super.c 35.3 KB
Newer Older
1 2 3 4 5 6 7 8 9
// SPDX-License-Identifier: GPL-2.0
/*
 *
 * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
 *
 *
 *                 terminology
 *
 * cluster - allocation unit     - 512,1K,2K,4K,...,2M
10 11 12 13 14 15 16 17 18
 * vcn - virtual cluster number  - Offset inside the file in clusters.
 * vbo - virtual byte offset     - Offset inside the file in bytes.
 * lcn - logical cluster number  - 0 based cluster in clusters heap.
 * lbo - logical byte offset     - Absolute position inside volume.
 * run - maps VCN to LCN         - Stored in attributes in packed form.
 * attr - attribute segment      - std/name/data etc records inside MFT.
 * mi  - MFT inode               - One MFT record(usually 1024 bytes or 4K), consists of attributes.
 * ni  - NTFS inode              - Extends linux inode. consists of one or more mft inodes.
 * index - unit inside directory - 2K, 4K, <=page size, does not depend on cluster size.
19 20 21 22 23 24 25 26 27 28 29
 *
 * WSL - Windows Subsystem for Linux
 * https://docs.microsoft.com/en-us/windows/wsl/file-permissions
 * It stores uid/gid/mode/dev in xattr
 *
 */

#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/fs.h>
30 31
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
32
#include <linux/log2.h>
33 34 35 36 37 38 39 40 41 42 43 44 45 46
#include <linux/module.h>
#include <linux/nls.h>
#include <linux/seq_file.h>
#include <linux/statfs.h>

#include "debug.h"
#include "ntfs.h"
#include "ntfs_fs.h"
#ifdef CONFIG_NTFS3_LZX_XPRESS
#include "lib/lib.h"
#endif

#ifdef CONFIG_PRINTK
/*
47 48
 * ntfs_printk - Trace warnings/notices/errors.
 *
49 50 51 52 53 54 55 56 57
 * Thanks Joe Perches <joe@perches.com> for implementation
 */
void ntfs_printk(const struct super_block *sb, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;
	int level;
	struct ntfs_sb_info *sbi = sb->s_fs_info;

58
	/* Should we use different ratelimits for warnings/notices/errors? */
59 60 61 62 63 64 65 66 67 68 69 70 71 72
	if (!___ratelimit(&sbi->msg_ratelimit, "ntfs3"))
		return;

	va_start(args, fmt);

	level = printk_get_level(fmt);
	vaf.fmt = printk_skip_level(fmt);
	vaf.va = &args;
	printk("%c%cntfs3: %s: %pV\n", KERN_SOH_ASCII, level, sb->s_id, &vaf);

	va_end(args);
}

static char s_name_buf[512];
73
static atomic_t s_name_buf_cnt = ATOMIC_INIT(1); // 1 means 'free s_name_buf'.
74

75 76 77 78 79
/*
 * ntfs_inode_printk
 *
 * Print warnings/notices/errors about inode using name or inode number.
 */
80 81 82 83 84 85 86 87 88 89 90 91
void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
{
	struct super_block *sb = inode->i_sb;
	struct ntfs_sb_info *sbi = sb->s_fs_info;
	char *name;
	va_list args;
	struct va_format vaf;
	int level;

	if (!___ratelimit(&sbi->msg_ratelimit, "ntfs3"))
		return;

92
	/* Use static allocated buffer, if possible. */
93 94 95 96 97 98 99 100 101 102 103 104
	name = atomic_dec_and_test(&s_name_buf_cnt)
		       ? s_name_buf
		       : kmalloc(sizeof(s_name_buf), GFP_NOFS);

	if (name) {
		struct dentry *de = d_find_alias(inode);
		const u32 name_len = ARRAY_SIZE(s_name_buf) - 1;

		if (de) {
			spin_lock(&de->d_lock);
			snprintf(name, name_len, " \"%s\"", de->d_name.name);
			spin_unlock(&de->d_lock);
105
			name[name_len] = 0; /* To be sure. */
106 107 108
		} else {
			name[0] = 0;
		}
109
		dput(de); /* Cocci warns if placed in branch "if (de)" */
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
	}

	va_start(args, fmt);

	level = printk_get_level(fmt);
	vaf.fmt = printk_skip_level(fmt);
	vaf.va = &args;

	printk("%c%cntfs3: %s: ino=%lx,%s %pV\n", KERN_SOH_ASCII, level,
	       sb->s_id, inode->i_ino, name ? name : "", &vaf);

	va_end(args);

	atomic_inc(&s_name_buf_cnt);
	if (name != s_name_buf)
		kfree(name);
}
#endif

/*
 * Shared memory struct.
 *
132 133 134 135 136 137
 * On-disk ntfs's upcase table is created by ntfs formatter.
 * 'upcase' table is 128K bytes of memory.
 * We should read it into memory when mounting.
 * Several ntfs volumes likely use the same 'upcase' table.
 * It is good idea to share in-memory 'upcase' table between different volumes.
 * Unfortunately winxp/vista/win7 use different upcase tables.
138 139 140 141 142 143 144 145 146 147 148 149
 */
static DEFINE_SPINLOCK(s_shared_lock);

static struct {
	void *ptr;
	u32 len;
	int cnt;
} s_shared[8];

/*
 * ntfs_set_shared
 *
150 151 152
 * Return:
 * * @ptr - If pointer was saved in shared memory.
 * * NULL - If pointer was not shared.
153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
 */
void *ntfs_set_shared(void *ptr, u32 bytes)
{
	void *ret = NULL;
	int i, j = -1;

	spin_lock(&s_shared_lock);
	for (i = 0; i < ARRAY_SIZE(s_shared); i++) {
		if (!s_shared[i].cnt) {
			j = i;
		} else if (bytes == s_shared[i].len &&
			   !memcmp(s_shared[i].ptr, ptr, bytes)) {
			s_shared[i].cnt += 1;
			ret = s_shared[i].ptr;
			break;
		}
	}

	if (!ret && j != -1) {
		s_shared[j].ptr = ptr;
		s_shared[j].len = bytes;
		s_shared[j].cnt = 1;
		ret = ptr;
	}
	spin_unlock(&s_shared_lock);

	return ret;
}

/*
 * ntfs_put_shared
 *
185 186 187
 * Return:
 * * @ptr - If pointer is not shared anymore.
 * * NULL - If pointer is still shared.
188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
 */
void *ntfs_put_shared(void *ptr)
{
	void *ret = ptr;
	int i;

	spin_lock(&s_shared_lock);
	for (i = 0; i < ARRAY_SIZE(s_shared); i++) {
		if (s_shared[i].cnt && s_shared[i].ptr == ptr) {
			if (--s_shared[i].cnt)
				ret = NULL;
			break;
		}
	}
	spin_unlock(&s_shared_lock);

	return ret;
}

207
static inline void put_mount_options(struct ntfs_mount_options *options)
208
{
209
	kfree(options->nls_name);
210
	unload_nls(options->nls);
211
	kfree(options);
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
}

enum Opt {
	Opt_uid,
	Opt_gid,
	Opt_umask,
	Opt_dmask,
	Opt_fmask,
	Opt_immutable,
	Opt_discard,
	Opt_force,
	Opt_sparse,
	Opt_nohidden,
	Opt_showmeta,
	Opt_acl,
227
	Opt_iocharset,
228
	Opt_prealloc,
229
	Opt_noacsrules,
230 231 232
	Opt_err,
};

