file.c 19.9 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2
/*
3
 *  linux/fs/ext4/file.c
4 5 6 7 8 9 10 11 12 13 14 15
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/file.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
16
 *  ext4 fs regular file handling primitives
17 18 19 20 21 22 23
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	(jj@sunsite.ms.mff.cuni.cz)
 */

#include <linux/time.h>
#include <linux/fs.h>
24
#include <linux/iomap.h>
25 26
#include <linux/mount.h>
#include <linux/path.h>
27
#include <linux/dax.h>
28
#include <linux/quotaops.h>
29
#include <linux/pagevec.h>
30
#include <linux/uio.h>
31
#include <linux/mman.h>
32
#include <linux/backing-dev.h>
33 34
#include "ext4.h"
#include "ext4_jbd2.h"
35 36
#include "xattr.h"
#include "acl.h"
37
#include "truncate.h"
38

39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
static bool ext4_dio_supported(struct inode *inode)
{
	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
		return false;
	if (fsverity_active(inode))
		return false;
	if (ext4_should_journal_data(inode))
		return false;
	if (ext4_has_inline_data(inode))
		return false;
	return true;
}

static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	ssize_t ret;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock_shared(inode))
			return -EAGAIN;
	} else {
		inode_lock_shared(inode);
	}

	if (!ext4_dio_supported(inode)) {
		inode_unlock_shared(inode);
		/*
		 * Fallback to buffered I/O if the operation being performed on
		 * the inode is not supported by direct I/O. The IOCB_DIRECT
		 * flag needs to be cleared here in order to ensure that the
		 * direct I/O path within generic_file_read_iter() is not
		 * taken.
		 */
		iocb->ki_flags &= ~IOCB_DIRECT;
		return generic_file_read_iter(iocb, to);
	}

	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
			   is_sync_kiocb(iocb));
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}

85 86 87 88 89 90
#ifdef CONFIG_FS_DAX
static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

G
Goldwyn Rodrigues 已提交
91 92 93 94 95
	if (!inode_trylock_shared(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock_shared(inode);
	}
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
	/*
	 * Recheck under inode lock - at this point we are sure it cannot
	 * change anymore
	 */
	if (!IS_DAX(inode)) {
		inode_unlock_shared(inode);
		/* Fallback to buffered IO in case we cannot support DAX */
		return generic_file_read_iter(iocb, to);
	}
	ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}
#endif

static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
115 116 117
	struct inode *inode = file_inode(iocb->ki_filp);

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
118 119
		return -EIO;

120 121 122 123
	if (!iov_iter_count(to))
		return 0; /* skip atime */

#ifdef CONFIG_FS_DAX
124
	if (IS_DAX(inode))
125 126
		return ext4_dax_read_iter(iocb, to);
#endif
127 128 129
	if (iocb->ki_flags & IOCB_DIRECT)
		return ext4_dio_read_iter(iocb, to);

130 131 132
	return generic_file_read_iter(iocb, to);
}

133 134
/*
 * Called when an inode is released. Note that this is different
135
 * from ext4_file_open: open gets called at every open, but release
136 137
 * gets called only when /all/ the files are closed.
 */
138
static int ext4_release_file(struct inode *inode, struct file *filp)
139
{
140
	if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
141
		ext4_alloc_da_blocks(inode);
142
		ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
143
	}
144 145
	/* if we are the last writer on the inode, drop the block reservation */
	if ((filp->f_mode & FMODE_WRITE) &&
146 147
			(atomic_read(&inode->i_writecount) == 1) &&
		        !EXT4_I(inode)->i_reserved_data_blocks)
148
	{
149
		down_write(&EXT4_I(inode)->i_data_sem);
150
		ext4_discard_preallocations(inode);
151
		up_write(&EXT4_I(inode)->i_data_sem);
152 153
	}
	if (is_dx(inode) && filp->private_data)
154
		ext4_htree_free_dir_info(filp->private_data);
155 156 157 158

	return 0;
}

159 160 161 162 163 164 165 166 167 168
/*
 * This tests whether the IO in question is block-aligned or not.
 * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
 * are converted to written only after the IO is complete.  Until they are
 * mapped, these blocks appear as holes, so dio_zero_block() will assume that
 * it needs to zero out portions of the start and/or end block.  If 2 AIO
 * threads are at work on the same unwritten block, they must be synchronized
 * or one thread will zero the other's data, causing corruption.
 */
static int
A
Al Viro 已提交
169
ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
170 171 172 173
{
	struct super_block *sb = inode->i_sb;
	int blockmask = sb->s_blocksize - 1;

174
	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
175 176
		return 0;

