1 // SPDX-License-Identifier: GPL-2.0-only
2 /*
3  *  linux/fs/open.c
4  *
5  *  Copyright (C) 1991, 1992  Linus Torvalds
6  */
7 
8 #include <linux/string.h>
9 #include <linux/mm.h>
10 #include <linux/file.h>
11 #include <linux/fdtable.h>
12 #include <linux/fsnotify.h>
13 #include <linux/module.h>
14 #include <linux/tty.h>
15 #include <linux/namei.h>
16 #include <linux/backing-dev.h>
17 #include <linux/capability.h>
18 #include <linux/securebits.h>
19 #include <linux/security.h>
20 #include <linux/mount.h>
21 #include <linux/fcntl.h>
22 #include <linux/slab.h>
23 #include <linux/uaccess.h>
24 #include <linux/fs.h>
25 #include <linux/personality.h>
26 #include <linux/pagemap.h>
27 #include <linux/syscalls.h>
28 #include <linux/rcupdate.h>
29 #include <linux/audit.h>
30 #include <linux/falloc.h>
31 #include <linux/fs_struct.h>
32 #include <linux/ima.h>
33 #include <linux/dnotify.h>
34 #include <linux/compat.h>
35 #include <linux/mnt_idmapping.h>
36 #include <linux/filelock.h>
37 
38 #include "internal.h"
39 
do_truncate(struct mnt_idmap * idmap,struct dentry * dentry,loff_t length,unsigned int time_attrs,struct file * filp)40 int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
41 		loff_t length, unsigned int time_attrs, struct file *filp)
42 {
43 	int ret;
44 	struct iattr newattrs;
45 
46 	/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
47 	if (length < 0)
48 		return -EINVAL;
49 
50 	newattrs.ia_size = length;
51 	newattrs.ia_valid = ATTR_SIZE | time_attrs;
52 	if (filp) {
53 		newattrs.ia_file = filp;
54 		newattrs.ia_valid |= ATTR_FILE;
55 	}
56 
57 	/* Remove suid, sgid, and file capabilities on truncate too */
58 	ret = dentry_needs_remove_privs(idmap, dentry);
59 	if (ret < 0)
60 		return ret;
61 	if (ret)
62 		newattrs.ia_valid |= ret | ATTR_FORCE;
63 
64 	inode_lock(dentry->d_inode);
65 	/* Note any delegations or leases have already been broken: */
66 	ret = notify_change(idmap, dentry, &newattrs, NULL);
67 	inode_unlock(dentry->d_inode);
68 	return ret;
69 }
70 
vfs_truncate(const struct path * path,loff_t length)71 long vfs_truncate(const struct path *path, loff_t length)
72 {
73 	struct mnt_idmap *idmap;
74 	struct inode *inode;
75 	long error;
76 
77 	inode = path->dentry->d_inode;
78 
79 	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
80 	if (S_ISDIR(inode->i_mode))
81 		return -EISDIR;
82 	if (!S_ISREG(inode->i_mode))
83 		return -EINVAL;
84 
85 	error = mnt_want_write(path->mnt);
86 	if (error)
87 		goto out;
88 
89 	idmap = mnt_idmap(path->mnt);
90 	error = inode_permission(idmap, inode, MAY_WRITE);
91 	if (error)
92 		goto mnt_drop_write_and_out;
93 
94 	error = -EPERM;
95 	if (IS_APPEND(inode))
96 		goto mnt_drop_write_and_out;
97 
98 	error = get_write_access(inode);
99 	if (error)
100 		goto mnt_drop_write_and_out;
101 
102 	/*
103 	 * Make sure that there are no leases.  get_write_access() protects
104 	 * against the truncate racing with a lease-granting setlease().
105 	 */
106 	error = break_lease(inode, O_WRONLY);
107 	if (error)
108 		goto put_write_and_out;
109 
110 	error = security_path_truncate(path);
111 	if (!error)
112 		error = do_truncate(idmap, path->dentry, length, 0, NULL);
113 
114 put_write_and_out:
115 	put_write_access(inode);
116 mnt_drop_write_and_out:
117 	mnt_drop_write(path->mnt);
118 out:
119 	return error;
120 }
121 EXPORT_SYMBOL_GPL(vfs_truncate);
122 
do_sys_truncate(const char __user * pathname,loff_t length)123 long do_sys_truncate(const char __user *pathname, loff_t length)
124 {
125 	unsigned int lookup_flags = LOOKUP_FOLLOW;
126 	struct path path;
127 	int error;
128 
129 	if (length < 0)	/* sorry, but loff_t says... */
130 		return -EINVAL;
131 
132 retry:
133 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
134 	if (!error) {
135 		error = vfs_truncate(&path, length);
136 		path_put(&path);
137 	}
138 	if (retry_estale(error, lookup_flags)) {
139 		lookup_flags |= LOOKUP_REVAL;
140 		goto retry;
141 	}
142 	return error;
143 }
144 
SYSCALL_DEFINE2(truncate,const char __user *,path,long,length)145 SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
146 {
147 	return do_sys_truncate(path, length);
148 }
149 
150 #ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(truncate,const char __user *,path,compat_off_t,length)151 COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
152 {
153 	return do_sys_truncate(path, length);
154 }
155 #endif
156 
do_sys_ftruncate(unsigned int fd,loff_t length,int small)157 long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
158 {
159 	struct inode *inode;
160 	struct dentry *dentry;
161 	struct fd f;
162 	int error;
163 
164 	error = -EINVAL;
165 	if (length < 0)
166 		goto out;
167 	error = -EBADF;
168 	f = fdget(fd);
169 	if (!f.file)
170 		goto out;
171 
172 	/* explicitly opened as large or we are on 64-bit box */
173 	if (f.file->f_flags & O_LARGEFILE)
174 		small = 0;
175 
176 	dentry = f.file->f_path.dentry;
177 	inode = dentry->d_inode;
178 	error = -EINVAL;
179 	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
180 		goto out_putf;
181 
182 	error = -EINVAL;
183 	/* Cannot ftruncate over 2^31 bytes without large file support */
184 	if (small && length > MAX_NON_LFS)
185 		goto out_putf;
186 
187 	error = -EPERM;
188 	/* Check IS_APPEND on real upper inode */
189 	if (IS_APPEND(file_inode(f.file)))
190 		goto out_putf;
191 	sb_start_write(inode->i_sb);
192 	error = security_file_truncate(f.file);
193 	if (!error)
194 		error = do_truncate(file_mnt_idmap(f.file), dentry, length,
195 				    ATTR_MTIME | ATTR_CTIME, f.file);
196 	sb_end_write(inode->i_sb);
197 out_putf:
198 	fdput(f);
199 out:
200 	return error;
201 }
202 
SYSCALL_DEFINE2(ftruncate,unsigned int,fd,unsigned long,length)203 SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
204 {
205 	return do_sys_ftruncate(fd, length, 1);
206 }
207 
208 #ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(ftruncate,unsigned int,fd,compat_ulong_t,length)209 COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
210 {
211 	return do_sys_ftruncate(fd, length, 1);
212 }
213 #endif
214 
215 /* LFS versions of truncate are only needed on 32 bit machines */
216 #if BITS_PER_LONG == 32
SYSCALL_DEFINE2(truncate64,const char __user *,path,loff_t,length)217 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length)
