path: root/fs/kernfs/file.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * fs/kernfs/file.c - kernfs file implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
 */

#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>
#include <linux/uio.h>

#include "kernfs-internal.h"

struct kernfs_open_node {
	struct rcu_head		rcu_head;
	atomic_t		event;
	wait_queue_head_t	poll;
	struct list_head	files; /* goes through kernfs_open_file.list */
	unsigned int		nr_mmapped;
	unsigned int		nr_to_release;
};

/*
 * kernfs_notify() may be called from any context and bounces notifications
 * through a work item.  To minimize space overhead in kernfs_node, the
 * pending queue is implemented as a singly linked list of kernfs_nodes.
 * The list is terminated with the self pointer so that whether a
 * kernfs_node is on the list or not can be determined by testing the next
 * pointer for %NULL.
 */
#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)

static DEFINE_SPINLOCK(kernfs_notify_lock);
static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;

static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn)
{
	int idx = hash_ptr(kn, NR_KERNFS_LOCK_BITS);

	return &kernfs_locks->open_file_mutex[idx];
}

static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn)
{
	struct mutex *lock;

	lock = kernfs_open_file_mutex_ptr(kn);

	mutex_lock(lock);

	return lock;
}

/**
 * of_on - Get the kernfs_open_node of the specified kernfs_open_file
 * @of: target kernfs_open_file
 *
 * Return: the kernfs_open_node of the kernfs_open_file
 */
static struct kernfs_open_node *of_on(struct kernfs_open_file *of)
{
	return rcu_dereference_protected(of->kn->attr.open,
					 !list_empty(&of->list));
}

/**
 * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn
 *
 * @kn: target kernfs_node.
 *
 * Fetch and return ->attr.open of @kn when caller holds the
 * kernfs_open_file_mutex_ptr(kn).
 *
 * Update of ->attr.open happens under kernfs_open_file_mutex_ptr(kn). So when
 * the caller guarantees that this mutex is being held, other updaters can't
 * change ->attr.open and this means that we can safely deref ->attr.open
 * outside RCU read-side critical section.
 *
 * The caller needs to make sure that kernfs_open_file_mutex is held.
 *
 * Return: @kn->attr.open when kernfs_open_file_mutex is held.
 */
static struct kernfs_open_node *
kernfs_deref_open_node_locked(struct kernfs_node *kn)
{
	return rcu_dereference_protected(kn->attr.open,
				lockdep_is_held(kernfs_open_file_mutex_ptr(kn)));
}

static struct kernfs_open_file *kernfs_of(struct file *file)
{
	return ((struct seq_file *)file->private_data)->private;
}

/*
 * Determine the kernfs_ops for the given kernfs_node.  This function must
 * be called while holding an active reference.
 */
static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
{
	if (kn->flags & KERNFS_LOCKDEP)
		lockdep_assert_held(kn);
	return kn->attr.ops;
}

/*
 * As kernfs_seq_stop() is also called after kernfs_seq_start() or
 * kernfs_seq_next() failure, it needs to distinguish whether it's stopping
 * a seq_file iteration which is fully initialized with an active reference
 * or an aborted kernfs_seq_start() due to get_active failure.  The
 * position pointer is the only context for each seq_file iteration and
 * thus the stop condition should be encoded in it.  As the return value is
 * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
 * choice to indicate get_active failure.
 *
 * Unfortunately, this is complicated due to the optional custom seq_file
 * operations which may return ERR_PTR(-ENODEV) too.  kernfs_seq_stop()
 * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
 * custom seq_file operations and thus can't decide whether put_active
 * should be performed or not only on ERR_PTR(-ENODEV).
 *
 * This is worked around by factoring out the custom seq_stop() and
 * put_active part into kernfs_seq_stop_active(), skipping it from
 * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
 * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
 * that kernfs_seq_stop_active() is skipped only after get_active failure.
 */
static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
{
	struct kernfs_open_file *of = sf->private;
	const struct kernfs_ops *ops = kernfs_ops(of->kn);

	if (ops->seq_stop)
		ops->seq_stop(sf, v);
	kernfs_put_active(of->kn);
}

static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
{
	struct kernfs_open_file *of = sf->private;
	const struct kernfs_ops *ops;

	/*
	 * @of->mutex nests outside active ref and is primarily to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
	if (!kernfs_get_active(of->kn))
		return ERR_PTR(-ENODEV);

	ops = kernfs_ops(of->kn);
	if (ops->seq_start) {
		void *next = ops->seq_start(sf, ppos);
		/* see the comment above kernfs_seq_stop_active() */
		if (next == ERR_PTR(-ENODEV))
			kernfs_seq_stop_active(sf, next);