fcntl.c 14.4 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10 11
/*
 *  linux/fs/fcntl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/file.h>
12
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
13 14 15 16 17 18
#include <linux/dnotify.h>
#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/ptrace.h>
19
#include <linux/signal.h>
20
#include <linux/rcupdate.h>
21
#include <linux/pid_namespace.h>
Linus Torvalds's avatar
Linus Torvalds committed
22 23 24 25 26 27 28 29

#include <asm/poll.h>
#include <asm/siginfo.h>
#include <asm/uaccess.h>

void fastcall set_close_on_exec(unsigned int fd, int flag)
{
	struct files_struct *files = current->files;
30
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
31
	spin_lock(&files->file_lock);
32
	fdt = files_fdtable(files);
Linus Torvalds's avatar
Linus Torvalds committed
33
	if (flag)
34
		FD_SET(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
35
	else
36
		FD_CLR(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
37 38 39
	spin_unlock(&files->file_lock);
}

40
static int get_close_on_exec(unsigned int fd)
Linus Torvalds's avatar
Linus Torvalds committed
41 42
{
	struct files_struct *files = current->files;
43
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
44
	int res;
45
	rcu_read_lock();
46 47
	fdt = files_fdtable(files);
	res = FD_ISSET(fd, fdt->close_on_exec);
48
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
	return res;
}

/*
 * locate_fd finds a free file descriptor in the open_fds fdset,
 * expanding the fd arrays if necessary.  Must be called with the
 * file_lock held for write.
 */

static int locate_fd(struct files_struct *files, 
			    struct file *file, unsigned int orig_start)
{
	unsigned int newfd;
	unsigned int start;
	int error;
64
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
65 66 67 68 69 70

	error = -EINVAL;
	if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
		goto out;

repeat:
71
	fdt = files_fdtable(files);
Linus Torvalds's avatar
Linus Torvalds committed
72 73
	/*
	 * Someone might have closed fd's in the range
74
	 * orig_start..fdt->next_fd
Linus Torvalds's avatar
Linus Torvalds committed
75 76
	 */
	start = orig_start;
77 78
	if (start < files->next_fd)
		start = files->next_fd;
Linus Torvalds's avatar
Linus Torvalds committed
79 80

	newfd = start;
81
	if (start < fdt->max_fds)
82
		newfd = find_next_zero_bit(fdt->open_fds->fds_bits,
83
					   fdt->max_fds, start);
Linus Torvalds's avatar
Linus Torvalds committed
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99
	
	error = -EMFILE;
	if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
		goto out;

	error = expand_files(files, newfd);
	if (error < 0)
		goto out;

	/*
	 * If we needed to expand the fs array we
	 * might have blocked - try again.
	 */
	if (error)
		goto repeat;

100 101 102 103 104
	/*
	 * We reacquired files_lock, so we are safe as long as
	 * we reacquire the fdtable pointer and use it while holding
	 * the lock, no one can free it during that time.
	 */
105 106
	if (start <= files->next_fd)
		files->next_fd = newfd + 1;
107

Linus Torvalds's avatar
Linus Torvalds committed
108 109 110 111 112 113
	error = newfd;
	
out:
	return error;
}

114
static int dupfd(struct file *file, unsigned int start, int cloexec)
Linus Torvalds's avatar
Linus Torvalds committed
115 116
{
	struct files_struct * files = current->files;
117
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
118 119 120 121 122
	int fd;

	spin_lock(&files->file_lock);
	fd = locate_fd(files, file, start);
	if (fd >= 0) {
123 124 125
		/* locate_fd() may have expanded fdtable, load the ptr */
		fdt = files_fdtable(files);
		FD_SET(fd, fdt->open_fds);
126 127 128 129
		if (cloexec)
			FD_SET(fd, fdt->close_on_exec);
		else
			FD_CLR(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
		spin_unlock(&files->file_lock);
		fd_install(fd, file);
	} else {
		spin_unlock(&files->file_lock);
		fput(file);
	}

	return fd;
}

asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
{
	int err = -EBADF;
	struct file * file, *tofree;
	struct files_struct * files = current->files;
145
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170

	spin_lock(&files->file_lock);
	if (!(file = fcheck(oldfd)))
		goto out_unlock;
	err = newfd;
	if (newfd == oldfd)
		goto out_unlock;
	err = -EBADF;
	if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
		goto out_unlock;
	get_file(file);			/* We are now finished with oldfd */

	err = expand_files(files, newfd);
	if (err < 0)
		goto out_fput;