218 {
219 	return do_sys_truncate(path, length);
220 }
221 
SYSCALL_DEFINE2(ftruncate64,unsigned int,fd,loff_t,length)222 SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
223 {
224 	return do_sys_ftruncate(fd, length, 0);
225 }
226 #endif /* BITS_PER_LONG == 32 */
227 
228 #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64)
COMPAT_SYSCALL_DEFINE3(truncate64,const char __user *,pathname,compat_arg_u64_dual (length))229 COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname,
230 		       compat_arg_u64_dual(length))
231 {
232 	return ksys_truncate(pathname, compat_arg_u64_glue(length));
233 }
234 #endif
235 
236 #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64)
COMPAT_SYSCALL_DEFINE3(ftruncate64,unsigned int,fd,compat_arg_u64_dual (length))237 COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd,
238 		       compat_arg_u64_dual(length))
239 {
240 	return ksys_ftruncate(fd, compat_arg_u64_glue(length));
241 }
242 #endif
243 
vfs_fallocate(struct file * file,int mode,loff_t offset,loff_t len)244 int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
245 {
246 	struct inode *inode = file_inode(file);
247 	long ret;
248 
249 	if (offset < 0 || len <= 0)
250 		return -EINVAL;
251 
252 	/* Return error if mode is not supported */
253 	if (mode & ~FALLOC_FL_SUPPORTED_MASK)
254 		return -EOPNOTSUPP;
255 
256 	/* Punch hole and zero range are mutually exclusive */
257 	if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
258 	    (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
259 		return -EOPNOTSUPP;
260 
261 	/* Punch hole must have keep size set */
262 	if ((mode & FALLOC_FL_PUNCH_HOLE) &&
263 	    !(mode & FALLOC_FL_KEEP_SIZE))
264 		return -EOPNOTSUPP;
265 
266 	/* Collapse range should only be used exclusively. */
267 	if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
268 	    (mode & ~FALLOC_FL_COLLAPSE_RANGE))
269 		return -EINVAL;
270 
271 	/* Insert range should only be used exclusively. */
272 	if ((mode & FALLOC_FL_INSERT_RANGE) &&
273 	    (mode & ~FALLOC_FL_INSERT_RANGE))
274 		return -EINVAL;
275 
276 	/* Unshare range should only be used with allocate mode. */
277 	if ((mode & FALLOC_FL_UNSHARE_RANGE) &&
278 	    (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE)))
279 		return -EINVAL;
280 
281 	if (!(file->f_mode & FMODE_WRITE))
282 		return -EBADF;
283 
284 	/*
285 	 * We can only allow pure fallocate on append only files
286 	 */
287 	if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
288 		return -EPERM;
289 
290 	if (IS_IMMUTABLE(inode))
291 		return -EPERM;
292 
293 	/*
294 	 * We cannot allow any fallocate operation on an active swapfile
295 	 */
296 	if (IS_SWAPFILE(inode))
297 		return -ETXTBSY;
298 
299 	/*
300 	 * Revalidate the write permissions, in case security policy has
301 	 * changed since the files were opened.
302 	 */
303 	ret = security_file_permission(file, MAY_WRITE);
304 	if (ret)
305 		return ret;
306 
307 	if (S_ISFIFO(inode->i_mode))
308 		return -ESPIPE;
309 
310 	if (S_ISDIR(inode->i_mode))
311 		return -EISDIR;
312 
313 	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
314 		return -ENODEV;
315 
316 	/* Check for wrap through zero too */
317 	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
318 		return -EFBIG;
319 
320 	if (!file->f_op->fallocate)
321 		return -EOPNOTSUPP;
322 
323 	file_start_write(file);
324 	ret = file->f_op->fallocate(file, mode, offset, len);
325 
326 	/*
327 	 * Create inotify and fanotify events.
328 	 *
329 	 * To keep the logic simple always create events if fallocate succeeds.
330 	 * This implies that events are even created if the file size remains
331 	 * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
332 	 */
333 	if (ret == 0)
334 		fsnotify_modify(file);
335 
336 	file_end_write(file);
337 	return ret;
338 }
339 EXPORT_SYMBOL_GPL(vfs_fallocate);
340 
ksys_fallocate(int fd,int mode,loff_t offset,loff_t len)341 int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len)
342 {
343 	struct fd f = fdget(fd);
344 	int error = -EBADF;
345 
346 	if (f.file) {
347 		error = vfs_fallocate(f.file, mode, offset, len);
348 		fdput(f);
349 	}
350 	return error;
351 }
352 
SYSCALL_DEFINE4(fallocate,int,fd,int,mode,loff_t,offset,loff_t,len)353 SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
354 {
355 	return ksys_fallocate(fd, mode, offset, len);
356 }
357 
358 #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE)
COMPAT_SYSCALL_DEFINE6(fallocate,int,fd,int,mode,compat_arg_u64_dual (offset),compat_arg_u64_dual (len))359 COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset),
360 		       compat_arg_u64_dual(len))
361 {
362 	return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset),
363 			      compat_arg_u64_glue(len));
364 }
365 #endif
366 
367 /*
368  * access() needs to use the real uid/gid, not the effective uid/gid.
369  * We do this by temporarily clearing all FS-related capabilities and
370  * switching the fsuid/fsgid around to the real ones.
371  *
372  * Creating new credentials is expensive, so we try to skip doing it,
373  * which we can if the result would match what we already got.
374  */
access_need_override_creds(int flags)375 static bool access_need_override_creds(int flags)
376 {
377 	const struct cred *cred;
378 
379 	if (flags & AT_EACCESS)
380 		return false;
381 
382 	cred = current_cred();
383 	if (!uid_eq(cred->fsuid, cred->uid) ||
384 	    !gid_eq(cred->fsgid, cred->gid))
385 		return true;
386 
387 	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
388 		kuid_t root_uid = make_kuid(cred->user_ns, 0);
389 		if (!uid_eq(cred->uid, root_uid)) {
390 			if (!cap_isclear(cred->cap_effective))
391 				return true;
392 		} else {
393 			if (!cap_isidentical(cred->cap_effective,
394 			    cred->cap_permitted))
395 				return true;
396 		}
397 	}
398 
399 	return false;
400 }
401 
access_override_creds(void)402 static const struct cred *access_override_creds(void)
403 {
404 	const struct cred *old_cred;
405 	struct cred *override_cred;
406 
407 	override_cred = prepare_creds();
408 	if (!override_cred)
409 		return NULL;
410 
411 	/*
412 	 * XXX access_need_override_creds performs checks in hopes of skipping
413 	 * this work. Make sure it stays in sync if making any changes in this
414 	 * routine.
