ptrace.c

linux-2.6.15.6

/* ptrace.c */
/* By Ross Biro 1/23/92 */
/*
 * Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 * 
 * x86-64 port 2000-2002 Andi Kleen
 */

#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>
#include <asm/proto.h>
#include <asm/ia32.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 */
#define FLAG_MASK 0x44dd5UL

/* set's the trap flag. */
#define TRAP_FLAG 0x100UL

/*
 * eflags and offset of eflags on child stack..
 */
#define EFLAGS offsetof(struct pt_regs, eflags)
#define EFL_OFFSET ((int)(EFLAGS-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.
 */   
static inline unsigned long get_stack_long(struct task_struct *task, int offset)
{
	unsigned char *stack;

	stack = (unsigned char *)task->thread.rsp0;
	stack += offset;
	return (*((unsigned long *)stack));
}

static inline struct pt_regs *get_child_regs(struct task_struct *task)
{
	struct pt_regs *regs = (void *)task->thread.rsp0;
	return regs - 1;
}

/*
 * 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 long put_stack_long(struct task_struct *task, int offset,
	unsigned long data)
{
	unsigned char * stack;

	stack = (unsigned char *) task->thread.rsp0;
	stack += offset;
	*(unsigned long *) stack = data;
	return 0;
}

#define LDT_SEGMENT 4

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

	addr = regs->rip;
	seg = regs->cs & 0xffff;

	/*
	 * 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 int is_at_popf(struct task_struct *child, struct pt_regs *regs)
{
	int i, copied;
	unsigned char opcode[16];
	unsigned long addr = convert_rip_to_linear(child, regs);

	copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
	for (i = 0; i < copied; i++) {
		switch (opcode[i]) {
		/* popf */
		case 0x9d:
			return 1;

			/* CHECKME: 64 65 */

		/* 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;

		/* REX prefixes */
		case 0x40 ... 0x4f:
			continue;

			/* CHECKME: f0, f2, f3 */

		/*
		 * 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;
}

static void set_singlestep(struct task_struct *child)
{
	struct pt_regs *regs = get_child_regs(child);

	/*
	 * 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);

	/*
	 * 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.
	 *
	 * AK: this is not enough, LAHF and IRET can change TF in user space too.
	 */
	if (is_at_popf(child, regs))
		return;

	child->ptrace |= PT_DTRACE;
}

static void clear_singlestep(struct task_struct *child)
{
	/* 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;
	}
}

/*
 * 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);
}

static int putreg(struct task_struct *child,
	unsigned long regno, unsigned long value)
{
	unsigned long tmp; 
	
	/* Some code in the 64bit emulation may not be 64bit clean.
	   Don't take any chances. */
	if (test_tsk_thread_flag(child, TIF_IA32))
		value &= 0xffffffff;
	switch (regno) {
		case offsetof(struct user_regs_struct,fs):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.fsindex = value & 0xffff; 
			return 0;
		case offsetof(struct user_regs_struct,gs):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.gsindex = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,ds):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.ds = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,es): 
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.es = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,ss):
			if ((value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,fs_base):
			if (value >= TASK_SIZE_OF(child))
				return -EIO;
			child->thread.fs = value;
			return 0;
		case offsetof(struct user_regs_struct,gs_base):
			if (value >= TASK_SIZE_OF(child))
				return -EIO;
			child->thread.gs = value;
			return 0;
		case offsetof(struct user_regs_struct, eflags):
			value &= FLAG_MASK;
			tmp = get_stack_long(child, EFL_OFFSET); 
			tmp &= ~FLAG_MASK; 
			value |= tmp;
			break;
		case offsetof(struct user_regs_struct,cs): 
			if ((value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			break;
		case offsetof(struct user_regs_struct, rip):
			/* Check if the new RIP address is canonical */
			if (value >= TASK_SIZE_OF(child))
				return -EIO;
			break;
	}
	put_stack_long(child, regno - sizeof(struct pt_regs), value);
	return 0;
}

static unsigned long getreg(struct task_struct *child, unsigned long regno)
{
	unsigned long val;
	switch (regno) {
		case offsetof(struct user_regs_struct, fs):
			return child->thread.fsindex;
		case offsetof(struct user_regs_struct, gs):
			return child->thread.gsindex;
		case offsetof(struct user_regs_struct, ds):
			return child->thread.ds;
		case offsetof(struct user_regs_struct, es):
			return child->thread.es; 
		case offsetof(struct user_regs_struct, fs_base):
			return child->thread.fs;
		case offsetof(struct user_regs_struct, gs_base):
			return child->thread.gs;
		default:
			regno = regno - sizeof(struct pt_regs);
			val = get_stack_long(child, regno);
			if (test_tsk_thread_flag(child, TIF_IA32))
				val &= 0xffffffff;
			return val;
	}

}

long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{