fcntl.c 13.6 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>
Linus Torvalds's avatar
Linus Torvalds committed
21 22 23 24 25 26 27 28

#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;
29
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
30
	spin_lock(&files->file_lock);
31
	fdt = files_fdtable(files);
Linus Torvalds's avatar
Linus Torvalds committed
32
	if (flag)
33
		FD_SET(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
34
	else
35
		FD_CLR(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
36 37 38 39 40 41
	spin_unlock(&files->file_lock);
}

static inline int get_close_on_exec(unsigned int fd)
{
	struct files_struct *files = current->files;
42
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
43
	int res;
44
	rcu_read_lock();
45 46
	fdt = files_fdtable(files);
	res = FD_ISSET(fd, fdt->close_on_exec);
47
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
	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;
63
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
64 65 66 67 68 69

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

repeat:
70
	fdt = files_fdtable(files);
Linus Torvalds's avatar
Linus Torvalds committed
71 72
	/*
	 * Someone might have closed fd's in the range
73
	 * orig_start..fdt->next_fd
Linus Torvalds's avatar
Linus Torvalds committed
74 75
	 */
	start = orig_start;
76 77
	if (start < fdt->next_fd)
		start = fdt->next_fd;
Linus Torvalds's avatar
Linus Torvalds committed
78 79

	newfd = start;
80 81 82
	if (start < fdt->max_fdset) {
		newfd = find_next_zero_bit(fdt->open_fds->fds_bits,
			fdt->max_fdset, start);
Linus Torvalds's avatar
Linus Torvalds committed
83 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;

100 101 102 103 104 105
	/*
	 * 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.
	 */
	fdt = files_fdtable(files);
106 107
	if (start <= fdt->next_fd)
		fdt->next_fd = newfd + 1;
108

Linus Torvalds's avatar
Linus Torvalds committed
109 110 111 112 113 114 115 116 117
	error = newfd;
	
out:
	return error;
}

static int dupfd(struct file *file, unsigned int start)
{
	struct files_struct * files = current->files;
118
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
119 120 121 122 123
	int fd;

	spin_lock(&files->file_lock);
	fd = locate_fd(files, file, start);
	if (fd >= 0) {
124 125 126 127
		/* locate_fd() may have expanded fdtable, load the ptr */
		fdt = files_fdtable(files);
		FD_SET(fd, fdt->open_fds);
		FD_CLR(fd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
		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;
143
	struct fdtable *fdt;
Linus Torvalds's avatar
Linus Torvalds committed
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168

	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;
169 170 171
	fdt = files_fdtable(files);
	tofree = fdt->fd[newfd];
	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
Linus Torvalds's avatar
Linus Torvalds committed
172 173
		goto out_fput;

174
	rcu_assign_pointer(fdt->fd[newfd], file);
175 176
	FD_SET(newfd, fdt->open_fds);
	FD_CLR(newfd, fdt->close_on_exec);
Linus Torvalds's avatar
Linus Torvalds committed
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
	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)
		ret = dupfd(file, 0);
	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)
{
	struct inode * inode = filp->f_dentry->d_inode;
	int error = 0;

	/* O_APPEND cannot be cleared if the file is marked as append-only */
	if (!(arg & O_APPEND) && IS_APPEND(inode))
		return -EPERM;

	/* O_NOATIME can only be set by the owner or superuser */
	if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
		if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
			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;
}

static void f_modown(struct file *filp, unsigned long pid,
                     uid_t uid, uid_t euid, int force)
{
	write_lock_irq(&filp->f_owner.lock);
	if (force || !filp->f_owner.pid) {
		filp->f_owner.pid = pid;
		filp->f_owner.uid = uid;
		filp->f_owner.euid = euid;
	}
	write_unlock_irq(&filp->f_owner.lock);
}

int f_setown(struct file *filp, unsigned long arg, int force)
{
	int err;
	
	err = security_file_set_fowner(filp);
	if (err)
		return err;

	f_modown(filp, arg, current->uid, current->euid, force);
	return 0;
}

EXPORT_SYMBOL(f_setown);

void f_delown(struct file *filp)
{
	f_modown(filp, 0, 0, 0, 1);
}

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

	switch (cmd) {
	case F_DUPFD:
		get_file(filp);
		err = dupfd(filp, arg);
		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:
310
		err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
Linus Torvalds's avatar
Linus Torvalds committed
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
		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.
		 */
		err = filp->f_owner.pid;
		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. */
331
		if (!valid_signal(arg)) {
Linus Torvalds's avatar
Linus Torvalds committed
332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397
			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:
398 399
			err = fcntl_setlk64(fd, filp, cmd,
					(struct flock64 __user *) arg);
Linus Torvalds's avatar
Linus Torvalds committed
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
			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 */

static long band_table[NSIGPOLL] = {
	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.  */
			if ((reason & __SI_MASK) != __SI_POLL)
				BUG();
			if (reason - POLL_IN >= NSIGPOLL)
				si.si_band  = ~0L;
			else
				si.si_band = band_table[reason - POLL_IN];
			si.si_fd    = fd;
461
			if (!group_send_sig_info(fown->signum, &si, p))
Linus Torvalds's avatar
Linus Torvalds committed
462 463 464
				break;
		/* fall-through: fall back on the old plain SIGIO signal */
		case 0:
465
			group_send_sig_info(SIGIO, SEND_SIG_PRIV, p);
Linus Torvalds's avatar
Linus Torvalds committed
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
	}
}

void send_sigio(struct fown_struct *fown, int fd, int band)
{
	struct task_struct *p;
	int pid;
	
	read_lock(&fown->lock);
	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;
	
	read_lock(&tasklist_lock);
	if (pid > 0) {
		p = find_task_by_pid(pid);
		if (p) {
			send_sigio_to_task(p, fown, fd, band);
		}
	} else {
		do_each_task_pid(-pid, PIDTYPE_PGID, p) {
			send_sigio_to_task(p, fown, fd, band);
		} while_each_task_pid(-pid, PIDTYPE_PGID, p);
	}
	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))
499
		group_send_sig_info(SIGURG, SEND_SIG_PRIV, p);
Linus Torvalds's avatar
Linus Torvalds committed
500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
}

int send_sigurg(struct fown_struct *fown)
{
	struct task_struct *p;
	int pid, ret = 0;
	
	read_lock(&fown->lock);
	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;

	ret = 1;
	
	read_lock(&tasklist_lock);
	if (pid > 0) {
		p = find_task_by_pid(pid);
		if (p) {
			send_sigurg_to_task(p, fown);
		}
	} else {
		do_each_task_pid(-pid, PIDTYPE_PGID, p) {
			send_sigurg_to_task(p, fown);
		} while_each_task_pid(-pid, PIDTYPE_PGID, p);
	}
	read_unlock(&tasklist_lock);
 out_unlock_fown:
	read_unlock(&fown->lock);
	return ret;
}

static DEFINE_RWLOCK(fasync_lock);
static kmem_cache_t *fasync_cache;

/*
 * 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) {
		new = kmem_cache_alloc(fasync_cache, SLAB_KERNEL);
		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",
		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL, NULL);
	return 0;
}

module_init(fasync_init)