A
Al Viro 已提交
177
	if ((pos | iov_iter_alignment(from)) & blockmask)
178 179 180 181 182
		return 1;

	return 0;
}

183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
/* Is IO overwriting allocated and initialized blocks? */
static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
	struct ext4_map_blocks map;
	unsigned int blkbits = inode->i_blkbits;
	int err, blklen;

	if (pos + len > i_size_read(inode))
		return false;

	map.m_lblk = pos >> blkbits;
	map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
	blklen = map.m_len;

	err = ext4_map_blocks(NULL, inode, &map, 0);
	/*
	 * 'err==len' means that all of the blocks have been preallocated,
	 * regardless of whether they have been initialized or not. To exclude
	 * unwritten extents, we need to check m_flags.
	 */
	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}

static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

211 212 213
	if (unlikely(IS_IMMUTABLE(inode)))
		return -EPERM;

214 215 216
	ret = generic_write_checks(iocb, from);
	if (ret <= 0)
		return ret;
217

218 219 220 221 222 223 224 225 226 227 228
	/*
	 * If we have encountered a bitmap-format file, the size limit
	 * is smaller than s_maxbytes, which is for extent-mapped files.
	 */
	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
			return -EFBIG;
		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
	}
229 230 231 232 233

	ret = file_modified(iocb->ki_filp);
	if (ret)
		return ret;

234 235 236
	return iov_iter_count(from);
}

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
static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
					struct iov_iter *from)
{
	ssize_t ret;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (iocb->ki_flags & IOCB_NOWAIT)
		return -EOPNOTSUPP;

	inode_lock(inode);
	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	current->backing_dev_info = inode_to_bdi(inode);
	ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos);
	current->backing_dev_info = NULL;

out:
	inode_unlock(inode);
	if (likely(ret > 0)) {
		iocb->ki_pos += ret;
		ret = generic_write_sync(iocb, ret);
	}

	return ret;
}

265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
					   ssize_t written, size_t count)
{
	handle_t *handle;
	bool truncate = false;
	u8 blkbits = inode->i_blkbits;
	ext4_lblk_t written_blk, end_blk;

	/*
	 * Note that EXT4_I(inode)->i_disksize can get extended up to
	 * inode->i_size while the I/O was running due to writeback of delalloc
	 * blocks. But, the code in ext4_iomap_alloc() is careful to use
	 * zeroed/unwritten extents if this is possible; thus we won't leave
	 * uninitialized blocks in a file even if we didn't succeed in writing
	 * as much as we intended.
	 */
	WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
	if (offset + count <= EXT4_I(inode)->i_disksize) {
		/*
		 * We need to ensure that the inode is removed from the orphan
		 * list if it has been added prematurely, due to writeback of
		 * delalloc blocks.
		 */
		if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
			handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);

			if (IS_ERR(handle)) {
				ext4_orphan_del(NULL, inode);
				return PTR_ERR(handle);
			}

			ext4_orphan_del(handle, inode);
			ext4_journal_stop(handle);
		}

		return written;
	}

	if (written < 0)
		goto truncate;

	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
	if (IS_ERR(handle)) {
		written = PTR_ERR(handle);
		goto truncate;
	}

	if (ext4_update_inode_size(inode, offset + written))
		ext4_mark_inode_dirty(handle, inode);

	/*
	 * We may need to truncate allocated but not written blocks beyond EOF.
	 */
	written_blk = ALIGN(offset + written, 1 << blkbits);
	end_blk = ALIGN(offset + count, 1 << blkbits);
	if (written_blk < end_blk && ext4_can_truncate(inode))
		truncate = true;

	/*
	 * Remove the inode from the orphan list if it has been extended and
	 * everything went OK.
	 */
	if (!truncate && inode->i_nlink)
		ext4_orphan_del(handle, inode);
	ext4_journal_stop(handle);

	if (truncate) {
truncate:
		ext4_truncate_failed_write(inode);
		/*
		 * If the truncate operation failed early, then the inode may
		 * still be on the orphan list. In that case, we need to try
		 * remove the inode from the in-memory linked list.
		 */
		if (inode->i_nlink)
			ext4_orphan_del(NULL, inode);
	}

	return written;
}

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
static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
				 int error, unsigned int flags)
{
	loff_t offset = iocb->ki_pos;
	struct inode *inode = file_inode(iocb->ki_filp);

	if (error)
		return error;

	if (size && flags & IOMAP_DIO_UNWRITTEN)
		return ext4_convert_unwritten_extents(NULL, inode,
						      offset, size);

	return 0;
}

static const struct iomap_dio_ops ext4_dio_write_ops = {
	.end_io = ext4_dio_write_end_io,
};

