diff options
58 files changed, 901 insertions, 1077 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e007887..926c2cc 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1058,7 +1058,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; @@ -1078,7 +1078,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; if (IS_ENABLED(CONFIG_X86_64)) { desc->l = 1; @@ -1099,7 +1099,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; @@ -1116,7 +1116,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = 0; desc->dpl = 0; desc->p = 1; - desc->limit = 0x0; + desc->limit1 = 0x0; desc->avl = 0; desc->l = 0; desc->d = 0; diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 48ef7bb..8a13d46 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -673,16 +673,8 @@ ENTRY(name) \ jmp ret_from_intr; \ ENDPROC(name) - -#ifdef CONFIG_TRACING -# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) -#else -# define TRACE_BUILD_INTERRUPT(name, nr) -#endif - #define BUILD_INTERRUPT(name, nr) \ BUILD_INTERRUPT3(name, nr, smp_##name); \ - TRACE_BUILD_INTERRUPT(name, nr) /* The include is where all of the SMP etc. interrupts come from */ #include <asm/entry_arch.h> @@ -880,25 +872,17 @@ ENTRY(xen_failsafe_callback) ENDPROC(xen_failsafe_callback) BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - xen_evtchn_do_upcall) + xen_evtchn_do_upcall) #endif /* CONFIG_XEN */ #if IS_ENABLED(CONFIG_HYPERV) BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - hyperv_vector_handler) + hyperv_vector_handler) #endif /* CONFIG_HYPERV */ -#ifdef CONFIG_TRACING -ENTRY(trace_page_fault) - ASM_CLAC - pushl $trace_do_page_fault - jmp common_exception -END(trace_page_fault) -#endif - ENTRY(page_fault) ASM_CLAC pushl $do_page_fault diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ca0b250..4916725 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -748,18 +748,6 @@ ENTRY(\sym) END(\sym) .endm -#ifdef CONFIG_TRACING -#define trace(sym) trace_##sym -#define smp_trace(sym) smp_trace_##sym - -.macro trace_apicinterrupt num sym -apicinterrupt3 \num trace(\sym) smp_trace(\sym) -.endm -#else -.macro trace_apicinterrupt num sym do_sym -.endm -#endif - /* Make sure APIC interrupt handlers end up in the irqentry section: */ #define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" #define POP_SECTION_IRQENTRY .popsection @@ -767,7 +755,6 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) .macro apicinterrupt num sym do_sym PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym -trace_apicinterrupt \num \sym POP_SECTION_IRQENTRY .endm @@ -829,7 +816,6 @@ ENTRY(\sym) .endif ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME .ifeq \has_error_code pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -913,17 +899,6 @@ ENTRY(\sym) END(\sym) .endm -#ifdef CONFIG_TRACING -.macro trace_idtentry sym do_sym has_error_code:req -idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#else -.macro trace_idtentry sym do_sym has_error_code:req -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#endif - idtentry divide_error do_divide_error has_error_code=0 idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 @@ -986,7 +961,7 @@ ENTRY(do_softirq_own_stack) ENDPROC(do_softirq_own_stack) #ifdef CONFIG_XEN -idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 /* * A note on the "critical region" in our callback handler. @@ -1053,8 +1028,6 @@ ENTRY(xen_failsafe_callback) movq 8(%rsp), %r11 addq $0x30, %rsp pushq $0 /* RIP */ - pushq %r11 - pushq %rcx UNWIND_HINT_IRET_REGS offset=8 jmp general_protection 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ @@ -1085,13 +1058,12 @@ idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 +idtentry xendebug do_debug has_error_code=0 +idtentry xenint3 do_int3 has_error_code=0 #endif idtentry general_protection do_general_protection has_error_code=1 -trace_idtentry page_fault do_page_fault has_error_code=1 +idtentry page_fault do_page_fault has_error_code=1 #ifdef CONFIG_KVM_GUEST idtentry async_page_fault do_async_page_fault has_error_code=1 @@ -1251,21 +1223,10 @@ ENTRY(error_exit) END(error_exit) /* Runs on exception stack */ +/* XXX: broken on Xen PV */ ENTRY(nmi) UNWIND_HINT_IRET_REGS /* - * Fix up the exception frame if we're on Xen. - * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most - * one value to the stack on native, so it may clobber the rdx - * scratch slot, but it won't clobber any of the important - * slots past it. - * - * Xen is a different story, because the Xen frame itself overlaps - * the "NMI executing" variable. - */ - PARAVIRT_ADJUST_EXCEPTION_FRAME - - /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. * This means that we can have nested NMIs where the next diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4b86d8d..e26c25c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -293,7 +293,6 @@ ENTRY(entry_INT80_compat) /* * Interrupts are off on entry. */ - PARAVIRT_ADJUST_EXCEPTION_FRAME ASM_CLAC /* Do this early to minimize exposure */ SWAPGS diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 726355c..1911310 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -351,7 +351,7 @@ static void vgetcpu_cpu_init(void *arg) * and 8 bits for the node) */ d.limit0 = cpu | ((node & 0xf) << 12); - d.limit = node >> 4; + d.limit1 = node >> 4; d.type = 5; /* RO data, expand down, accessed */ d.dpl = 3; /* Visible to user code */ d.s = 1; /* Not a system segment */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index d0a21b1..1a2ba36 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -5,6 +5,7 @@ #include <asm/ldt.h> #include <asm/mmu.h> #include <asm/fixmap.h> +#include <asm/irq_vectors.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -22,7 +23,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->s = 1; desc->dpl = 0x3; desc->p = info->seg_not_present ^ 1; - desc->limit = (info->limit & 0xf0000) >> 16; + desc->limit1 = (info->limit & 0xf0000) >> 16; desc->avl = info->useable; desc->d = info->seg_32bit; desc->g = info->limit_in_pages; @@ -83,33 +84,25 @@ static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } -#ifdef CONFIG_X86_64 - static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { - gate->offset_low = PTR_LOW(func); + gate->offset_low = (u16) func; + gate->bits.p = 1; + gate->bits.dpl = dpl; + gate->bits.zero = 0; + gate->bits.type = type; + gate->offset_middle = (u16) (func >> 16); +#ifdef CONFIG_X86_64 gate->segment = __KERNEL_CS; - gate->ist = ist; - gate->p = 1; - gate->dpl = dpl; - gate->zero0 = 0; - gate->zero1 = 0; - gate->type = type; - gate->offset_middle = PTR_MIDDLE(func); - gate->offset_high = PTR_HIGH(func); -} - + gate->bits.ist = ist; + gate->reserved = 0; + gate->offset_high = (u32) (func >> 32); #else -static inline void pack_gate(gate_desc *gate, unsigned char type, - unsigned long base, unsigned dpl, unsigned flags, - unsigned short seg) -{ - gate->a = (seg << 16) | (base & 0xffff); - gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8); -} - + gate->segment = seg; + gate->bits.ist = 0; #endif +} static inline int desc_empty(const void *ptr) { @@ -173,35 +166,22 @@ native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int memcpy(&gdt[entry], desc, size); } -static inline void pack_descriptor(struct desc_struct *desc, unsigned long base, - unsigned long limit, unsigned char type, - unsigned char flags) -{ - desc->a = ((base & 0xffff) << 16) | (limit & 0xffff); - desc->b = (base & 0xff000000) | ((base & 0xff0000) >> 16) | - (limit & 0x000f0000) | ((type & 0xff) << 8) | - ((flags & 0xf) << 20); - desc->p = 1; -} - - -static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) +static inline void set_tssldt_descriptor(void *d, unsigned long addr, + unsigned type, unsigned size) { -#ifdef CONFIG_X86_64 - struct ldttss_desc64 *desc = d; + struct ldttss_desc *desc = d; memset(desc, 0, sizeof(*desc)); - desc->limit0 = size & 0xFFFF; - desc->base0 = PTR_LOW(addr); - desc->base1 = PTR_MIDDLE(addr) & 0xFF; + desc->limit0 = (u16) size; + desc->base0 = (u16) addr; + desc->base1 = (addr >> 16) & 0xFF; desc->type = type; desc->p = 1; desc->limit1 = (size >> 16) & 0xF; - desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF; - desc->base3 = PTR_HIGH(addr); -#else - pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0); + desc->base2 = (addr >> 24) & 0xFF; +#ifdef CONFIG_X86_64 + desc->base3 = (u32) (addr >> 32); #endif } @@ -401,147 +381,20 @@ static inline void set_desc_base(struct desc_struct *desc, unsigned long base) static inline unsigned long get_desc_limit(const struct desc_struct *desc) { - return desc->limit0 | (desc->limit << 16); + return desc->limit0 | (desc->limit1 << 16); } static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { desc->limit0 = limit & 0xffff; - desc->limit = (limit >> 16) & 0xf; -} - -#ifdef CONFIG_X86_64 -static inline void set_nmi_gate(int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(debug_idt_table, gate, &s); + desc->limit1 = (limit >> 16) & 0xf; } -#endif -#ifdef CONFIG_TRACING -extern struct desc_ptr trace_idt_descr; -extern gate_desc trace_idt_table[]; -static inline void write_trace_idt_entry(int entry, const gate_desc *gate) -{ - write_idt_entry(trace_idt_table, entry, gate); -} +void update_intr_gate(unsigned int n, const void *addr); +void alloc_intr_gate(unsigned int n, const void *addr); -static inline void _trace_set_gate(int gate, unsigned type, void *addr, - unsigned dpl, unsigned ist, unsigned seg) -{ - gate_desc s; - - pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); - /* - * does not need to be atomic because it is only done once at - * setup time - */ - write_trace_idt_entry(gate, &s); -} -#else -static inline void write_trace_idt_entry(int entry, const gate_desc *gate) -{ -} - -#define _trace_set_gate(gate, type, addr, dpl, ist, seg) -#endif - -static inline void _set_gate(int gate, unsigned type, void *addr, - unsigned dpl, unsigned ist, unsigned seg) -{ - gate_desc s; - - pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); - /* - * does not need to be atomic because it is only done once at - * setup time - */ - write_idt_entry(idt_table, gate, &s); - write_trace_idt_entry(gate, &s); -} - -/* - * This needs to use 'idt_table' rather than 'idt', and - * thus use the _nonmapped_ version of the IDT, as the - * Pentium F0 0F bugfix can have resulted in the mapped - * IDT being write-protected. - */ -#define set_intr_gate_notrace(n, addr) \ - do { \ - BUG_ON((unsigned)n > 0xFF); \ - _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ - __KERNEL_CS); \ - } while (0) - -#define set_intr_gate(n, addr) \ - do { \ - set_intr_gate_notrace(n, addr); \ - _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ - 0, 0, __KERNEL_CS); \ - } while (0) - -extern int first_system_vector; -/* used_vectors is BITMAP for irq is not managed by percpu vector_irq */ extern unsigned long used_vectors[]; -static inline void alloc_system_vector(int vector) -{ - if (!test_bit(vector, used_vectors)) { - set_bit(vector, used_vectors); - if (first_system_vector > vector) - first_system_vector = vector; - } else { - BUG(); - } -} - -#define alloc_intr_gate(n, addr) \ - do { \ - alloc_system_vector(n); \ - set_intr_gate(n, addr); \ - } while (0) - -/* - * This routine sets up an interrupt gate at directory privilege level 3. - */ -static inline void set_system_intr_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS); -} - -static inline void set_system_trap_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS); -} - -static inline void set_trap_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS); -} - -static inline void set_task_gate(unsigned int n, unsigned int gdt_entry) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TASK, (void *)0, 0, 0, (gdt_entry<<3)); -} - -static inline void set_intr_gate_ist(int n, void *addr, unsigned ist) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS); -} - -static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS); -} - #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u32, debug_idt_ctr); static inline bool is_debug_idt_enabled(void) @@ -567,31 +420,6 @@ static inline void load_debug_idt(void) } #endif -#ifdef CONFIG_TRACING -extern atomic_t trace_idt_ctr; -static inline bool is_trace_idt_enabled(void) -{ - if (atomic_read(&trace_idt_ctr)) - return true; - - return false; -} - -static inline void load_trace_idt(void) -{ - load_idt((const struct desc_ptr *)&trace_idt_descr); -} -#else -static inline bool is_trace_idt_enabled(void) -{ - return false; -} - -static inline void load_trace_idt(void) -{ -} -#endif - /* * The load_current_idt() must be called with interrupts disabled * to avoid races. That way the IDT will always be set back to the expected @@ -603,9 +431,25 @@ static inline void load_current_idt(void) { if (is_debug_idt_enabled()) load_debug_idt(); - else if (is_trace_idt_enabled()) - load_trace_idt(); else load_idt((const struct desc_ptr *)&idt_descr); } + +extern void idt_setup_early_handler(void); +extern void idt_setup_early_traps(void); +extern void idt_setup_traps(void); +extern void idt_setup_apic_and_irq_gates(void); + +#ifdef CONFIG_X86_64 +extern void idt_setup_early_pf(void); +extern void idt_setup_ist_traps(void); +extern void idt_setup_debugidt_traps(void); +#else +static inline void idt_setup_early_pf(void) { } +static inline void idt_setup_ist_traps(void) { } +static inline void idt_setup_debugidt_traps(void) { } +#endif + +extern void idt_invalidate(void *addr); + #endif /* _ASM_X86_DESC_H */ diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 4926534..346d252 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -11,34 +11,30 @@ #include <linux/types.h> -/* - * FIXME: Accessing the desc_struct through its fields is more elegant, - * and should be the one valid thing to do. However, a lot of open code - * still touches the a and b accessors, and doing this allow us to do it - * incrementally. We keep the signature as a struct, rather than a union, - * so we can get rid of it transparently in the future -- glommer - */ /* 8 byte segment descriptor */ struct desc_struct { - union { - struct { - unsigned int a; - unsigned int b; - }; - struct { - u16 limit0; - u16 base0; - unsigned base1: 8, type: 4, s: 1, dpl: 2, p: 1; - unsigned limit: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8; - }; - }; + u16 limit0; + u16 base0; + u16 base1: 8, type: 4, s: 1, dpl: 2, p: 1; + u16 limit1: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8; } __attribute__((packed)); -#define GDT_ENTRY_INIT(flags, base, limit) { { { \ - .a = ((limit) & 0xffff) | (((base) & 0xffff) << 16), \ - .b = (((base) & 0xff0000) >> 16) | (((flags) & 0xf0ff) << 8) | \ - ((limit) & 0xf0000) | ((base) & 0xff000000), \ - } } } +#define GDT_ENTRY_INIT(flags, base, limit) \ + { \ + .limit0 = (u16) (limit), \ + .limit1 = ((limit) >> 16) & 0x0F, \ + .base0 = (u16) (base), \ + .base1 = ((base) >> 16) & 0xFF, \ + .base2 = ((base) >> 24) & 0xFF, \ + .type = (flags & 0x0f), \ + .s = (flags >> 4) & 0x01, \ + .dpl = (flags >> 5) & 0x03, \ + .p = (flags >> 7) & 0x01, \ + .avl = (flags >> 12) & 0x01, \ + .l = (flags >> 13) & 0x01, \ + .d = (flags >> 14) & 0x01, \ + .g = (flags >> 15) & 0x01, \ + } enum { GATE_INTERRUPT = 0xE, @@ -47,49 +43,63 @@ enum { GATE_TASK = 0x5, }; -/* 16byte gate */ -struct gate_struct64 { - u16 offset_low; - u16 segment; - unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1; - u16 offset_middle; - u32 offset_high; - u32 zero1; -} __attribute__((packed)); - -#define PTR_LOW(x) ((unsigned long long)(x) & 0xFFFF) -#define PTR_MIDDLE(x) (((unsigned long long)(x) >> 16) & 0xFFFF) -#define PTR_HIGH(x) ((unsigned long long)(x) >> 32) - enum { DESC_TSS = 0x9, DESC_LDT = 0x2, DESCTYPE_S = 0x10, /* !system */ }; -/* LDT or TSS descriptor in the GDT. 16 bytes. */ -struct ldttss_desc64 { - u16 limit0; - u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; - u32 base3; - u32 zero1; +/* LDT or TSS descriptor in the GDT. */ +struct ldttss_desc { + u16 limit0; + u16 base0; + + u16 base1 : 8, type : 5, dpl : 2, p : 1; + u16 limit1 : 4, zero0 : 3, g : 1, base2 : 8; +#ifdef CONFIG_X86_64 + u32 base3; + u32 zero1; +#endif } __attribute__((packed)); +typedef struct ldttss_desc ldt_desc; +typedef struct ldttss_desc tss_desc; + +struct idt_bits { + u16 ist : 3, + zero : 5, + type : 5, + dpl : 2, + p : 1; +} __attribute__((packed)); + +struct gate_struct { + u16 offset_low; + u16 segment; + struct idt_bits bits; + u16 offset_middle; +#ifdef CONFIG_X86_64 + u32 offset_high; + u32 reserved; +#endif +} __attribute__((packed)); + +typedef struct gate_struct gate_desc; + +static inline unsigned long gate_offset(const gate_desc *g) +{ #ifdef CONFIG_X86_64 -typedef struct gate_struct64 gate_desc; -typedef struct ldttss_desc64 ldt_desc; -typedef struct ldttss_desc64 tss_desc; -#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32)) -#define gate_segment(g) ((g).segment) + return g->offset_low | ((unsigned long)g->offset_middle << 16) | + ((unsigned long) g->offset_high << 32); #else -typedef struct desc_struct gate_desc; -typedef struct desc_struct ldt_desc; -typedef struct desc_struct tss_desc; -#define gate_offset(g) (((g).b & 0xffff0000) | ((g).a & 0x0000ffff)) -#define gate_segment(g) ((g).a >> 16) + return g->offset_low | ((unsigned long)g->offset_middle << 16); #endif +} + +static inline unsigned long gate_segment(const gate_desc *g) +{ + return g->segment; +} struct desc_ptr { unsigned short size; diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 07b0695..aa15d1f 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -13,20 +13,14 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR) BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) -BUILD_INTERRUPT3(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR, - smp_irq_move_cleanup_interrupt) -BUILD_INTERRUPT3(reboot_interrupt, REBOOT_VECTOR, smp_reboot_interrupt) +BUILD_INTERRUPT(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR) +BUILD_INTERRUPT(reboot_interrupt, REBOOT_VECTOR) #endif -BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) - #ifdef CONFIG_HAVE_KVM -BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR, - smp_kvm_posted_intr_ipi) -BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, - smp_kvm_posted_intr_wakeup_ipi) -BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR, - smp_kvm_posted_intr_nested_ipi) +BUILD_INTERRUPT(kvm_posted_intr_ipi, POSTED_INTR_VECTOR) +BUILD_INTERRUPT(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR) +BUILD_INTERRUPT(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR) #endif /* @@ -41,6 +35,7 @@ BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR, BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR) BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR) BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR) +BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) #ifdef CONFIG_IRQ_WORK BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index d6dbafb..6dfe366 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -46,26 +46,6 @@ extern asmlinkage void deferred_error_interrupt(void); extern asmlinkage void call_function_interrupt(void); extern asmlinkage void call_function_single_interrupt(void); -#ifdef CONFIG_TRACING -/* Interrupt handlers registered during init_IRQ */ -extern void trace_apic_timer_interrupt(void); -extern void trace_x86_platform_ipi(void); -extern void trace_error_interrupt(void); -extern void trace_irq_work_interrupt(void); -extern void trace_spurious_interrupt(void); -extern void trace_thermal_interrupt(void); -extern void trace_reschedule_interrupt(void); -extern void trace_threshold_interrupt(void); -extern void trace_deferred_error_interrupt(void); -extern void trace_call_function_interrupt(void); -extern void trace_call_function_single_interrupt(void); -#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt -#define trace_reboot_interrupt reboot_interrupt -#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi -#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi -#define trace_kvm_posted_intr_nested_ipi kvm_posted_intr_nested_ipi -#endif /* CONFIG_TRACING */ - #ifdef CONFIG_X86_LOCAL_APIC struct irq_data; struct pci_dev; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 668cca5..9958cee 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -42,10 +42,6 @@ extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); -/* Interrupt vector management */ -extern DECLARE_BITMAP(used_vectors, NR_VECTORS); -extern int vector_used_by_percpu_irq(unsigned int vector); - extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index f706041..ddbb8ea 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -3,9 +3,17 @@ #include <asm/cpufeature.h> +#ifdef CONFIG_X86_LOCAL_APIC static inline bool arch_irq_work_has_interrupt(void) { return boot_cpu_has(X86_FEATURE_APIC); } +extern void arch_irq_work_raise(void); +#else +static inline bool arch_irq_work_has_interrupt(void) +{ + return false; +} +#endif #endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 9ccac19..c25dd22 