file.c 19.4 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*
 * fs/kernfs/file.c - kernfs file implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 */
10 11 12 13 14 15 16 17 18 19 20 21

#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/pagemap.h>
#include <linux/sched.h>

#include "kernfs-internal.h"

/*
 * There's one sysfs_open_file for each open file and one sysfs_open_dirent
22
 * for each kernfs_node with one or more open files.
23
 *
24
 * kernfs_node->attr.open points to sysfs_open_dirent.  attr.open is
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
 * protected by sysfs_open_dirent_lock.
 *
 * filp->private_data points to seq_file whose ->private points to
 * sysfs_open_file.  sysfs_open_files are chained at
 * sysfs_open_dirent->files, which is protected by sysfs_open_file_mutex.
 */
static DEFINE_SPINLOCK(sysfs_open_dirent_lock);
static DEFINE_MUTEX(sysfs_open_file_mutex);

struct sysfs_open_dirent {
	atomic_t		refcnt;
	atomic_t		event;
	wait_queue_head_t	poll;
	struct list_head	files; /* goes through sysfs_open_file.list */
};

static struct sysfs_open_file *sysfs_of(struct file *file)
{
	return ((struct seq_file *)file->private_data)->private;
}

/*
47
 * Determine the kernfs_ops for the given kernfs_node.  This function must
48 49
 * be called while holding an active reference.
 */
50
static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
51
{
52
	if (kn->flags & SYSFS_FLAG_LOCKDEP)
53
		lockdep_assert_held(kn);
54
	return kn->attr.ops;
55 56 57 58 59 60 61 62 63 64 65 66
}

static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
{
	struct sysfs_open_file *of = sf->private;
	const struct kernfs_ops *ops;

	/*
	 * @of->mutex nests outside active ref and is just to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
67
	if (!sysfs_get_active(of->kn))
68 69
		return ERR_PTR(-ENODEV);

70
	ops = kernfs_ops(of->kn);
71 72 73 74 75 76 77 78 79 80 81 82 83 84
	if (ops->seq_start) {
		return ops->seq_start(sf, ppos);
	} else {
		/*
		 * The same behavior and code as single_open().  Returns
		 * !NULL if pos is at the beginning; otherwise, NULL.
		 */
		return NULL + !*ppos;
	}
}

static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
{
	struct sysfs_open_file *of = sf->private;
85
	const struct kernfs_ops *ops = kernfs_ops(of->kn);
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101

	if (ops->seq_next) {
		return ops->seq_next(sf, v, ppos);
	} else {
		/*
		 * The same behavior and code as single_open(), always
		 * terminate after the initial read.
		 */
		++*ppos;
		return NULL;
	}
}

static void kernfs_seq_stop(struct seq_file *sf, void *v)
{
	struct sysfs_open_file *of = sf->private;
102
	const struct kernfs_ops *ops = kernfs_ops(of->kn);
103 104 105 106

	if (ops->seq_stop)
		ops->seq_stop(sf, v);

107
	sysfs_put_active(of->kn);
108 109 110 111 112 113 114
	mutex_unlock(&of->mutex);
}

static int kernfs_seq_show(struct seq_file *sf, void *v)
{
	struct sysfs_open_file *of = sf->private;

115
	of->event = atomic_read(&of->kn->attr.open->event);
116

117
	return of->kn->attr.ops->seq_show(sf, v);
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
}

static const struct seq_operations kernfs_seq_ops = {
	.start = kernfs_seq_start,
	.next = kernfs_seq_next,
	.stop = kernfs_seq_stop,
	.show = kernfs_seq_show,
};

/*
 * As reading a bin file can have side-effects, the exact offset and bytes
 * specified in read(2) call should be passed to the read callback making
 * it difficult to use seq_file.  Implement simplistic custom buffering for
 * bin files.
 */
static ssize_t kernfs_file_direct_read(struct sysfs_open_file *of,
				       char __user *user_buf, size_t count,
				       loff_t *ppos)
{
	ssize_t len = min_t(size_t, count, PAGE_SIZE);
	const struct kernfs_ops *ops;
	char *buf;

	buf = kmalloc(len, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	/*
	 * @of->mutex nests outside active ref and is just to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
150
	if (!sysfs_get_active(of->kn)) {
151 152 153 154 155
		len = -ENODEV;
		mutex_unlock(&of->mutex);
		goto out_free;
	}

