ptrace.c

/*
 * linux/kernel/ptrace.c
 *
 * (C) Copyright 1999 Linus Torvalds
 *
 * Common interfaces for "ptrace()" which we do not want
 * to continually duplicate across every architecture.
 */

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/signal.h>

#include <asm/pgtable.h>
#include <asm/uaccess.h>

/*
 * ptrace a task: make the debugger its new parent and
 * move it to the ptrace list.
 *
 * Must be called with the tasklist lock write-held.
 */
void __ptrace_link(task_t *child, task_t *new_parent)
{
	if (!list_empty(&child->ptrace_list))
		BUG();
	if (child->parent == new_parent)
		return;
	list_add(&child->ptrace_list, &child->parent->ptrace_children);
	REMOVE_LINKS(child);
	child->parent = new_parent;
	SET_LINKS(child);
}
 
/*
 * Turn a tracing stop into a normal stop now, since with no tracer there
 * would be no way to wake it up with SIGCONT or SIGKILL.  If there was a
 * signal sent that would resume the child, but didn't because it was in
 * TASK_TRACED, resume it now.
 * Requires that irqs be disabled.
 */
void ptrace_untrace(task_t *child)
{
	spin_lock(&child->sighand->siglock);
	if (child->state == TASK_TRACED) {
		if (child->signal->flags & SIGNAL_STOP_STOPPED) {
			child->state = TASK_STOPPED;
		} else {
			signal_wake_up(child, 1);
		}
	}
	if (child->signal->flags & SIGNAL_GROUP_EXIT) {
		sigaddset(&child->pending.signal, SIGKILL);
		signal_wake_up(child, 1);
	}
	spin_unlock(&child->sighand->siglock);
}

/*
 * unptrace a task: move it back to its original parent and
 * remove it from the ptrace list.
 *
 * Must be called with the tasklist lock write-held.
 */
void __ptrace_unlink(task_t *child)
{
	if (!child->ptrace)
		BUG();
	child->ptrace = 0;
	if (!list_empty(&child->ptrace_list)) {
		list_del_init(&child->ptrace_list);
		REMOVE_LINKS(child);
		child->parent = child->real_parent;
		SET_LINKS(child);
	}

	ptrace_untrace(child);
}

/*
 * Check that we have indeed attached to the thing..
 */
int ptrace_check_attach(struct task_struct *child, int kill)
{
	int ret = -ESRCH;

	/*
	 * We take the read lock around doing both checks to close a
	 * possible race where someone else was tracing our child and
	 * detached between these two checks.  After this locked check,
	 * we are sure that this is our traced child and that can only
	 * be changed by us so it's not changing right after this.
	 */
	read_lock(&tasklist_lock);
	if ((child->ptrace & PT_PTRACED) && child->parent == current &&
	    (!(child->ptrace & PT_ATTACHED) || child->real_parent != current)
	    && child->signal != NULL) {
		ret = 0;
		spin_lock_irq(&child->sighand->siglock);
		if (child->state == TASK_STOPPED) {
			child->state = TASK_TRACED;
		} else if (child->state != TASK_TRACED && !kill) {
			ret = -ESRCH;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);

	if (!ret && !kill) {
		wait_task_inactive(child);
	}

	/* All systems go.. */
	return ret;
}

static int may_attach(struct task_struct *task)
{
	if (!task->mm)
		return -EPERM;
	if (((current->uid != task->euid) ||
	     (current->uid != task->suid) ||
	     (current->uid != task->uid) ||
	     (current->gid != task->egid) ||
	     (current->gid != task->sgid) ||
	     (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
		return -EPERM;
	smp_rmb();
	if (!task->mm->dumpable && !capable(CAP_SYS_PTRACE))
		return -EPERM;

	return security_ptrace(current, task);
}

int ptrace_may_attach(struct task_struct *task)
{
	int err;
	task_lock(task);
	err = may_attach(task);
	task_unlock(task);
	return !err;
}

int ptrace_attach(struct task_struct *task)
{
	int retval;
	task_lock(task);
	retval = -EPERM;
	if (task->pid <= 1)
		goto bad;
	if (task->tgid == current->tgid)
		goto bad;
	/* the same process cannot be attached many times */
	if (task->ptrace & PT_PTRACED)
		goto bad;
	retval = may_attach(task);
	if (retval)
		goto bad;