	/* To avoid races with open() and dup(), we will mark the fd as
	 * in-use in the open-file bitmap throughout the entire dup2()
	 * process.  This is quite safe: do_close() uses the fd array
	 * entry, not the bitmap, to decide what work needs to be
	 * done.  --sct */
	/* Doesn't work. open() might be there first. --AV */

	/* Yes. It's a race. In user space. Nothing sane to do */
	err = -EBUSY;
171 172 173
	fdt = files_fdtable(files);
	tofree = fdt->fd[newfd];
	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
Linus Torvalds's avatar
Linus Torvalds committed
174 175
		goto out_fput;

176
	rcu_assign_pointer(fdt->fd[newfd], file);
177 178
	FD_SET(newfd, fdt->open_fds);
	FD_CLR(newfd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
	spin_unlock(&files->file_lock);

	if (tofree)
		filp_close(tofree, files);
	err = newfd;
out:
	return err;
out_unlock:
	spin_unlock(&files->file_lock);
	goto out;

out_fput:
	spin_unlock(&files->file_lock);
	fput(file);
	goto out;
}

asmlinkage long sys_dup(unsigned int fildes)
{
	int ret = -EBADF;
	struct file * file = fget(fildes);

	if (file)
202
		ret = dupfd(file, 0, 0);
Linus Torvalds's avatar
Linus Torvalds committed
203 204 205 206 207 208 209
	return ret;
}

#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | FASYNC | O_DIRECT | O_NOATIME)

static int setfl(int fd, struct file * filp, unsigned long arg)
{
210
	struct inode * inode = filp->f_path.dentry->d_inode;
Linus Torvalds's avatar
Linus Torvalds committed
211 212
	int error = 0;

213 214 215 216 217
	/*
	 * O_APPEND cannot be cleared if the file is marked as append-only
	 * and the file is open for write.
	 */
	if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
Linus Torvalds's avatar
Linus Torvalds committed
218 219 220 221
		return -EPERM;

	/* O_NOATIME can only be set by the owner or superuser */
	if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
222
		if (!is_owner_or_cap(inode))
Linus Torvalds's avatar
Linus Torvalds committed
223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
			return -EPERM;

	/* required for strict SunOS emulation */
	if (O_NONBLOCK != O_NDELAY)
	       if (arg & O_NDELAY)
		   arg |= O_NONBLOCK;

	if (arg & O_DIRECT) {
		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
			!filp->f_mapping->a_ops->direct_IO)
				return -EINVAL;
	}

	if (filp->f_op && filp->f_op->check_flags)
		error = filp->f_op->check_flags(arg);
	if (error)
		return error;

	lock_kernel();
	if ((arg ^ filp->f_flags) & FASYNC) {
		if (filp->f_op && filp->f_op->fasync) {
			error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
			if (error < 0)
				goto out;
		}
	}

	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
 out:
	unlock_kernel();
	return error;
}

256
static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
Linus Torvalds's avatar
Linus Torvalds committed
257 258 259 260
                     uid_t uid, uid_t euid, int force)
{
	write_lock_irq(&filp->f_owner.lock);
	if (force || !filp->f_owner.pid) {
261 262 263
		put_pid(filp->f_owner.pid);
		filp->f_owner.pid = get_pid(pid);
		filp->f_owner.pid_type = type;
Linus Torvalds's avatar
Linus Torvalds committed
264 265 266 267 268 269
		filp->f_owner.uid = uid;
		filp->f_owner.euid = euid;
	}
	write_unlock_irq(&filp->f_owner.lock);
}

270 271
int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
		int force)
Linus Torvalds's avatar
Linus Torvalds committed
272 273 274 275 276 277 278
{
	int err;
	
	err = security_file_set_fowner(filp);
	if (err)
		return err;

