base.c

linux 内核源代码

	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= mounts_release,
};

#define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */

static ssize_t proc_info_read(struct file * file, char __user * buf,
			  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	unsigned long page;
	ssize_t length;
	struct task_struct *task = get_proc_task(inode);

	length = -ESRCH;
	if (!task)
		goto out_no_task;

	if (count > PROC_BLOCK_SIZE)
		count = PROC_BLOCK_SIZE;

	length = -ENOMEM;
	if (!(page = __get_free_page(GFP_TEMPORARY)))
		goto out;

	length = PROC_I(inode)->op.proc_read(task, (char*)page);

	if (length >= 0)
		length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
	free_page(page);
out:
	put_task_struct(task);
out_no_task:
	return length;
}

static const struct file_operations proc_info_file_operations = {
	.read		= proc_info_read,
};

static int mem_open(struct inode* inode, struct file* file)
{
	file->private_data = (void*)((long)current->self_exec_id);
	return 0;
}

static ssize_t mem_read(struct file * file, char __user * buf,
			size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	char *page;
	unsigned long src = *ppos;
	int ret = -ESRCH;
	struct mm_struct *mm;

	if (!task)
		goto out_no_task;

	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
		goto out;

	ret = -ENOMEM;
	page = (char *)__get_free_page(GFP_TEMPORARY);
	if (!page)
		goto out;

	ret = 0;
 
	mm = get_task_mm(task);
	if (!mm)
		goto out_free;

	ret = -EIO;
 
	if (file->private_data != (void*)((long)current->self_exec_id))
		goto out_put;

	ret = 0;
 
	while (count > 0) {
		int this_len, retval;

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		retval = access_process_vm(task, src, page, this_len, 0);
		if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) {
			if (!ret)
				ret = -EIO;
			break;
		}

		if (copy_to_user(buf, page, retval)) {
			ret = -EFAULT;
			break;
		}
 
		ret += retval;
		src += retval;
		buf += retval;
		count -= retval;
	}
	*ppos = src;

out_put:
	mmput(mm);
out_free:
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return ret;
}

#define mem_write NULL

#ifndef mem_write
/* This is a security hazard */
static ssize_t mem_write(struct file * file, const char __user *buf,
			 size_t count, loff_t *ppos)
{
	int copied;
	char *page;
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	unsigned long dst = *ppos;

	copied = -ESRCH;
	if (!task)
		goto out_no_task;

	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
		goto out;

	copied = -ENOMEM;
	page = (char *)__get_free_page(GFP_TEMPORARY);
	if (!page)
		goto out;

	copied = 0;
	while (count > 0) {
		int this_len, retval;

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		if (copy_from_user(page, buf, this_len)) {
			copied = -EFAULT;
			break;
		}
		retval = access_process_vm(task, dst, page, this_len, 1);
		if (!retval) {
			if (!copied)
				copied = -EIO;
			break;
		}
		copied += retval;
		buf += retval;
		dst += retval;
		count -= retval;			
	}
	*ppos = dst;
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return copied;
}
#endif

static loff_t mem_lseek(struct file * file, loff_t offset, int orig)
{
	switch (orig) {
	case 0:
		file->f_pos = offset;
		break;
	case 1:
		file->f_pos += offset;
		break;
	default:
		return -EINVAL;
	}
	force_successful_syscall_return();
	return file->f_pos;
}

static const struct file_operations proc_mem_operations = {
	.llseek		= mem_lseek,
	.read		= mem_read,
	.write		= mem_write,
	.open		= mem_open,
};

static ssize_t environ_read(struct file *file, char __user *buf,
			size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
	char *page;
	unsigned long src = *ppos;
	int ret = -ESRCH;
	struct mm_struct *mm;

	if (!task)
		goto out_no_task;

	if (!ptrace_may_attach(task))
		goto out;

	ret = -ENOMEM;
	page = (char *)__get_free_page(GFP_TEMPORARY);
	if (!page)
		goto out;

	ret = 0;

	mm = get_task_mm(task);
	if (!mm)
		goto out_free;

	while (count > 0) {
		int this_len, retval, max_len;

		this_len = mm->env_end - (mm->env_start + src);

		if (this_len <= 0)
			break;

		max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		this_len = (this_len > max_len) ? max_len : this_len;

		retval = access_process_vm(task, (mm->env_start + src),
			page, this_len, 0);

		if (retval <= 0) {
			ret = retval;
			break;
		}

		if (copy_to_user(buf, page, retval)) {
			ret = -EFAULT;
			break;
		}

		ret += retval;
		src += retval;
		buf += retval;
		count -= retval;
	}
	*ppos = src;

	mmput(mm);
out_free:
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return ret;
}

static const struct file_operations proc_environ_operations = {
	.read		= environ_read,
};

static ssize_t oom_adjust_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	char buffer[PROC_NUMBUF];
	size_t len;
	int oom_adjust;

	if (!task)
		return -ESRCH;
	oom_adjust = task->oomkilladj;
	put_task_struct(task);

	len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);

	return simple_read_from_buffer(buf, count, ppos, buffer, len);
}

static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF], *end;
	int oom_adjust;

