diff options
Diffstat (limited to 'arch/x86/include')
51 files changed, 504 insertions, 1181 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6c23d1661b17..58f4ddecc5fa 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index dc03a647776d..e3903b731305 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/stringify.h> +#include <linux/objtool.h> #include <asm/asm.h> #define ALT_FLAGS_SHIFT 16 @@ -55,16 +56,6 @@ #endif /* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -#define ANNOTATE_IGNORE_ALTERNATIVE \ - "999:\n\t" \ - ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - -/* * The patching flags are part of the upper bits of the @ft_flags parameter when * specifying them. The split is currently like this: * @@ -311,17 +302,6 @@ void nop_func(void); #endif /* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -.macro ANNOTATE_IGNORE_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.ignore_alts - .long .Lannotate_\@ - .popsection -.endm - -/* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains * enough information for the alternatives patching code to patch an diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index d0caac26533f..4c4efb93045e 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -4,7 +4,7 @@ #include <linux/ioport.h> #include <linux/pci.h> -#include <linux/refcount.h> +#include <asm/amd_node.h> struct amd_nb_bus_dev_range { u8 bus; @@ -21,49 +21,16 @@ extern int amd_numa_init(void); extern int amd_get_subcaches(int); extern int amd_set_subcaches(int, unsigned long); -int __must_check amd_smn_read(u16 node, u32 address, u32 *value); -int __must_check amd_smn_write(u16 node, u32 address, u32 value); - struct amd_l3_cache { unsigned indices; u8 subcaches[4]; }; -struct threshold_block { - unsigned int block; /* Number within bank */ - unsigned int bank; /* MCA bank the block belongs to */ - unsigned int cpu; /* CPU which controls MCA bank */ - u32 address; /* MSR address for the block */ - u16 interrupt_enable; /* Enable/Disable APIC interrupt */ - bool interrupt_capable; /* Bank can generate an interrupt. */ - - u16 threshold_limit; /* - * Value upon which threshold - * interrupt is generated. - */ - - struct kobject kobj; /* sysfs object */ - struct list_head miscj; /* - * List of threshold blocks - * within a bank. - */ -}; - -struct threshold_bank { - struct kobject *kobj; - struct threshold_block *blocks; - - /* initialized to the number of CPUs on the node sharing this bank */ - refcount_t cpus; - unsigned int shared; -}; - struct amd_northbridge { struct pci_dev *root; struct pci_dev *misc; struct pci_dev *link; struct amd_l3_cache l3_cache; - struct threshold_bank *bank4; }; struct amd_northbridge_info { @@ -82,23 +49,6 @@ u16 amd_nb_num(void); bool amd_nb_has_feature(unsigned int feature); struct amd_northbridge *node_to_amd_nb(int node); -static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) -{ - struct pci_dev *misc; - int i; - - for (i = 0; i != amd_nb_num(); i++) { - misc = node_to_amd_nb(i)->misc; - - if (pci_domain_nr(misc->bus) == pci_domain_nr(pdev->bus) && - PCI_SLOT(misc->devfn) == PCI_SLOT(pdev->devfn)) - return i; - } - - WARN(1, "Unable to find AMD Northbridge id for %s\n", pci_name(pdev)); - return 0; -} - static inline bool amd_gart_present(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h new file mode 100644 index 000000000000..113ad3e8ee40 --- /dev/null +++ b/arch/x86/include/asm/amd_node.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + * + * Note: + * Items in this file may only be used in a single place. + * However, it's prudent to keep all AMD Node functionality + * in a unified place rather than spreading throughout the + * kernel. + */ + +#ifndef _ASM_X86_AMD_NODE_H_ +#define _ASM_X86_AMD_NODE_H_ + +#include <linux/pci.h> + +#define MAX_AMD_NUM_NODES 8 +#define AMD_NODE0_PCI_SLOT 0x18 + +struct pci_dev *amd_node_get_func(u16 node, u8 func); +struct pci_dev *amd_node_get_root(u16 node); + +static inline u16 amd_num_nodes(void) +{ + return topology_amd_nodes_per_pkg() * topology_max_packages(); +} + +int __must_check amd_smn_read(u16 node, u32 address, u32 *value); +int __must_check amd_smn_write(u16 node, u32 address, u32 value); + +#endif /*_ASM_X86_AMD_NODE_H_*/ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 806649c7f23d..e85ac0c7c039 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -92,7 +92,7 @@ do { \ do { \ __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ANNOTATE_REACHABLE(1b)); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index e4121d9aa9e1..ba32e0f44cba 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -56,7 +56,6 @@ /* x86_cpu_id::flags */ #define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) -#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY @@ -208,6 +207,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, X86_FEATURE_ANY, data) +#define __X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping * @vfm: Encoded 8-bits each for vendor, family, model @@ -218,12 +218,13 @@ * * feature is set to wildcard */ -#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ - X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ - VFM_VENDOR(vfm), \ - VFM_FAMILY(vfm), \ - VFM_MODEL(vfm), \ - steppings, X86_FEATURE_ANY, data) +#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + __X86_STEPPINGS(min_step, max_step), \ + X86_FEATURE_ANY, data) /** * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature @@ -242,41 +243,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, feature, data) -/* - * Match specific microcode revisions. - * - * vendor/family/model/stepping must be all set. - * - * Only checks against the boot CPU. When mixed-stepping configs are - * valid for a CPU model, add a quirk for every valid stepping and - * do the fine-tuning in the quirk handler. - */ - -struct x86_cpu_desc { - u8 x86_family; - u8 x86_vendor; - u8 x86_model; - u8 x86_stepping; - u32 x86_microcode_rev; -}; - -#define INTEL_CPU_DESC(vfm, stepping, revision) { \ - .x86_family = VFM_FAMILY(vfm), \ - .x86_vendor = VFM_VENDOR(vfm), \ - .x86_model = VFM_MODEL(vfm), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - -#define AMD_CPU_DESC(fam, model, stepping, revision) { \ - .x86_family = (fam), \ - .x86_vendor = X86_VENDOR_AMD, \ - .x86_model = (model), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); -extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); +extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table); #endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0b9611da6c53..de1ad09fe8d7 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -132,11 +132,12 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* - * This macro is for detection of features which need kernel - * infrastructure to be used. It may *not* directly test the CPU - * itself. Use the cpu_has() family if you want true runtime - * testing of CPU features, like in hypervisor code where you are - * supporting a possible guest feature where host support for it + * This is the default CPU features testing macro to use in code. + * + * It is for detection of features which need kernel infrastructure to be + * used. It may *not* directly test the CPU itself. Use the cpu_has() family + * if you want true runtime testing of CPU features, like in hypervisor code + * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ @@ -161,13 +162,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* - * Static testing of CPU features. Used the same as boot_cpu_has(). It - * statically patches the target code for additional performance. Use - * static_cpu_has() only in fast paths, where every cycle counts. Which - * means that the boot_cpu_has() variant is already fast enough for the - * majority of cases and you should stick to using it as it is generally - * only two instructions: a RIP-relative MOV and a TEST. - * * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 17b6590748c0..508c0dad116b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -83,8 +83,8 @@ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ #define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ #define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +/* Free ( 3*32+ 6) */ +/* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ #define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ @@ -443,15 +443,18 @@ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ @@ -464,6 +467,7 @@ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ +#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */ /* * Extended auxiliary flags: Linux defined - for features scattered in various diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 239b9ba5c398..b2b9b4ef3dae 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -21,6 +21,13 @@ enum cpuid_regs_idx { CPUID_EDX, }; +#define CPUID_LEAF_MWAIT 