_package_id(cpu), + packages)) + continue; + + /* + * TDH.SYS.KEY.CONFIG cannot run concurrently on + * different cpus. Do it one by one. + */ + ret = smp_call_on_cpu(cpu, do_global_key_config, NULL, true); + if (ret) + break; + } + + free_cpumask_var(packages); + return ret; +} + +static int init_tdmr(struct tdmr_info *tdmr) +{ + u64 next; + + /* + * Initializing a TDMR can be time consuming. To avoid long + * SEAMCALLs, the TDX module may only initialize a part of the + * TDMR in each call. + */ + do { + struct tdx_module_args args = { + .rcx = tdmr->base, + }; + int ret; + + ret = seamcall_prerr_ret(TDH_SYS_TDMR_INIT, &args); + if (ret) + return ret; + /* + * RDX contains 'next-to-initialize' address if + * TDH.SYS.TDMR.INIT did not fully complete and + * should be retried. + */ + next = args.rdx; + cond_resched(); + /* Keep making SEAMCALLs until the TDMR is done */ + } while (next < tdmr->base + tdmr->size); + + return 0; +} + +static int init_tdmrs(struct tdmr_info_list *tdmr_list) +{ + int i; + + /* + * This operation is costly. It can be parallelized, + * but keep it simple for now. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = init_tdmr(tdmr_entry(tdmr_list, i)); + if (ret) + return ret; + } + + return 0; +} + +static int init_tdx_module(void) +{ + struct tdx_tdmr_sysinfo tdmr_sysinfo; + int ret; + + /* + * To keep things simple, assume that all TDX-protected memory + * will come from the page allocator. Make sure all pages in the + * page allocator are TDX-usable memory. + * + * Build the list of "TDX-usable" memory regions which cover all + * pages in the page allocator to guarantee that. Do it while + * holding mem_hotplug_lock read-lock as the memory hotplug code + * path reads the @tdx_memlist to reject any new memory. + */ + get_online_mems(); + + ret = build_tdx_memlist(&tdx_memlist); + if (ret) + goto out_put_tdxmem; + + ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Allocate enough space for constructing TDMRs */ + ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Cover all TDX-usable memory regions in TDMRs */ + ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdmrs; + + /* Pass the TDMRs and the global KeyID to the TDX module */ + ret = config_tdx_module(&tdx_tdmr_list, tdx_global_keyid); + if (ret) + goto err_free_pamts; + + /* Config the key of global KeyID on all packages */ + ret = config_global_keyid(); + if (ret) + goto err_reset_pamts; + + /* Initialize TDMRs to complete the TDX module initialization */ + ret = init_tdmrs(&tdx_tdmr_list); + if (ret) + goto err_reset_pamts; + + pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list)); + +out_put_tdxmem: + /* + * @tdx_memlist is written here and read at memory hotplug time. + * Lock out memory hotplug code while building it. + */ + put_online_mems(); + return ret; + +err_reset_pamts: + /* + * Part of PAMTs may already have been initialized by the + * TDX module. Flush cache before returning PAMTs back + * to the kernel. + */ + wbinvd_on_all_cpus(); + /* + * According to the TDX hardware spec, if the platform + * doesn't have the "partial write machine check" + * erratum, any kernel read/write will never cause #MC + * in kernel space, thus it's OK to not convert PAMTs + * back to normal. But do the conversion anyway here + * as suggested by the TDX spec. + */ + tdmrs_reset_pamt_all(&tdx_tdmr_list); +err_free_pamts: + tdmrs_free_pamt_all(&tdx_tdmr_list); +err_free_tdmrs: + free_tdmr_list(&tdx_tdmr_list); +err_free_tdxmem: + free_tdx_memlist(&tdx_memlist); + goto out_put_tdxmem; +} + +static int __tdx_enable(void) +{ + int ret; + + ret = init_tdx_module(); + if (ret) { + pr_err("module initialization failed (%d)\n", ret); + tdx_module_status = TDX_MODULE_ERROR; + return ret; + } + + pr_info("module initialized\n"); + tdx_module_status = TDX_MODULE_INITIALIZED; + + return 0; +} + +/** + * tdx_enable - Enable TDX module to make it ready to run TDX guests + * + * This function assumes the caller has: 1) held read lock of CPU hotplug + * lock to prevent any new cpu from becoming online; 2) done both VMXON + * and tdx_cpu_enable() on all online cpus. + * + * This function requires there's at least one online cpu for each CPU + * package to succeed. + * + * This function can be called in parallel by multiple callers. + * + * Return 0 if TDX is enabled successfully, otherwise error. + */ +int tdx_enable(void) +{ + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_cpus_held(); + + mutex_lock(&tdx_module_lock); + + switch (tdx_module_status) { + case TDX_MODULE_UNINITIALIZED: + ret = __tdx_enable(); + break; + case TDX_MODULE_INITIALIZED: + /* Already initialized, great, tell the caller. */ + ret = 0; + break; + default: + /* Failed to initialize in the previous attempts */ + ret = -EINVAL; + break; + } + + mutex_unlock(&tdx_module_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tdx_enable); + +static bool is_pamt_page(unsigned long phys) +{ + struct tdmr_info_list *tdmr_list = &tdx_tdmr_list; + int i; + + /* Ensure that all remote 'tdmr_list' writes are visible: */ + smp_rmb(); + + /* + * The TDX module is no longer returning TDX_SYS_NOT_READY and + * is initialized. The 'tdmr_list' was initialized long ago + * and is now read-only. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + + if (phys >= base && phys < (base + size)) + return true; + } + + return false; +} + +/* + * Return whether the memory page at the given physical address is TDX + * private memory or not. + * + * This can be imprecise for two known reasons: + * 1. PAMTs are private memory and exist before the TDX module is + * ready and TDH_PHYMEM_PAGE_RDMD works. This is a relatively + * short window that occurs once per boot. + * 2. TDH_PHYMEM_PAGE_RDMD reflects the TDX module's knowledge of the + * page. However, the page can still cause #MC until it has been + * fully converted to shared using 64-byte writes like MOVDIR64B. + * Buggy hosts might still leave #MC-causing memory in place which + * this function can not detect. + */ +static bool paddr_is_tdx_private(unsigned long phys) +{ + struct tdx_module_args args = { + .rcx = phys & PAGE_MASK, + }; + u64 sret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return false; + + /* Get page type from the TDX module */ + sret = __seamcall_ret(TDH_PHYMEM_PAGE_RDMD, &args); + + /* + * The SEAMCALL will not return success unless there is a + * working, "ready" TDX module. Assume an absence of TDX + * private pages until SEAMCALL is working. + */ + if (sret) + return false; + + /* + * SEAMCALL was successful -- read page type (via RCX): + * + * - PT_NDA: Page is not used by the TDX module + * - PT_RSVD: Reserved for Non-TDX use + * - Others: Page is used by the TDX module + * + * Note PAMT pages are marked as PT_RSVD but they are also TDX + * private memory. + */ + switch (args.rcx) { + case PT_NDA: + return false; + case PT_RSVD: + return is_pamt_page(phys); + default: + return true; + } +} + +/* + * Some TDX-capable CPUs have an erratum. A write to TDX private + * memory poisons that memory, and a subsequent read of that memory + * triggers #MC. + * + * Help distinguish erratum-triggered #MCs from a normal hardware one. + * Just print additional message to show such #MC may be result of the + * erratum. + */ +const char *tdx_dump_mce_info(struct mce *m) +{ + if (!m || !mce_is_memory_error(m) || !mce_usable_address(m)) + return NULL; + + if (!paddr_is_tdx_private(m->addr)) + return NULL; + + return "TDX private memory error. Possible kernel bug."; +} + +static __init int record_keyid_partitioning(u32 *tdx_keyid_start, + u32 *nr_tdx_keyids) +{ + u32 _nr_mktme_keyids, _tdx_keyid_start, _nr_tdx_keyids; + int ret; + + /* + * IA32_MKTME_KEYID_PARTIONING: + * Bit [31:0]: Number of MKTME KeyIDs. + * Bit [63:32]: Number of TDX private KeyIDs. + */ + ret = rdmsr_safe(MSR_IA32_MKTME_KEYID_PARTITIONING, &_nr_mktme_keyids, + &_nr_tdx_keyids); + if (ret || !_nr_tdx_keyids) + return -EINVAL; + + /* TDX KeyIDs start after the last MKTME KeyID. */ + _tdx_keyid_start = _nr_mktme_keyids + 1; + + *tdx_keyid_start = _tdx_keyid_start; + *nr_tdx_keyids = _nr_tdx_keyids; + + return 0; +} + +static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn) +{ + struct tdx_memblock *tmb; + + /* + * This check assumes that the start_pfn<->end_pfn range does not + * cross multiple @tdx_memlist entries. A single memory online + * event across multiple memblocks (from which @tdx_memlist + * entries are derived at the time of module initialization) is + * not possible. This is because memory offline/online is done + * on granularity of 'struct memory_block', and the hotpluggable + * memory region (one memblock) must be multiple of memory_block. + */ + list_for_each_entry(tmb, &tdx_memlist, list) { + if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn) + return true; + } + return false; +} + +static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action, + void *v) +{ + struct memory_notify *mn = v; + + if (action != MEM_GOING_ONLINE) + return NOTIFY_OK; + + /* + * Empty list means TDX isn't enabled. Allow any memory + * to go online. + */ + if (list_empty(&tdx_memlist)) + return NOTIFY_OK; + + /* + * The TDX memory configuration is static and can not be + * changed. Reject onlining any memory which is outside of + * the static configuration whether it supports TDX or not. + */ + if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages)) + return NOTIFY_OK; + + return NOTIFY_BAD; +} + +static struct notifier_block tdx_memory_nb = { + .notifier_call = tdx_memory_notifier, +}; + +static void __init check_tdx_erratum(void) +{ + /* + * These CPUs have an erratum. A partial write from non-TD + * software (e.g. via MOVNTI variants or UC/WC mapping) to TDX + * private memory poisons that memory, and a subsequent read of + * that memory triggers #MC. + */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: + setup_force_cpu_bug(X86_BUG_TDX_PW_MCE); + } +} + +void __init tdx_init(void) +{ + u32 tdx_keyid_start, nr_tdx_keyids; + int err; + + err = record_keyid_partitioning(&tdx_keyid_start, &nr_tdx_keyids); + if (err) + return; + + pr_info("BIOS enabled: private KeyID range [%u, %u)\n", + tdx_keyid_start, tdx_keyid_start + nr_tdx_keyids); + + /* + * The TDX module itself requires one 'global KeyID' to protect + * its metadata. If there's only one TDX KeyID, there won't be + * any left for TDX guests thus there's no point to enable TDX + * at all. + */ + if (nr_tdx_keyids < 2) { + pr_err("initialization failed: too few private KeyIDs available.