file.c 25.7 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 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 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/crc32.h>
#include <linux/writeback.h>
#include <asm/uaccess.h>
#include <linux/dlm.h>
#include <linux/dlm_plock.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "dir.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"

/**
 * gfs2_llseek - seek to a location in a file
 * @file: the file
 * @offset: the offset
 * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
 *
 * SEEK_END requires the glock for the file because it references the
 * file's size.
 *
 * Returns: The new offset, or errno
 */

static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
{
	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
	struct gfs2_holder i_gh;
	loff_t error;

	switch (origin) {
	case SEEK_END: /* These reference inode->i_size */
	case SEEK_DATA:
	case SEEK_HOLE:
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
					   &i_gh);
		if (!error) {
			error = generic_file_llseek(file, offset, origin);
			gfs2_glock_dq_uninit(&i_gh);
		}
		break;
	case SEEK_CUR:
	case SEEK_SET:
		error = generic_file_llseek(file, offset, origin);
		break;
	default:
		error = -EINVAL;
	}

	return error;
}

/**
 * gfs2_readdir - Read directory entries from a directory
 * @file: The directory to read from
 * @dirent: Buffer for dirents
 * @filldir: Function used to do the copying
 *
 * Returns: errno
 */

static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
{
	struct inode *dir = file->f_mapping->host;
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_holder d_gh;
	u64 offset = file->f_pos;
	int error;

	gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
	error = gfs2_glock_nq(&d_gh);
	if (error) {
		gfs2_holder_uninit(&d_gh);
		return error;
	}

	error = gfs2_dir_read(dir, &offset, dirent, filldir, &file->f_ra);

	gfs2_glock_dq_uninit(&d_gh);

	file->f_pos = offset;

	return error;
}

/**
 * fsflags_cvt
 * @table: A table of 32 u32 flags
 * @val: a 32 bit value to convert
 *
 * This function can be used to convert between fsflags values and
 * GFS2's own flags values.
 *
 * Returns: the converted flags
 */
static u32 fsflags_cvt(const u32 *table, u32 val)
{
	u32 res = 0;
	while(val) {
		if (val & 1)
			res |= *table;
		table++;
		val >>= 1;
	}
	return res;
}

static const u32 fsflags_to_gfs2[32] = {
	[3] = GFS2_DIF_SYNC,
	[4] = GFS2_DIF_IMMUTABLE,
	[5] = GFS2_DIF_APPENDONLY,
	[7] = GFS2_DIF_NOATIME,
	[12] = GFS2_DIF_EXHASH,
	[14] = GFS2_DIF_INHERIT_JDATA,
	[17] = GFS2_DIF_TOPDIR,
};

static const u32 gfs2_to_fsflags[32] = {
	[gfs2fl_Sync] = FS_SYNC_FL,
	[gfs2fl_Immutable] = FS_IMMUTABLE_FL,
	[gfs2fl_AppendOnly] = FS_APPEND_FL,
	[gfs2fl_NoAtime] = FS_NOATIME_FL,
	[gfs2fl_ExHash] = FS_INDEX_FL,
	[gfs2fl_TopLevel] = FS_TOPDIR_FL,
	[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
};

static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int error;
	u32 fsflags;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
	error = gfs2_glock_nq(&gh);
	if (error)
		return error;

	fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_diskflags);
	if (!S_ISDIR(inode->i_mode) && ip->i_diskflags & GFS2_DIF_JDATA)
		fsflags |= FS_JOURNAL_DATA_FL;
	if (put_user(fsflags, ptr))
		error = -EFAULT;

	gfs2_glock_dq(&gh);
	gfs2_holder_uninit(&gh);
	return error;
}

void gfs2_set_inode_flags(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	unsigned int flags = inode->i_flags;

	flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_NOSEC);
	if ((ip->i_eattr == 0) && !is_sxid(inode->i_mode))
		inode->i_flags |= S_NOSEC;
	if (ip->i_diskflags & GFS2_DIF_IMMUTABLE)
		flags |= S_IMMUTABLE;
	if (ip->i_diskflags & GFS2_DIF_APPENDONLY)
		flags |= S_APPEND;
	if (ip->i_diskflags & GFS2_DIF_NOATIME)
		flags |= S_NOATIME;
	if (ip->i_diskflags & GFS2_DIF_SYNC)
		flags |= S_SYNC;
	inode->i_flags = flags;
}