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -960,11 +960,6 @@ extern void default_banner(void); #define GET_CR2_INTO_RAX \ call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) -#define PARAVIRT_ADJUST_EXCEPTION_FRAME \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \ - CLBR_NONE, \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame)) - #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 9ffc36b..6b64fc6 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -196,9 +196,6 @@ struct pv_irq_ops { void (*safe_halt)(void); void (*halt)(void); -#ifdef CONFIG_X86_64 - void (*adjust_exception_frame)(void); -#endif } __no_randomize_layout; struct pv_mmu_ops { diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 8d3964f..b408b18 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -24,6 +24,9 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_INT80_compat(void); +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +void xen_entry_INT80_compat(void); +#endif #endif void x86_configure_nx(void); diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 1549caa0..066aaf8 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -238,9 +238,7 @@ #ifndef __ASSEMBLY__ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; -#ifdef CONFIG_TRACING -# define trace_early_idt_handler_array early_idt_handler_array -#endif +extern void early_ignore_irq(void); /* * Load a segment. Fall back on loading the zero segment if something goes diff --git a/arch/x86/include/asm/trace/common.h b/arch/x86/include/asm/trace/common.h new file mode 100644 index 0000000..57c8da02 --- /dev/null +++ b/arch/x86/include/asm/trace/common.h @@ -0,0 +1,16 @@ +#ifndef _ASM_TRACE_COMMON_H +#define _ASM_TRACE_COMMON_H + +#ifdef CONFIG_TRACING +DECLARE_STATIC_KEY_FALSE(trace_pagefault_key); +#define trace_pagefault_enabled() \ + static_branch_unlikely(&trace_pagefault_key) +DECLARE_STATIC_KEY_FALSE(trace_resched_ipi_key); +#define trace_resched_ipi_enabled() \ + static_branch_unlikely(&trace_resched_ipi_key) +#else +static inline bool trace_pagefault_enabled(void) { return false; } +static inline bool trace_resched_ipi_enabled(void) { return false; } +#endif + +#endif diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h index 2422b14..5665bf2 100644 --- a/arch/x86/include/asm/trace/exceptions.h +++ b/arch/x86/include/asm/trace/exceptions.h @@ -5,9 +5,10 @@ #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> +#include <asm/trace/common.h> -extern int trace_irq_vector_regfunc(void); -extern void trace_irq_vector_unregfunc(void); +extern int trace_pagefault_reg(void); +extern void trace_pagefault_unreg(void); DECLARE_EVENT_CLASS(x86_exceptions, @@ -37,8 +38,7 @@ DEFINE_EVENT_FN(x86_exceptions, name, \ TP_PROTO(unsigned long address, struct pt_regs *regs, \ unsigned long error_code), \ TP_ARGS(address, regs, error_code), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); + trace_pagefault_reg, trace_pagefault_unreg); DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 32dd6a9..1599d39 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -5,9 +5,12 @@ #define _TRACE_IRQ_VECTORS_H #include <linux/tracepoint.h> +#include <asm/trace/common.h> -extern int trace_irq_vector_regfunc(void); -extern void trace_irq_vector_unregfunc(void); +#ifdef CONFIG_X86_LOCAL_APIC + +extern int trace_resched_ipi_reg(void); +extern void trace_resched_ipi_unreg(void); DECLARE_EVENT_CLASS(x86_irq_vector, @@ -28,15 +31,22 @@ DECLARE_EVENT_CLASS(x86_irq_vector, #define DEFINE_IRQ_VECTOR_EVENT(name) \ DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \ TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); \ +DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ + TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); + +#define DEFINE_RESCHED_IPI_EVENT(name) \ +DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \ + TP_PROTO(int vector), \ TP_ARGS(vector), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); \ + trace_resched_ipi_reg, \ + trace_resched_ipi_unreg); \ DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ TP_PROTO(int vector), \ TP_ARGS(vector), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); - + trace_resched_ipi_reg, \ + trace_resched_ipi_unreg); /* * local_timer - called when entering/exiting a local timer interrupt @@ -45,11 +55,6 @@ DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ DEFINE_IRQ_VECTOR_EVENT(local_timer); /* - * reschedule - called when entering/exiting a reschedule vector handler - */ -DEFINE_IRQ_VECTOR_EVENT(reschedule); - -/* * spurious_apic - called when entering/exiting a spurious apic vector handler */ DEFINE_IRQ_VECTOR_EVENT(spurious_apic); @@ -65,6 +70,7 @@ DEFINE_IRQ_VECTOR_EVENT(error_apic); */ DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi); +#ifdef CONFIG_IRQ_WORK /* * irq_work - called when entering/exiting a irq work interrupt * vector handler @@ -81,6 +87,18 @@ DEFINE_IRQ_VECTOR_EVENT(irq_work); * 4) goto 1 */ TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0); +#endif + +/* + * The ifdef is required because that tracepoint macro hell emits tracepoint + * code in files which include this header even if the tracepoint is not + * enabled. Brilliant stuff that. + */ +#ifdef CONFIG_SMP +/* + * reschedule - called when entering/exiting a reschedule vector handler + */ +DEFINE_RESCHED_IPI_EVENT(reschedule); /* * call_function - called when entering/exiting a call function interrupt @@ -93,24 +111,33 @@ DEFINE_IRQ_VECTOR_EVENT(call_function); * single interrupt vector handler */ DEFINE_IRQ_VECTOR_EVENT(call_function_single); +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD /* * threshold_apic - called when entering/exiting a threshold apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(threshold_apic); +#endif +#ifdef CONFIG_X86_MCE_AMD /* * deferred_error_apic - called when entering/exiting a deferred apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); +#endif +#ifdef CONFIG_X86_THERMAL_VECTOR /* * thermal_apic - called when entering/exiting a thermal apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(thermal_apic); +#endif + +#endif /* CONFIG_X86_LOCAL_APIC */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 01fd0a7..5545f64 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,9 +13,6 @@ asmlinkage void divide_error(void); asmlinkage void debug(void); asmlinkage void nmi(void); asmlinkage void int3(void); -asmlinkage void xen_debug(void); -asmlinkage void xen_int3(void); -asmlinkage void xen_stack_segment(void); asmlinkage void overflow(void); asmlinkage void bounds(void); asmlinkage void invalid_op(void); @@ -38,22 +35,29 @@ asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); -#ifdef CONFIG_TRACING -asmlinkage void trace_page_fault(void); -#define trace_stack_segment stack_segment -#define trace_divide_error divide_error -#define trace_bounds bounds -#define trace_invalid_op invalid_op -#define trace_device_not_available device_not_available -#define trace_coprocessor_segment_overrun coprocessor_segment_overrun -#define trace_invalid_TSS invalid_TSS -#define trace_segment_not_present segment_not_present -#define trace_general_protection general_protection -#define trace_spurious_interrupt_bug spurious_interrupt_bug -#define trace_coprocessor_error coprocessor_error -#define trace_alignment_check alignment_check -#define trace_simd_coprocessor_error simd_coprocessor_error -#define trace_async_page_fault async_page_fault +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +asmlinkage void xen_divide_error(void); +asmlinkage void xen_xendebug(void); +asmlinkage void xen_xenint3(void); +asmlinkage void xen_nmi(void); +asmlinkage void xen_overflow(void); +asmlinkage void xen_bounds(void); +asmlinkage void xen_invalid_op(void); +asmlinkage void xen_device_not_available(void); +asmlinkage void xen_double_fault(void); +asmlinkage void xen_coprocessor_segment_overrun(void); +asmlinkage void xen_invalid_TSS(void); +asmlinkage void xen_segment_not_present(void); +asmlinkage void xen_stack_segment(void); +asmlinkage void xen_general_protection(void); +asmlinkage void xen_page_fault(void); +asmlinkage void xen_spurious_interrupt_bug(void); +asmlinkage void xen_coprocessor_error(void); +asmlinkage void xen_alignment_check(void); +#ifdef CONFIG_X86_MCE +asmlinkage void xen_machine_check(void); +#endif /* CONFIG_X86_MCE */ +asmlinkage void xen_simd_coprocessor_error(void); #endif dotraplinkage void do_divide_error(struct pt_regs *, long); @@ -74,14 +78,6 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); -#ifdef CONFIG_TRACING -dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); -#else -static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error) -{ - do_page_fault(regs, error); -} -#endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); dotraplinkage void do_alignment_check(struct pt_regs *, long); diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 11071fc..9606688 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -552,6 +552,8 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { + u32 *p = (u32 *) &desc; + mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; @@ -559,8 +561,8 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, } else { mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; - mcl->args[2] = desc.a; - mcl->args[3] = desc.b; + mcl->args[2] = *p++; + mcl->args[3] = *p; } trace_xen_mc_entry(mcl, sizeof(maddr) == sizeof(long) ? 2 : 4); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 287eac7..fd0a789 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -42,7 +42,7 @@ CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o obj-$(CONFIG_COMPAT) += signal_compat.o -obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o +obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o @@ -111,6 +111,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o +obj-$(CONFIG_EISA) += eisa.