2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/fs/file.c
Linus Torvalds 38e7571c07 io_uring-2019-03-06
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlyAJvAQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgphb+EACFaKI2HIdjExQ5T7Cxebzwky+Qiro3FV55
 ziW00FZrkJ5g0h4ItBzh/5SDlcNQYZDMlA3s4xzWIMadWl5PjMPq1uJul0cITbSl
 WIJO5hpgNMXeUEhvcXUl6+f/WzpgYUxN40uW8N5V7EKlooaFVfudDqJGlvEv+UgB
 g8NWQYThSG+/e7r9OGwK0xDRVKfpjxVvmqmnDH3DrxKaDgSOwTf4xn1u41wKwfQ3
 3uPfQ+GBeTqt4a2AhOi7K6KQFNnj5Jz5CXYMiOZI2JGtLPcL6dmyBVD7K0a0HUr+
 rs4ghNdd1+puvPGNK4TX8qV0uiNrMctoRNVA/JDd1ZTYEKTmNLxeFf+olfYHlwuK
 K5FRs60/lgNzNkzcUpFvJHitPwYtxYJdB36PyswE1FZP1YviEeVoKNt9W8aIhEoA
 549uj90brfA74eCINGhq98pJqj9CNyCPw3bfi76f5Ej2utwYDb9S5Cp2gfSa853X
 qc/qNda9efEq7ikwCbPzhekRMXZo6TSXtaSmC2C+Vs5+mD1Scc4kdAvdCKGQrtr9
 aoy0iQMYO2NDZ/G5fppvXtMVuEPAZWbsGftyOe15IlMysjRze2ycJV8cFahKEVM9
 uBeXLyH1pqGU/j7ABP4+XRZ/sbHJTwjKJbnXhTgBsdU8XO/CR3U+kRQFTsidKMfH
 Wlo3uH2h2A==
 =p78E
 -----END PGP SIGNATURE-----

Merge tag 'io_uring-2019-03-06' of git://git.kernel.dk/linux-block

Pull io_uring IO interface from Jens Axboe:
 "Second attempt at adding the io_uring interface.

  Since the first one, we've added basic unit testing of the three
  system calls, that resides in liburing like the other unit tests that
  we have so far. It'll take a while to get full coverage of it, but
  we're working towards it. I've also added two basic test programs to
  tools/io_uring. One uses the raw interface and has support for all the
  various features that io_uring supports outside of standard IO, like
  fixed files, fixed IO buffers, and polled IO. The other uses the
  liburing API, and is a simplified version of cp(1).

  This adds support for a new IO interface, io_uring.

  io_uring allows an application to communicate with the kernel through
  two rings, the submission queue (SQ) and completion queue (CQ) ring.
  This allows for very efficient handling of IOs, see the v5 posting for
  some basic numbers:

    https://lore.kernel.org/linux-block/20190116175003.17880-1-axboe@kernel.dk/

  Outside of just efficiency, the interface is also flexible and
  extendable, and allows for future use cases like the upcoming NVMe
  key-value store API, networked IO, and so on. It also supports async
  buffered IO, something that we've always failed to support in the
  kernel.

  Outside of basic IO features, it supports async polled IO as well.
  This particular feature has already been tested at Facebook months ago
  for flash storage boxes, with 25-33% improvements. It makes polled IO
  actually useful for real world use cases, where even basic flash sees
  a nice win in terms of efficiency, latency, and performance. These
  boxes were IOPS bound before, now they are not.

  This series adds three new system calls. One for setting up an
  io_uring instance (io_uring_setup(2)), one for submitting/completing
  IO (io_uring_enter(2)), and one for aux functions like registrating
  file sets, buffers, etc (io_uring_register(2)). Through the help of
  Arnd, I've coordinated the syscall numbers so merge on that front
  should be painless.

  Jon did a writeup of the interface a while back, which (except for
  minor details that have been tweaked) is still accurate. Find that
  here:

    https://lwn.net/Articles/776703/

  Huge thanks to Al Viro for helping getting the reference cycle code
  correct, and to Jann Horn for his extensive reviews focused on both
  security and bugs in general.

