base.c

linux 内核源代码

	unsigned fd = *(unsigned *)ptr;
 	struct inode *inode;
 	struct proc_inode *ei;
	struct dentry *error = ERR_PTR(-ENOENT);

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;
	ei = PROC_I(inode);
	ei->fd = fd;
	inode->i_mode = S_IFREG | S_IRUSR;
	inode->i_fop = &proc_fdinfo_file_operations;
	dentry->d_op = &tid_fd_dentry_operations;
	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (tid_fd_revalidate(dentry, NULL))
		error = NULL;

 out:
	return error;
}

static struct dentry *proc_lookupfdinfo(struct inode *dir,
					struct dentry *dentry,
					struct nameidata *nd)
{
	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
}

static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
{
	return proc_readfd_common(filp, dirent, filldir,
				  proc_fdinfo_instantiate);
}

static const struct file_operations proc_fdinfo_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_readfdinfo,
};

/*
 * proc directories can do almost nothing..
 */
static const struct inode_operations proc_fdinfo_inode_operations = {
	.lookup		= proc_lookupfdinfo,
	.setattr	= proc_setattr,
};


static struct dentry *proc_pident_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	const struct pid_entry *p = ptr;
	struct inode *inode;
	struct proc_inode *ei;
	struct dentry *error = ERR_PTR(-EINVAL);

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	ei = PROC_I(inode);
	inode->i_mode = p->mode;
	if (S_ISDIR(inode->i_mode))
		inode->i_nlink = 2;	/* Use getattr to fix if necessary */
	if (p->iop)
		inode->i_op = p->iop;
	if (p->fop)
		inode->i_fop = p->fop;
	ei->op = p->op;
	dentry->d_op = &pid_dentry_operations;
	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		error = NULL;
out:
	return error;
}

static struct dentry *proc_pident_lookup(struct inode *dir, 
					 struct dentry *dentry,
					 const struct pid_entry *ents,
					 unsigned int nents)
{
	struct inode *inode;
	struct dentry *error;
	struct task_struct *task = get_proc_task(dir);
	const struct pid_entry *p, *last;

	error = ERR_PTR(-ENOENT);
	inode = NULL;

	if (!task)
		goto out_no_task;

	/*
	 * Yes, it does not scale. And it should not. Don't add
	 * new entries into /proc/<tgid>/ without very good reasons.
	 */
	last = &ents[nents - 1];
	for (p = ents; p <= last; p++) {
		if (p->len != dentry->d_name.len)
			continue;
		if (!memcmp(dentry->d_name.name, p->name, p->len))
			break;
	}
	if (p > last)
		goto out;

	error = proc_pident_instantiate(dir, dentry, task, p);
out:
	put_task_struct(task);
out_no_task:
	return error;
}

static int proc_pident_fill_cache(struct file *filp, void *dirent,
	filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
{
	return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
				proc_pident_instantiate, task, p);
}

static int proc_pident_readdir(struct file *filp,
		void *dirent, filldir_t filldir,
		const struct pid_entry *ents, unsigned int nents)
{
	int i;
	struct dentry *dentry = filp->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	const struct pid_entry *p, *last;
	ino_t ino;
	int ret;

	ret = -ENOENT;
	if (!task)
		goto out_no_task;

	ret = 0;
	i = filp->f_pos;
	switch (i) {
	case 0:
		ino = inode->i_ino;
		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
			goto out;
		i++;
		filp->f_pos++;
		/* fall through */
	case 1:
		ino = parent_ino(dentry);
		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
			goto out;
		i++;
		filp->f_pos++;
		/* fall through */
	default:
		i -= 2;
		if (i >= nents) {
			ret = 1;
			goto out;
		}
		p = ents + i;
		last = &ents[nents - 1];
		while (p <= last) {
			if (proc_pident_fill_cache(filp, dirent, filldir, task, p) < 0)
				goto out;
			filp->f_pos++;
			p++;
		}
	}

	ret = 1;
out:
	put_task_struct(task);
out_no_task:
	return ret;
}

#ifdef CONFIG_SECURITY
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_path.dentry->d_inode;
	char *p = NULL;
	ssize_t length;
	struct task_struct *task = get_proc_task(inode);

	if (!task)
		return -ESRCH;

	length = security_getprocattr(task,
				      (char*)file->f_path.dentry->d_name.name,
				      &p);
	put_task_struct(task);
	if (length > 0)
		length = simple_read_from_buffer(buf, count, ppos, p, length);
	kfree(p);
	return length;
}

static ssize_t proc_pid_attr_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;
	ssize_t length;
	struct task_struct *task = get_proc_task(inode);