233 234 235 236 237 238 239 240 241 242
static const struct fs_parameter_spec ntfs_fs_parameters[] = {
	fsparam_u32("uid",			Opt_uid),
	fsparam_u32("gid",			Opt_gid),
	fsparam_u32oct("umask",			Opt_umask),
	fsparam_u32oct("dmask",			Opt_dmask),
	fsparam_u32oct("fmask",			Opt_fmask),
	fsparam_flag_no("sys_immutable",	Opt_immutable),
	fsparam_flag_no("discard",		Opt_discard),
	fsparam_flag_no("force",		Opt_force),
	fsparam_flag_no("sparse",		Opt_sparse),
243
	fsparam_flag_no("hidden",		Opt_nohidden),
244 245 246
	fsparam_flag_no("acl",			Opt_acl),
	fsparam_flag_no("showmeta",		Opt_showmeta),
	fsparam_flag_no("prealloc",		Opt_prealloc),
247
	fsparam_flag_no("acsrules",		Opt_noacsrules),
248
	fsparam_string("iocharset",		Opt_iocharset),
249
	{}
250 251
};

252 253 254 255
/*
 * Load nls table or if @nls is utf8 then return NULL.
 */
static struct nls_table *ntfs_load_nls(char *nls)
256
{
257
	struct nls_table *ret;
258

259 260
	if (!nls)
		nls = CONFIG_NLS_DEFAULT;
261

262 263
	if (strcmp(nls, "utf8") == 0)
		return NULL;
264

265 266
	if (strcmp(nls, CONFIG_NLS_DEFAULT) == 0)
		return load_nls_default();
267

268 269 270
	ret = load_nls(nls);
	if (ret)
		return ret;
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
	return ERR_PTR(-EINVAL);
}

static int ntfs_fs_parse_param(struct fs_context *fc,
			       struct fs_parameter *param)
{
	struct ntfs_mount_options *opts = fc->fs_private;
	struct fs_parse_result result;
	int opt;

	opt = fs_parse(fc, ntfs_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_uid:
		opts->fs_uid = make_kuid(current_user_ns(), result.uint_32);
		if (!uid_valid(opts->fs_uid))
			return invalf(fc, "ntfs3: Invalid value for uid.");
		break;
	case Opt_gid:
		opts->fs_gid = make_kgid(current_user_ns(), result.uint_32);
		if (!gid_valid(opts->fs_gid))
			return invalf(fc, "ntfs3: Invalid value for gid.");
		break;
	case Opt_umask:
		if (result.uint_32 & ~07777)
			return invalf(fc, "ntfs3: Invalid value for umask.");
		opts->fs_fmask_inv = ~result.uint_32;
		opts->fs_dmask_inv = ~result.uint_32;
		opts->fmask = 1;
		opts->dmask = 1;
		break;
	case Opt_dmask:
		if (result.uint_32 & ~07777)
			return invalf(fc, "ntfs3: Invalid value for dmask.");
		opts->fs_dmask_inv = ~result.uint_32;
		opts->dmask = 1;
		break;
	case Opt_fmask:
		if (result.uint_32 & ~07777)
			return invalf(fc, "ntfs3: Invalid value for fmask.");
		opts->fs_fmask_inv = ~result.uint_32;
		opts->fmask = 1;
		break;
	case Opt_immutable:
		opts->sys_immutable = result.negated ? 0 : 1;
		break;
	case Opt_discard:
		opts->discard = result.negated ? 0 : 1;
		break;
	case Opt_force:
		opts->force = result.negated ? 0 : 1;
		break;
	case Opt_sparse:
		opts->sparse = result.negated ? 0 : 1;
		break;
	case Opt_nohidden:
330
		opts->nohidden = result.negated ? 1 : 0;
331 332 333
		break;
	case Opt_acl:
		if (!result.negated)
334
#ifdef CONFIG_NTFS3_FS_POSIX_ACL
335
			fc->sb_flags |= SB_POSIXACL;
336
#else
337
			return invalf(fc, "ntfs3: Support for ACL not compiled in!");
338
#endif
339 340 341 342 343 344
		else
			fc->sb_flags &= ~SB_POSIXACL;
		break;
	case Opt_showmeta:
		opts->showmeta = result.negated ? 0 : 1;
		break;
345
	case Opt_iocharset:
346 347 348 349 350 351 352
		kfree(opts->nls_name);
		opts->nls_name = param->string;
		param->string = NULL;
		break;
	case Opt_prealloc:
		opts->prealloc = result.negated ? 0 : 1;
		break;
353 354
	case Opt_noacsrules:
		opts->noacsrules = result.negated ? 1 : 0;
355 356 357 358
		break;
	default:
		/* Should not be here unless we forget add case. */
		return -EINVAL;
359 360 361 362
	}
	return 0;
}

363
static int ntfs_fs_reconfigure(struct fs_context *fc)
364
{
365
	struct super_block *sb = fc->root->d_sb;
366
	struct ntfs_sb_info *sbi = sb->s_fs_info;
367 368
	struct ntfs_mount_options *new_opts = fc->fs_private;
	int ro_rw;
369

370
	ro_rw = sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY);
371
	if (ro_rw && (sbi->flags & NTFS_FLAGS_NEED_REPLAY)) {
372 373 374 375 376 377 378
		errorf(fc, "ntfs3: Couldn't remount rw because journal is not replayed. Please umount/remount instead\n");
		return -EINVAL;
	}

	new_opts->nls = ntfs_load_nls(new_opts->nls_name);
	if (IS_ERR(new_opts->nls)) {
		new_opts->nls = NULL;
379
		errorf(fc, "ntfs3: Cannot load iocharset %s", new_opts->nls_name);
380
		return -EINVAL;
381
	}
382
	if (new_opts->nls != sbi->options->nls)
383
		return invalf(fc, "ntfs3: Cannot use different iocharset when remounting!");
384 385 386 387

	sync_filesystem(sb);

	if (ro_rw && (sbi->volume.flags & VOLUME_FLAG_DIRTY) &&
388 389 390
	    !new_opts->force) {
		errorf(fc, "ntfs3: Volume is dirty and \"force\" flag is not set!");
		return -EINVAL;
391 392
	}