0x5 +#define CPUID_LEAF_DCA 0x9 +#define CPUID_LEAF_XSTATE 0x0d +#define CPUID_LEAF_TSC 0x15 +#define CPUID_LEAF_FREQ 0x16 +#define CPUID_LEAF_TILE 0x1d + #ifdef CONFIG_X86_32 bool have_cpuid_p(void); #else diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 521aad70e41b..f227a70ac91f 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -250,6 +250,9 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_allocate_pool(type, size, buffer) \ ((type), (size), efi64_zero_upper(buffer)) +#define __efi64_argmap_locate_handle_buffer(type, proto, key, num, buf) \ + ((type), (proto), (key), efi64_zero_upper(num), efi64_zero_upper(buf)) + #define __efi64_argmap_create_event(type, tpl, f, c, event) \ ((type), (tpl), (f), (c), efi64_zero_upper(event)) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index d4427b88ee12..7f39fe7980c5 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -12,10 +12,6 @@ /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) -#define XSTATE_CPUID 0x0000000d - -#define TILE_CPUID 0x0000001d - #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 6e8cf0fa48fc..f9cb4d07df58 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,6 +34,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ +#ifdef CONFIG_X86_KERNEL_IBT + u32 instr; + + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) { + if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE))) + return fentry_ip; + } else { + instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE); + } + if (is_endbr(instr)) + fentry_ip -= ENDBR_INSN_SIZE; +#endif + return fentry_ip; +} +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) + #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS #include <linux/ftrace_regs.h> @@ -47,10 +68,23 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &arch_ftrace_regs(fregs)->regs; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ + (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ + (_regs)->cs = __KERNEL_CS; \ + (_regs)->flags = 0; \ + } while (0) + #define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0) +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs); +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -134,24 +168,4 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) #endif /* !COMPILE_OFFSETS */ #endif /* !__ASSEMBLY__ */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long ax; - unsigned long dx; - unsigned long bp; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->ax; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->bp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index ab9f3dd87c80..ab0c78855ecb 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -84,7 +84,6 @@ extern int hpet_set_rtc_irq_bit(unsigned long bit_mask); extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec); extern int hpet_set_periodic_freq(unsigned long freq); -extern int hpet_rtc_dropped_irq(void); extern int hpet_rtc_timer_init(void); extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id); extern int hpet_register_irq_handler(rtc_irq_handler handler); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h deleted file mode 100644 index 3787d26810c1..000000000000 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ /dev/null @@ -1,811 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file contains definitions from Hyper-V Hypervisor Top-Level Functional - * Specification (TLFS): - * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs - */ - -#ifndef _ASM_X86_HYPERV_TLFS_H -#define _ASM_X86_HYPERV_TLFS_H - -#include <linux/types.h> -#include <asm/page.h> -/* - * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent - * is set by CPUID(HvCpuIdFunctionVersionAndFeatures). - */ -#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 -#define HYPERV_CPUID_INTERFACE 0x40000001 -#define HYPERV_CPUID_VERSION 0x40000002 -#define HYPERV_CPUID_FEATURES 0x40000003 -#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 -#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 -#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 -#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A -#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C - -#define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081 -#define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */ - -#define HYPERV_CPUID_VIRT_STACK_PROPERTIES 0x40000082 -/* Support for the extended IOAPIC RTE format */ -#define HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE BIT(2) - -#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000 -#define HYPERV_CPUID_MIN 0x40000005 -#define HYPERV_CPUID_MAX 0x4000ffff - -/* - * Group D Features. The bit assignments are custom to each architecture. - * On x86/x64 these are HYPERV_CPUID_FEATURES.EDX bits. - */ -/* The MWAIT instruction is available (per section MONITOR / MWAIT) */ -#define HV_X64_MWAIT_AVAILABLE BIT(0) -/* Guest debugging support is available */ -#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) -/* Performance Monitor support is available*/ -#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) -/* Support for physical CPU dynamic partitioning events is available*/ -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -/* - * Support for passing hypercall input parameter block via XMM - * registers is available - */ -#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) -/* Support for a virtual guest idle state is available */ -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) -/* Frequency MSRs available */ -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) -/* Crash MSR available */ -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) -/* Support for debug MSRs available */ -#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) -/* Support for extended gva ranges for flush hypercalls available */ -#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14) -/* - * Support for returning hypercall output block via XMM - * registers is available - */ -#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15) -/* stimer Direct Mode is available */ -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) - -/* - * Implementation recommendations. Indicates which behaviors the hypervisor - * recommends the OS implement for optimal performance. - * These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits. - */ -/* - * Recommend using hypercall for address space switches rather - * than MOV to CR3 instruction - */ -#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) -/* Recommend using hypercall for local TLB flushes rather - * than INVLPG or MOV to CR3 instructions */ -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) -/* - * Recommend using hypercall for remote TLB flushes rather - * than inter-processor interrupts - */ -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) -/* - * Recommend using MSRs for accessing APIC registers - * EOI, ICR and TPR rather than their memory-mapped counterparts - */ -#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) -/* Recommend using the hypervisor-provided MSR to initiate a system RESET */ -#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) -/* - * Recommend using relaxed timing for this partition. If used, - * the VM should disable any watchdog timeouts that rely on the - * timely delivery of external interrupts - */ -#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) - -/* - * Recommend not using Auto End-Of-Interrupt feature - */ -#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) - -/* - * Recommend using cluster IPI hypercalls. - */ -#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) - -/* Recommend using the newer ExProcessorMasks interface */ -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) - -/* Indicates that the hypervisor is nested within a Hyper-V partition. */ -#define HV_X64_HYPERV_NESTED BIT(12) - -/* Recommend using enlightened VMCS */ -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) - -/* Use hypercalls for MMIO config space access */ -#define HV_X64_USE_MMIO_HYPERCALLS BIT(21) - -/* - * CPU management features identification. - * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. - */ -#define HV_X64_START_LOGICAL_PROCESSOR BIT(0) -#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1) -#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2) -#define HV_X64_RESERVED_IDENTITY_BIT BIT(31) - -/* - * Virtual processor will never share a physical core with another virtual - * processor, except for virtual processors that are reported as sibling SMT - * threads. - */ -#define HV_X64_NO_NONARCH_CORESHARING BIT(18) - -/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ -#define HV_X64_NESTED_DIRECT_FLUSH BIT(17) -#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) -#define HV_X64_NESTED_MSR_BITMAP BIT(19) - -/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */ -#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0) - -/* - * This is specific to AMD and specifies that enlightened TLB flush is - * supported. If guest opts in to this feature, ASID invalidations only - * flushes gva -> hpa mapping entries. To flush the TLB entries derived - * from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace - * or HvFlushGuestPhysicalAddressList). - */ -#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22) - -/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ -#define HV_PARAVISOR_PRESENT BIT(0) - -/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */ -#define HV_ISOLATION_TYPE GENMASK(3, 0) -#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5) -#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6) - -enum hv_isolation_type { - HV_ISOLATION_TYPE_NONE = 0, - HV_ISOLATION_TYPE_VBS = 1, - HV_ISOLATION_TYPE_SNP = 2, - HV_ISOLATION_TYPE_TDX = 3 -}; - -/* Hyper-V specific model specific registers (MSRs) */ - -/* MSR used to identify the guest OS. */ -#define HV_X64_MSR_GUEST_OS_ID 0x40000000 - -/* MSR used to setup pages used to communicate with the hypervisor. */ -#define HV_X64_MSR_HYPERCALL 0x40000001 - -/* MSR used to provide vcpu index */ -#define HV_X64_MSR_VP_INDEX 0x40000002 - -/* MSR used to reset the guest OS. */ -#define HV_X64_MSR_RESET 0x40000003 - -/* MSR used to provide vcpu runtime in 100ns units */ -#define HV_X64_MSR_VP_RUNTIME 0x40000010 - -/* MSR used to read the per-partition time reference counter */ -#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 - -/* A partition's reference time stamp counter (TSC) page */ -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 - -/* MSR used to retrieve the TSC frequency */ -#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 - -/* MSR used to retrieve the local APIC timer frequency */ -#define HV_X64_MSR_APIC_FREQUENCY 0x40000023 - -/* Define the virtual APIC registers */ -#define HV_X64_MSR_EOI 0x40000070 -#define HV_X64_MSR_ICR 0x40000071 -#define HV_X64_MSR_TPR 0x40000072 -#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 - -/* Define synthetic interrupt controller model specific registers. */ -#define HV_X64_MSR_SCONTROL 0x40000080 -#define HV_X64_MSR_SVERSION 0x40000081 -#define HV_X64_MSR_SIEFP 0x40000082 -#define HV_X64_MSR_SIMP 0x40000083 -#define HV_X64_MSR_EOM 0x40000084 -#define HV_X64_MSR_SINT0 0x40000090 -#define HV_X64_MSR_SINT1 0x40000091 -#define HV_X64_MSR_SINT2 0x40000092 -#define HV_X64_MSR_SINT3 0x40000093 -#define HV_X64_MSR_SINT4 0x40000094 -#define HV_X64_MSR_SINT5 0x40000095 -#define HV_X64_MSR_SINT6 0x40000096 -#define HV_X64_MSR_SINT7 0x40000097 -#define HV_X64_MSR_SINT8 0x40000098 -#define HV_X64_MSR_SINT9 0x40000099 -#define HV_X64_MSR_SINT10 0x4000009A -#define HV_X64_MSR_SINT11 0x4000009B -#define HV_X64_MSR_SINT12 0x4000009C -#define HV_X64_MSR_SINT13 0x4000009D -#define HV_X64_MSR_SINT14 0x4000009E -#define HV_X64_MSR_SINT15 0x4000009F - -/* - * Define synthetic interrupt controller model specific registers for - * nested hypervisor. - */ -#define HV_X64_MSR_NESTED_SCONTROL 0x40001080 -#define HV_X64_MSR_NESTED_SVERSION 0x40001081 -#define HV_X64_MSR_NESTED_SIEFP 0x40001082 -#define HV_X64_MSR_NESTED_SIMP 0x40001083 -#define HV_X64_MSR_NESTED_EOM 0x40001084 -#define HV_X64_MSR_NESTED_SINT0 0x40001090 - -/* - * Synthetic Timer MSRs. Four timers per vcpu. - */ -#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 -#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 -#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 -#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 -#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 -#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 -#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 -#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 - -/* Hyper-V guest idle MSR */ -#define HV_X64_MSR_GUEST_IDLE 0x400000F0 - -/* Hyper-V guest crash notification MSR's */ -#define HV_X64_MSR_CRASH_P0 0x40000100 -#define HV_X64_MSR_CRASH_P1 0x40000101 -#define HV_X64_MSR_CRASH_P2 0x40000102 -#define HV_X64_MSR_CRASH_P3 0x40000103 -#define HV_X64_MSR_CRASH_P4 0x40000104 -#define HV_X64_MSR_CRASH_CTL 0x40000105 - -/* TSC emulation after migration */ -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 -#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 - -/* TSC invariant control */ -#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 - -/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ -#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) - -/* - * To support arch-generic code calling hv_set/get_register: - * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl - * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall - */ -#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0) -#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1) -#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2) -#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3) -#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4) -#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL) - -#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX) -#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT) -#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC) - -#define HV_MSR_SINT0 (HV_X64_MSR_SINT0) -#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION) -#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL) -#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP) -#define HV_MSR_SIMP (HV_X64_MSR_SIMP) -#define HV_MSR_EOM (HV_X64_MSR_EOM) - -#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL) -#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION) -#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP) -#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP) -#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM) -#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0) - -#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG) -#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT) - -/* - * Registers are only accessible via HVCALL_GET_VP_REGISTERS hvcall and - * there is not associated MSR address. - */ -#define HV_X64_REGISTER_VSM_VP_STATUS 0x000D0003 -#define HV_X64_VTL_MASK GENMASK(3, 0) - -/* Hyper-V memory host visibility */ -enum hv_mem_host_visibility { - VMBUS_PAGE_NOT_VISIBLE = 0, - VMBUS_PAGE_VISIBLE_READ_ONLY = 1, - VMBUS_PAGE_VISIBLE_READ_WRITE = 3 -}; - -/* HvCallModifySparseGpaPageHostVisibility hypercall */ -#define HV_MAX_MODIFY_GPA_REP_COUNT ((PAGE_SIZE / sizeof(u64)) - 2) -struct hv_gpa_range_for_visibility { - u64 partition_id; - u32 host_visibility:2; - u32 reserved0:30; - u32 reserved1; - u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT]; -} __packed; - -/* - * Declare the MSR used to setup pages used to communicate with the hypervisor. - */ -union hv_x64_msr_hypercall_contents { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:11; - u64 guest_physical_address:52; - } __packed; -}; - -union hv_vp_assist_msr_contents { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:11; - u64 pfn:52; - } __packed; -}; - -struct hv_reenlightenment_control { - __u64 vector:8; - __u64 reserved1:8; - __u64 enabled:1; - __u64 reserved2:15; - __u64 target_vp:32; -} __packed; - -struct hv_tsc_emulation_control { - __u64 enabled:1; - __u64 reserved:63; -} __packed; - -struct hv_tsc_emulation_status { - __u64 inprogress:1; - __u64 reserved:63; -} __packed; - -#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 -#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 -#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ - (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) - -#define HV_X64_MSR_CRASH_PARAMS \ - (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) - -#define HV_IPI_LOW_VECTOR 0x10 -#define HV_IPI_HIGH_VECTOR 0xff - -#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ - (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) - -/* Hyper-V Enlightened VMCS version mask in nested features CPUID */ -#define HV_X64_ENLIGHTENED_VMCS_VERSION 0xff - -#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001 -#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12 - -/* Number of XMM registers used in hypercall input/output */ -#define HV_HYPERCALL_MAX_XMM_REGISTERS 6 - -struct hv_nested_enlightenments_control { - struct { - __u32 directhypercall:1; - __u32 reserved:31; - } features; - struct { - __u32 inter_partition_comm:1; - __u32 reserved:31; - } hypercallControls; -} __packed; - -/* Define virtual processor assist page structure. */ -struct hv_vp_assist_page { - __u32 apic_assist; - __u32 reserved1; - __u32 vtl_entry_reason; - __u32 vtl_reserved; - __u64 vtl_ret_x64rax; - __u64 vtl_ret_x64rcx; - struct hv_nested_enlightenments_control nested_control; - __u8 enlighten_vmentry; - __u8 