linux/fs/file.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/file.c
 *
 *  Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes
 *
 *  Manage the dynamic fd arrays in the process files_struct.
 */

#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/close_range.h>
#include <net/sock.h>

#include "internal.h"

unsigned int sysctl_nr_open __read_mostly = …;
unsigned int sysctl_nr_open_min = …;
/* our min() is unusable in constant expressions ;-/ */
#define __const_min(x, y) …
unsigned int sysctl_nr_open_max = …;

static void __free_fdtable(struct fdtable *fdt)
{ … }

static void free_fdtable_rcu(struct rcu_head *rcu)
{ … }

#define BITBIT_NR(nr) …
#define BITBIT_SIZE(nr) …

/*
 * Copy 'count' fd bits from the old table to the new table and clear the extra
 * space if any.  This does not copy the file pointers.  Called with the files
 * spinlock held for write.
 */
static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
			    unsigned int count)
{ … }

/*
 * Copy all file descriptors from the old table to the new, expanded table and
 * clear the extra space.  Called with the files spinlock held for write.
 */
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{ … }

/*
 * Note how the fdtable bitmap allocations very much have to be a multiple of
 * BITS_PER_LONG. This is not only because we walk those things in chunks of
 * 'unsigned long' in some places, but simply because that is how the Linux
 * kernel bitmaps are defined to work: they are not "bits in an array of bytes",
 * they are very much "bits in an array of unsigned long".
 *
 * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied
 * by that "1024/sizeof(ptr)" before, we already know there are sufficient
 * clear low bits. Clang seems to realize that, gcc ends up being confused.
 *
 * On a 128-bit machine, the ALIGN() would actually matter. In the meantime,
 * let's consider it documentation (and maybe a test-case for gcc to improve
 * its code generation ;)
 */
static struct fdtable * alloc_fdtable(unsigned int nr)
{ … }

/*
 * Expand the file descriptor table.
 * This function will allocate a new fdtable and both fd array and fdset, of
 * the given size.
 * Return <0 error code on error; 1 on successful completion.
 * The files->file_lock should be held on entry, and will be held on exit.
 */
static int expand_fdtable(struct files_struct *files, unsigned int nr)
	__releases(files->file_lock)
	__acquires(files->file_lock)
{ … }

/*
 * Expand files.
 * This function will expand the file structures, if the requested size exceeds
 * the current capacity and there is room for expansion.
 * Return <0 error code on error; 0 when nothing done; 1 when files were
 * expanded and execution may have blocked.
 * The files->file_lock should be held on entry, and will be held on exit.
 */
static int expand_files(struct files_struct *files, unsigned int nr)
	__releases(files->file_lock)
	__acquires(files->file_lock)
{ … }

static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt)
{ … }

static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt)
{ … }

static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
{ … }

static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
{ … }

static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
{ … }

static unsigned int count_open_files(struct fdtable *fdt)
{ … }

/*
 * Note that a sane fdtable size always has to be a multiple of
 * BITS_PER_LONG, since we have bitmaps that are sized by this.
 *
 * 'max_fds' will normally already be properly aligned, but it
 * turns out that in the close_range() -> __close_range() ->
 * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end
 * up having a 'max_fds' value that isn't already aligned.
 *
 * Rather than make close_range() have to worry about this,
 * just make that BITS_PER_LONG alignment be part of a sane
 * fdtable size. Becuase that's really what it is.
 */
static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
{ … }

/*
 * Allocate a new files structure and copy contents from the
 * passed in files structure.
 * errorp will be valid only when the returned files_struct is NULL.
 */
struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
{ … }

static struct fdtable *close_files(struct files_struct * files)
{ … }

void put_files_struct(struct files_struct *files)
{ … }

void exit_files(struct task_struct *tsk)
{ … }

struct files_struct init_files = …;

static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
{ … }

/*
 * allocate a file descriptor, mark it busy.
 */
static int alloc_fd(unsigned start, unsigned end, unsigned flags)
{ … }

int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
{ … }

int get_unused_fd_flags(unsigned flags)
{ … }
EXPORT_SYMBOL(…);

static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{ … }

void put_unused_fd(unsigned int fd)
{ … }

EXPORT_SYMBOL(…);

/*
 * Install a file pointer in the fd array.
 *
 * The VFS is full of places where we drop the files lock between
 * setting the open_fds bitmap and installing the file in the file
 * array.  At any such point, we are vulnerable to a dup2() race
 * installing a file in the array before us.  We need to detect this and
 * fput() the struct file we are about to overwrite in this case.
 *
 * It should never happen - if we allow dup2() do it, _really_ bad things
 * will follow.
 *
 * This consumes the "file" refcount, so callers should treat it
 * as if they had called fput(file).
 */

void fd_install(unsigned int fd, struct file *file)
{ … }

EXPORT_SYMBOL(…);

/**
 * file_close_fd_locked - return file associated with fd
 * @files: file struct to retrieve file from
 * @fd: file descriptor to retrieve file for
 *
 * Doesn't take a separate reference count.
 *
 * Context: files_lock must be held.
 *
 * Returns: The file associated with @fd (NULL if @fd is not open)
 */
struct file *file_close_fd_locked(struct files_struct *files, unsigned fd)
{ … }

int close_fd(unsigned fd)
{ … }
EXPORT_SYMBOL(…); /* for ksys_close() */

/**
 * last_fd - return last valid index into fd table
 * @fdt: File descriptor table.
 *
 * Context: Either rcu read lock or files_lock must be held.
 *
 * Returns: Last valid index into fdtable.
 */
static inline unsigned last_fd(struct fdtable *fdt)
{ … }

static inline void __range_cloexec(struct files_struct *cur_fds,
				   unsigned int fd, unsigned int max_fd)
{ … }

static inline void __range_close(struct files_struct *files, unsigned int fd,
				 unsigned int max_fd)
{ … }

