diff options
Diffstat (limited to 'arch/x86/include/asm')
38 files changed, 701 insertions, 84 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 2b892e2313a9..5d6a53fd7521 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += clkdev.h -generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 0c5fbc68e82d..eff8e36aaf72 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v) static inline void native_apic_msr_eoi_write(u32 reg, u32 v) { - wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); + __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); } static inline u32 native_apic_msr_read(u32 reg) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index eafee3161d1c..4e7772387c6e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -100,7 +100,7 @@ #define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ #define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ @@ -186,7 +186,7 @@ * * Reuse free bits when adding new feature flags! */ - +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ @@ -288,6 +288,7 @@ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ @@ -320,5 +321,4 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ - #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 12080d87da3b..cb8f9149f6c8 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -177,16 +177,8 @@ static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) struct desc_struct *d = get_cpu_gdt_table(cpu); tss_desc tss; - /* - * sizeof(unsigned long) coming from an extra "long" at the end - * of the iobitmap. See tss_struct definition in processor.h - * - * -1? seg base+limit should be pointing to the address of the - * last valid byte - */ set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, - IO_BITMAP_OFFSET + IO_BITMAP_BYTES + - sizeof(unsigned long) - 1); + __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } @@ -213,6 +205,54 @@ static inline void native_load_tr_desc(void) asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +static inline void force_reload_TR(void) +{ + struct desc_struct *d = get_cpu_gdt_table(smp_processor_id()); + tss_desc tss; + + memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); + + /* + * LTR requires an available TSS, and the TSS is currently + * busy. Make it be available so that LTR will work. + */ + tss.type = DESC_TSS; + write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); + + load_TR_desc(); +} + +DECLARE_PER_CPU(bool, need_tr_refresh); + +static inline void refresh_TR(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(this_cpu_read(need_tr_refresh))) { + force_reload_TR(); + this_cpu_write(need_tr_refresh, false); + } +} + +/* + * If you do something evil that corrupts the cached TSS limit (I'm looking + * at you, VMX exits), call this function. + * + * The optimization here is that the TSS limit only matters for Linux if the + * IO bitmap is in use. If the TSS limit gets forced to its minimum value, + * everything works except that IO bitmap will be ignored and all CPL 3 IO + * instructions will #GP, which is exactly what we want for normal tasks. + */ +static inline void invalidate_tss_limit(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(need_tr_refresh, true); +} + static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index ced283ac79df..af95c47d5c9e 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) } #define div_u64_rem div_u64_rem +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#define mul_u32_u32 mul_u32_u32 + #else # include <asm-generic/div64.h> #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec23d8e1297c..67313f3a9874 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype); extern void update_e820(void); extern void e820_setup_gap(void); -extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr); struct setup_data; extern void parse_e820_ext(u64 phys_addr, u32 data_len); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index e99675b9c861..2f77bcefe6b4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( struct efi_config { u64 image_handle; u64 table; + u64 runtime_services; u64 boot_services; u64 text_output; efi_status_t (*call)(unsigned long, ...); @@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void) #define __efi_call_early(f, ...) \ __efi_early()->call((unsigned long)f, __VA_ARGS__); +#define efi_call_runtime(f, ...) \ + __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ + __efi_early()->runtime_services), __VA_ARGS__) + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index e7f155c3045e..9d49c18b5ea9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -258,6 +258,15 @@ extern int force_personality32; #define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) +extern u32 elf_hwcap2; + +/* + * HWCAP2 supplies mask with kernel enabled CPU features, so that + * the application can discover that it can safely use them. + * The bits are defined in uapi/asm/hwcap2.h. + */ +#define ELF_HWCAP2 (elf_hwcap2) + /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index d4a684997497..255645f60ca2 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif + +static inline void fpstate_init_xstate(struct xregs_state *xsave) +{ + /* + * XRSTORS requires these bits set in xcomp_bv, or it will + * trigger #GP: + */ + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask; +} + static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 34a46dc076d3..8167fdb67ae8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -57,7 +57,7 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 49da9f497b90..fe04491130ae 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -27,7 +27,6 @@ extern void intel_mid_pwr_power_off(void); extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); extern int get_gpio_by_name(const char *name); -extern void intel_scu_device_register(struct platform_device *pdev); extern int __init sfi_parse_mrtc(struct sfi_table_header *table); extern int __init sfi_parse_mtmr(struct sfi_table_header *table); extern int sfi_mrtc_num; @@ -42,10 +41,8 @@ struct devs_id { char name[SFI_NAME_LEN + 1]; u8 type; u8 delay; + u8 msic; void *(*get_platform_data)(void *info); - /* Custom handler for devices */ - void (*device_handler)(struct sfi_device_table_entry *pentry, - struct devs_id *dev); }; #define sfi_device(i) \ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index d34bd370074b..7afb0e2f07f4 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -164,6 +164,17 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) #define virt_to_bus virt_to_phys #define bus_to_virt phys_to_virt +/* + * The default ioremap() behavior is non-cached; if you need something + * else, you probably want one of the following. + */ +extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); +#define ioremap_uc ioremap_uc + +extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); + /** * ioremap - map bus memory into CPU space * @offset: bus address of the memory @@ -178,17 +189,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * If the area you are trying to map is a PCI BAR you should have a * look at pci_iomap(). */ -extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); -extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); -#define ioremap_uc ioremap_uc - -extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); -extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, - unsigned long prot_val); - -/* - * The default ioremap() behavior is non-cached: - */ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) { return ioremap_nocache(offset, size); @@ -207,18 +207,42 @@ extern void set_iounmap_nonlazy(void); */ #define xlate_dev_kmem_ptr(p) p +/** + * memset_io Set a range of I/O memory to a constant value + * @addr: The beginning of the I/O-memory range to set + * @val: The value to set the memory to + * @count: The number of bytes to set + * + * Set a range of I/O memory to a given value. + */ static inline void memset_io(volatile void __iomem *addr, unsigned char val, size_t count) { memset((void __force *)addr, val, count); } +/** + * memcpy_fromio Copy a block of data from I/O memory + * @dst: The (RAM) destination for the copy + * @src: The (I/O memory) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data from I/O memory. + */ static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) { memcpy(dst, (const void __force *)src, count); } +/** + * memcpy_toio Copy a block of data into I/O memory + * @dst: The (I/O memory) destination for the copy + * @src: The (RAM) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data to I/O memory. + */ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) { diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index e9cd7befcb76..3e8c287090e4 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -441,5 +441,6 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq); void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt); void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt); +bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a7066dc1a7e9..74ef58c8ff53 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -55,7 +55,6 @@ #define KVM_REQ_TRIPLE_FAULT 10 #define KVM_REQ_MMU_SYNC 11 #define KVM_REQ_CLOCK_UPDATE 12 -#define KVM_REQ_DEACTIVATE_FPU 13 #define KVM_REQ_EVENT 14 #define KVM_REQ_APF_HALT 15 #define KVM_REQ_STEAL_UPDATE 16 @@ -115,7 +114,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 -#define KVM_MMU_HASH_SHIFT 10 +#define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 @@ -208,6 +207,13 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting + * with the SVE bit in EPT PTEs. + */ +#define SPTE_SPECIAL_MASK (1ULL << 62) + /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -668,6 +674,9 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; + + /* GPA available (AMD only) */ + bool gpa_available; }; struct kvm_lpage_info { @@ -716,6 +725,12 @@ struct kvm_hv { HV_REFERENCE_TSC_PAGE tsc_ref; }; +enum kvm_irqchip_mode { + KVM_IRQCHIP_NONE, + KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ + KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -788,7 +803,7 @@ struct kvm_arch { u64 disabled_quirks; - bool irqchip_split; + enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; bool disabled_lapic_found; @@ -815,6 +830,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong max_mmu_page_hash_collisions; }; struct kvm_vcpu_stat { @@ -844,6 +860,7 @@ struct kvm_vcpu_stat { u64 hypercalls; u64 irq_injections; u64 nmi_injections; + u64 req_event; }; struct x86_instruction_info; @@ -918,8 +935,6 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); u32 (*get_pkru)(struct kvm_vcpu *vcpu); - void (*fpu_activate)(struct kvm_vcpu *vcpu); - void (*fpu_deactivate)(struct kvm_vcpu *vcpu); void (*tlb_flush)(struct kvm_vcpu *vcpu); @@ -951,7 +966,7 @@ struct kvm_x86_ops { void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); - void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); + int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); @@ -1050,7 +1065,8 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask); + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, + u64 acc_track_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h new file mode 100644 index 000000000000..f260bef63591 --- /dev/null +++ b/arch/x86/include/asm/kvmclock.