156
	ops = kernfs_ops(of->kn);
157 158 159 160 161
	if (ops->read)
		len = ops->read(of, buf, len, *ppos);
	else
		len = -EINVAL;

162
	sysfs_put_active(of->kn);
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
	mutex_unlock(&of->mutex);

	if (len < 0)
		goto out_free;

	if (copy_to_user(user_buf, buf, len)) {
		len = -EFAULT;
		goto out_free;
	}

	*ppos += len;

 out_free:
	kfree(buf);
	return len;
}

/**
 * kernfs_file_read - kernfs vfs read callback
 * @file: file pointer
 * @user_buf: data to write
 * @count: number of bytes
 * @ppos: starting offset
 */
static ssize_t kernfs_file_read(struct file *file, char __user *user_buf,
				size_t count, loff_t *ppos)
{
	struct sysfs_open_file *of = sysfs_of(file);

192
	if (of->kn->flags & SYSFS_FLAG_HAS_SEQ_SHOW)
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
		return seq_read(file, user_buf, count, ppos);
	else
		return kernfs_file_direct_read(of, user_buf, count, ppos);
}

/**
 * kernfs_file_write - kernfs vfs write callback
 * @file: file pointer
 * @user_buf: data to write
 * @count: number of bytes
 * @ppos: starting offset
 *
 * Copy data in from userland and pass it to the matching kernfs write
 * operation.
 *
 * There is no easy way for us to know if userspace is only doing a partial
 * write, so we don't support them. We expect the entire buffer to come on
 * the first write.  Hint: if you're writing a value, first read the file,
 * modify only the the value you're changing, then write entire buffer
 * back.
 */
static ssize_t kernfs_file_write(struct file *file, const char __user *user_buf,
				 size_t count, loff_t *ppos)
{
	struct sysfs_open_file *of = sysfs_of(file);
	ssize_t len = min_t(size_t, count, PAGE_SIZE);
	const struct kernfs_ops *ops;
	char *buf;

	buf = kmalloc(len + 1, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	if (copy_from_user(buf, user_buf, len)) {
		len = -EFAULT;
		goto out_free;
	}
	buf[len] = '\0';	/* guarantee string termination */

	/*
	 * @of->mutex nests outside active ref and is just to ensure that
	 * the ops aren't called concurrently for the same open file.
	 */
	mutex_lock(&of->mutex);
237
	if (!sysfs_get_active(of->kn)) {
238 239 240 241 242
		mutex_unlock(&of->mutex);
		len = -ENODEV;
		goto out_free;
	}

243
	ops = kernfs_ops(of->kn);
244 245 246 247 248
	if (ops->write)
		len = ops->write(of, buf, len, *ppos);
	else
		len = -EINVAL;

249
	sysfs_put_active(of->kn);
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266
	mutex_unlock(&of->mutex);

	if (len > 0)
		*ppos += len;
out_free:
	kfree(buf);
	return len;
}

static void kernfs_vma_open(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);

	if (!of->vm_ops)
		return;

267
	if (!sysfs_get_active(of->kn))
268 269 270 271 272
		return;

	if (of->vm_ops->open)
		of->vm_ops->open(vma);

273
	sysfs_put_active(of->kn);
274 275 276 277 278 279 280 281 282 283 284
}

static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

285
	if (!sysfs_get_active(of->kn))
286 287 288 289 290 291
		return VM_FAULT_SIGBUS;

	ret = VM_FAULT_SIGBUS;
	if (of->vm_ops->fault)
		ret = of->vm_ops->fault(vma, vmf);

292
	sysfs_put_active(of->kn);
293 294 295 296 297 298 299 300 301 302 303 304 305
	return ret;
}

static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
				   struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return VM_FAULT_SIGBUS;

