compat.c 52.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33
/*
 *  linux/fs/compat.c
 *
 *  Kernel compatibililty routines for e.g. 32 bit syscall support
 *  on 64 bit kernels.
 *
 *  Copyright (C) 2002       Stephen Rothwell, IBM Corporation
 *  Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
 *  Copyright (C) 1998       Eddie C. Dost  (ecd@skynet.be)
 *  Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
 *  Copyright (C) 2003       Pavel Machek (pavel@suse.cz)
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License version 2 as
 *  published by the Free Software Foundation.
 */

#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/fcntl.h>
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/vfs.h>
#include <linux/ioctl32.h>
#include <linux/ioctl.h>
#include <linux/init.h>
#include <linux/sockios.h>	/* for SIOCDEVPRIVATE */
#include <linux/smb.h>
#include <linux/smb_mount.h>
#include <linux/ncp_mount.h>
34
#include <linux/nfs4_mount.h>
L
Linus Torvalds 已提交
35 36 37 38 39
#include <linux/smp_lock.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/dirent.h>
R
Robert Love 已提交
40
#include <linux/fsnotify.h>
L
Linus Torvalds 已提交
41 42 43 44 45 46
#include <linux/highuid.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/syscall.h>
#include <linux/personality.h>
#include <linux/rwsem.h>
47 48
#include <linux/acct.h>
#include <linux/mm.h>
L
Linus Torvalds 已提交
49 50 51 52 53 54 55

#include <net/sock.h>		/* siocdevprivate_ioctl */

#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/ioctls.h>

56 57
extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);

L
Linus Torvalds 已提交
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
/*
 * Not all architectures have sys_utime, so implement this in terms
 * of sys_utimes.
 */
asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __user *t)
{
	struct timeval tv[2];

	if (t) {
		if (get_user(tv[0].tv_sec, &t->actime) ||
		    get_user(tv[1].tv_sec, &t->modtime))
			return -EFAULT;
		tv[0].tv_usec = 0;
		tv[1].tv_usec = 0;
	}
73
	return do_utimes(AT_FDCWD, filename, t ? tv : NULL);
L
Linus Torvalds 已提交
74 75
}

76
asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, struct compat_timeval __user *t)
L
Linus Torvalds 已提交
77 78 79
{
	struct timeval tv[2];

80
	if (t) {
L
Linus Torvalds 已提交
81 82 83 84
		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
		    get_user(tv[0].tv_usec, &t[0].tv_usec) ||
		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
		    get_user(tv[1].tv_usec, &t[1].tv_usec))
85 86
			return -EFAULT;
	}
87 88 89 90 91 92
	return do_utimes(dfd, filename, t ? tv : NULL);
}

asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval __user *t)
{
	return compat_sys_futimesat(AT_FDCWD, filename, t);
L
Linus Torvalds 已提交
93 94 95 96 97 98
}

asmlinkage long compat_sys_newstat(char __user * filename,
		struct compat_stat __user *statbuf)
{
	struct kstat stat;
99
	int error = vfs_stat_fd(AT_FDCWD, filename, &stat);
L
Linus Torvalds 已提交
100 101 102 103 104 105 106 107 108 109

	if (!error)
		error = cp_compat_stat(&stat, statbuf);
	return error;
}

asmlinkage long compat_sys_newlstat(char __user * filename,
		struct compat_stat __user *statbuf)
{
	struct kstat stat;
110
	int error = vfs_lstat_fd(AT_FDCWD, filename, &stat);
L
Linus Torvalds 已提交
111 112 113 114 115 116

	if (!error)
		error = cp_compat_stat(&stat, statbuf);
	return error;
}

117
#ifndef __ARCH_WANT_STAT64
118
asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user *filename,
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
		struct compat_stat __user *statbuf, int flag)
{
	struct kstat stat;
	int error = -EINVAL;

	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
		goto out;

	if (flag & AT_SYMLINK_NOFOLLOW)
		error = vfs_lstat_fd(dfd, filename, &stat);
	else
		error = vfs_stat_fd(dfd, filename, &stat);

	if (!error)
		error = cp_compat_stat(&stat, statbuf);

out:
	return error;
}
138
#endif
139

L
Linus Torvalds 已提交
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
asmlinkage long compat_sys_newfstat(unsigned int fd,
		struct compat_stat __user * statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_compat_stat(&stat, statbuf);
	return error;
}

static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
{
	
	if (sizeof ubuf->f_blocks == 4) {
		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
		    0xffffffff00000000ULL)
			return -EOVERFLOW;
		/* f_files and f_ffree may be -1; it's okay
		 * to stuff that into 32 bits */
		if (kbuf->f_files != 0xffffffffffffffffULL
		 && (kbuf->f_files & 0xffffffff00000000ULL))
			return -EOVERFLOW;
		if (kbuf->f_ffree != 0xffffffffffffffffULL
		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
			return -EOVERFLOW;
	}
	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
	    __put_user(kbuf->f_type, &ubuf->f_type) ||
	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
	    __put_user(kbuf->f_files, &ubuf->f_files) ||
	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
	    __put_user(0, &ubuf->f_spare[0]) || 
	    __put_user(0, &ubuf->f_spare[1]) || 
	    __put_user(0, &ubuf->f_spare[2]) || 
	    __put_user(0, &ubuf->f_spare[3]) || 
	    __put_user(0, &ubuf->f_spare[4]))
		return -EFAULT;
	return 0;
}

/*
 * The following statfs calls are copies of code from fs/open.c and
 * should be checked against those from time to time
 */
asmlinkage long compat_sys_statfs(const char __user *path, struct compat_statfs __user *buf)
{
	struct nameidata nd;
	int error;

	error = user_path_walk(path, &nd);
	if (!error) {
		struct kstatfs tmp;
		error = vfs_statfs(nd.dentry->d_inode->i_sb, &tmp);
201 202
		if (!error)
			error = put_compat_statfs(buf, &tmp);
L
Linus Torvalds 已提交
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218
		path_release(&nd);
	}
	return error;
}

asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
{
	struct file * file;
	struct kstatfs tmp;
	int error;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;
	error = vfs_statfs(file->f_dentry->d_inode->i_sb, &tmp);
219 220
	if (!error)
		error = put_compat_statfs(buf, &tmp);
L
Linus Torvalds 已提交
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
	fput(file);
out:
	return error;
}

static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
{
	if (sizeof ubuf->f_blocks == 4) {
		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
		    0xffffffff00000000ULL)
			return -EOVERFLOW;
		/* f_files and f_ffree may be -1; it's okay
		 * to stuff that into 32 bits */
		if (kbuf->f_files != 0xffffffffffffffffULL
		 && (kbuf->f_files & 0xffffffff00000000ULL))
			return -EOVERFLOW;
		if (kbuf->f_ffree != 0xffffffffffffffffULL
		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
			return -EOVERFLOW;
	}
	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
	    __put_user(kbuf->f_type, &ubuf->f_type) ||
	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
	    __put_user(kbuf->f_files, &ubuf->f_files) ||
	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
	    __put_user(kbuf->f_frsize, &ubuf->f_frsize))
		return -EFAULT;
	return 0;
}

asmlinkage long compat_sys_statfs64(const char __user *path, compat_size_t sz, struct compat_statfs64 __user *buf)
{
	struct nameidata nd;
	int error;

	if (sz != sizeof(*buf))
		return -EINVAL;

	error = user_path_walk(path, &nd);
	if (!error) {
		struct kstatfs tmp;
		error = vfs_statfs(nd.dentry->d_inode->i_sb, &tmp);
269 270
		if (!error)
			error = put_compat_statfs64(buf, &tmp);
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
		path_release(&nd);
	}
	return error;
}

asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
{
	struct file * file;
	struct kstatfs tmp;
	int error;

	if (sz != sizeof(*buf))
		return -EINVAL;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;
	error = vfs_statfs(file->f_dentry->d_inode->i_sb, &tmp);
290 291
	if (!error)
		error = put_compat_statfs64(buf, &tmp);
L
Linus Torvalds 已提交
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
	fput(file);
out:
	return error;
}