/* Flags that can be set by user space */
#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA|			\
			     GFS2_DIF_IMMUTABLE|		\
			     GFS2_DIF_APPENDONLY|		\
			     GFS2_DIF_NOATIME|			\
			     GFS2_DIF_SYNC|			\
			     GFS2_DIF_SYSTEM|			\
			     GFS2_DIF_TOPDIR|			\
			     GFS2_DIF_INHERIT_JDATA)

/**
 * gfs2_set_flags - set flags on an inode
 * @inode: The inode
 * @flags: The flags to set
 * @mask: Indicates which flags are valid
 *
 */
static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct buffer_head *bh;
	struct gfs2_holder gh;
	int error;
	u32 new_flags, flags;

	error = mnt_want_write_file(filp);
	if (error)
		return error;

	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	if (error)
		goto out_drop_write;

	error = -EACCES;
	if (!inode_owner_or_capable(inode))
		goto out;

	error = 0;
	flags = ip->i_diskflags;
	new_flags = (flags & ~mask) | (reqflags & mask);
	if ((new_flags ^ flags) == 0)
		goto out;

	error = -EINVAL;
	if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
		goto out;

	error = -EPERM;
	if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
		goto out;
	if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
		goto out;
	if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
	    !capable(CAP_LINUX_IMMUTABLE))
		goto out;
	if (!IS_IMMUTABLE(inode)) {
		error = gfs2_permission(inode, MAY_WRITE);
		if (error)
			goto out;
	}
	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
		if (flags & GFS2_DIF_JDATA)
			gfs2_log_flush(sdp, ip->i_gl);
		error = filemap_fdatawrite(inode->i_mapping);
		if (error)
			goto out;
		error = filemap_fdatawait(inode->i_mapping);
		if (error)
			goto out;
	}
	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (error)
		goto out;
	error = gfs2_meta_inode_buffer(ip, &bh);
	if (error)
		goto out_trans_end;
	gfs2_trans_add_bh(ip->i_gl, bh, 1);
	ip->i_diskflags = new_flags;
	gfs2_dinode_out(ip, bh->b_data);
	brelse(bh);
	gfs2_set_inode_flags(inode);
	gfs2_set_aops(inode);
out_trans_end:
	gfs2_trans_end(sdp);
out:
	gfs2_glock_dq_uninit(&gh);
out_drop_write:
	mnt_drop_write_file(filp);
	return error;
}

static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	u32 fsflags, gfsflags;

	if (get_user(fsflags, ptr))
		return -EFAULT;

	gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
	if (!S_ISDIR(inode->i_mode)) {
		gfsflags &= ~GFS2_DIF_TOPDIR;
		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
		return do_gfs2_set_flags(filp, gfsflags, ~0);
	}
	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
}

static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	switch(cmd) {
	case FS_IOC_GETFLAGS:
		return gfs2_get_flags(filp, (u32 __user *)arg);
	case FS_IOC_SETFLAGS:
		return gfs2_set_flags(filp, (u32 __user *)arg);
	case FITRIM:
		return gfs2_fitrim(filp, (void __user *)arg);
	}
	return -ENOTTY;
}

/**
 * gfs2_allocate_page_backing - Use bmap to allocate blocks
 * @page: The (locked) page to allocate backing for
 *
 * We try to allocate all the blocks required for the page in
 * one go. This might fail for various reasons, so we keep
 * trying until all the blocks to back this page are allocated.
 * If some of the blocks are already allocated, thats ok too.
 */

static int gfs2_allocate_page_backing(struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct buffer_head bh;
	unsigned long size = PAGE_CACHE_SIZE;
	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);

	do {
		bh.b_state = 0;
		bh.b_size = size;
		gfs2_block_map(inode, lblock, &bh, 1);
		if (!buffer_mapped(&bh))
			return -EIO;
		size -= bh.b_size;
		lblock += (bh.b_size >> inode->i_blkbits);
	} while(size > 0);
	return 0;
}

/**
 * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
 * @vma: The virtual memory area
 * @page: The page which is about to become writable
 *
 * When the page becomes writable, we need to ensure that we have
 * blocks allocated on disk to back that page.
 */

static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	unsigned long last_index;
	u64 pos = page->index << PAGE_CACHE_SHIFT;
	unsigned int data_blocks, ind_blocks, rblocks;
	struct gfs2_holder gh;
	loff_t size;
	int ret;

	sb_start_pagefault(inode->i_sb);

