diff options
Diffstat (limited to 'arch/x86/include')
43 files changed, 352 insertions, 129 deletions
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 2e599384abd8..84402de885b9 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -53,7 +53,7 @@ extern int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; -extern unsigned int lapic_timer_frequency; +extern unsigned int lapic_timer_period; extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { @@ -448,6 +448,14 @@ static inline void ack_APIC_irq(void) apic_eoi(); } + +static inline bool lapic_vector_set_in_irr(unsigned int vector) +{ + u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + + return !!(irr & (1U << (vector % 32))); +} + static inline unsigned default_get_apic_id(unsigned long x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 31c379c1da41..0c814cd9ea42 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -9,6 +9,36 @@ #include <linux/mod_devicetable.h> +#define X86_CENTAUR_FAM6_C7_D 0xd +#define X86_CENTAUR_FAM6_NANO 0xf + +#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 + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Backport version to keep the SRBDS pile consistant. No shorter variants + * required for this. + */ +#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = X86_VENDOR_##_vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .driver_data = (unsigned long) _data \ +} + /* * Match specific microcode revisions. * diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index cff3f3f3bfe0..6e9c9af3255a 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -78,8 +78,12 @@ struct cpu_entry_area { /* * The GDT is just below entry_stack and thus serves (on x86_64) as - * a a read-only guard page. + * a read-only guard page. On 32-bit the GDT must be writeable, so + * it needs an extra guard page. */ +#ifdef CONFIG_X86_32 + char guard_entry_stack[PAGE_SIZE]; +#endif struct entry_stack_page entry_stack_page; /* @@ -94,7 +98,6 @@ struct cpu_entry_area { */ struct cea_exception_stacks estacks; #endif -#ifdef CONFIG_CPU_SUP_INTEL /* * Per CPU debug store for Intel performance monitoring. Wastes a * full page at the moment. @@ -105,11 +108,13 @@ struct cpu_entry_area { * Reserve enough fixmap PTEs. */ struct debug_store_buffers cpu_debug_buffers; -#endif }; -#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) -#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_ARRAY_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) + +/* Total size includes the readonly IDT mapping page as well: */ +#define CPU_ENTRY_AREA_TOTAL_SIZE (CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); @@ -117,13 +122,14 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); extern void setup_cpu_entry_areas(void); extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); +/* Single page reserved for the readonly IDT mapping: */ #define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE #define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) #define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) #define CPU_ENTRY_AREA_MAP_SIZE \ - (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) + (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) extern struct cpu_entry_area *get_cpu_entry_area(int cpu); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6086e00f4b97..463395d7a306 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -351,6 +351,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ @@ -395,5 +396,6 @@ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index 0acf5ee45a21..ef5638f641f2 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_CRASH_H #define _ASM_X86_CRASH_H +struct kimage; + int crash_load_segments(struct kimage *image); int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 00f7cf45e699..8e95aa4b0d17 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -74,7 +74,7 @@ #define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ -#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) +#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT)) #ifdef CONFIG_X86_32 /* The maximum address that we can perform a DMA transfer to on this platform */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 9da8cccdf3fb..6a295acd3de6 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -157,7 +157,7 @@ extern pte_t *kmap_pte; extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); -void native_set_fixmap(enum fixed_addresses idx, +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index b774c52e5411..1786e4d9f70e 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -23,6 +23,7 @@ extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +extern void kernel_fpu_resched(void); /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 4c95c365058a..00eac7f1529b 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { - return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; + return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* @@ -619,6 +619,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 5cbce6fbb534..296b346184b2 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -22,6 +22,35 @@ pop %_ASM_BP .endm +#ifdef CONFIG_X86_64 +/* + * This is a sneaky trick to help the unwinder find pt_regs on the stack. The + * frame pointer is replaced with an encoded pointer to pt_regs. The encoding + * is just setting the LSB, which makes it an invalid stack address and is also + * a signal to the unwinder that it's a pt_regs pointer in disguise. + * + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts + * the original rbp. + */ +.macro ENCODE_FRAME_POINTER ptregs_offset=0 + leaq 1+\ptregs_offset(%rsp), %rbp +.endm +#else /* !CONFIG_X86_64 */ +/* + * This is a sneaky trick to help the unwinder find pt_regs on the stack. The + * frame pointer is replaced with an encoded pointer to pt_regs. The encoding + * is just clearing the MSB, which makes it an invalid stack address and is also + * a signal to the unwinder that it's a pt_regs pointer in disguise. + * + * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the + * original ebp. + */ +.macro ENCODE_FRAME_POINTER + mov %esp, %ebp + andl $0x7fffffff, %ebp +.endm +#endif /* CONFIG_X86_64 */ + #else /* !__ASSEMBLY__ */ #define FRAME_BEGIN \ @@ -30,12 +59,32 @@ #define FRAME_END "pop %" _ASM_BP "\n" +#ifdef CONFIG_X86_64 +#define ENCODE_FRAME_POINTER \ + "lea 1(%rsp), %rbp\n\t" +#else /* !CONFIG_X86_64 */ +#define ENCODE_FRAME_POINTER \ + "movl %esp, %ebp\n\t" \ + "andl $0x7fffffff, %ebp\n\t" +#endif /* CONFIG_X86_64 */ + #endif /* __ASSEMBLY__ */ #define FRAME_OFFSET __ASM_SEL(4, 8) #else /* !CONFIG_FRAME_POINTER */ +#ifdef __ASSEMBLY__ + +.macro ENCODE_FRAME_POINTER ptregs_offset=0 +.endm + +#else /* !__ASSEMBLY */ + +#define ENCODE_FRAME_POINTER + +#endif + #define FRAME_BEGIN #define FRAME_END #define FRAME_OFFSET 0 diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 82a57d344b9b..2a8e5f78e23c 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -61,6 +61,9 @@ #define INTEL_FAM6_TIGERLAKE_L 0x8C #define INTEL_FAM6_TIGERLAKE 0x8D +#define INTEL_FAM6_COMETLAKE 0xA5 +#define INTEL_FAM6_COMETLAKE_L 0xA6 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 003f2daa3b0f..5e7d6b46de97 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -71,22 +71,6 @@ struct kimage; #define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */ /* - * CPU does not save ss and sp on stack if execution is already - * running in kernel mode at the time of NMI occurrence. This code - * fixes it. - */ -static inline void crash_fixup_ss_esp(struct pt_regs *newregs, - struct pt_regs *oldregs) -{ -#ifdef CONFIG_X86_32 - newregs->sp = (unsigned long)&(oldregs->sp); - asm volatile("xorl %%eax, %%eax\n\t" - "movw %%ss, %%ax\n\t" - :"=a"(newregs->ss)); -#endif -} - -/* * This function is responsible for capturing register states if coming * via panic otherwise just fix up the ss and sp if coming via kernel * mode exception. @@ -96,7 +80,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, { if (oldregs) { memcpy(newregs, oldregs, sizeof(*newregs)); - crash_fixup_ss_esp(newregs, oldregs); } else { #ifdef CONFIG_X86_32 asm volatile("movl %%ebx,%0" : "=m"(newregs->bx)); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4512200c33d2..c58b42c1011c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -385,12 +385,12 @@ struct kvm_mmu { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, + int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, + u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, @@ -555,6 +555,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 host_pkru; u32 pkru; u32 hflags; u64 efer; @@ -570,6 +571,7 @@ struct kvm_vcpu_arch { u64 smbase; u64 smi_count; bool tpr_access_reporting; + bool xsaves_enabled; u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; @@ -620,7 +622,7 @@ struct kvm_vcpu_arch { * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu user_fpu; + struct fpu *user_fpu; struct fpu *guest_fpu; u64 xcr0; @@ -672,10 +674,10 @@ struct kvm_vcpu_arch { bool pvclock_set_guest_stopped_request; struct { + u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_hva_cache stime; - struct kvm_steal_time steal; + struct gfn_to_pfn_cache cache; } st; u64 tsc_offset; @@ -1094,7 +1096,7 @@ struct kvm_x86_ops { 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, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); @@ -1124,8 +1126,9 @@ struct kvm_x86_ops { bool (*xsaves_supported)(void); bool (*umip_emulated)(void); bool (*pt_supported)(void); + bool (*pku_supported)(void); - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1154,7 +1157,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1417,7 +1420,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +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_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); @@ -1585,8 +1588,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 5ed3cf1c3934..9b4df6eaa11a 