	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	oom_adjust = simple_strtol(buffer, &end, 0);
	if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
	     oom_adjust != OOM_DISABLE)
		return -EINVAL;
	if (*end == '\n')
		end++;
	task = get_proc_task(file->f_path.dentry->d_inode);
	if (!task)
		return -ESRCH;
	if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
		put_task_struct(task);
		return -EACCES;
	}
	task->oomkilladj = oom_adjust;
	put_task_struct(task);
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static const struct file_operations proc_oom_adjust_operations = {
	.read		= oom_adjust_read,
	.write		= oom_adjust_write,
};

#ifdef CONFIG_MMU
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF], *end;
	struct mm_struct *mm;

	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	if (!simple_strtol(buffer, &end, 0))
		return -EINVAL;
	if (*end == '\n')
		end++;
	task = get_proc_task(file->f_path.dentry->d_inode);
	if (!task)
		return -ESRCH;
	mm = get_task_mm(task);
	if (mm) {
		clear_refs_smap(mm);
		mmput(mm);
	}
	put_task_struct(task);
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static struct file_operations proc_clear_refs_operations = {
	.write		= clear_refs_write,
};
#endif

#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	ssize_t length;
	char tmpbuf[TMPBUFLEN];

	if (!task)
		return -ESRCH;
	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
				audit_get_loginuid(task->audit_context));
	put_task_struct(task);
	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
}

static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
				   size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	char *page, *tmp;
	ssize_t length;
	uid_t loginuid;

	if (!capable(CAP_AUDIT_CONTROL))
		return -EPERM;

	if (current != pid_task(proc_pid(inode), PIDTYPE_PID))
		return -EPERM;

	if (count >= PAGE_SIZE)
		count = PAGE_SIZE - 1;

	if (*ppos != 0) {
		/* No partial writes. */
		return -EINVAL;
	}
	page = (char*)__get_free_page(GFP_TEMPORARY);
	if (!page)
		return -ENOMEM;
	length = -EFAULT;
	if (copy_from_user(page, buf, count))
		goto out_free_page;

	page[count] = '\0';
	loginuid = simple_strtoul(page, &tmp, 10);
	if (tmp == page) {
		length = -EINVAL;
		goto out_free_page;

	}
	length = audit_set_loginuid(current, loginuid);
	if (likely(length == 0))
		length = count;

out_free_page:
	free_page((unsigned long) page);
	return length;
}

static const struct file_operations proc_loginuid_operations = {
	.read		= proc_loginuid_read,
	.write		= proc_loginuid_write,
};
#endif

#ifdef CONFIG_FAULT_INJECTION
static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
				      size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
	char buffer[PROC_NUMBUF];
	size_t len;
	int make_it_fail;

	if (!task)
		return -ESRCH;
	make_it_fail = task->make_it_fail;
	put_task_struct(task);

	len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail);

	return simple_read_from_buffer(buf, count, ppos, buffer, len);
}

static ssize_t proc_fault_inject_write(struct file * file,
			const char __user * buf, size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF], *end;
	int make_it_fail;

	if (!capable(CAP_SYS_RESOURCE))
		return -EPERM;
	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	make_it_fail = simple_strtol(buffer, &end, 0);
	if (*end == '\n')
		end++;
	task = get_proc_task(file->f_dentry->d_inode);
	if (!task)
		return -ESRCH;
	task->make_it_fail = make_it_fail;
	put_task_struct(task);
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static const struct file_operations proc_fault_inject_operations = {
	.read		= proc_fault_inject_read,
	.write		= proc_fault_inject_write,
};
#endif

#ifdef CONFIG_SCHED_DEBUG
/*
 * Print out various scheduling related per-task fields:
 */
static int sched_show(struct seq_file *m, void *v)
{
	struct inode *inode = m->private;
	struct task_struct *p;

	WARN_ON(!inode);

	p = get_proc_task(inode);
	if (!p)
		return -ESRCH;
	proc_sched_show_task(p, m);

	put_task_struct(p);

	return 0;
}

static ssize_t
sched_write(struct file *file, const char __user *buf,
	    size_t count, loff_t *offset)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct task_struct *p;

	WARN_ON(!inode);

	p = get_proc_task(inode);
	if (!p)
		return -ESRCH;
	proc_sched_set_task(p);

	put_task_struct(p);

	return count;
}

static int sched_open(struct inode *inode, struct file *filp)
{
	int ret;

	ret = single_open(filp, sched_show, NULL);
	if (!ret) {
		struct seq_file *m = filp->private_data;

		m->private = inode;
	}
	return ret;
}

static const struct file_operations proc_pid_sched_operations = {
	.open		= sched_open,
	.read		= seq_read,
	.write		= sched_write,
	.llseek		= seq_lseek,
	.release	= single_release,
};

#endif

static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	int error = -EACCES;

	/* We don't need a base pointer in the /proc filesystem */
	path_release(nd);

	/* Are we allowed to snoop on the tasks file descriptors? */
	if (!proc_fd_access_allowed(inode))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt);
	nd->last_type = LAST_BIND;
out:
	return ERR_PTR(error);
}

static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,