393
	memcpy(sbi->options, new_opts, sizeof(*new_opts));
394

395
	return 0;
396 397 398 399 400 401
}

static struct kmem_cache *ntfs_inode_cachep;

static struct inode *ntfs_alloc_inode(struct super_block *sb)
{
402
	struct ntfs_inode *ni = alloc_inode_sb(sb, ntfs_inode_cachep, GFP_NOFS);
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

	if (!ni)
		return NULL;

	memset(ni, 0, offsetof(struct ntfs_inode, vfs_inode));

	mutex_init(&ni->ni_lock);

	return &ni->vfs_inode;
}

static void ntfs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct ntfs_inode *ni = ntfs_i(inode);

	mutex_destroy(&ni->ni_lock);

	kmem_cache_free(ntfs_inode_cachep, ni);
}

static void ntfs_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, ntfs_i_callback);
}

static void init_once(void *foo)
{
	struct ntfs_inode *ni = foo;

	inode_init_once(&ni->vfs_inode);
}

436 437 438
/*
 * put_ntfs - Noinline to reduce binary size.
 */
439 440
static noinline void put_ntfs(struct ntfs_sb_info *sbi)
{
441 442 443
	kfree(sbi->new_rec);
	kvfree(ntfs_put_shared(sbi->upcase));
	kfree(sbi->def_table);
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

	wnd_close(&sbi->mft.bitmap);
	wnd_close(&sbi->used.bitmap);

	if (sbi->mft.ni)
		iput(&sbi->mft.ni->vfs_inode);

	if (sbi->security.ni)
		iput(&sbi->security.ni->vfs_inode);

	if (sbi->reparse.ni)
		iput(&sbi->reparse.ni->vfs_inode);

	if (sbi->objid.ni)
		iput(&sbi->objid.ni->vfs_inode);

	if (sbi->volume.ni)
		iput(&sbi->volume.ni->vfs_inode);

	ntfs_update_mftmirr(sbi, 0);

	indx_clear(&sbi->security.index_sii);
	indx_clear(&sbi->security.index_sdh);
	indx_clear(&sbi->reparse.index_r);
	indx_clear(&sbi->objid.index_o);
469
	kfree(sbi->compress.lznt);
470 471 472 473
#ifdef CONFIG_NTFS3_LZX_XPRESS
	xpress_free_decompressor(sbi->compress.xpress);
	lzx_free_decompressor(sbi->compress.lzx);
#endif
474
	kfree(sbi);
475 476 477 478 479 480
}

static void ntfs_put_super(struct super_block *sb)
{
	struct ntfs_sb_info *sbi = sb->s_fs_info;

481
	/* Mark rw ntfs as clear, if possible. */
482 483
	ntfs_set_state(sbi, NTFS_DIRTY_CLEAR);

484
	put_mount_options(sbi->options);
485
	put_ntfs(sbi);
486
	sb->s_fs_info = NULL;
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512

	sync_blockdev(sb->s_bdev);
}

static int ntfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct ntfs_sb_info *sbi = sb->s_fs_info;
	struct wnd_bitmap *wnd = &sbi->used.bitmap;

	buf->f_type = sb->s_magic;
	buf->f_bsize = sbi->cluster_size;
	buf->f_blocks = wnd->nbits;

	buf->f_bfree = buf->f_bavail = wnd_zeroes(wnd);
	buf->f_fsid.val[0] = sbi->volume.ser_num;
	buf->f_fsid.val[1] = (sbi->volume.ser_num >> 32);
	buf->f_namelen = NTFS_NAME_LEN;

	return 0;
}

static int ntfs_show_options(struct seq_file *m, struct dentry *root)
{
	struct super_block *sb = root->d_sb;
	struct ntfs_sb_info *sbi = sb->s_fs_info;
513
	struct ntfs_mount_options *opts = sbi->options;
514 515
	struct user_namespace *user_ns = seq_user_ns(m);

516 517 518 519
	seq_printf(m, ",uid=%u",
		  from_kuid_munged(user_ns, opts->fs_uid));
	seq_printf(m, ",gid=%u",
		  from_kgid_munged(user_ns, opts->fs_gid));
520 521 522 523 524
	if (opts->fmask)
		seq_printf(m, ",fmask=%04o", ~opts->fs_fmask_inv);
	if (opts->dmask)
		seq_printf(m, ",dmask=%04o", ~opts->fs_dmask_inv);
	if (opts->nls)
525
		seq_printf(m, ",iocharset=%s", opts->nls->charset);
526
	else
527
		seq_puts(m, ",iocharset=utf8");
528 529 530 531 532 533 534 535 536 537 538 539
	if (opts->sys_immutable)
		seq_puts(m, ",sys_immutable");
	if (opts->discard)
		seq_puts(m, ",discard");
	if (opts->sparse)
		seq_puts(m, ",sparse");
	if (opts->showmeta)
		seq_puts(m, ",showmeta");
	if (opts->nohidden)
		seq_puts(m, ",nohidden");
	if (opts->force)
		seq_puts(m, ",force");
540 541
	if (opts->noacsrules)
		seq_puts(m, ",noacsrules");
542 543 544 545 546 547 548 549
	if (opts->prealloc)
		seq_puts(m, ",prealloc");
	if (sb->s_flags & SB_POSIXACL)
		seq_puts(m, ",acl");

	return 0;
}

550 551 552
/*
 * ntfs_sync_fs - super_operations::sync_fs
 */
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652
static int ntfs_sync_fs(struct super_block *sb, int wait)
{
	int err = 0, err2;
	struct ntfs_sb_info *sbi = sb->s_fs_info;
	struct ntfs_inode *ni;
	struct inode *inode;

	ni = sbi->security.ni;
	if (ni) {
		inode = &ni->vfs_inode;
		err2 = _ni_write_inode(inode, wait);
		if (err2 && !err)
			err = err2;
	}

	ni = sbi->objid.ni;
	if (ni) {
		inode = &ni->vfs_inode;
		err2 = _ni_write_inode(inode, wait);
		if (err2 && !err)
			err = err2;
	}

	ni = sbi->reparse.ni;
	if (ni) {
		inode = &ni->vfs_inode;
		err2 = _ni_write_inode(inode, wait);
		if (err2 && !err)
			err = err2;
	}

	if (!err)
		ntfs_set_state(sbi, NTFS_DIRTY_CLEAR);

	ntfs_update_mftmirr(sbi, wait);