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -92,7 +92,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); -void do_async_page_fault(struct pt_regs *regs, unsigned long error_code); +void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address); #ifdef CONFIG_PARAVIRT_SPINLOCKS void __init kvm_spinlock_init(void); diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 209492849566..5c524d4f71cd 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -41,7 +41,7 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define PATCH_MAX_SIZE PAGE_SIZE +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 5ff3e8af2c20..e78c7db87801 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -59,6 +59,7 @@ typedef struct { #define INIT_MM_CONTEXT(mm) \ .context = { \ .ctx_id = 1, \ + .lock = __MUTEX_INITIALIZER(mm.context.lock), \ } void leave_mm(int cpu); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index cc60e617931c..ae44aa1f8a80 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -343,7 +343,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); -void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index bae74871c017..e1c4bf0fa66c 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -110,6 +110,10 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ +/* SRBDS support */ +#define MSR_IA32_MCU_OPT_CTRL 0x00000123 +#define RNGDS_MITG_DIS BIT(0) + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -493,6 +497,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 75ded1d13d98..9d5d949e662e 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -41,7 +41,6 @@ struct nmiaction { struct list_head list; nmi_handler_t handler; u64 max_duration; - struct irq_work irq_work; unsigned long flags; const char *name; }; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d6f5ae2c79ab..dce26f1d13e1 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -116,7 +116,7 @@ static inline void write_cr0(unsigned long x) static inline unsigned long read_cr2(void) { - return PVOP_CALL0(unsigned long, mmu.read_cr2); + return PVOP_CALLEE0(unsigned long, mmu.read_cr2); } static inline void write_cr2(unsigned long x) @@ -910,13 +910,7 @@ extern void default_banner(void); ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \ ) -#endif - -#define GET_CR2_INTO_RAX \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2); -#ifdef CONFIG_PARAVIRT_XXL #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \ ANNOTATE_RETPOLINE_SAFE; \ @@ -930,9 +924,19 @@ extern void default_banner(void); call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif -#endif +#endif /* CONFIG_PARAVIRT_XXL */ +#endif /* CONFIG_X86_64 */ + +#ifdef CONFIG_PARAVIRT_XXL + +#define GET_CR2_INTO_AX \ + PARA_SITE(PARA_PATCH(PV_MMU_read_cr2), \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2); \ + ) + +#endif /* CONFIG_PARAVIRT_XXL */ -#endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ #else /* CONFIG_PARAVIRT */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 2474e434a6f7..8e46f1b764a3 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -220,7 +220,7 @@ struct pv_mmu_ops { void (*exit_mmap)(struct mm_struct *mm); #ifdef CONFIG_PARAVIRT_XXL - unsigned long (*read_cr2)(void); + struct paravirt_callee_save read_cr2; void (*write_cr2)(unsigned long); unsigned long (*read_cr3)(void); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5e0509b41986..c8e859cdead7 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -253,6 +253,7 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; @@ -624,12 +625,15 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return __pmd(val); } -/* mprotect needs to preserve PAT bits when updating vm_page_prot */ +/* + * mprotect needs to preserve PAT and encryption bits when updating + * vm_page_prot + */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; - pgprotval_t addbits = pgprot_val(newprot); + pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 4fe9e7fc74d3..c78da8eda8f2 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -106,6 +106,6 @@ do { \ * with only a host target support using a 32-bit type for internal * representation. */ -#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) +#define LOWMEM_PAGES ((((_ULL(2)<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) #endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index b0bc0fff5f1f..1636eb8e5a5b 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,11 +44,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c * to avoid include recursion hell */ -#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 39) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ - & PMD_MASK) +/* The +1 is for the readonly IDT page: */ +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) #define LDT_BASE_ADDR \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index d6ff0bbdb394..9484b06291ec 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -124,7 +124,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 