reserved2[7]; - __u64 current_nested_vmcs; - __u8 synthetic_time_unhalted_timer_expired; - __u8 reserved3[7]; - __u8 virtualization_fault_information[40]; - __u8 reserved4[8]; - __u8 intercept_message[256]; - __u8 vtl_ret_actions[256]; -} __packed; - -struct hv_enlightened_vmcs { - u32 revision_id; - u32 abort; - - u16 host_es_selector; - u16 host_cs_selector; - u16 host_ss_selector; - u16 host_ds_selector; - u16 host_fs_selector; - u16 host_gs_selector; - u16 host_tr_selector; - - u16 padding16_1; - - u64 host_ia32_pat; - u64 host_ia32_efer; - - u64 host_cr0; - u64 host_cr3; - u64 host_cr4; - - u64 host_ia32_sysenter_esp; - u64 host_ia32_sysenter_eip; - u64 host_rip; - u32 host_ia32_sysenter_cs; - - u32 pin_based_vm_exec_control; - u32 vm_exit_controls; - u32 secondary_vm_exec_control; - - u64 io_bitmap_a; - u64 io_bitmap_b; - u64 msr_bitmap; - - u16 guest_es_selector; - u16 guest_cs_selector; - u16 guest_ss_selector; - u16 guest_ds_selector; - u16 guest_fs_selector; - u16 guest_gs_selector; - u16 guest_ldtr_selector; - u16 guest_tr_selector; - - u32 guest_es_limit; - u32 guest_cs_limit; - u32 guest_ss_limit; - u32 guest_ds_limit; - u32 guest_fs_limit; - u32 guest_gs_limit; - u32 guest_ldtr_limit; - u32 guest_tr_limit; - u32 guest_gdtr_limit; - u32 guest_idtr_limit; - - u32 guest_es_ar_bytes; - u32 guest_cs_ar_bytes; - u32 guest_ss_ar_bytes; - u32 guest_ds_ar_bytes; - u32 guest_fs_ar_bytes; - u32 guest_gs_ar_bytes; - u32 guest_ldtr_ar_bytes; - u32 guest_tr_ar_bytes; - - u64 guest_es_base; - u64 guest_cs_base; - u64 guest_ss_base; - u64 guest_ds_base; - u64 guest_fs_base; - u64 guest_gs_base; - u64 guest_ldtr_base; - u64 guest_tr_base; - u64 guest_gdtr_base; - u64 guest_idtr_base; - - u64 padding64_1[3]; - - u64 vm_exit_msr_store_addr; - u64 vm_exit_msr_load_addr; - u64 vm_entry_msr_load_addr; - - u64 cr3_target_value0; - u64 cr3_target_value1; - u64 cr3_target_value2; - u64 cr3_target_value3; - - u32 page_fault_error_code_mask; - u32 page_fault_error_code_match; - - u32 cr3_target_count; - u32 vm_exit_msr_store_count; - u32 vm_exit_msr_load_count; - u32 vm_entry_msr_load_count; - - u64 tsc_offset; - u64 virtual_apic_page_addr; - u64 vmcs_link_pointer; - - u64 guest_ia32_debugctl; - u64 guest_ia32_pat; - u64 guest_ia32_efer; - - u64 guest_pdptr0; - u64 guest_pdptr1; - u64 guest_pdptr2; - u64 guest_pdptr3; - - u64 guest_pending_dbg_exceptions; - u64 guest_sysenter_esp; - u64 guest_sysenter_eip; - - u32 guest_activity_state; - u32 guest_sysenter_cs; - - u64 cr0_guest_host_mask; - u64 cr4_guest_host_mask; - u64 cr0_read_shadow; - u64 cr4_read_shadow; - u64 guest_cr0; - u64 guest_cr3; - u64 guest_cr4; - u64 guest_dr7; - - u64 host_fs_base; - u64 host_gs_base; - u64 host_tr_base; - u64 host_gdtr_base; - u64 host_idtr_base; - u64 host_rsp; - - u64 ept_pointer; - - u16 virtual_processor_id; - u16 padding16_2[3]; - - u64 padding64_2[5]; - u64 guest_physical_address; - - u32 vm_instruction_error; - u32 vm_exit_reason; - u32 vm_exit_intr_info; - u32 vm_exit_intr_error_code; - u32 idt_vectoring_info_field; - u32 idt_vectoring_error_code; - u32 vm_exit_instruction_len; - u32 vmx_instruction_info; - - u64 exit_qualification; - u64 exit_io_instruction_ecx; - u64 exit_io_instruction_esi; - u64 exit_io_instruction_edi; - u64 exit_io_instruction_eip; - - u64 guest_linear_address; - u64 guest_rsp; - u64 guest_rflags; - - u32 guest_interruptibility_info; - u32 cpu_based_vm_exec_control; - u32 exception_bitmap; - u32 vm_entry_controls; - u32 vm_entry_intr_info_field; - u32 vm_entry_exception_error_code; - u32 vm_entry_instruction_len; - u32 tpr_threshold; - - u64 guest_rip; - - u32 hv_clean_fields; - u32 padding32_1; - u32 hv_synthetic_controls; - struct { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 reserved:30; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u32 padding32_2; - u64 hv_vm_id; - u64 partition_assist_page; - u64 padding64_4[4]; - u64 guest_bndcfgs; - u64 guest_ia32_perf_global_ctrl; - u64 guest_ia32_s_cet; - u64 guest_ssp; - u64 guest_ia32_int_ssp_table_addr; - u64 guest_ia32_lbr_ctl; - u64 padding64_5[2]; - u64 xss_exit_bitmap; - u64 encls_exiting_bitmap; - u64 host_ia32_perf_global_ctrl; - u64 tsc_multiplier; - u64 host_ia32_s_cet; - u64 host_ssp; - u64 host_ia32_int_ssp_table_addr; - u64 padding64_6; -} __packed; - -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14) -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) - -#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF - -/* - * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by - * pairing it with architecturally impossible exit reasons. Bit 28 is set only - * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit - * is pending. I.e. it will never be set by hardware for non-SMI exits (there - * are only three), nor will it ever be set unless the VMM is an STM. - */ -#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 - -/* - * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose - * SVM enlightenments to guests. - */ -struct hv_vmcb_enlightenments { - struct __packed hv_enlightenments_control { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 enlightened_npt_tlb: 1; - u32 reserved:29; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u64 hv_vm_id; - u64 partition_assist_page; - u64 reserved; -} __packed; - -/* - * Hyper-V uses the software reserved clean bit in VMCB. - */ -#define HV_VMCB_NESTED_ENLIGHTENMENTS 31 - -/* Synthetic VM-Exit */ -#define HV_SVM_EXITCODE_ENL 0xf0000000 -#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) - -struct hv_partition_assist_pg { - u32 tlb_lock_count; -}; - -enum hv_interrupt_type { - HV_X64_INTERRUPT_TYPE_FIXED = 0x0000, - HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001, - HV_X64_INTERRUPT_TYPE_SMI = 0x0002, - HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003, - HV_X64_INTERRUPT_TYPE_NMI = 0x0004, - HV_X64_INTERRUPT_TYPE_INIT = 0x0005, - HV_X64_INTERRUPT_TYPE_SIPI = 0x0006, - HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007, - HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008, - HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009, - HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A, -}; - -union hv_msi_address_register { - u32 as_uint32; - struct { - u32 reserved1:2; - u32 destination_mode:1; - u32 redirection_hint:1; - u32 reserved2:8; - u32 destination_id:8; - u32 msi_base:12; - }; -} __packed; - -union hv_msi_data_register { - u32 as_uint32; - struct { - u32 vector:8; - u32 delivery_mode:3; - u32 reserved1:3; - u32 level_assert:1; - u32 trigger_mode:1; - u32 reserved2:16; - }; -} __packed; - -/* HvRetargetDeviceInterrupt hypercall */ -union hv_msi_entry { - u64 as_uint64; - struct { - union hv_msi_address_register address; - union hv_msi_data_register data; - } __packed; -}; - -struct hv_x64_segment_register { - u64 base; - u32 limit; - u16 selector; - union { - struct { - u16 segment_type : 4; - u16 non_system_segment : 1; - u16 descriptor_privilege_level : 2; - u16 present : 1; - u16 reserved : 4; - u16 available : 1; - u16 _long : 1; - u16 _default : 1; - u16 granularity : 1; - } __packed; - u16 attributes; - }; -} __packed; - -struct hv_x64_table_register { - u16 pad[3]; - u16 limit; - u64 base; -} __packed; - -struct hv_init_vp_context { - u64 rip; - u64 rsp; - u64 rflags; - - struct hv_x64_segment_register cs; - struct hv_x64_segment_register ds; - struct hv_x64_segment_register es; - struct hv_x64_segment_register fs; - struct hv_x64_segment_register gs; - struct hv_x64_segment_register ss; - struct hv_x64_segment_register tr; - struct hv_x64_segment_register ldtr; - - struct hv_x64_table_register idtr; - struct hv_x64_table_register gdtr; - - u64 efer; - u64 cr0; - u64 cr3; - u64 cr4; - u64 msr_cr_pat; -} __packed; - -union hv_input_vtl { - u8 as_uint8; - struct { - u8 target_vtl: 4; - u8 use_target_vtl: 1; - u8 reserved_z: 3; - }; -} __packed; - -struct hv_enable_vp_vtl { - u64 partition_id; - u32 vp_index; - union hv_input_vtl target_vtl; - u8 mbz0; - u16 mbz1; - struct hv_init_vp_context vp_context; -} __packed; - -struct hv_get_vp_from_apic_id_in { - u64 partition_id; - union hv_input_vtl target_vtl; - u8 res[7]; - u32 apic_ids[]; -} __packed; - -#include <asm-generic/hyperv-tlfs.h> - -#endif diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 14d72727d7ee..0e82ebc5d1e1 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H -#define __head __section(".head.text") +#define __head __section(".head.text") __no_sanitize_undefined struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ diff --git a/arch/x86/include/asm/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h index ce16da719596..1f9b5d225912 100644 --- a/arch/x86/include/asm/intel_punit_ipc.h +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -80,17 +80,10 @@ typedef enum { #if