ptrace.c

linux内核的改写可以进行新的读写命令同时也可以在linux下体验编译内核的快感 这是我们os的一个project

/* ptrace.c */
/* By Ross Biro 1/23/92 */
/*
 * Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>

#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>

/*
 * does not yet catch signals sent when the child dies.
 * in exit.c or in signal.c.
 */

/* determines which flags the user has access to. */
/* 1 = access 0 = no access */



/******************LKRR start 0372180****************/

#define FLAG_MASK 0x00044dd5/***  EFLAG访问权限设定  ***/

/* set's the trap flag. */
#define TRAP_FLAG 0x100/***  设置陷阱标志  ***/



/******************LKRR end 0372180****************/


/*
 * Offset of eflags on child stack..
 */
#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))/*  用于清除TF标志  */

static inline struct pt_regs *get_child_regs(struct task_struct *task)
{
	void *stack_top = (void *)task->thread.esp0;
	return stack_top - sizeof(struct pt_regs);
}

/*
 * this routine will get a word off of the processes privileged stack. 
 * the offset is how far from the base addr as stored in the TSS.  
 * this routine assumes that all the privileged stacks are in our
 * data space.
 */   


/******************LKRR start 0372180****************/

static inline int get_stack_long(struct task_struct *task, int offset)
{
	unsigned char *stack;

	stack = (unsigned char *)task->thread.esp0;/*  获得ESP0寄存器值  */
	stack += offset;/*  加偏移量  */
	return (*((int *)stack));
}

/*
 * this routine will put a word on the processes privileged stack. 
 * the offset is how far from the base addr as stored in the TSS.  
 * this routine assumes that all the privileged stacks are in our
 * data space.
 */
static inline int put_stack_long(struct task_struct *task, int offset,
	unsigned long data)
{
	unsigned char * stack;

	stack = (unsigned char *) task->thread.esp0;/*  获得ESP0寄存器值  */
	stack += offset;/*  加偏移量  */
	*(unsigned long *) stack = data;
	return 0;
}

/***读写所有i386用户寄存器
使用ptrace的PTRACE_GETFPREGS和PTRACE_PUTFPREGS
读写所有i387浮点寄存器。***/
static int putreg(struct task_struct *child,
	unsigned long regno, unsigned long value)
{
	switch (regno >> 2) {//参数regno，表示寄存器的序号
		case FS:
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.fs = value;
			return 0;
		case GS:
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.gs = value;
			return 0;
		case DS:
		case ES:
			if (value && (value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			break;
		case SS:
		case CS:
			if ((value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			break;
		case EFL:
			value &= FLAG_MASK;
//函数get_stack_long()和put_stack_long()为对子进程核心堆栈的操作
			value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
			break;
	}
	if (regno > GS*4)
		regno -= 2*4;
	put_stack_long(child, regno - sizeof(struct pt_regs), value);
	return 0;
}

/***作用和putreg相仿，读写所有i386用户寄存器
使用ptrace的PTRACE_GETFPREGS和PTRACE_PUTFPREGS
读写所有i387浮点寄存器。***/
static unsigned long getreg(struct task_struct *child,
	unsigned long regno)
{
	unsigned long retval = ~0UL;

	switch (regno >> 2) {
		case FS:
			retval = child->thread.fs;
			break;
		case GS:
			retval = child->thread.gs;
			break;
		case DS:
		case ES:
		case SS:
		case CS:
			retval = 0xffff;
			/* fall through */
		default:
			if (regno > GS*4)
				regno -= 2*4;
			regno = regno - sizeof(struct pt_regs);
//函数get_stack_long()和put_stack_long()为对子进程核心堆栈的操作
			retval &= get_stack_long(child, regno);
	}
	return retval;
}


/******************LKRR end 0372180****************/


#define LDT_SEGMENT 4

static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_regs *regs)
{
	unsigned long addr, seg;

	addr = regs->eip;
	seg = regs->xcs & 0xffff;
	if (regs->eflags & VM_MASK) {
		addr = (addr & 0xffff) + (seg << 4);
		return addr;
	}

	/*
	 * We'll assume that the code segments in the GDT
	 * are all zero-based. That is largely true: the
	 * TLS segments are used for data, and the PNPBIOS
	 * and APM bios ones we just ignore here.
	 */
	if (seg & LDT_SEGMENT) {
		u32 *desc;
		unsigned long base;

		down(&child->mm->context.sem);
		desc = child->mm->context.ldt + (seg & ~7);
		base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000);

		/* 16-bit code segment? */
		if (!((desc[1] >> 22) & 1))
			addr &= 0xffff;
		addr += base;
		up(&child->mm->context.sem);
	}
	return addr;
}

static inline int is_at_popf(struct task_struct *child, struct pt_regs *regs)
{
	int i, copied;
	unsigned char opcode[16];
	unsigned long addr = convert_eip_to_linear(child, regs);//调用转换函数

	copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
	for (i = 0; i < copied; i++) {
		switch (opcode[i]) {
		/* popf */
		case 0x9d:
			return 1;
		/* opcode and address size prefixes */
		case 0x66: case 0x67:
			continue;
		/* irrelevant prefixes (segment overrides and repeats) */
		case 0x26: case 0x2e:
		case 0x36: case 0x3e:
		case 0x64: case 0x65:
		case 0xf0: case 0xf2: case 0xf3:
			continue;