static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	ssize_t ret;
	size_t count;
	loff_t offset;
	handle_t *handle;
	struct inode *inode = file_inode(iocb->ki_filp);
	bool extend = false, overwrite = false, unaligned_aio = false;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		if (!inode_trylock(inode))
			return -EAGAIN;
	} else {
		inode_lock(inode);
	}

	if (!ext4_dio_supported(inode)) {
		inode_unlock(inode);
		/*
		 * Fallback to buffered I/O if the inode does not support
		 * direct I/O.
		 */
		return ext4_buffered_write_iter(iocb, from);
	}

	ret = ext4_write_checks(iocb, from);
	if (ret <= 0) {
		inode_unlock(inode);
		return ret;
	}

	/*
	 * Unaligned asynchronous direct I/O must be serialized among each
	 * other as the zeroing of partial blocks of two competing unaligned
	 * asynchronous direct I/O writes can result in data corruption.
	 */
	offset = iocb->ki_pos;
	count = iov_iter_count(from);
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
	    !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
		unaligned_aio = true;
		inode_dio_wait(inode);
	}

	/*
	 * Determine whether the I/O will overwrite allocated and initialized
	 * blocks. If so, check to see whether it is possible to take the
	 * dioread_nolock path.
	 */
	if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
	    ext4_should_dioread_nolock(inode)) {
		overwrite = true;
		downgrade_write(&inode->i_rwsem);
	}

	if (offset + count > EXT4_I(inode)->i_disksize) {
		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}

		ret = ext4_orphan_add(handle, inode);
		if (ret) {
			ext4_journal_stop(handle);
			goto out;
		}

		extend = true;
		ext4_journal_stop(handle);
	}

	ret = iomap_dio_rw(iocb, from, &ext4_iomap_ops, &ext4_dio_write_ops,
			   is_sync_kiocb(iocb) || unaligned_aio || extend);

	if (extend)
		ret = ext4_handle_inode_extension(inode, offset, ret, count);

out:
	if (overwrite)
		inode_unlock_shared(inode);
	else
		inode_unlock(inode);

	if (ret >= 0 && iov_iter_count(from)) {
		ssize_t err;
		loff_t endbyte;

		offset = iocb->ki_pos;
		err = ext4_buffered_write_iter(iocb, from);
		if (err < 0)
			return err;

		/*
		 * We need to ensure that the pages within the page cache for
		 * the range covered by this I/O are written to disk and
		 * invalidated. This is in attempt to preserve the expected
		 * direct I/O semantics in the case we fallback to buffered I/O
		 * to complete off the I/O request.
		 */
		ret += err;
		endbyte = offset + err - 1;
		err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
						   offset, endbyte);
		if (!err)
			invalidate_mapping_pages(iocb->ki_filp->f_mapping,
						 offset >> PAGE_SHIFT,
						 endbyte >> PAGE_SHIFT);
	}

	return ret;
}

J
Jan Kara 已提交
479 480 481 482 483
#ifdef CONFIG_FS_DAX
static ssize_t
ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	ssize_t ret;
484 485
	size_t count;
	loff_t offset;
486 487
	handle_t *handle;
	bool extend = false;
488
	struct inode *inode = file_inode(iocb->ki_filp);
J
Jan Kara 已提交
489

G
Goldwyn Rodrigues 已提交
490 491 492 493 494
	if (!inode_trylock(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock(inode);
	}
495

J
Jan Kara 已提交
496 497 498 499
	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

500 501
	offset = iocb->ki_pos;
	count = iov_iter_count(from);
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519

	if (offset + count > EXT4_I(inode)->i_disksize) {
		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}

		ret = ext4_orphan_add(handle, inode);
		if (ret) {
			ext4_journal_stop(handle);
			goto out;
		}

		extend = true;
		ext4_journal_stop(handle);
	}

J
Jan Kara 已提交
520
	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
521 522 523

	if (extend)
		ret = ext4_handle_inode_extension(inode, offset, ret, count);
J
Jan Kara 已提交
524
out:
C
Christoph Hellwig 已提交
525
	inode_unlock(inode);
J
Jan Kara 已提交
526 527 528 529 530 531
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}
#endif

532
static ssize_t
A
Al Viro 已提交
533
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
534
{
535
	struct inode *inode = file_inode(iocb->ki_filp);
536

537 538 539
	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

J
Jan Kara 已提交
540 541 542 543
#ifdef CONFIG_FS_DAX
	if (IS_DAX(inode))
		return ext4_dax_write_iter(iocb, from);
#endif
544 545
	if (iocb->ki_flags & IOCB_DIRECT)
		return ext4_dio_write_iter(iocb, from);
J
Jan Kara 已提交
546