  There's a userspace library that provides basic functionality for
  applications that don't need or want to care about how to fiddle with
  the rings directly. It has helpers to allow applications to easily set
  up an io_uring instance, and submit/complete IO through it without
  knowing about the intricacies of the rings. It also includes man pages
  (thanks to Jeff Moyer), and will continue to grow support helper
  functions and features as time progresses. Find it here:

    git://git.kernel.dk/liburing

  Fio has full support for the raw interface, both in the form of an IO
  engine (io_uring), but also with a small test application (t/io_uring)
  that can exercise and benchmark the interface"

* tag 'io_uring-2019-03-06' of git://git.kernel.dk/linux-block:
  io_uring: add a few test tools
  io_uring: allow workqueue item to handle multiple buffered requests
  io_uring: add support for IORING_OP_POLL
  io_uring: add io_kiocb ref count
  io_uring: add submission polling
  io_uring: add file set registration
  net: split out functions related to registering inflight socket files
  io_uring: add support for pre-mapped user IO buffers
  block: implement bio helper to add iter bvec pages to bio
  io_uring: batch io_kiocb allocation
  io_uring: use fget/fput_many() for file references
  fs: add fget_many() and fput_many()
  io_uring: support for IO polling
  io_uring: add fsync support
  Add io_uring IO interface
2019-03-08 14:48:40 -08:00