/* ioctl32 stuff, used by sparc64, parisc, s390x, ppc64, x86_64, MIPS */

#define IOCTL_HASHSIZE 256
static struct ioctl_trans *ioctl32_hash_table[IOCTL_HASHSIZE];

extern struct ioctl_trans ioctl_start[];
extern int ioctl_table_size;

static inline unsigned long ioctl32_hash(unsigned long cmd)
{
	return (((cmd >> 6) ^ (cmd >> 4) ^ cmd)) % IOCTL_HASHSIZE;
}

static void ioctl32_insert_translation(struct ioctl_trans *trans)
{
	unsigned long hash;
	struct ioctl_trans *t;

	hash = ioctl32_hash (trans->cmd);
	if (!ioctl32_hash_table[hash])
		ioctl32_hash_table[hash] = trans;
	else {
		t = ioctl32_hash_table[hash];
		while (t->next)
			t = t->next;
		trans->next = NULL;
		t->next = trans;
	}
}

static int __init init_sys32_ioctl(void)
{
	int i;

	for (i = 0; i < ioctl_table_size; i++) {
		if (ioctl_start[i].next != 0) { 
			printk("ioctl translation %d bad\n",i); 
			return -1;
		}

		ioctl32_insert_translation(&ioctl_start[i]);
	}
	return 0;
}

__initcall(init_sys32_ioctl);

static void compat_ioctl_error(struct file *filp, unsigned int fd,
		unsigned int cmd, unsigned long arg)
{
	char buf[10];
	char *fn = "?";
	char *path;

	/* find the name of the device. */
	path = (char *)__get_free_page(GFP_KERNEL);
	if (path) {
		fn = d_path(filp->f_dentry, filp->f_vfsmnt, path, PAGE_SIZE);
		if (IS_ERR(fn))
			fn = "?";
	}

	sprintf(buf,"'%c'", (cmd>>24) & 0x3f);
	if (!isprint(buf[1]))
		sprintf(buf, "%02x", buf[1]);
	printk("ioctl32(%s:%d): Unknown cmd fd(%d) "
			"cmd(%08x){%s} arg(%08x) on %s\n",
			current->comm, current->pid,
			(int)fd, (unsigned int)cmd, buf,
			(unsigned int)arg, fn);

	if (path)
		free_page((unsigned long)path);
}

asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
				unsigned long arg)
{
	struct file *filp;
	int error = -EBADF;
	struct ioctl_trans *t;
	int fput_needed;

	filp = fget_light(fd, &fput_needed);
	if (!filp)
		goto out;

	/* RED-PEN how should LSM module know it's handling 32bit? */
	error = security_file_ioctl(filp, cmd, arg);
	if (error)
		goto out_fput;

	/*
	 * To allow the compat_ioctl handlers to be self contained
	 * we need to check the common ioctls here first.
	 * Just handle them with the standard handlers below.
	 */
	switch (cmd) {
	case FIOCLEX:
	case FIONCLEX:
	case FIONBIO:
	case FIOASYNC:
	case FIOQSIZE:
		break;

	case FIBMAP:
	case FIGETBSZ:
	case FIONREAD:
		if (S_ISREG(filp->f_dentry->d_inode->i_mode))
			break;
		/*FALL THROUGH*/

	default:
		if (filp->f_op && filp->f_op->compat_ioctl) {
			error = filp->f_op->compat_ioctl(filp, cmd, arg);
			if (error != -ENOIOCTLCMD)
				goto out_fput;
		}

		if (!filp->f_op ||
		    (!filp->f_op->ioctl && !filp->f_op->unlocked_ioctl))
			goto do_ioctl;
		break;
	}

	for (t = ioctl32_hash_table[ioctl32_hash(cmd)]; t; t = t->next) {
		if (t->cmd == cmd)
			goto found_handler;
	}

	if (S_ISSOCK(filp->f_dentry->d_inode->i_mode) &&
	    cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
		error = siocdevprivate_ioctl(fd, cmd, arg);
	} else {
		static int count;

		if (++count <= 50)
			compat_ioctl_error(filp, fd, cmd, arg);
		error = -EINVAL;
	}

	goto out_fput;

 found_handler:
	if (t->handler) {
		lock_kernel();
		error = t->handler(fd, cmd, arg, filp);
		unlock_kernel();
		goto out_fput;
	}

 do_ioctl:
	error = vfs_ioctl(filp, fd, cmd, arg);
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}

static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
		unsigned long arg)
{
	mm_segment_t old_fs;
	struct flock f;
	long ret;

	switch (cmd) {
	case F_GETLK:
	case F_SETLK:
	case F_SETLKW:
		ret = get_compat_flock(&f, compat_ptr(arg));
		if (ret != 0)
			break;
		old_fs = get_fs();
		set_fs(KERNEL_DS);
		ret = sys_fcntl(fd, cmd, (unsigned long)&f);
		set_fs(old_fs);
		if (cmd == F_GETLK && ret == 0) {
527 528 529 530 531 532 533 534 535 536 537 538
			/* GETLK was successfule and we need to return the data...
			 * but it needs to fit in the compat structure.
			 * l_start shouldn't be too big, unless the original
			 * start + end is greater than COMPAT_OFF_T_MAX, in which
			 * case the app was asking for trouble, so we return
			 * -EOVERFLOW in that case.
			 * l_len could be too big, in which case we just truncate it,
			 * and only allow the app to see that part of the conflicting
			 * lock that might make sense to it anyway
			 */

			if (f.l_start > COMPAT_OFF_T_MAX)
L
Linus Torvalds 已提交
539
				ret = -EOVERFLOW;
540 541
			if (f.l_len > COMPAT_OFF_T_MAX)
				f.l_len = COMPAT_OFF_T_MAX;
L
Linus Torvalds 已提交
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
			if (ret == 0)
				ret = put_compat_flock(&f, compat_ptr(arg));
		}
		break;

	case F_GETLK64:
	case F_SETLK64:
	case F_SETLKW64:
		ret = get_compat_flock64(&f, compat_ptr(arg));
		if (ret != 0)
			break;
		old_fs = get_fs();
		set_fs(KERNEL_DS);
		ret = sys_fcntl(fd, (cmd == F_GETLK64) ? F_GETLK :
				((cmd == F_SETLK64) ? F_SETLK : F_SETLKW),
				(unsigned long)&f);
		set_fs(old_fs);
		if (cmd == F_GETLK64 && ret == 0) {
560 561
			/* need to return lock information - see above for commentary */
			if (f.l_start > COMPAT_LOFF_T_MAX)
L
Linus Torvalds 已提交
562
				ret = -EOVERFLOW;
563 564
			if (f.l_len > COMPAT_LOFF_T_MAX)
				f.l_len = COMPAT_LOFF_T_MAX;
L
Linus Torvalds 已提交
565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
			if (ret == 0)
				ret = put_compat_flock64(&f, compat_ptr(arg));
		}
		break;

	default:
		ret = sys_fcntl(fd, cmd, arg);
		break;
	}
	return ret;
}

asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
		unsigned long arg)
{
	if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64))
		return -EINVAL;
	return compat_sys_fcntl64(fd, cmd, arg);
}

asmlinkage long
compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p)
{
	long ret;
	aio_context_t ctx64;

	mm_segment_t oldfs = get_fs();
	if (unlikely(get_user(ctx64, ctx32p)))
		return -EFAULT;

	set_fs(KERNEL_DS);
	/* The __user pointer cast is valid because of the set_fs() */
	ret = sys_io_setup(nr_reqs, (aio_context_t __user *) &ctx64);
	set_fs(oldfs);
	/* truncating is ok because it's a user address */
	if (!ret)
		ret = put_user((u32) ctx64, ctx32p);
	return ret;
}

asmlinkage long
compat_sys_io_getevents(aio_context_t ctx_id,
				 unsigned long min_nr,
				 unsigned long nr,
				 struct io_event __user *events,
				 struct compat_timespec __user *timeout)
{
	long ret;
	struct timespec t;
	struct timespec __user *ut = NULL;

	ret = -EFAULT;
	if (unlikely(!access_ok(VERIFY_WRITE, events, 
				nr * sizeof(struct io_event))))
		goto out;
	if (timeout) {
		if (get_compat_timespec(&t, timeout))
			goto out;

		ut = compat_alloc_user_space(sizeof(*ut));
		if (copy_to_user(ut, &t, sizeof(t)) )
			goto out;
	} 
	ret = sys_io_getevents(ctx_id, min_nr, nr, events, ut);
out:
	return ret;
}

static inline long
copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
{
	compat_uptr_t uptr;
	int i;

	for (i = 0; i < nr; ++i) {
		if (get_user(uptr, ptr32 + i))
			return -EFAULT;
		if (put_user(compat_ptr(uptr), ptr64 + i))
			return -EFAULT;
	}
	return 0;
}