	return err;
}

static const struct super_operations ntfs_sops = {
	.alloc_inode = ntfs_alloc_inode,
	.destroy_inode = ntfs_destroy_inode,
	.evict_inode = ntfs_evict_inode,
	.put_super = ntfs_put_super,
	.statfs = ntfs_statfs,
	.show_options = ntfs_show_options,
	.sync_fs = ntfs_sync_fs,
	.write_inode = ntfs3_write_inode,
};

static struct inode *ntfs_export_get_inode(struct super_block *sb, u64 ino,
					   u32 generation)
{
	struct MFT_REF ref;
	struct inode *inode;

	ref.low = cpu_to_le32(ino);
#ifdef CONFIG_NTFS3_64BIT_CLUSTER
	ref.high = cpu_to_le16(ino >> 32);
#else
	ref.high = 0;
#endif
	ref.seq = cpu_to_le16(generation);

	inode = ntfs_iget5(sb, &ref, NULL);
	if (!IS_ERR(inode) && is_bad_inode(inode)) {
		iput(inode);
		inode = ERR_PTR(-ESTALE);
	}

	return inode;
}

static struct dentry *ntfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
					int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    ntfs_export_get_inode);
}

static struct dentry *ntfs_fh_to_parent(struct super_block *sb, struct fid *fid,
					int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    ntfs_export_get_inode);
}

/* TODO: == ntfs_sync_inode */
static int ntfs_nfs_commit_metadata(struct inode *inode)
{
	return _ni_write_inode(inode, 1);
}

static const struct export_operations ntfs_export_ops = {
	.fh_to_dentry = ntfs_fh_to_dentry,
	.fh_to_parent = ntfs_fh_to_parent,
	.get_parent = ntfs3_get_parent,
	.commit_metadata = ntfs_nfs_commit_metadata,
};

653 654 655
/*
 * format_size_gb - Return Gb,Mb to print with "%u.%02u Gb".
 */
656 657
static u32 format_size_gb(const u64 bytes, u32 *mb)
{
658
	/* Do simple right 30 bit shift of 64 bit value. */
659 660 661 662 663 664 665 666 667 668 669 670
	u64 kbytes = bytes >> 10;
	u32 kbytes32 = kbytes;

	*mb = (100 * (kbytes32 & 0xfffff) + 0x7ffff) >> 20;
	if (*mb >= 100)
		*mb = 99;

	return (kbytes32 >> 20) | (((u32)(kbytes >> 32)) << 12);
}

static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot)
{
671 672 673 674 675
	if (boot->sectors_per_clusters <= 0x80)
		return boot->sectors_per_clusters;
	if (boot->sectors_per_clusters >= 0xf4) /* limit shift to 2MB max */
		return 1U << (0 - boot->sectors_per_clusters);
	return -EINVAL;
676 677
}

678 679 680
/*
 * ntfs_init_from_boot - Init internal info from on-disk boot sector.
 */
681 682 683 684 685 686
static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
			       u64 dev_size)
{
	struct ntfs_sb_info *sbi = sb->s_fs_info;
	int err;
	u32 mb, gb, boot_sector_size, sct_per_clst, record_size;
687
	u64 sectors, clusters, mlcn, mlcn2;
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711
	struct NTFS_BOOT *boot;
	struct buffer_head *bh;
	struct MFT_REC *rec;
	u16 fn, ao;

	sbi->volume.blocks = dev_size >> PAGE_SHIFT;

	bh = ntfs_bread(sb, 0);
	if (!bh)
		return -EIO;

	err = -EINVAL;
	boot = (struct NTFS_BOOT *)bh->b_data;

	if (memcmp(boot->system_id, "NTFS    ", sizeof("NTFS    ") - 1))
		goto out;

	/* 0x55AA is not mandaroty. Thanks Maxim Suhanov*/
	/*if (0x55 != boot->boot_magic[0] || 0xAA != boot->boot_magic[1])
	 *	goto out;
	 */

	boot_sector_size = (u32)boot->bytes_per_sector[1] << 8;
	if (boot->bytes_per_sector[0] || boot_sector_size < SECTOR_SIZE ||
712
	    !is_power_of_2(boot_sector_size)) {
713 714 715 716 717
		goto out;
	}

	/* cluster size: 512, 1K, 2K, 4K, ... 2M */
	sct_per_clst = true_sectors_per_clst(boot);
718 719
	if ((int)sct_per_clst < 0)
		goto out;
720
	if (!is_power_of_2(sct_per_clst))
721 722 723 724 725 726 727 728 729 730 731 732
		goto out;

	mlcn = le64_to_cpu(boot->mft_clst);
	mlcn2 = le64_to_cpu(boot->mft2_clst);
	sectors = le64_to_cpu(boot->sectors_per_volume);

	if (mlcn * sct_per_clst >= sectors)
		goto out;

	if (mlcn2 * sct_per_clst >= sectors)
		goto out;

733
	/* Check MFT record size. */
734 735
	if ((boot->record_size < 0 &&
	     SECTOR_SIZE > (2U << (-boot->record_size))) ||
736
	    (boot->record_size >= 0 && !is_power_of_2(boot->record_size))) {
737 738 739
		goto out;
	}

740
	/* Check index record size. */
741 742
	if ((boot->index_size < 0 &&
	     SECTOR_SIZE > (2U << (-boot->index_size))) ||
743
	    (boot->index_size >= 0 && !is_power_of_2(boot->index_size))) {
744 745 746
		goto out;
	}

747
	sbi->volume.size = sectors * boot_sector_size;
748

749
	gb = format_size_gb(sbi->volume.size + boot_sector_size, &mb);
750 751

	/*
752 753 754
	 * - Volume formatted and mounted with the same sector size.
	 * - Volume formatted 4K and mounted as 512.
	 * - Volume formatted 512 and mounted as 4K.
755
	 */
756 757 758 759 760
	if (boot_sector_size != sector_size) {
		ntfs_warn(
			sb,
			"Different NTFS' sector size (%u) and media sector size (%u)",
			boot_sector_size, sector_size);
761 762 763 764 765 766 767 768 769
		dev_size += sector_size - 1;
	}

	sbi->cluster_size = boot_sector_size * sct_per_clst;
	sbi->cluster_bits = blksize_bits(sbi->cluster_size);

	sbi->mft.lbo = mlcn << sbi->cluster_bits;
	sbi->mft.lbo2 = mlcn2 << sbi->cluster_bits;

770 771
	/* Compare boot's cluster and sector. */
	if (sbi->cluster_size < boot_sector_size)
772 773
		goto out;

774 775 776 777 778 779 780 781 782 783
	/* Compare boot's cluster and media sector. */
	if (sbi->cluster_size < sector_size) {
		/* No way to use ntfs_get_block in this case. */
		ntfs_err(
			sb,
			"Failed to mount 'cause NTFS's cluster size (%u) is less than media sector size (%u)",
			sbi->cluster_size, sector_size);
		goto out;
	}