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

	/* No partial writes. */
	length = -EINVAL;
	if (*ppos != 0)
		goto out;

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

	length = -EFAULT;
	if (copy_from_user(page, buf, count))
		goto out_free;

	length = security_setprocattr(task,
				      (char*)file->f_path.dentry->d_name.name,
				      (void*)page, count);
out_free:
	free_page((unsigned long) page);
out:
	put_task_struct(task);
out_no_task:
	return length;
}

static const struct file_operations proc_pid_attr_operations = {
	.read		= proc_pid_attr_read,
	.write		= proc_pid_attr_write,
};

static const struct pid_entry attr_dir_stuff[] = {
	REG("current",    S_IRUGO|S_IWUGO, pid_attr),
	REG("prev",       S_IRUGO,	   pid_attr),
	REG("exec",       S_IRUGO|S_IWUGO, pid_attr),
	REG("fscreate",   S_IRUGO|S_IWUGO, pid_attr),
	REG("keycreate",  S_IRUGO|S_IWUGO, pid_attr),
	REG("sockcreate", S_IRUGO|S_IWUGO, pid_attr),
};

static int proc_attr_dir_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   attr_dir_stuff,ARRAY_SIZE(attr_dir_stuff));
}

static const struct file_operations proc_attr_dir_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_attr_dir_readdir,
};

static struct dentry *proc_attr_dir_lookup(struct inode *dir,
				struct dentry *dentry, struct nameidata *nd)
{
	return proc_pident_lookup(dir, dentry,
				  attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
}

static const struct inode_operations proc_attr_dir_inode_operations = {
	.lookup		= proc_attr_dir_lookup,
	.getattr	= pid_getattr,
	.setattr	= proc_setattr,
};

#endif

#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
static ssize_t proc_coredump_filter_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);
	struct mm_struct *mm;
	char buffer[PROC_NUMBUF];
	size_t len;
	int ret;

	if (!task)
		return -ESRCH;

	ret = 0;
	mm = get_task_mm(task);
	if (mm) {
		len = snprintf(buffer, sizeof(buffer), "%08lx\n",
			       ((mm->flags & MMF_DUMP_FILTER_MASK) >>
				MMF_DUMP_FILTER_SHIFT));
		mmput(mm);
		ret = simple_read_from_buffer(buf, count, ppos, buffer, len);
	}

	put_task_struct(task);

	return ret;
}

static ssize_t proc_coredump_filter_write(struct file *file,
					  const char __user *buf,
					  size_t count,
					  loff_t *ppos)
{
	struct task_struct *task;
	struct mm_struct *mm;
	char buffer[PROC_NUMBUF], *end;
	unsigned int val;
	int ret;
	int i;
	unsigned long mask;

	ret = -EFAULT;
	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		goto out_no_task;

	ret = -EINVAL;
	val = (unsigned int)simple_strtoul(buffer, &end, 0);
	if (*end == '\n')
		end++;
	if (end - buffer == 0)
		goto out_no_task;

	ret = -ESRCH;
	task = get_proc_task(file->f_dentry->d_inode);
	if (!task)
		goto out_no_task;

	ret = end - buffer;
	mm = get_task_mm(task);
	if (!mm)
		goto out_no_mm;

	for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
		if (val & mask)
			set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
		else
			clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
	}

	mmput(mm);
 out_no_mm:
	put_task_struct(task);
 out_no_task:
	return ret;
}

static const struct file_operations proc_coredump_filter_operations = {
	.read		= proc_coredump_filter_read,
	.write		= proc_coredump_filter_write,
};
#endif

/*
 * /proc/self:
 */
static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
			      int buflen)
{
	char tmp[PROC_NUMBUF];
	sprintf(tmp, "%d", task_tgid_vnr(current));
	return vfs_readlink(dentry,buffer,buflen,tmp);
}

static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	char tmp[PROC_NUMBUF];
	sprintf(tmp, "%d", task_tgid_vnr(current));
	return ERR_PTR(vfs_follow_link(nd,tmp));
}

static const struct inode_operations proc_self_inode_operations = {
	.readlink	= proc_self_readlink,
	.follow_link	= proc_self_follow_link,
};