1018 lines
24 KiB
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/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>
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
/* our min() is unusable in constant expressions ;-/ */
#define __const_min(x, y) ((x) < (y) ? (x) : (y))
unsigned int sysctl_nr_open_max =
__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;
static void __free_fdtable(struct fdtable *fdt)
{
kvfree(fdt->fd);
kvfree(fdt->open_fds);
kfree(fdt);
}
static void free_fdtable_rcu(struct rcu_head *rcu)
{
__free_fdtable(container_of(rcu, struct fdtable, rcu));
}
#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))
#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
/*
* 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)
{
unsigned int cpy, set;
cpy = count / BITS_PER_BYTE;
set = (nfdt->max_fds - count) / BITS_PER_BYTE;
memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
memset((char *)nfdt->open_fds + cpy, 0, set);
memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
memset((char *)nfdt->close_on_exec + cpy, 0, set);
cpy = BITBIT_SIZE(count);
set = BITBIT_SIZE(nfdt->max_fds) - cpy;
memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
memset((char *)nfdt->full_fds_bits + cpy, 0, set);
}
/*
* 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)
{
unsigned int cpy, set;
BUG_ON(nfdt->max_fds < ofdt->max_fds);
cpy = ofdt->max_fds * sizeof(struct file *);
set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)nfdt->fd + cpy, 0, set);
copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
}
static struct fdtable * alloc_fdtable(unsigned int nr)
{
struct fdtable *fdt;
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.
*/
nr /= (1024 / sizeof(struct file *));
nr = roundup_pow_of_two(nr + 1);
nr *= (1024 / sizeof(struct file *));
/*
* 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. Deal
* with that in caller, it's cheaper that way.
*
* 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 = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
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;
return fdt;
out_arr:
kvfree(fdt->fd);
out_fdt:
kfree(fdt);
out:
return NULL;
}
/*
* 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)
{
struct fdtable *new_fdt, *cur_fdt;
spin_unlock(&files->file_lock);
new_fdt = alloc_fdtable(nr);
/* 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 (!new_fdt)
return -ENOMEM;
/*
* extremely unlikely race - sysctl_nr_open decreased between the check in
* caller and alloc_fdtable(). Cheaper to catch it here...
*/
if (unlikely(new_fdt->max_fds <= nr)) {
__free_fdtable(new_fdt);
return -EMFILE;
}
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 1;
}
/*
* 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)
{
struct fdtable *fdt;
int expanded = 0;
repeat:
fdt = files_fdtable(files);
/* Do we need to expand? */
if (nr < fdt->max_fds)
return expanded;
/* Can we expand? */
if (nr >= sysctl_nr_open)
return -EMFILE;
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
expanded = 1;
wait_event(files->resize_wait, !files->resize_in_progress);
spin_lock(&files->file_lock);
goto repeat;
}
/* All good, so we try */
files->resize_in_progress = true;
expanded = expand_fdtable(files, nr);
files->resize_in_progress = false;
wake_up_all(&files->resize_wait);
return expanded;
}
static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt)
{
__set_bit(fd, fdt->close_on_exec);
}
static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt)
{
if (test_bit(fd, fdt->close_on_exec))
__clear_bit(fd, fdt->close_on_exec);
}
static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
{
__set_bit(fd, fdt->open_fds);
fd /= BITS_PER_LONG;
if (!~fdt->open_fds[fd])
__set_bit(fd, fdt->full_fds_bits);
}
static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
{
__clear_bit(fd, fdt->open_fds);
__clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits);
}
static unsigned int count_open_files(struct fdtable *fdt)
{
unsigned int size = fdt->max_fds;
unsigned int i;
/* Find the last open fd */
for (i = size / BITS_PER_LONG; i > 0; ) {
if (fdt->open_fds[--i])
break;
}
i = (i + 1) * BITS_PER_LONG;
return i;
}
/*
* 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, int *errorp)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
unsigned int open_files, i;
struct fdtable *old_fdt, *new_fdt;
*errorp = -ENOMEM;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
goto out;
atomic_set(&newf->count, 1);
spin_lock_init(&newf->file_lock);
newf->resize_in_progress = false;
init_waitqueue_head(&newf->resize_wait);
newf->next_fd = 0;
new_fdt = &newf->fdtab;
new_fdt->max_fds = NR_OPEN_DEFAULT;
new_fdt->close_on_exec = newf->close_on_exec_init;
new_fdt->open_fds = newf->open_fds_init;
new_fdt->full_fds_bits = newf->full_fds_bits_init;
new_fdt->fd = &newf->fd_array[0];
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = count_open_files(old_fdt);
/*
* 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);
new_fdt = alloc_fdtable(open_files - 1);
if (!new_fdt) {
*errorp = -ENOMEM;
goto out_release;
}
/* beyond sysctl_nr_open; nothing to do */
if (unlikely(new_fdt->max_fds < open_files)) {
__free_fdtable(new_fdt);
*errorp = -EMFILE;
goto out_release;
}
/*
* 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 = count_open_files(old_fdt);
}
copy_fd_bitmaps(new_fdt, old_fdt, open_files);
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
for (i = open_files; i != 0; i--) {
struct file *f = *old_fds++;
if (f) {
get_file(f);
} else {
/*
* The fd may be claimed in the fd bitmap but not yet
* instantiated in the files array if a sibling thread
* is partway through open(). So make sure that this
* fd is available to the new process.
*/
__clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
}
spin_unlock(&oldf->file_lock);