784 785 786 787 788 789 790 791 792 793 794 795 796 797
	sbi->cluster_mask = sbi->cluster_size - 1;
	sbi->cluster_mask_inv = ~(u64)sbi->cluster_mask;
	sbi->record_size = record_size = boot->record_size < 0
						 ? 1 << (-boot->record_size)
						 : (u32)boot->record_size
							   << sbi->cluster_bits;

	if (record_size > MAXIMUM_BYTES_PER_MFT)
		goto out;

	sbi->record_bits = blksize_bits(record_size);
	sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes

	sbi->max_bytes_per_attr =
798 799 800
		record_size - ALIGN(MFTRECORD_FIXUP_OFFSET_1, 8) -
		ALIGN(((record_size >> SECTOR_SHIFT) * sizeof(short)), 8) -
		ALIGN(sizeof(enum ATTR_TYPE), 8);
801 802 803 804 805 806 807

	sbi->index_size = boot->index_size < 0
				  ? 1u << (-boot->index_size)
				  : (u32)boot->index_size << sbi->cluster_bits;

	sbi->volume.ser_num = le64_to_cpu(boot->serial_num);

808
	/* Warning if RAW volume. */
809
	if (dev_size < sbi->volume.size + boot_sector_size) {
810 811 812 813 814 815 816 817 818 819 820 821
		u32 mb0, gb0;

		gb0 = format_size_gb(dev_size, &mb0);
		ntfs_warn(
			sb,
			"RAW NTFS volume: Filesystem size %u.%02u Gb > volume size %u.%02u Gb. Mount in read-only",
			gb, mb, gb0, mb0);
		sb->s_flags |= SB_RDONLY;
	}

	clusters = sbi->volume.size >> sbi->cluster_bits;
#ifndef CONFIG_NTFS3_64BIT_CLUSTER
822
	/* 32 bits per cluster. */
823 824 825 826 827 828 829 830 831 832 833 834 835
	if (clusters >> 32) {
		ntfs_notice(
			sb,
			"NTFS %u.%02u Gb is too big to use 32 bits per cluster",
			gb, mb);
		goto out;
	}
#elif BITS_PER_LONG < 64
#error "CONFIG_NTFS3_64BIT_CLUSTER incompatible in 32 bit OS"
#endif

	sbi->used.bitmap.nbits = clusters;

836
	rec = kzalloc(record_size, GFP_NOFS);
837 838 839 840 841 842 843 844 845 846
	if (!rec) {
		err = -ENOMEM;
		goto out;
	}

	sbi->new_rec = rec;
	rec->rhdr.sign = NTFS_FILE_SIGNATURE;
	rec->rhdr.fix_off = cpu_to_le16(MFTRECORD_FIXUP_OFFSET_1);
	fn = (sbi->record_size >> SECTOR_SHIFT) + 1;
	rec->rhdr.fix_num = cpu_to_le16(fn);
847
	ao = ALIGN(MFTRECORD_FIXUP_OFFSET_1 + sizeof(short) * fn, 8);
848
	rec->attr_off = cpu_to_le16(ao);
849
	rec->used = cpu_to_le32(ao + ALIGN(sizeof(enum ATTR_TYPE), 8));
850 851 852
	rec->total = cpu_to_le32(sbi->record_size);
	((struct ATTRIB *)Add2Ptr(rec, ao))->type = ATTR_END;

853
	sb_set_blocksize(sb, min_t(u32, sbi->cluster_size, PAGE_SIZE));
854 855 856 857 858

	sbi->block_mask = sb->s_blocksize - 1;
	sbi->blocks_per_cluster = sbi->cluster_size >> sb->s_blocksize_bits;
	sbi->volume.blocks = sbi->volume.size >> sb->s_blocksize_bits;

859
	/* Maximum size for normal files. */
860 861 862 863 864 865
	sbi->maxbytes = (clusters << sbi->cluster_bits) - 1;

#ifdef CONFIG_NTFS3_64BIT_CLUSTER
	if (clusters >= (1ull << (64 - sbi->cluster_bits)))
		sbi->maxbytes = -1;
	sbi->maxbytes_sparse = -1;
866
	sb->s_maxbytes = MAX_LFS_FILESIZE;
867
#else
868
	/* Maximum size for sparse file. */
869
	sbi->maxbytes_sparse = (1ull << (sbi->cluster_bits + 32)) - 1;
870
	sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits;
871 872 873 874 875 876 877 878 879 880
#endif

	err = 0;

out:
	brelse(bh);

	return err;
}

881 882 883
/*
 * ntfs_fill_super - Try to mount.
 */
884
static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
885 886
{
	int err;
887
	struct ntfs_sb_info *sbi = sb->s_fs_info;
888
	struct block_device *bdev = sb->s_bdev;
889
	struct request_queue *rq;
890
	struct inode *inode;
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910
	struct ntfs_inode *ni;
	size_t i, tt;
	CLST vcn, lcn, len;
	struct ATTRIB *attr;
	const struct VOLUME_INFO *info;
	u32 idx, done, bytes;
	struct ATTR_DEF_ENTRY *t;
	u16 *shared;
	struct MFT_REF ref;

	ref.high = 0;

	sbi->sb = sb;
	sb->s_flags |= SB_NODIRATIME;
	sb->s_magic = 0x7366746e; // "ntfs"
	sb->s_op = &ntfs_sops;
	sb->s_export_op = &ntfs_export_ops;
	sb->s_time_gran = NTFS_TIME_GRAN; // 100 nsec
	sb->s_xattr = ntfs_xattr_handlers;

911 912 913 914
	sbi->options->nls = ntfs_load_nls(sbi->options->nls_name);
	if (IS_ERR(sbi->options->nls)) {
		sbi->options->nls = NULL;
		errorf(fc, "Cannot load nls %s", sbi->options->nls_name);
915 916
		err = -EINVAL;
		goto out;
917
	}
918

919 920
	rq = bdev_get_queue(bdev);
	if (blk_queue_discard(rq) && rq->limits.discard_granularity) {
921 922 923 924 925
		sbi->discard_granularity = rq->limits.discard_granularity;
		sbi->discard_granularity_mask_inv =
			~(u64)(sbi->discard_granularity - 1);
	}

926
	/* Parse boot. */
927
	err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512,
928
				  bdev_nr_bytes(bdev));
929
	if (err)
930
		goto out;
931 932

	/*
933 934
	 * Load $Volume. This should be done before $LogFile
	 * 'cause 'sbi->volume.ni' is used 'ntfs_set_state'.
935 936 937 938 939 940
	 */
	ref.low = cpu_to_le32(MFT_REC_VOL);
	ref.seq = cpu_to_le16(MFT_REC_VOL);
	inode = ntfs_iget5(sb, &ref, &NAME_VOLUME);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $Volume.");
941 942
		err = PTR_ERR(inode);
		goto out;
943 944 945 946
	}

	ni = ntfs_i(inode);

