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 e007887a33b0..926c2cc4facc 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 48ef7bb32c42..8a13d468635a 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 ca0b250eefc4..49167258d587 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 4b86d8da3ea3..e26c25ca7756 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 726355ce8497..1911310959f8 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 d0a21b12dd58..1a2ba368da39 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 49265345d4d2..346d252029b7 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_bi |