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_KVM_CLOCK_H +#define _ASM_X86_KVM_CLOCK_H + +extern struct clocksource kvm_clock; + +#endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 5132f2a6c0a2..e63873683d4a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -97,10 +97,6 @@ #define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ -/* Software defined banks */ -#define MCE_EXTENDED_BANK 128 -#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) - #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" @@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; + +enum mce_notifier_prios { + MCE_PRIO_SRAO = INT_MAX, + MCE_PRIO_EXTLOG = INT_MAX - 1, + MCE_PRIO_NFIT = INT_MAX - 2, + MCE_PRIO_EDAC = INT_MAX - 3, + MCE_PRIO_LOWEST = 0, +}; + extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void); void intel_init_thermal(struct cpuinfo_x86 *c); -void mce_log_therm_throt_event(__u64 status); - /* Interrupt Handler for core thermal thresholds */ extern int (*platform_thermal_notify)(__u64 msr_val); @@ -362,12 +365,13 @@ struct smca_hwid { unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ u32 hwid_mcatype; /* (hwid,mcatype) tuple */ u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ + u8 count; /* Number of instances. */ }; struct smca_bank { struct smca_hwid *hwid; - /* Instance ID */ - u32 id; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ }; extern struct smca_bank smca_banks[MAX_NR_BANKS]; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..daadeeea00b1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -7,18 +7,17 @@ #define native_rdmsr(msr, val1, val2) \ do { \ - u64 __val = native_read_msr((msr)); \ + u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) #define native_wrmsr(msr, low, high) \ - native_write_msr(msr, low, high) + __wrmsr(msr, low, high) #define native_wrmsrl(msr, val) \ - native_write_msr((msr), \ - (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)) + __wrmsr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)) struct ucode_patch { struct list_head plist; @@ -140,6 +139,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 3e3e20be829a..3d57009e168b 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -54,6 +54,4 @@ static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } void reload_ucode_amd(void) {} #endif - -extern bool check_current_patch_level(u32 *rev, bool early); #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 195becc6f780..e793fc9a9b20 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -52,6 +52,21 @@ struct extended_sigtable { #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) +static inline u32 intel_get_microcode_revision(void) +{ + u32 rev, dummy; + + native_wrmsrl(MSR_IA32_UCODE_REV, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + native_cpuid_eax(1); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); + + return rev; +} + #ifdef CONFIG_MICROCODE_INTEL extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index aaf59b7da98a..7c9c895432a9 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -3,8 +3,28 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/clocksource.h> #include <asm/hyperv.h> +/* + * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent + * is set by CPUID(HVCPUID_VERSION_FEATURES). + */ +enum hv_cpuid_function { + HVCPUID_VERSION_FEATURES = 0x00000001, + HVCPUID_VENDOR_MAXFUNCTION = 0x40000000, + HVCPUID_INTERFACE = 0x40000001, + + /* + * The remaining functions depend on the value of + * HVCPUID_INTERFACE + */ + HVCPUID_VERSION = 0x40000002, + HVCPUID_FEATURES = 0x40000003, + HVCPUID_ENLIGHTENMENT_INFO = 0x40000004, + HVCPUID_IMPLEMENTATION_LIMITS = 0x40000005, +}; + struct ms_hyperv_info { u32 features; u32 misc_features; @@ -13,6 +33,128 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; +/* + * 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; + }; +}; + +/* + * TSC page layout. + */ + +struct ms_hyperv_tsc_page { + volatile u32 tsc_sequence; + u32 reserved1; + volatile u64 tsc_scale; + volatile s64 tsc_offset; + u64 reserved2[509]; +}; + +/* + * The guest OS needs to register the guest ID with the hypervisor. + * The guest ID is a 64 bit entity and the structure of this ID is + * specified in the Hyper-V specification: + * + * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx + * + * While the current guideline does not specify how Linux guest ID(s) + * need to be generated, our plan is to publish the guidelines for + * Linux and other guest operating systems that currently are hosted + * on Hyper-V. The