947
	/* Load and save label (not necessary). */
948 949 950 951 952
	attr = ni_find_attr(ni, NULL, NULL, ATTR_LABEL, NULL, 0, NULL, NULL);

	if (!attr) {
		/* It is ok if no ATTR_LABEL */
	} else if (!attr->non_res && !is_attr_ext(attr)) {
953
		/* $AttrDef allows labels to be up to 128 symbols. */
954 955 956 957 958 959 960
		err = utf16s_to_utf8s(resident_data(attr),
				      le32_to_cpu(attr->res.data_size) >> 1,
				      UTF16_LITTLE_ENDIAN, sbi->volume.label,
				      sizeof(sbi->volume.label));
		if (err < 0)
			sbi->volume.label[0] = 0;
	} else {
961
		/* Should we break mounting here? */
962
		//err = -EINVAL;
963
		//goto put_inode_out;
964 965 966 967 968
	}

	attr = ni_find_attr(ni, attr, NULL, ATTR_VOL_INFO, NULL, 0, NULL, NULL);
	if (!attr || is_attr_ext(attr)) {
		err = -EINVAL;
969
		goto put_inode_out;
970 971 972 973 974
	}

	info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO);
	if (!info) {
		err = -EINVAL;
975
		goto put_inode_out;
976 977 978 979 980 981 982
	}

	sbi->volume.major_ver = info->major_ver;
	sbi->volume.minor_ver = info->minor_ver;
	sbi->volume.flags = info->flags;
	sbi->volume.ni = ni;

983
	/* Load $MFTMirr to estimate recs_mirr. */
984 985 986 987 988
	ref.low = cpu_to_le32(MFT_REC_MIRR);
	ref.seq = cpu_to_le16(MFT_REC_MIRR);
	inode = ntfs_iget5(sb, &ref, &NAME_MIRROR);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $MFTMirr.");
989 990
		err = PTR_ERR(inode);
		goto out;
991 992 993 994 995 996 997
	}

	sbi->mft.recs_mirr =
		ntfs_up_cluster(sbi, inode->i_size) >> sbi->record_bits;

	iput(inode);

998
	/* Load LogFile to replay. */
999 1000 1001 1002 1003
	ref.low = cpu_to_le32(MFT_REC_LOG);
	ref.seq = cpu_to_le16(MFT_REC_LOG);
	inode = ntfs_iget5(sb, &ref, &NAME_LOGFILE);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load \x24LogFile.");
1004 1005
		err = PTR_ERR(inode);
		goto out;
1006 1007 1008 1009 1010 1011
	}

	ni = ntfs_i(inode);

	err = ntfs_loadlog_and_replay(ni, sbi);
	if (err)
1012
		goto put_inode_out;
1013 1014 1015 1016

	iput(inode);

	if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) {
1017
		if (!sb_rdonly(sb)) {
1018 1019
			ntfs_warn(sb,
				  "failed to replay log file. Can't mount rw!");
1020 1021
			err = -EINVAL;
			goto out;
1022 1023
		}
	} else if (sbi->volume.flags & VOLUME_FLAG_DIRTY) {
1024
		if (!sb_rdonly(sb) && !sbi->options->force) {
1025 1026 1027
			ntfs_warn(
				sb,
				"volume is dirty and \"force\" flag is not set!");
1028 1029
			err = -EINVAL;
			goto out;
1030 1031 1032
		}
	}

1033
	/* Load $MFT. */
1034 1035 1036 1037 1038 1039
	ref.low = cpu_to_le32(MFT_REC_MFT);
	ref.seq = cpu_to_le16(1);

	inode = ntfs_iget5(sb, &ref, &NAME_MFT);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $MFT.");
1040 1041
		err = PTR_ERR(inode);
		goto out;
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	}

	ni = ntfs_i(inode);

	sbi->mft.used = ni->i_valid >> sbi->record_bits;
	tt = inode->i_size >> sbi->record_bits;
	sbi->mft.next_free = MFT_REC_USER;

	err = wnd_init(&sbi->mft.bitmap, sb, tt);
	if (err)
1052
		goto put_inode_out;
1053 1054 1055

	err = ni_load_all_mi(ni);
	if (err)
1056
		goto put_inode_out;
1057 1058 1059

	sbi->mft.ni = ni;

1060
	/* Load $BadClus. */
1061 1062 1063 1064 1065
	ref.low = cpu_to_le32(MFT_REC_BADCLUST);
	ref.seq = cpu_to_le16(MFT_REC_BADCLUST);
	inode = ntfs_iget5(sb, &ref, &NAME_BADCLUS);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $BadClus.");
1066 1067
		err = PTR_ERR(inode);
		goto out;
1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
	}

	ni = ntfs_i(inode);

	for (i = 0; run_get_entry(&ni->file.run, i, &vcn, &lcn, &len); i++) {
		if (lcn == SPARSE_LCN)
			continue;

		if (!sbi->bad_clusters)
			ntfs_notice(sb, "Volume contains bad blocks");

		sbi->bad_clusters += len;
	}

	iput(inode);

1084
	/* Load $Bitmap. */
1085 1086 1087 1088 1089
	ref.low = cpu_to_le32(MFT_REC_BITMAP);
	ref.seq = cpu_to_le16(MFT_REC_BITMAP);
	inode = ntfs_iget5(sb, &ref, &NAME_BITMAP);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $Bitmap.");
1090 1091
		err = PTR_ERR(inode);
		goto out;
1092 1093 1094 1095 1096
	}

#ifndef CONFIG_NTFS3_64BIT_CLUSTER
	if (inode->i_size >> 32) {
		err = -EINVAL;
1097
		goto put_inode_out;
1098 1099 1100
	}
#endif

1101
	/* Check bitmap boundary. */
1102 1103 1104
	tt = sbi->used.bitmap.nbits;
	if (inode->i_size < bitmap_size(tt)) {
		err = -EINVAL;
1105
		goto put_inode_out;
1106 1107
	}

1108
	/* Not necessary. */
1109
	sbi->used.bitmap.set_tail = true;
1110
	err = wnd_init(&sbi->used.bitmap, sb, tt);
1111
	if (err)
1112
		goto put_inode_out;
1113 1114 1115

	iput(inode);

1116
	/* Compute the MFT zone. */
1117 1118
	err = ntfs_refresh_zone(sbi);
	if (err)
1119
		goto out;
1120

