【Linux内核分析】【第五周作业】系统调用源码分析

内核代码理解起来还是太困难了，需要对体系结构有很强的了解才行，这周作业就简单写一下吧。

系统调用经过了如下的流程
1) 初始化
首先，在内核初始化时，前几周已经讲到了通过start_kernel进行全局的初始化工作。
start_kernel中会调用trap_init来进行中断相关的初始化工作。

    setup_log_buf(0);
    pidhash_init();
    vfs_caches_init_early();
    sort_main_extable();
    trap_init();
    mm_init();

trap_init源码如下所示，

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_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
    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, ia32_syscall);
    set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif

#ifdef CONFIG_X86_32
    set_system_trap_gate(SYSCALL_VECTOR, &system_call);
    set_bit(SYSCALL_VECTOR, used_vectors);
#endif

    /*
     * Should be a barrier for any external CPU state:
     */
    cpu_init();

    x86_init.irqs.trap_init();
}

可以看到，trap_init中主要对中断门进行了初始化工作。 对于X86结构来说，中断向量表中1-32与0x80分配给内部中断，内部中断又分为“异常” “陷阱” (?)，具体分配情况如代码所示，

/* Interrupts/Exceptions */
enum {
    X86_TRAP_DE = 0,    /* 0, Divide-by-zero */
    X86_TRAP_DB,        /* 1, Debug */
    X86_TRAP_NMI,        /* 2, Non-maskable Interrupt */
    X86_TRAP_BP,        /* 3, Breakpoint */
    X86_TRAP_OF,        /* 4, Overflow */
    X86_TRAP_BR,        /* 5, Bound Range Exceeded */
    X86_TRAP_UD,        /* 6, Invalid Opcode */
    X86_TRAP_NM,        /* 7, Device Not Available */
    X86_TRAP_DF,        /* 8, Double Fault */
    X86_TRAP_OLD_MF,    /* 9, Coprocessor Segment Overrun */
    X86_TRAP_TS,        /* 10, Invalid TSS */
    X86_TRAP_NP,        /* 11, Segment Not Present */
    X86_TRAP_SS,        /* 12, Stack Segment Fault */
    X86_TRAP_GP,        /* 13, General Protection Fault */
    X86_TRAP_PF,        /* 14, Page Fault */
    X86_TRAP_SPURIOUS,    /* 15, Spurious Interrupt */
    X86_TRAP_MF,        /* 16, x87 Floating-Point Exception */
    X86_TRAP_AC,        /* 17, Alignment Check */
    X86_TRAP_MC,        /* 18, Machine Check */
    X86_TRAP_XF,        /* 19, SIMD Floating-Point Exception */
    X86_TRAP_IRET = 32,    /* 32, IRET Exception */
};

举一例来说， set_intr_gate(X86_TRAP_PF, &page_fault);
就是将page_fault这个函数，注册给缺页异常。 当系统内产生缺页异常时，则调用page_fault。
当然，在Trap_init中，我们关注的是  set_system_trap_gate(SYSCALL_VECTOR, &system_call);
对比一下，setset_intr_gate与set_system_trap_gate的实现，发现他们最终都是操作了IDT（Interrupt Descriptor Table--中断描述表），来完成的中断服务程序函数与中断号的绑定。

set_intr_gate
set_intr_gate_ist                              
set_system_intr_gate  ---> _set_gate ---> pack_gate / write_idt_entry

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);
}

static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate)
{
    memcpy(&idt[entry], gate, sizeof(*gate));
}

关于IDT的结构，如下

/* 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;
        };
    };
}

base就是中断服务程序isr的地址。

（逐项分析一下idt的内容，比较一下异同）

顺便提一句，另外还有听着相似的gdt，ldt两个概念，分别是
GDT：Global Descriptor Table   --全局描述表
LDT：Local Descriptor Table    --局部描述表
后续，在评论中会补充一下这两个表的含义。

=====
分析 system_call

未完成