	/* Update file times before taking page lock */
	file_update_time(vma->vm_file);

	ret = gfs2_rs_alloc(ip);
	if (ret)
		return ret;

	atomic_set(&ip->i_res->rs_sizehint,
		   PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift);

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	ret = gfs2_glock_nq(&gh);
	if (ret)
		goto out;

	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
	set_bit(GIF_SW_PAGED, &ip->i_flags);

	if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
		lock_page(page);
		if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
			ret = -EAGAIN;
			unlock_page(page);
		}
		goto out_unlock;
	}

	ret = gfs2_rindex_update(sdp);
	if (ret)
		goto out_unlock;

	ret = gfs2_quota_lock_check(ip);
	if (ret)
		goto out_unlock;
	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
	ret = gfs2_inplace_reserve(ip, data_blocks + ind_blocks);
	if (ret)
		goto out_quota_unlock;

	rblocks = RES_DINODE + ind_blocks;
	if (gfs2_is_jdata(ip))
		rblocks += data_blocks ? data_blocks : 1;
	if (ind_blocks || data_blocks) {
		rblocks += RES_STATFS + RES_QUOTA;
		rblocks += gfs2_rg_blocks(ip);
	}
	ret = gfs2_trans_begin(sdp, rblocks, 0);
	if (ret)
		goto out_trans_fail;

	lock_page(page);
	ret = -EINVAL;
	size = i_size_read(inode);
	last_index = (size - 1) >> PAGE_CACHE_SHIFT;
	/* Check page index against inode size */
	if (size == 0 || (page->index > last_index))
		goto out_trans_end;

	ret = -EAGAIN;
	/* If truncated, we must retry the operation, we may have raced
	 * with the glock demotion code.
	 */
	if (!PageUptodate(page) || page->mapping != inode->i_mapping)
		goto out_trans_end;

	/* Unstuff, if required, and allocate backing blocks for page */
	ret = 0;
	if (gfs2_is_stuffed(ip))
		ret = gfs2_unstuff_dinode(ip, page);
	if (ret == 0)
		ret = gfs2_allocate_page_backing(page);

out_trans_end:
	if (ret)
		unlock_page(page);
	gfs2_trans_end(sdp);
out_trans_fail:
	gfs2_inplace_release(ip);
out_quota_unlock:
	gfs2_quota_unlock(ip);
out_unlock:
	gfs2_glock_dq(&gh);
out:
	gfs2_holder_uninit(&gh);
	if (ret == 0) {
		set_page_dirty(page);
		wait_on_page_writeback(page);
	}
	sb_end_pagefault(inode->i_sb);
	return block_page_mkwrite_return(ret);
}

static const struct vm_operations_struct gfs2_vm_ops = {
	.fault = filemap_fault,
	.page_mkwrite = gfs2_page_mkwrite,
};

/**
 * gfs2_mmap -
 * @file: The file to map
 * @vma: The VMA which described the mapping
 *
 * There is no need to get a lock here unless we should be updating
 * atime. We ignore any locking errors since the only consequence is
 * a missed atime update (which will just be deferred until later).
 *
 * Returns: 0
 */

static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);

	if (!(file->f_flags & O_NOATIME) &&
	    !IS_NOATIME(&ip->i_inode)) {
		struct gfs2_holder i_gh;
		int error;

		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
		error = gfs2_glock_nq(&i_gh);
		if (error == 0) {
			file_accessed(file);
			gfs2_glock_dq(&i_gh);
		}
		gfs2_holder_uninit(&i_gh);
		if (error)
			return error;
	}
	vma->vm_ops = &gfs2_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;

	return 0;
}

/**
 * gfs2_open - open a file
 * @inode: the inode to open
 * @file: the struct file for this opening
 *
 * Returns: errno
 */

static int gfs2_open(struct inode *inode, struct file *file)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder i_gh;
	struct gfs2_file *fp;
	int error;

	fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
	if (!fp)
		return -ENOMEM;

	mutex_init(&fp->f_fl_mutex);

	gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
	file->private_data = fp;

	if (S_ISREG(ip->i_inode.i_mode)) {
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
					   &i_gh);
		if (error)
			goto fail;

		if (!(file->f_flags & O_LARGEFILE) &&
		    i_size_read(inode) > MAX_NON_LFS) {
			error = -EOVERFLOW;
			goto fail_gunlock;
		}

		gfs2_glock_dq_uninit(&i_gh);
	}

	return 0;

fail_gunlock:
	gfs2_glock_dq_uninit(&i_gh);
fail:
	file->private_data = NULL;
	kfree(fp);
	return error;
}