1121
	/* Load $AttrDef. */
1122 1123
	ref.low = cpu_to_le32(MFT_REC_ATTR);
	ref.seq = cpu_to_le16(MFT_REC_ATTR);
1124
	inode = ntfs_iget5(sb, &ref, &NAME_ATTRDEF);
1125 1126
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load $AttrDef -> %d", err);
1127 1128
		err = PTR_ERR(inode);
		goto out;
1129 1130 1131 1132
	}

	if (inode->i_size < sizeof(struct ATTR_DEF_ENTRY)) {
		err = -EINVAL;
1133
		goto put_inode_out;
1134 1135
	}
	bytes = inode->i_size;
1136
	sbi->def_table = t = kmalloc(bytes, GFP_NOFS);
1137 1138
	if (!t) {
		err = -ENOMEM;
1139
		goto put_inode_out;
1140 1141 1142 1143 1144 1145 1146 1147
	}

	for (done = idx = 0; done < bytes; done += PAGE_SIZE, idx++) {
		unsigned long tail = bytes - done;
		struct page *page = ntfs_map_page(inode->i_mapping, idx);

		if (IS_ERR(page)) {
			err = PTR_ERR(page);
1148
			goto put_inode_out;
1149 1150 1151 1152 1153 1154 1155
		}
		memcpy(Add2Ptr(t, done), page_address(page),
		       min(PAGE_SIZE, tail));
		ntfs_unmap_page(page);

		if (!idx && ATTR_STD != t->type) {
			err = -EINVAL;
1156
			goto put_inode_out;
1157 1158 1159 1160 1161 1162 1163
		}
	}

	t += 1;
	sbi->def_entries = 1;
	done = sizeof(struct ATTR_DEF_ENTRY);
	sbi->reparse.max_size = MAXIMUM_REPARSE_DATA_BUFFER_SIZE;
1164
	sbi->ea_max_size = 0x10000; /* default formatter value */
1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183

	while (done + sizeof(struct ATTR_DEF_ENTRY) <= bytes) {
		u32 t32 = le32_to_cpu(t->type);
		u64 sz = le64_to_cpu(t->max_sz);

		if ((t32 & 0xF) || le32_to_cpu(t[-1].type) >= t32)
			break;

		if (t->type == ATTR_REPARSE)
			sbi->reparse.max_size = sz;
		else if (t->type == ATTR_EA)
			sbi->ea_max_size = sz;

		done += sizeof(struct ATTR_DEF_ENTRY);
		t += 1;
		sbi->def_entries += 1;
	}
	iput(inode);

1184
	/* Load $UpCase. */
1185 1186 1187 1188
	ref.low = cpu_to_le32(MFT_REC_UPCASE);
	ref.seq = cpu_to_le16(MFT_REC_UPCASE);
	inode = ntfs_iget5(sb, &ref, &NAME_UPCASE);
	if (IS_ERR(inode)) {
1189
		ntfs_err(sb, "Failed to load $UpCase.");
1190 1191
		err = PTR_ERR(inode);
		goto out;
1192 1193 1194 1195
	}

	if (inode->i_size != 0x10000 * sizeof(short)) {
		err = -EINVAL;
1196
		goto put_inode_out;
1197 1198 1199 1200
	}

	for (idx = 0; idx < (0x10000 * sizeof(short) >> PAGE_SHIFT); idx++) {
		const __le16 *src;
1201
		u16 *dst = Add2Ptr(sbi->upcase, idx << PAGE_SHIFT);
1202 1203 1204 1205
		struct page *page = ntfs_map_page(inode->i_mapping, idx);

		if (IS_ERR(page)) {
			err = PTR_ERR(page);
1206
			goto put_inode_out;
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219
		}

		src = page_address(page);

#ifdef __BIG_ENDIAN
		for (i = 0; i < PAGE_SIZE / sizeof(u16); i++)
			*dst++ = le16_to_cpu(*src++);
#else
		memcpy(dst, src, PAGE_SIZE);
#endif
		ntfs_unmap_page(page);
	}

1220 1221 1222
	shared = ntfs_set_shared(sbi->upcase, 0x10000 * sizeof(short));
	if (shared && sbi->upcase != shared) {
		kvfree(sbi->upcase);
1223 1224 1225 1226 1227 1228
		sbi->upcase = shared;
	}

	iput(inode);

	if (is_ntfs3(sbi)) {
1229
		/* Load $Secure. */
1230 1231
		err = ntfs_security_init(sbi);
		if (err)
1232
			goto out;
1233

1234
		/* Load $Extend. */
1235 1236 1237 1238
		err = ntfs_extend_init(sbi);
		if (err)
			goto load_root;

1239
		/* Load $Extend\$Reparse. */
1240 1241 1242 1243
		err = ntfs_reparse_init(sbi);
		if (err)
			goto load_root;

1244
		/* Load $Extend\$ObjId. */
1245 1246 1247 1248 1249 1250
		err = ntfs_objid_init(sbi);
		if (err)
			goto load_root;
	}

load_root:
1251
	/* Load root. */
1252 1253 1254 1255 1256
	ref.low = cpu_to_le32(MFT_REC_ROOT);
	ref.seq = cpu_to_le16(MFT_REC_ROOT);
	inode = ntfs_iget5(sb, &ref, &NAME_ROOT);
	if (IS_ERR(inode)) {
		ntfs_err(sb, "Failed to load root.");
1257 1258
		err = PTR_ERR(inode);
		goto out;
1259 1260 1261
	}

	sb->s_root = d_make_root(inode);
1262 1263 1264 1265
	if (!sb->s_root) {
		err = -ENOMEM;
		goto put_inode_out;
	}
1266

1267 1268
	fc->fs_private = NULL;

1269
	return 0;
1270 1271

put_inode_out:
1272
	iput(inode);
1273 1274 1275 1276 1277 1278 1279 1280
out:
	/*
	 * Free resources here.
	 * ntfs_fs_free will be called with fc->s_fs_info = NULL
	 */
	put_ntfs(sbi);
	sb->s_fs_info = NULL;

1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
	return err;
}

void ntfs_unmap_meta(struct super_block *sb, CLST lcn, CLST len)
{
	struct ntfs_sb_info *sbi = sb->s_fs_info;
	struct block_device *bdev = sb->s_bdev;
	sector_t devblock = (u64)lcn * sbi->blocks_per_cluster;
	unsigned long blocks = (u64)len * sbi->blocks_per_cluster;
	unsigned long cnt = 0;
	unsigned long limit = global_zone_page_state(NR_FREE_PAGES)
			      << (PAGE_SHIFT - sb->s_blocksize_bits);

	if (limit >= 0x2000)
		limit -= 0x1000;
	else if (limit < 32)
		limit = 32;
	else
		limit >>= 1;

	while (blocks--) {
		clean_bdev_aliases(bdev, devblock++, 1);
		if (cnt++ >= limit) {
			sync_blockdev(bdev);
			cnt = 0;
		}
	}
}