#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))

asmlinkage long
compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb)
{
	struct iocb __user * __user *iocb64; 
	long ret;

	if (unlikely(nr < 0))
		return -EINVAL;

	if (nr > MAX_AIO_SUBMITS)
		nr = MAX_AIO_SUBMITS;
	
	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
	ret = copy_iocb(nr, iocb, iocb64);
	if (!ret)
		ret = sys_io_submit(ctx_id, nr, iocb64);
	return ret;
}

struct compat_ncp_mount_data {
	compat_int_t version;
	compat_uint_t ncp_fd;
672
	__compat_uid_t mounted_uid;
L
Linus Torvalds 已提交
673 674 675 676 677
	compat_pid_t wdog_pid;
	unsigned char mounted_vol[NCP_VOLNAME_LEN + 1];
	compat_uint_t time_out;
	compat_uint_t retry_count;
	compat_uint_t flags;
678 679
	__compat_uid_t uid;
	__compat_gid_t gid;
L
Linus Torvalds 已提交
680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735
	compat_mode_t file_mode;
	compat_mode_t dir_mode;
};

struct compat_ncp_mount_data_v4 {
	compat_int_t version;
	compat_ulong_t flags;
	compat_ulong_t mounted_uid;
	compat_long_t wdog_pid;
	compat_uint_t ncp_fd;
	compat_uint_t time_out;
	compat_uint_t retry_count;
	compat_ulong_t uid;
	compat_ulong_t gid;
	compat_ulong_t file_mode;
	compat_ulong_t dir_mode;
};

static void *do_ncp_super_data_conv(void *raw_data)
{
	int version = *(unsigned int *)raw_data;

	if (version == 3) {
		struct compat_ncp_mount_data *c_n = raw_data;
		struct ncp_mount_data *n = raw_data;

		n->dir_mode = c_n->dir_mode;
		n->file_mode = c_n->file_mode;
		n->gid = c_n->gid;
		n->uid = c_n->uid;
		memmove (n->mounted_vol, c_n->mounted_vol, (sizeof (c_n->mounted_vol) + 3 * sizeof (unsigned int)));
		n->wdog_pid = c_n->wdog_pid;
		n->mounted_uid = c_n->mounted_uid;
	} else if (version == 4) {
		struct compat_ncp_mount_data_v4 *c_n = raw_data;
		struct ncp_mount_data_v4 *n = raw_data;

		n->dir_mode = c_n->dir_mode;
		n->file_mode = c_n->file_mode;
		n->gid = c_n->gid;
		n->uid = c_n->uid;
		n->retry_count = c_n->retry_count;
		n->time_out = c_n->time_out;
		n->ncp_fd = c_n->ncp_fd;
		n->wdog_pid = c_n->wdog_pid;
		n->mounted_uid = c_n->mounted_uid;
		n->flags = c_n->flags;
	} else if (version != 5) {
		return NULL;
	}

	return raw_data;
}

struct compat_smb_mount_data {
	compat_int_t version;
736 737 738
	__compat_uid_t mounted_uid;
	__compat_uid_t uid;
	__compat_gid_t gid;
L
Linus Torvalds 已提交
739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758
	compat_mode_t file_mode;
	compat_mode_t dir_mode;
};

static void *do_smb_super_data_conv(void *raw_data)
{
	struct smb_mount_data *s = raw_data;
	struct compat_smb_mount_data *c_s = raw_data;

	if (c_s->version != SMB_MOUNT_OLDVERSION)
		goto out;
	s->dir_mode = c_s->dir_mode;
	s->file_mode = c_s->file_mode;
	s->gid = c_s->gid;
	s->uid = c_s->uid;
	s->mounted_uid = c_s->mounted_uid;
 out:
	return raw_data;
}

759 760
struct compat_nfs_string {
	compat_uint_t len;
761
	compat_uptr_t data;
762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785
};

static inline void compat_nfs_string(struct nfs_string *dst,
				     struct compat_nfs_string *src)
{
	dst->data = compat_ptr(src->data);
	dst->len = src->len;
}

struct compat_nfs4_mount_data_v1 {
	compat_int_t version;
	compat_int_t flags;
	compat_int_t rsize;
	compat_int_t wsize;
	compat_int_t timeo;
	compat_int_t retrans;
	compat_int_t acregmin;
	compat_int_t acregmax;
	compat_int_t acdirmin;
	compat_int_t acdirmax;
	struct compat_nfs_string client_addr;
	struct compat_nfs_string mnt_path;
	struct compat_nfs_string hostname;
	compat_uint_t host_addrlen;
786
	compat_uptr_t host_addr;
787 788
	compat_int_t proto;
	compat_int_t auth_flavourlen;
789
	compat_uptr_t auth_flavours;
790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826
};

static int do_nfs4_super_data_conv(void *raw_data)
{
	int version = *(compat_uint_t *) raw_data;

	if (version == 1) {
		struct compat_nfs4_mount_data_v1 *raw = raw_data;
		struct nfs4_mount_data *real = raw_data;

		/* copy the fields backwards */
		real->auth_flavours = compat_ptr(raw->auth_flavours);
		real->auth_flavourlen = raw->auth_flavourlen;
		real->proto = raw->proto;
		real->host_addr = compat_ptr(raw->host_addr);
		real->host_addrlen = raw->host_addrlen;
		compat_nfs_string(&real->hostname, &raw->hostname);
		compat_nfs_string(&real->mnt_path, &raw->mnt_path);
		compat_nfs_string(&real->client_addr, &raw->client_addr);
		real->acdirmax = raw->acdirmax;
		real->acdirmin = raw->acdirmin;
		real->acregmax = raw->acregmax;
		real->acregmin = raw->acregmin;
		real->retrans = raw->retrans;
		real->timeo = raw->timeo;
		real->wsize = raw->wsize;
		real->rsize = raw->rsize;
		real->flags = raw->flags;
		real->version = raw->version;
	}
	else {
		return -EINVAL;
	}

	return 0;
}

L
Linus Torvalds 已提交
827 828 829 830
extern int copy_mount_options (const void __user *, unsigned long *);