306
	if (!sysfs_get_active(of->kn))
307 308 309 310 311 312 313 314
		return VM_FAULT_SIGBUS;

	ret = 0;
	if (of->vm_ops->page_mkwrite)
		ret = of->vm_ops->page_mkwrite(vma, vmf);
	else
		file_update_time(file);

315
	sysfs_put_active(of->kn);
316 317 318 319 320 321 322 323 324 325 326 327 328
	return ret;
}

static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
			     void *buf, int len, int write)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return -EINVAL;

329
	if (!sysfs_get_active(of->kn))
330 331 332 333 334 335
		return -EINVAL;

	ret = -EINVAL;
	if (of->vm_ops->access)
		ret = of->vm_ops->access(vma, addr, buf, len, write);

336
	sysfs_put_active(of->kn);
337 338 339 340 341 342 343 344 345 346 347 348 349 350
	return ret;
}

#ifdef CONFIG_NUMA
static int kernfs_vma_set_policy(struct vm_area_struct *vma,
				 struct mempolicy *new)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return 0;

351
	if (!sysfs_get_active(of->kn))
352 353 354 355 356 357
		return -EINVAL;

	ret = 0;
	if (of->vm_ops->set_policy)
		ret = of->vm_ops->set_policy(vma, new);

358
	sysfs_put_active(of->kn);
359 360 361 362 363 364 365 366 367 368 369 370 371
	return ret;
}

static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
					       unsigned long addr)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	struct mempolicy *pol;

	if (!of->vm_ops)
		return vma->vm_policy;

372
	if (!sysfs_get_active(of->kn))
373 374 375 376 377 378
		return vma->vm_policy;

	pol = vma->vm_policy;
	if (of->vm_ops->get_policy)
		pol = of->vm_ops->get_policy(vma, addr);

379
	sysfs_put_active(of->kn);
380 381 382 383 384 385 386 387 388 389 390 391 392 393
	return pol;
}

static int kernfs_vma_migrate(struct vm_area_struct *vma,
			      const nodemask_t *from, const nodemask_t *to,
			      unsigned long flags)
{
	struct file *file = vma->vm_file;
	struct sysfs_open_file *of = sysfs_of(file);
	int ret;

	if (!of->vm_ops)
		return 0;

394
	if (!sysfs_get_active(of->kn))
395 396 397 398 399 400
		return 0;

	ret = 0;
	if (of->vm_ops->migrate)
		ret = of->vm_ops->migrate(vma, from, to, flags);

401
	sysfs_put_active(of->kn);
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
	return ret;
}
#endif

static const struct vm_operations_struct kernfs_vm_ops = {
	.open		= kernfs_vma_open,
	.fault		= kernfs_vma_fault,
	.page_mkwrite	= kernfs_vma_page_mkwrite,
	.access		= kernfs_vma_access,
#ifdef CONFIG_NUMA
	.set_policy	= kernfs_vma_set_policy,
	.get_policy	= kernfs_vma_get_policy,
	.migrate	= kernfs_vma_migrate,
#endif
};

static int kernfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct sysfs_open_file *of = sysfs_of(file);
	const struct kernfs_ops *ops;
	int rc;

424 425 426 427 428 429 430
	/*
	 * mmap path and of->mutex are prone to triggering spurious lockdep
	 * warnings and we don't want to add spurious locking dependency
	 * between the two.  Check whether mmap is actually implemented
	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
	 * comment in kernfs_file_open() for more details.
	 */
431
	if (!(of->kn->flags & SYSFS_FLAG_HAS_MMAP))
432 433
		return -ENODEV;

434 435 436
	mutex_lock(&of->mutex);

	rc = -ENODEV;
437
	if (!sysfs_get_active(of->kn))
438 439
		goto out_unlock;

440
	ops = kernfs_ops(of->kn);
441
	rc = ops->mmap(of, vma);
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