IS_ENABLED(CONFIG_INTEL_PUNIT_IPC) -int intel_punit_ipc_simple_command(int cmd, int para1, int para2); int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out); #else -static inline int intel_punit_ipc_simple_command(int cmd, - int para1, int para2) -{ - return -ENODEV; -} - static inline int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out) { diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index b71ad173f877..562a547c29a5 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,8 +100,8 @@ } #define ASM_CALL_ARG0 \ - "call %c[__func] \n" \ - ASM_REACHABLE + "1: call %c[__func] \n" \ + ANNOTATE_REACHABLE(1b) #define ASM_CALL_ARG1 \ "movq %[arg1], %%rdi \n" \ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index ae5482a2f0ca..8ad187462b68 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -8,14 +8,9 @@ # define PA_PGD 2 # define PA_SWAP_PAGE 3 # define PAGES_NR 4 -#else -# define PA_CONTROL_PAGE 0 -# define VA_CONTROL_PAGE 1 -# define PA_TABLE_PAGE 2 -# define PA_SWAP_PAGE 3 -# define PAGES_NR 4 #endif +# define KEXEC_CONTROL_PAGE_SIZE 4096 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048 #ifndef __ASSEMBLY__ @@ -43,7 +38,6 @@ struct kimage; /* Maximum address we can use for the control code buffer */ # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE -# define KEXEC_CONTROL_PAGE_SIZE 4096 /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_386 @@ -58,11 +52,12 @@ struct kimage; /* Maximum address we can use for the control pages */ # define KEXEC_CONTROL_MEMORY_LIMIT (MAXMEM-1) -/* Allocate one page for the pdp and the second for the code */ -# define KEXEC_CONTROL_PAGE_SIZE (4096UL + 4096UL) - /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_X86_64 + +extern unsigned long kexec_va_control_page; +extern unsigned long kexec_pa_table_page; +extern unsigned long kexec_pa_swap_page; #endif /* @@ -116,21 +111,21 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #ifdef CONFIG_X86_32 -asmlinkage unsigned long -relocate_kernel(unsigned long indirection_page, - unsigned long control_page, - unsigned long start_address, - unsigned int has_pae, - unsigned int preserve_context); +typedef asmlinkage unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); #else -unsigned long -relocate_kernel(unsigned long indirection_page, - unsigned long page_list, - unsigned long start_address, - unsigned int preserve_context, - unsigned int host_mem_enc_active); +typedef unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long pa_control_page, + unsigned long start_address, + unsigned int preserve_context, + unsigned int host_mem_enc_active); #endif - +extern relocate_kernel_fn relocate_kernel; #define ARCH_HAS_KIMAGE_ARCH #ifdef CONFIG_X86_32 @@ -145,6 +140,19 @@ struct kimage_arch { }; #else struct kimage_arch { + /* + * This is a kimage control page, as it must not overlap with either + * source or destination address ranges. + */ + pgd_t *pgd; + /* + * The virtual mapping of the control code page itself is used only + * during the transition, while the current kernel's pages are all + * in place. Thus the intermediate page table pages used to map it + * are not control pages, but instead just normal pages obtained + * with get_zeroed_page(). And have to be tracked (below) so that + * they can be freed. + */ p4d_t *p4d; pud_t *pud; pmd_t *pmd; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 5aff7222e40f..823c0434bbad 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -48,6 +48,7 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) @@ -83,7 +84,6 @@ KVM_X86_OP(enable_nmi_window) KVM_X86_OP(enable_irq_window) KVM_X86_OP_OPTIONAL(update_cr8_intercept) KVM_X86_OP(refresh_apicv_exec_ctrl) -KVM_X86_OP_OPTIONAL(hwapic_irr_update) KVM_X86_OP_OPTIONAL(hwapic_isr_update) KVM_X86_OP_OPTIONAL(load_eoi_exitmap) KVM_X86_OP_OPTIONAL(set_virtual_apic_mode) @@ -94,12 +94,17 @@ KVM_X86_OP_OPTIONAL_RET0(set_tss_addr) KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr) KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) KVM_X86_OP(load_mmu_pgd) +KVM_X86_OP_OPTIONAL(link_external_spt) +KVM_X86_OP_OPTIONAL(set_external_spte) +KVM_X86_OP_OPTIONAL(free_external_spt) +KVM_X86_OP_OPTIONAL(remove_external_spte) KVM_X86_OP(has_wbinvd_exit) KVM_X86_OP(get_l2_tsc_offset) KVM_X86_OP(get_l2_tsc_multiplier) KVM_X86_OP(write_tsc_offset) KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) +KVM_X86_OP(get_entry_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e159e44a6a1b..0b7af5902ff7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -24,9 +24,9 @@ #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> -#include <linux/hyperv.h> #include <linux/kfifo.h> #include <linux/sched/vhost_task.h> +#include <linux/call_once.h> #include <asm/apic.h> #include <asm/pvclock-abi.h> @@ -36,8 +36,8 @@ #include <asm/asm.h> #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> -#include <asm/hyperv-tlfs.h> #include <asm/reboot.h> +#include <hyperv/hvhdk.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -313,10 +313,11 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 19 bits in the mask below, not all combinations + * But, even though there are 20 bits in the mask below, not all combinations * of modes and flags are possible: * - * - invalid shadow pages are not accounted, so the bits are effectively 18 + * - invalid shadow pages are not accounted, mirror pages are not shadowed, + * so the bits are effectively 18. * * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); * execonly and ad_disabled are only used for nested EPT which has @@ -349,7 +350,8 @@ union kvm_mmu_page_role { unsigned ad_disabled:1; unsigned guest_mode:1; unsigned passthrough:1; - unsigned :5; + unsigned is_mirror:1; + unsigned :4; /* * This is left at the top of the word so that @@ -457,6 +459,7 @@ struct kvm_mmu { int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); struct kvm_mmu_root_info root; + hpa_t mirror_root_hpa; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; @@ -739,6 +742,23 @@ struct kvm_queued_exception { bool has_payload; }; +/* + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. + */ +enum kvm_only_cpuid_leafs { + CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, + CPUID_8000_0007_EDX, + CPUID_8000_0022_EAX, + CPUID_7_2_EDX, + CPUID_24_0_EBX, + NR_KVM_CPU_CAPS, + + NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -813,6 +833,11 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_shadow_page_cache; struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * This cache is to allocate external page table. E.g. private EPT used + * by the TDX module. + */ + struct kvm_mmu_memory_cache mmu_external_spt_cache; /* * QEMU userspace and the guest each have their own FPU state. @@ -854,27 +879,23 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - struct kvm_hypervisor_cpuid kvm_cpuid; bool is_amd_compatible; /* - * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly - * when "struct kvm_vcpu_arch" is no longer defined in an - * arch/x86/include/asm header. The max is mostly arbitrary, i.e. - * can be increased as necessary. - */ -#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG - - /* - * Track whether or not the guest is allowed to use features that are - * governed by KVM, where "governed" means KVM needs to manage state - * and/or explicitly enable the feature in hardware. Typically, but - * not always, governed features can be used by the guest if and only - * if both KVM and userspace want to expose the feature to the guest. + * cpu_caps holds the effective guest capabilities, i.e. the features + * the vCPU is allowed to use. Typically, but not always, features can + * be used by the guest if and only if both KVM and userspace want to + * expose the feature to the guest. + * + * A common exception is for virtualization holes, i.e. when KVM can't + * prevent the guest from using a feature, in which case the vCPU "has" + * the feature regardless of what KVM or userspace desires. + * + * Note, features that don't require KVM involvement in any way are + * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the + * guest CPUID provided by userspace. */ - struct { - DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES); - } governed_features; + u32 cpu_caps[NR_KVM_CPU_CAPS]; u64 reserved_gpa_bits; int maxphyaddr; @@ -1445,6 +1466,7 @@ struct kvm_arch { struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct vhost_task *nx_huge_page_recovery_thread; u64 nx_huge_page_last; + struct once nx_once; #ifdef CONFIG_X86_64 /* The number of TDP MMU pages across all roots. */ @@ -1536,6 +1558,8 @@ struct kvm_arch { */ #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) struct kvm_mmu_memory_cache split_desc_cache; + + gfn_t gfn_direct_bits; }; struct kvm_vm_stat { @@ -1672,6 +1696,7 