415 	 */
416 
417 	override_cred->fsuid = override_cred->uid;
418 	override_cred->fsgid = override_cred->gid;
419 
420 	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
421 		/* Clear the capabilities if we switch to a non-root user */
422 		kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
423 		if (!uid_eq(override_cred->uid, root_uid))
424 			cap_clear(override_cred->cap_effective);
425 		else
426 			override_cred->cap_effective =
427 				override_cred->cap_permitted;
428 	}
429 
430 	/*
431 	 * The new set of credentials can *only* be used in
432 	 * task-synchronous circumstances, and does not need
433 	 * RCU freeing, unless somebody then takes a separate
434 	 * reference to it.
435 	 *
436 	 * NOTE! This is _only_ true because this credential
437 	 * is used purely for override_creds() that installs
438 	 * it as the subjective cred. Other threads will be
439 	 * accessing ->real_cred, not the subjective cred.
440 	 *
441 	 * If somebody _does_ make a copy of this (using the
442 	 * 'get_current_cred()' function), that will clear the
443 	 * non_rcu field, because now that other user may be
444 	 * expecting RCU freeing. But normal thread-synchronous
445 	 * cred accesses will keep things non-RCY.
446 	 */
447 	override_cred->non_rcu = 1;
448 
449 	old_cred = override_creds(override_cred);
450 
451 	/* override_cred() gets its own ref */
452 	put_cred(override_cred);
453 
454 	return old_cred;
455 }
456 
do_faccessat(int dfd,const char __user * filename,int mode,int flags)457 static long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
458 {
459 	struct path path;
460 	struct inode *inode;
461 	int res;
462 	unsigned int lookup_flags = LOOKUP_FOLLOW;
463 	const struct cred *old_cred = NULL;
464 
465 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
466 		return -EINVAL;
467 
468 	if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
469 		return -EINVAL;
470 
471 	if (flags & AT_SYMLINK_NOFOLLOW)
472 		lookup_flags &= ~LOOKUP_FOLLOW;
473 	if (flags & AT_EMPTY_PATH)
474 		lookup_flags |= LOOKUP_EMPTY;
475 
476 	if (access_need_override_creds(flags)) {
477 		old_cred = access_override_creds();
478 		if (!old_cred)
479 			return -ENOMEM;
480 	}
481 
482 retry:
483 	res = user_path_at(dfd, filename, lookup_flags, &path);
484 	if (res)
485 		goto out;
486 
487 	inode = d_backing_inode(path.dentry);
488 
489 	if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
490 		/*
491 		 * MAY_EXEC on regular files is denied if the fs is mounted
492 		 * with the "noexec" flag.
493 		 */
494 		res = -EACCES;
495 		if (path_noexec(&path))
496 			goto out_path_release;
497 	}
498 
499 	res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS);
500 	/* SuS v2 requires we report a read only fs too */
501 	if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
502 		goto out_path_release;
503 	/*
504 	 * This is a rare case where using __mnt_is_readonly()
505 	 * is OK without a mnt_want/drop_write() pair.  Since
506 	 * no actual write to the fs is performed here, we do
507 	 * not need to telegraph to that to anyone.
508 	 *
509 	 * By doing this, we accept that this access is
510 	 * inherently racy and know that the fs may change
511 	 * state before we even see this result.
512 	 */
513 	if (__mnt_is_readonly(path.mnt))
514 		res = -EROFS;
515 
516 out_path_release:
517 	path_put(&path);
518 	if (retry_estale(res, lookup_flags)) {
519 		lookup_flags |= LOOKUP_REVAL;
520 		goto retry;
521 	}
522 out:
523 	if (old_cred)
524 		revert_creds(old_cred);
525 
526 	return res;
527 }
528 
SYSCALL_DEFINE3(faccessat,int,dfd,const char __user *,filename,int,mode)529 SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
530 {
531 	return do_faccessat(dfd, filename, mode, 0);
532 }
533 
SYSCALL_DEFINE4(faccessat2,int,dfd,const char __user *,filename,int,mode,int,flags)534 SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode,
535 		int, flags)
536 {
537 	return do_faccessat(dfd, filename, mode, flags);
538 }
539 
SYSCALL_DEFINE2(access,const char __user *,filename,int,mode)540 SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
541 {
542 	return do_faccessat(AT_FDCWD, filename, mode, 0);
543 }
544 
SYSCALL_DEFINE1(chdir,const char __user *,filename)545 SYSCALL_DEFINE1(chdir, const char __user *, filename)
546 {
547 	struct path path;
548 	int error;
549 	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
550 retry:
551 	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
552 	if (error)
553 		goto out;
554 
555 	error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
556 	if (error)
557 		goto dput_and_out;
558 
559 	set_fs_pwd(current->fs, &path);
560 
561 dput_and_out:
562 	path_put(&path);
563 	if (retry_estale(error, lookup_flags)) {
564 		lookup_flags |= LOOKUP_REVAL;
565 		goto retry;
566 	}
567 out:
568 	return error;
569 }
570 
SYSCALL_DEFINE1(fchdir,unsigned int,fd)571 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
572 {
573 	struct fd f = fdget_raw(fd);
574 	int error;
575 
576 	error = -EBADF;
577 	if (!f.file)
578 		goto out;
579 
580 	error = -ENOTDIR;
581 	if (!d_can_lookup(f.file->f_path.dentry))
582 		goto out_putf;
583 
584 	error = file_permission(f.file, MAY_EXEC | MAY_CHDIR);
585 	if (!error)
586 		set_fs_pwd(current->fs, &f.file->f_path);
587 out_putf:
588 	fdput(f);
589 out:
590 	return error;
591 }
592 
SYSCALL_DEFINE1(chroot,const char __user *,filename)593 SYSCALL_DEFINE1(chroot, const char __user *, filename)
594 {
595 	struct path path;
596 	int error;
597 	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
598 retry:
599 	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
600 	if (error)
601 		goto out;
602 
603 	error = path_permission(&path, MAY_EXEC | MAY_CHDIR);
604 	if (error)
605 		goto dput_and_out;
606 
607 	error = -EPERM;
608 	if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
609 		goto dput_and_out;
610 	error = security_path_chroot(&path);
611 	if (error)
612 		goto dput_and_out;
613 
614 	set_fs_root(current->fs, &path);
615 	error = 0;
616 dput_and_out:
617 	path_put(&path);
618 	if (retry_estale(error, lookup_flags)) {
619 		lookup_flags |= LOOKUP_REVAL;
620 		goto retry;
621 	}
622 out:
623 	return error;
624 }
625 
chmod_common(const struct path * path,umode_t mode)626 int chmod_common(const struct path *path, umode_t mode)
627 {
628 	struct inode *inode = path->dentry->d_inode;
