// 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.
*/
static noinline bool __file_ref_put_badval(file_ref_t *ref, unsignedlong cnt)
{ /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object.
*/ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) {
atomic_long_set(&ref->refcnt, FILE_REF_DEAD); returnfalse;
}
/* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object.
*/ if (cnt > FILE_REF_MAXREF)
atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); returnfalse;
}
/** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object.
*/ bool __file_ref_put(file_ref_t *ref, unsignedlong cnt)
{ /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object.
*/ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) returnfalse;
/* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering.
*/
smp_acquire__after_ctrl_dep(); returntrue;
}
#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * 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.
*/ staticinlinevoid copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsignedint copy_words)
{ unsignedint nwords = fdt_words(nfdt);
/* * 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.
*/ staticvoid copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{
size_t cpy, set;
/* * 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".
*/ staticstruct fdtable *alloc_fdtable(unsignedint slots_wanted)
{ struct fdtable *fdt; unsignedint nr; void *data;
/* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less.
*/ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256)
nr = 256; else
nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly...
*/ if (unlikely(nr > sysctl_nr_open)) {
nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE);
}
/* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cachep objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size.
*/ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE);
fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out;
fdt->max_fds = nr;
data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt;
fdt->fd = data;
data = kvmalloc(max_t(size_t,
2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES),
GFP_KERNEL_ACCOUNT); if (!data) goto out_arr;
fdt->open_fds = data;
data += nr / BITS_PER_BYTE;
fdt->close_on_exec = data;
data += nr / BITS_PER_BYTE;
fdt->full_fds_bits = data;
/* * 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; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit.
*/ staticint expand_fdtable(struct files_struct *files, unsignedint nr)
__releases(files->file_lock)
__acquires(files->file_lock)
{ struct fdtable *new_fdt, *cur_fdt;
/* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section.
*/ if (atomic_read(&files->count) > 1)
synchronize_rcu();
spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt);
cur_fdt = files_fdtable(files);
BUG_ON(nr < cur_fdt->max_fds);
copy_fdtable(new_fdt, cur_fdt);
rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab)
call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */
smp_wmb(); return 0;
}
/* * 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 on success. * The files->file_lock should be held on entry, and will be held on exit.
*/ staticint expand_files(struct files_struct *files, unsignedint nr)
__releases(files->file_lock)
__acquires(files->file_lock)
{ struct fdtable *fdt; int error;
repeat:
fdt = files_fdtable(files);
/* Do we need to expand? */ if (nr < fdt->max_fds) return 0;
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
wait_event(files->resize_wait, !files->resize_in_progress);
spin_lock(&files->file_lock); goto repeat;
}
/* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE;
/* All good, so we try */
files->resize_in_progress = true;
error = expand_fdtable(files, nr);
files->resize_in_progress = false;
/* * 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. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range.
*/ staticunsignedint sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole)
{ unsignedint last = find_last_bit(fdt->open_fds, fdt->max_fds);
if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) {
last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT;
} return ALIGN(last + 1, BITS_PER_LONG);
}
/* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size().
*/ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole)
{ struct files_struct *newf; struct file **old_fds, **new_fds; unsignedint open_files, i; struct fdtable *old_fdt, *new_fdt;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM);
/* * Check whether we need to allocate a larger fd array and fd set.
*/ while (unlikely(open_files > new_fdt->max_fds)) {
spin_unlock(&oldf->file_lock);
if (new_fdt != &newf->fdtab)
__free_fdtable(new_fdt);
/* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer.
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = sane_fdtable_size(old_fdt, punch_hole);
}
/* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise.
*/ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) {
get_file(f);
} else {
__clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
}
spin_unlock(&oldf->file_lock);
staticstruct fdtable *close_files(struct files_struct * files)
{ /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure.
*/ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsignedint i, j = 0;
for (;;) { unsignedlong set;
i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break;
set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) {
filp_close(file, files);
cond_resched();
}
}
i++;
set >>= 1;
}
}
/* * Try to avoid looking at the second level bitmap
*/
bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG,
start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG;
if (likely(fd < fdt->max_fds))
fd = find_next_fd(fdt, fd);
/* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened.
*/
error = -EMFILE; if (unlikely(fd >= end)) goto out;
if (unlikely(fd >= fdt->max_fds)) {
error = expand_files(files, fd); if (error < 0) goto out;
goto repeat;
}
if (start <= files->next_fd)
files->next_fd = fd + 1;
/** * fd_install - install a file pointer in the fd array * @fd: file descriptor to install the file in * @file: the file to install * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file).
*/ void fd_install(unsignedint fd, struct file *file)
{ struct files_struct *files = current->files; struct fdtable *fdt;
if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return;
/** * 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)
{ struct fdtable *fdt = files_fdtable(files); struct file *file;
/** * 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.