/**
 * __close_range() - Close all file descriptors in a given range.
 *
 * @fd:     starting file descriptor to close
 * @max_fd: last file descriptor to close
 * @flags:  CLOSE_RANGE flags.
 *
 * This closes a range of file descriptors. All file descriptors
 * from @fd up to and including @max_fd are closed.
 */
int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
{ … }

/**
 * file_close_fd - return file associated with fd
 * @fd: file descriptor to retrieve file for
 *
 * Doesn't take a separate reference count.
 *
 * Returns: The file associated with @fd (NULL if @fd is not open)
 */
struct file *file_close_fd(unsigned int fd)
{ … }

void do_close_on_exec(struct files_struct *files)
{ … }

static struct file *__get_file_rcu(struct file __rcu **f)
{ … }

/**
 * get_file_rcu - try go get a reference to a file under rcu
 * @f: the file to get a reference on
 *
 * This function tries to get a reference on @f carefully verifying that
 * @f hasn't been reused.
 *
 * This function should rarely have to be used and only by users who
 * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it.
 *
 * Return: Returns @f with the reference count increased or NULL.
 */
struct file *get_file_rcu(struct file __rcu **f)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * get_file_active - try go get a reference to a file
 * @f: the file to get a reference on
 *
 * In contast to get_file_rcu() the pointer itself isn't part of the
 * reference counting.
 *
 * This function should rarely have to be used and only by users who
 * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it.
 *
 * Return: Returns @f with the reference count increased or NULL.
 */
struct file *get_file_active(struct file **f)
{ … }
EXPORT_SYMBOL_GPL(…);

static inline struct file *__fget_files_rcu(struct files_struct *files,
       unsigned int fd, fmode_t mask)
{ … }

static struct file *__fget_files(struct files_struct *files, unsigned int fd,
				 fmode_t mask)
{ … }

static inline struct file *__fget(unsigned int fd, fmode_t mask)
{ … }

struct file *fget(unsigned int fd)
{ … }
EXPORT_SYMBOL(…);

struct file *fget_raw(unsigned int fd)
{ … }
EXPORT_SYMBOL(…);

struct file *fget_task(struct task_struct *task, unsigned int fd)
{ … }

struct file *lookup_fdget_rcu(unsigned int fd)
{ … }
EXPORT_SYMBOL_GPL(…);

struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd)
{ … }

struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd)
{ … }
EXPORT_SYMBOL(…);

/*
 * Lightweight file lookup - no refcnt increment if fd table isn't shared.
 *
 * You can use this instead of fget if you satisfy all of the following
 * conditions:
 * 1) You must call fput_light before exiting the syscall and returning control
 *    to userspace (i.e. you cannot remember the returned struct file * after
 *    returning to userspace).
 * 2) You must not call filp_close on the returned struct file * in between
 *    calls to fget_light and fput_light.
 * 3) You must not clone the current task in between the calls to fget_light
 *    and fput_light.
 *
 * The fput_needed flag returned by fget_light should be passed to the
 * corresponding fput_light.
 */
static unsigned long __fget_light(unsigned int fd, fmode_t mask)
{ … }
unsigned long __fdget(unsigned int fd)
{ … }
EXPORT_SYMBOL(…);

unsigned long __fdget_raw(unsigned int fd)
{ … }

/*
 * Try to avoid f_pos locking. We only need it if the
 * file is marked for FMODE_ATOMIC_POS, and it can be
 * accessed multiple ways.
 *
 * Always do it for directories, because pidfd_getfd()
 * can make a file accessible even if it otherwise would
 * not be, and for directories this is a correctness
 * issue, not a "POSIX requirement".
 */
static inline bool file_needs_f_pos_lock(struct file *file)
{ … }

unsigned long __fdget_pos(unsigned int fd)
{ … }

void __f_unlock_pos(struct file *f)
{ … }

/*
 * We only lock f_pos if we have threads or if the file might be
 * shared with another process. In both cases we'll have an elevated
 * file count (done either by fdget() or by fork()).
 */

void set_close_on_exec(unsigned int fd, int flag)
{ … }

bool get_close_on_exec(unsigned int fd)
{ … }

static int do_dup2(struct files_struct *files,
	struct file *file, unsigned fd, unsigned flags)
__releases(&files->file_lock)
{ … }

int replace_fd(unsigned fd, struct file *file, unsigned flags)
{ … }

/**
 * receive_fd() - Install received file into file descriptor table
 * @file: struct file that was received from another process
 * @ufd: __user pointer to write new fd number to
 * @o_flags: the O_* flags to apply to the new fd entry
 *
 * Installs a received file into the file descriptor table, with appropriate
 * checks and count updates. Optionally writes the fd number to userspace, if
 * @ufd is non-NULL.
 *
 * This helper handles its own reference counting of the incoming
 * struct file.
 *
 * Returns newly install fd or -ve on error.
 */
int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
{ … }
EXPORT_SYMBOL_GPL(…);

int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
{ … }

static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{ … }

SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{ … }

SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
{ … }

SYSCALL_DEFINE1(dup, unsigned int, fildes)
{ … }

int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{ … }

int iterate_fd(struct files_struct *files, unsigned n,
		int (*f)(const void *, struct file *, unsigned),
		const void *p)
{ … }
EXPORT_SYMBOL(…);