99a7fa9ab0a3..9496299d23fc 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -89,17 +89,48 @@ static __always_inline void __preempt_count_sub(int val) * a decrement which hits zero means we have no preempt_count and should * reschedule. */ -static __always_inline bool __preempt_count_dec_and_test(void) +static __always_inline bool ____preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } +static __always_inline bool __preempt_count_dec_and_test(void) +{ + if (____preempt_count_dec_and_test()) + return true; +#ifdef CONFIG_PREEMPT_LAZY + if (preempt_count()) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else + return false; +#endif +} + /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { +#ifdef CONFIG_PREEMPT_LAZY + u32 tmp; + + tmp = raw_cpu_read_4(__preempt_count); + if (tmp == preempt_offset) + return true; + + /* preempt count == 0 ? */ + tmp &= ~PREEMPT_NEED_RESCHED; + if (tmp != preempt_offset) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); +#endif } #ifdef CONFIG_PREEMPT diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7781114574f0..f9300c86d95d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -331,7 +331,7 @@ struct x86_hw_tss { #define INVALID_IO_BITMAP_OFFSET 0x8000 struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { @@ -738,6 +738,7 @@ extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); +extern void cr4_init(void); static inline unsigned long get_debugctlmsr(void) { diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 8a7fc0cca2d1..3703c91f441e 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -166,14 +166,10 @@ static inline bool user_64bit_mode(struct pt_regs *regs) #define compat_user_stack_pointer() current_pt_regs()->sp #endif -#ifdef CONFIG_X86_32 -extern unsigned long kernel_stack_pointer(struct pt_regs *regs); -#else static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } -#endif #define GET_IP(regs) ((regs)->ip) #define GET_FP(regs) ((regs)->bp) @@ -201,14 +197,6 @@ static inline unsigned long regs_get_register(struct pt_regs *regs, if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 - /* - * Traps from the kernel do not save sp and ss. - * Use the helper function to retrieve sp. - */ - if (offset == offsetof(struct pt_regs, sp) && - regs->cs == __KERNEL_CS) - return kernel_stack_pointer(regs); - /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || @@ -234,8 +222,7 @@ static inline unsigned long regs_get_register(struct pt_regs *regs, static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { - return ((addr & ~(THREAD_SIZE - 1)) == - (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); + return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** @@ -249,7 +236,7 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs, */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { - unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index ac3892920419..6669164abadc 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -31,6 +31,18 @@ */ #define SEGMENT_RPL_MASK 0x3 +/* + * When running on Xen PV, the actual privilege level of the kernel is 1, + * not 0. Testing the Requested Privilege Level in a segment selector to + * determine whether the context is user mode or kernel mode with + * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level + * matches the 0x3 mask. + * + * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV + * kernels because privilege level 2 is never used. + */ +#define USER_SEGMENT_RPL_MASK 0x2 + /* User mode is privilege level 3: */ #define USER_RPL 0x3 diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index ae7b909dc242..75d298cbc780 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -93,28 +93,35 @@ void set_kernel_text_rw(void); void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 -static inline int set_mce_nospec(unsigned long pfn) +/* + * Prevent speculative access to the page by either unmapping + * it (if we do not require access to any part of the page) or + * marking it uncacheable (if we want to try to retrieve data + * from non-poisoned lines in the page). + */ +static inline int set_mce_nospec(unsigned long pfn, bool unmap) { unsigned long decoy_addr; int rc; /* - * Mark the linear address as UC to make sure we don't log more - * errors because of speculative access to the page. * We would like to just call: - * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1); + * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address * that looks just like the one we want, but has bit 63 flipped. - * This relies on set_memory_uc() properly sanitizing any __pa() + * This relies on set_memory_XX() properly sanitizing any __pa() * results with __PHYSICAL_MASK or PTE_PFN_MASK. */ decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); - rc = set_memory_uc(decoy_addr, 1); + if (unmap) + rc = set_memory_np(decoy_addr, 1); + else + rc = set_memory_uc(decoy_addr, 1); if (rc) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); return