629 	struct inode *delegated_inode = NULL;
630 	struct iattr newattrs;
631 	int error;
632 
633 	error = mnt_want_write(path->mnt);
634 	if (error)
635 		return error;
636 retry_deleg:
637 	inode_lock(inode);
638 	error = security_path_chmod(path, mode);
639 	if (error)
640 		goto out_unlock;
641 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
642 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
643 	error = notify_change(mnt_idmap(path->mnt), path->dentry,
644 			      &newattrs, &delegated_inode);
645 out_unlock:
646 	inode_unlock(inode);
647 	if (delegated_inode) {
648 		error = break_deleg_wait(&delegated_inode);
649 		if (!error)
650 			goto retry_deleg;
651 	}
652 	mnt_drop_write(path->mnt);
653 	return error;
654 }
655 
vfs_fchmod(struct file * file,umode_t mode)656 int vfs_fchmod(struct file *file, umode_t mode)
657 {
658 	audit_file(file);
659 	return chmod_common(&file->f_path, mode);
660 }
661 
SYSCALL_DEFINE2(fchmod,unsigned int,fd,umode_t,mode)662 SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
663 {
664 	struct fd f = fdget(fd);
665 	int err = -EBADF;
666 
667 	if (f.file) {
668 		err = vfs_fchmod(f.file, mode);
669 		fdput(f);
670 	}
671 	return err;
672 }
673 
do_fchmodat(int dfd,const char __user * filename,umode_t mode)674 static int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
675 {
676 	struct path path;
677 	int error;
678 	unsigned int lookup_flags = LOOKUP_FOLLOW;
679 retry:
680 	error = user_path_at(dfd, filename, lookup_flags, &path);
681 	if (!error) {
682 		error = chmod_common(&path, mode);
683 		path_put(&path);
684 		if (retry_estale(error, lookup_flags)) {
685 			lookup_flags |= LOOKUP_REVAL;
686 			goto retry;
687 		}
688 	}
689 	return error;
690 }
691 
SYSCALL_DEFINE3(fchmodat,int,dfd,const char __user *,filename,umode_t,mode)692 SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename,
693 		umode_t, mode)
694 {
695 	return do_fchmodat(dfd, filename, mode);
696 }
697 
SYSCALL_DEFINE2(chmod,const char __user *,filename,umode_t,mode)698 SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
699 {
700 	return do_fchmodat(AT_FDCWD, filename, mode);
701 }
702 
703 /**
704  * setattr_vfsuid - check and set ia_fsuid attribute
705  * @kuid: new inode owner
706  *
707  * Check whether @kuid is valid and if so generate and set vfsuid_t in
708  * ia_vfsuid.
709  *
710  * Return: true if @kuid is valid, false if not.
711  */
setattr_vfsuid(struct iattr * attr,kuid_t kuid)712 static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid)
713 {
714 	if (!uid_valid(kuid))
715 		return false;
716 	attr->ia_valid |= ATTR_UID;
717 	attr->ia_vfsuid = VFSUIDT_INIT(kuid);
718 	return true;
719 }
720 
721 /**
722  * setattr_vfsgid - check and set ia_fsgid attribute
723  * @kgid: new inode owner
724  *
725  * Check whether @kgid is valid and if so generate and set vfsgid_t in
726  * ia_vfsgid.
727  *
728  * Return: true if @kgid is valid, false if not.
729  */
setattr_vfsgid(struct iattr * attr,kgid_t kgid)730 static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid)
731 {
732 	if (!gid_valid(kgid))
733 		return false;
734 	attr->ia_valid |= ATTR_GID;
735 	attr->ia_vfsgid = VFSGIDT_INIT(kgid);
736 	return true;
737 }
738 
chown_common(const struct path * path,uid_t user,gid_t group)739 int chown_common(const struct path *path, uid_t user, gid_t group)
740 {
741 	struct mnt_idmap *idmap;
742 	struct user_namespace *fs_userns;
743 	struct inode *inode = path->dentry->d_inode;
744 	struct inode *delegated_inode = NULL;
745 	int error;
746 	struct iattr newattrs;
747 	kuid_t uid;
748 	kgid_t gid;
749 
750 	uid = make_kuid(current_user_ns(), user);
751 	gid = make_kgid(current_user_ns(), group);
752 
753 	idmap = mnt_idmap(path->mnt);
754 	fs_userns = i_user_ns(inode);
755 
756 retry_deleg:
757 	newattrs.ia_vfsuid = INVALID_VFSUID;
758 	newattrs.ia_vfsgid = INVALID_VFSGID;
759 	newattrs.ia_valid =  ATTR_CTIME;
760 	if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid))
761 		return -EINVAL;
762 	if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid))
763 		return -EINVAL;
764 	inode_lock(inode);
765 	if (!S_ISDIR(inode->i_mode))
766 		newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV |
767 				     setattr_should_drop_sgid(idmap, inode);
768 	/* Continue to send actual fs values, not the mount values. */
769 	error = security_path_chown(
770 		path,
771 		from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid),
772 		from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid));
773 	if (!error)
774 		error = notify_change(idmap, path->dentry, &newattrs,
775 				      &delegated_inode);
776 	inode_unlock(inode);
777 	if (delegated_inode) {
778 		error = break_deleg_wait(&delegated_inode);
779 		if (!error)
780 			goto retry_deleg;
781 	}
782 	return error;
783 }
784 
do_fchownat(int dfd,const char __user * filename,uid_t user,gid_t group,int flag)785 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
786 		int flag)
787 {
788 	struct path path;
789 	int error = -EINVAL;
790 	int lookup_flags;
791 
792 	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
793 		goto out;
794 
795 	lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
796 	if (flag & AT_EMPTY_PATH)
797 		lookup_flags |= LOOKUP_EMPTY;
798 retry:
799 	error = user_path_at(dfd, filename, lookup_flags, &path);
800 	if (error)
801 		goto out;
802 	error = mnt_want_write(path.mnt);
803 	if (error)
804 		goto out_release;
805 	error = chown_common(&path, user, group);
806 	mnt_drop_write(path.mnt);
807 out_release:
808 	path_put(&path);
809 	if (retry_estale(error, lookup_flags)) {
810 		lookup_flags |= LOOKUP_REVAL;
811 		goto retry;
812 	}
813 out:
814 	return error;
815 }
816 
SYSCALL_DEFINE5(fchownat,int,dfd,const char __user *,filename,uid_t,user,gid_t,group,int,flag)817 SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
818 		gid_t, group, int, flag)
819 {
820 	return do_fchownat(dfd, filename, user, group, flag);
821 }
822 
SYSCALL_DEFINE3(chown,const char __user *,filename,uid_t,user,gid_t,group)823 SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
824 {
825 	return do_fchownat(AT_FDCWD, filename, user, group, 0);
826 }
827 
SYSCALL_DEFINE3(lchown,const char __user *,filename,uid_t,user,gid_t,group)828 SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
829 {
830 	return do_fchownat(AT_FDCWD, filename, user, group,