/*
1311
 * ntfs_discard - Issue a discard request (trim for SSD).
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324
 */
int ntfs_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len)
{
	int err;
	u64 lbo, bytes, start, end;
	struct super_block *sb;

	if (sbi->used.next_free_lcn == lcn + len)
		sbi->used.next_free_lcn = lcn;

	if (sbi->flags & NTFS_FLAGS_NODISCARD)
		return -EOPNOTSUPP;

1325
	if (!sbi->options->discard)
1326 1327 1328 1329 1330
		return -EOPNOTSUPP;

	lbo = (u64)lcn << sbi->cluster_bits;
	bytes = (u64)len << sbi->cluster_bits;

1331
	/* Align up 'start' on discard_granularity. */
1332 1333
	start = (lbo + sbi->discard_granularity - 1) &
		sbi->discard_granularity_mask_inv;
1334
	/* Align down 'end' on discard_granularity. */
1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
	end = (lbo + bytes) & sbi->discard_granularity_mask_inv;

	sb = sbi->sb;
	if (start >= end)
		return 0;

	err = blkdev_issue_discard(sb->s_bdev, start >> 9, (end - start) >> 9,
				   GFP_NOFS, 0);

	if (err == -EOPNOTSUPP)
		sbi->flags |= NTFS_FLAGS_NODISCARD;

	return err;
}

1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386
static int ntfs_fs_get_tree(struct fs_context *fc)
{
	return get_tree_bdev(fc, ntfs_fill_super);
}

/*
 * ntfs_fs_free - Free fs_context.
 *
 * Note that this will be called after fill_super and reconfigure
 * even when they pass. So they have to take pointers if they pass.
 */
static void ntfs_fs_free(struct fs_context *fc)
{
	struct ntfs_mount_options *opts = fc->fs_private;
	struct ntfs_sb_info *sbi = fc->s_fs_info;

	if (sbi)
		put_ntfs(sbi);

	if (opts)
		put_mount_options(opts);
}

static const struct fs_context_operations ntfs_context_ops = {
	.parse_param	= ntfs_fs_parse_param,
	.get_tree	= ntfs_fs_get_tree,
	.reconfigure	= ntfs_fs_reconfigure,
	.free		= ntfs_fs_free,
};

/*
 * ntfs_init_fs_context - Initialize spi and opts
 *
 * This will called when mount/remount. We will first initiliaze
 * options so that if remount we can use just that.
 */
static int ntfs_init_fs_context(struct fs_context *fc)
1387
{
1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404
	struct ntfs_mount_options *opts;
	struct ntfs_sb_info *sbi;

	opts = kzalloc(sizeof(struct ntfs_mount_options), GFP_NOFS);
	if (!opts)
		return -ENOMEM;

	/* Default options. */
	opts->fs_uid = current_uid();
	opts->fs_gid = current_gid();
	opts->fs_fmask_inv = ~current_umask();
	opts->fs_dmask_inv = ~current_umask();

	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)
		goto ok;

	sbi = kzalloc(sizeof(struct ntfs_sb_info), GFP_NOFS);
1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
	if (!sbi)
		goto free_opts;

	sbi->upcase = kvmalloc(0x10000 * sizeof(short), GFP_KERNEL);
	if (!sbi->upcase)
		goto free_sbi;

	ratelimit_state_init(&sbi->msg_ratelimit, DEFAULT_RATELIMIT_INTERVAL,
			     DEFAULT_RATELIMIT_BURST);

	mutex_init(&sbi->compress.mtx_lznt);
#ifdef CONFIG_NTFS3_LZX_XPRESS
	mutex_init(&sbi->compress.mtx_xpress);
	mutex_init(&sbi->compress.mtx_lzx);
#endif
1420 1421 1422 1423 1424 1425 1426 1427

	sbi->options = opts;
	fc->s_fs_info = sbi;
ok:
	fc->fs_private = opts;
	fc->ops = &ntfs_context_ops;

	return 0;
1428 1429
free_sbi:
	kfree(sbi);
1430 1431
free_opts:
	kfree(opts);
1432
	return -ENOMEM;
1433 1434 1435 1436
}

// clang-format off
static struct file_system_type ntfs_fs_type = {
1437 1438 1439 1440 1441 1442
	.owner			= THIS_MODULE,
	.name			= "ntfs3",
	.init_fs_context	= ntfs_init_fs_context,
	.parameters		= ntfs_fs_parameters,
	.kill_sb		= kill_block_super,
	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
1443 1444 1445 1446 1447 1448 1449
};
// clang-format on

static int __init init_ntfs_fs(void)
{
	int err;

1450
	pr_info("ntfs3: Max link count %u\n", NTFS_LINK_MAX);
1451

1452 1453 1454 1455 1456 1457
	if (IS_ENABLED(CONFIG_NTFS3_FS_POSIX_ACL))
		pr_info("ntfs3: Enabled Linux POSIX ACLs support\n");
	if (IS_ENABLED(CONFIG_NTFS3_64BIT_CLUSTER))
		pr_notice("ntfs3: Warning: Activated 64 bits per cluster. Windows does not support this\n");
	if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS))
		pr_info("ntfs3: Read-only LZX/Xpress compression included\n");
1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500

	err = ntfs3_init_bitmap();
	if (err)
		return err;

	ntfs_inode_cachep = kmem_cache_create(
		"ntfs_inode_cache", sizeof(struct ntfs_inode), 0,
		(SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT),
		init_once);
	if (!ntfs_inode_cachep) {
		err = -ENOMEM;
		goto out1;
	}

	err = register_filesystem(&ntfs_fs_type);
	if (err)
		goto out;

	return 0;
out:
	kmem_cache_destroy(ntfs_inode_cachep);
out1:
	ntfs3_exit_bitmap();
	return err;
}

static void __exit exit_ntfs_fs(void)
{
	if (ntfs_inode_cachep) {
		rcu_barrier();
		kmem_cache_destroy(ntfs_inode_cachep);
	}

	unregister_filesystem(&ntfs_fs_type);
	ntfs3_exit_bitmap();
}

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("ntfs3 read/write filesystem");
#ifdef CONFIG_NTFS3_FS_POSIX_ACL
MODULE_INFO(behaviour, "Enabled Linux POSIX ACLs support");
#endif
#ifdef CONFIG_NTFS3_64BIT_CLUSTER
1501
MODULE_INFO(cluster, "Warning: Activated 64 bits per cluster. Windows does not support this");
1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
#endif
#ifdef CONFIG_NTFS3_LZX_XPRESS
MODULE_INFO(compression, "Read-only lzx/xpress compression included");
#endif

MODULE_AUTHOR("Konstantin Komarov");
MODULE_ALIAS_FS("ntfs3");

module_init(init_ntfs_fs);
module_exit(exit_ntfs_fs);