diff options
Diffstat (limited to 'arch/x86/include/asm/desc.h')
| -rw-r--r-- | arch/x86/include/asm/desc.h | 484 |
1 files changed, 209 insertions, 275 deletions
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index b90e5dfeee46..ec95fe44fa3a 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -1,10 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DESC_H #define _ASM_X86_DESC_H #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> +#include <asm/fixmap.h> +#include <asm/irq_vectors.h> +#include <asm/cpu_entry_area.h> +#include <linux/debug_locks.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -17,11 +22,13 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; + /* Set the ACCESS bit so it can be mapped RO */ + desc->type |= 1; 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; @@ -34,49 +41,61 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->l = 0; } -extern struct desc_ptr idt_descr; -extern gate_desc idt_table[]; -extern struct desc_ptr debug_idt_descr; -extern gate_desc debug_idt_table[]; - struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); -static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) +/* Provide the original GDT */ +static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } -#ifdef CONFIG_X86_64 +/* Provide the current original GDT */ +static inline struct desc_struct *get_current_gdt_rw(void) +{ + return this_cpu_ptr(&gdt_page)->gdt; +} -static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, - unsigned dpl, unsigned ist, unsigned seg) +/* Provide the fixmap address of the remapped GDT */ +static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { - gate->offset_low = PTR_LOW(func); - 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); + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } -#else -static inline void pack_gate(gate_desc *gate, unsigned char type, - unsigned long base, unsigned dpl, unsigned flags, - unsigned short seg) +/* Provide the current read-only GDT */ +static inline struct desc_struct *get_current_gdt_ro(void) +{ + return get_cpu_gdt_ro(smp_processor_id()); +} + +/* Provide the physical address of the GDT page. */ +static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) { - gate->a = (seg << 16) | (base & 0xffff); - gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8); + return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } +static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, + unsigned dpl, unsigned ist, unsigned seg) +{ + 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->bits.ist = ist; + gate->reserved = 0; + gate->offset_high = (u32) (func >> 32); +#else + gate->segment = seg; + gate->bits.ist = 0; #endif +} static inline int desc_empty(const void *ptr) { @@ -85,7 +104,7 @@ static inline int desc_empty(const void *ptr) return !(desc[0] | desc[1]); } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define load_TR_desc() native_load_tr_desc() @@ -95,7 +114,6 @@ static inline int desc_empty(const void *ptr) #define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) #define store_gdt(dtr) native_store_gdt(dtr) -#define store_idt(dtr) native_store_idt(dtr) #define store_tr(tr) (tr = native_store_tr()) #define load_TLS(t, cpu) native_load_tls(t, cpu) @@ -112,7 +130,7 @@ static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { } -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) @@ -140,53 +158,32 @@ 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) +static inline void set_tssldt_descriptor(void *d, unsigned long addr, + unsigned type, unsigned size) { - 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) -{ -#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 } -static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { - struct desc_struct *d = get_cpu_gdt_table(cpu); + struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; - /* - * sizeof(unsigned long) coming from an extra "long" at the end - * of the iobitmap. See tss_struct definition in processor.h - * - * -1? seg base+limit should be pointing to the address of the - * last valid byte - */ set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, - IO_BITMAP_OFFSET + IO_BITMAP_BYTES + - sizeof(unsigned long) - 1); + __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } @@ -202,23 +199,18 @@ static inline void native_set_ldt(const void *addr, unsigned int entries) set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } -static inline void native_load_tr_desc(void) -{ - asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); -} - static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); } -static inline void native_load_idt(const struct desc_ptr *dtr) +static __always_inline void native_load_idt(const struct desc_ptr *dtr) { asm volatile("lidt %0"::"m" (*dtr)); } @@ -228,288 +220,230 @@ static inline void