831 			   AT_SYMLINK_NOFOLLOW);
832 }
833 
vfs_fchown(struct file * file,uid_t user,gid_t group)834 int vfs_fchown(struct file *file, uid_t user, gid_t group)
835 {
836 	int error;
837 
838 	error = mnt_want_write_file(file);
839 	if (error)
840 		return error;
841 	audit_file(file);
842 	error = chown_common(&file->f_path, user, group);
843 	mnt_drop_write_file(file);
844 	return error;
845 }
846 
ksys_fchown(unsigned int fd,uid_t user,gid_t group)847 int ksys_fchown(unsigned int fd, uid_t user, gid_t group)
848 {
849 	struct fd f = fdget(fd);
850 	int error = -EBADF;
851 
852 	if (f.file) {
853 		error = vfs_fchown(f.file, user, group);
854 		fdput(f);
855 	}
856 	return error;
857 }
858 
SYSCALL_DEFINE3(fchown,unsigned int,fd,uid_t,user,gid_t,group)859 SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
860 {
861 	return ksys_fchown(fd, user, group);
862 }
863 
do_dentry_open(struct file * f,struct inode * inode,int (* open)(struct inode *,struct file *))864 static int do_dentry_open(struct file *f,
865 			  struct inode *inode,
866 			  int (*open)(struct inode *, struct file *))
867 {
868 	static const struct file_operations empty_fops = {};
869 	int error;
870 
871 	path_get(&f->f_path);
872 	f->f_inode = inode;
873 	f->f_mapping = inode->i_mapping;
874 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
875 	f->f_sb_err = file_sample_sb_err(f);
876 
877 	if (unlikely(f->f_flags & O_PATH)) {
878 		f->f_mode = FMODE_PATH | FMODE_OPENED;
879 		f->f_op = &empty_fops;
880 		return 0;
881 	}
882 
883 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) {
884 		i_readcount_inc(inode);
885 	} else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
886 		error = get_write_access(inode);
887 		if (unlikely(error))
888 			goto cleanup_file;
889 		error = __mnt_want_write(f->f_path.mnt);
890 		if (unlikely(error)) {
891 			put_write_access(inode);
892 			goto cleanup_file;
893 		}
894 		f->f_mode |= FMODE_WRITER;
895 	}
896 
897 	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
898 	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
899 		f->f_mode |= FMODE_ATOMIC_POS;
900 
901 	f->f_op = fops_get(inode->i_fop);
902 	if (WARN_ON(!f->f_op)) {
903 		error = -ENODEV;
904 		goto cleanup_all;
905 	}
906 
907 	error = security_file_open(f);
908 	if (error)
909 		goto cleanup_all;
910 
911 	error = break_lease(file_inode(f), f->f_flags);
912 	if (error)
913 		goto cleanup_all;
914 
915 	/* normally all 3 are set; ->open() can clear them if needed */
916 	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
917 	if (!open)
918 		open = f->f_op->open;
919 	if (open) {
920 		error = open(inode, f);
921 		if (error)
922 			goto cleanup_all;
923 	}
924 	f->f_mode |= FMODE_OPENED;
925 	if ((f->f_mode & FMODE_READ) &&
926 	     likely(f->f_op->read || f->f_op->read_iter))
927 		f->f_mode |= FMODE_CAN_READ;
928 	if ((f->f_mode & FMODE_WRITE) &&
929 	     likely(f->f_op->write || f->f_op->write_iter))
930 		f->f_mode |= FMODE_CAN_WRITE;
931 	if ((f->f_mode & FMODE_LSEEK) && !f->f_op->llseek)
932 		f->f_mode &= ~FMODE_LSEEK;
933 	if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO)
934 		f->f_mode |= FMODE_CAN_ODIRECT;
935 
936 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
937 	f->f_iocb_flags = iocb_flags(f);
938 
939 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
940 
941 	if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT))
942 		return -EINVAL;
943 
944 	/*
945 	 * XXX: Huge page cache doesn't support writing yet. Drop all page
946 	 * cache for this file before processing writes.
947 	 */
948 	if (f->f_mode & FMODE_WRITE) {
949 		/*
950 		 * Paired with smp_mb() in collapse_file() to ensure nr_thps
951 		 * is up to date and the update to i_writecount by
952 		 * get_write_access() is visible. Ensures subsequent insertion
953 		 * of THPs into the page cache will fail.
954 		 */
955 		smp_mb();
956 		if (filemap_nr_thps(inode->i_mapping)) {
957 			struct address_space *mapping = inode->i_mapping;
958 
959 			filemap_invalidate_lock(inode->i_mapping);
960 			/*
961 			 * unmap_mapping_range just need to be called once
962 			 * here, because the private pages is not need to be
963 			 * unmapped mapping (e.g. data segment of dynamic
964 			 * shared libraries here).
965 			 */
966 			unmap_mapping_range(mapping, 0, 0, 0);
967 			truncate_inode_pages(mapping, 0);
968 			filemap_invalidate_unlock(inode->i_mapping);
969 		}
970 	}
971 
972 	return 0;
973 
974 cleanup_all:
975 	if (WARN_ON_ONCE(error > 0))
976 		error = -EINVAL;
977 	fops_put(f->f_op);
978 	put_file_access(f);
979 cleanup_file:
980 	path_put(&f->f_path);
981 	f->f_path.mnt = NULL;
982 	f->f_path.dentry = NULL;
983 	f->f_inode = NULL;
984 	return error;
985 }
986 
987 /**
988  * finish_open - finish opening a file
989  * @file: file pointer
990  * @dentry: pointer to dentry
991  * @open: open callback
992  * @opened: state of open
993  *
994  * This can be used to finish opening a file passed to i_op->atomic_open().
995  *
996  * If the open callback is set to NULL, then the standard f_op->open()
997  * filesystem callback is substituted.
998  *
999  * NB: the dentry reference is _not_ consumed.  If, for example, the dentry is
1000  * the return value of d_splice_alias(), then the caller needs to perform dput()
1001  * on it after finish_open().
1002  *
1003  * Returns zero on success or -errno if the open failed.
1004  */
finish_open(struct file * file,struct dentry * dentry,int (* open)(struct inode *,struct file *))1005 int finish_open(struct file *file, struct dentry *dentry,
1006 		int (*open)(struct inode *, struct file *))
1007 {
1008 	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
1009 
1010 	file->f_path.dentry = dentry;
1011 	return do_dentry_open(file, d_backing_inode(dentry), open);
1012 }
1013 EXPORT_SYMBOL(finish_open);
1014 
1015 /**
1016  * finish_no_open - finish ->atomic_open() without opening the file
1017  *
1018  * @file: file pointer
1019  * @dentry: dentry or NULL (as returned from ->lookup())
1020  *
1021  * This can be used to set the result of a successful lookup in ->atomic_open().
1022  *
1023  * NB: unlike finish_open() this function does consume the dentry reference and
1024  * the caller need not dput() it.
1025  *
1026  * Returns "0" which must be the return value of ->atomic_open() after having
1027  * called this function.
1028  */
finish_no_open(struct file * file,struct dentry * dentry)1029 int finish_no_open(struct file *file, struct dentry *dentry)
1030 {
1031 	file->f_path.dentry = dentry;
1032 	return 0;
1033 }
1034 EXPORT_SYMBOL(finish_no_open);
1035 
file_path(struct file * filp,char * buf,int buflen)1036 char *file_path(struct file *filp, char *buf, int buflen)
1037 {
1038 	return d_path(&filp->f_path, buf, buflen);
1039 }
1040 EXPORT_SYMBOL(file_path);
1041 
1042 /**
1043  * vfs_open - open the file at the given path
1044  * @path: path to open
1045  * @file: newly allocated file with f_flag initialized
1046  * @cred: credentials to use
1047  */
vfs_open(const struct path * path,struct file * file)1048 int vfs_open(const struct path *path, struct file *file)
1049 {
1050 	file->f_path = *path;
1051 	return do_dentry_open(file, d_backing_inode(path->dentry), NULL);
1052 }
1053 
dentry_open(const struct path * path,int flags,const struct cred * cred)1054 struct file *dentry_open(const struct path *path, int flags,
1055 			 const struct cred *cred)
1056 {
1057 	int error;
1058 	struct file *f;
1059 
1060 	validate_creds(cred);
1061 
1062 	/* We must always pass in a valid mount pointer. */
1063 	BUG_ON(!path->mnt);
1064 
1065 	f = alloc_empty_file(flags, cred);
1066 	if (!IS_ERR(f)) {
1067 		error = vfs_open(path, f);
1068 		if (error) {
1069 			fput(f);
1070 			f = ERR_PTR(error);
1071 		}
1072 	}
1073 	return f;
1074 }
1075 EXPORT_SYMBOL(dentry_open);
1076 
1077 /**
1078  * dentry_create - Create and open a file
1079  * @path: path to create
1080  * @flags: O_ flags
1081  * @mode: mode bits for new file
1082  * @cred: credentials to use
1083  *
1084  * Caller must hold the parent directory's lock, and have prepared
1085  * a negative dentry, placed in @path->dentry, for the new file.
1086  *
1087  * Caller sets @path->mnt to the vfsmount of the filesystem where
1088  * the new file is to be created. The parent directory and the
1089  * negative dentry must reside on the same filesystem instance.
1090  *
1091  * On success, returns a "struct file *". Otherwise a ERR_PTR
1092  * is returned.
1093  */
dentry_create(const struct path * path,int flags,umode_t mode,const struct cred * cred)1094 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
1095 			   const struct cred *cred)
1096 {
1097 	struct file *f;
1098 	int error;
1099 
1100 	validate_creds(cred);
1101 	f = alloc_empty_file(flags, cred);
1102 	if (IS_ERR(f))
1103 		return f;
1104 
1105 	error = vfs_create(mnt_idmap(path->mnt),
1106 			   d_inode(path->dentry->d_parent),
1107 			   path->dentry, mode, true);
1108 	if (!error)
1109 		error = vfs_open(path, f);
1110 
1111 	if (unlikely(error)) {
1112 		fput(f);
1113 		return ERR_PTR(error);
1114 	}
1115 	return f;
1116 }
1117 EXPORT_SYMBOL(dentry_create);
1118 
open_with_fake_path(const struct path * path,int flags,struct inode * inode,const struct cred * cred)1119 struct file *open_with_fake_path(const struct path *path, int flags,
1120 				struct inode *inode, const struct cred *cred)
1121 {
1122 	struct file *f = alloc_empty_file_noaccount(flags, cred);
1123 	if (!IS_ERR(f)) {
1124 		int error;
1125 
1126 		f->f_path = *path;
1127 		error = do_dentry_open(f, inode, NULL);
1128 		if (error) {
1129 			fput(f);
1130 			f = ERR_PTR(error);
1131 		}
1132 	}
1133 	return f;
1134 }
1135 EXPORT_SYMBOL(open_with_fake_path);
1136 
1137 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
1138 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
1139 
build_open_how(int flags,umode_t mode)1140 inline struct open_how build_open_how(int flags, umode_t mode)
1141 {
1142 	struct open_how how = {
1143 		.flags = flags & VALID_OPEN_FLAGS,
1144 		.mode = mode & S_IALLUGO,
1145 	};
1146 
1147 	/* O_PATH beats everything else. */
1148 	if (how.flags & O_PATH)
1149 		how.flags &= O_PATH_FLAGS;
1150 	/* Modes should only be set for create-like flags. */
1151 	if (!WILL_CREATE(how.flags))
1152 		how.mode = 0;
1153 	return how;
1154 }
1155 
build_open_flags(const struct open_how * how,struct open_flags * op)1156 inline int build_open_flags(const struct open_how *how, struct open_flags *op)
1157 {
1158 	u64 flags = how->flags;
1159 	u64 strip = FMODE_NONOTIFY | O_CLOEXEC;
1160 	int lookup_flags = 0;
1161 	int acc_mode = ACC_MODE(flags);
1162 
1163 	BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS),
1164 			 "struct open_flags doesn't yet handle flags > 32 bits");
1165 
1166 	/*
1167 	 * Strip flags that either shouldn't be set by userspace like
1168 	 * FMODE_NONOTIFY or that aren't relevant in determining struct
1169 	 * open_flags like O_CLOEXEC.
1170 	 */
1171 	flags &= ~strip;
1172 
1173 	/*
1174 	 * Older syscalls implicitly clear all of the invalid flags or argument
1175 	 * values before calling build_open_flags(), but openat2(2) checks all
1176 	 * of its arguments.
1177 	 */
1178 	if (flags & ~VALID_OPEN_FLAGS)
1179 		return -EINVAL;
1180 	if (how->resolve & ~VALID_RESOLVE_FLAGS)
1181 		return -EINVAL;
1182 
1183 	/* Scoping flags are mutually exclusive. */
1184 	if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT))
1185 		return -EINVAL;
1186 
1187 	/* Deal with the mode. */
1188 	if (WILL_CREATE(flags)) {
1189 		if (how->mode & ~S_IALLUGO)
1190 			return -EINVAL;
1191 		op->mode = how->mode | S_IFREG;
1192 	} else {
1193 		if (how->mode != 0)
1194 			return -EINVAL;
1195 		op->mode = 0;
1196 	}
1197 
1198 	/*
1199 	 * In order to ensure programs get explicit errors when trying to use
1200 	 * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it
1201 	 * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we
1202 	 * have to require userspace to explicitly set it.
1203 	 */
1204 	if (flags & __O_TMPFILE) {
1205 		if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
1206 			return -EINVAL;
1207 		if (!(acc_mode & MAY_WRITE))
1208 			return -EINVAL;
1209 	}
1210 	if (flags & O_PATH) {
1211 		/* O_PATH only permits certain other flags to be set. */
1212 		if (flags & ~O_PATH_FLAGS)
1213 			return -EINVAL;
1214 		acc_mode = 0;
1215 	}
1216 
1217 	/*
1218 	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
1219 	 * check for O_DSYNC if the need any syncing at all we enforce it's
1220 	 * always set instead of having to deal with possibly weird behaviour
1221 	 * for malicious applications setting only __O_SYNC.