/*
 * proc base
 *
 * These are the directory entries in the root directory of /proc
 * that properly belong to the /proc filesystem, as they describe
 * describe something that is process related.
 */
static const struct pid_entry proc_base_stuff[] = {
	NOD("self", S_IFLNK|S_IRWXUGO,
		&proc_self_inode_operations, NULL, {}),
};

/*
 *	Exceptional case: normally we are not allowed to unhash a busy
 * directory. In this case, however, we can do it - no aliasing problems
 * due to the way we treat inodes.
 */
static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	if (task) {
		put_task_struct(task);
		return 1;
	}
	d_drop(dentry);
	return 0;
}

static struct dentry_operations proc_base_dentry_operations =
{
	.d_revalidate	= proc_base_revalidate,
	.d_delete	= pid_delete_dentry,
};

static struct dentry *proc_base_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	const struct pid_entry *p = ptr;
	struct inode *inode;
	struct proc_inode *ei;
	struct dentry *error = ERR_PTR(-EINVAL);

	/* Allocate the inode */
	error = ERR_PTR(-ENOMEM);
	inode = new_inode(dir->i_sb);
	if (!inode)
		goto out;

	/* Initialize the inode */
	ei = PROC_I(inode);
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;

	/*
	 * grab the reference to the task.
	 */
	ei->pid = get_task_pid(task, PIDTYPE_PID);
	if (!ei->pid)
		goto out_iput;

	inode->i_uid = 0;
	inode->i_gid = 0;
	inode->i_mode = p->mode;
	if (S_ISDIR(inode->i_mode))
		inode->i_nlink = 2;
	if (S_ISLNK(inode->i_mode))
		inode->i_size = 64;
	if (p->iop)
		inode->i_op = p->iop;
	if (p->fop)
		inode->i_fop = p->fop;
	ei->op = p->op;
	dentry->d_op = &proc_base_dentry_operations;
	d_add(dentry, inode);
	error = NULL;
out:
	return error;
out_iput:
	iput(inode);
	goto out;
}

static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry)
{
	struct dentry *error;
	struct task_struct *task = get_proc_task(dir);
	const struct pid_entry *p, *last;

	error = ERR_PTR(-ENOENT);

	if (!task)
		goto out_no_task;

	/* Lookup the directory entry */
	last = &proc_base_stuff[ARRAY_SIZE(proc_base_stuff) - 1];
	for (p = proc_base_stuff; p <= last; p++) {
		if (p->len != dentry->d_name.len)
			continue;
		if (!memcmp(dentry->d_name.name, p->name, p->len))
			break;
	}
	if (p > last)
		goto out;

	error = proc_base_instantiate(dir, dentry, task, p);

out:
	put_task_struct(task);
out_no_task:
	return error;
}

static int proc_base_fill_cache(struct file *filp, void *dirent,
	filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
{
	return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
				proc_base_instantiate, task, p);
}

#ifdef CONFIG_TASK_IO_ACCOUNTING
static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
{
	return sprintf(buffer,
#ifdef CONFIG_TASK_XACCT
			"rchar: %llu\n"
			"wchar: %llu\n"
			"syscr: %llu\n"
			"syscw: %llu\n"
#endif
			"read_bytes: %llu\n"
			"write_bytes: %llu\n"
			"cancelled_write_bytes: %llu\n",
#ifdef CONFIG_TASK_XACCT
			(unsigned long long)task->rchar,
			(unsigned long long)task->wchar,
			(unsigned long long)task->syscr,
			(unsigned long long)task->syscw,
#endif
			(unsigned long long)task->ioac.read_bytes,
			(unsigned long long)task->ioac.write_bytes,
			(unsigned long long)task->ioac.cancelled_write_bytes);
}
#endif

/*
 * Thread groups
 */
static const struct file_operations proc_task_operations;
static const struct inode_operations proc_task_inode_operations;

static const struct pid_entry tgid_base_stuff[] = {
	DIR("task",       S_IRUGO|S_IXUGO, task),
	DIR("fd",         S_IRUSR|S_IXUSR, fd),
	DIR("fdinfo",     S_IRUSR|S_IXUSR, fdinfo),
	REG("environ",    S_IRUSR, environ),
	INF("auxv",       S_IRUSR, pid_auxv),
	INF("status",     S_IRUGO, pid_status),
	INF("limits",	  S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
	REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
#endif
	INF("cmdline",    S_IRUGO, pid_cmdline),
	INF("stat",       S_IRUGO, tgid_stat),