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 98b3dd8..7834f73 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -177,8 +177,6 @@ static int disable_apic_timer __initdata; int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); -int first_system_vector = FIRST_SYSTEM_VECTOR; - /* * Debug level, exported for io_apic.c */ @@ -599,9 +597,13 @@ static const struct x86_cpu_id deadline_match[] = { static void apic_check_deadline_errata(void) { - const struct x86_cpu_id *m = x86_match_cpu(deadline_match); + const struct x86_cpu_id *m; u32 rev; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + m = x86_match_cpu(deadline_match); if (!m) return; @@ -990,8 +992,7 @@ void setup_secondary_APIC_clock(void) */ static void local_apic_timer_interrupt(void) { - int cpu = smp_processor_id(); - struct clock_event_device *evt = &per_cpu(lapic_events, cpu); + struct clock_event_device *evt = this_cpu_ptr(&lapic_events); /* * Normally we should not be here till LAPIC has been initialized but @@ -1005,7 +1006,8 @@ static void local_apic_timer_interrupt(void) * spurious. */ if (!evt->event_handler) { - pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu); + pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", + smp_processor_id()); /* Switch it off */ lapic_timer_shutdown(evt); return; @@ -1040,25 +1042,6 @@ __visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * interrupt lock, which is the WrongThing (tm) to do. */ entering_ack_irq(); - local_apic_timer_interrupt(); - exiting_irq(); - - set_irq_regs(old_regs); -} - -__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - - /* - * NOTE! We'd better ACK the irq immediately, - * because timer handling can be slow. - * - * update_process_times() expects us to have done irq_enter(). - * Besides, if we don't timer interrupts ignore the global - * interrupt lock, which is the WrongThing (tm) to do. - */ - entering_ack_irq(); trace_local_timer_entry(LOCAL_TIMER_VECTOR); local_apic_timer_interrupt(); trace_local_timer_exit(LOCAL_TIMER_VECTOR); @@ -1920,10 +1903,14 @@ void __init register_lapic_address(unsigned long address) /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static void __smp_spurious_interrupt(u8 vector) +__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) { + u8 vector = ~regs->orig_ax; u32 v; + entering_irq(); + trace_spurious_apic_entry(vector); + /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1938,22 +1925,7 @@ static void __smp_spurious_interrupt(u8 vector) /* see sw-dev-man vol 3, chapter 7.4.13.5 */ pr_info("spurious APIC interrupt through vector %02x on CPU#%d, " "should never happen.\n", vector, smp_processor_id()); -} -__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_spurious_interrupt(~regs->orig_ax); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) -{ - u8 vector = ~regs->orig_ax; - - entering_irq(); - trace_spurious_apic_entry(vector); - __smp_spurious_interrupt(vector); trace_spurious_apic_exit(vector); exiting_irq(); } @@ -1961,10 +1933,8 @@ __visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) /* * This interrupt should never happen with our APIC/SMP architecture */ -static void __smp_error_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) { - u32 v; - u32 i = 0; static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ "Receive CS error", /* APIC Error Bit 1 */ @@ -1975,6 +1945,10 @@ static void __smp_error_interrupt(struct pt_regs *regs) "Received illegal vector", /* APIC Error Bit 6 */ "Illegal register address", /* APIC Error Bit 7 */ }; + u32 v, i = 0; + + entering_irq(); + trace_error_apic_entry(ERROR_APIC_VECTOR); /* First tickle the hardware, only then report what went on. -- REW */ if (lapic_get_maxlvt() > 3) /* Due to the Pentium erratum 3AP. */ @@ -1996,20 +1970,6 @@ static void __smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT "\n"); -} - -__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_error_interrupt(regs); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - trace_error_apic_entry(ERROR_APIC_VECTOR); - __smp_error_interrupt(regs); trace_error_apic_exit(ERROR_APIC_VECTOR); exiting_irq(); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 237e9c2..70e48aa 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1243,7 +1243,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) entry.vector, entry.irr, entry.delivery_status); if (ir_entry->format) printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", - buf, (ir_entry->index << 15) | ir_entry->index, + buf, (ir_entry->index2 << 15) | ir_entry->index, ir_entry->zero); else printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index b3af457..88c214e7 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -166,7 +166,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, offset = current_offset; next: vector += 16; - if (vector >= first_system_vector) { + if (vector >= FIRST_SYSTEM_VECTOR) { offset = (offset + 1) % 16; vector = FIRST_EXTERNAL_VECTOR + offset; } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 99332f5..cf42206 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -20,7 +20,6 @@ static char syscalls_ia32[] = { int main(void) { #ifdef CONFIG_PARAVIRT - OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b95cd94..efba8e3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1329,15 +1329,6 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 -struct desc_ptr idt_descr __ro_after_init = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) idt_table, -}; -const struct desc_ptr debug_idt_descr = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) debug_idt_table, -}; - DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 5ce1a56..40e28ed 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -771,24 +771,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) mce_log(&m); } -static inline void __smp_deferred_error_interrupt(void) -{ - inc_irq_stat(irq_deferred_error_count); - deferred_error_int_vector(); -} - asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void) { entering_irq(); - __smp_deferred_error_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) -{ - entering_irq(); trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); - __smp_deferred_error_interrupt(); + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index f7370ab..2da67b7 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -390,26 +390,12 @@ static void unexpected_thermal_interrupt(void) static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; -static inline void __smp_thermal_interrupt(void) -{ - inc_irq_stat(irq_thermal_count); - smp_thermal_vector(); -} - -asmlinkage __visible void __irq_entry -smp_thermal_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_thermal_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry -smp_trace_thermal_interrupt(struct pt_regs *regs) +asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *r) { entering_irq(); trace_thermal_apic_entry(THERMAL_APIC_VECTOR); - __smp_thermal_interrupt(); + inc_irq_stat(irq_thermal_count); + smp_thermal_vector(); trace_thermal_apic_exit(THERMAL_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index bb0e75ee..5e7249e 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -17,24 +17,12 @@ static void default_threshold_interrupt(void) void (*mce_threshold_vector)(void) = default_threshold_interrupt; -static inline void __smp_threshold_interrupt(void) -{ - inc_irq_stat(irq_threshold_count); - mce_threshold_vector(); -} - asmlinkage __visible void __irq_entry smp_threshold_interrupt(void) { entering_irq(); - __smp_threshold_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_threshold_interrupt(void) -{ - entering_irq(); trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); - __smp_threshold_interrupt(); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 70e717f..9fc32651 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -59,13 +59,8 @@ void hyperv_vector_handler(struct pt_regs *regs) void hv_setup_vmbus_irq(void (*handler)(void)) { vmbus_handler = handler; - /* - * Setup the IDT for hypervisor callback. Prevent reallocation - * at module reload. - */ - if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, - hyperv_callback_vector); + /* Setup the IDT for hypervisor callback */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); } void hv_remove_vmbus_irq(void) diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c new file mode 100644 index 0000000..f260e45 --- /dev/null +++ b/arch/x86/kernel/eisa.c @@ -0,0 +1,19 @@ +/* + * EISA specific code + * + * This file is licensed under the GPL V2 + */ +#include <linux/ioport.h> +#include <linux/eisa.h> +#include <linux/io.h> + +static __init int eisa_bus_probe(void) +{ + void __iomem *p = ioremap(0x0FFFD9, 4); + + if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + EISA_bus = 1; + iounmap(p); + return 0; +} +subsys_initcall(eisa_bus_probe); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 538ec01..cf2ce06 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/memblock.h> +#include <asm/desc.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/e820/api.h> @@ -30,6 +31,9 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { cr4_init_shadow(); + + idt_setup_early_handler(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6a193b9..bab4fa5 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -311,8 +311,6 @@ static void __init copy_bootdata(char *real_mode_data) asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) { - int i; - /* * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) @@ -345,9 +343,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) kasan_early_init(); - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handler_array[i]); - load_idt((const struct desc_ptr *)&idt_descr); + idt_setup_early_handler(); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 29da959..9ed3074 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -345,7 +345,6 @@ ENTRY(startup_32_smp) movl %eax,%cr0 lgdt early_gdt_descr - lidt idt_descr ljmp $(__KERNEL_CS),$1f 1: movl $(__KERNEL_DS),%eax # reload all the segment registers movl %eax,%ss # after changing gdt. @@ -378,37 +377,6 @@ ENDPROC(startup_32_smp) */ __INIT setup_once: - /* - * Set up a idt with 256 interrupt gates that push zero if there - * is no error code and then jump to early_idt_handler_common. - * It doesn't actually load the idt - that needs to be done on - * each CPU. Interrupts are enabled elsewhere, when we can be - * relatively sure everything is ok. - */ - - movl $idt_table,%edi - movl $early_idt_handler_array,%eax - movl $NUM_EXCEPTION_VECTORS,%ecx -1: - movl %eax,(%edi) - movl %eax,4(%edi) - /* interrupt gate, dpl=0, present */ - movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $EARLY_IDT_HANDLER_SIZE,%eax - addl $8,%edi - loop 1b - - movl $256 - NUM_EXCEPTION_VECTORS,%ecx - movl $ignore_int,%edx - movl $(__KERNEL_CS << 16),%eax - movw %dx,%ax /* selector = 0x0010 = cs */ - movw $0x8E00,%dx /* interrupt gate - dpl=0, present */ -2: - movl %eax,(%edi) - movl %edx,4(%edi) - addl $8,%edi - loop 2b - #ifdef CONFIG_CC_STACKPROTECTOR /* * Configure the stack canary. The linker can't handle this by @@ -497,8 +465,7 @@ early_idt_handler_common: ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ - ALIGN -ignore_int: +ENTRY(early_ignore_irq) cld #ifdef CONFIG_PRINTK pushl %eax @@ -533,7 +500,8 @@ ignore_int: hlt_loop: hlt jmp hlt_loop -ENDPROC(ignore_int) +ENDPROC(early_ignore_irq) + __INITDATA .align 4 GLOBAL(early_recursion_flag) @@ -622,7 +590,6 @@ int_msg: .data .globl boot_gdt_descr -.globl idt_descr ALIGN # early boot GDT descriptor (must use 1:1 address mapping) @@ -631,11 +598,6 @@ boot_gdt_descr: .word __BOOT_DS+7 .long boot_gdt - __PAGE_OFFSET - .word 0 # 32-bit align idt_desc.address -idt_descr: - .word IDT_ENTRIES*8-1 # idt contains 256 entries - .long idt_table - # boot GDT descriptor (later on used by CPU#0): .word 0 # 32 bit align gdt_desc.address ENTRY(early_gdt_descr) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c new file mode 100644 index 0000000..6107ee1 --- /dev/null +++ b/arch/x86/kernel/idt.c @@ -0,0 +1,371 @@ +/* + * Interrupt descriptor table related code + * + * This file is licensed under the GPL V2 + */ +#include <linux/interrupt.h> + +#include <asm/traps.h> +#include <asm/proto.h> +#include <asm/desc.h> + +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + +#define DPL0 0x0 +#define DPL3 0x3 + +#define DEFAULT_STACK 0 + +#define G(_vector, _addr, _ist, _type, _dpl, _segment) \ + { \ + .vector = _vector, \ + .bits.ist = _ist, \ + .bits.type = _type, \ + .bits.dpl = _dpl, \ + .bits.p = 1, \ + .addr = _addr, \ + .segment = _segment, \ + } + +/* Interrupt gate */ +#define INTG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate */ +#define SYSG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Interrupt gate with interrupt stack */ +#define ISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate with interrupt stack */ +#define SISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Task gate */ +#define TSKG(_vector, _gdt) \ + G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3) + +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_idts[] = { + INTG(X86_TRAP_DB, debug), + SYSG(X86_TRAP_BP, int3), +#ifdef CONFIG_X86_32 + INTG(X86_TRAP_PF, page_fault), +#endif +}; + +/* + * The default IDT entries which are set up in trap_init() before + * cpu_init() is invoked. Interrupt stacks cannot be used at that point and + * the traps which use them are reinitialized with IST after cpu_init() has + * set up TSS. + */ +static const __initdata struct idt_data def_idts[] = { + INTG(X86_TRAP_DE, divide_error), + INTG(X86_TRAP_NMI, nmi), + INTG(X86_TRAP_BR, bounds), + INTG(X86_TRAP_UD, invalid_op), + INTG(X86_TRAP_NM, device_not_available), + INTG(X86_TRAP_OLD_MF, coprocessor_segment_overrun), + INTG(X86_TRAP_TS, invalid_TSS), + INTG(X86_TRAP_NP, segment_not_present), + INTG(X86_TRAP_SS, stack_segment), + INTG(X86_TRAP_GP, general_protection), + INTG(X86_TRAP_SPURIOUS, spurious_interrupt_bug), + INTG(X86_TRAP_MF, coprocessor_error), + INTG(X86_TRAP_AC, alignment_check), + INTG(X86_TRAP_XF, simd_coprocessor_error), + +#ifdef CONFIG_X86_32 + TSKG(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS), +#else + INTG(X86_TRAP_DF, double_fault), +#endif + INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_NMI, nmi), + INTG(X86_TRAP_BP, int3), + +#ifdef CONFIG_X86_MCE + INTG(X86_TRAP_MC, &machine_check), +#endif + + SYSG(X86_TRAP_OF, overflow), +#if defined(CONFIG_IA32_EMULATION) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), +#elif defined(CONFIG_X86_32) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), +#endif +}; + +/* + * The APIC and SMP idt entries + */ +static const __initdata struct idt_data apic_idts[] = { +#ifdef CONFIG_SMP + INTG(RESCHEDULE_VECTOR, reschedule_interrupt), + INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), + INTG(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt), + INTG(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt), + INTG(REBOOT_VECTOR, reboot_interrupt), +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR + INTG(THERMAL_APIC_VECTOR, thermal_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_THRESHOLD + INTG(THRESHOLD_APIC_VECTOR, threshold_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_AMD + INTG(DEFERRED_ERROR_VECTOR, deferred_error_interrupt), +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + INTG(LOCAL_TIMER_VECTOR, apic_timer_interrupt), + INTG(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), +# ifdef CONFIG_HAVE_KVM + INTG(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), + INTG(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), + INTG(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), +# endif +# ifdef CONFIG_IRQ_WORK + INTG(IRQ_WORK_VECTOR, irq_work_interrupt), +# endif + INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt), + INTG(ERROR_APIC_VECTOR, error_interrupt), +#endif +}; + +#ifdef CONFIG_X86_64 +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_pf_idts[] = { + INTG(X86_TRAP_PF, page_fault), +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +static const __initdata struct idt_data dbg_idts[] = { + INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_BP, int3), +}; +#endif + +/* Must be page-aligned because the real IDT is used in a fixmap. */ +gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; + +struct desc_ptr idt_descr __ro_after_init = { + .size = (IDT_ENTRIES * 2 * sizeof(unsigned long)) - 1, + .address = (unsigned long) idt_table, +}; + +#ifdef CONFIG_X86_64 +/* No need to be aligned, but done to keep all IDTs defined the same way. */ +gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; + +/* + * The exceptions which use Interrupt stacks. They are setup after + * cpu_init() when the TSS has been initialized. + */ +static const __initdata struct idt_data ist_idts[] = { + ISTG(X86_TRAP_DB, debug, DEBUG_STACK), + ISTG(X86_TRAP_NMI, nmi, NMI_STACK), + SISTG(X86_TRAP_BP, int3, DEBUG_STACK), + ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK), +#ifdef CONFIG_X86_MCE + ISTG(X86_TRAP_MC, &machine_check, MCE_STACK), +#endif +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +const struct desc_ptr debug_idt_descr = { + .size = IDT_ENTRIES * 16 - 1, + .address = (unsigned long) debug_idt_table, +}; +#endif + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + +static void +idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) +{ + gate_desc desc; + + for (; size > 0; t++, size--) { + idt_init_desc(&desc, t); + write_idt_entry(idt, t->vector, &desc); + if (sys) + set_bit(t->vector, used_vectors); + } +} + +static void set_intr_gate(unsigned int n, const void *addr) +{ + struct idt_data data; + + BUG_ON(n > 0xFF); + + memset(&data, 0, sizeof(data)); + data.vector = n; + data.addr = addr; + data.segment = __KERNEL_CS; + data.bits.type = GATE_INTERRUPT; + data.bits.p = 1; + + idt_setup_from_table(idt_table, &data, 1, false); +} + +/** + * idt_setup_early_traps - Initialize the idt table with early traps + * + * On X8664 these traps do not use interrupt stacks as they can't work + * before cpu_init() is invoked and sets up TSS. The IST variants are + * installed after that. + */ +void __init idt_setup_early_traps(void) +{ + idt_setup_from_table(idt_table, early_idts, ARRAY_SIZE(early_idts), + true); + load_idt(&idt_descr); +} + +/** + * idt_setup_traps - Initialize the idt table with default traps + */ +void __init idt_setup_traps(void) +{ + idt_setup_from_table(idt_table, def_idts, ARRAY_SIZE(def_idts), true); +} + +#ifdef CONFIG_X86_64 +/** + * idt_setup_early_pf - Initialize the idt table with early pagefault handler + * + * On X8664 this does not use interrupt stacks as they can't work before + * cpu_init() is invoked and sets up TSS. The IST variant is installed + * after that. + * + * FIXME: Why is 32bit and 64bit installing the PF handler at different + * places in the early setup code? + */ +void __init idt_setup_early_pf(void) +{ + idt_setup_from_table(idt_table, early_pf_idts, + ARRAY_SIZE(early_pf_idts), true); +} + +/** + * idt_setup_ist_traps - Initialize the idt table with traps using IST + */ +void __init idt_setup_ist_traps(void) +{ + idt_setup_from_table(idt_table, ist_idts, ARRAY_SIZE(ist_idts), true); +} + +/** + * idt_setup_debugidt_traps - Initialize the debug idt table with debug traps + */ +void __init idt_setup_debugidt_traps(void) +{ + memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); + + idt_setup_from_table(debug_idt_table, dbg_idts, ARRAY_SIZE(dbg_idts), false); +} +#endif + +/** + * idt_setup_apic_and_irq_gates - Setup APIC/SMP and normal interrupt gates + */ +void __init idt_setup_apic_and_irq_gates(void) +{ + int i = FIRST_EXTERNAL_VECTOR; + void *entry; + + idt_setup_from_table(idt_table, apic_idts, ARRAY_SIZE(apic_idts), true); + + for_each_clear_bit_from(i, used_vectors, FIRST_SYSTEM_VECTOR) { + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); + } + + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { +#ifdef CONFIG_X86_LOCAL_APIC + set_bit(i, used_vectors); + set_intr_gate(i, spurious_interrupt); +#else + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); +#endif + } +} + +/** + * idt_setup_early_handler - Initializes the idt table with early handlers + */ +void __init idt_setup_early_handler(void) +{ + int i; + + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) + set_intr_gate(i, early_idt_handler_array[i]); +#ifdef CONFIG_X86_32 + for ( ; i < NR_VECTORS; i++) + set_intr_gate(i, early_ignore_irq); +#endif + load_idt(&idt_descr); +} + +/** + * idt_invalidate - Invalidate interrupt descriptor table + * @addr: The virtual address of the 'invalid' IDT + */ +void idt_invalidate(void *addr) +{ + struct desc_ptr idt = { .address = (unsigned long) addr, .size = 0 }; + + load_idt(&idt); +} + +void __init update_intr_gate(unsigned int n, const void *addr) +{ + if (WARN_ON_ONCE(!test_bit(n, used_vectors))) + return; + set_intr_gate(n, addr); +} + +void alloc_intr_gate(unsigned int n, const void *addr) +{ + BUG_ON(n < FIRST_SYSTEM_VECTOR); + if (!test_and_set_bit(n, used_vectors)) + set_intr_gate(n, addr); +} diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4ed0aba..52089c0 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -29,9 +29,6 @@ EXPORT_PER_CPU_SYMBOL(irq_regs); atomic_t irq_err_count; -/* Function pointer for generic interrupt vector handling */ -void (*x86_platform_ipi_callback)(void) = NULL; - /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -87,13 +84,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); seq_puts(p, " APIC ICR read