1222 	 */
1223 	if (flags & __O_SYNC)
1224 		flags |= O_DSYNC;
1225 
1226 	op->open_flag = flags;
1227 
1228 	/* O_TRUNC implies we need access checks for write permissions */
1229 	if (flags & O_TRUNC)
1230 		acc_mode |= MAY_WRITE;
1231 
1232 	/* Allow the LSM permission hook to distinguish append
1233 	   access from general write access. */
1234 	if (flags & O_APPEND)
1235 		acc_mode |= MAY_APPEND;
1236 
1237 	op->acc_mode = acc_mode;
1238 
1239 	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
1240 
1241 	if (flags & O_CREAT) {
1242 		op->intent |= LOOKUP_CREATE;
1243 		if (flags & O_EXCL) {
1244 			op->intent |= LOOKUP_EXCL;
1245 			flags |= O_NOFOLLOW;
1246 		}
1247 	}
1248 
1249 	if (flags & O_DIRECTORY)
1250 		lookup_flags |= LOOKUP_DIRECTORY;
1251 	if (!(flags & O_NOFOLLOW))
1252 		lookup_flags |= LOOKUP_FOLLOW;
1253 
1254 	if (how->resolve & RESOLVE_NO_XDEV)
1255 		lookup_flags |= LOOKUP_NO_XDEV;
1256 	if (how->resolve & RESOLVE_NO_MAGICLINKS)
1257 		lookup_flags |= LOOKUP_NO_MAGICLINKS;
1258 	if (how->resolve & RESOLVE_NO_SYMLINKS)
1259 		lookup_flags |= LOOKUP_NO_SYMLINKS;
1260 	if (how->resolve & RESOLVE_BENEATH)
1261 		lookup_flags |= LOOKUP_BENEATH;
1262 	if (how->resolve & RESOLVE_IN_ROOT)
1263 		lookup_flags |= LOOKUP_IN_ROOT;
1264 	if (how->resolve & RESOLVE_CACHED) {
1265 		/* Don't bother even trying for create/truncate/tmpfile open */
1266 		if (flags & (O_TRUNC | O_CREAT | O_TMPFILE))
1267 			return -EAGAIN;
1268 		lookup_flags |= LOOKUP_CACHED;
1269 	}
1270 
1271 	op->lookup_flags = lookup_flags;
1272 	return 0;
1273 }
1274 
1275 /**
1276  * file_open_name - open file and return file pointer
1277  *
1278  * @name:	struct filename containing path to open
1279  * @flags:	open flags as per the open(2) second argument
1280  * @mode:	mode for the new file if O_CREAT is set, else ignored
1281  *
1282  * This is the helper to open a file from kernelspace if you really
1283  * have to.  But in generally you should not do this, so please move
1284  * along, nothing to see here..
1285  */
file_open_name(struct filename * name,int flags,umode_t mode)1286 struct file *file_open_name(struct filename *name, int flags, umode_t mode)
1287 {
1288 	struct open_flags op;
1289 	struct open_how how = build_open_how(flags, mode);
1290 	int err = build_open_flags(&how, &op);
1291 	if (err)
1292 		return ERR_PTR(err);
1293 	return do_filp_open(AT_FDCWD, name, &op);
1294 }
1295 
1296 /**
1297  * filp_open - open file and return file pointer
1298  *
1299  * @filename:	path to open
1300  * @flags:	open flags as per the open(2) second argument
1301  * @mode:	mode for the new file if O_CREAT is set, else ignored
1302  *
1303  * This is the helper to open a file from kernelspace if you really
1304  * have to.  But in generally you should not do this, so please move
1305  * along, nothing to see here..
1306  */
filp_open(const char * filename,int flags,umode_t mode)1307 struct file *filp_open(const char *filename, int flags, umode_t mode)
1308 {
1309 	struct filename *name = getname_kernel(filename);
1310 	struct file *file = ERR_CAST(name);
1311 
1312 	if (!IS_ERR(name)) {
1313 		file = file_open_name(name, flags, mode);
1314 		putname(name);
1315 	}
1316 	return file;
1317 }
1318 EXPORT_SYMBOL(filp_open);
1319 
file_open_root(const struct path * root,const char * filename,int flags,umode_t mode)1320 struct file *file_open_root(const struct path *root,
1321 			    const char *filename, int flags, umode_t mode)
1322 {
1323 	struct open_flags op;
1324 	struct open_how how = build_open_how(flags, mode);
1325 	int err = build_open_flags(&how, &op);
1326 	if (err)
1327 		return ERR_PTR(err);
1328 	return do_file_open_root(root, filename, &op);
1329 }
1330 EXPORT_SYMBOL(file_open_root);
1331 
do_sys_openat2(int dfd,const char __user * filename,struct open_how * how)1332 static long do_sys_openat2(int dfd, const char __user *filename,
1333 			   struct open_how *how)
1334 {
1335 	struct open_flags op;
1336 	int fd = build_open_flags(how, &op);
1337 	struct filename *tmp;
1338 
1339 	if (fd)
1340 		return fd;
1341 
1342 	tmp = getname(filename);
1343 	if (IS_ERR(tmp))
1344 		return PTR_ERR(tmp);
1345 
1346 	fd = get_unused_fd_flags(how->flags);
1347 	if (fd >= 0) {
1348 		struct file *f = do_filp_open(dfd, tmp, &op);
1349 		if (IS_ERR(f)) {
1350 			put_unused_fd(fd);
1351 			fd = PTR_ERR(f);
1352 		} else {
1353 			fsnotify_open(f);
1354 			fd_install(fd, f);
1355 		}
1356 	}
1357 	putname(tmp);
1358 	return fd;
1359 }
1360 
do_sys_open(int dfd,const char __user * filename,int flags,umode_t mode)1361 long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
1362 {
1363 	struct open_how how = build_open_how(flags, mode);
1364 	return do_sys_openat2(dfd, filename, &how);
1365 }
1366 
1367 
SYSCALL_DEFINE3(open,const char __user *,filename,int,flags,umode_t,mode)1368 SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
1369 {
1370 	if (force_o_largefile())
1371 		flags |= O_LARGEFILE;
1372 	return do_sys_open(AT_FDCWD, filename, flags, mode);
1373 }
1374 
SYSCALL_DEFINE4(openat,int,dfd,const char __user *,filename,int,flags,umode_t,mode)1375 SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
1376 		umode_t, mode)
1377 {
1378 	if (force_o_largefile())
1379 		flags |= O_LARGEFILE;
1380 	return do_sys_open(dfd, filename, flags, mode);
1381 }
1382 
SYSCALL_DEFINE4(openat2,int,dfd,const char __user *,filename,struct open_how __user *,how,size_t,usize)1383 SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename,
1384 		struct open_how __user *, how, size_t, usize)
1385 {
1386 	int err;
1387 	struct open_how tmp;
1388 
1389 	BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0);
1390 	BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST);
1391 
1392 	if (unlikely(usize < OPEN_HOW_SIZE_VER0))
1393 		return -EINVAL;
1394 
1395 	err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize);
1396 	if (err)
1397 		return err;
1398 
1399 	audit_openat2_how(&tmp);
1400 
1401 	/* O_LARGEFILE is only allowed for non-O_PATH. */
1402 	if (!(tmp.flags & O_PATH) && force_o_largefile())
1403 		tmp.flags |= O_LARGEFILE;
1404 
1405 	return do_sys_openat2(dfd, filename, &tmp);
1406 }
1407 
1408 #ifdef CONFIG_COMPAT
1409 /*
1410  * Exactly like sys_open(), except that it doesn't set the
1411  * O_LARGEFILE flag.