279
	f_modown(filp, pid, type, current->uid, current->euid, force);
Linus Torvalds's avatar
Linus Torvalds committed
280 281
	return 0;
}
282
EXPORT_SYMBOL(__f_setown);
Linus Torvalds's avatar
Linus Torvalds committed
283

284 285 286 287 288 289 290 291 292 293 294 295
int f_setown(struct file *filp, unsigned long arg, int force)
{
	enum pid_type type;
	struct pid *pid;
	int who = arg;
	int result;
	type = PIDTYPE_PID;
	if (who < 0) {
		type = PIDTYPE_PGID;
		who = -who;
	}
	rcu_read_lock();
296
	pid = find_vpid(who);
297 298 299 300
	result = __f_setown(filp, pid, type, force);
	rcu_read_unlock();
	return result;
}
Linus Torvalds's avatar
Linus Torvalds committed
301 302 303 304
EXPORT_SYMBOL(f_setown);

void f_delown(struct file *filp)
{
305 306 307 308 309 310
	f_modown(filp, NULL, PIDTYPE_PID, 0, 0, 1);
}

pid_t f_getown(struct file *filp)
{
	pid_t pid;
311
	read_lock(&filp->f_owner.lock);
312
	pid = pid_nr_ns(filp->f_owner.pid, current->nsproxy->pid_ns);
313 314
	if (filp->f_owner.pid_type == PIDTYPE_PGID)
		pid = -pid;
315
	read_unlock(&filp->f_owner.lock);
316
	return pid;
Linus Torvalds's avatar
Linus Torvalds committed
317 318 319 320 321 322 323 324 325
}

static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
		struct file *filp)
{
	long err = -EINVAL;

	switch (cmd) {
	case F_DUPFD:
326
	case F_DUPFD_CLOEXEC:
Linus Torvalds's avatar
Linus Torvalds committed
327
		get_file(filp);
328
		err = dupfd(filp, arg, cmd == F_DUPFD_CLOEXEC);
Linus Torvalds's avatar
Linus Torvalds committed
329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347
		break;
	case F_GETFD:
		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
		break;
	case F_SETFD:
		err = 0;
		set_close_on_exec(fd, arg & FD_CLOEXEC);
		break;
	case F_GETFL:
		err = filp->f_flags;
		break;
	case F_SETFL:
		err = setfl(fd, filp, arg);
		break;
	case F_GETLK:
		err = fcntl_getlk(filp, (struct flock __user *) arg);
		break;
	case F_SETLK:
	case F_SETLKW:
348
		err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
Linus Torvalds's avatar
Linus Torvalds committed
349 350 351 352 353 354 355 356 357
		break;
	case F_GETOWN:
		/*
		 * XXX If f_owner is a process group, the
		 * negative return value will get converted
		 * into an error.  Oops.  If we keep the
		 * current syscall conventions, the only way
		 * to fix this will be in libc.
		 */
358
		err = f_getown(filp);
Linus Torvalds's avatar
Linus Torvalds committed
359 360 361 362 363 364 365 366 367 368
		force_successful_syscall_return();
		break;
	case F_SETOWN:
		err = f_setown(filp, arg, 1);
		break;
	case F_GETSIG:
		err = filp->f_owner.signum;
		break;
	case F_SETSIG:
		/* arg == 0 restores default behaviour. */
369
		if (!valid_signal(arg)) {
Linus Torvalds's avatar
Linus Torvalds committed
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435
			break;
		}
		err = 0;
		filp->f_owner.signum = arg;
		break;
	case F_GETLEASE:
		err = fcntl_getlease(filp);
		break;
	case F_SETLEASE:
		err = fcntl_setlease(fd, filp, arg);
		break;
	case F_NOTIFY:
		err = fcntl_dirnotify(fd, filp, arg);
		break;
	default:
		break;
	}
	return err;
}

asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg)
{	
	struct file *filp;
	long err = -EBADF;

	filp = fget(fd);
	if (!filp)
		goto out;

	err = security_file_fcntl(filp, cmd, arg);
	if (err) {
		fput(filp);
		return err;
	}