retries\n"); -#endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_puts(p, " Platform interrupts\n"); } +#endif #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) @@ -183,9 +180,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_irq_work_irqs; sum += irq_stats(cpu)->icr_read_retry_count; -#endif if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; +#endif #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -259,26 +256,26 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) return 1; } +#ifdef CONFIG_X86_LOCAL_APIC +/* Function pointer for generic interrupt vector handling */ +void (*x86_platform_ipi_callback)(void) = NULL; /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -void __smp_x86_platform_ipi(void) -{ - inc_irq_stat(x86_platform_ipis); - - if (x86_platform_ipi_callback) - x86_platform_ipi_callback(); -} - __visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); entering_ack_irq(); - __smp_x86_platform_ipi(); + trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); + inc_irq_stat(x86_platform_ipis); + if (x86_platform_ipi_callback) + x86_platform_ipi_callback(); + trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); exiting_irq(); set_irq_regs(old_regs); } +#endif #ifdef CONFIG_HAVE_KVM static void dummy_handler(void) {} @@ -334,19 +331,6 @@ __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) } #endif -__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - - entering_ack_irq(); - trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); - __smp_x86_platform_ipi(); - trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); - exiting_irq(); - set_irq_regs(old_regs); -} - -EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU @@ -431,7 +415,7 @@ int check_irq_vectors_for_cpu_disable(void) * this w/o holding vector_lock. */ for (vector = FIRST_EXTERNAL_VECTOR; - vector < first_system_vector; vector++) { + vector < FIRST_SYSTEM_VECTOR; vector++) { if (!test_bit(vector, used_vectors) && IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { if (++count == this_count) diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 2754878..70dee05 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -11,35 +11,23 @@ #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> -static inline void __smp_irq_work_interrupt(void) -{ - inc_irq_stat(apic_irq_work_irqs); - irq_work_run(); -} - +#ifdef CONFIG_X86_LOCAL_APIC __visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_irq_work_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_irq_work_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); - __smp_irq_work_interrupt(); + inc_irq_stat(apic_irq_work_irqs); + irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); exiting_irq(); } void arch_irq_work_raise(void) { -#ifdef CONFIG_X86_LOCAL_APIC if (!arch_irq_work_has_interrupt()) return; apic->send_IPI_self(IRQ_WORK_VECTOR); apic_wait_icr_idle(); -#endif } +#endif diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index c7fd185..1add9e0 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -55,18 +55,6 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; -int vector_used_by_percpu_irq(unsigned int vector) -{ - int cpu; - - for_each_online_cpu(cpu) { - if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) - return 1; - } - - return 0; -} - void __init init_ISA_irqs(void) { struct irq_chip *chip = legacy_pic->chip; @@ -99,100 +87,12 @@ void __init init_IRQ(void) x86_init.irqs.intr_init(); } -static void __init smp_intr_init(void) -{ -#ifdef CONFIG_SMP - /* - * The reschedule interrupt is a CPU-to-CPU reschedule-helper - * IPI, driven by wakeup. - */ - alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - - /* IPI for generic function call */ - alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); - - /* IPI for generic single function call */ - alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, - call_function_single_interrupt); - - /* Low priority IPI to cleanup after moving an irq */ - set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); - set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors); - - /* IPI used for rebooting/stopping */ - alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt); -#endif /* CONFIG_SMP */ -} - -static void __init apic_intr_init(void) -{ - smp_intr_init(); - -#ifdef CONFIG_X86_THERMAL_VECTOR - alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); -#endif -#ifdef CONFIG_X86_MCE_THRESHOLD - alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); -#endif - -#ifdef CONFIG_X86_MCE_AMD - alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - /* self generated IPI for local APIC timer */ - alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - - /* IPI for X86 platform specific use */ - alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi); -#ifdef CONFIG_HAVE_KVM - /* IPI for KVM to deliver posted interrupt */ - alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); - /* IPI for KVM to deliver interrupt to wake up tasks */ - alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); - /* IPI for KVM to deliver nested posted interrupt */ - alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi); -#endif - - /* IPI vectors for APIC spurious and error interrupts */ - alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); - alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - - /* IRQ work interrupts: */ -# ifdef CONFIG_IRQ_WORK - alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt); -# endif - -#endif -} - void __init native_init_IRQ(void) { - int i; - /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - apic_intr_init(); - - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - i = FIRST_EXTERNAL_VECTOR; -#ifndef CONFIG_X86_LOCAL_APIC -#define first_system_vector NR_VECTORS -#endif - for_each_clear_bit_from(i, used_vectors, first_system_vector) { - /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - set_intr_gate(i, irq_entries_start + - 8 * (i - FIRST_EXTERNAL_VECTOR)); - } -#ifdef CONFIG_X86_LOCAL_APIC - for_each_clear_bit_from(i, used_vectors, NR_VECTORS) - set_intr_gate(i, spurious_interrupt); -#endif + idt_setup_apic_and_irq_gates(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d04e30e..874827b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -263,7 +263,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) switch (kvm_read_and_reset_pf_reason()) { default: - trace_do_page_fault(regs, error_code); + do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ @@ -455,7 +455,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, async_page_fault); + update_intr_gate(X86_TRAP_PF, async_page_fault); } void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8c53c5d..00bc751 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -26,18 +26,6 @@ #include <asm/set_memory.h> #include <asm/debugreg.h> -static void set_idt(void *newidt, __u16 limit) -{ - struct desc_ptr curidt; - - /* ia32 supports unaliged loads & stores */ - curidt.size = limit; - curidt.address = (unsigned long)newidt; - - load_idt(&curidt); -} - - static void set_gdt(void *newgdt, __u16 limit) { struct desc_ptr curgdt; @@ -245,7 +233,7 @@ void machine_kexec(struct kimage *image) * If you want to load them you must set up your own idt & gdt. */ set_gdt(phys_to_virt(0), 0); - set_idt(phys_to_virt(0), 0); + idt_invalidate(phys_to_virt(0)); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index bc0a849..a14df9e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -319,9 +319,6 @@ __visible struct pv_irq_ops pv_irq_ops = { .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = paravirt_nop, -#endif }; __visible struct pv_cpu_ops pv_cpu_ops = { diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index a56bf60..54984b1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -38,8 +38,6 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static const struct desc_ptr no_idt = {}; - /* * This is set if we need to go through the 'emergency' path. * When machine_emergency_restart() is called, we may be on @@ -638,7 +636,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_TRIPLE: - load_idt(&no_idt); + idt_invalidate(NULL); __asm__ __volatile__("int3"); /* We're probably dead after this, but... */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 022ebdd..9cc16a8 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -900,7 +900,7 @@ void __init setup_arch(char **cmdline_p) */ olpc_ofw_detect(); - early_trap_init(); + idt_setup_early_traps(); early_cpu_init(); early_ioremap_init(); @@ -1171,7 +1171,7 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); - early_trap_pf_init(); + idt_setup_early_pf(); /* * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 10edd1e..6e8fcb6f 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -155,13 +155,10 @@ static void __init pcpup_populate_pte(unsigned long addr) static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 - struct desc_struct gdt; + struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu), + 0xFFFFF); - pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, - 0x2 | DESCTYPE_S, 0x8); - gdt.s = 1; - write_gdt_entry(get_cpu_gdt_rw(cpu), - GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S); #endif } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index d798c0d..5c574df 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -254,84 +254,45 @@ finish: } /* - * Reschedule call back. + * Reschedule call back. KVM uses this interrupt to force a cpu out of + * guest mode */ -static inline void __smp_reschedule_interrupt(void) -{ - inc_irq_stat(irq_resched_count); - scheduler_ipi(); -} - __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); - __smp_reschedule_interrupt(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} - -__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs) -{ - /* - * Need to call irq_enter() before calling the trace point. - * __smp_reschedule_interrupt() calls irq_enter/exit() too (in - * scheduler_ipi(). This is OK, since those functions are allowed - * to nest. - */ - ipi_entering_ack_irq(); - trace_reschedule_entry(RESCHEDULE_VECTOR); - __smp_reschedule_interrupt(); - trace_reschedule_exit(RESCHEDULE_VECTOR); - exiting_irq(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} + inc_irq_stat(irq_resched_count); -static inline void __smp_call_function_interrupt(void) -{ - generic_smp_call_function_interrupt(); - inc_irq_stat(irq_call_count); + if (trace_resched_ipi_enabled()) { + /* + * scheduler_ipi() might call irq_enter() as well, but + * nested calls are fine. + */ + irq_enter(); + trace_reschedule_entry(RESCHEDULE_VECTOR); + scheduler_ipi(); + trace_reschedule_exit(RESCHEDULE_VECTOR); + irq_exit(); + return; + } + scheduler_ipi(); } __visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_call_function_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry -smp_trace_call_function_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); - __smp_call_function_interrupt(); - trace_call_function_exit(CALL_FUNCTION_VECTOR); - exiting_irq(); -} - -static inline void __smp_call_function_single_interrupt(void) -{ - generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); -} - -__visible void __irq_entry -smp_call_function_single_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); - __smp_call_function_single_interrupt(); + generic_smp_call_function_interrupt(); + trace_call_function_exit(CALL_FUNCTION_VECTOR); exiting_irq(); } -__visible void __irq_entry -smp_trace_call_function_single_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r) { ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); - __smp_call_function_single_interrupt(); + inc_irq_stat(irq_call_count); + generic_smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); exiting_irq(); } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index dcd699b..a106b97 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -93,7 +93,7 @@ static void set_tls_desc(struct task_struct *p, int idx, while (n-- > 0) { if (LDT_empty(info) || LDT_zero(info)) { - desc->a = desc->b = 0; + memset(desc, 0, sizeof(*desc)); } else { fill_ldt(desc, info); diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 1551513..c6636d1 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -4,57 +4,38 @@ * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com> * */ -#include <asm/hw_irq.h> -#include <asm/desc.h> +#include <linux/jump_label.h> #include <linux/atomic.h> -atomic_t trace_idt_ctr = ATOMIC_INIT(0); -struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) trace_idt_table }; - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; +#include <asm/hw_irq.h> +#include <asm/desc.h> -static int trace_irq_vector_refcount; -static DEFINE_MUTEX(irq_vector_mutex); +DEFINE_STATIC_KEY_FALSE(trace_pagefault_key); -static void set_trace_idt_ctr(int val) +int trace_pagefault_reg(void) { - atomic_set(&trace_idt_ctr, val); - /* Ensure the trace_idt_ctr is set before sending IPI */ - wmb(); + static_branch_inc(&trace_pagefault_key); + return 0; } -static void switch_idt(void *arg) +void trace_pagefault_unreg(void) { - unsigned long flags; - - local_irq_save(flags); - load_current_idt(); - local_irq_restore(flags); + static_branch_dec(&trace_pagefault_key); } -int trace_irq_vector_regfunc(void) +#ifdef CONFIG_SMP + +DEFINE_STATIC_KEY_FALSE(trace_resched_ipi_key); + +int trace_resched_ipi_reg(void) { - mutex_lock(&irq_vector_mutex); - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(1); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - trace_irq_vector_refcount++; - mutex_unlock(&irq_vector_mutex); + static_branch_inc(&trace_resched_ipi_key); return 0; } -void trace_irq_vector_unregfunc(void) +void trace_resched_ipi_unreg(void) { - mutex_lock(&irq_vector_mutex); - trace_irq_vector_refcount--; - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(0); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - mutex_unlock(&irq_vector_mutex); + static_branch_dec(&trace_resched_ipi_key); } + +#endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf54309..34ea365 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -38,11 +38,6 @@ #include <linux/smp.h> #include <linux/io.h> -#ifdef CONFIG_EISA -#include <linux/ioport.h> -#include <linux/eisa.h> -#endif - #if defined(CONFIG_EDAC) #include <linux/edac.h> #endif @@ -70,20 +65,13 @@ #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <asm/proto.h> - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> #include <asm/proto.h> #endif -/* Must be page-aligned because the real IDT is used in a fixmap. */ -gate_desc idt_table[NR_VECTORS] __page_aligned_bss; - DECLARE_BITMAP(used_vectors, NR_VECTORS); -EXPORT_SYMBOL_GPL(used_vectors); static inline void cond_local_irq_enable(struct pt_regs *regs) { @@ -935,87 +923,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) } #endif -/* Set of traps needed for early debugging. */ -void __init early_trap_init(void) -{ - /* - * Don't use IST to set DEBUG_STACK as it doesn't work until TSS - * is ready in cpu_init() <-- trap_init(). Before trap_init(), - * CPU runs at ring 0 so it is impossible to hit an invalid - * stack. Using the original stack works well enough at this - * early stage. DEBUG_STACK will be equipped after cpu_init() in - * trap_init(). - * - * We don't need to set trace_idt_table like set_intr_gate(), - * since we don't have trace_debug and it will be reset to - * 'debug' in trap_init() by set_intr_gate_ist(). - */ - set_intr_gate_notrace(X86_TRAP_DB, debug); - /* int3 can be called from all */ - set_system_intr_gate(X86_TRAP_BP, &int3); -#ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif - load_idt(&idt_descr); -} - -void __init early_trap_pf_init(void) -{ -#ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif -} - void __init trap_init(void) { - int i; - -#ifdef CONFIG_EISA - void __iomem *p = early_ioremap(0x0FFFD9, 4); - - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) - EISA_bus = 1; - early_iounmap(p, 4); -#endif - - set_intr_gate(X86_TRAP_DE, divide_error); - set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); - /* int4 can be called from all */ - set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, bounds); - set_intr_gate(X86_TRAP_UD, invalid_op); - set_intr_gate(X86_TRAP_NM, device_not_available); -#ifdef CONFIG_X86_32 - set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); -#else - set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); -#endif - set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, invalid_TSS); - set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate(X86_TRAP_SS, stack_segment); - set_intr_gate(X86_TRAP_GP, general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, coprocessor_error); - set_intr_gate(X86_TRAP_AC, alignment_check); -#ifdef CONFIG_X86_MCE - set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); -#endif - set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); - - /* Reserve all the builtin and the syscall vector: */ - for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) - set_bit(i, used_vectors); - -#ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif - -#ifdef CONFIG_X86_32 - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif + idt_setup_traps(); /* * Set the IDT descriptor to a fixed read-only location, so that the @@ -1030,20 +940,9 @@ void __init trap_init(void) */ cpu_init(); - /* - * X86_TRAP_DB and X86_TRAP_BP have been set - * in early_trap_init(). However, ITS works only after - * cpu_init() loads TSS. See comments in early_trap_init(). - */ - set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); - /* int3 can be called from all */ - set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + idt_setup_ist_traps(); x86_init.irqs.trap_init(); -#ifdef CONFIG_X86_64 - memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); - set_nmi_gate(X86_TRAP_DB, &debug); - set_nmi_gate(X86_TRAP_BP, &int3); -#endif + idt_setup_debugidt_traps(); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d409009..70b90c0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8779,7 +8779,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) vector = exit_intr_info & INTR_INFO_VECTOR_MASK; desc = (gate_desc *)vmx->host_idt_base + vector; - entry = gate_offset(*desc); + entry = gate_offset(desc); asm volatile( #ifdef CONFIG_X86_64 "mov %%" _ASM_SP ", %[sp]\n\t" diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 0203bae..d4a7df2 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -147,7 +147,7 @@ void math_emulate(struct math_emu_info *info) } code_descriptor = FPU_get_ldt_descriptor(FPU_CS); - if (SEG_D_SIZE(code_descriptor)) { + if (code_descriptor.d) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ addr_modes.default_mode = SEG32; @@ -155,11 +155,10 @@ void math_emulate(struct math_emu_info *info) /* 16 bit protected mode */ addr_modes.default_mode = PM16; } - FPU_EIP += code_base = SEG_BASE_ADDR(code_descriptor); - code_limit = code_base - + (SEG_LIMIT(code_descriptor) + - 1) * SEG_GRANULARITY(code_descriptor) - - 1; + FPU_EIP += code_base = seg_get_base(&code_descriptor); + code_limit = seg_get_limit(&code_descriptor) + 1; + code_limit *= seg_get_granularity(&code_descriptor); + code_limit += code_base - 1; if (code_limit < code_base) code_limit = 0xffffffff; } diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index a179254..699f329 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -34,17 +34,43 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) return ret; } -#define SEG_D_SIZE(x) ((x).b & (3 << 21)) -#define SEG_G_BIT(x) ((x).b & (1 << 23)) -#define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) -#define SEG_286_MODE(x) ((x).b & ( 0xff000000 | 0xf0000 | (1 << 23))) -#define SEG_BASE_ADDR(s) (((s).b & 0xff000000) \ - | (((s).b & 0xff) << 16) | ((s).a >> 16)) -#define SEG_LIMIT(s) (((s).b & 0xff0000) | ((s).a & 0xffff)) -#define SEG_EXECUTE_ONLY(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 11)) -#define SEG_WRITE_PERM(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 9)) -#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ - == (1 << 10)) +#define SEG_TYPE_WRITABLE (1U << 1) +#define SEG_TYPE_EXPANDS_DOWN (1U << 2) +#define SEG_TYPE_EXECUTE (1U << 3) +#define SEG_TYPE_EXPAND_MASK (SEG_TYPE_EXPANDS_DOWN | SEG_TYPE_EXECUTE) +#define SEG_TYPE_EXECUTE_MASK (SEG_TYPE_WRITABLE | SEG_TYPE_EXECUTE) + +static inline unsigned long seg_get_base(struct desc_struct *d) +{ + unsigned long base = (unsigned long)d->base2 << 24; + + return base | ((unsigned long)d->base1 << 16) | d->base0; +} + +static inline unsigned long seg_get_limit(struct desc_struct *d) +{ + return ((unsigned long)d->limit1 << 16) | d->limit0; +} + +static inline unsigned long seg_get_granularity(struct desc_struct *d) +{ + return d->g ? 