\n"); + return; + } + + /* + * At this point, hibernation_available() indicates whether or + * not hibernation support has been permanently disabled. + */ + if (hibernation_available()) { + pr_err("initialization failed: Hibernation support is enabled\n"); + return; + } + + err = register_memory_notifier(&tdx_memory_nb); + if (err) { + pr_err("initialization failed: register_memory_notifier() failed (%d)\n", + err); + return; + } + +#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) + pr_info("Disable ACPI S3. Turn off TDX in the BIOS to use ACPI S3.\n"); + acpi_suspend_lowlevel = NULL; +#endif + + /* + * Just use the first TDX KeyID as the 'global KeyID' and + * leave the rest for TDX guests. + */ + tdx_global_keyid = tdx_keyid_start; + tdx_guest_keyid_start = tdx_keyid_start + 1; + tdx_nr_guest_keyids = nr_tdx_keyids - 1; + + setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM); + + check_tdx_erratum(); +} diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h new file mode 100644 index 000000000000..b701f69485d3 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_VIRT_TDX_H +#define _X86_VIRT_TDX_H + +#include <linux/bits.h> + +/* + * This file contains both macros and data structures defined by the TDX + * architecture and Linux defined software data structures and functions. + * The two should not be mixed together for better readability. The + * architectural definitions come first. + */ + +/* + * TDX module SEAMCALL leaf functions + */ +#define TDH_PHYMEM_PAGE_RDMD 24 +#define TDH_SYS_KEY_CONFIG 31 +#define TDH_SYS_INIT 33 +#define TDH_SYS_RD 34 +#define TDH_SYS_LP_INIT 35 +#define TDH_SYS_TDMR_INIT 36 +#define TDH_SYS_CONFIG 45 + +/* TDX page types */ +#define PT_NDA 0x0 +#define PT_RSVD 0x1 + +/* + * Global scope metadata field ID. + * + * See Table "Global Scope Metadata", TDX module 1.5 ABI spec. + */ +#define MD_FIELD_ID_MAX_TDMRS 0x9100000100000008ULL +#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR 0x9100000100000009ULL +#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE 0x9100000100000010ULL +#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE 0x9100000100000011ULL +#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE 0x9100000100000012ULL + +/* + * Sub-field definition of metadata field ID. + * + * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header) + * Definition", TDX module 1.5 ABI spec. + * + * - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata + * + * 0: 8 bits + * 1: 16 bits + * 2: 32 bits + * 3: 64 bits + */ +#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id) \ + (((_field_id) & GENMASK_ULL(33, 32)) >> 32) + +#define MD_FIELD_ID_ELE_SIZE_16BIT 1 + +struct tdmr_reserved_area { + u64 offset; + u64 size; +} __packed; + +#define TDMR_INFO_ALIGNMENT 512 +#define TDMR_INFO_PA_ARRAY_ALIGNMENT 512 + +struct tdmr_info { + u64 base; + u64 size; + u64 pamt_1g_base; + u64 pamt_1g_size; + u64 pamt_2m_base; + u64 pamt_2m_size; + u64 pamt_4k_base; + u64 pamt_4k_size; + /* + * The actual number of reserved areas depends on the value of + * field MD_FIELD_ID_MAX_RESERVED_PER_TDMR in the TDX module + * global metadata. + */ + DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas); +} __packed __aligned(TDMR_INFO_ALIGNMENT); + +/* + * Do not put any hardware-defined TDX structure representations below + * this comment! + */ + +/* Kernel defined TDX module status during module initialization. */ +enum tdx_module_status_t { + TDX_MODULE_UNINITIALIZED, + TDX_MODULE_INITIALIZED, + TDX_MODULE_ERROR +}; + +struct tdx_memblock { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +}; + +/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */ +struct tdx_tdmr_sysinfo { + u16 max_tdmrs; + u16 max_reserved_per_tdmr; + u16 pamt_entry_size[TDX_PS_NR]; +}; + +/* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */ +#define TDMR_NR_WARN 4 + +struct tdmr_info_list { + void *tdmrs; /* Flexible array to hold 'tdmr_info's */ + int nr_consumed_tdmrs; /* How many 'tdmr_info's are in use */ + + /* Metadata for finding target 'tdmr_info' and freeing @tdmrs */ + int tdmr_sz; /* Size of one 'tdmr_info' */ + int max_tdmrs; /* How many 'tdmr_info's are allocated */ +}; + +#endif |