1412  */
COMPAT_SYSCALL_DEFINE3(open,const char __user *,filename,int,flags,umode_t,mode)1413 COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
1414 {
1415 	return do_sys_open(AT_FDCWD, filename, flags, mode);
1416 }
1417 
1418 /*
1419  * Exactly like sys_openat(), except that it doesn't set the
1420  * O_LARGEFILE flag.
1421  */
COMPAT_SYSCALL_DEFINE4(openat,int,dfd,const char __user *,filename,int,flags,umode_t,mode)1422 COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
1423 {
1424 	return do_sys_open(dfd, filename, flags, mode);
1425 }
1426 #endif
1427 
1428 #ifndef __alpha__
1429 
1430 /*
1431  * For backward compatibility?  Maybe this should be moved
1432  * into arch/i386 instead?
1433  */
SYSCALL_DEFINE2(creat,const char __user *,pathname,umode_t,mode)1434 SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
1435 {
1436 	int flags = O_CREAT | O_WRONLY | O_TRUNC;
1437 
1438 	if (force_o_largefile())
1439 		flags |= O_LARGEFILE;
1440 	return do_sys_open(AT_FDCWD, pathname, flags, mode);
1441 }
1442 #endif
1443 
1444 /*
1445  * "id" is the POSIX thread ID. We use the
1446  * files pointer for this..
1447  */
filp_close(struct file * filp,fl_owner_t id)1448 int filp_close(struct file *filp, fl_owner_t id)
1449 {
1450 	int retval = 0;
1451 
1452 	if (CHECK_DATA_CORRUPTION(file_count(filp) == 0,
1453 			"VFS: Close: file count is 0 (f_op=%ps)",
1454 			filp->f_op)) {
1455 		return 0;
1456 	}
1457 
1458 	if (filp->f_op->flush)
1459 		retval = filp->f_op->flush(filp, id);
1460 
1461 	if (likely(!(filp->f_mode & FMODE_PATH))) {
1462 		dnotify_flush(filp, id);
1463 		locks_remove_posix(filp, id);
1464 	}
1465 	fput(filp);
1466 	return retval;
1467 }
1468 
1469 EXPORT_SYMBOL(filp_close);
1470 
1471 /*
1472  * Careful here! We test whether the file pointer is NULL before
1473  * releasing the fd. This ensures that one clone task can't release
1474  * an fd while another clone is opening it.
1475  */
SYSCALL_DEFINE1(close,unsigned int,fd)1476 SYSCALL_DEFINE1(close, unsigned int, fd)
1477 {
1478 	int retval = close_fd(fd);
1479 
1480 	/* can't restart close syscall because file table entry was cleared */
1481 	if (unlikely(retval == -ERESTARTSYS ||
1482 		     retval == -ERESTARTNOINTR ||
1483 		     retval == -ERESTARTNOHAND ||
1484 		     retval == -ERESTART_RESTARTBLOCK))
1485 		retval = -EINTR;
1486 
1487 	return retval;
1488 }
1489 
1490 /**
1491  * close_range() - Close all file descriptors in a given range.
1492  *
1493  * @fd:     starting file descriptor to close
1494  * @max_fd: last file descriptor to close
1495  * @flags:  reserved for future extensions
1496  *
1497  * This closes a range of file descriptors. All file descriptors
1498  * from @fd up to and including @max_fd are closed.
1499  * Currently, errors to close a given file descriptor are ignored.
1500  */
SYSCALL_DEFINE3(close_range,unsigned int,fd,unsigned int,max_fd,unsigned int,flags)1501 SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
1502 		unsigned int, flags)
1503 {
1504 	return __close_range(fd, max_fd, flags);
1505 }
1506 
1507 /*
1508  * This routine simulates a hangup on the tty, to arrange that users
1509  * are given clean terminals at login time.
1510  */
SYSCALL_DEFINE0(vhangup)1511 SYSCALL_DEFINE0(vhangup)
1512 {
1513 	if (capable(CAP_SYS_TTY_CONFIG)) {
1514 		tty_vhangup_self();
1515 		return 0;
1516 	}
1517 	return -EPERM;
1518 }
1519 
1520 /*
1521  * Called when an inode is about to be open.
1522  * We use this to disallow opening large files on 32bit systems if
1523  * the caller didn't specify O_LARGEFILE.  On 64bit systems we force
1524  * on this flag in sys_open.
1525  */
generic_file_open(struct inode * inode,struct file * filp)1526 int generic_file_open(struct inode * inode, struct file * filp)
1527 {
1528 	if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
1529 		return -EOVERFLOW;
1530 	return 0;
1531 }
1532 
1533 EXPORT_SYMBOL(generic_file_open);
1534 
1535 /*
1536  * This is used by subsystems that don't want seekable
1537  * file descriptors. The function is not supposed to ever fail, the only
1538  * reason it returns an 'int' and not 'void' is so that it can be plugged
1539  * directly into file_operations structure.
1540  */
nonseekable_open(struct inode * inode,struct file * filp)1541 int nonseekable_open(struct inode *inode, struct file *filp)
1542 {
1543 	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
1544 	return 0;
1545 }
1546 
1547 EXPORT_SYMBOL(nonseekable_open);
1548 
1549 /*
1550  * stream_open is used by subsystems that want stream-like file descriptors.
1551  * Such file descriptors are not seekable and don't have notion of position
1552  * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL).
1553  * Contrary to file descriptors of other regular files, .read() and .write()
1554  * can run simultaneously.
1555  *
1556  * stream_open never fails and is marked to return int so that it could be
1557  * directly used as file_operations.open .
1558  */
stream_open(struct inode * inode,struct file * filp)1559 int stream_open(struct inode *inode, struct file *filp)
1560 {
1561 	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
1562 	filp->f_mode |= FMODE_STREAM;
1563 	return 0;
1564 }
1565 
1566 EXPORT_SYMBOL(stream_open);
1567