	err = do_fcntl(fd, cmd, arg, filp);

 	fput(filp);
out:
	return err;
}

#if BITS_PER_LONG == 32
asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg)
{	
	struct file * filp;
	long err;

	err = -EBADF;
	filp = fget(fd);
	if (!filp)
		goto out;

	err = security_file_fcntl(filp, cmd, arg);
	if (err) {
		fput(filp);
		return err;
	}
	err = -EBADF;
	
	switch (cmd) {
		case F_GETLK64:
			err = fcntl_getlk64(filp, (struct flock64 __user *) arg);
			break;
		case F_SETLK64:
		case F_SETLKW64:
436 437
			err = fcntl_setlk64(fd, filp, cmd,
					(struct flock64 __user *) arg);
Linus Torvalds's avatar
Linus Torvalds committed
438 439 440 441 442 443 444 445 446 447 448 449 450
			break;
		default:
			err = do_fcntl(fd, cmd, arg, filp);
			break;
	}
	fput(filp);
out:
	return err;
}
#endif

/* Table to convert sigio signal codes into poll band bitmaps */

451
static const long band_table[NSIGPOLL] = {
Linus Torvalds's avatar
Linus Torvalds committed
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491
	POLLIN | POLLRDNORM,			/* POLL_IN */
	POLLOUT | POLLWRNORM | POLLWRBAND,	/* POLL_OUT */
	POLLIN | POLLRDNORM | POLLMSG,		/* POLL_MSG */
	POLLERR,				/* POLL_ERR */
	POLLPRI | POLLRDBAND,			/* POLL_PRI */
	POLLHUP | POLLERR			/* POLL_HUP */
};

static inline int sigio_perm(struct task_struct *p,
                             struct fown_struct *fown, int sig)
{
	return (((fown->euid == 0) ||
		 (fown->euid == p->suid) || (fown->euid == p->uid) ||
		 (fown->uid == p->suid) || (fown->uid == p->uid)) &&
		!security_file_send_sigiotask(p, fown, sig));
}

static void send_sigio_to_task(struct task_struct *p,
			       struct fown_struct *fown, 
			       int fd,
			       int reason)
{
	if (!sigio_perm(p, fown, fown->signum))
		return;

	switch (fown->signum) {
		siginfo_t si;
		default:
			/* Queue a rt signal with the appropriate fd as its
			   value.  We use SI_SIGIO as the source, not 
			   SI_KERNEL, since kernel signals always get 
			   delivered even if we can't queue.  Failure to
			   queue in this case _should_ be reported; we fall
			   back to SIGIO in that case. --sct */
			si.si_signo = fown->signum;
			si.si_errno = 0;
		        si.si_code  = reason;
			/* Make sure we are called with one of the POLL_*
			   reasons, otherwise we could leak kernel stack into
			   userspace.  */
492
			BUG_ON((reason & __SI_MASK) != __SI_POLL);
Linus Torvalds's avatar
Linus Torvalds committed
493 494 495 496 497
			if (reason - POLL_IN >= NSIGPOLL)
				si.si_band  = ~0L;
			else
				si.si_band = band_table[reason - POLL_IN];
			si.si_fd    = fd;
498
			if (!group_send_sig_info(fown->signum, &si, p))
Linus Torvalds's avatar
Linus Torvalds committed
499 500 501
				break;
		/* fall-through: fall back on the old plain SIGIO signal */
		case 0:
502
			group_send_sig_info(SIGIO, SEND_SIG_PRIV, p);
Linus Torvalds's avatar
Linus Torvalds committed
503 504 505 506 507 508
	}
}

void send_sigio(struct fown_struct *fown, int fd, int band)
{
	struct task_struct *p;
509 510
	enum pid_type type;
	struct pid *pid;
Linus Torvalds's avatar
Linus Torvalds committed
511 512
	
	read_lock(&fown->lock);
513
	type = fown->pid_type;
Linus Torvalds's avatar
Linus Torvalds committed
514 515 516 517 518
	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;
	