	/* Go */
	task->ptrace |= PT_PTRACED | ((task->real_parent != current)
				      ? PT_ATTACHED : 0);
	if (capable(CAP_SYS_PTRACE))
		task->ptrace |= PT_PTRACE_CAP;
	task_unlock(task);

	write_lock_irq(&tasklist_lock);
	__ptrace_link(task, current);
	write_unlock_irq(&tasklist_lock);

	force_sig_specific(SIGSTOP, task);
	return 0;

bad:
	task_unlock(task);
	return retval;
}

int ptrace_detach(struct task_struct *child, unsigned int data)
{
	if (!valid_signal(data))
		return	-EIO;

	/* Architecture-specific hardware disable .. */
	ptrace_disable(child);

	/* .. re-parent .. */
	child->exit_code = data;

	write_lock_irq(&tasklist_lock);
	__ptrace_unlink(child);
	/* .. and wake it up. */
	if (child->exit_state != EXIT_ZOMBIE)
		wake_up_process(child);
	write_unlock_irq(&tasklist_lock);

	return 0;
}

/*
 * Access another process' address space.
 * Source/target buffer must be kernel space, 
 * Do not walk the page table directly, use get_user_pages
 */

int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
{
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	struct page *page;
	void *old_buf = buf;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	down_read(&mm->mmap_sem);
	/* ignore errors, just check how much was sucessfully transfered */
	while (len) {
		int bytes, ret, offset;
		void *maddr;

		ret = get_user_pages(tsk, mm, addr, 1,
				write, 1, &page, &vma);
		if (ret <= 0)
			break;

		bytes = len;
		offset = addr & (PAGE_SIZE-1);
		if (bytes > PAGE_SIZE-offset)
			bytes = PAGE_SIZE-offset;

		maddr = kmap(page);
		if (write) {
			copy_to_user_page(vma, page, addr,
					  maddr + offset, buf, bytes);
			set_page_dirty_lock(page);
		} else {
			copy_from_user_page(vma, page, addr,
					    buf, maddr + offset, bytes);
		}
		kunmap(page);
		page_cache_release(page);
		len -= bytes;
		buf += bytes;
		addr += bytes;
	}
	up_read(&mm->mmap_sem);
	mmput(mm);
	
	return buf - old_buf;
}

int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		retval = access_process_vm(tsk, src, buf, this_len, 0);
		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		if (copy_to_user(dst, buf, retval))
			return -EFAULT;
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;			
	}
	return copied;
}

int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		if (copy_from_user(buf, src, this_len))
			return -EFAULT;
		retval = access_process_vm(tsk, dst, buf, this_len, 1);
		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;			
	}
	return copied;
}

static int ptrace_setoptions(struct task_struct *child, long data)
{
	child->ptrace &= ~PT_TRACE_MASK;

	if (data & PTRACE_O_TRACESYSGOOD)
		child->ptrace |= PT_TRACESYSGOOD;

	if (data & PTRACE_O_TRACEFORK)
		child->ptrace |= PT_TRACE_FORK;

	if (data & PTRACE_O_TRACEVFORK)
		child->ptrace |= PT_TRACE_VFORK;

	if (data & PTRACE_O_TRACECLONE)
		child->ptrace |= PT_TRACE_CLONE;

	if (data & PTRACE_O_TRACEEXEC)
		child->ptrace |= PT_TRACE_EXEC;

	if (data & PTRACE_O_TRACEVFORKDONE)
		child->ptrace |= PT_TRACE_VFORK_DONE;