/**
 * gfs2_release - called to close a struct file
 * @inode: the inode the struct file belongs to
 * @file: the struct file being closed
 *
 * Returns: errno
 */

static int gfs2_release(struct inode *inode, struct file *file)
{
	struct gfs2_inode *ip = GFS2_I(inode);

	kfree(file->private_data);
	file->private_data = NULL;

	if ((file->f_mode & FMODE_WRITE) &&
	    (atomic_read(&inode->i_writecount) == 1))
		gfs2_rs_delete(ip);

	return 0;
}

/**
 * gfs2_fsync - sync the dirty data for a file (across the cluster)
 * @file: the file that points to the dentry
 * @start: the start position in the file to sync
 * @end: the end position in the file to sync
 * @datasync: set if we can ignore timestamp changes
 *
 * We split the data flushing here so that we don't wait for the data
 * until after we've also sent the metadata to disk. Note that for
 * data=ordered, we will write & wait for the data at the log flush
 * stage anyway, so this is unlikely to make much of a difference
 * except in the data=writeback case.
 *
 * If the fdatawrite fails due to any reason except -EIO, we will
 * continue the remainder of the fsync, although we'll still report
 * the error at the end. This is to match filemap_write_and_wait_range()
 * behaviour.
 *
 * Returns: errno
 */

static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync)
{
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
	struct gfs2_inode *ip = GFS2_I(inode);
	int ret = 0, ret1 = 0;

	if (mapping->nrpages) {
		ret1 = filemap_fdatawrite_range(mapping, start, end);
		if (ret1 == -EIO)
			return ret1;
	}

	if (datasync)
		sync_state &= ~I_DIRTY_SYNC;

	if (sync_state) {
		ret = sync_inode_metadata(inode, 1);
		if (ret)
			return ret;
		if (gfs2_is_jdata(ip))
			filemap_write_and_wait(mapping);
		gfs2_ail_flush(ip->i_gl, 1);
	}

	if (mapping->nrpages)
		ret = filemap_fdatawait_range(mapping, start, end);

	return ret ? ret : ret1;
}

/**
 * gfs2_file_aio_write - Perform a write to a file
 * @iocb: The io context
 * @iov: The data to write
 * @nr_segs: Number of @iov segments
 * @pos: The file position
 *
 * We have to do a lock/unlock here to refresh the inode size for
 * O_APPEND writes, otherwise we can land up writing at the wrong
 * offset. There is still a race, but provided the app is using its
 * own file locking, this will make O_APPEND work as expected.
 *
 */

static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
				   unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	size_t writesize = iov_length(iov, nr_segs);
	struct dentry *dentry = file->f_dentry;
	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
	struct gfs2_sbd *sdp;
	int ret;

	sdp = GFS2_SB(file->f_mapping->host);
	ret = gfs2_rs_alloc(ip);
	if (ret)
		return ret;

	atomic_set(&ip->i_res->rs_sizehint, writesize >> sdp->sd_sb.sb_bsize_shift);
	if (file->f_flags & O_APPEND) {
		struct gfs2_holder gh;

		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
		if (ret)
			return ret;
		gfs2_glock_dq_uninit(&gh);
	}

	return generic_file_aio_write(iocb, iov, nr_segs, pos);
}

static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
			   int mode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct buffer_head *dibh;
	int error;
	loff_t size = len;
	unsigned int nr_blks;
	sector_t lblock = offset >> inode->i_blkbits;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (unlikely(error))
		return error;

	gfs2_trans_add_bh(ip->i_gl, dibh, 1);

	if (gfs2_is_stuffed(ip)) {
		error = gfs2_unstuff_dinode(ip, NULL);
		if (unlikely(error))
			goto out;
	}

	while (len) {
		struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
		bh_map.b_size = len;
		set_buffer_zeronew(&bh_map);

		error = gfs2_block_map(inode, lblock, &bh_map, 1);
		if (unlikely(error))
			goto out;
		len -= bh_map.b_size;
		nr_blks = bh_map.b_size >> inode->i_blkbits;
		lblock += nr_blks;
		if (!buffer_new(&bh_map))
			continue;
		if (unlikely(!buffer_zeronew(&bh_map))) {
			error = -EIO;
			goto out;
		}
	}
	if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
		i_size_write(inode, offset + size);

	mark_inode_dirty(inode);

out:
	brelse(dibh);
	return error;
}

static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
			    unsigned int *data_blocks, unsigned int *ind_blocks)
{
	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	unsigned int max_blocks = ip->i_rgd->rd_free_clone;
	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);