	read_lock(&tasklist_lock);
519 520 521
	do_each_pid_task(pid, type, p) {
		send_sigio_to_task(p, fown, fd, band);
	} while_each_pid_task(pid, type, p);
Linus Torvalds's avatar
Linus Torvalds committed
522 523 524 525 526 527 528 529 530
	read_unlock(&tasklist_lock);
 out_unlock_fown:
	read_unlock(&fown->lock);
}

static void send_sigurg_to_task(struct task_struct *p,
                                struct fown_struct *fown)
{
	if (sigio_perm(p, fown, SIGURG))
531
		group_send_sig_info(SIGURG, SEND_SIG_PRIV, p);
Linus Torvalds's avatar
Linus Torvalds committed
532 533 534 535 536
}

int send_sigurg(struct fown_struct *fown)
{
	struct task_struct *p;
537 538 539
	enum pid_type type;
	struct pid *pid;
	int ret = 0;
Linus Torvalds's avatar
Linus Torvalds committed
540 541
	
	read_lock(&fown->lock);
542
	type = fown->pid_type;
Linus Torvalds's avatar
Linus Torvalds committed
543 544 545 546 547 548 549
	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;

	ret = 1;
	
	read_lock(&tasklist_lock);
550 551 552
	do_each_pid_task(pid, type, p) {
		send_sigurg_to_task(p, fown);
	} while_each_pid_task(pid, type, p);
Linus Torvalds's avatar
Linus Torvalds committed
553 554 555 556 557 558 559
	read_unlock(&tasklist_lock);
 out_unlock_fown:
	read_unlock(&fown->lock);
	return ret;
}

static DEFINE_RWLOCK(fasync_lock);
560
static struct kmem_cache *fasync_cache __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
561 562 563 564 565 566 567 568 569 570 571 572 573

/*
 * fasync_helper() is used by some character device drivers (mainly mice)
 * to set up the fasync queue. It returns negative on error, 0 if it did
 * no changes and positive if it added/deleted the entry.
 */
int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
{
	struct fasync_struct *fa, **fp;
	struct fasync_struct *new = NULL;
	int result = 0;

	if (on) {
574
		new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
		if (!new)
			return -ENOMEM;
	}
	write_lock_irq(&fasync_lock);
	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
		if (fa->fa_file == filp) {
			if(on) {
				fa->fa_fd = fd;
				kmem_cache_free(fasync_cache, new);
			} else {
				*fp = fa->fa_next;
				kmem_cache_free(fasync_cache, fa);
				result = 1;
			}
			goto out;
		}
	}

	if (on) {
		new->magic = FASYNC_MAGIC;
		new->fa_file = filp;
		new->fa_fd = fd;
		new->fa_next = *fapp;
		*fapp = new;
		result = 1;
	}
out:
	write_unlock_irq(&fasync_lock);
	return result;
}

EXPORT_SYMBOL(fasync_helper);

void __kill_fasync(struct fasync_struct *fa, int sig, int band)
{
	while (fa) {
		struct fown_struct * fown;
		if (fa->magic != FASYNC_MAGIC) {
			printk(KERN_ERR "kill_fasync: bad magic number in "
			       "fasync_struct!\n");
			return;
		}
		fown = &fa->fa_file->f_owner;
		/* Don't send SIGURG to processes which have not set a
		   queued signum: SIGURG has its own default signalling
		   mechanism. */
		if (!(sig == SIGURG && fown->signum == 0))
			send_sigio(fown, fa->fa_fd, band);
		fa = fa->fa_next;
	}
}

EXPORT_SYMBOL(__kill_fasync);

void kill_fasync(struct fasync_struct **fp, int sig, int band)
{
	/* First a quick test without locking: usually
	 * the list is empty.
	 */
	if (*fp) {
		read_lock(&fasync_lock);
		/* reread *fp after obtaining the lock */
		__kill_fasync(*fp, sig, band);
		read_unlock(&fasync_lock);
	}
}
EXPORT_SYMBOL(kill_fasync);

static int __init fasync_init(void)
{
	fasync_cache = kmem_cache_create("fasync_cache",
646
		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
Linus Torvalds's avatar
Linus Torvalds committed
647 648 649 650
	return 0;
}

module_init(fasync_init)