4096 : 1; +} + +static inline bool seg_expands_down(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXPAND_MASK) == SEG_TYPE_EXPANDS_DOWN; +} + +static inline bool seg_execute_only(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_EXECUTE; +} + +static inline bool seg_writable(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE; +} #define I387 (¤t->thread.fpu.state) #define FPU_info (I387->soft.info) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index b8ef9f9d2..c48967c 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -159,17 +159,18 @@ static long pm_address(u_char FPU_modrm, u_char segment, } descriptor = FPU_get_ldt_descriptor(addr->selector); - base_address = SEG_BASE_ADDR(descriptor); + base_address = seg_get_base(&descriptor); address = base_address + offset; - limit = base_address - + (SEG_LIMIT(descriptor) + 1) * SEG_GRANULARITY(descriptor) - 1; + limit = seg_get_limit(&descriptor) + 1; + limit *= seg_get_granularity(&descriptor); + limit += base_address - 1; if (limit < base_address) limit = 0xffffffff; - if (SEG_EXPAND_DOWN(descriptor)) { - if (SEG_G_BIT(descriptor)) + if (seg_expands_down(&descriptor)) { + if (descriptor.g) { seg_top = 0xffffffff; - else { + } else { seg_top = base_address + (1 << 20); if (seg_top < base_address) seg_top = 0xffffffff; @@ -182,8 +183,8 @@ static long pm_address(u_char FPU_modrm, u_char segment, (address > limit) || (address < base_address) ? 0 : ((limit - address) >= 254 ? 255 : limit - address + 1); } - if (SEG_EXECUTE_ONLY(descriptor) || - (!SEG_WRITE_PERM(descriptor) && (FPU_modrm & FPU_WRITE_BIT))) { + if (seg_execute_only(&descriptor) || + (!seg_writable(&descriptor) && (FPU_modrm & FPU_WRITE_BIT))) { access_limit = 0; } return address; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 0cdf14c..b836a72 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1258,10 +1258,6 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. - * - * This function must have noinline because both callers - * {,trace_}do_page_fault() have notrace on. Having this an actual function - * guarantees there's a function trace entry. */ static noinline void __do_page_fault(struct pt_regs *regs, unsigned long error_code, @@ -1494,27 +1490,6 @@ good_area: } NOKPROBE_SYMBOL(__do_page_fault); -dotraplinkage void notrace -do_page_fault(struct pt_regs *regs, unsigned long error_code) -{ - unsigned long address = read_cr2(); /* Get the faulting address */ - enum ctx_state prev_state; - - /* - * We must have this function tagged with __kprobes, notrace and call - * read_cr2() before calling anything else. To avoid calling any kind - * of tracing machinery before we've observed the CR2 value. - * - * exception_{enter,exit}() contain all sorts of tracepoints. - */ - - prev_state = exception_enter(); - __do_page_fault(regs, error_code, address); - exception_exit(prev_state); -} -NOKPROBE_SYMBOL(do_page_fault); - -#ifdef CONFIG_TRACING static nokprobe_inline void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, unsigned long error_code) @@ -1525,22 +1500,24 @@ trace_page_fault_entries(unsigned long address, struct pt_regs *regs, trace_page_fault_kernel(address, regs, error_code); } +/* + * We must have this function blacklisted from kprobes, tagged with notrace + * and call read_cr2() before calling anything else. To avoid calling any + * kind of tracing machinery before we've observed the CR2 value. + * + * exception_{enter,exit}() contains all sorts of tracepoints. + */ dotraplinkage void notrace -trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) +do_page_fault(struct pt_regs *regs, unsigned long error_code) { - /* - * The exception_enter and tracepoint processing could - * trigger another page faults (user space callchain - * reading) and destroy the original cr2 value, so read - * the faulting address now. - */ - unsigned long address = read_cr2(); + unsigned long address = read_cr2(); /* Get the faulting address */ enum ctx_state prev_state; prev_state = exception_enter(); - trace_page_fault_entries(address, regs, error_code); + if (trace_pagefault_enabled()) + trace_page_fault_entries(address, regs, error_code); + __do_page_fault(regs, error_code, address); exception_exit(prev_state); } -NOKPROBE_SYMBOL(trace_do_page_fault); -#endif /* CONFIG_TRACING */ +NOKPROBE_SYMBOL(do_page_fault); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 6c279c8..ae2a2e2 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -501,7 +501,7 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) static inline bool desc_equal(const struct desc_struct *d1, const struct desc_struct *d2) { - return d1->a == d2->a && d1->b == d2->b; + return !memcmp(d1, d2, sizeof(*d1)); } static void load_TLS_descriptor(struct thread_struct *t, @@ -586,59 +586,91 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, preempt_enable(); } +#ifdef CONFIG_X86_64 +struct trap_array_entry { + void (*orig)(void); + void (*xen)(void); + bool ist_okay; +}; + +static struct trap_array_entry trap_array[] = { + { debug, xen_xendebug, true }, + { int3, xen_xenint3, true }, + { double_fault, xen_double_fault, true }, +#ifdef CONFIG_X86_MCE + { machine_check, xen_machine_check, true }, +#endif + { nmi, xen_nmi, true }, + { overflow, xen_overflow, false }, +#ifdef CONFIG_IA32_EMULATION + { entry_INT80_compat, xen_entry_INT80_compat, false }, +#endif + { page_fault, xen_page_fault, false }, + { divide_error, xen_divide_error, false }, + { bounds, xen_bounds, false }, + { invalid_op, xen_invalid_op, false }, + { device_not_available, xen_device_not_available, false }, + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, + { invalid_TSS, xen_invalid_TSS, false }, + { segment_not_present, xen_segment_not_present, false }, + { stack_segment, xen_stack_segment, false }, + { general_protection, xen_general_protection, false }, + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, + { coprocessor_error, xen_coprocessor_error, false }, + { alignment_check, xen_alignment_check, false }, + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, +}; + +static bool get_trap_addr(void **addr, unsigned int ist) +{ + unsigned int nr; + bool ist_okay = false; + + /* + * Replace trap handler addresses by Xen specific ones. + * Check for known traps using IST and whitelist them. + * The debugger ones are the only ones we care about. + * Xen will handle faults like double_fault, * so we should never see + * them. Warn if there's an unexpected IST-using fault handler. + */ + for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) { + struct trap_array_entry *entry = trap_array + nr; + + if (*addr == entry->orig) { + *addr = entry->xen; + ist_okay = entry->ist_okay; + break; + } + } + + if (WARN_ON(ist != 0 && !ist_okay)) + return false; + + return true; +} +#endif + static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { unsigned long addr; - if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) + if (val->bits.type != GATE_TRAP && val->bits.type != GATE_INTERRUPT) return 0; info->vector = vector; - addr = gate_offset(*val); + addr = gate_offset(val); #ifdef CONFIG_X86_64 - /* - * Look for known traps using IST, and substitute them - * appropriately. The debugger ones are the only ones we care - * about. Xen will handle faults like double_fault, - * so we should never see them. Warn if - * there's an unexpected IST-using fault handler. - */ - if (addr == (unsigned long)debug) - addr = (unsigned long)xen_debug; - else if (addr == (unsigned long)int3) - addr = (unsigned long)xen_int3; - else if (addr == (unsigned long)stack_segment) - addr = (unsigned long)xen_stack_segment; - else if (addr == (unsigned long)double_fault) { - /* Don't need to handle these */ + if (!get_trap_addr((void **)&addr, val->bits.ist)) return 0; -#ifdef CONFIG_X86_MCE - } else if (addr == (unsigned long)machine_check) { - /* - * when xen hypervisor inject vMCE to guest, - * use native mce handler to handle it - */ - ; -#endif - } else if (addr == (unsigned long)nmi) - /* - * Use the native version as well. - */ - ; - else { - /* Some other trap using IST? */ - if (WARN_ON(val->ist != 0)) - return 0; - } #endif /* CONFIG_X86_64 */ info->address = addr; - info->cs = gate_segment(*val); - info->flags = val->dpl; + info->cs = gate_segment(val); + info->flags = val->bits.dpl; /* interrupt gates clear IF */ - if (val->type == GATE_INTERRUPT) + if (val->bits.type == GATE_INTERRUPT) info->flags |= 1 << 2; return 1; diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 33e9295..d4eff56 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -123,9 +123,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = { .safe_halt = xen_safe_halt, .halt = xen_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = xen_adjust_exception_frame, -#endif }; void __init xen_init_irq_ops(void) diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 3a3b6a2..dae2cc3 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -16,11 +16,42 @@ #include <linux/linkage.h> -ENTRY(xen_adjust_exception_frame) - mov 8+0(%rsp), %rcx - mov 8+8(%rsp), %r11 - ret $16 -ENDPROC(xen_adjust_exception_frame) +.macro xen_pv_trap name +ENTRY(xen_\name) + pop %rcx + pop %r11 + jmp \name +END(xen_\name) +.endm + +xen_pv_trap divide_error +xen_pv_trap debug +xen_pv_trap xendebug +xen_pv_trap int3 +xen_pv_trap xenint3 +xen_pv_trap nmi +xen_pv_trap overflow +xen_pv_trap bounds +xen_pv_trap invalid_op +xen_pv_trap device_not_available +xen_pv_trap double_fault +xen_pv_trap coprocessor_segment_overrun +xen_pv_trap invalid_TSS +xen_pv_trap segment_not_present +xen_pv_trap stack_segment +xen_pv_trap general_protection +xen_pv_trap page_fault +xen_pv_trap spurious_interrupt_bug +xen_pv_trap coprocessor_error +xen_pv_trap alignment_check +#ifdef CONFIG_X86_MCE +xen_pv_trap machine_check +#endif /* CONFIG_X86_MCE */ +xen_pv_trap simd_coprocessor_error +#ifdef CONFIG_IA32_EMULATION +xen_pv_trap entry_INT80_compat +#endif +xen_pv_trap hypervisor_callback hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 70301ac..c8a6d22 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -138,7 +138,6 @@ __visible void xen_restore_fl_direct(unsigned long); __visible void xen_iret(void); __visible void xen_sysret32(void); __visible void xen_sysret64(void); -__visible void xen_adjust_exception_frame(void); extern int xen_panic_handler_init(void); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 2d43118..1ab4bd1 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1653,10 +1653,8 @@ void xen_callback_vector(void) return; } pr_info("Xen HVM callback vector for event delivery is enabled\n"); - /* in the restore case the vector has already been allocated */ - if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, - xen_hvm_callback_vector); + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, + xen_hvm_callback_vector); } } #else |