	if (data & PTRACE_O_TRACEEXIT)
		child->ptrace |= PT_TRACE_EXIT;

	return (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
}

static int ptrace_getsiginfo(struct task_struct *child, siginfo_t __user * data)
{
	siginfo_t lastinfo;
	int error = -ESRCH;

	read_lock(&tasklist_lock);
	if (likely(child->sighand != NULL)) {
		error = -EINVAL;
		spin_lock_irq(&child->sighand->siglock);
		if (likely(child->last_siginfo != NULL)) {
			lastinfo = *child->last_siginfo;
			error = 0;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);
	if (!error)
		return copy_siginfo_to_user(data, &lastinfo);
	return error;
}

static int ptrace_setsiginfo(struct task_struct *child, siginfo_t __user * data)
{
	siginfo_t newinfo;
	int error = -ESRCH;

	if (copy_from_user(&newinfo, data, sizeof (siginfo_t)))
		return -EFAULT;

	read_lock(&tasklist_lock);
	if (likely(child->sighand != NULL)) {
		error = -EINVAL;
		spin_lock_irq(&child->sighand->siglock);
		if (likely(child->last_siginfo != NULL)) {
			*child->last_siginfo = newinfo;
			error = 0;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);
	return error;
}

int ptrace_request(struct task_struct *child, long request,
		   long addr, long data)
{
	int ret = -EIO;

	switch (request) {
#ifdef PTRACE_OLDSETOPTIONS
	case PTRACE_OLDSETOPTIONS:
#endif
	case PTRACE_SETOPTIONS:
		ret = ptrace_setoptions(child, data);
		break;
	case PTRACE_GETEVENTMSG:
		ret = put_user(child->ptrace_message, (unsigned long __user *) data);
		break;
	case PTRACE_GETSIGINFO:
		ret = ptrace_getsiginfo(child, (siginfo_t __user *) data);
		break;
	case PTRACE_SETSIGINFO:
		ret = ptrace_setsiginfo(child, (siginfo_t __user *) data);
		break;
	default:
		break;
	}

	return ret;
}

#ifndef __ARCH_SYS_PTRACE
static int ptrace_get_task_struct(long request, long pid,
		struct task_struct **childp)
{
	struct task_struct *child;
	int ret;

	/*
	 * Callers use child == NULL as an indication to exit early even
	 * when the return value is 0, so make sure it is non-NULL here.
	 */
	*childp = NULL;

	if (request == PTRACE_TRACEME) {
		/*
		 * Are we already being traced?
		 */
		if (current->ptrace & PT_PTRACED)
			return -EPERM;
		ret = security_ptrace(current->parent, current);
		if (ret)
			return -EPERM;
		/*
		 * Set the ptrace bit in the process ptrace flags.
		 */
		current->ptrace |= PT_PTRACED;
		return 0;
	}

	/*
	 * You may not mess with init
	 */
	if (pid == 1)
		return -EPERM;

	ret = -ESRCH;
	read_lock(&tasklist_lock);
	child = find_task_by_pid(pid);
	if (child)
		get_task_struct(child);
	read_unlock(&tasklist_lock);
	if (!child)
		return -ESRCH;

	*childp = child;
	return 0;
}

asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
{
	struct task_struct *child;
	long ret;

	/*
	 * This lock_kernel fixes a subtle race with suid exec
	 */
	lock_kernel();
	ret = ptrace_get_task_struct(request, pid, &child);
	if (!child)
		goto out;

	if (request == PTRACE_ATTACH) {
		ret = ptrace_attach(child);
		goto out_put_task_struct;
	}

	ret = ptrace_check_attach(child, request == PTRACE_KILL);
	if (ret < 0)
		goto out_put_task_struct;

	ret = arch_ptrace(child, request, addr, data);
	if (ret < 0)
		goto out_put_task_struct;

 out_put_task_struct:
	put_task_struct(child);
 out:
	unlock_kernel();
	return ret;
}
#endif /* __ARCH_SYS_PTRACE */