native_store_gdt(struct desc_ptr *dtr) asm volatile("sgdt %0":"=m" (*dtr)); } -static inline void native_store_idt(struct desc_ptr *dtr) +static inline void store_idt(struct desc_ptr *dtr) { asm volatile("sidt %0":"=m" (*dtr)); } -static inline unsigned long native_store_tr(void) +static inline void native_gdt_invalidate(void) { - unsigned long tr; - - asm volatile("str %0":"=r" (tr)); + const struct desc_ptr invalid_gdt = { + .address = 0, + .size = 0 + }; - return tr; + native_load_gdt(&invalid_gdt); } -static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) +static inline void native_idt_invalidate(void) { - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - unsigned int i; + const struct desc_ptr invalid_idt = { + .address = 0, + .size = 0 + }; - for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) - gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; -} - -#define _LDT_empty(info) \ - ((info)->base_addr == 0 && \ - (info)->limit == 0 && \ - (info)->contents == 0 && \ - (info)->read_exec_only == 1 && \ - (info)->seg_32bit == 0 && \ - (info)->limit_in_pages == 0 && \ - (info)->seg_not_present == 1 && \ - (info)->useable == 0) - -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif - -static inline void clear_LDT(void) -{ - set_ldt(NULL, 0); + native_load_idt(&invalid_idt); } /* - * load one particular LDT into the current CPU + * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is + * a read-only remapping. To prevent a page fault, the GDT is switched to the + * original writeable version when needed. */ -static inline void load_LDT_nolock(mm_context_t *pc) +#ifdef CONFIG_X86_64 +static inline void native_load_tr_desc(void) { - set_ldt(pc->ldt, pc->size); -} + struct desc_ptr gdt; + int cpu = raw_smp_processor_id(); + bool restore = 0; + struct desc_struct *fixmap_gdt; -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} + native_store_gdt(&gdt); + fixmap_gdt = get_cpu_gdt_ro(cpu); -static inline unsigned long get_desc_base(const struct desc_struct *desc) -{ - return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); + /* + * If the current GDT is the read-only fixmap, swap to the original + * writeable version. Swap back at the end. + */ + if (gdt.address == (unsigned long)fixmap_gdt) { + load_direct_gdt(cpu); + restore = 1; + } + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); + if (restore) + load_fixmap_gdt(cpu); } - -static inline void set_desc_base(struct desc_struct *desc, unsigned long base) +#else +static inline void native_load_tr_desc(void) { - desc->base0 = base & 0xffff; - desc->base1 = (base >> 16) & 0xff; - desc->base2 = (base >> 24) & 0xff; + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +#endif -static inline unsigned long get_desc_limit(const struct desc_struct *desc) +static inline unsigned long native_store_tr(void) { - return desc->limit0 | (desc->limit << 16); -} + unsigned long tr; -static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) -{ - desc->limit0 = limit & 0xffff; - desc->limit = (limit >> 16) & 0xf; + asm volatile("str %0":"=r" (tr)); + + return tr; } -#ifdef CONFIG_X86_64 -static inline void set_nmi_gate(int gate, void *addr) +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { - gate_desc s; + struct desc_struct *gdt = get_cpu_gdt_rw(cpu); + unsigned int i; - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(debug_idt_table, gate, &s); + for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) + gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } -#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); -} -#else -static inline void write_trace_idt_entry(int entry, const gate_desc *gate) -{ -} -#endif +DECLARE_PER_CPU(bool, __tss_limit_invalid); -static inline void _set_gate(int gate, unsigned type, void *addr, - unsigned dpl, unsigned ist, unsigned seg) +static inline void force_reload_TR(void) { - gate_desc s; + struct desc_struct *d = get_current_gdt_rw(); + tss_desc tss; + + memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); - 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 + * LTR requires an available TSS, and the TSS is currently + * busy. Make it be available so that LTR will work. */ - write_idt_entry(idt_table, gate, &s); - write_trace_idt_entry(gate, &s); + tss.type = DESC_TSS; + write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); + + load_TR_desc(); + this_cpu_write(__tss_limit_invalid, false); } /* - * 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. + * Call this if you need the TSS limit to be correct, which should be the case + * if and only if you have TIF_IO_BITMAP set or you're switching to a task + * with TIF_IO_BITMAP set. */ -static inline void set_intr_gate(unsigned int n, void *addr) +static inline void