implementation here conforms to this yet + * unpublished guidelines. + * + * + * Bit(s) + * 63 - Indicates if the OS is Open Source or not; 1 is Open Source + * 62:56 - Os Type; Linux is 0x100 + * 55:48 - Distro specific identification + * 47:16 - Linux kernel version number + * 15:0 - Distro specific identification + * + * + */ + +#define HV_LINUX_VENDOR_ID 0x8100 + +/* + * Generate the guest ID based on the guideline described above. + */ + +static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version, + __u64 d_info2) +{ + __u64 guest_id = 0; + + guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48); + guest_id |= (d_info1 << 48); + guest_id |= (kernel_version << 16); + guest_id |= d_info2; + + return guest_id; +} + + +/* Free the message slot and signal end-of-message if required */ +static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) +{ + /* + * On crash we're reading some other CPU's message page and we need + * to be careful: this other CPU may already had cleared the header + * and the host may already had delivered some other message there. + * In case we blindly write msg->header.message_type we're going + * to lose it. We can still lose a message of the same type but + * we count on the fact that there can only be one + * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages + * on crash. + */ + if (cmpxchg(&msg->header.message_type, old_msg_type, + HVMSG_NONE) != old_msg_type) + return; + + /* + * Make sure the write to MessageType (ie set to + * HVMSG_NONE) happens before we read the + * MessagePending and EOMing. Otherwise, the EOMing + * will not deliver any more messages since there is + * no empty slot + */ + mb(); + + if (msg->header.message_flags.msg_pending) { + /* + * This will cause message queue rescan to + * possibly deliver another msg from the + * hypervisor + */ + wrmsrl(HV_X64_MSR_EOM, 0); + } +} + +#define hv_get_current_tick(tick) rdmsrl(HV_X64_MSR_TIME_REF_COUNT, tick) +#define hv_init_timer(timer, tick) wrmsrl(timer, tick) +#define hv_init_timer_config(config, val) wrmsrl(config, val) + +#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val) +#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val) + +#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val) +#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val) + +#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val) +#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val) + +#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index) + +#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val) +#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) + void hyperv_callback_vector(void); #ifdef CONFIG_TRACING #define trace_hyperv_callback_vector hyperv_callback_vector @@ -25,4 +167,13 @@ void hv_setup_kexec_handler(void (*handler)(void)); void hv_remove_kexec_handler(void); void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); void hv_remove_crash_handler(void); + +#if IS_ENABLED(CONFIG_HYPERV) +extern struct clocksource *hyperv_cs; + +void hyperv_init(void); +void hyperv_report_panic(struct pt_regs *regs); +bool hv_is_hypercall_page_setup(void); +void hyperv_cleanup(void); +#endif #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 710273c617b8..00293a94ffaf 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -543,6 +543,11 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) +/* MISC_FEATURE_ENABLES non-architectural features */ +#define MSR_MISC_FEATURE_ENABLES 0x00000140 + +#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 + #define MSR_IA32_TSC_DEADLINE 0x000006E0 /* P4/Xeon+ specific */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index db0b90c3b03e..898dba2e2e2c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {} static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} #endif -static inline unsigned long long native_read_msr(unsigned int msr) +/* + * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR + * accessors and should not have any tracing or other functionality piggybacking + * on them - those are *purely* for accessing MSRs and nothing more. So don't even + * think of extending them - you will be slapped with a stinking trout or a frozen + * shark will reach you, wherever you are! You've been warned. + */ +static inline unsigned long long notrace __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr) "2:\n" _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) : EAX_EDX_RET(val, low, high) : "c" (msr)); - if (msr_tracepoint_active(__tracepoint_read_msr)) - do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); + return EAX_EDX_VAL(val, low, high); } +static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +{ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + : : "c" (msr), "a"(low), "d" (high) : "memory"); +} + +static inline unsigned long long native_read_msr(unsigned int msr) +{ + unsigned long long val; + + val = __rdmsr(msr); + + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, val, 0); + + return val; +} + static inline unsigned long long native_read_msr_safe(unsigned int msr, int *err) { @@ -116,29 +142,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, /* Can be uninlined because referenced by paravirt */ static inline void notrace -__native_write_msr_notrace(unsigned int