	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
		max_data -= tmp;
	}
	/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
	   so it might end up with fewer data blocks */
	if (max_data <= *data_blocks)
		return;
	*data_blocks = max_data;
	*ind_blocks = max_blocks - max_data;
	*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
	if (*len > max) {
		*len = max;
		gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
	}
}

static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
			   loff_t len)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_inode *ip = GFS2_I(inode);
	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
	loff_t bytes, max_bytes;
	int error;
	const loff_t pos = offset;
	const loff_t count = len;
	loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
	loff_t max_chunk_size = UINT_MAX & bsize_mask;
	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;

	/* We only support the FALLOC_FL_KEEP_SIZE mode */
	if (mode & ~FALLOC_FL_KEEP_SIZE)
		return -EOPNOTSUPP;

	offset &= bsize_mask;

	len = next - offset;
	bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
	if (!bytes)
		bytes = UINT_MAX;
	bytes &= bsize_mask;
	if (bytes == 0)
		bytes = sdp->sd_sb.sb_bsize;

	error = gfs2_rs_alloc(ip);
	if (error)
		return error;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
	error = gfs2_glock_nq(&ip->i_gh);
	if (unlikely(error))
		goto out_uninit;

	atomic_set(&ip->i_res->rs_sizehint, len >> sdp->sd_sb.sb_bsize_shift);

	while (len > 0) {
		if (len < bytes)
			bytes = len;
		if (!gfs2_write_alloc_required(ip, offset, bytes)) {
			len -= bytes;
			offset += bytes;
			continue;
		}
		error = gfs2_quota_lock_check(ip);
		if (error)
			goto out_unlock;

retry:
		gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);

		error = gfs2_inplace_reserve(ip, data_blocks + ind_blocks);
		if (error) {
			if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
				bytes >>= 1;
				bytes &= bsize_mask;
				if (bytes == 0)
					bytes = sdp->sd_sb.sb_bsize;
				goto retry;
			}
			goto out_qunlock;
		}
		max_bytes = bytes;
		calc_max_reserv(ip, (len > max_chunk_size)? max_chunk_size: len,
				&max_bytes, &data_blocks, &ind_blocks);

		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
			  RES_RG_HDR + gfs2_rg_blocks(ip);
		if (gfs2_is_jdata(ip))
			rblocks += data_blocks ? data_blocks : 1;

		error = gfs2_trans_begin(sdp, rblocks,
					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
		if (error)
			goto out_trans_fail;

		error = fallocate_chunk(inode, offset, max_bytes, mode);
		gfs2_trans_end(sdp);

		if (error)
			goto out_trans_fail;

		len -= max_bytes;
		offset += max_bytes;
		gfs2_inplace_release(ip);
		gfs2_quota_unlock(ip);
	}

	if (error == 0)
		error = generic_write_sync(file, pos, count);
	goto out_unlock;

out_trans_fail:
	gfs2_inplace_release(ip);
out_qunlock:
	gfs2_quota_unlock(ip);
out_unlock:
	gfs2_glock_dq(&ip->i_gh);
out_uninit:
	gfs2_holder_uninit(&ip->i_gh);
	return error;
}

#ifdef CONFIG_GFS2_FS_LOCKING_DLM

/**
 * gfs2_setlease - acquire/release a file lease
 * @file: the file pointer
 * @arg: lease type
 * @fl: file lock
 *
 * We don't currently have a way to enforce a lease across the whole
 * cluster; until we do, disable leases (by just returning -EINVAL),
 * unless the administrator has requested purely local locking.
 *
 * Locking: called under lock_flocks
 *
 * Returns: errno
 */

static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
{
	return -EINVAL;
}

/**
 * gfs2_lock - acquire/release a posix lock on a file
 * @file: the file pointer
 * @cmd: either modify or retrieve lock state, possibly wait
 * @fl: type and range of lock
 *
 * Returns: errno
 */

static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
{
	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;

	if (!(fl->fl_flags & FL_POSIX))
		return -ENOLCK;
	if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK)
		return -ENOLCK;

	if (cmd == F_CANCELLK) {
		/* Hack: */
		cmd = F_SETLK;
		fl->fl_type = F_UNLCK;
	}
	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		return -EIO;
	if (IS_GETLK(cmd))
		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
	else if (fl->fl_type == F_UNLCK)
		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
	else
		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
}

static int do_flock(struct file *file, int cmd, struct file_lock *fl)
{
	struct gfs2_file *fp = file->private_data;
	struct gfs2_holder *fl_gh = &fp->f_fl_gh;
	struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
	struct gfs2_glock *gl;
	unsigned int state;
	int flags;
	int error = 0;