/* clear the remainder */
memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *));
rcu_assign_pointer(newf->fdt, new_fdt);
return newf;
out_release:
kmem_cache_free(files_cachep, newf);
out:
return NULL;
}
static struct 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);
unsigned int i, j = 0;
for (;;) {
unsigned long 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 = xchg(&fdt->fd[i], NULL);
if (file) {
filp_close(file, files);
cond_resched();
}
}
i++;
set >>= 1;
}
}
return fdt;
}
struct files_struct *get_files_struct(struct task_struct *task)
{
struct files_struct *files;
task_lock(task);
files = task->files;
if (files)
atomic_inc(&files->count);
task_unlock(task);
return files;
}
void put_files_struct(struct files_struct *files)
{
if (atomic_dec_and_test(&files->count)) {
struct fdtable *fdt = close_files(files);
/* free the arrays if they are not embedded */
if (fdt != &files->fdtab)
__free_fdtable(fdt);
kmem_cache_free(files_cachep, files);
}
}
void reset_files_struct(struct files_struct *files)
{
struct task_struct *tsk = current;
struct files_struct *old;
old = tsk->files;
task_lock(tsk);
tsk->files = files;
task_unlock(tsk);
put_files_struct(old);
}
void exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
if (files) {
task_lock(tsk);
tsk->files = NULL;
task_unlock(tsk);
put_files_struct(files);
}
}
struct files_struct init_files = {
.count = ATOMIC_INIT(1),
.fdt = &init_files.fdtab,
.fdtab = {
.max_fds = NR_OPEN_DEFAULT,
.fd = &init_files.fd_array[0],
.close_on_exec = init_files.close_on_exec_init,
.open_fds = init_files.open_fds_init,
.full_fds_bits = init_files.full_fds_bits_init,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
.resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait),
};
static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
{
unsigned int maxfd = fdt->max_fds;
unsigned int maxbit = maxfd / BITS_PER_LONG;
unsigned int bitbit = start / BITS_PER_LONG;
bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
if (bitbit > maxfd)
return maxfd;
if (bitbit > start)
start = bitbit;
return find_next_zero_bit(fdt->open_fds, maxfd, start);
}
/*
* allocate a file descriptor, mark it busy.
*/
int __alloc_fd(struct files_struct *files,
unsigned start, unsigned end, unsigned flags)
{
unsigned int fd;
int error;
struct fdtable *fdt;
spin_lock(&files->file_lock);
repeat:
fdt = files_fdtable(files);
fd = start;
if (fd < files->next_fd)
fd = files->next_fd;
if (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 (fd >= end)
goto out;
error = expand_files(files, fd);
if (error < 0)
goto out;
/*
* If we needed to expand the fs array we
* might have blocked - try again.
*/
if (error)
goto repeat;
if (start <= files->next_fd)
files->next_fd = fd + 1;
__set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
error = fd;
#if 1
/* Sanity check */
if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
rcu_assign_pointer(fdt->fd[fd], NULL);
}
#endif
out:
spin_unlock(&files->file_lock);
return error;
}
static int alloc_fd(unsigned start, unsigned flags)
{
return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
}
int get_unused_fd_flags(unsigned flags)
{
return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags);
}
EXPORT_SYMBOL(get_unused_fd_flags);
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
struct fdtable *fdt = files_fdtable(files);
__clear_open_fd(fd, fdt);
if (fd < files->next_fd)
files->next_fd = fd;
}
void put_unused_fd(unsigned int fd)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(put_unused_fd);
/*
* 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.
*
* NOTE: __fd_install() variant is really, really low-level; don't
* use it unless you are forced to by truly lousy API shoved down
* your throat. 'files' *MUST* be either current->files or obtained
* by get_files_struct(current) done by whoever had given it to you,
* or really bad things will happen. Normally you want to use
* fd_install() instead.
*/
void __fd_install(struct files_struct *files, unsigned int fd,
struct file *file)
{
struct fdtable *fdt;
rcu_read_lock_sched();
if (unlikely(files->resize_in_progress)) {
rcu_read_unlock_sched();
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
return;
}
/* coupled with smp_wmb() in expand_fdtable() */
smp_rmb();
fdt = rcu_dereference_sched(files->fdt);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
rcu_read_unlock_sched();
}
void fd_install(unsigned int fd, struct file *file)
{
__fd_install(current->files, fd, file);
}
EXPORT_SYMBOL(fd_install);
/*
* The same warnings as for __alloc_fd()/__fd_install() apply here...
*/
int __close_fd(struct files_struct *files, unsigned fd)
{
struct file *file;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
goto out_unlock;
file = fdt->fd[fd];
if (!file)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
return filp_close(file, files);
out_unlock:
spin_unlock(&files->file_lock);
return -EBADF;
}
EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
/*
* variant of __close_fd that gets a ref on the file for later fput
*/
int __close_fd_get_file(unsigned int fd, struct file **res)
{
struct files_struct *files = current->files;
struct file *file;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
goto out_unlock;
file = fdt->fd[fd];
if (!file)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
get_file(file);
*res = file;
return filp_close(file, files);
out_unlock:
spin_unlock(&files->file_lock);
*res = NULL;
return -ENOENT;
}
void do_close_on_exec(struct files_struct *files)
{
unsigned i;
struct fdtable *fdt;
/* exec unshares first */
spin_lock(&files->file_lock);
for (i = 0; ; i++) {
unsigned long set;
unsigned fd = i * BITS_PER_LONG;
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
break;
set = fdt->close_on_exec[i];
if (!set)
continue;
fdt->close_on_exec[i] = 0;