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); + void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); @@ -1734,8 +1759,7 @@ struct kvm_x86_ops { const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); - void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); - void (*hwapic_isr_update)(int isr); + void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); @@ -1749,6 +1773,21 @@ struct kvm_x86_ops { void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); + /* Update external mapping with page table link. */ + int (*link_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + /* Update the external page table from spte getting set. */ + int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + + /* Update external page tables for page table about to be freed. */ + int (*free_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + + /* Update external page table from spte getting removed, and flush TLB. */ + int (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); @@ -1757,12 +1796,15 @@ struct kvm_x86_ops { void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); /* - * Retrieve somewhat arbitrary exit information. Intended to + * Retrieve somewhat arbitrary exit/entry information. Intended to * be used only from within tracepoints or error paths. */ void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, - u32 *exit_int_info, u32 *exit_int_info_err_code); + u32 *intr_info, u32 *error_code); + + void (*get_entry_info)(struct kvm_vcpu *vcpu, + u32 *intr_info, u32 *error_code); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, @@ -2019,8 +2061,8 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); * VMware backdoor emulation handles select instructions * and reinjects the #GP for all other cases. * - * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which - * case the CR2/GPA value pass on the stack is valid. + * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case + * the CR2/GPA value pass on the stack is valid. * * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping @@ -2055,6 +2097,11 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) +static inline bool kvm_can_emulate_event_vectoring(int emul_type) +{ + return !(emul_type & EMULTYPE_PF); +} + int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); @@ -2062,6 +2109,8 @@ void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa); + void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data); @@ -2181,12 +2230,6 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } -unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, - unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, - int op_64_bit, int cpl); -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4543cf2eb5e8..eb2db07ef39c 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -276,7 +276,7 @@ static inline void cmci_rediscover(void) {} static inline void cmci_recheck(void) {} #endif -int mce_available(struct cpuinfo_x86 *c); +bool mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); bool mce_usable_address(struct mce *m); @@ -296,7 +296,7 @@ enum mcp_flags { void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); -int mce_notify_irq(void); +bool mce_notify_irq(void); DECLARE_PER_CPU(struct mce, injectm); @@ -386,8 +386,6 @@ static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } #endif -static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } - unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index ce4677b8b735..3b496cdcb74b 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,6 +37,8 @@ typedef struct { */ atomic64_t tlb_gen; + unsigned long next_trim_cpumask; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct rw_semaphore ldt_usr_sem; struct ldt_struct *ldt; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 2886cb668d7f..795fdd53bd0a 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -151,6 +151,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); + mm->context.next_trim_cpumask = jiffies + HZ; #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5f0bc6a6d025..f91ab1e75f9f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -6,10 +6,9 @@ #include <linux/nmi.h> #include <linux/msi.h> #include <linux/io.h> -#include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> #include <asm/paravirt.h> -#include <asm/mshyperv.h> +#include <hyperv/hvhdk.h> /* * Hyper-V always provides a single IO-APIC at this MMIO address. diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3ae84c3b8e6d..72765b2fe0d8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -395,7 +395,8 @@ #define MSR_IA32_PASID_VALID BIT_ULL(31) /* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) @@ -608,6 +609,7 @@ #define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 @@ -644,6 +646,7 @@ #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 @@ -682,11 +685,12 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_RESV_BIT 18 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) - -#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f - #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_AMD64_RMP_CFG 0xc0010136 +#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0 +#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT) +#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8) #define MSR_SVSM_CAA 0xc001f000 diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 4218248083d9..c69e269937c5 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -58,8 +58,8 @@ struct mtrr_state_type { */ # ifdef CONFIG_MTRR void mtrr_bp_init(void); -void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, - mtrr_type def_type); +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type); extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); @@ -75,9 +75,9 @@ void mtrr_disable(void); void mtrr_enable(void); void mtrr_generic_set_state(void); # else -static inline void mtrr_overwrite_state(struct mtrr_var_range *var, - unsigned int num_var, - mtrr_type def_type) +static inline void guest_force_mtrr_state(struct mtrr_var_range *var, + unsigned int num_var, + mtrr_type def_type) { } diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 920426d691ce..ce857ef54cf1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -15,7 +15,6 @@ #define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK) #define MWAIT_C1_SUBSTATE_MASK 0xf0 -#define CPUID_MWAIT_LEAF 5 #define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 #define CPUID5_ECX_INTERRUPT_BREAK 0x2 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 96b410b1d4e8..7e8bf78c03d5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -180,18 +180,6 @@ #ifdef __ASSEMBLY__ /* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -.macro ANNOTATE_RETPOLINE_SAFE -.Lhere_\@: - .pushsection .discard.retpoline_safe - .long .Lhere_\@ - .popsection -.endm - -/* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ @@ -350,12 +338,6 @@ #else /* __ASSEMBLY__ */ -#define ANNOTATE_RETPOLINE_SAFE \ - "999:\n\t" \ - ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d4eb9e1d61b8..041aff51eb50 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -180,13 +180,6 @@ static inline void halt(void) PVOP_VCALL0(irq.halt); } -extern noinstr void pv_native_wbinvd(void); - -static __always_inline void wbinvd(void) -{ - PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN); -} - static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8d4fbe1be489..fea56b04f436 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -86,8 +86,6 @@ struct pv_cpu_ops { void (*update_io_bitmap)(void); #endif - void (*wbinvd)(void); - /* cpuid emulation, mostly so that caps bits can be disabled */ void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index d95f902acc52..0ba8d20f2d1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -41,6 +41,7 @@ #define INTEL_FIXED_0_USER (1ULL << 1) #define INTEL_FIXED_0_ANYTHREAD (1ULL << 2) #define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3) +#define INTEL_FIXED_3_METRICS_CLEAR (1ULL << 2) #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) @@ -187,11 +188,33 @@ union cpuid10_edx { * detection/enumeration details: */ #define ARCH_PERFMON_EXT_LEAF 0x00000023 -#define ARCH_PERFMON_EXT_UMASK2 0x1 -#define ARCH_PERFMON_EXT_EQ 0x2 -#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 #define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +union cpuid35_eax { + struct { + unsigned int leaf0:1; + /* Counters Sub-Leaf */ + unsigned int cntr_subleaf:1; + /* Auto Counter Reload Sub-Leaf */ + unsigned int acr_subleaf:1; + /* Events Sub-Leaf */ + unsigned int events_subleaf:1; + unsigned int reserved:28; + } split; + unsigned int full; +}; + +union cpuid35_ebx { + struct { + /* UnitMask2 Supported */ + unsigned int umask2:1; + /* EQ-bit Supported */ + unsigned int eq:1; + unsigned int reserved:30; + } split; + unsigned int full; +}; + /* * Intel