	/*
	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
	 * to satisfy versions of X which crash if the mmap fails: that
	 * substitutes a new vm_file, and we don't then want bin_vm_ops.
	 */
	if (vma->vm_file != file)
		goto out_put;

	rc = -EINVAL;
	if (of->mmapped && of->vm_ops != vma->vm_ops)
		goto out_put;

	/*
	 * It is not possible to successfully wrap close.
	 * So error if someone is trying to use close.
	 */
	rc = -EINVAL;
	if (vma->vm_ops && vma->vm_ops->close)
		goto out_put;

	rc = 0;
	of->mmapped = 1;
	of->vm_ops = vma->vm_ops;
	vma->vm_ops = &kernfs_vm_ops;
out_put:
468
	sysfs_put_active(of->kn);
469 470 471 472 473 474 475 476
out_unlock:
	mutex_unlock(&of->mutex);

	return rc;
}

/**
 *	sysfs_get_open_dirent - get or create sysfs_open_dirent
477
 *	@kn: target kernfs_node
478 479
 *	@of: sysfs_open_file for this instance of open
 *
480 481
 *	If @kn->attr.open exists, increment its reference count; otherwise,
 *	create one.  @of is chained to the files list.
482 483 484 485 486 487 488
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, -errno on failure.
 */
489
static int sysfs_get_open_dirent(struct kernfs_node *kn,
490 491 492 493 494 495 496 497
				 struct sysfs_open_file *of)
{
	struct sysfs_open_dirent *od, *new_od = NULL;

 retry:
	mutex_lock(&sysfs_open_file_mutex);
	spin_lock_irq(&sysfs_open_dirent_lock);

498 499
	if (!kn->attr.open && new_od) {
		kn->attr.open = new_od;
500 501 502
		new_od = NULL;
	}

503
	od = kn->attr.open;
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
	if (od) {
		atomic_inc(&od->refcnt);
		list_add_tail(&of->list, &od->files);
	}

	spin_unlock_irq(&sysfs_open_dirent_lock);
	mutex_unlock(&sysfs_open_file_mutex);

	if (od) {
		kfree(new_od);
		return 0;
	}

	/* not there, initialize a new one and retry */
	new_od = kmalloc(sizeof(*new_od), GFP_KERNEL);
	if (!new_od)
		return -ENOMEM;

	atomic_set(&new_od->refcnt, 0);
	atomic_set(&new_od->event, 1);
	init_waitqueue_head(&new_od->poll);
	INIT_LIST_HEAD(&new_od->files);
	goto retry;
}

/**
 *	sysfs_put_open_dirent - put sysfs_open_dirent
531
 *	@kn: target kernfs_nodet
532 533
 *	@of: associated sysfs_open_file
 *
534
 *	Put @kn->attr.open and unlink @of from the files list.  If
535 536 537 538 539
 *	reference count reaches zero, disassociate and free it.
 *
 *	LOCKING:
 *	None.
 */
540
static void sysfs_put_open_dirent(struct kernfs_node *kn,
541 542
				  struct sysfs_open_file *of)
{
543
	struct sysfs_open_dirent *od = kn->attr.open;
544 545 546 547 548 549 550 551 552
	unsigned long flags;

	mutex_lock(&sysfs_open_file_mutex);
	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);

	if (of)
		list_del(&of->list);

	if (atomic_dec_and_test(&od->refcnt))
553
		kn->attr.open = NULL;
554 555 556 557 558 559 560 561 562 563 564
	else
		od = NULL;

	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
	mutex_unlock(&sysfs_open_file_mutex);

	kfree(od);
}

static int kernfs_file_open(struct inode *inode, struct file *file)
{
565
	struct kernfs_node *kn = file->f_path.dentry->d_fsdata;
566 567 568 569 570
	const struct kernfs_ops *ops;
	struct sysfs_open_file *of;
	bool has_read, has_write, has_mmap;
	int error = -EACCES;

571
	if (!sysfs_get_active(kn))
572 573
		return -ENODEV;

574
	ops = kernfs_ops(kn);
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

	has_read = ops->seq_show || ops->read || ops->mmap;
	has_write = ops->write || ops->mmap;
	has_mmap = ops->mmap;

