linux/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 <[email protected]>
 */

#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 { … };

/*
 * 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 …

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

static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn)
{ … }

static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn)
{ … }

/**
 * 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)
{ … }

/**
 * 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)
{ … }

static struct kernfs_open_file *kernfs_of(struct file *file)
{ … }

/*
 * 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)
{ … }

/*
 * 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)
{ … }

static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
{ … }

static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
{ … }

static void kernfs_seq_stop(struct seq_file *sf, void *v)
{ … }

static int kernfs_seq_show(struct seq_file *sf, void *v)
{ … }

static const struct seq_operations kernfs_seq_ops = …;

/*
 * As reading a bin file can have side-effects, the exact offset and bytes
 * specified in read(2) call should be passed to the read callback making
 * it difficult to use seq_file.  Implement simplistic custom buffering for
 * bin files.
 */
static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{ … }

static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{ … }

/*
 * Copy data in from userland and pass it to the matching kernfs write
 * operation.
 *
 * There is no easy way for us to know if userspace is only doing a partial
 * write, so we don't support them. We expect the entire buffer to come on
 * the first write.  Hint: if you're writing a value, first read the file,
 * modify only the value you're changing, then write entire buffer
 * back.
 */
static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{ … }

static void kernfs_vma_open(struct vm_area_struct *vma)
{ … }

static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
{ … }

static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
{ … }

static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
			     void *buf, int len, int write)
{ … }

static const struct vm_operations_struct kernfs_vm_ops = …;

static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
{ … }

/**
 *	kernfs_get_open_node - get or create kernfs_open_node
 *	@kn: target kernfs_node
 *	@of: kernfs_open_file for this instance of open
 *
 *	If @kn->attr.open exists, increment its reference count; otherwise,
 *	create one.  @of is chained to the files list.
 *
 *	Locking:
 *	Kernel thread context (may sleep).
 *
 *	Return:
 *	%0 on success, -errno on failure.
 */
static int kernfs_get_open_node(struct kernfs_node *kn,
				struct kernfs_open_file *of)
{ … }

/**
 *	kernfs_unlink_open_file - Unlink @of from @kn.
 *
 *	@kn: target kernfs_node
 *	@of: associated kernfs_open_file
 *	@open_failed: ->open() failed, cancel ->release()
 *
 *	Unlink @of from list of @kn's associated open files. If list of
 *	associated open files becomes empty, disassociate and free
 *	kernfs_open_node.
 *
 *	LOCKING:
 *	None.
 */
static void kernfs_unlink_open_file(struct kernfs_node *kn,
				    struct kernfs_open_file *of,
				    bool open_failed)
{ … }

static int kernfs_fop_open(struct inode *inode, struct file *file)
{ … }

/* used from release/drain to ensure that ->release() is called exactly once */
static void kernfs_release_file(struct kernfs_node *kn,
				struct kernfs_open_file *of)
{ … }

static int kernfs_fop_release(struct inode *inode, struct file *filp)
{ … }

bool kernfs_should_drain_open_files(struct kernfs_node *kn)
{ … }

void kernfs_drain_open_files(struct kernfs_node *kn)
{ … }

/*
 * Kernfs attribute files are pollable.  The idea is that you read
 * the content and then you use 'poll' or 'select' to wait for
 * the content to change.  When the content changes (assuming the
 * manager for the kobject supports notification), poll will
 * return EPOLLERR|EPOLLPRI, and select will return the fd whether
 * it is waiting for read, write, or exceptions.
 * Once poll/select indicates that the value has changed, you
 * need to close and re-open the file, or seek to 0 and read again.
 * Reminder: this only works for attributes which actively support
 * it, and it is not possible to test an attribute from userspace
 * to see if it supports poll (Neither 'poll' nor 'select' return
 * an appropriate error code).  When in doubt, set a suitable timeout value.
 */
__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
{ … }

static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
{ … }

static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
{ … }

static void kernfs_notify_workfn(struct work_struct *work)
{ … }

/**
 * kernfs_notify - notify a kernfs file
 * @kn: file to notify
 *
 * Notify @kn such that poll(2) on @kn wakes up.  Maybe be called from any
 * context.
 */
void kernfs_notify(struct kernfs_node *kn)
{ … }
EXPORT_SYMBOL_GPL(…);

const struct file_operations kernfs_file_fops = …;

/**
 * __kernfs_create_file - kernfs internal function to create a file
 * @parent: directory to create the file in
 * @name: name of the file
 * @mode: mode of the file
 * @uid: uid of the file
 * @gid: gid of the file
 * @size: size of the file
 * @ops: kernfs operations for the file
 * @priv: private data for the file
 * @ns: optional namespace tag of the file
 * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
 *
 * Return: the created node on success, ERR_PTR() value on error.
 */
struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
					 const char *name,
					 umode_t mode, kuid_t uid, kgid_t gid,
					 loff_t size,
					 const struct kernfs_ops *ops,
					 void *priv, const void *ns,
					 struct lock_class_key *key)
{ … }