#define SMBFS_NAME      "smbfs"
#define NCPFS_NAME      "ncpfs"
831
#define NFS4_NAME	"nfs4"
L
Linus Torvalds 已提交
832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866

asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name,
				 char __user * type, unsigned long flags,
				 void __user * data)
{
	unsigned long type_page;
	unsigned long data_page;
	unsigned long dev_page;
	char *dir_page;
	int retval;

	retval = copy_mount_options (type, &type_page);
	if (retval < 0)
		goto out;

	dir_page = getname(dir_name);
	retval = PTR_ERR(dir_page);
	if (IS_ERR(dir_page))
		goto out1;

	retval = copy_mount_options (dev_name, &dev_page);
	if (retval < 0)
		goto out2;

	retval = copy_mount_options (data, &data_page);
	if (retval < 0)
		goto out3;

	retval = -EINVAL;

	if (type_page) {
		if (!strcmp((char *)type_page, SMBFS_NAME)) {
			do_smb_super_data_conv((void *)data_page);
		} else if (!strcmp((char *)type_page, NCPFS_NAME)) {
			do_ncp_super_data_conv((void *)data_page);
867 868 869
		} else if (!strcmp((char *)type_page, NFS4_NAME)) {
			if (do_nfs4_super_data_conv((void *) data_page))
				goto out4;
L
Linus Torvalds 已提交
870 871 872 873 874 875 876 877
		}
	}

	lock_kernel();
	retval = do_mount((char*)dev_page, dir_page, (char*)type_page,
			flags, (void*)data_page);
	unlock_kernel();

878
 out4:
L
Linus Torvalds 已提交
879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216
	free_page(data_page);
 out3:
	free_page(dev_page);
 out2:
	putname(dir_page);
 out1:
	free_page(type_page);
 out:
	return retval;
}

#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
#define COMPAT_ROUND_UP(x) (((x)+sizeof(compat_long_t)-1) & \
				~(sizeof(compat_long_t)-1))

struct compat_old_linux_dirent {
	compat_ulong_t	d_ino;
	compat_ulong_t	d_offset;
	unsigned short	d_namlen;
	char		d_name[1];
};

struct compat_readdir_callback {
	struct compat_old_linux_dirent __user *dirent;
	int result;
};

static int compat_fillonedir(void *__buf, const char *name, int namlen,
			loff_t offset, ino_t ino, unsigned int d_type)
{
	struct compat_readdir_callback *buf = __buf;
	struct compat_old_linux_dirent __user *dirent;

	if (buf->result)
		return -EINVAL;
	buf->result++;
	dirent = buf->dirent;
	if (!access_ok(VERIFY_WRITE, dirent,
			(unsigned long)(dirent->d_name + namlen + 1) -
				(unsigned long)dirent))
		goto efault;
	if (	__put_user(ino, &dirent->d_ino) ||
		__put_user(offset, &dirent->d_offset) ||
		__put_user(namlen, &dirent->d_namlen) ||
		__copy_to_user(dirent->d_name, name, namlen) ||
		__put_user(0, dirent->d_name + namlen))
		goto efault;
	return 0;
efault:
	buf->result = -EFAULT;
	return -EFAULT;
}

asmlinkage long compat_sys_old_readdir(unsigned int fd,
	struct compat_old_linux_dirent __user *dirent, unsigned int count)
{
	int error;
	struct file *file;
	struct compat_readdir_callback buf;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	buf.result = 0;
	buf.dirent = dirent;

	error = vfs_readdir(file, compat_fillonedir, &buf);
	if (error >= 0)
		error = buf.result;

	fput(file);
out:
	return error;
}

struct compat_linux_dirent {
	compat_ulong_t	d_ino;
	compat_ulong_t	d_off;
	unsigned short	d_reclen;
	char		d_name[1];
};

struct compat_getdents_callback {
	struct compat_linux_dirent __user *current_dir;
	struct compat_linux_dirent __user *previous;
	int count;
	int error;
};

static int compat_filldir(void *__buf, const char *name, int namlen,
		loff_t offset, ino_t ino, unsigned int d_type)
{
	struct compat_linux_dirent __user * dirent;
	struct compat_getdents_callback *buf = __buf;
	int reclen = COMPAT_ROUND_UP(NAME_OFFSET(dirent) + namlen + 2);

	buf->error = -EINVAL;	/* only used if we fail.. */
	if (reclen > buf->count)
		return -EINVAL;
	dirent = buf->previous;
	if (dirent) {
		if (__put_user(offset, &dirent->d_off))
			goto efault;
	}
	dirent = buf->current_dir;
	if (__put_user(ino, &dirent->d_ino))
		goto efault;
	if (__put_user(reclen, &dirent->d_reclen))
		goto efault;
	if (copy_to_user(dirent->d_name, name, namlen))
		goto efault;
	if (__put_user(0, dirent->d_name + namlen))
		goto efault;
	if (__put_user(d_type, (char  __user *) dirent + reclen - 1))
		goto efault;
	buf->previous = dirent;
	dirent = (void __user *)dirent + reclen;
	buf->current_dir = dirent;
	buf->count -= reclen;
	return 0;
efault:
	buf->error = -EFAULT;
	return -EFAULT;
}

asmlinkage long compat_sys_getdents(unsigned int fd,
		struct compat_linux_dirent __user *dirent, unsigned int count)
{
	struct file * file;
	struct compat_linux_dirent __user * lastdirent;
	struct compat_getdents_callback buf;
	int error;

	error = -EFAULT;
	if (!access_ok(VERIFY_WRITE, dirent, count))
		goto out;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	buf.current_dir = dirent;
	buf.previous = NULL;
	buf.count = count;
	buf.error = 0;

	error = vfs_readdir(file, compat_filldir, &buf);
	if (error < 0)
		goto out_putf;
	error = buf.error;
	lastdirent = buf.previous;
	if (lastdirent) {
		if (put_user(file->f_pos, &lastdirent->d_off))
			error = -EFAULT;
		else
			error = count - buf.count;
	}

out_putf:
	fput(file);
out:
	return error;
}

#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64
#define COMPAT_ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1))

struct compat_getdents_callback64 {
	struct linux_dirent64 __user *current_dir;
	struct linux_dirent64 __user *previous;
	int count;
	int error;
};

static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset,
		     ino_t ino, unsigned int d_type)
{
	struct linux_dirent64 __user *dirent;
	struct compat_getdents_callback64 *buf = __buf;
	int jj = NAME_OFFSET(dirent);
	int reclen = COMPAT_ROUND_UP64(jj + namlen + 1);
	u64 off;

	buf->error = -EINVAL;	/* only used if we fail.. */
	if (reclen > buf->count)
		return -EINVAL;
	dirent = buf->previous;

	if (dirent) {
		if (__put_user_unaligned(offset, &dirent->d_off))
			goto efault;
	}
	dirent = buf->current_dir;
	if (__put_user_unaligned(ino, &dirent->d_ino))
		goto efault;
	off = 0;
	if (__put_user_unaligned(off, &dirent->d_off))
		goto efault;
	if (__put_user(reclen, &dirent->d_reclen))
		goto efault;
	if (__put_user(d_type, &dirent->d_type))
		goto efault;
	if (copy_to_user(dirent->d_name, name, namlen))
		goto efault;
	if (__put_user(0, dirent->d_name + namlen))
		goto efault;
	buf->previous = dirent;
	dirent = (void __user *)dirent + reclen;
	buf->current_dir = dirent;
	buf->count -= reclen;
	return 0;
efault:
	buf->error = -EFAULT;
	return -EFAULT;
}

asmlinkage long compat_sys_getdents64(unsigned int fd,
		struct linux_dirent64 __user * dirent, unsigned int count)
{
	struct file * file;
	struct linux_dirent64 __user * lastdirent;
	struct compat_getdents_callback64 buf;
	int error;

	error = -EFAULT;
	if (!access_ok(VERIFY_WRITE, dirent, count))
		goto out;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	buf.current_dir = dirent;
	buf.previous = NULL;
	buf.count = count;
	buf.error = 0;

	error = vfs_readdir(file, compat_filldir64, &buf);
	if (error < 0)
		goto out_putf;
	error = buf.error;
	lastdirent = buf.previous;
	if (lastdirent) {
		typeof(lastdirent->d_off) d_off = file->f_pos;
		__put_user_unaligned(d_off, &lastdirent->d_off);
		error = count - buf.count;
	}

out_putf:
	fput(file);
out:
	return error;
}
#endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */

static ssize_t compat_do_readv_writev(int type, struct file *file,
			       const struct compat_iovec __user *uvector,
			       unsigned long nr_segs, loff_t *pos)
{
	typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
	typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);

	compat_ssize_t tot_len;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov=iovstack, *vector;
	ssize_t ret;
	int seg;
	io_fn_t fn;
	iov_fn_t fnv;