for ( ; set ; fd++, set >>= 1) {
struct file *file;
if (!(set & 1))
continue;
file = fdt->fd[fd];
if (!file)
continue;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
filp_close(file, files);
cond_resched();
spin_lock(&files->file_lock);
}
}
spin_unlock(&files->file_lock);
}
static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
{
struct files_struct *files = current->files;
struct file *file;
rcu_read_lock();
loop:
file = fcheck_files(files, fd);
if (file) {
/* File object ref couldn't be taken.
* dup2() atomicity guarantee is the reason
* we loop to catch the new file (or NULL pointer)
*/
if (file->f_mode & mask)
file = NULL;
else if (!get_file_rcu_many(file, refs))
goto loop;
}
rcu_read_unlock();
return file;
}
struct file *fget_many(unsigned int fd, unsigned int refs)
{
return __fget(fd, FMODE_PATH, refs);
}
struct file *fget(unsigned int fd)
{
return __fget(fd, FMODE_PATH, 1);
}
EXPORT_SYMBOL(fget);
struct file *fget_raw(unsigned int fd)
{
return __fget(fd, 0, 1);
}
EXPORT_SYMBOL(fget_raw);
/*
* 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)
{
struct files_struct *files = current->files;
struct file *file;
if (atomic_read(&files->count) == 1) {
file = __fcheck_files(files, fd);
if (!file || unlikely(file->f_mode & mask))
return 0;
return (unsigned long)file;
} else {
file = __fget(fd, mask, 1);
if (!file)
return 0;
return FDPUT_FPUT | (unsigned long)file;
}
}
unsigned long __fdget(unsigned int fd)
{
return __fget_light(fd, FMODE_PATH);
}
EXPORT_SYMBOL(__fdget);
unsigned long __fdget_raw(unsigned int fd)
{
return __fget_light(fd, 0);
}
unsigned long __fdget_pos(unsigned int fd)
{
unsigned long v = __fdget(fd);
struct file *file = (struct file *)(v & ~3);
if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
if (file_count(file) > 1) {
v |= FDPUT_POS_UNLOCK;
mutex_lock(&file->f_pos_lock);
}
}
return v;
}
void __f_unlock_pos(struct file *f)
{
mutex_unlock(&f->f_pos_lock);
}
/*
* 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)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (flag)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
spin_unlock(&files->file_lock);
}
bool get_close_on_exec(unsigned int fd)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
bool res;
rcu_read_lock();
fdt = files_fdtable(files);
res = close_on_exec(fd, fdt);
rcu_read_unlock();
return res;
}
static int do_dup2(struct files_struct *files,
struct file *file, unsigned fd, unsigned flags)
__releases(&files->file_lock)
{
struct file *tofree;
struct fdtable *fdt;
/*
* We need to detect attempts to do dup2() over allocated but still
* not finished descriptor. NB: OpenBSD avoids that at the price of
* extra work in their equivalent of fget() - they insert struct
* file immediately after grabbing descriptor, mark it larval if
* more work (e.g. actual opening) is needed and make sure that
* fget() treats larval files as absent. Potentially interesting,
* but while extra work in fget() is trivial, locking implications
* and amount of surgery on open()-related paths in VFS are not.
* FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
* deadlocks in rather amusing ways, AFAICS. All of that is out of
* scope of POSIX or SUS, since neither considers shared descriptor
* tables and this condition does not arise without those.
*/
fdt = files_fdtable(files);
tofree = 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);
if (flags & O_CLOEXEC)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
spin_unlock(&files->file_lock);
if (tofree)
filp_close(tofree, files);
return fd;
Ebusy:
spin_unlock(&files->file_lock);
return -EBUSY;
}
int replace_fd(unsigned fd, struct file *file, unsigned flags)
{
int err;
struct files_struct *files = current->files;
if (!file)
return __close_fd(files, fd);
if (fd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, fd);
if (unlikely(err < 0))
goto out_unlock;
return do_dup2(files, file, fd, flags);
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{
int err = -EBADF;
struct file *file;
struct files_struct *files = current->files;
if ((flags & ~O_CLOEXEC) != 0)
return -EINVAL;
if (unlikely(oldfd == newfd))
return -EINVAL;
if (newfd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, newfd);
file = fcheck(oldfd);
if (unlikely(!file))
goto Ebadf;
if (unlikely(err < 0)) {
if (err == -EMFILE)
goto Ebadf;
goto out_unlock;
}
return do_dup2(files, file, newfd, flags);
Ebadf:
err = -EBADF;
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{
return ksys_dup3(oldfd, newfd, flags);
}
SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
{
if (unlikely(newfd == oldfd)) { /* corner case */
struct files_struct *files = current->files;
int retval = oldfd;
rcu_read_lock();
if (!fcheck_files(files, oldfd))
retval = -EBADF;
rcu_read_unlock();
return retval;
}
return ksys_dup3(oldfd, newfd, 0);
}
int ksys_dup(unsigned int fildes)
{
int ret = -EBADF;
struct file *file = fget_raw(fildes);
if (file) {
ret = get_unused_fd_flags(0);
if (ret >= 0)
fd_install(ret, file);
else
fput(file);
}
return ret;
}
SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
return ksys_dup(fildes);
}
int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{
int err;
if (from >= rlimit(RLIMIT_NOFILE))
return -EINVAL;
err = alloc_fd(from, flags);
if (err >= 0) {
get_file(file);
fd_install(err, file);
}
return err;
}
int iterate_fd(struct files_struct *files, unsigned n,
int (*f)(const void *, struct file *, unsigned),
const void *p)
{
struct fdtable *fdt;
int res = 0;
if (!files)
return 0;
spin_lock(&files->file_lock);
for (fdt = files_fdtable(files); n < fdt->max_fds; n++) {
struct file *file;
file = rcu_dereference_check_fdtable(files, fdt->fd[n]);
if (!file)
continue;
res = f(p, file, n);
if (res)
break;
}
spin_unlock(&files->file_lock);
return res;
}
EXPORT_SYMBOL(iterate_fd);