rc; diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 33d3c88a7225..c00e27af2205 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -28,6 +28,19 @@ typedef struct { #define SA_IA32_ABI 0x02000000u #define SA_X32_ABI 0x01000000u +/* + * Because some traps use the IST stack, we must keep preemption + * disabled while calling do_trap(), but do_trap() may call + * force_sig_info() which will grab the signal spin_locks for the + * task, which in PREEMPT_RT_FULL are mutexes. By defining + * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +#if defined(CONFIG_PREEMPT_RT_FULL) +#define ARCH_RT_DELAYS_SIGNAL_SEND +#endif + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 27c47d183f4b..8b58d6975d5d 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void) { unsigned long flags; - asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC, - X86_FEATURE_SMAP) + asm volatile ("# smap_save\n\t" + ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) + "pushf; pop %0; " __ASM_CLAC "\n\t" + "1:" : "=rm" (flags) : : "memory", "cc"); return flags; @@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void) static __always_inline void smap_restore(unsigned long flags) { - asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP) + asm volatile ("# smap_restore\n\t" + ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) + "push %0; popf\n\t" + "1:" : : "g" (flags) : "memory", "cc"); } diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 0a3c4cab39db..219be88a59d2 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -6,6 +6,8 @@ #ifdef __KERNEL__ #include <asm/nops.h> +#include <asm/processor-flags.h> +#include <linux/jump_label.h> /* * Volatile isn't enough to prevent the compiler from reordering the @@ -16,6 +18,8 @@ */ extern unsigned long __force_order; +void native_write_cr0(unsigned long val); + static inline unsigned long native_read_cr0(void) { unsigned long val; @@ -23,11 +27,6 @@ static inline unsigned long native_read_cr0(void) return val; } -static inline void native_write_cr0(unsigned long val) -{ - asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); -} - static inline unsigned long native_read_cr2(void) { unsigned long val; @@ -72,10 +71,7 @@ static inline unsigned long native_read_cr4(void) return val; } -static inline void native_write_cr4(unsigned long val) -{ - asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); -} +void native_write_cr4(unsigned long val); #ifdef CONFIG_X86_64 static inline unsigned long native_read_cr8(void) diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 91e29b6a86a5..2624c4b94014 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,12 +55,17 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 uninitialized_var(canary); u64 tsc; #ifdef CONFIG_X86_64 @@ -71,8 +76,14 @@ static __always_inline void boot_init_stack_canary(void) * of randomness. The TSC only matters for very early init, * there it already has some randomness on most systems. Later * on during the bootup the random pool has true entropy too. + * For preempt-rt we need to weaken the randomness a bit, as + * we can't call into the random generator from atomic context + * due to locking constraints. We just leave canary + * uninitialized and use the TSC based randomness on top of it. */ +#ifndef CONFIG_PREEMPT_RT_FULL get_random_bytes(&canary, sizeof(canary)); +#endif tsc = rdtsc(); canary += tsc + (tsc << 32UL); canary &= CANARY_MASK; diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index a8d0cdf48616..14db05086bbf 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -78,7 +78,7 @@ static inline unsigned long * get_stack_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) - return (unsigned long *)kernel_stack_pointer(regs); + return (unsigned long *)regs->sp; if (task == current) return __builtin_frame_address(0); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2dc4a021beea..8db3fdb6102e 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -36,6 +36,10 @@ extern const sys_call_ptr_t sys_call_table[]; extern const sys_call_ptr_t ia32_sys_call_table[]; #endif +#ifdef CONFIG_X86_X32_ABI +extern const sys_call_ptr_t x32_sys_call_table[]; +#endif + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e046a405743d..e2389ce9bf58 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H +struct pt_regs; + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -28,13 +30,21 @@ * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(x, name) \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name(); \ + } + #define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #define __IA32_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ @@ -48,16 +58,23 @@ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias * named __ia32_sys_*() */ -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(void) -#define COND_SYSCALL(name) \ - cond_syscall(__x64_sys_##name); \ - cond_syscall(__ia32_sys_##name) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } \ + asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ + { \ + return sys_ni_syscall(); \ + } #define SYS_NI(name) \ SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ @@ -75,15 +92,24 @@ * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ +#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name();\ + } + #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #else /* CONFIG_X86_X32 */ +#define __X32_COMPAT_SYS_STUB0(x, name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #endif /* CONFIG_X86_X32 */ @@ -94,6 +120,17 @@ * mapping of registers to parameters, we need to generate stubs for each * of them. */ +#define COMPAT_SYSCALL_DEFINE0(name) \ + static long __se_compat_sys_##name(void); \ + static inline long __do_compat_sys_##name(void); \ + __IA32_COMPAT_SYS_STUB0(x, name) \ + __X32_COMPAT_SYS_STUB0(x, name) \ + static long __se_compat_sys_##name(void) \ + { \ + return __do_compat_sys_##name(); \ + } \ + static inline long __do_compat_sys_##name(void) + #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -181,15 +218,19 @@ * macros to work correctly. */ #ifndef SYSCALL_DEFINE0 -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(void) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) #endif #ifndef COND_SYSCALL -#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name) +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } #endif #ifndef SYS_NI @@ -201,7 +242,6 @@ * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -struct pt_regs; asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); asmlinkage long __x64_sys_time(const struct pt_regs *regs); diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 880b5515b1d6..ebf185fa30bc 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -51,7 +51,6 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) #define INT3_INSN_SIZE 1 #define CALL_INSN_SIZE 5 -#ifdef CONFIG_X86_64 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) { /* @@ -69,7 +68,6 @@ static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func) int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); int3_emulate_jmp(regs, func); } -#endif /* CONFIG_X86_64 */ #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index f9453536f9bb..f346f24140be 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -56,17 +56,24 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ u32 status; /* thread synchronous flags */ + int preempt_lazy_count; /* 0 => lazy preemptable + <0 => BUG */ }; #define INIT_THREAD_INFO(tsk) \ { \ .flags = 0, \ + .preempt_lazy_count = 0, \ } #else /* !__ASSEMBLY__ */ #include <asm/asm-offsets.h> +#define GET_THREAD_INFO(reg) \ + _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ + _ASM_SUB $(THREAD_SIZE),reg ; + #endif /* @@ -92,6 +99,7 @@ struct thread_info { #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ +#define TIF_NEED_RESCHED_LAZY 18 /* lazy rescheduling necessary */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ @@ -122,6 +130,7 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) @@ -159,6 +168,8 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define STACK_WARN (THREAD_SIZE/8) /* diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index f2bd284abc16..b25e633033c3 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -74,14 +74,14 @@ dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code); dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code); dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_64 -dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code); +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long address); asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); void __init trap_init(void); #endif dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code); -dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code); +dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address); dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code); dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code); dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 146859efd83c..b923b8d333d4 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -5,12 +5,6 @@ #include <uapi/asm/unistd.h> -# ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT)) -# else -# define __SYSCALL_MASK (~0) -# endif - # ifdef CONFIG_X86_32 # include <asm/unistd_32.h> diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index 30d7d04d72d6..be5e2e747f50 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -2,7 +2,14 @@ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H -/* x32 syscall flag bit */ +/* + * x32 syscall flag bit. Some user programs expect syscall NR macros + * and __X32_SYSCALL_BIT to have type int, even though syscall numbers + * are, for practical purposes, unsigned long. + * + * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right + * thing regardless. + */ #define __X32_SYSCALL_BIT 0x40000000 #ifndef __KERNEL__ |