	/*
	 * SuS says "The readv() function *may* fail if the iovcnt argument
	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
	 * traditionally returned zero for zero segments, so...
	 */
	ret = 0;
	if (nr_segs == 0)
		goto out;

	/*
	 * First get the "struct iovec" from user memory and
	 * verify all the pointers
	 */
	ret = -EINVAL;
	if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0))
		goto out;
	if (!file->f_op)
		goto out;
	if (nr_segs > UIO_FASTIOV) {
		ret = -ENOMEM;
		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
		if (!iov)
			goto out;
	}
	ret = -EFAULT;
	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
		goto out;

	/*
	 * Single unix specification:
	 * We should -EINVAL if an element length is not >= 0 and fitting an
	 * ssize_t.  The total length is fitting an ssize_t
	 *
	 * Be careful here because iov_len is a size_t not an ssize_t
	 */
	tot_len = 0;
	vector = iov;
	ret = -EINVAL;
	for (seg = 0 ; seg < nr_segs; seg++) {
		compat_ssize_t tmp = tot_len;
		compat_ssize_t len;
		compat_uptr_t buf;

		if (__get_user(len, &uvector->iov_len) ||
		    __get_user(buf, &uvector->iov_base)) {
			ret = -EFAULT;
			goto out;
		}
		if (len < 0)	/* size_t not fitting an compat_ssize_t .. */
			goto out;
		tot_len += len;
		if (tot_len < tmp) /* maths overflow on the compat_ssize_t */
			goto out;
		vector->iov_base = compat_ptr(buf);
		vector->iov_len = (compat_size_t) len;
		uvector++;
		vector++;
	}
	if (tot_len == 0) {
		ret = 0;
		goto out;
	}

	ret = rw_verify_area(type, file, pos, tot_len);
1217
	if (ret < 0)
L
Linus Torvalds 已提交
1218 1219
		goto out;

1220 1221 1222 1223
	ret = security_file_permission(file, type == READ ? MAY_READ:MAY_WRITE);
	if (ret)
		goto out;

L
Linus Torvalds 已提交
1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262
	fnv = NULL;
	if (type == READ) {
		fn = file->f_op->read;
		fnv = file->f_op->readv;
	} else {
		fn = (io_fn_t)file->f_op->write;
		fnv = file->f_op->writev;
	}
	if (fnv) {
		ret = fnv(file, iov, nr_segs, pos);
		goto out;
	}

	/* Do it by hand, with file-ops */
	ret = 0;
	vector = iov;
	while (nr_segs > 0) {
		void __user * base;
		size_t len;
		ssize_t nr;

		base = vector->iov_base;
		len = vector->iov_len;
		vector++;
		nr_segs--;

		nr = fn(file, base, len, pos);

		if (nr < 0) {
			if (!ret) ret = nr;
			break;
		}
		ret += nr;
		if (nr != len)
			break;
	}
out:
	if (iov != iovstack)
		kfree(iov);
R
Robert Love 已提交
1263 1264 1265 1266 1267 1268 1269
	if ((ret + (type == READ)) > 0) {
		struct dentry *dentry = file->f_dentry;
		if (type == READ)
			fsnotify_access(dentry);
		else
			fsnotify_modify(dentry);
	}
L
Linus Torvalds 已提交
1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
	return ret;
}

asmlinkage ssize_t
compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen)
{
	struct file *file;
	ssize_t ret = -EBADF;

	file = fget(fd);
	if (!file)
		return -EBADF;

	if (!(file->f_mode & FMODE_READ))
		goto out;

	ret = -EINVAL;
	if (!file->f_op || (!file->f_op->readv && !file->f_op->read))
		goto out;

	ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos);

out:
	fput(file);
	return ret;
}

asmlinkage ssize_t
compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen)
{
	struct file *file;
	ssize_t ret = -EBADF;

	file = fget(fd);
	if (!file)
		return -EBADF;
	if (!(file->f_mode & FMODE_WRITE))
		goto out;

	ret = -EINVAL;
	if (!file->f_op || (!file->f_op->writev && !file->f_op->write))
		goto out;

	ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos);

out:
	fput(file);
	return ret;
}

1320 1321 1322 1323 1324 1325
asmlinkage long
compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32,
		    unsigned int nr_segs, unsigned int flags)
{
	unsigned i;
	struct iovec *iov;
1326
	if (nr_segs > UIO_MAXIOV)
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339
		return -EINVAL;
	iov = compat_alloc_user_space(nr_segs * sizeof(struct iovec));
	for (i = 0; i < nr_segs; i++) {
		struct compat_iovec v;
		if (get_user(v.iov_base, &iov32[i].iov_base) ||
		    get_user(v.iov_len, &iov32[i].iov_len) ||
		    put_user(compat_ptr(v.iov_base), &iov[i].iov_base) ||
		    put_user(v.iov_len, &iov[i].iov_len))
			return -EFAULT;
	}
	return sys_vmsplice(fd, iov, nr_segs, flags);
}

1340 1341 1342 1343 1344 1345 1346
/*
 * Exactly like fs/open.c:sys_open(), except that it doesn't set the
 * O_LARGEFILE flag.
 */
asmlinkage long
compat_sys_open(const char __user *filename, int flags, int mode)
{
1347 1348 1349 1350 1351 1352 1353 1354
	return do_sys_open(AT_FDCWD, filename, flags, mode);
}

/*
 * Exactly like fs/open.c:sys_openat(), except that it doesn't set the
 * O_LARGEFILE flag.
 */
asmlinkage long
1355
compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, int mode)
1356 1357
{
	return do_sys_open(dfd, filename, flags, mode);
1358 1359
}

L
Linus Torvalds 已提交
1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502
/*
 * compat_count() counts the number of arguments/envelopes. It is basically
 * a copy of count() from fs/exec.c, except that it works with 32 bit argv
 * and envp pointers.
 */
static int compat_count(compat_uptr_t __user *argv, int max)
{
	int i = 0;

	if (argv != NULL) {
		for (;;) {
			compat_uptr_t p;

			if (get_user(p, argv))
				return -EFAULT;
			if (!p)
				break;
			argv++;
			if(++i > max)
				return -E2BIG;
		}
	}
	return i;
}

/*
 * compat_copy_strings() is basically a copy of copy_strings() from fs/exec.c
 * except that it works with 32 bit argv and envp pointers.
 */
static int compat_copy_strings(int argc, compat_uptr_t __user *argv,
				struct linux_binprm *bprm)
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
	int ret;

	while (argc-- > 0) {
		compat_uptr_t str;
		int len;
		unsigned long pos;

		if (get_user(str, argv+argc) ||
			!(len = strnlen_user(compat_ptr(str), bprm->p))) {
			ret = -EFAULT;
			goto out;
		}

		if (bprm->p < len)  {
			ret = -E2BIG;
			goto out;
		}

		bprm->p -= len;
		/* XXX: add architecture specific overflow check here. */
		pos = bprm->p;

		while (len > 0) {
			int i, new, err;
			int offset, bytes_to_copy;
			struct page *page;

			offset = pos % PAGE_SIZE;
			i = pos/PAGE_SIZE;
			page = bprm->page[i];
			new = 0;
			if (!page) {
				page = alloc_page(GFP_HIGHUSER);
				bprm->page[i] = page;
				if (!page) {
					ret = -ENOMEM;
					goto out;
				}
				new = 1;
			}

			if (page != kmapped_page) {
				if (kmapped_page)
					kunmap(kmapped_page);
				kmapped_page = page;
				kaddr = kmap(kmapped_page);
			}
			if (new && offset)
				memset(kaddr, 0, offset);
			bytes_to_copy = PAGE_SIZE - offset;
			if (bytes_to_copy > len) {
				bytes_to_copy = len;
				if (new)
					memset(kaddr+offset+len, 0,
						PAGE_SIZE-offset-len);
			}
			err = copy_from_user(kaddr+offset, compat_ptr(str),
						bytes_to_copy);
			if (err) {
				ret = -EFAULT;
				goto out;
			}

			pos += bytes_to_copy;
			str += bytes_to_copy;
			len -= bytes_to_copy;
		}
	}
	ret = 0;
out:
	if (kmapped_page)
		kunmap(kmapped_page);
	return ret;
}