547
	return ext4_buffered_write_iter(iocb, from);
548 549
}

R
Ross Zwisler 已提交
550
#ifdef CONFIG_FS_DAX
551
static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
552
		enum page_entry_size pe_size)
R
Ross Zwisler 已提交
553
{
554 555
	int error = 0;
	vm_fault_t result;
556
	int retries = 0;
557
	handle_t *handle = NULL;
558
	struct inode *inode = file_inode(vmf->vma->vm_file);
559
	struct super_block *sb = inode->i_sb;
560 561 562 563 564 565 566 567 568 569 570 571 572 573

	/*
	 * We have to distinguish real writes from writes which will result in a
	 * COW page; COW writes should *not* poke the journal (the file will not
	 * be changed). Doing so would cause unintended failures when mounted
	 * read-only.
	 *
	 * We check for VM_SHARED rather than vmf->cow_page since the latter is
	 * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for
	 * other sizes, dax_iomap_fault will handle splitting / fallback so that
	 * we eventually come back with a COW page.
	 */
	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
		(vmf->vma->vm_flags & VM_SHARED);
574
	pfn_t pfn;
575 576 577

	if (write) {
		sb_start_pagefault(sb);
578
		file_update_time(vmf->vma->vm_file);
579
		down_read(&EXT4_I(inode)->i_mmap_sem);
580
retry:
581 582
		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
					       EXT4_DATA_TRANS_BLOCKS(sb));
583 584 585 586 587
		if (IS_ERR(handle)) {
			up_read(&EXT4_I(inode)->i_mmap_sem);
			sb_end_pagefault(sb);
			return VM_FAULT_SIGBUS;
		}
588 589
	} else {
		down_read(&EXT4_I(inode)->i_mmap_sem);
J
Jan Kara 已提交
590
	}
591
	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
592
	if (write) {
593
		ext4_journal_stop(handle);
594 595 596 597

		if ((result & VM_FAULT_ERROR) && error == -ENOSPC &&
		    ext4_should_retry_alloc(sb, &retries))
			goto retry;
598 599 600
		/* Handling synchronous page fault? */
		if (result & VM_FAULT_NEEDDSYNC)
			result = dax_finish_sync_fault(vmf, pe_size, pfn);
601
		up_read(&EXT4_I(inode)->i_mmap_sem);
602
		sb_end_pagefault(sb);
603 604 605
	} else {
		up_read(&EXT4_I(inode)->i_mmap_sem);
	}
606 607

	return result;
R
Ross Zwisler 已提交
608 609
}

610
static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
611 612 613 614
{
	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}

R
Ross Zwisler 已提交
615 616
static const struct vm_operations_struct ext4_dax_vm_ops = {
	.fault		= ext4_dax_fault,
617
	.huge_fault	= ext4_dax_huge_fault,
618
	.page_mkwrite	= ext4_dax_fault,
619
	.pfn_mkwrite	= ext4_dax_fault,
R
Ross Zwisler 已提交
620 621 622 623 624
};
#else
#define ext4_dax_vm_ops	ext4_file_vm_ops
#endif

625
static const struct vm_operations_struct ext4_file_vm_ops = {
626
	.fault		= ext4_filemap_fault,
627
	.map_pages	= filemap_map_pages,
628 629 630 631 632
	.page_mkwrite   = ext4_page_mkwrite,
};

static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
633
	struct inode *inode = file->f_mapping->host;
634 635
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	struct dax_device *dax_dev = sbi->s_daxdev;
636

637
	if (unlikely(ext4_forced_shutdown(sbi)))
638 639
		return -EIO;

640
	/*
641 642
	 * We don't support synchronous mappings for non-DAX files and
	 * for DAX files if underneath dax_device is not synchronous.
643
	 */
644
	if (!daxdev_mapping_supported(vma, dax_dev))
645 646
		return -EOPNOTSUPP;

647
	file_accessed(file);
R
Ross Zwisler 已提交
648 649
	if (IS_DAX(file_inode(file))) {
		vma->vm_ops = &ext4_dax_vm_ops;
650
		vma->vm_flags |= VM_HUGEPAGE;
R
Ross Zwisler 已提交
651 652 653
	} else {
		vma->vm_ops = &ext4_file_vm_ops;
	}
654 655 656
	return 0;
}

657 658
static int ext4_sample_last_mounted(struct super_block *sb,
				    struct vfsmount *mnt)
659
{
660
	struct ext4_sb_info *sbi = EXT4_SB(sb);
661 662
	struct path path;
	char buf[64], *cp;
663 664 665 666 667 668
	handle_t *handle;
	int err;