		/*
		 * pushf: NOTE! We should probably not let
		 * the user see the TF bit being set. But
		 * it's more pain than it's worth to avoid
		 * it, and a debugger could emulate this
		 * all in user space if it _really_ cares.
		 */
		case 0x9c:
		default:
			return 0;
		}
	}
	return 0;
}

/******************LKRR start 0372180****************/


/***在处理器状态字（PSW）中设置Trace bit位，让子进程单步执行***/
static void set_singlestep(struct task_struct *child)
{
	struct pt_regs *regs = get_child_regs(child);//调用函数获取子函数标志

	/*
	 * Always set TIF_SINGLESTEP - this guarantees that 
	 * we single-step system calls etc..  This will also
	 * cause us to set TF when returning to user mode.
	 */
	set_tsk_thread_flag(child, TIF_SINGLESTEP);//设置标志函数

	/*
	 * If TF was already set, don't do anything else
	 */
	if (regs->eflags & TRAP_FLAG)
		return;

	/* Set TF on the kernel stack.. */
	regs->eflags |= TRAP_FLAG;

	/*
	 * ..but if TF is changed by the instruction we will trace,
	 * don't mark it as being "us" that set it, so that we
	 * won't clear it by hand later.
	 */
	if (is_at_popf(child, regs))//进行判断，如果在栈顶需要进行pop操作，则返回
		return;
	
	child->ptrace |= PT_DTRACE;
}

static void clear_singlestep(struct task_struct *child)//用于清楚状态字的设置
{
	/* Always clear TIF_SINGLESTEP... */
	clear_tsk_thread_flag(child, TIF_SINGLESTEP);

	/* But touch TF only if it was set by us.. */
	if (child->ptrace & PT_DTRACE) {
		struct pt_regs *regs = get_child_regs(child);
		regs->eflags &= ~TRAP_FLAG;
		child->ptrace &= ~PT_DTRACE;
	}
}

/******************LKRR end 0372180****************/




/*
 * Called by kernel/ptrace.c when detaching..
 *
 * Make sure the single step bit is not set.
 */
void ptrace_disable(struct task_struct *child)
{ 
	clear_singlestep(child);
}

/*
 * Perform get_thread_area on behalf of the traced child.
 */
static int


/******************LKRR start 0372180****************/

/***此函数负责对线程空间的传递操作***/

ptrace_get_thread_area(struct task_struct *child,
		       int idx, struct user_desc __user *user_desc)
{
	struct user_desc info;
	struct desc_struct *desc;

/*
 * Get the current Thread-Local Storage area:
 */

#define GET_BASE(desc) ( \
	(((desc)->a >> 16) & 0x0000ffff) | \
	(((desc)->b << 16) & 0x00ff0000) | \
	( (desc)->b        & 0xff000000)   )

#define GET_LIMIT(desc) ( \
	((desc)->a & 0x0ffff) | \
	 ((desc)->b & 0xf0000) )

#define GET_32BIT(desc)		(((desc)->b >> 22) & 1)
#define GET_CONTENTS(desc)	(((desc)->b >> 10) & 3)
#define GET_WRITABLE(desc)	(((desc)->b >>  9) & 1)
#define GET_LIMIT_PAGES(desc)	(((desc)->b >> 23) & 1)
#define GET_PRESENT(desc)	(((desc)->b >> 15) & 1)
#define GET_USEABLE(desc)	(((desc)->b >> 20) & 1)

	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
		return -EINVAL;

	desc = child->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;

	info.entry_number = idx;
	info.base_addr = GET_BASE(desc);
	info.limit = GET_LIMIT(desc);
	info.seg_32bit = GET_32BIT(desc);
	info.contents = GET_CONTENTS(desc);
	info.read_exec_only = !GET_WRITABLE(desc);
	info.limit_in_pages = GET_LIMIT_PAGES(desc);
	info.seg_not_present = !GET_PRESENT(desc);
	info.useable = GET_USEABLE(desc);

	if (copy_to_user(user_desc, &info, sizeof(info)))
		return -EFAULT;

	return 0;
}

/*
 * Perform set_thread_area on behalf of the traced child.
 */
static int
ptrace_set_thread_area(struct task_struct *child,
		       int idx, struct user_desc __user *user_desc)
{
	struct user_desc info;
	struct desc_struct *desc;

	if (copy_from_user(&info, user_desc, sizeof(info)))
		return -EFAULT;

	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
		return -EINVAL;

	desc = child->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
	if (LDT_empty(&info)) {
		desc->a = 0;
		desc->b = 0;
	} else {
		desc->a = LDT_entry_a(&info);
		desc->b = LDT_entry_b(&info);
	}

	return 0;
}

/***************LKRR end 0372180*************/


/***************LKRR end 0372180*************/

/***接下来，就进入ptrace最为关键的函数部分，
其核心函数sys_ptrace函叔：
 	sys_ptrace函数，完成ptrace系统调用的代码。
 	为完成sys_ptrace功能所需调用的一些辅助
 	函数 	寄存器读写函数和内存读写函数。
 	信号处理函数中，对被调试进程的处