#ifdef CONFIG_MMU

#define free_arg_pages(bprm) do { } while (0)

#else

static inline void free_arg_pages(struct linux_binprm *bprm)
{
	int i;

	for (i = 0; i < MAX_ARG_PAGES; i++) {
		if (bprm->page[i])
			__free_page(bprm->page[i]);
		bprm->page[i] = NULL;
	}
}

#endif /* CONFIG_MMU */

/*
 * compat_do_execve() is mostly a copy of do_execve(), with the exception
 * that it processes 32 bit argv and envp pointers.
 */
int compat_do_execve(char * filename,
	compat_uptr_t __user *argv,
	compat_uptr_t __user *envp,
	struct pt_regs * regs)
{
	struct linux_binprm *bprm;
	struct file *file;
	int retval;
	int i;

	retval = -ENOMEM;
1503
	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
L
Linus Torvalds 已提交
1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561
	if (!bprm)
		goto out_ret;

	file = open_exec(filename);
	retval = PTR_ERR(file);
	if (IS_ERR(file))
		goto out_kfree;

	sched_exec();

	bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;
	bprm->mm = mm_alloc();
	retval = -ENOMEM;
	if (!bprm->mm)
		goto out_file;

	retval = init_new_context(current, bprm->mm);
	if (retval < 0)
		goto out_mm;

	bprm->argc = compat_count(argv, bprm->p / sizeof(compat_uptr_t));
	if ((retval = bprm->argc) < 0)
		goto out_mm;

	bprm->envc = compat_count(envp, bprm->p / sizeof(compat_uptr_t));
	if ((retval = bprm->envc) < 0)
		goto out_mm;

	retval = security_bprm_alloc(bprm);
	if (retval)
		goto out;

	retval = prepare_binprm(bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings_kernel(1, &bprm->filename, bprm);
	if (retval < 0)
		goto out;

	bprm->exec = bprm->p;
	retval = compat_copy_strings(bprm->envc, envp, bprm);
	if (retval < 0)
		goto out;

	retval = compat_copy_strings(bprm->argc, argv, bprm);
	if (retval < 0)
		goto out;

	retval = search_binary_handler(bprm, regs);
	if (retval >= 0) {
		free_arg_pages(bprm);

		/* execve success */
		security_bprm_free(bprm);
1562
		acct_update_integrals(current);
L
Linus Torvalds 已提交
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
		kfree(bprm);
		return retval;
	}

out:
	/* Something went wrong, return the inode and free the argument pages*/
	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
		struct page * page = bprm->page[i];
		if (page)
			__free_page(page);
	}

	if (bprm->security)
		security_bprm_free(bprm);

out_mm:
	if (bprm->mm)
		mmdrop(bprm->mm);

out_file:
	if (bprm->file) {
		allow_write_access(bprm->file);
		fput(bprm->file);
	}

out_kfree:
	kfree(bprm);

out_ret:
	return retval;
}

#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))

#define ROUND_UP(x,y) (((x)+(y)-1)/(y))

/*
 * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
 * 64-bit unsigned longs.
 */
1603
static
L
Linus Torvalds 已提交
1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635
int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
			unsigned long *fdset)
{
	nr = ROUND_UP(nr, __COMPAT_NFDBITS);
	if (ufdset) {
		unsigned long odd;

		if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t)))
			return -EFAULT;

		odd = nr & 1UL;
		nr &= ~1UL;
		while (nr) {
			unsigned long h, l;
			__get_user(l, ufdset);
			__get_user(h, ufdset+1);
			ufdset += 2;
			*fdset++ = h << 32 | l;
			nr -= 2;
		}
		if (odd)
			__get_user(*fdset, ufdset);
	} else {
		/* Tricky, must clear full unsigned long in the
		 * kernel fdset at the end, this makes sure that
		 * actually happens.
		 */
		memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t));
	}
	return 0;
}

1636
static
L
Linus Torvalds 已提交
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677
void compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
			unsigned long *fdset)
{
	unsigned long odd;
	nr = ROUND_UP(nr, __COMPAT_NFDBITS);

	if (!ufdset)
		return;

	odd = nr & 1UL;
	nr &= ~1UL;
	while (nr) {
		unsigned long h, l;
		l = *fdset++;
		h = l >> 32;
		__put_user(l, ufdset);
		__put_user(h, ufdset+1);
		ufdset += 2;
		nr -= 2;
	}
	if (odd)
		__put_user(*fdset, ufdset);
}


/*
 * This is a virtual copy of sys_select from fs/select.c and probably
 * should be compared to it from time to time
 */

/*
 * We can actually return ERESTARTSYS instead of EINTR, but I'd
 * like to be certain this leads to no problems. So I return
 * EINTR just for safety.
 *
 * Update: ERESTARTSYS breaks at least the xview clock binary, so
 * I'm trying ERESTARTNOHAND which restart only when you want to.
 */
#define MAX_SELECT_SECONDS \
	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)

1678 1679
int compat_core_sys_select(int n, compat_ulong_t __user *inp,
	compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
L
Linus Torvalds 已提交
1680 1681 1682 1683
{
	fd_set_bits fds;
	char *bits;
	int size, max_fdset, ret = -EINVAL;
1684
	struct fdtable *fdt;
L
Linus Torvalds 已提交
1685 1686 1687 1688 1689

	if (n < 0)
		goto out_nofds;

	/* max_fdset can increase, so grab it once to avoid race */
L
Linus Torvalds 已提交
1690
	rcu_read_lock();
1691 1692
	fdt = files_fdtable(current->files);
	max_fdset = fdt->max_fdset;
L
Linus Torvalds 已提交
1693
	rcu_read_unlock();
L
Linus Torvalds 已提交
1694 1695 1696 1697 1698 1699 1700 1701 1702 1703
	if (n > max_fdset)
		n = max_fdset;

	/*
	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
	 * since we used fdset we need to allocate memory in units of
	 * long-words.
	 */
	ret = -ENOMEM;
	size = FDS_BYTES(n);
1704
	bits = kmalloc(6 * size, GFP_KERNEL);
L
Linus Torvalds 已提交
1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721
	if (!bits)
		goto out_nofds;
	fds.in      = (unsigned long *)  bits;
	fds.out     = (unsigned long *) (bits +   size);
	fds.ex      = (unsigned long *) (bits + 2*size);
	fds.res_in  = (unsigned long *) (bits + 3*size);
	fds.res_out = (unsigned long *) (bits + 4*size);
	fds.res_ex  = (unsigned long *) (bits + 5*size);

	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
	    (ret = compat_get_fd_set(n, exp, fds.ex)))
		goto out;
	zero_fd_set(n, fds.res_in);
	zero_fd_set(n, fds.res_out);
	zero_fd_set(n, fds.res_ex);

1722
	ret = do_select(n, &fds, timeout);
L
Linus Torvalds 已提交
1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737

	if (ret < 0)
		goto out;
	if (!ret) {
		ret = -ERESTARTNOHAND;
		if (signal_pending(current))
			goto out;
		ret = 0;
	}

	compat_set_fd_set(n, inp, fds.res_in);
	compat_set_fd_set(n, outp, fds.res_out);
	compat_set_fd_set(n, exp, fds.res_ex);

out:
1738
	kfree(bits);
L
Linus Torvalds 已提交
1739 1740 1741 1742
out_nofds:
	return ret;
}