	/* check perms and supported operations */
	if ((file->f_mode & FMODE_WRITE) &&
	    (!(inode->i_mode & S_IWUGO) || !has_write))
		goto err_out;

	if ((file->f_mode & FMODE_READ) &&
	    (!(inode->i_mode & S_IRUGO) || !has_read))
		goto err_out;

	/* allocate a sysfs_open_file for the file */
	error = -ENOMEM;
	of = kzalloc(sizeof(struct sysfs_open_file), GFP_KERNEL);
	if (!of)
		goto err_out;

	/*
	 * The following is done to give a different lockdep key to
	 * @of->mutex for files which implement mmap.  This is a rather
	 * crude way to avoid false positive lockdep warning around
	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
	 * open file has a separate mutex, it's okay as long as those don't
	 * happen on the same file.  At this point, we can't easily give
	 * each file a separate locking class.  Let's differentiate on
	 * whether the file has mmap or not for now.
606 607 608
	 *
	 * Both paths of the branch look the same.  They're supposed to
	 * look that way and give @of->mutex different static lockdep keys.
609 610 611 612 613 614
	 */
	if (has_mmap)
		mutex_init(&of->mutex);
	else
		mutex_init(&of->mutex);

615
	of->kn = kn;
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636
	of->file = file;

	/*
	 * Always instantiate seq_file even if read access doesn't use
	 * seq_file or is not requested.  This unifies private data access
	 * and readable regular files are the vast majority anyway.
	 */
	if (ops->seq_show)
		error = seq_open(file, &kernfs_seq_ops);
	else
		error = seq_open(file, NULL);
	if (error)
		goto err_free;

	((struct seq_file *)file->private_data)->private = of;

	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
	if (file->f_mode & FMODE_WRITE)
		file->f_mode |= FMODE_PWRITE;

	/* make sure we have open dirent struct */
637
	error = sysfs_get_open_dirent(kn, of);
638 639 640 641
	if (error)
		goto err_close;

	/* open succeeded, put active references */
642
	sysfs_put_active(kn);
643 644 645 646 647 648 649
	return 0;

err_close:
	seq_release(inode, file);
err_free:
	kfree(of);
err_out:
650
	sysfs_put_active(kn);
651 652 653 654 655
	return error;
}

static int kernfs_file_release(struct inode *inode, struct file *filp)
{
656
	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
657 658
	struct sysfs_open_file *of = sysfs_of(filp);

659
	sysfs_put_open_dirent(kn, of);
660 661 662 663 664 665
	seq_release(inode, filp);
	kfree(of);

	return 0;
}

666
void sysfs_unmap_bin_file(struct kernfs_node *kn)
667 668 669 670
{
	struct sysfs_open_dirent *od;
	struct sysfs_open_file *of;

671
	if (!(kn->flags & SYSFS_FLAG_HAS_MMAP))
672 673 674
		return;

	spin_lock_irq(&sysfs_open_dirent_lock);
675
	od = kn->attr.open;
676 677 678 679 680 681 682 683 684 685 686 687 688
	if (od)
		atomic_inc(&od->refcnt);
	spin_unlock_irq(&sysfs_open_dirent_lock);
	if (!od)
		return;

	mutex_lock(&sysfs_open_file_mutex);
	list_for_each_entry(of, &od->files, list) {
		struct inode *inode = file_inode(of->file);
		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
	}
	mutex_unlock(&sysfs_open_file_mutex);

689
	sysfs_put_open_dirent(kn, NULL);
690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
}

/* Sysfs attribute files are pollable.  The idea is that you read
 * the content and then you use 'poll' or 'select' to wait for
 * the content to change.  When the content changes (assuming the
 * manager for the kobject supports notification), poll will
 * return POLLERR|POLLPRI, and select will return the fd whether
 * it is waiting for read, write, or exceptions.
 * Once poll/select indicates that the value has changed, you
 * need to close and re-open the file, or seek to 0 and read again.
 * Reminder: this only works for attributes which actively support
 * it, and it is not possible to test an attribute from userspace
 * to see if it supports poll (Neither 'poll' nor 'select' return
 * an appropriate error code).  When in doubt, set a suitable timeout value.
 */
static unsigned int kernfs_file_poll(struct file *filp, poll_table *wait)
{
	struct sysfs_open_file *of = sysfs_of(filp);
708
	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
709
	struct sysfs_open_dirent *od = kn->attr.open;
710 711