refresh_tss_limit(void) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS); -} + DEBUG_LOCKS_WARN_ON(preemptible()); -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(); - } + if (unlikely(this_cpu_read(__tss_limit_invalid))) + force_reload_TR(); } -#ifdef CONFIG_TRACING -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(trace_idt_table, gate, &s); -} - -static inline void __trace_alloc_intr_gate(unsigned int n, void *addr) -{ - trace_set_intr_gate(n, addr); -} -#else -static inline void trace_set_intr_gate(unsigned int gate, void *addr) +/* + * If you do something evil that corrupts the cached TSS limit (I'm looking + * at you, VMX exits), call this function. + * + * The optimization here is that the TSS limit only matters for Linux if the + * IO bitmap is in use. If the TSS limit gets forced to its minimum value, + * everything works except that IO bitmap will be ignored and all CPL 3 IO + * instructions will #GP, which is exactly what we want for normal tasks. + */ +static inline void invalidate_tss_limit(void) { -} + DEBUG_LOCKS_WARN_ON(preemptible()); -#define __trace_alloc_intr_gate(n, addr) -#endif - -static inline void __alloc_intr_gate(unsigned int n, void *addr) -{ - set_intr_gate(n, addr); + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(__tss_limit_invalid, true); } -#define alloc_intr_gate(n, addr) \ - do { \ - alloc_system_vector(n); \ - __alloc_intr_gate(n, addr); \ - __trace_alloc_intr_gate(n, trace_##addr); \ - } while (0) +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ + ((info)->base_addr == 0 && \ + (info)->limit == 0 && \ + (info)->contents == 0 && \ + (info)->read_exec_only == 1 && \ + (info)->seg_32bit == 0 && \ + (info)->limit_in_pages == 0 && \ + (info)->seg_not_present == 1 && \ + (info)->useable == 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) +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS); + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); } -static inline void set_system_trap_gate(unsigned int n, void *addr) +static inline void clear_LDT(void) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS); + set_ldt(NULL, 0); } -static inline void set_trap_gate(unsigned int n, void *addr) +static inline unsigned long get_desc_base(const struct desc_struct *desc) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS); + return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); } -static inline void set_task_gate(unsigned int n, unsigned int gdt_entry) +static inline void set_desc_base(struct desc_struct *desc, unsigned long base) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TASK, (void *)0, 0, 0, (gdt_entry<<3)); + desc->base0 = base & 0xffff; + desc->base1 = (base >> 16) & 0xff; + desc->base2 = (base >> 24) & 0xff; } -static inline void set_intr_gate_ist(int n, void *addr, unsigned ist) +static inline unsigned long get_desc_limit(const struct desc_struct *desc) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS); + return desc->limit0 | (desc->limit1 << 16); } -static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist) +static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS); + desc->limit0 = limit & 0xffff; + desc->limit1 = (limit >> 16) & 0xf; } -#ifdef CONFIG_X86_64 -DECLARE_PER_CPU(u32, debug_idt_ctr); -static inline bool is_debug_idt_enabled(void) +static inline void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) { - if (this_cpu_read(debug_idt_ctr)) - return true; + BUG_ON(n > 0xFF); - return false; + memset(data, 0, sizeof(*data)); + data->vector = n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p = 1; } -static inline void load_debug_idt(void) -{ - load_idt((const struct desc_ptr *)&debug_idt_descr); -} -#else -static inline bool is_debug_idt_enabled(void) +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) { - return false; -} + unsigned long addr = (unsigned long) d->addr; -static inline void load_debug_idt(void) -{ -} + 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 +} -#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; +extern unsigned long system_vectors[]; - return false; -} +extern void load_current_idt(void); +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); +extern bool idt_is_f00f_address(unsigned long address); -static inline void load_trace_idt(void) -{ - load_idt((const struct desc_ptr *)&trace_idt_descr); -} +#ifdef CONFIG_X86_64 +extern void idt_setup_early_pf(void); #else -static inline bool is_trace_idt_enabled(void) -{ - return false; -} - -static inline void load_trace_idt(void) -{ -} +static inline void idt_setup_early_pf(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 - * descriptor. It's also called when a CPU is being initialized, and - * that doesn't need to disable interrupts, as nothing should be - * bothering the CPU then. - */ -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_invalidate(void); + #endif /* _ASM_X86_DESC_H */ |