1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761
asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
	struct compat_timeval __user *tvp)
{
	s64 timeout = -1;
	struct compat_timeval tv;
	int ret;

	if (tvp) {
		if (copy_from_user(&tv, tvp, sizeof(tv)))
			return -EFAULT;

		if (tv.tv_sec < 0 || tv.tv_usec < 0)
			return -EINVAL;

		/* Cast to u64 to make GCC stop complaining */
		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
			timeout = -1;	/* infinite */
		else {
1762
			timeout = ROUND_UP(tv.tv_usec, 1000000/HZ);
1763 1764 1765 1766 1767 1768 1769
			timeout += tv.tv_sec * HZ;
		}
	}

	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);

	if (tvp) {
1770 1771
		struct compat_timeval rtv;

1772 1773
		if (current->personality & STICKY_TIMEOUTS)
			goto sticky;
1774 1775
		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
		rtv.tv_sec = timeout;
1776
		if (compat_timeval_compare(&rtv, &tv) >= 0)
1777 1778
			rtv = tv;
		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
sticky:
			/*
			 * If an application puts its timeval in read-only
			 * memory, we don't want the Linux-specific update to
			 * the timeval to cause a fault after the select has
			 * completed successfully. However, because we're not
			 * updating the timeval, we can't restart the system
			 * call.
			 */
			if (ret == -ERESTARTNOHAND)
				ret = -EINTR;
		}
	}

	return ret;
}

#ifdef TIF_RESTORE_SIGMASK
asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
	compat_size_t sigsetsize)
{
	compat_sigset_t ss32;
	sigset_t ksigmask, sigsaved;
1804
	s64 timeout = MAX_SCHEDULE_TIMEOUT;
1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844
	struct compat_timespec ts;
	int ret;

	if (tsp) {
		if (copy_from_user(&ts, tsp, sizeof(ts)))
			return -EFAULT;

		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
			return -EINVAL;
	}

	if (sigmask) {
		if (sigsetsize != sizeof(compat_sigset_t))
			return -EINVAL;
		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
			return -EFAULT;
		sigset_from_compat(&ksigmask, &ss32);

		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
	}

	do {
		if (tsp) {
			if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
				timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ);
				timeout += ts.tv_sec * (unsigned long)HZ;
				ts.tv_sec = 0;
				ts.tv_nsec = 0;
			} else {
				ts.tv_sec -= MAX_SELECT_SECONDS;
				timeout = MAX_SELECT_SECONDS * HZ;
			}
		}

		ret = compat_core_sys_select(n, inp, outp, exp, &timeout);

	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));

	if (tsp && !(current->personality & STICKY_TIMEOUTS)) {
1845 1846 1847 1848 1849 1850 1851
		struct compat_timespec rts;

		rts.tv_sec = timeout / HZ;
		rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
		if (rts.tv_nsec >= NSEC_PER_SEC) {
			rts.tv_sec++;
			rts.tv_nsec -= NSEC_PER_SEC;
1852
		}
1853
		if (compat_timespec_compare(&rts, &ts) >= 0)
1854 1855
			rts = ts;
		copy_to_user(tsp, &rts, sizeof(rts));
1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910
	}

	if (ret == -ERESTARTNOHAND) {
		/*
		 * Don't restore the signal mask yet. Let do_signal() deliver
		 * the signal on the way back to userspace, before the signal
		 * mask is restored.
		 */
		if (sigmask) {
			memcpy(&current->saved_sigmask, &sigsaved,
					sizeof(sigsaved));
			set_thread_flag(TIF_RESTORE_SIGMASK);
		}
	} else if (sigmask)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	return ret;
}

asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
	struct compat_timespec __user *tsp, void __user *sig)
{
	compat_size_t sigsetsize = 0;
	compat_uptr_t up = 0;

	if (sig) {
		if (!access_ok(VERIFY_READ, sig,
				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
		    	__get_user(up, (compat_uptr_t __user *)sig) ||
		    	__get_user(sigsetsize,
				(compat_size_t __user *)(sig+sizeof(up))))
			return -EFAULT;
	}
	return compat_sys_pselect7(n, inp, outp, exp, tsp, compat_ptr(up),
					sigsetsize);
}

asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
	unsigned int nfds, struct compat_timespec __user *tsp,
	const compat_sigset_t __user *sigmask, compat_size_t sigsetsize)
{
	compat_sigset_t ss32;
	sigset_t ksigmask, sigsaved;
	struct compat_timespec ts;
	s64 timeout = -1;
	int ret;

	if (tsp) {
		if (copy_from_user(&ts, tsp, sizeof(ts)))
			return -EFAULT;

		/* We assume that ts.tv_sec is always lower than
		   the number of seconds that can be expressed in
		   an s64. Otherwise the compiler bitches at us */
1911
		timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ);
1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
		timeout += ts.tv_sec * HZ;
	}

	if (sigmask) {
		if (sigsetsize |= sizeof(compat_sigset_t))
			return -EINVAL;
		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
			return -EFAULT;
		sigset_from_compat(&ksigmask, &ss32);

		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
	}

	ret = do_sys_poll(ufds, nfds, &timeout);

	/* We can restart this syscall, usually */
	if (ret == -EINTR) {
		/*
		 * Don't restore the signal mask yet. Let do_signal() deliver
		 * the signal on the way back to userspace, before the signal
		 * mask is restored.
		 */
		if (sigmask) {
			memcpy(&current->saved_sigmask, &sigsaved,
				sizeof(sigsaved));
			set_thread_flag(TIF_RESTORE_SIGMASK);
		}
		ret = -ERESTARTNOHAND;
	} else if (sigmask)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	if (tsp && timeout >= 0) {
1945 1946
		struct compat_timespec rts;

1947 1948 1949
		if (current->personality & STICKY_TIMEOUTS)
			goto sticky;
		/* Yes, we know it's actually an s64, but it's also positive. */
1950 1951 1952
		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
					1000;
		rts.tv_sec = timeout;
1953
		if (compat_timespec_compare(&rts, &ts) >= 0)
1954 1955
			rts = ts;
		if (copy_to_user(tsp, &rts, sizeof(rts))) {
1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973
sticky:
			/*
			 * If an application puts its timeval in read-only
			 * memory, we don't want the Linux-specific update to
			 * the timeval to cause a fault after the select has
			 * completed successfully. However, because we're not
			 * updating the timeval, we can't restart the system
			 * call.
			 */
			if (ret == -ERESTARTNOHAND && timeout >= 0)
				ret = -EINTR;
		}
	}

	return ret;
}
#endif /* TIF_RESTORE_SIGMASK */

L
Linus Torvalds 已提交
1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995
#if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)
/* Stuff for NFS server syscalls... */
struct compat_nfsctl_svc {
	u16			svc32_port;
	s32			svc32_nthreads;
};

struct compat_nfsctl_client {
	s8			cl32_ident[NFSCLNT_IDMAX+1];
	s32			cl32_naddr;
	struct in_addr		cl32_addrlist[NFSCLNT_ADDRMAX];
	s32			cl32_fhkeytype;
	s32			cl32_fhkeylen;
	u8			cl32_fhkey[NFSCLNT_KEYMAX];
};

struct compat_nfsctl_export {
	char		ex32_client[NFSCLNT_IDMAX+1];
	char		ex32_path[NFS_MAXPATHLEN+1];
	compat_dev_t	ex32_dev;
	compat_ino_t	ex32_ino;
	compat_int_t	ex32_flags;
1996 1997
	__compat_uid_t	ex32_anon_uid;
	__compat_gid_t	ex32_anon_gid;
L
Linus Torvalds 已提交
1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186
};

struct compat_nfsctl_fdparm {
	struct sockaddr		gd32_addr;
	s8			gd32_path[NFS_MAXPATHLEN+1];
	compat_int_t		gd32_version;
};