	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;

	mutex_lock(&fp->f_fl_mutex);

	gl = fl_gh->gh_gl;
	if (gl) {
		if (fl_gh->gh_state == state)
			goto out;
		flock_lock_file_wait(file,
				     &(struct file_lock){.fl_type = F_UNLCK});
		gfs2_glock_dq_wait(fl_gh);
		gfs2_holder_reinit(state, flags, fl_gh);
	} else {
		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
				       &gfs2_flock_glops, CREATE, &gl);
		if (error)
			goto out;
		gfs2_holder_init(gl, state, flags, fl_gh);
		gfs2_glock_put(gl);
	}
	error = gfs2_glock_nq(fl_gh);
	if (error) {
		gfs2_holder_uninit(fl_gh);
		if (error == GLR_TRYFAILED)
			error = -EAGAIN;
	} else {
		error = flock_lock_file_wait(file, fl);
		gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
	}

out:
	mutex_unlock(&fp->f_fl_mutex);
	return error;
}

static void do_unflock(struct file *file, struct file_lock *fl)
{
	struct gfs2_file *fp = file->private_data;
	struct gfs2_holder *fl_gh = &fp->f_fl_gh;

	mutex_lock(&fp->f_fl_mutex);
	flock_lock_file_wait(file, fl);
	if (fl_gh->gh_gl) {
		gfs2_glock_dq_wait(fl_gh);
		gfs2_holder_uninit(fl_gh);
	}
	mutex_unlock(&fp->f_fl_mutex);
}

/**
 * gfs2_flock - acquire/release a flock lock on a file
 * @file: the file pointer
 * @cmd: either modify or retrieve lock state, possibly wait
 * @fl: type and range of lock
 *
 * Returns: errno
 */

static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
{
	if (!(fl->fl_flags & FL_FLOCK))
		return -ENOLCK;
	if (fl->fl_type & LOCK_MAND)
		return -EOPNOTSUPP;

	if (fl->fl_type == F_UNLCK) {
		do_unflock(file, fl);
		return 0;
	} else {
		return do_flock(file, cmd, fl);
	}
}

const struct file_operations gfs2_file_fops = {
	.llseek		= gfs2_llseek,
	.read		= do_sync_read,
	.aio_read	= generic_file_aio_read,
	.write		= do_sync_write,
	.aio_write	= gfs2_file_aio_write,
	.unlocked_ioctl	= gfs2_ioctl,
	.mmap		= gfs2_mmap,
	.open		= gfs2_open,
	.release	= gfs2_release,
	.fsync		= gfs2_fsync,
	.lock		= gfs2_lock,
	.flock		= gfs2_flock,
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
	.setlease	= gfs2_setlease,
	.fallocate	= gfs2_fallocate,
};

const struct file_operations gfs2_dir_fops = {
	.readdir	= gfs2_readdir,
	.unlocked_ioctl	= gfs2_ioctl,
	.open		= gfs2_open,
	.release	= gfs2_release,
	.fsync		= gfs2_fsync,
	.lock		= gfs2_lock,
	.flock		= gfs2_flock,
	.llseek		= default_llseek,
};

#endif /* CONFIG_GFS2_FS_LOCKING_DLM */

const struct file_operations gfs2_file_fops_nolock = {
	.llseek		= gfs2_llseek,
	.read		= do_sync_read,
	.aio_read	= generic_file_aio_read,
	.write		= do_sync_write,
	.aio_write	= gfs2_file_aio_write,
	.unlocked_ioctl	= gfs2_ioctl,
	.mmap		= gfs2_mmap,
	.open		= gfs2_open,
	.release	= gfs2_release,
	.fsync		= gfs2_fsync,
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
	.setlease	= generic_setlease,
	.fallocate	= gfs2_fallocate,
};

const struct file_operations gfs2_dir_fops_nolock = {
	.readdir	= gfs2_readdir,
	.unlocked_ioctl	= gfs2_ioctl,
	.open		= gfs2_open,
	.release	= gfs2_release,
	.fsync		= gfs2_fsync,
	.llseek		= default_llseek,
};