Architectural LBR CPUID detection/enumeration details: */ @@ -372,6 +395,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code) #define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_MEM_BOUND #define INTEL_TD_METRIC_NUM 8 +#define INTEL_TD_CFG_METRIC_CLEAR_BIT 0 +#define INTEL_TD_CFG_METRIC_CLEAR BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT) + static inline bool is_metric_idx(int idx) { return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM; @@ -422,7 +448,9 @@ static inline bool is_topdown_idx(int idx) */ struct pebs_basic { - u64 format_size; + u64 format_group:32, + retire_latency:16, + format_size:16; u64 ip; u64 applicable_counters; u64 tsc; @@ -431,7 +459,17 @@ struct pebs_basic { struct pebs_meminfo { u64 address; u64 aux; - u64 latency; + union { + /* pre Alder Lake */ + u64 mem_latency; + /* Alder Lake and later */ + struct { + u64 instr_latency:16; + u64 pad2:16; + u64 cache_latency:16; + u64 pad3:16; + }; + }; u64 tsx_tuning; }; diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index dcd836b59beb..dd4841231bb9 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -147,24 +147,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4 set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - gfp_t gfp = GFP_KERNEL_ACCOUNT; - - if (mm == &init_mm) - gfp &= ~__GFP_ACCOUNT; - return (p4d_t *)get_zeroed_page(gfp); -} - -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (!pgtable_l5_enabled()) - return; - - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..c0cd10182e90 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -98,6 +98,7 @@ struct cpuinfo_topology { // Logical ID mappings u32 logical_pkg_id; u32 logical_die_id; + u32 logical_core_id; // AMD Node ID and Nodes per Package info u32 amd_node_id; @@ -230,6 +231,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 3fa87e5e11ab..30e8ee7006f9 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -5,6 +5,7 @@ #include <asm-generic/sections.h> #include <asm/extable.h> +extern char __relocate_kernel_start[], __relocate_kernel_end[]; extern char __brk_base[], __brk_limit[]; extern char __end_rodata_aligned[]; diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 0667b2a88614..85f4fde3515c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -49,7 +49,7 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); -extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); +extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp); extern void startup_64_setup_gdt_idt(void); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 50f5666938c0..dcbccdb280f9 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -206,6 +206,8 @@ struct snp_psc_desc { #define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ #define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ #define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ +#define GHCB_TERM_SECURE_TSC 10 /* Secure TSC initialization failed */ +#define GHCB_TERM_SVSM_CA_REMAP_FAIL 11 /* SVSM is present but CA could not be remapped */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 91f08af31078..1581246491b5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -14,6 +14,7 @@ #include <asm/insn.h> #include <asm/sev-common.h> #include <asm/coco.h> +#include <asm/set_memory.h> #define GHCB_PROTOCOL_MIN 1ULL #define GHCB_PROTOCOL_MAX 2ULL @@ -124,6 +125,9 @@ struct snp_req_data { #define AAD_LEN 48 #define MSG_HDR_VER 1 +#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) +#define SNP_REQ_RETRY_DELAY (2*HZ) + /* See SNP spec SNP_GUEST_REQUEST section for the structure */ enum msg_type { SNP_MSG_TYPE_INVALID = 0, @@ -142,6 +146,9 @@ enum msg_type { SNP_MSG_VMRK_REQ, SNP_MSG_VMRK_RSP, + SNP_MSG_TSC_INFO_REQ = 17, + SNP_MSG_TSC_INFO_RSP, + SNP_MSG_TYPE_MAX }; @@ -170,9 +177,20 @@ struct snp_guest_msg { u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; } __packed; -struct sev_guest_platform_data { - u64 secrets_gpa; -}; +#define SNP_TSC_INFO_REQ_SZ 128 + +struct snp_tsc_info_req { + u8 rsvd[SNP_TSC_INFO_REQ_SZ]; +} __packed; + +struct snp_tsc_info_resp { + u32 status; + u32 rsvd1; + u64 tsc_scale; + u64 tsc_offset; + u32 tsc_factor; + u8 rsvd2[100]; +} __packed; struct snp_guest_req { void *req_buf; @@ -253,6 +271,7 @@ struct snp_msg_desc { u32 *os_area_msg_seqno; u8 *vmpck; + int vmpck_id; }; /* @@ -445,8 +464,6 @@ void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); void snp_dmi_setup(void); -int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio); int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -458,6 +475,15 @@ void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot); void snp_kexec_finish(void); void snp_kexec_begin(void); +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id); +struct snp_msg_desc *snp_msg_alloc(void); +void snp_msg_free(struct snp_msg_desc *mdesc); +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio); + +void __init snp_secure_tsc_prepare(void); +void __init snp_secure_tsc_init(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -480,11 +506,6 @@ static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } static inline void snp_dmi_setup(void) { } -static inline int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio) -{ - return -ENOTTY; -} static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) { return -ENOTTY; @@ -498,11 +519,19 @@ static inline int prepare_pte_enc(struct pte_enc_desc *d) { return 0; } static inline void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot) { } static inline void snp_kexec_finish(void) { } static inline void snp_kexec_begin(void) { } +static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; } +static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; } +static inline void snp_msg_free(struct snp_msg_desc *mdesc) { } +static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) { return -ENODEV; } +static inline void __init snp_secure_tsc_prepare(void) { } +static inline void __init snp_secure_tsc_init(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); void snp_dump_hva_rmpentry(unsigned long address); int psmash(u64 pfn); @@ -513,6 +542,7 @@ void kdump_sev_callback(void); void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } static inline void snp_dump_hva_rmpentry(unsigned long address) {} static inline int psmash(u64 pfn) { return -ENODEV; } diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 89f7fcade8ae..fcbbef484a78 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -19,6 +19,32 @@ #define TDG_VM_RD 7 #define TDG_VM_WR 8 +/* TDX attributes */ +#define TDX_ATTR_DEBUG_BIT 0 +#define TDX_ATTR_DEBUG BIT_ULL(TDX_ATTR_DEBUG_BIT) +#define TDX_ATTR_HGS_PLUS_PROF_BIT 4 +#define TDX_ATTR_HGS_PLUS_PROF BIT_ULL(TDX_ATTR_HGS_PLUS_PROF_BIT) +#define TDX_ATTR_PERF_PROF_BIT 5 +#define TDX_ATTR_PERF_PROF BIT_ULL(TDX_ATTR_PERF_PROF_BIT) +#define TDX_ATTR_PMT_PROF_BIT 6 +#define TDX_ATTR_PMT_PROF BIT_ULL(TDX_ATTR_PMT_PROF_BIT) +#define TDX_ATTR_ICSSD_BIT 16 +#define TDX_ATTR_ICSSD BIT_ULL(TDX_ATTR_ICSSD_BIT) +#define TDX_ATTR_LASS_BIT 27 +#define TDX_ATTR_LASS BIT_ULL(TDX_ATTR_LASS_BIT) +#define TDX_ATTR_SEPT_VE_DISABLE_BIT 28 +#define TDX_ATTR_SEPT_VE_DISABLE BIT_ULL(TDX_ATTR_SEPT_VE_DISABLE_BIT) +#define TDX_ATTR_MIGRTABLE_BIT 29 +#define TDX_ATTR_MIGRTABLE BIT_ULL(TDX_ATTR_MIGRTABLE_BIT) +#define TDX_ATTR_PKS_BIT 30 +#define TDX_ATTR_PKS BIT_ULL(TDX_ATTR_PKS_BIT) +#define TDX_ATTR_KL_BIT 31 +#define TDX_ATTR_KL BIT_ULL(TDX_ATTR_KL_BIT) +#define TDX_ATTR_TPA_BIT 62 +#define TDX_ATTR_TPA BIT_ULL(TDX_ATTR_TPA_BIT) +#define TDX_ATTR_PERFMON_BIT 63 +#define TDX_ATTR_PERFMON BIT_ULL(TDX_ATTR_PERFMON_BIT) + /* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */ #define TDCS_CONFIG_FLAGS 0x1110000300000016 #define TDCS_TD_CTLS 0x1110000300000017 @@ -29,8 +55,16 @@ #define TDCS_CONFIG_FLEXIBLE_PENDING_VE BIT_ULL(1) /* TDCS_TD_CTLS bits */ -#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(0) -#define TD_CTLS_ENUM_TOPOLOGY BIT_ULL(1) +#define TD_CTLS_PENDING_VE_DISABLE_BIT 0 +#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(TD_CTLS_PENDING_VE_DISABLE_BIT) +#define TD_CTLS_ENUM_TOPOLOGY_BIT 1 +#define TD_CTLS_ENUM_TOPOLOGY BIT_ULL(TD_CTLS_ENUM_TOPOLOGY_BIT) +#define TD_CTLS_VIRT_CPUID2_BIT 2 +#define TD_CTLS_VIRT_CPUID2 BIT_ULL(TD_CTLS_VIRT_CPUID2_BIT) +#define TD_CTLS_REDUCE_VE_BIT 3 +#define TD_CTLS_REDUCE_VE BIT_ULL(TD_CTLS_REDUCE_VE_BIT) +#define TD_CTLS_LOCK_BIT 63 +#define TD_CTLS_LOCK BIT_ULL(TD_CTLS_LOCK_BIT) /* TDX hypercall Leaf IDs */ #define TDVMCALL_MAP_GPA 0x10001 diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index bab490379c65..2de1e5a75c57 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -13,30 +13,26 @@ #include <asm/cpufeatures.h> #include <asm/alternative.h> -/* "Raw" instruction opcodes */ -#define __ASM_CLAC ".byte 0x0f,0x01,0xca" -#define __ASM_STAC ".byte 0x0f,0x01,0xcb" - #ifdef __ASSEMBLY__ #define ASM_CLAC \ - ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP + ALTERNATIVE "", "clac", X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP + ALTERNATIVE "", "stac", X86_FEATURE_SMAP #else /* __ASSEMBLY__ */ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_CLAC, X86_FEATURE_SMAP); + alternative("", "clac", X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_STAC, X86_FEATURE_SMAP); + alternative("", "stac", X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) @@ -44,7 +40,7 @@ static __always_inline unsigned long smap_save(void) unsigned long flags; asm volatile ("# smap_save\n\t" - ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t", + ALTERNATIVE("", "pushf; pop %0; " "clac" "\n\t", X86_FEATURE_SMAP) : "=rm" (flags) : : "memory", "cc"); @@ -61,9 +57,9 @@ static __always_inline void smap_restore(unsigned long flags) /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "clac", X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "stac", X86_FEATURE_SMAP) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index aec6e2d3aa1d..03e7c2d49559 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru) } #endif -static __always_inline void native_wbinvd(void) +static __always_inline void wbinvd(void) { asm volatile("wbinvd": : :"memory"); } @@ -167,12 +167,6 @@ static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } - -static __always_inline void wbinvd(void) -{ - native_wbinvd(); -} - #endif /* CONFIG_PARAVIRT_XXL */ static __always_inline void clflush(volatile void *__p) @@ -217,7 +211,7 @@ fail: #define nop() asm volatile ("nop") -static inline void serialize(void) +static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 2b59b9951c90..e2fac21471f5 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -5,7 +5,7 @@ #include <uapi/asm/svm.h> #include <uapi/asm/kvm.h> -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> /* * 32-bit intercept words in the VMCB Control Area, starting @@ -417,7 +417,9 @@ struct sev_es_save_area { u8 reserved_0x298[80]; u32 pkru; u32 tsc_aux; - u8 reserved_0x2f0[24]; + u64 tsc_scale; + u64 tsc_offset; + u8 reserved_0x300[8]; u64 rcx; u64 rdx; u64 rbx; @@ -564,7 +566,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); - BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x300); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index eba178996d84..b4b16dafd55e 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -66,6 +66,9 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport); u64 tdx_hcall_get_quote(u8 *buf, size_t size); +void __init tdx_dump_attributes(u64 td_attr); +void __init tdx_dump_td_ctls(u64 td_ctls); + #else static inline void tdx_early_init(void) { }; diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 4d3c9d00d6b6..77f52bc1578a 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -20,22 +20,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } -/* - * While x86 architecture in general requires an IPI to perform TLB - * shootdown, enablement code for several hypervisors overrides - * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing - * a hypercall. To keep software pagetable walkers safe in this case we - * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment - * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h - * for more details. - */ -static inline void __tlb_remove_table(void *table) -{ - free_page_and_swap_cache(table); -} - static inline void invlpg(unsigned long addr) { asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); } + #endif /* _ASM_X86_TLB_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 69e79fff41b8..02fc2aa06e9e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -222,6 +222,7 @@ struct flush_tlb_info { unsigned int initiating_cpu; u8 stride_shift; u8 freed_tables; + u8 trim_cpumask; }; void flush_tlb_local(void); diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index fd41103ad342..ec134b719144 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -143,6 +143,7 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id) #define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id) +#define topology_logical_core_id(cpu) (cpu_data(cpu).topo.logical_core_id) #define topology_die_id(cpu) (cpu_data(cpu).topo.die_id) #define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) #define topology_ppin(cpu) (cpu_data(cpu).ppin) @@ -250,7 +251,7 @@ extern bool x86_topology_update; #include <asm/percpu.h> DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority); -extern unsigned int __read_mostly sysctl_sched_itmt_enabled; +extern bool __read_mostly sysctl_sched_itmt_enabled; /* Interface to set priority of a cpu */ void sched_set_itmt_core_prio(int prio, int core_cpu); @@ -263,7 +264,7 @@ void sched_clear_itmt_support(void); #else /* CONFIG_SCHED_MC_PRIO */ -#define sysctl_sched_itmt_enabled 0 +#define sysctl_sched_itmt_enabled false static inline void sched_set_itmt_core_prio(int prio, int core_cpu) { } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index b0a887209400..c52f0133425b 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -63,13 +63,13 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, */ static inline void __user *mask_user_address(const void __user *ptr) { - unsigned long mask; + void __user *ret; asm("cmp %1,%0\n\t" - "sbb %0,%0" - :"=r" (mask) - :"r" (ptr), - "0" (runtime_const_ptr(USER_PTR_MAX))); - return (__force void __user *)(mask | (__force unsigned long)ptr); + "cmova %1,%0" + :"=r" (ret) + :"r" (runtime_const_ptr(USER_PTR_MAX)), + "0" (ptr)); + return ret; } #define masked_user_access_begin(x) ({ \ __auto_type __masked_ptr = (x); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h index 4a7cace06204..92d8f256d096 100644 --- a/arch/x86/include/uapi/asm/amd_hsmp.h +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -50,6 +50,12 @@ enum hsmp_message_ids { HSMP_GET_METRIC_TABLE_VER, /* 23h Get metrics table version */ HSMP_GET_METRIC_TABLE, /* 24h Get metrics table */ HSMP_GET_METRIC_TABLE_DRAM_ADDR,/* 25h Get metrics table dram address */ + HSMP_SET_XGMI_PSTATE_RANGE, /* 26h Set xGMI P-state range */ + HSMP_CPU_RAIL_ISO_FREQ_POLICY, /* 27h Get/Set Cpu Iso frequency policy */ + HSMP_DFC_ENABLE_CTRL, /* 28h Enable/Disable DF C-state */ + HSMP_GET_RAPL_UNITS = 0x30, /* 30h Get scaling factor for energy */ + HSMP_GET_RAPL_CORE_COUNTER, /* 31h Get core energy counter value */ + HSMP_GET_RAPL_PACKAGE_COUNTER, /* 32h Get package energy counter value */ HSMP_MSG_ID_MAX, }; @@ -65,6 +71,7 @@ enum hsmp_msg_type { HSMP_RSVD = -1, HSMP_SET = 0, HSMP_GET = 1, + HSMP_SET_GET = 2, }; enum hsmp_proto_versions { @@ -72,7 +79,8 @@ enum hsmp_proto_versions { HSMP_PROTO_VER3, HSMP_PROTO_VER4, HSMP_PROTO_VER5, - HSMP_PROTO_VER6 + HSMP_PROTO_VER6, + HSMP_PROTO_VER7 }; struct hsmp_msg_desc { @@ -300,7 +308,7 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] * HSMP_SET_POWER_MODE, num_args = 1, response_sz = 0 * input: args[0] = power efficiency mode[2:0] */ - {1, 0, HSMP_SET}, + {1, 1, HSMP_SET_GET}, /* * HSMP_SET_PSTATE_MAX_MIN, num_args = 1, response_sz = 0 @@ -325,6 +333,58 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] * output: args[1] = upper 32 bits of the address */ {0, 2, HSMP_GET}, + + /* + * HSMP_SET_XGMI_PSTATE_RANGE, num_args = 1, response_sz = 0 + * input: args[0] = min xGMI p-state[15:8] + max xGMI p-state[7:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_CPU_RAIL_ISO_FREQ_POLICY, num_args = 1, response_sz = 1 + * input: args[0] = set/get policy[31] + + * disable/enable independent control[0] + * output: args[0] = current policy[0] + */ + {1, 1, HSMP_SET_GET}, + + /* + * HSMP_DFC_ENABLE_CTRL, num_args = 1, response_sz = 1 + * input: args[0] = set/get policy[31] + enable/disable DFC[0] + * output: args[0] = current policy[0] + */ + {1, 1, HSMP_SET_GET}, + + /* RESERVED(0x29-0x2f) */ + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + {0, 0, HSMP_RSVD}, + + /* + * HSMP_GET_RAPL_UNITS, response_sz = 1 + * output: args[0] = tu value[19:16] + esu value[12:8] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_RAPL_CORE_COUNTER, num_args = 1, response_sz = 1 + * input: args[0] = apic id[15:0] + * output: args[0] = lower 32 bits of energy + * output: args[1] = upper 32 bits of energy + */ + {1, 2, HSMP_GET}, + + /* + * HSMP_GET_RAPL_PACKAGE_COUNTER, num_args = 0, response_sz = 1 + * output: args[0] = lower 32 bits of energy + * output: args[1] = upper 32 bits of energy + */ + {0, 2, HSMP_GET}, + }; /* Metrics table (supported only with proto version 6) */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 88585c1de416..9e75da97bce0 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -925,5 +925,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 #define KVM_X86_SNP_VM 4 +#define KVM_X86_TDX_VM 5 #endif /* _ASM_X86_KVM_H */ |