struct compat_nfsctl_fsparm {
	struct sockaddr		gd32_addr;
	s8			gd32_path[NFS_MAXPATHLEN+1];
	compat_int_t		gd32_maxlen;
};

struct compat_nfsctl_arg {
	compat_int_t		ca32_version;	/* safeguard */
	union {
		struct compat_nfsctl_svc	u32_svc;
		struct compat_nfsctl_client	u32_client;
		struct compat_nfsctl_export	u32_export;
		struct compat_nfsctl_fdparm	u32_getfd;
		struct compat_nfsctl_fsparm	u32_getfs;
	} u;
#define ca32_svc	u.u32_svc
#define ca32_client	u.u32_client
#define ca32_export	u.u32_export
#define ca32_getfd	u.u32_getfd
#define ca32_getfs	u.u32_getfs
};

union compat_nfsctl_res {
	__u8			cr32_getfh[NFS_FHSIZE];
	struct knfsd_fh		cr32_getfs;
};

static int compat_nfs_svc_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg)
{
	int err;

	err = access_ok(VERIFY_READ, &arg->ca32_svc, sizeof(arg->ca32_svc));
	err |= get_user(karg->ca_version, &arg->ca32_version);
	err |= __get_user(karg->ca_svc.svc_port, &arg->ca32_svc.svc32_port);
	err |= __get_user(karg->ca_svc.svc_nthreads, &arg->ca32_svc.svc32_nthreads);
	return (err) ? -EFAULT : 0;
}

static int compat_nfs_clnt_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg)
{
	int err;

	err = access_ok(VERIFY_READ, &arg->ca32_client, sizeof(arg->ca32_client));
	err |= get_user(karg->ca_version, &arg->ca32_version);
	err |= __copy_from_user(&karg->ca_client.cl_ident[0],
			  &arg->ca32_client.cl32_ident[0],
			  NFSCLNT_IDMAX);
	err |= __get_user(karg->ca_client.cl_naddr, &arg->ca32_client.cl32_naddr);
	err |= __copy_from_user(&karg->ca_client.cl_addrlist[0],
			  &arg->ca32_client.cl32_addrlist[0],
			  (sizeof(struct in_addr) * NFSCLNT_ADDRMAX));
	err |= __get_user(karg->ca_client.cl_fhkeytype,
		      &arg->ca32_client.cl32_fhkeytype);
	err |= __get_user(karg->ca_client.cl_fhkeylen,
		      &arg->ca32_client.cl32_fhkeylen);
	err |= __copy_from_user(&karg->ca_client.cl_fhkey[0],
			  &arg->ca32_client.cl32_fhkey[0],
			  NFSCLNT_KEYMAX);

	return (err) ? -EFAULT : 0;
}

static int compat_nfs_exp_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg)
{
	int err;

	err = access_ok(VERIFY_READ, &arg->ca32_export, sizeof(arg->ca32_export));
	err |= get_user(karg->ca_version, &arg->ca32_version);
	err |= __copy_from_user(&karg->ca_export.ex_client[0],
			  &arg->ca32_export.ex32_client[0],
			  NFSCLNT_IDMAX);
	err |= __copy_from_user(&karg->ca_export.ex_path[0],
			  &arg->ca32_export.ex32_path[0],
			  NFS_MAXPATHLEN);
	err |= __get_user(karg->ca_export.ex_dev,
		      &arg->ca32_export.ex32_dev);
	err |= __get_user(karg->ca_export.ex_ino,
		      &arg->ca32_export.ex32_ino);
	err |= __get_user(karg->ca_export.ex_flags,
		      &arg->ca32_export.ex32_flags);
	err |= __get_user(karg->ca_export.ex_anon_uid,
		      &arg->ca32_export.ex32_anon_uid);
	err |= __get_user(karg->ca_export.ex_anon_gid,
		      &arg->ca32_export.ex32_anon_gid);
	SET_UID(karg->ca_export.ex_anon_uid, karg->ca_export.ex_anon_uid);
	SET_GID(karg->ca_export.ex_anon_gid, karg->ca_export.ex_anon_gid);

	return (err) ? -EFAULT : 0;
}

static int compat_nfs_getfd_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg)
{
	int err;

	err = access_ok(VERIFY_READ, &arg->ca32_getfd, sizeof(arg->ca32_getfd));
	err |= get_user(karg->ca_version, &arg->ca32_version);
	err |= __copy_from_user(&karg->ca_getfd.gd_addr,
			  &arg->ca32_getfd.gd32_addr,
			  (sizeof(struct sockaddr)));
	err |= __copy_from_user(&karg->ca_getfd.gd_path,
			  &arg->ca32_getfd.gd32_path,
			  (NFS_MAXPATHLEN+1));
	err |= __get_user(karg->ca_getfd.gd_version,
		      &arg->ca32_getfd.gd32_version);

	return (err) ? -EFAULT : 0;
}

static int compat_nfs_getfs_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg)
{
	int err;

	err = access_ok(VERIFY_READ, &arg->ca32_getfs, sizeof(arg->ca32_getfs));
	err |= get_user(karg->ca_version, &arg->ca32_version);
	err |= __copy_from_user(&karg->ca_getfs.gd_addr,
			  &arg->ca32_getfs.gd32_addr,
			  (sizeof(struct sockaddr)));
	err |= __copy_from_user(&karg->ca_getfs.gd_path,
			  &arg->ca32_getfs.gd32_path,
			  (NFS_MAXPATHLEN+1));
	err |= __get_user(karg->ca_getfs.gd_maxlen,
		      &arg->ca32_getfs.gd32_maxlen);

	return (err) ? -EFAULT : 0;
}

/* This really doesn't need translations, we are only passing
 * back a union which contains opaque nfs file handle data.
 */
static int compat_nfs_getfh_res_trans(union nfsctl_res *kres, union compat_nfsctl_res __user *res)
{
	int err;

	err = copy_to_user(res, kres, sizeof(*res));

	return (err) ? -EFAULT : 0;
}

asmlinkage long compat_sys_nfsservctl(int cmd, struct compat_nfsctl_arg __user *arg,
					union compat_nfsctl_res __user *res)
{
	struct nfsctl_arg *karg;
	union nfsctl_res *kres;
	mm_segment_t oldfs;
	int err;

	karg = kmalloc(sizeof(*karg), GFP_USER);
	kres = kmalloc(sizeof(*kres), GFP_USER);
	if(!karg || !kres) {
		err = -ENOMEM;
		goto done;
	}

	switch(cmd) {
	case NFSCTL_SVC:
		err = compat_nfs_svc_trans(karg, arg);
		break;

	case NFSCTL_ADDCLIENT:
		err = compat_nfs_clnt_trans(karg, arg);
		break;

	case NFSCTL_DELCLIENT:
		err = compat_nfs_clnt_trans(karg, arg);
		break;

	case NFSCTL_EXPORT:
	case NFSCTL_UNEXPORT:
		err = compat_nfs_exp_trans(karg, arg);
		break;

	case NFSCTL_GETFD:
		err = compat_nfs_getfd_trans(karg, arg);
		break;

	case NFSCTL_GETFS:
		err = compat_nfs_getfs_trans(karg, arg);
		break;

	default:
		err = -EINVAL;
2187
		break;
L
Linus Torvalds 已提交
2188 2189
	}

2190 2191 2192
	if (err)
		goto done;

L
Linus Torvalds 已提交
2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216
	oldfs = get_fs();
	set_fs(KERNEL_DS);
	/* The __user pointer casts are valid because of the set_fs() */
	err = sys_nfsservctl(cmd, (void __user *) karg, (void __user *) kres);
	set_fs(oldfs);

	if (err)
		goto done;

	if((cmd == NFSCTL_GETFD) ||
	   (cmd == NFSCTL_GETFS))
		err = compat_nfs_getfh_res_trans(kres, res);

done:
	kfree(karg);
	kfree(kres);
	return err;
}
#else /* !NFSD */
long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2)
{
	return sys_ni_syscall();
}
#endif