	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
		return 0;

669
	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
670 671 672 673 674 675 676 677 678 679 680 681 682
		return 0;

	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
	/*
	 * Sample where the filesystem has been mounted and
	 * store it in the superblock for sysadmin convenience
	 * when trying to sort through large numbers of block
	 * devices or filesystem images.
	 */
	memset(buf, 0, sizeof(buf));
	path.mnt = mnt;
	path.dentry = mnt->mnt_root;
	cp = d_path(&path, buf, sizeof(buf));
683
	err = 0;
684
	if (IS_ERR(cp))
685
		goto out;
686 687

	handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
688
	err = PTR_ERR(handle);
689
	if (IS_ERR(handle))
690
		goto out;
691 692 693
	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
	if (err)
694
		goto out_journal;
695 696 697
	strlcpy(sbi->s_es->s_last_mounted, cp,
		sizeof(sbi->s_es->s_last_mounted));
	ext4_handle_dirty_super(handle, sb);
698
out_journal:
699
	ext4_journal_stop(handle);
700 701
out:
	sb_end_intwrite(sb);
702 703 704 705 706
	return err;
}

static int ext4_file_open(struct inode * inode, struct file * filp)
{
707
	int ret;
708

709 710 711
	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

712 713 714
	ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);
	if (ret)
		return ret;
715

E
Eric Biggers 已提交
716 717
	ret = fscrypt_file_open(inode, filp);
	if (ret)
E
Eric Biggers 已提交
718 719 720 721
		return ret;

	ret = fsverity_file_open(inode, filp);
	if (ret)
E
Eric Biggers 已提交
722 723
		return ret;

724 725 726 727
	/*
	 * Set up the jbd2_inode if we are opening the inode for
	 * writing and the journal is present
	 */
728
	if (filp->f_mode & FMODE_WRITE) {
729
		ret = ext4_inode_attach_jinode(inode);
730 731
		if (ret < 0)
			return ret;
732
	}
G
Goldwyn Rodrigues 已提交
733

734
	filp->f_mode |= FMODE_NOWAIT;
735
	return dquot_file_open(inode, filp);
736 737
}

738
/*
739 740 741
 * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
 * by calling generic_file_llseek_size() with the appropriate maxbytes
 * value for each.
742
 */
743
loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
744 745 746 747 748 749 750 751 752
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes;

	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
	else
		maxbytes = inode->i_sb->s_maxbytes;

753
	switch (whence) {
754
	default:
755
		return generic_file_llseek_size(file, offset, whence,
756 757
						maxbytes, i_size_read(inode));
	case SEEK_HOLE:
758
		inode_lock_shared(inode);
759 760
		offset = iomap_seek_hole(inode, offset,
					 &ext4_iomap_report_ops);
761 762 763 764
		inode_unlock_shared(inode);
		break;
	case SEEK_DATA:
		inode_lock_shared(inode);
765 766
		offset = iomap_seek_data(inode, offset,
					 &ext4_iomap_report_ops);
767 768
		inode_unlock_shared(inode);
		break;
769 770
	}

771 772 773
	if (offset < 0)
		return offset;
	return vfs_setpos(file, offset, maxbytes);
774 775
}

776
const struct file_operations ext4_file_operations = {
777
	.llseek		= ext4_llseek,
778
	.read_iter	= ext4_file_read_iter,
A
Al Viro 已提交
779
	.write_iter	= ext4_file_write_iter,
A
Andi Kleen 已提交
780
	.unlocked_ioctl = ext4_ioctl,
781
#ifdef CONFIG_COMPAT
782
	.compat_ioctl	= ext4_compat_ioctl,
783
#endif
784
	.mmap		= ext4_file_mmap,
785
	.mmap_supported_flags = MAP_SYNC,
786
	.open		= ext4_file_open,
787 788
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
789
	.get_unmapped_area = thp_get_unmapped_area,
790
	.splice_read	= generic_file_splice_read,
A
Al Viro 已提交
791
	.splice_write	= iter_file_splice_write,
792
	.fallocate	= ext4_fallocate,
793 794
};

795
const struct inode_operations ext4_file_inode_operations = {
796
	.setattr	= ext4_setattr,
D
David Howells 已提交
797
	.getattr	= ext4_file_getattr,
798
	.listxattr	= ext4_listxattr,
799
	.get_acl	= ext4_get_acl,
800
	.set_acl	= ext4_set_acl,
801
	.fiemap		= ext4_fiemap,
802 803
};