	/* need parent for the kobj, grab both */
712
	if (!sysfs_get_active(kn))
713 714 715 716
		goto trigger;

	poll_wait(filp, &od->poll, wait);

717
	sysfs_put_active(kn);
718 719 720 721 722 723 724 725 726 727 728 729

	if (of->event != atomic_read(&od->event))
		goto trigger;

	return DEFAULT_POLLMASK;

 trigger:
	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
}

/**
 * kernfs_notify - notify a kernfs file
730
 * @kn: file to notify
731
 *
732
 * Notify @kn such that poll(2) on @kn wakes up.
733
 */
734
void kernfs_notify(struct kernfs_node *kn)
735 736 737 738 739 740
{
	struct sysfs_open_dirent *od;
	unsigned long flags;

	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);

741
	if (!WARN_ON(sysfs_type(kn) != SYSFS_KOBJ_ATTR)) {
742
		od = kn->attr.open;
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775
		if (od) {
			atomic_inc(&od->event);
			wake_up_interruptible(&od->poll);
		}
	}

	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
}
EXPORT_SYMBOL_GPL(kernfs_notify);

const struct file_operations kernfs_file_operations = {
	.read		= kernfs_file_read,
	.write		= kernfs_file_write,
	.llseek		= generic_file_llseek,
	.mmap		= kernfs_file_mmap,
	.open		= kernfs_file_open,
	.release	= kernfs_file_release,
	.poll		= kernfs_file_poll,
};

/**
 * kernfs_create_file_ns_key - create a file
 * @parent: directory to create the file in
 * @name: name of the file
 * @mode: mode of the file
 * @size: size of the file
 * @ops: kernfs operations for the file
 * @priv: private data for the file
 * @ns: optional namespace tag of the file
 * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
 *
 * Returns the created node on success, ERR_PTR() value on error.
 */
776 777 778 779 780 781
struct kernfs_node *kernfs_create_file_ns_key(struct kernfs_node *parent,
					      const char *name,
					      umode_t mode, loff_t size,
					      const struct kernfs_ops *ops,
					      void *priv, const void *ns,
					      struct lock_class_key *key)
782 783
{
	struct sysfs_addrm_cxt acxt;
784
	struct kernfs_node *kn;
785 786
	int rc;

787
	kn = sysfs_new_dirent(kernfs_root(parent), name,
788
			      (mode & S_IALLUGO) | S_IFREG, SYSFS_KOBJ_ATTR);
789
	if (!kn)
790 791
		return ERR_PTR(-ENOMEM);

792 793 794
	kn->attr.ops = ops;
	kn->attr.size = size;
	kn->ns = ns;
795
	kn->priv = priv;
796 797 798

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	if (key) {
799
		lockdep_init_map(&kn->dep_map, "s_active", key, 0);
800
		kn->flags |= SYSFS_FLAG_LOCKDEP;
801 802 803 804
	}
#endif

	/*
805
	 * kn->attr.ops is accesible only while holding active ref.  We
806 807 808 809
	 * need to know whether some ops are implemented outside active
	 * ref.  Cache their existence in flags.
	 */
	if (ops->seq_show)
810
		kn->flags |= SYSFS_FLAG_HAS_SEQ_SHOW;
811
	if (ops->mmap)
812
		kn->flags |= SYSFS_FLAG_HAS_MMAP;
813 814

	sysfs_addrm_start(&acxt);
815
	rc = sysfs_add_one(&acxt, kn, parent);
816 817 818
	sysfs_addrm_finish(&acxt);

	if (rc) {
819
		kernfs_put(kn);
820 821
		return ERR_PTR(rc);
	}
822
	return kn;
823
}