msr, u32 low, u32 high) -{ - asm volatile("1: wrmsr\n" - "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) - : : "c" (msr), "a"(low), "d" (high) : "memory"); -} - -/* Can be uninlined because referenced by paravirt */ -static inline void notrace native_write_msr(unsigned int msr, u32 low, u32 high) { - __native_write_msr_notrace(msr, low, high); + __wrmsr(msr, low, high); + if (msr_tracepoint_active(__tracepoint_write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } -static inline void -wrmsr_notrace(unsigned int msr, u32 low, u32 high) -{ - __native_write_msr_notrace(msr, low, high); -} - /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(unsigned int msr, u32 low, u32 high) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 1eea6ca40694..0489884fdc44 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -475,6 +475,17 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, native_pmd_val(pmd)); } +static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + if (sizeof(pudval_t) > sizeof(long)) + /* 5 arg words */ + pv_mmu_ops.set_pud_at(mm, addr, pudp, pud); + else + PVOP_VCALL4(pv_mmu_ops.set_pud_at, mm, addr, pudp, + native_pud_val(pud)); +} + static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { pmdval_t val = native_pmd_val(pmd); @@ -673,7 +684,7 @@ static __always_inline void pv_kick(int cpu) PVOP_VCALL1(pv_lock_ops.kick, cpu); } -static __always_inline bool pv_vcpu_is_preempted(int cpu) +static __always_inline bool pv_vcpu_is_preempted(long cpu) { return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu); } diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index bb2de45a60f2..b060f962d581 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -249,6 +249,8 @@ struct pv_mmu_ops { void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmdval); + void (*set_pud_at)(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pudval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index fd74a11959de..a8b96e708c2b 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -21,6 +21,10 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) *pmdp = pmd; } +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ +} + static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); @@ -31,6 +35,10 @@ static inline void native_pmd_clear(pmd_t *pmdp) native_set_pmd(pmdp, __pmd(0)); } +static inline void native_pud_clear(pud_t *pudp) +{ +} + static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp) { @@ -55,6 +63,15 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ + return __pud(xchg((pudval_t *)xp, 0)); +} +#else +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + /* Bit manipulation helper on pte/pgoff entry */ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift, unsigned long mask, unsigned int leftshift) diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index cdaa58c9b39e..8f50fb3f04e1 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -121,6 +121,12 @@ static inline void native_pmd_clear(pmd_t *pmd) *(tmp + 1) = 0; } +#ifndef CONFIG_SMP +static inline void native_pud_clear(pud_t *pudp) +{ +} +#endif + static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); @@ -176,6 +182,30 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +union split_pud { + struct { + u32 pud_low; + u32 pud_high; + }; + pud_t pud; +}; + +static inline pud_t native_pudp_get_and_clear(pud_t *pudp) +{ + union split_pud res, *orig = (union split_pud *)pudp; + + /* xchg acts as a barrier before setting of the high bits */ + res.pud_low = xchg(&orig->pud_low, 0); + res.pud_high = orig->pud_high; + orig->pud_high = 0; + + return res.pud; +} +#else +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + /* Encode and de-code a swap entry */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) #define __swp_type(x) (((x).val) & 0x1f) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 437feb436efa..1cfb36b8c024 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -46,6 +46,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) #define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd) +#define set_pud_at(mm, addr, pudp, pud) native_set_pud_at(mm, addr, pudp, pud) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) @@ -128,6 +129,16 @@ static inline int pmd_young(pmd_t pmd) return pmd_flags(pmd) & _PAGE_ACCESSED; } +static inline int pud_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_DIRTY; +} + +static inline int pud_young(pud_t pud) +{ + return pud_flags(pud) & _PAGE_ACCESSED; +} + static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; @@ -181,6 +192,13 @@ static inline int pmd_trans_huge(pmd_t pmd) return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline int pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; +} +#endif + #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { @@ -192,6 +210,18 @@ static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline int pud_devmap(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_DEVMAP); +} +#else +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +#endif #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -333,6 +363,65 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE); } +static inline pud_t pud_set_flags(pud_t pud, pudval_t set) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v | set); +} + +static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v & ~clear); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_DIRTY); +} + +static inline pud_t pud_wrprotect(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_RW); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_DEVMAP); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_PSE); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_RW); +} + +static inline pud_t pud_mknotpresent(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE); +} + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { @@ -344,6 +433,11 @@ static inline int pmd_soft_dirty(pmd_t pmd) return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } +static inline int pud_soft_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_SOFT_DIRTY; +} + static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); @@ -354,6 +448,11 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pud_t pud_mksoft_dirty(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_SOFT_DIRTY); +} + static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); @@ -364,6 +463,11 @@ static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pud_t pud_clear_soft_dirty(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); +} + #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* @@ -392,6 +496,12 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) massage_pgprot(pgprot)); } +static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) +{ + return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); +} + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte); @@ -771,6 +881,14 @@ static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) return res; } +static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) +{ + pud_t res = *pudp; + + native_pud_clear(pudp); + return res; +} + static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep , pte_t pte) { @@ -783,6 +901,12 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, native_set_pmd(pmdp, pmd); } +static inline void native_set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + native_set_pud(pudp, pud); +} + #ifndef CONFIG_PARAVIRT /* * Rules for using pte_update - it must be called after any PTE update which @@ -861,10 +985,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, @@ -884,6 +1013,13 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long return native_pmdp_get_and_clear(pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + return native_pudp_get_and_clear(pudp); +} + #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -932,6 +1068,10 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b6c0b404898a..fbc73360aea0 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -27,6 +27,7 @@ struct vm_area_struct; extern pgd_t swapper_pg_dir[1024]; extern pgd_t initial_page_table[1024]; +extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } @@ -75,4 +76,35 @@ do { \ #define kern_addr_valid(kaddr) (0) #endif +/* + * This is how much memory in addition to the memory covered up to + * and including _end we need mapped initially. + * We need: + * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) + * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) + * + * Modulo rounding, each megabyte assigned here requires a kilobyte of + * memory, which is currently unreclaimed. + * + * This should be a multiple of a page. + * + * KERNEL_IMAGE_SIZE should be greater than pa(_end) + * and small than max_low_pfn, otherwise will waste some page table entries + */ +#if PTRS_PER_PMD > 1 +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) +#else +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) +#endif + +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) + #endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 62b775926045..73c7ccc38912 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -106,6 +106,21 @@ static inline void native_pud_clear(pud_t *pud) native_set_pud(pud, native_make_pud(0)); } +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ +#ifdef CONFIG_SMP + return native_make_pud(xchg(&xp->pud, 0)); +#else + /* native_local_pudp_get_and_clear, + * but duplicated because of cyclic dependency + */ + pud_t ret = *xp; + + native_pud_clear(xp); + return ret; +#endif +} + static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { *pgdp = pgd; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index eaf100508c36..f385eca5407a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -104,6 +104,7 @@ struct cpuinfo_x86 { __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; + __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ @@ -219,6 +220,24 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, : "memory"); } +#define native_cpuid_reg(reg) \ +static inline unsigned int native_cpuid_##reg(unsigned int op) \ +{ \ + unsigned int eax = op, ebx, ecx = 0, edx; \ + \ + native_cpuid(&eax, &ebx, &ecx, &edx); \ + \ + return reg; \ +} + +/* + * Native CPUID functions returning a single datum. + */ +native_cpuid_reg(eax) +native_cpuid_reg(ebx) +native_cpuid_reg(ecx) +native_cpuid_reg(edx) + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); @@ -285,7 +304,7 @@ struct x86_hw_tss { u16 reserved5; u16 