*/ staticinlineunsigned last_fd(struct fdtable *fdt)
{ return fdt->max_fds - 1;
}
/** * sys_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. * Currently, errors to close a given file descriptor are ignored.
*/
SYSCALL_DEFINE3(close_range, unsignedint, fd, unsignedint, max_fd, unsignedint, flags)
{ struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL;
if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL;
if (fd > max_fd) return -EINVAL;
if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥
/* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them.
*/ if (flags & CLOSE_RANGE_CLOEXEC)
punch_hole = NULL;
fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below.
*/
swap(cur_fds, fds);
}
if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one.
*/
task_lock(me);
me->files = cur_fds;
task_unlock(me);
put_files_struct(fds);
}
return 0;
}
/** * 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(unsignedint fd)
{ struct files_struct *files = current->files; struct file *file;
file = rcu_dereference_raw(*f); if (!file) return NULL;
if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN);
file_reloaded = rcu_dereference_raw(*f);
/* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below.
*/
file_reloaded_cmp = file_reloaded;
OPTIMIZER_HIDE_VAR(file_reloaded_cmp);
/* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU.
*/ if (file == file_reloaded_cmp) return file_reloaded;
fput(file); return ERR_PTR(-EAGAIN);
}
/** * 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)
{ for (;;) { struct file __rcu *file;
file = __get_file_rcu(f); if (!IS_ERR(file)) return file;
}
}
EXPORT_SYMBOL_GPL(get_file_rcu);
/** * 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)
{ struct file __rcu *file;
/* Mask is a 0 for invalid fd's, ~0 for valid ones */
nospec_mask = array_index_mask_nospec(fd, fdt->max_fds);
/* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists.
*/
fdentry = fdt->fd + (fd & nospec_mask);
/* Do the load, then mask any invalid result */
file = rcu_dereference_raw(*fdentry);
file = (void *)(nospec_mask & (unsignedlong)file); if (unlikely(!file)) return NULL;
/* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that.
*/ if (unlikely(!file_ref_get(&file->f_ref))) continue;
/* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again.
*/ if (unlikely(file != rcu_dereference_raw(*fdentry)) ||
unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
fput(file); continue;
}
/* * This isn't the file we're looking for or we're not * allowed to get a reference to it.
*/ if (unlikely(file->f_mode & mask)) {
fput(file); return NULL;
}
/* * Ok, we have a ref to the file, and checked that it * still exists.
*/ return file;
}
}
/* * 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. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs.
*/ staticinlinestruct fd __fget_light(unsignedint fd, fmode_t mask)
{ struct files_struct *files = current->files; struct file *file;
/* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct().
*/ if (likely(atomic_read_acquire(&files->count) == 1)) {
file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file);
} else {
file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file);
}
} struct fd fdget(unsignedint fd)
{ return __fget_light(fd, FMODE_PATH);
}
EXPORT_SYMBOL(fdget);
/* * 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".
*/ staticinlinebool file_needs_f_pos_lock(struct file *file)
{ if (!(file->f_mode & FMODE_ATOMIC_POS)) returnfalse; if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF) returntrue; if (file->f_op->iterate_shared) returntrue; returnfalse;
}
/* * Note that we are not guaranteed to be called after fdget_pos() on * this file obj, in which case the caller is expected to provide the * appropriate locking.
*/
/* * 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()).
*/
/* * dup2() is expected to close the file installed in the target fd slot * (if any). However, userspace hand-picking a fd may be racing against * its own threads which happened to allocate it in open() et al but did * not populate it yet. * * Broadly speaking we may be racing against the following: * fd = get_unused_fd_flags(); // fd slot reserved, ->fd[fd] == NULL * file = hard_work_goes_here(); * fd_install(fd, file); // only now ->fd[fd] == file * * It is an invariant that a successfully allocated fd has a NULL entry * in the array until the matching fd_install(). * * If we fit the window, we have the fd to populate, yet no target file * to close. Trying to ignore it and install our new file would violate * the invariant and make fd_install() overwrite our file. * * Things can be done(tm) to handle this. However, the issue does not * concern legitimate programs and we only need to make sure the kernel * does not trip over it. * * The simplest way out is to return an error if we find ourselves here. * * POSIX is silent on the issue, we return -EBUSY.
*/
fdt = files_fdtable(files);
fd = array_index_nospec(fd, fdt->max_fds);
tofree = rcu_dereference_raw(fdt->fd[fd]); if (!tofree && fd_is_open(fd, fdt)) goto Ebusy;
get_file(file);
rcu_assign_pointer(fdt->fd[fd], file);
__set_open_fd(fd, fdt, flags & O_CLOEXEC);
spin_unlock(&files->file_lock);
/** * 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, unsignedint o_flags)
{ int new_fd; int error;
error = security_file_receive(file); if (error) return error;
new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd;
if (ufd) {
error = put_user(new_fd, ufd); if (error) {
put_unused_fd(new_fd); return error;
}
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.