io_bitmap_base; -} __attribute__((packed)) ____cacheline_aligned; +} __attribute__((packed)); #endif /* @@ -323,6 +342,16 @@ struct tss_struct { DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +/* + * sizeof(unsigned long) coming from an extra "long" at the end + * of the iobitmap. + * + * -1? seg base+limit should be pointing to the address of the + * last valid byte + */ +#define __KERNEL_TSS_LIMIT \ + (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) + #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #endif diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index c343ab52579f..48a706f641f2 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -34,7 +34,7 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) +static inline bool vcpu_is_preempted(long cpu) { return pv_vcpu_is_preempted(cpu); } diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 921bea7a2708..6d391909e864 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -23,9 +23,6 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -extern struct static_key paravirt_ticketlocks_enabled; -static __always_inline bool static_key_false(struct static_key *key); - #include <asm/qspinlock.h> /* diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index a3269c897ec5..2e41c50ddf47 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -58,7 +58,7 @@ get_frame_pointer(struct task_struct *task, struct pt_regs *regs) if (task == current) return __builtin_frame_address(0); - return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; + return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 5cb436acd463..fcc5cd387fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -36,7 +36,10 @@ static inline void prepare_switch_to(struct task_struct *prev, asmlinkage void ret_from_fork(void); -/* data that is pointed to by thread.sp */ +/* + * This is the structure pointed to by thread.sp for an inactive task. The + * order of the fields must match the code in __switch_to_asm(). + */ struct inactive_task_frame { #ifdef CONFIG_X86_64 unsigned long r15; @@ -48,6 +51,11 @@ struct inactive_task_frame { unsigned long di; #endif unsigned long bx; + + /* + * These two fields must be together. They form a stack frame header, + * needed by get_frame_pointer(). + */ unsigned long bp; unsigned long ret_addr; }; diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 062921ef34e9..6686820feae9 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -10,6 +10,7 @@ struct mm_struct; extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); +extern int is_uv_hubless(void); extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); @@ -23,6 +24,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } +static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 097b80c989c4..72e8300b1e8a 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -772,6 +772,7 @@ static inline int uv_num_possible_blades(void) /* Per Hub NMI support */ extern void uv_nmi_setup(void); +extern void uv_nmi_setup_hubless(void); /* BMC sets a bit this MMR non-zero before sending an NMI */ #define UVH_NMI_MMR UVH_SCRATCH5 @@ -799,6 +800,8 @@ struct uv_hub_nmi_s { atomic_t read_mmr_count; /* count of MMR reads */ atomic_t nmi_count; /* count of true UV NMIs */ unsigned long nmi_value; /* last value read from NMI MMR */ + bool hub_present; /* false means UV hubless system */ + bool pch_owner; /* indicates this hub owns PCH */ }; struct uv_cpu_nmi_s { diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2b5b2d4b924e..cc54b7026567 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -467,8 +467,16 @@ enum vmcs_field { #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull #define VMX_EPT_IPAT_BIT (1ull << 6) -#define VMX_EPT_ACCESS_BIT (1ull << 8) -#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ + VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) +#define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) + +/* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ +#define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul @@ -500,6 +508,22 @@ struct vmx_msr_entry { #define ENTRY_FAIL_VMCS_LINK_PTR 4 /* + * Exit Qualifications for EPT Violations + */ +#define EPT_VIOLATION_ACC_READ_BIT 0 +#define EPT_VIOLATION_ACC_WRITE_BIT 1 +#define EPT_VIOLATION_ACC_INSTR_BIT 2 +#define EPT_VIOLATION_READABLE_BIT 3 +#define EPT_VIOLATION_WRITABLE_BIT 4 +#define EPT_VIOLATION_EXECUTABLE_BIT 5 +#define EPT_VIOLATION_ACC_READ (1 << EPT_VIOLATION_ACC_READ_BIT) +#define EPT_VIOLATION_ACC_WRITE (1 << EPT_VIOLATION_ACC_WRITE_BIT) +#define EPT_VIOLATION_ACC_INSTR (1 << EPT_VIOLATION_ACC_INSTR_BIT) +#define EPT_VIOLATION_READABLE (1 << EPT_VIOLATION_READABLE_BIT) +#define EPT_VIOLATION_WRITABLE (1 << EPT_VIOLATION_WRITABLE_BIT) +#define EPT_VIOLATION_EXECUTABLE (1 << EPT_VIOLATION_EXECUTABLE_BIT) + +/* * VM-instruction error numbers */ enum vm_instruction_error_number { diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a12a047184ee..f6d20f6cca12 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -472,6 +472,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg) return _hypercall2(int, xenpmu_op, op, arg); } +static inline int +HYPERVISOR_dm_op( + domid_t dom, unsigned int nr_bufs, void *bufs) +{ + return _hypercall3(int, dm_op, dom, nr_bufs, bufs); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { |